From 584a0146ec4989f30d0aef46ce1ea6f6ba22a690 Mon Sep 17 00:00:00 2001 From: Philippe Cornu Date: Mon, 9 Apr 2018 17:24:27 +0200 Subject: drm: clarify adjusted_mode documentation for bridges This patch clarifies the adjusted_mode documentation for bridges. Signed-off-by: Philippe Cornu Signed-off-by: Laurent Pinchart Reviewed-by: Archit Taneja Link: https://patchwork.freedesktop.org/patch/msgid/20180409152427.12449-1-philippe.cornu@st.com --- include/drm/drm_bridge.h | 16 ++++++++++++++++ include/drm/drm_crtc.h | 11 +++++++---- 2 files changed, 23 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/drm/drm_bridge.h b/include/drm/drm_bridge.h index 3270fec46979..9917651a7fdd 100644 --- a/include/drm/drm_bridge.h +++ b/include/drm/drm_bridge.h @@ -178,6 +178,22 @@ struct drm_bridge_funcs { * then this would be &drm_encoder_helper_funcs.mode_set. The display * pipe (i.e. clocks and timing signals) is off when this function is * called. + * + * The adjusted_mode parameter is the mode output by the CRTC for the + * first bridge in the chain. It can be different from the mode + * parameter that contains the desired mode for the connector at the end + * of the bridges chain, for instance when the first bridge in the chain + * performs scaling. The adjusted mode is mostly useful for the first + * bridge in the chain and is likely irrelevant for the other bridges. + * + * For atomic drivers the adjusted_mode is the mode stored in + * &drm_crtc_state.adjusted_mode. + * + * NOTE: + * + * If a need arises to store and access modes adjusted for other + * locations than the connection between the CRTC and the first bridge, + * the DRM framework will have to be extended with DRM bridge states. */ void (*mode_set)(struct drm_bridge *bridge, struct drm_display_mode *mode, diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h index a2d81d2907a9..5cf7adeae6a5 100644 --- a/include/drm/drm_crtc.h +++ b/include/drm/drm_crtc.h @@ -134,10 +134,13 @@ struct drm_crtc_state { * * Internal display timings which can be used by the driver to handle * differences between the mode requested by userspace in @mode and what - * is actually programmed into the hardware. It is purely driver - * implementation defined what exactly this adjusted mode means. Usually - * it is used to store the hardware display timings used between the - * CRTC and encoder blocks. + * is actually programmed into the hardware. + * + * For drivers using drm_bridge, this stores hardware display timings + * used between the CRTC and the first bridge. For other drivers, the + * meaning of the adjusted_mode field is purely driver implementation + * defined information, and will usually be used to store the hardware + * display timings used between the CRTC and encoder blocks. */ struct drm_display_mode adjusted_mode; -- cgit v1.2.3 From 5d435b46fa68c53af8dc3a69ff2936b8f17aa294 Mon Sep 17 00:00:00 2001 From: Philippe Cornu Date: Tue, 15 May 2018 22:37:36 +0200 Subject: drm/bridge: spelling and coding style minor fixes Minor fixes detected with "scripts/checkpatch.pl --strict" Signed-off-by: Philippe Cornu Acked-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20180515203736.9224-1-philippe.cornu@st.com --- include/drm/drm_bridge.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/drm/drm_bridge.h b/include/drm/drm_bridge.h index 9917651a7fdd..70131ab57e8f 100644 --- a/include/drm/drm_bridge.h +++ b/include/drm/drm_bridge.h @@ -97,7 +97,7 @@ struct drm_bridge_funcs { /** * @mode_fixup: * - * This callback is used to validate and adjust a mode. The paramater + * This callback is used to validate and adjust a mode. The parameter * mode is the display mode that should be fed to the next element in * the display chain, either the final &drm_connector or the next * &drm_bridge. The parameter adjusted_mode is the input mode the bridge @@ -301,15 +301,15 @@ int drm_bridge_attach(struct drm_encoder *encoder, struct drm_bridge *bridge, struct drm_bridge *previous); bool drm_bridge_mode_fixup(struct drm_bridge *bridge, - const struct drm_display_mode *mode, - struct drm_display_mode *adjusted_mode); + const struct drm_display_mode *mode, + struct drm_display_mode *adjusted_mode); enum drm_mode_status drm_bridge_mode_valid(struct drm_bridge *bridge, const struct drm_display_mode *mode); void drm_bridge_disable(struct drm_bridge *bridge); void drm_bridge_post_disable(struct drm_bridge *bridge); void drm_bridge_mode_set(struct drm_bridge *bridge, - struct drm_display_mode *mode, - struct drm_display_mode *adjusted_mode); + struct drm_display_mode *mode, + struct drm_display_mode *adjusted_mode); void drm_bridge_pre_enable(struct drm_bridge *bridge); void drm_bridge_enable(struct drm_bridge *bridge); -- cgit v1.2.3 From 50525c332b55f899fb231d786931d0b45a3f3d41 Mon Sep 17 00:00:00 2001 From: Stanislav Lisovskiy Date: Tue, 15 May 2018 16:59:27 +0300 Subject: drm: content-type property for HDMI connector MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Added content_type property to drm_connector_state in order to properly handle external HDMI TV content-type setting. v2: * Moved helper function which attaches content type property to the drm core, as was suggested. Removed redundant connector state initialization. v3: * Removed caps in drm_content_type_enum_list. After some discussion it turned out that HDMI Spec 1.4 was wrongly assuming that IT Content(itc) bit doesn't affect Content type states, however itc bit needs to be manupulated as well. In order to not expose additional property for itc, for sake of simplicity it was decided to bind those together in same "content type" property. v4: * Added it_content checking in intel_digital_connector_atomic_check. Fixed documentation for new content type enum. v5: * Moved patch revision's description to commit messages. v6: * Minor naming fix for the content type enumeration string. v7: * Fix parameter name for documentation and parameter alignment in order not to get warning. Added Content Type description to new HDMI connector properties section. v8: * Thrown away unneeded numbers from HDMI content-type property description. Switch to strings desription instead of plain definitions. v9: * Moved away hdmi specific content-type enum from drm_connector_state. Content type property should probably not be bound to any specific connector interface in drm_connector_state. Same probably should be done to hdmi_picture_aspect_ration enum which is also contained in drm_connector_state. Added special helper function to get derive hdmi specific relevant infoframe fields. v10: * Added usage description to HDMI properties kernel doc. v11: * Created centralized function for filling HDMI AVI infoframe, based on correspondent DRM property value. Acked-by: Hans Verkuil Acked-by: Daniel Vetter Signed-off-by: Stanislav Lisovskiy Link: https://patchwork.freedesktop.org/patch/msgid/20180515135928.31092-2-stanislav.lisovskiy@intel.com [vsyrjala: clean up checkpatch multiple blank lines warnings] Signed-off-by: Ville Syrjälä --- Documentation/gpu/drm-kms.rst | 6 ++ Documentation/gpu/kms-properties.csv | 1 + drivers/gpu/drm/drm_atomic.c | 4 ++ drivers/gpu/drm/drm_connector.c | 113 +++++++++++++++++++++++++++++++++++ drivers/gpu/drm/drm_edid.c | 8 +++ include/drm/drm_connector.h | 13 ++++ include/drm/drm_mode_config.h | 5 ++ include/uapi/drm/drm_mode.h | 7 +++ 8 files changed, 157 insertions(+) (limited to 'include') diff --git a/Documentation/gpu/drm-kms.rst b/Documentation/gpu/drm-kms.rst index 1dffd1ac4cd4..e233c2626bd0 100644 --- a/Documentation/gpu/drm-kms.rst +++ b/Documentation/gpu/drm-kms.rst @@ -517,6 +517,12 @@ Standard Connector Properties .. kernel-doc:: drivers/gpu/drm/drm_connector.c :doc: standard connector properties +HDMI Specific Connector Properties +----------------------------- + +.. kernel-doc:: drivers/gpu/drm/drm_connector.c + :doc: HDMI connector properties + Plane Composition Properties ---------------------------- diff --git a/Documentation/gpu/kms-properties.csv b/Documentation/gpu/kms-properties.csv index 07ed22ea3bd6..bfde04eddd14 100644 --- a/Documentation/gpu/kms-properties.csv +++ b/Documentation/gpu/kms-properties.csv @@ -17,6 +17,7 @@ Owner Module/Drivers,Group,Property Name,Type,Property Values,Object attached,De ,Virtual GPU,“suggested X”,RANGE,"Min=0, Max=0xffffffff",Connector,property to suggest an X offset for a connector ,,“suggested Y”,RANGE,"Min=0, Max=0xffffffff",Connector,property to suggest an Y offset for a connector ,Optional,"""aspect ratio""",ENUM,"{ ""None"", ""4:3"", ""16:9"" }",Connector,TDB +,Optional,"""content type""",ENUM,"{ ""No Data"", ""Graphics"", ""Photo"", ""Cinema"", ""Game"" }",Connector,TBD i915,Generic,"""Broadcast RGB""",ENUM,"{ ""Automatic"", ""Full"", ""Limited 16:235"" }",Connector,"When this property is set to Limited 16:235 and CTM is set, the hardware will be programmed with the result of the multiplication of CTM by the limited range matrix to ensure the pixels normaly in the range 0..1.0 are remapped to the range 16/255..235/255." ,,“audio”,ENUM,"{ ""force-dvi"", ""off"", ""auto"", ""on"" }",Connector,TBD ,SDVO-TV,“mode”,ENUM,"{ ""NTSC_M"", ""NTSC_J"", ""NTSC_443"", ""PAL_B"" } etc.",Connector,TBD diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c index dc850b4b6e21..07fef42869aa 100644 --- a/drivers/gpu/drm/drm_atomic.c +++ b/drivers/gpu/drm/drm_atomic.c @@ -1270,6 +1270,8 @@ static int drm_atomic_connector_set_property(struct drm_connector *connector, state->link_status = val; } else if (property == config->aspect_ratio_property) { state->picture_aspect_ratio = val; + } else if (property == config->content_type_property) { + state->content_type = val; } else if (property == connector->scaling_mode_property) { state->scaling_mode = val; } else if (property == connector->content_protection_property) { @@ -1355,6 +1357,8 @@ drm_atomic_connector_get_property(struct drm_connector *connector, *val = state->link_status; } else if (property == config->aspect_ratio_property) { *val = state->picture_aspect_ratio; + } else if (property == config->content_type_property) { + *val = state->content_type; } else if (property == connector->scaling_mode_property) { *val = state->scaling_mode; } else if (property == connector->content_protection_property) { diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c index 9b9ba5d5ec0c..002b244391f9 100644 --- a/drivers/gpu/drm/drm_connector.c +++ b/drivers/gpu/drm/drm_connector.c @@ -720,6 +720,14 @@ static const struct drm_prop_enum_list drm_aspect_ratio_enum_list[] = { { DRM_MODE_PICTURE_ASPECT_16_9, "16:9" }, }; +static const struct drm_prop_enum_list drm_content_type_enum_list[] = { + { DRM_MODE_CONTENT_TYPE_NO_DATA, "No Data" }, + { DRM_MODE_CONTENT_TYPE_GRAPHICS, "Graphics" }, + { DRM_MODE_CONTENT_TYPE_PHOTO, "Photo" }, + { DRM_MODE_CONTENT_TYPE_CINEMA, "Cinema" }, + { DRM_MODE_CONTENT_TYPE_GAME, "Game" }, +}; + static const struct drm_prop_enum_list drm_panel_orientation_enum_list[] = { { DRM_MODE_PANEL_ORIENTATION_NORMAL, "Normal" }, { DRM_MODE_PANEL_ORIENTATION_BOTTOM_UP, "Upside Down" }, @@ -996,6 +1004,84 @@ int drm_mode_create_dvi_i_properties(struct drm_device *dev) } EXPORT_SYMBOL(drm_mode_create_dvi_i_properties); +/** + * DOC: HDMI connector properties + * + * content type (HDMI specific): + * Indicates content type setting to be used in HDMI infoframes to indicate + * content type for the external device, so that it adjusts it's display + * settings accordingly. + * + * The value of this property can be one of the following: + * + * No Data: + * Content type is unknown + * Graphics: + * Content type is graphics + * Photo: + * Content type is photo + * Cinema: + * Content type is cinema + * Game: + * Content type is game + * + * Drivers can set up this property by calling + * drm_connector_attach_content_type_property(). Decoding to + * infoframe values is done through + * drm_hdmi_get_content_type_from_property() and + * drm_hdmi_get_itc_bit_from_property(). + */ + +/** + * drm_connector_attach_content_type_property - attach content-type property + * @connector: connector to attach content type property on. + * + * Called by a driver the first time a HDMI connector is made. + */ +int drm_connector_attach_content_type_property(struct drm_connector *connector) +{ + if (!drm_mode_create_content_type_property(connector->dev)) + drm_object_attach_property(&connector->base, + connector->dev->mode_config.content_type_property, + DRM_MODE_CONTENT_TYPE_NO_DATA); + return 0; +} +EXPORT_SYMBOL(drm_connector_attach_content_type_property); + + +/** + * drm_hdmi_avi_infoframe_content_type() - fill the HDMI AVI infoframe + * content type information, based + * on correspondent DRM property. + * @frame: HDMI AVI infoframe + * @conn_state: DRM display connector state + * + */ +void drm_hdmi_avi_infoframe_content_type(struct hdmi_avi_infoframe *frame, + const struct drm_connector_state *conn_state) +{ + switch (conn_state->content_type) { + case DRM_MODE_CONTENT_TYPE_GRAPHICS: + frame->content_type = HDMI_CONTENT_TYPE_GRAPHICS; + break; + case DRM_MODE_CONTENT_TYPE_CINEMA: + frame->content_type = HDMI_CONTENT_TYPE_CINEMA; + break; + case DRM_MODE_CONTENT_TYPE_GAME: + frame->content_type = HDMI_CONTENT_TYPE_GAME; + break; + case DRM_MODE_CONTENT_TYPE_PHOTO: + frame->content_type = HDMI_CONTENT_TYPE_PHOTO; + break; + default: + /* Graphics is the default(0) */ + frame->content_type = HDMI_CONTENT_TYPE_GRAPHICS; + } + + frame->itc = conn_state->content_type != DRM_MODE_CONTENT_TYPE_NO_DATA; +} +EXPORT_SYMBOL(drm_hdmi_avi_infoframe_content_type); + /** * drm_create_tv_properties - create TV specific connector properties * @dev: DRM device @@ -1260,6 +1346,33 @@ int drm_mode_create_aspect_ratio_property(struct drm_device *dev) } EXPORT_SYMBOL(drm_mode_create_aspect_ratio_property); +/** + * drm_mode_create_content_type_property - create content type property + * @dev: DRM device + * + * Called by a driver the first time it's needed, must be attached to desired + * connectors. + * + * Returns: + * Zero on success, negative errno on failure. + */ +int drm_mode_create_content_type_property(struct drm_device *dev) +{ + if (dev->mode_config.content_type_property) + return 0; + + dev->mode_config.content_type_property = + drm_property_create_enum(dev, 0, "content type", + drm_content_type_enum_list, + ARRAY_SIZE(drm_content_type_enum_list)); + + if (dev->mode_config.content_type_property == NULL) + return -ENOMEM; + + return 0; +} +EXPORT_SYMBOL(drm_mode_create_content_type_property); + /** * drm_mode_create_suggested_offset_properties - create suggests offset properties * @dev: DRM device diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index 40e1e24f2ff0..82f1ab09169d 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -4872,6 +4872,14 @@ drm_hdmi_avi_infoframe_from_display_mode(struct hdmi_avi_infoframe *frame, frame->picture_aspect = HDMI_PICTURE_ASPECT_NONE; + /* + * As some drivers don't support atomic, we can't use connector state. + * So just initialize the frame with default values, just the same way + * as it's done with other properties here. + */ + frame->content_type = HDMI_CONTENT_TYPE_GRAPHICS; + frame->itc = 0; + /* * Populate picture aspect ratio from either * user input (if specified) or from the CEA mode list. diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h index 675cc3f8cf85..ee4c48218c85 100644 --- a/include/drm/drm_connector.h +++ b/include/drm/drm_connector.h @@ -418,6 +418,14 @@ struct drm_connector_state { */ enum hdmi_picture_aspect picture_aspect_ratio; + /** + * @content_type: Connector property to control the + * HDMI infoframe content type setting. + * The %DRM_MODE_CONTENT_TYPE_\* values much + * match the values. + */ + unsigned int content_type; + /** * @scaling_mode: Connector property to control the * upscaling, mostly used for built-in panels. @@ -1089,11 +1097,16 @@ int drm_mode_create_tv_properties(struct drm_device *dev, unsigned int num_modes, const char * const modes[]); int drm_mode_create_scaling_mode_property(struct drm_device *dev); +int drm_connector_attach_content_type_property(struct drm_connector *dev); int drm_connector_attach_scaling_mode_property(struct drm_connector *connector, u32 scaling_mode_mask); int drm_connector_attach_content_protection_property( struct drm_connector *connector); int drm_mode_create_aspect_ratio_property(struct drm_device *dev); +int drm_mode_create_content_type_property(struct drm_device *dev); +void drm_hdmi_avi_infoframe_content_type(struct hdmi_avi_infoframe *frame, + const struct drm_connector_state *conn_state); + int drm_mode_create_suggested_offset_properties(struct drm_device *dev); int drm_mode_connector_set_path_property(struct drm_connector *connector, diff --git a/include/drm/drm_mode_config.h b/include/drm/drm_mode_config.h index 33b3a96d66d0..fb45839179dd 100644 --- a/include/drm/drm_mode_config.h +++ b/include/drm/drm_mode_config.h @@ -726,6 +726,11 @@ struct drm_mode_config { * HDMI infoframe aspect ratio setting. */ struct drm_property *aspect_ratio_property; + /** + * @content_type_property: Optional connector property to control the + * HDMI infoframe content type setting. + */ + struct drm_property *content_type_property; /** * @degamma_lut_property: Optional CRTC property to set the LUT used to * convert the framebuffer's colors to linear gamma. diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h index 4b3a1bb58e68..971c016b368c 100644 --- a/include/uapi/drm/drm_mode.h +++ b/include/uapi/drm/drm_mode.h @@ -96,6 +96,13 @@ extern "C" { #define DRM_MODE_PICTURE_ASPECT_64_27 3 #define DRM_MODE_PICTURE_ASPECT_256_135 4 +/* Content type options */ +#define DRM_MODE_CONTENT_TYPE_NO_DATA 0 +#define DRM_MODE_CONTENT_TYPE_GRAPHICS 1 +#define DRM_MODE_CONTENT_TYPE_PHOTO 2 +#define DRM_MODE_CONTENT_TYPE_CINEMA 3 +#define DRM_MODE_CONTENT_TYPE_GAME 4 + /* Aspect ratio flag bitmask (4 bits 22:19) */ #define DRM_MODE_FLAG_PIC_AR_MASK (0x0F<<19) #define DRM_MODE_FLAG_PIC_AR_NONE \ -- cgit v1.2.3 From 0c08754b59da5557532d946599854e6df28edc22 Mon Sep 17 00:00:00 2001 From: Jyri Sarha Date: Thu, 26 Apr 2018 11:07:00 +0300 Subject: drm/panel: Add device_link from panel device to DRM device Add device_link from panel device (supplier) to DRM device (consumer) when drm_panel_attach() is called. This patch should protect the master DRM driver if an attached panel driver unbinds while it is in use. The device_link should make sure the DRM device is unbound before the panel driver becomes unavailable. The device_link is removed when drm_panel_detach() is called. The drm_panel_detach() should be called by the consumer DRM driver, not the panel driver, otherwise both drivers are racing to delete the same link. Signed-off-by: Jyri Sarha Reviewed-by: Eric Anholt Signed-off-by: Thierry Reding Link: https://patchwork.freedesktop.org/patch/msgid/b53584fd988d045c13de22d81825395b0ae0aad7.1524727888.git.jsarha@ti.com --- drivers/gpu/drm/drm_panel.c | 10 ++++++++++ include/drm/drm_panel.h | 1 + 2 files changed, 11 insertions(+) (limited to 'include') diff --git a/drivers/gpu/drm/drm_panel.c b/drivers/gpu/drm/drm_panel.c index 71e407574276..965530a6f4cd 100644 --- a/drivers/gpu/drm/drm_panel.c +++ b/drivers/gpu/drm/drm_panel.c @@ -24,6 +24,7 @@ #include #include +#include #include #include @@ -104,6 +105,13 @@ int drm_panel_attach(struct drm_panel *panel, struct drm_connector *connector) if (panel->connector) return -EBUSY; + panel->link = device_link_add(connector->dev->dev, panel->dev, 0); + if (!panel->link) { + dev_err(panel->dev, "failed to link panel to %s\n", + dev_name(connector->dev->dev)); + return -EINVAL; + } + panel->connector = connector; panel->drm = connector->dev; @@ -125,6 +133,8 @@ EXPORT_SYMBOL(drm_panel_attach); */ int drm_panel_detach(struct drm_panel *panel) { + device_link_del(panel->link); + panel->connector = NULL; panel->drm = NULL; diff --git a/include/drm/drm_panel.h b/include/drm/drm_panel.h index 14ac240a1f64..26a1b5fd8796 100644 --- a/include/drm/drm_panel.h +++ b/include/drm/drm_panel.h @@ -89,6 +89,7 @@ struct drm_panel { struct drm_device *drm; struct drm_connector *connector; struct device *dev; + struct device_link *link; const struct drm_panel_funcs *funcs; -- cgit v1.2.3 From 2f7e87692e0441abf27a9714991edd136e87363a Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Mon, 21 May 2018 09:21:28 +0100 Subject: drm/mm: Reject over-sized allocation requests early As we keep an rbtree of available holes sorted by their size, we can very easily determine if there is any hole large enough that might satisfy the allocation request. This helps when dealing with a highly fragmented address space and a request for a search by address. To cache the largest size, we convert into the cached rbtree variant which tracks the leftmost node for us. However, currently we sorted into ascending size order so the leftmost node is the smallest, and so to make it the largest hole we need to invert our sorting. Signed-off-by: Chris Wilson Cc: Joonas Lahtinen Reviewed-by: Joonas Lahtinen Link: https://patchwork.freedesktop.org/patch/msgid/20180521082131.13744-1-chris@chris-wilson.co.uk --- drivers/gpu/drm/drm_mm.c | 82 +++++++++++++++++++++++++++++++++--------------- include/drm/drm_mm.h | 2 +- 2 files changed, 58 insertions(+), 26 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c index 3166026a1874..7b4ad05fe1c0 100644 --- a/drivers/gpu/drm/drm_mm.c +++ b/drivers/gpu/drm/drm_mm.c @@ -239,6 +239,32 @@ static void drm_mm_interval_tree_add_node(struct drm_mm_node *hole_node, #define HOLE_SIZE(NODE) ((NODE)->hole_size) #define HOLE_ADDR(NODE) (__drm_mm_hole_node_start(NODE)) +static u64 rb_to_hole_size(struct rb_node *rb) +{ + return rb_entry(rb, struct drm_mm_node, rb_hole_size)->hole_size; +} + +static void insert_hole_size(struct rb_root_cached *root, + struct drm_mm_node *node) +{ + struct rb_node **link = &root->rb_root.rb_node, *rb = NULL; + u64 x = node->hole_size; + bool first = true; + + while (*link) { + rb = *link; + if (x > rb_to_hole_size(rb)) { + link = &rb->rb_left; + } else { + link = &rb->rb_right; + first = false; + } + } + + rb_link_node(&node->rb_hole_size, rb, link); + rb_insert_color_cached(&node->rb_hole_size, root, first); +} + static void add_hole(struct drm_mm_node *node) { struct drm_mm *mm = node->mm; @@ -247,7 +273,7 @@ static void add_hole(struct drm_mm_node *node) __drm_mm_hole_node_end(node) - __drm_mm_hole_node_start(node); DRM_MM_BUG_ON(!drm_mm_hole_follows(node)); - RB_INSERT(mm->holes_size, rb_hole_size, HOLE_SIZE); + insert_hole_size(&mm->holes_size, node); RB_INSERT(mm->holes_addr, rb_hole_addr, HOLE_ADDR); list_add(&node->hole_stack, &mm->hole_stack); @@ -258,7 +284,7 @@ static void rm_hole(struct drm_mm_node *node) DRM_MM_BUG_ON(!drm_mm_hole_follows(node)); list_del(&node->hole_stack); - rb_erase(&node->rb_hole_size, &node->mm->holes_size); + rb_erase_cached(&node->rb_hole_size, &node->mm->holes_size); rb_erase(&node->rb_hole_addr, &node->mm->holes_addr); node->hole_size = 0; @@ -282,38 +308,39 @@ static inline u64 rb_hole_size(struct rb_node *rb) static struct drm_mm_node *best_hole(struct drm_mm *mm, u64 size) { - struct rb_node *best = NULL; - struct rb_node **link = &mm->holes_size.rb_node; + struct rb_node *rb = mm->holes_size.rb_root.rb_node; + struct drm_mm_node *best = NULL; - while (*link) { - struct rb_node *rb = *link; + do { + struct drm_mm_node *node = + rb_entry(rb, struct drm_mm_node, rb_hole_size); - if (size <= rb_hole_size(rb)) { - link = &rb->rb_left; - best = rb; + if (size <= node->hole_size) { + best = node; + rb = rb->rb_right; } else { - link = &rb->rb_right; + rb = rb->rb_left; } - } + } while (rb); - return rb_hole_size_to_node(best); + return best; } static struct drm_mm_node *find_hole(struct drm_mm *mm, u64 addr) { + struct rb_node *rb = mm->holes_addr.rb_node; struct drm_mm_node *node = NULL; - struct rb_node **link = &mm->holes_addr.rb_node; - while (*link) { + while (rb) { u64 hole_start; - node = rb_hole_addr_to_node(*link); + node = rb_hole_addr_to_node(rb); hole_start = __drm_mm_hole_node_start(node); if (addr < hole_start) - link = &node->rb_hole_addr.rb_left; + rb = node->rb_hole_addr.rb_left; else if (addr > hole_start + node->hole_size) - link = &node->rb_hole_addr.rb_right; + rb = node->rb_hole_addr.rb_right; else break; } @@ -326,9 +353,6 @@ first_hole(struct drm_mm *mm, u64 start, u64 end, u64 size, enum drm_mm_insert_mode mode) { - if (RB_EMPTY_ROOT(&mm->holes_size)) - return NULL; - switch (mode) { default: case DRM_MM_INSERT_BEST: @@ -355,7 +379,7 @@ next_hole(struct drm_mm *mm, switch (mode) { default: case DRM_MM_INSERT_BEST: - return rb_hole_size_to_node(rb_next(&node->rb_hole_size)); + return rb_hole_size_to_node(rb_prev(&node->rb_hole_size)); case DRM_MM_INSERT_LOW: return rb_hole_addr_to_node(rb_next(&node->rb_hole_addr)); @@ -426,6 +450,11 @@ int drm_mm_reserve_node(struct drm_mm *mm, struct drm_mm_node *node) } EXPORT_SYMBOL(drm_mm_reserve_node); +static u64 rb_to_hole_size_or_zero(struct rb_node *rb) +{ + return rb ? rb_to_hole_size(rb) : 0; +} + /** * drm_mm_insert_node_in_range - ranged search for space and insert @node * @mm: drm_mm to allocate from @@ -457,6 +486,9 @@ int drm_mm_insert_node_in_range(struct drm_mm * const mm, if (unlikely(size == 0 || range_end - range_start < size)) return -ENOSPC; + if (rb_to_hole_size_or_zero(rb_first_cached(&mm->holes_size)) < size) + return -ENOSPC; + if (alignment <= 1) alignment = 0; @@ -587,9 +619,9 @@ void drm_mm_replace_node(struct drm_mm_node *old, struct drm_mm_node *new) if (drm_mm_hole_follows(old)) { list_replace(&old->hole_stack, &new->hole_stack); - rb_replace_node(&old->rb_hole_size, - &new->rb_hole_size, - &mm->holes_size); + rb_replace_node_cached(&old->rb_hole_size, + &new->rb_hole_size, + &mm->holes_size); rb_replace_node(&old->rb_hole_addr, &new->rb_hole_addr, &mm->holes_addr); @@ -885,7 +917,7 @@ void drm_mm_init(struct drm_mm *mm, u64 start, u64 size) INIT_LIST_HEAD(&mm->hole_stack); mm->interval_tree = RB_ROOT_CACHED; - mm->holes_size = RB_ROOT; + mm->holes_size = RB_ROOT_CACHED; mm->holes_addr = RB_ROOT; /* Clever trick to avoid a special case in the free hole tracking. */ diff --git a/include/drm/drm_mm.h b/include/drm/drm_mm.h index 101f566ae43d..e3aa3bfd4860 100644 --- a/include/drm/drm_mm.h +++ b/include/drm/drm_mm.h @@ -173,7 +173,7 @@ struct drm_mm { struct drm_mm_node head_node; /* Keep an interval_tree for fast lookup of drm_mm_nodes by address. */ struct rb_root_cached interval_tree; - struct rb_root holes_size; + struct rb_root_cached holes_size; struct rb_root holes_addr; unsigned long scan_active; -- cgit v1.2.3 From 83bc4ec37210b17bd611a58968b2ce0e9cc7f251 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Mon, 21 May 2018 09:21:29 +0100 Subject: drm/mm: Add a search-by-address variant to only inspect a single hole Searching for an available hole by address is slow, as there no guarantee that a hole will be available and so we must walk over all nodes in the rbtree before we determine the search was futile. In many cases, the caller doesn't strictly care for the highest available hole and was just opportunistically laying out the address space in a preferred order. In such cases, the caller can accept any address and would rather do so then do a slow walk. To be able to mix search strategies, the caller wants to tell the drm_mm how long to spend on the search. Without a good guide for what should be the best split, start with a request to try once at most. That is return the top-most (or lowest) hole if it fulfils the alignment and size requirements. v2: Documentation, by why of example (selftests) and kerneldoc. Signed-off-by: Chris Wilson Cc: Joonas Lahtinen Reviewed-by: Joonas Lahtinen Link: https://patchwork.freedesktop.org/patch/msgid/20180521082131.13744-2-chris@chris-wilson.co.uk --- drivers/gpu/drm/drm_mm.c | 9 +++- drivers/gpu/drm/selftests/drm_mm_selftests.h | 2 + drivers/gpu/drm/selftests/test-drm_mm.c | 71 ++++++++++++++++++++++++++++ include/drm/drm_mm.h | 32 +++++++++++++ 4 files changed, 112 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c index 7b4ad05fe1c0..3cc5fbd78ee2 100644 --- a/drivers/gpu/drm/drm_mm.c +++ b/drivers/gpu/drm/drm_mm.c @@ -480,6 +480,7 @@ int drm_mm_insert_node_in_range(struct drm_mm * const mm, { struct drm_mm_node *hole; u64 remainder_mask; + bool once; DRM_MM_BUG_ON(range_start >= range_end); @@ -492,9 +493,13 @@ int drm_mm_insert_node_in_range(struct drm_mm * const mm, if (alignment <= 1) alignment = 0; + once = mode & DRM_MM_INSERT_ONCE; + mode &= ~DRM_MM_INSERT_ONCE; + remainder_mask = is_power_of_2(alignment) ? alignment - 1 : 0; - for (hole = first_hole(mm, range_start, range_end, size, mode); hole; - hole = next_hole(mm, hole, mode)) { + for (hole = first_hole(mm, range_start, range_end, size, mode); + hole; + hole = once ? NULL : next_hole(mm, hole, mode)) { u64 hole_start = __drm_mm_hole_node_start(hole); u64 hole_end = hole_start + hole->hole_size; u64 adj_start, adj_end; diff --git a/drivers/gpu/drm/selftests/drm_mm_selftests.h b/drivers/gpu/drm/selftests/drm_mm_selftests.h index 54acc117550c..6b943ea1c57d 100644 --- a/drivers/gpu/drm/selftests/drm_mm_selftests.h +++ b/drivers/gpu/drm/selftests/drm_mm_selftests.h @@ -19,7 +19,9 @@ selftest(align64, igt_align64) selftest(evict, igt_evict) selftest(evict_range, igt_evict_range) selftest(bottomup, igt_bottomup) +selftest(lowest, igt_lowest) selftest(topdown, igt_topdown) +selftest(highest, igt_highest) selftest(color, igt_color) selftest(color_evict, igt_color_evict) selftest(color_evict_range, igt_color_evict_range) diff --git a/drivers/gpu/drm/selftests/test-drm_mm.c b/drivers/gpu/drm/selftests/test-drm_mm.c index 7cc935d7b7aa..f69d8da222b0 100644 --- a/drivers/gpu/drm/selftests/test-drm_mm.c +++ b/drivers/gpu/drm/selftests/test-drm_mm.c @@ -1825,6 +1825,77 @@ err: return ret; } +static int __igt_once(unsigned int mode) +{ + struct drm_mm mm; + struct drm_mm_node rsvd_lo, rsvd_hi, node; + int err; + + drm_mm_init(&mm, 0, 7); + + memset(&rsvd_lo, 0, sizeof(rsvd_lo)); + rsvd_lo.start = 1; + rsvd_lo.size = 1; + err = drm_mm_reserve_node(&mm, &rsvd_lo); + if (err) { + pr_err("Could not reserve low node\n"); + goto err; + } + + memset(&rsvd_hi, 0, sizeof(rsvd_hi)); + rsvd_hi.start = 5; + rsvd_hi.size = 1; + err = drm_mm_reserve_node(&mm, &rsvd_hi); + if (err) { + pr_err("Could not reserve low node\n"); + goto err_lo; + } + + if (!drm_mm_hole_follows(&rsvd_lo) || !drm_mm_hole_follows(&rsvd_hi)) { + pr_err("Expected a hole after lo and high nodes!\n"); + err = -EINVAL; + goto err_hi; + } + + memset(&node, 0, sizeof(node)); + err = drm_mm_insert_node_generic(&mm, &node, + 2, 0, 0, + mode | DRM_MM_INSERT_ONCE); + if (!err) { + pr_err("Unexpectedly inserted the node into the wrong hole: node.start=%llx\n", + node.start); + err = -EINVAL; + goto err_node; + } + + err = drm_mm_insert_node_generic(&mm, &node, 2, 0, 0, mode); + if (err) { + pr_err("Could not insert the node into the available hole!\n"); + err = -EINVAL; + goto err_hi; + } + +err_node: + drm_mm_remove_node(&node); +err_hi: + drm_mm_remove_node(&rsvd_hi); +err_lo: + drm_mm_remove_node(&rsvd_lo); +err: + drm_mm_takedown(&mm); + return err; +} + +static int igt_lowest(void *ignored) +{ + return __igt_once(DRM_MM_INSERT_LOW); +} + +static int igt_highest(void *ignored) +{ + return __igt_once(DRM_MM_INSERT_HIGH); +} + static void separate_adjacent_colors(const struct drm_mm_node *node, unsigned long color, u64 *start, diff --git a/include/drm/drm_mm.h b/include/drm/drm_mm.h index e3aa3bfd4860..2c3bbb43c7d1 100644 --- a/include/drm/drm_mm.h +++ b/include/drm/drm_mm.h @@ -109,6 +109,38 @@ enum drm_mm_insert_mode { * Allocates the node from the bottom of the found hole. */ DRM_MM_INSERT_EVICT, + + /** + * @DRM_MM_INSERT_ONCE: + * + * Only check the first hole for suitablity and report -ENOSPC + * immediately otherwise, rather than check every hole until a + * suitable one is found. Can only be used in conjunction with another + * search method such as DRM_MM_INSERT_HIGH or DRM_MM_INSERT_LOW. + */ + DRM_MM_INSERT_ONCE = BIT(31), + + /** + * @DRM_MM_INSERT_HIGHEST: + * + * Only check the highest hole (the hole with the largest address) and + * insert the node at the top of the hole or report -ENOSPC if + * unsuitable. + * + * Does not search all holes. + */ + DRM_MM_INSERT_HIGHEST = DRM_MM_INSERT_HIGH | DRM_MM_INSERT_ONCE, + + /** + * @DRM_MM_INSERT_LOWEST: + * + * Only check the lowest hole (the hole with the smallest address) and + * insert the node at the bottom of the hole or report -ENOSPC if + * unsuitable. + * + * Does not search all holes. + */ + DRM_MM_INSERT_LOWEST = DRM_MM_INSERT_LOW | DRM_MM_INSERT_ONCE, }; /** -- cgit v1.2.3 From 8fb756dfa273bcb42bdaff65baae83548b6c326d Mon Sep 17 00:00:00 2001 From: Eric Anholt Date: Fri, 16 Mar 2018 15:04:33 -0700 Subject: drm: Trust format_mod_supported() when it OKs a plane modifier. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit For parameterized modifiers (Broadcom's SAND and UIF), we need to allow the parameter fields to be filled in, while exposing only the variant of the modifier with the parameter unfilled in the internal arrays and the format blob. Signed-off-by: Eric Anholt Cc: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20180316220435.31416-1-eric@anholt.net Reviewed-by: Ville Syrjälä --- drivers/gpu/drm/drm_plane.c | 23 ++++++++++++----------- include/drm/drm_plane.h | 5 ++++- 2 files changed, 16 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_plane.c b/drivers/gpu/drm/drm_plane.c index 035054455301..7ce88dff871d 100644 --- a/drivers/gpu/drm/drm_plane.c +++ b/drivers/gpu/drm/drm_plane.c @@ -561,19 +561,20 @@ int drm_plane_check_pixel_format(struct drm_plane *plane, if (i == plane->format_count) return -EINVAL; - if (!plane->modifier_count) - return 0; + if (plane->funcs->format_mod_supported) { + if (!plane->funcs->format_mod_supported(plane, format, modifier)) + return -EINVAL; + } else { + if (!plane->modifier_count) + return 0; - for (i = 0; i < plane->modifier_count; i++) { - if (modifier == plane->modifiers[i]) - break; + for (i = 0; i < plane->modifier_count; i++) { + if (modifier == plane->modifiers[i]) + break; + } + if (i == plane->modifier_count) + return -EINVAL; } - if (i == plane->modifier_count) - return -EINVAL; - - if (plane->funcs->format_mod_supported && - !plane->funcs->format_mod_supported(plane, format, modifier)) - return -EINVAL; return 0; } diff --git a/include/drm/drm_plane.h b/include/drm/drm_plane.h index 26fa50c2a50e..14b1607aba4b 100644 --- a/include/drm/drm_plane.h +++ b/include/drm/drm_plane.h @@ -431,7 +431,10 @@ struct drm_plane_funcs { * This optional hook is used for the DRM to determine if the given * format/modifier combination is valid for the plane. This allows the * DRM to generate the correct format bitmask (which formats apply to - * which modifier). + * which modifier), and to valdiate modifiers at atomic_check time. + * + * If not present, then any modifier in the plane's modifier + * list is allowed with any of the plane's formats. * * Returns: * -- cgit v1.2.3 From e065a8dd30af703b4794dc740c0825ee12b92efd Mon Sep 17 00:00:00 2001 From: Dave Stevenson Date: Fri, 16 Mar 2018 15:04:35 -0700 Subject: drm/vc4: Add support for SAND modifier. This is the format generated by VC4's H.264 engine, and preferred by the ISP as well. By displaying SAND buffers directly, we can avoid needing to use the ISP to rewrite the SAND H.264 output to linear before display. This is a joint effort by Dave Stevenson (who wrote the initial patch and DRM demo) and Eric Anholt (drm_fourcc.h generalization, safety checks, RGBA support). v2: Make the parameter macro give all of the middle 48 bits (suggested by Daniels). Fix fourcc_mod_broadcom_mod()'s bits/shift being swapped. Mark NV12/21 as supported, not YUV420. Signed-off-by: Dave Stevenson Signed-off-by: Eric Anholt Cc: Daniel Vetter Acked-by: Daniel Stone (v1) Cc: Boris Brezillon Cc: Maxime Ripard Link: https://patchwork.freedesktop.org/patch/msgid/20180316220435.31416-3-eric@anholt.net --- drivers/gpu/drm/vc4/vc4_plane.c | 84 +++++++++++++++++++++++++++++++++++++---- drivers/gpu/drm/vc4/vc4_regs.h | 6 +++ include/uapi/drm/drm_fourcc.h | 59 +++++++++++++++++++++++++++++ 3 files changed, 142 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c index 6efd55bae8db..2575bd81a010 100644 --- a/drivers/gpu/drm/vc4/vc4_plane.c +++ b/drivers/gpu/drm/vc4/vc4_plane.c @@ -467,12 +467,14 @@ static int vc4_plane_mode_set(struct drm_plane *plane, struct drm_framebuffer *fb = state->fb; u32 ctl0_offset = vc4_state->dlist_count; const struct hvs_format *format = vc4_get_hvs_format(fb->format->format); + u64 base_format_mod = fourcc_mod_broadcom_mod(fb->modifier); int num_planes = drm_format_num_planes(format->drm); bool mix_plane_alpha; bool covers_screen; u32 scl0, scl1, pitch0; u32 lbm_size, tiling; unsigned long irqflags; + u32 hvs_format = format->hvs; int ret, i; ret = vc4_plane_setup_clipping_and_scaling(state); @@ -512,7 +514,7 @@ static int vc4_plane_mode_set(struct drm_plane *plane, scl1 = vc4_get_scl_field(state, 0); } - switch (fb->modifier) { + switch (base_format_mod) { case DRM_FORMAT_MOD_LINEAR: tiling = SCALER_CTL0_TILING_LINEAR; pitch0 = VC4_SET_FIELD(fb->pitches[0], SCALER_SRC_PITCH); @@ -535,6 +537,49 @@ static int vc4_plane_mode_set(struct drm_plane *plane, break; } + case DRM_FORMAT_MOD_BROADCOM_SAND64: + case DRM_FORMAT_MOD_BROADCOM_SAND128: + case DRM_FORMAT_MOD_BROADCOM_SAND256: { + uint32_t param = fourcc_mod_broadcom_param(fb->modifier); + + /* Column-based NV12 or RGBA. + */ + if (fb->format->num_planes > 1) { + if (hvs_format != HVS_PIXEL_FORMAT_YCBCR_YUV420_2PLANE) { + DRM_DEBUG_KMS("SAND format only valid for NV12/21"); + return -EINVAL; + } + hvs_format = HVS_PIXEL_FORMAT_H264; + } else { + if (base_format_mod == DRM_FORMAT_MOD_BROADCOM_SAND256) { + DRM_DEBUG_KMS("SAND256 format only valid for H.264"); + return -EINVAL; + } + } + + switch (base_format_mod) { + case DRM_FORMAT_MOD_BROADCOM_SAND64: + tiling = SCALER_CTL0_TILING_64B; + break; + case DRM_FORMAT_MOD_BROADCOM_SAND128: + tiling = SCALER_CTL0_TILING_128B; + break; + case DRM_FORMAT_MOD_BROADCOM_SAND256: + tiling = SCALER_CTL0_TILING_256B_OR_T; + break; + default: + break; + } + + if (param > SCALER_TILE_HEIGHT_MASK) { + DRM_DEBUG_KMS("SAND height too large (%d)\n", param); + return -EINVAL; + } + + pitch0 = VC4_SET_FIELD(param, SCALER_TILE_HEIGHT); + break; + } + default: DRM_DEBUG_KMS("Unsupported FB tiling flag 0x%16llx", (long long)fb->modifier); @@ -546,7 +591,7 @@ static int vc4_plane_mode_set(struct drm_plane *plane, SCALER_CTL0_VALID | VC4_SET_FIELD(SCALER_CTL0_RGBA_EXPAND_ROUND, SCALER_CTL0_RGBA_EXPAND) | (format->pixel_order << SCALER_CTL0_ORDER_SHIFT) | - (format->hvs << SCALER_CTL0_PIXEL_FORMAT_SHIFT) | + (hvs_format << SCALER_CTL0_PIXEL_FORMAT_SHIFT) | VC4_SET_FIELD(tiling, SCALER_CTL0_TILING) | (vc4_state->is_unity ? SCALER_CTL0_UNITY : 0) | VC4_SET_FIELD(scl0, SCALER_CTL0_SCL0) | @@ -608,8 +653,13 @@ static int vc4_plane_mode_set(struct drm_plane *plane, /* Pitch word 1/2 */ for (i = 1; i < num_planes; i++) { - vc4_dlist_write(vc4_state, - VC4_SET_FIELD(fb->pitches[i], SCALER_SRC_PITCH)); + if (hvs_format != HVS_PIXEL_FORMAT_H264) { + vc4_dlist_write(vc4_state, + VC4_SET_FIELD(fb->pitches[i], + SCALER_SRC_PITCH)); + } else { + vc4_dlist_write(vc4_state, pitch0); + } } /* Colorspace conversion words */ @@ -867,13 +917,30 @@ static bool vc4_format_mod_supported(struct drm_plane *plane, case DRM_FORMAT_BGR565: case DRM_FORMAT_ARGB1555: case DRM_FORMAT_XRGB1555: - return true; + switch (fourcc_mod_broadcom_mod(modifier)) { + case DRM_FORMAT_MOD_LINEAR: + case DRM_FORMAT_MOD_BROADCOM_VC4_T_TILED: + case DRM_FORMAT_MOD_BROADCOM_SAND64: + case DRM_FORMAT_MOD_BROADCOM_SAND128: + return true; + default: + return false; + } + case DRM_FORMAT_NV12: + case DRM_FORMAT_NV21: + switch (fourcc_mod_broadcom_mod(modifier)) { + case DRM_FORMAT_MOD_LINEAR: + case DRM_FORMAT_MOD_BROADCOM_SAND64: + case DRM_FORMAT_MOD_BROADCOM_SAND128: + case DRM_FORMAT_MOD_BROADCOM_SAND256: + return true; + default: + return false; + } case DRM_FORMAT_YUV422: case DRM_FORMAT_YVU422: case DRM_FORMAT_YUV420: case DRM_FORMAT_YVU420: - case DRM_FORMAT_NV12: - case DRM_FORMAT_NV21: case DRM_FORMAT_NV16: case DRM_FORMAT_NV61: default: @@ -903,6 +970,9 @@ struct drm_plane *vc4_plane_init(struct drm_device *dev, unsigned i; static const uint64_t modifiers[] = { DRM_FORMAT_MOD_BROADCOM_VC4_T_TILED, + DRM_FORMAT_MOD_BROADCOM_SAND128, + DRM_FORMAT_MOD_BROADCOM_SAND64, + DRM_FORMAT_MOD_BROADCOM_SAND256, DRM_FORMAT_MOD_LINEAR, DRM_FORMAT_MOD_INVALID }; diff --git a/drivers/gpu/drm/vc4/vc4_regs.h b/drivers/gpu/drm/vc4/vc4_regs.h index d1fb6fec46eb..d6864fa4bd14 100644 --- a/drivers/gpu/drm/vc4/vc4_regs.h +++ b/drivers/gpu/drm/vc4/vc4_regs.h @@ -1031,6 +1031,12 @@ enum hvs_pixel_format { #define SCALER_SRC_PITCH_MASK VC4_MASK(15, 0) #define SCALER_SRC_PITCH_SHIFT 0 +/* PITCH0/1/2 fields for tiled (SAND). */ +#define SCALER_TILE_SKIP_0_MASK VC4_MASK(18, 16) +#define SCALER_TILE_SKIP_0_SHIFT 16 +#define SCALER_TILE_HEIGHT_MASK VC4_MASK(15, 0) +#define SCALER_TILE_HEIGHT_SHIFT 0 + /* PITCH0 fields for T-tiled. */ #define SCALER_PITCH0_TILE_WIDTH_L_MASK VC4_MASK(22, 16) #define SCALER_PITCH0_TILE_WIDTH_L_SHIFT 16 diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h index e04613d30a13..64bf67abff7e 100644 --- a/include/uapi/drm/drm_fourcc.h +++ b/include/uapi/drm/drm_fourcc.h @@ -384,6 +384,23 @@ extern "C" { #define DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK_THIRTYTWO_GOB \ fourcc_mod_code(NVIDIA, 0x15) +/* + * Some Broadcom modifiers take parameters, for example the number of + * vertical lines in the image. Reserve the lower 32 bits for modifier + * type, and the next 24 bits for parameters. Top 8 bits are the + * vendor code. + */ +#define __fourcc_mod_broadcom_param_shift 8 +#define __fourcc_mod_broadcom_param_bits 48 +#define fourcc_mod_broadcom_code(val, params) \ + fourcc_mod_code(BROADCOM, ((((__u64)params) << __fourcc_mod_broadcom_param_shift) | val)) +#define fourcc_mod_broadcom_param(m) \ + ((int)(((m) >> __fourcc_mod_broadcom_param_shift) & \ + ((1ULL << __fourcc_mod_broadcom_param_bits) - 1))) +#define fourcc_mod_broadcom_mod(m) \ + ((m) & ~(((1ULL << __fourcc_mod_broadcom_param_bits) - 1) << \ + __fourcc_mod_broadcom_param_shift)) + /* * Broadcom VC4 "T" format * @@ -405,6 +422,48 @@ extern "C" { */ #define DRM_FORMAT_MOD_BROADCOM_VC4_T_TILED fourcc_mod_code(BROADCOM, 1) +/* + * Broadcom SAND format + * + * This is the native format that the H.264 codec block uses. For VC4 + * HVS, it is only valid for H.264 (NV12/21) and RGBA modes. + * + * The image can be considered to be split into columns, and the + * columns are placed consecutively into memory. The width of those + * columns can be either 32, 64, 128, or 256 pixels, but in practice + * only 128 pixel columns are used. + * + * The pitch between the start of each column is set to optimally + * switch between SDRAM banks. This is passed as the number of lines + * of column width in the modifier (we can't use the stride value due + * to various core checks that look at it , so you should set the + * stride to width*cpp). + * + * Note that the column height for this format modifier is the same + * for all of the planes, assuming that each column contains both Y + * and UV. Some SAND-using hardware stores UV in a separate tiled + * image from Y to reduce the column height, which is not supported + * with these modifiers. + */ + +#define DRM_FORMAT_MOD_BROADCOM_SAND32_COL_HEIGHT(v) \ + fourcc_mod_broadcom_code(2, v) +#define DRM_FORMAT_MOD_BROADCOM_SAND64_COL_HEIGHT(v) \ + fourcc_mod_broadcom_code(3, v) +#define DRM_FORMAT_MOD_BROADCOM_SAND128_COL_HEIGHT(v) \ + fourcc_mod_broadcom_code(4, v) +#define DRM_FORMAT_MOD_BROADCOM_SAND256_COL_HEIGHT(v) \ + fourcc_mod_broadcom_code(5, v) + +#define DRM_FORMAT_MOD_BROADCOM_SAND32 \ + DRM_FORMAT_MOD_BROADCOM_SAND32_COL_HEIGHT(0) +#define DRM_FORMAT_MOD_BROADCOM_SAND64 \ + DRM_FORMAT_MOD_BROADCOM_SAND64_COL_HEIGHT(0) +#define DRM_FORMAT_MOD_BROADCOM_SAND128 \ + DRM_FORMAT_MOD_BROADCOM_SAND128_COL_HEIGHT(0) +#define DRM_FORMAT_MOD_BROADCOM_SAND256 \ + DRM_FORMAT_MOD_BROADCOM_SAND256_COL_HEIGHT(0) + #if defined(__cplusplus) } #endif -- cgit v1.2.3 From 09ea0dfbf972c63dfea8cf46f2fb67f39e4d833b Mon Sep 17 00:00:00 2001 From: Gerd Hoffmann Date: Tue, 29 May 2018 15:59:18 +0200 Subject: dma-buf: make map_atomic and map function pointers optional So drivers don't need dummy functions just returning NULL. Cc: Daniel Vetter Signed-off-by: Gerd Hoffmann Reviewed-by: Daniel Vetter Reviewed-by: Oleksandr Andrushchenko Link: http://patchwork.freedesktop.org/patch/msgid/20180529135918.19729-1-kraxel@redhat.com --- drivers/dma-buf/dma-buf.c | 4 ++++ include/linux/dma-buf.h | 4 ++-- 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index d78d5fc173dc..4c45e31258f0 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -872,6 +872,8 @@ void *dma_buf_kmap_atomic(struct dma_buf *dmabuf, unsigned long page_num) { WARN_ON(!dmabuf); + if (!dmabuf->ops->map_atomic) + return NULL; return dmabuf->ops->map_atomic(dmabuf, page_num); } EXPORT_SYMBOL_GPL(dma_buf_kmap_atomic); @@ -907,6 +909,8 @@ void *dma_buf_kmap(struct dma_buf *dmabuf, unsigned long page_num) { WARN_ON(!dmabuf); + if (!dmabuf->ops->map) + return NULL; return dmabuf->ops->map(dmabuf, page_num); } EXPORT_SYMBOL_GPL(dma_buf_kmap); diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 085db2fee2d7..88917fa796e4 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -39,12 +39,12 @@ struct dma_buf_attachment; /** * struct dma_buf_ops - operations possible on struct dma_buf - * @map_atomic: maps a page from the buffer into kernel address + * @map_atomic: [optional] maps a page from the buffer into kernel address * space, users may not block until the subsequent unmap call. * This callback must not sleep. * @unmap_atomic: [optional] unmaps a atomically mapped page from the buffer. * This Callback must not sleep. - * @map: maps a page from the buffer into kernel address space. + * @map: [optional] maps a page from the buffer into kernel address space. * @unmap: [optional] unmaps a page from the buffer. * @vmap: [optional] creates a virtual mapping for the buffer into kernel * address space. Same restrictions as for vmap and friends apply. -- cgit v1.2.3 From e00fb8564ee98c5c3a72c74b1a27e441abff6cca Mon Sep 17 00:00:00 2001 From: Ville Syrjälä Date: Fri, 25 May 2018 21:50:45 +0300 Subject: drm: Stop updating plane->crtc/fb/old_fb on atomic drivers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Stop playing around with plane->crtc/fb/old_fb with atomic drivers. Make life a lot simpler when we don't have to do the magic old_fb vs. fb dance around plane updates. That way we can't risk plane->fb getting out of sync with plane->state->fb and we're less likely to leak any refcounts as well. Signed-off-by: Ville Syrjälä Reviewed-by: Maarten Lankhorst Acked-by: Harry Wentland Link: https://patchwork.freedesktop.org/patch/msgid/20180525185045.29689-14-ville.syrjala@linux.intel.com Reviewed-by: Sinclair Yeh --- drivers/gpu/drm/drm_atomic.c | 55 ++++--------------------------------- drivers/gpu/drm/drm_atomic_helper.c | 15 +--------- drivers/gpu/drm/drm_crtc.c | 8 ++++-- drivers/gpu/drm/drm_fb_helper.c | 7 ----- drivers/gpu/drm/drm_framebuffer.c | 5 ---- drivers/gpu/drm/drm_plane.c | 14 ++++++---- drivers/gpu/drm/drm_plane_helper.c | 4 ++- include/drm/drm_atomic.h | 3 -- 8 files changed, 24 insertions(+), 87 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c index 07fef42869aa..11059d556dbd 100644 --- a/drivers/gpu/drm/drm_atomic.c +++ b/drivers/gpu/drm/drm_atomic.c @@ -692,6 +692,11 @@ drm_atomic_get_plane_state(struct drm_atomic_state *state, WARN_ON(!state->acquire_ctx); + /* the legacy pointers should never be set */ + WARN_ON(plane->fb); + WARN_ON(plane->old_fb); + WARN_ON(plane->crtc); + plane_state = drm_atomic_get_existing_plane_state(state, plane); if (plane_state) return plane_state; @@ -2039,45 +2044,6 @@ int drm_atomic_set_property(struct drm_atomic_state *state, return ret; } -/** - * drm_atomic_clean_old_fb -- Unset old_fb pointers and set plane->fb pointers. - * - * @dev: drm device to check. - * @plane_mask: plane mask for planes that were updated. - * @ret: return value, can be -EDEADLK for a retry. - * - * Before doing an update &drm_plane.old_fb is set to &drm_plane.fb, but before - * dropping the locks old_fb needs to be set to NULL and plane->fb updated. This - * is a common operation for each atomic update, so this call is split off as a - * helper. - */ -void drm_atomic_clean_old_fb(struct drm_device *dev, - unsigned plane_mask, - int ret) -{ - struct drm_plane *plane; - - /* if succeeded, fixup legacy plane crtc/fb ptrs before dropping - * locks (ie. while it is still safe to deref plane->state). We - * need to do this here because the driver entry points cannot - * distinguish between legacy and atomic ioctls. - */ - drm_for_each_plane_mask(plane, dev, plane_mask) { - if (ret == 0) { - struct drm_framebuffer *new_fb = plane->state->fb; - if (new_fb) - drm_framebuffer_get(new_fb); - plane->fb = new_fb; - plane->crtc = plane->state->crtc; - - if (plane->old_fb) - drm_framebuffer_put(plane->old_fb); - } - plane->old_fb = NULL; - } -} -EXPORT_SYMBOL(drm_atomic_clean_old_fb); - /** * DOC: explicit fencing properties * @@ -2298,9 +2264,7 @@ int drm_mode_atomic_ioctl(struct drm_device *dev, unsigned int copied_objs, copied_props; struct drm_atomic_state *state; struct drm_modeset_acquire_ctx ctx; - struct drm_plane *plane; struct drm_out_fence_state *fence_state; - unsigned plane_mask; int ret = 0; unsigned int i, j, num_fences; @@ -2340,7 +2304,6 @@ int drm_mode_atomic_ioctl(struct drm_device *dev, state->allow_modeset = !!(arg->flags & DRM_MODE_ATOMIC_ALLOW_MODESET); retry: - plane_mask = 0; copied_objs = 0; copied_props = 0; fence_state = NULL; @@ -2411,12 +2374,6 @@ retry: copied_props++; } - if (obj->type == DRM_MODE_OBJECT_PLANE && count_props && - !(arg->flags & DRM_MODE_ATOMIC_TEST_ONLY)) { - plane = obj_to_plane(obj); - plane_mask |= (1 << drm_plane_index(plane)); - plane->old_fb = plane->fb; - } drm_mode_object_put(obj); } @@ -2437,8 +2394,6 @@ retry: } out: - drm_atomic_clean_old_fb(dev, plane_mask, ret); - complete_crtc_signaling(dev, state, fence_state, num_fences, !ret); if (ret == -EDEADLK) { diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index 130da5195f3b..232fa11a5e31 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -2914,7 +2914,6 @@ static int __drm_atomic_helper_disable_all(struct drm_device *dev, struct drm_plane *plane; struct drm_crtc_state *crtc_state; struct drm_crtc *crtc; - unsigned plane_mask = 0; int ret, i; state = drm_atomic_state_alloc(dev); @@ -2957,17 +2956,10 @@ static int __drm_atomic_helper_disable_all(struct drm_device *dev, goto free; drm_atomic_set_fb_for_plane(plane_state, NULL); - - if (clean_old_fbs) { - plane->old_fb = plane->fb; - plane_mask |= BIT(drm_plane_index(plane)); - } } ret = drm_atomic_commit(state); free: - if (plane_mask) - drm_atomic_clean_old_fb(dev, plane_mask, ret); drm_atomic_state_put(state); return ret; } @@ -3129,13 +3121,8 @@ int drm_atomic_helper_commit_duplicated_state(struct drm_atomic_state *state, state->acquire_ctx = ctx; - for_each_new_plane_in_state(state, plane, new_plane_state, i) { - WARN_ON(plane->crtc != new_plane_state->crtc); - WARN_ON(plane->fb != new_plane_state->fb); - WARN_ON(plane->old_fb); - + for_each_new_plane_in_state(state, plane, new_plane_state, i) state->planes[i].old_state = plane->state; - } for_each_new_crtc_in_state(state, crtc, new_crtc_state, i) state->crtcs[i].old_state = crtc->state; diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c index 237bd34212db..53828fc8d911 100644 --- a/drivers/gpu/drm/drm_crtc.c +++ b/drivers/gpu/drm/drm_crtc.c @@ -479,8 +479,12 @@ static int __drm_mode_set_config_internal(struct drm_mode_set *set, ret = crtc->funcs->set_config(set, ctx); if (ret == 0) { - crtc->primary->crtc = fb ? crtc : NULL; - crtc->primary->fb = fb; + struct drm_plane *plane = crtc->primary; + + if (!plane->state) { + plane->crtc = fb ? crtc : NULL; + plane->fb = fb; + } } drm_for_each_crtc(tmp, crtc->dev) { diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index 91f051e5e130..cab14f253384 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -368,7 +368,6 @@ static int restore_fbdev_mode_atomic(struct drm_fb_helper *fb_helper, bool activ struct drm_plane *plane; struct drm_atomic_state *state; int i, ret; - unsigned int plane_mask; struct drm_modeset_acquire_ctx ctx; drm_modeset_acquire_init(&ctx, 0); @@ -381,7 +380,6 @@ static int restore_fbdev_mode_atomic(struct drm_fb_helper *fb_helper, bool activ state->acquire_ctx = &ctx; retry: - plane_mask = 0; drm_for_each_plane(plane, dev) { plane_state = drm_atomic_get_plane_state(state, plane); if (IS_ERR(plane_state)) { @@ -391,9 +389,6 @@ retry: plane_state->rotation = DRM_MODE_ROTATE_0; - plane->old_fb = plane->fb; - plane_mask |= 1 << drm_plane_index(plane); - /* disable non-primary: */ if (plane->type == DRM_PLANE_TYPE_PRIMARY) continue; @@ -430,8 +425,6 @@ retry: ret = drm_atomic_commit(state); out_state: - drm_atomic_clean_old_fb(dev, plane_mask, ret); - if (ret == -EDEADLK) goto backoff; diff --git a/drivers/gpu/drm/drm_framebuffer.c b/drivers/gpu/drm/drm_framebuffer.c index bfedceff87bb..46b11e46edbd 100644 --- a/drivers/gpu/drm/drm_framebuffer.c +++ b/drivers/gpu/drm/drm_framebuffer.c @@ -836,8 +836,6 @@ retry: goto unlock; plane_mask |= BIT(drm_plane_index(plane)); - - plane->old_fb = plane->fb; } /* This list is only filled when disable_crtcs is set. */ @@ -852,9 +850,6 @@ retry: ret = drm_atomic_commit(state); unlock: - if (plane_mask) - drm_atomic_clean_old_fb(dev, plane_mask, ret); - if (ret == -EDEADLK) { drm_atomic_state_clear(state); drm_modeset_backoff(&ctx); diff --git a/drivers/gpu/drm/drm_plane.c b/drivers/gpu/drm/drm_plane.c index 7ce88dff871d..534b57933576 100644 --- a/drivers/gpu/drm/drm_plane.c +++ b/drivers/gpu/drm/drm_plane.c @@ -651,9 +651,11 @@ static int __setplane_internal(struct drm_plane *plane, crtc_x, crtc_y, crtc_w, crtc_h, src_x, src_y, src_w, src_h, ctx); if (!ret) { - plane->crtc = crtc; - plane->fb = fb; - drm_framebuffer_get(plane->fb); + if (!plane->state) { + plane->crtc = crtc; + plane->fb = fb; + drm_framebuffer_get(plane->fb); + } } else { plane->old_fb = NULL; } @@ -1093,8 +1095,10 @@ retry: /* Keep the old fb, don't unref it. */ plane->old_fb = NULL; } else { - plane->fb = fb; - drm_framebuffer_get(fb); + if (!plane->state) { + plane->fb = fb; + drm_framebuffer_get(fb); + } } out: diff --git a/drivers/gpu/drm/drm_plane_helper.c b/drivers/gpu/drm/drm_plane_helper.c index f88f68161519..2010794943bc 100644 --- a/drivers/gpu/drm/drm_plane_helper.c +++ b/drivers/gpu/drm/drm_plane_helper.c @@ -502,6 +502,7 @@ EXPORT_SYMBOL(drm_plane_helper_update); int drm_plane_helper_disable(struct drm_plane *plane) { struct drm_plane_state *plane_state; + struct drm_framebuffer *old_fb; /* crtc helpers love to call disable functions for already disabled hw * functions. So cope with that. */ @@ -521,8 +522,9 @@ int drm_plane_helper_disable(struct drm_plane *plane) plane_state->plane = plane; plane_state->crtc = NULL; + old_fb = plane_state->fb; drm_atomic_set_fb_for_plane(plane_state, NULL); - return drm_plane_helper_commit(plane, plane_state, plane->fb); + return drm_plane_helper_commit(plane, plane_state, old_fb); } EXPORT_SYMBOL(drm_plane_helper_disable); diff --git a/include/drm/drm_atomic.h b/include/drm/drm_atomic.h index a57a8aa90ffb..ca461b6cf71f 100644 --- a/include/drm/drm_atomic.h +++ b/include/drm/drm_atomic.h @@ -601,9 +601,6 @@ int __must_check drm_atomic_add_affected_planes(struct drm_atomic_state *state, struct drm_crtc *crtc); -void -drm_atomic_clean_old_fb(struct drm_device *dev, unsigned plane_mask, int ret); - int __must_check drm_atomic_check_only(struct drm_atomic_state *state); int __must_check drm_atomic_commit(struct drm_atomic_state *state); int __must_check drm_atomic_nonblocking_commit(struct drm_atomic_state *state); -- cgit v1.2.3 From 2e076f199097d670ce5e5492cea57f552b93bba9 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 28 May 2018 15:47:40 +0200 Subject: nl80211: add scan features for improved scan privacy Add the scan flags for randomized SN and minimized probe request content for improved scan privacy. Signed-off-by: Johannes Berg Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 15 +++++++++++++++ net/wireless/nl80211.c | 8 +++++++- 2 files changed, 22 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 28b36545de24..49f718e821a3 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -5133,6 +5133,11 @@ enum nl80211_feature_flags { * support to nl80211. * @NL80211_EXT_FEATURE_TXQS: Driver supports FQ-CoDel-enabled intermediate * TXQs. + * @NL80211_EXT_FEATURE_SCAN_RANDOM_SN: Driver/device supports randomizing the + * SN in probe request frames if requested by %NL80211_SCAN_FLAG_RANDOM_SN. + * @NL80211_EXT_FEATURE_SCAN_MIN_PREQ_CONTENT: Driver/device can omit all data + * except for supported rates from the probe request content if requested + * by the %NL80211_SCAN_FLAG_MIN_PREQ_CONTENT flag. * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. @@ -5167,6 +5172,8 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_CONTROL_PORT_OVER_NL80211, NL80211_EXT_FEATURE_DATA_ACK_SIGNAL_SUPPORT, NL80211_EXT_FEATURE_TXQS, + NL80211_EXT_FEATURE_SCAN_RANDOM_SN, + NL80211_EXT_FEATURE_SCAN_MIN_PREQ_CONTENT, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, @@ -5272,6 +5279,12 @@ enum nl80211_timeout_reason { * possible scan results. This flag hints the driver to use the best * possible scan configuration to improve the accuracy in scanning. * Latency and power use may get impacted with this flag. + * @NL80211_SCAN_FLAG_RANDOM_SN: randomize the sequence number in probe + * request frames from this scan to avoid correlation/tracking being + * possible. + * @NL80211_SCAN_FLAG_MIN_PREQ_CONTENT: minimize probe request content to + * only have supported rates and no additional capabilities (unless + * added by userspace explicitly.) */ enum nl80211_scan_flags { NL80211_SCAN_FLAG_LOW_PRIORITY = 1<<0, @@ -5285,6 +5298,8 @@ enum nl80211_scan_flags { NL80211_SCAN_FLAG_LOW_SPAN = 1<<8, NL80211_SCAN_FLAG_LOW_POWER = 1<<9, NL80211_SCAN_FLAG_HIGH_ACCURACY = 1<<10, + NL80211_SCAN_FLAG_RANDOM_SN = 1<<11, + NL80211_SCAN_FLAG_MIN_PREQ_CONTENT = 1<<12, }; /** diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 6c3ded1223fb..d2677259e13e 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -6925,7 +6925,13 @@ nl80211_check_scan_flags(struct wiphy *wiphy, struct wireless_dev *wdev, NL80211_EXT_FEATURE_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION) || !nl80211_check_scan_feat(wiphy, *flags, NL80211_SCAN_FLAG_OCE_PROBE_REQ_HIGH_TX_RATE, - NL80211_EXT_FEATURE_OCE_PROBE_REQ_HIGH_TX_RATE)) + NL80211_EXT_FEATURE_OCE_PROBE_REQ_HIGH_TX_RATE) || + !nl80211_check_scan_feat(wiphy, *flags, + NL80211_SCAN_FLAG_RANDOM_SN, + NL80211_EXT_FEATURE_SCAN_RANDOM_SN) || + !nl80211_check_scan_feat(wiphy, *flags, + NL80211_SCAN_FLAG_MIN_PREQ_CONTENT, + NL80211_EXT_FEATURE_SCAN_MIN_PREQ_CONTENT)) return -EOPNOTSUPP; if (*flags & NL80211_SCAN_FLAG_RANDOM_ADDR) { -- cgit v1.2.3 From 2d4f545cb14fa2d9865124183f3100d46dc9b3b5 Mon Sep 17 00:00:00 2001 From: Peter Meerwald Date: Mon, 4 Jun 2018 23:34:06 +0200 Subject: rfkill: Fixes and cleanup of kernel-doc in the header file Fixes kerneldoc parameter names to match implementation, rfkill_set_hw_state(), rfkill_set_sw_state(). Fix description of rfkill_resume_polling(). Fix typos in documentation of rfkill_find_type(). Consistently start kerneldoc description with uppercase letter. Signed-off-by: Peter Meerwald-Stadler Signed-off-by: Johannes Berg --- include/linux/rfkill.h | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/rfkill.h b/include/linux/rfkill.h index e6a0031d1b1f..8ad2487a86d5 100644 --- a/include/linux/rfkill.h +++ b/include/linux/rfkill.h @@ -66,7 +66,7 @@ struct rfkill_ops { #if defined(CONFIG_RFKILL) || defined(CONFIG_RFKILL_MODULE) /** - * rfkill_alloc - allocate rfkill structure + * rfkill_alloc - Allocate rfkill structure * @name: name of the struct -- the string is not copied internally * @parent: device that has rf switch on it * @type: type of the switch (RFKILL_TYPE_*) @@ -112,7 +112,7 @@ void rfkill_pause_polling(struct rfkill *rfkill); /** * rfkill_resume_polling(struct rfkill *rfkill) * - * Pause polling -- say transmitter is off for other reasons. + * Resume polling * NOTE: not necessary for suspend/resume -- in that case the * core stops polling anyway */ @@ -130,7 +130,7 @@ void rfkill_resume_polling(struct rfkill *rfkill); void rfkill_unregister(struct rfkill *rfkill); /** - * rfkill_destroy - free rfkill structure + * rfkill_destroy - Free rfkill structure * @rfkill: rfkill structure to be destroyed * * Destroys the rfkill structure. @@ -140,7 +140,7 @@ void rfkill_destroy(struct rfkill *rfkill); /** * rfkill_set_hw_state - Set the internal rfkill hardware block state * @rfkill: pointer to the rfkill class to modify. - * @state: the current hardware block state to set + * @blocked: the current hardware block state to set * * rfkill drivers that get events when the hard-blocked state changes * use this function to notify the rfkill core (and through that also @@ -161,7 +161,7 @@ bool rfkill_set_hw_state(struct rfkill *rfkill, bool blocked); /** * rfkill_set_sw_state - Set the internal rfkill software block state * @rfkill: pointer to the rfkill class to modify. - * @state: the current software block state to set + * @blocked: the current software block state to set * * rfkill drivers that get events when the soft-blocked state changes * (yes, some platforms directly act on input but allow changing again) @@ -183,7 +183,7 @@ bool rfkill_set_sw_state(struct rfkill *rfkill, bool blocked); /** * rfkill_init_sw_state - Initialize persistent software block state * @rfkill: pointer to the rfkill class to modify. - * @state: the current software block state to set + * @blocked: the current software block state to set * * rfkill drivers that preserve their software block state over power off * use this function to notify the rfkill core (and through that also @@ -208,17 +208,17 @@ void rfkill_init_sw_state(struct rfkill *rfkill, bool blocked); void rfkill_set_states(struct rfkill *rfkill, bool sw, bool hw); /** - * rfkill_blocked - query rfkill block + * rfkill_blocked - Query rfkill block state * * @rfkill: rfkill struct to query */ bool rfkill_blocked(struct rfkill *rfkill); /** - * rfkill_find_type - Helpper for finding rfkill type by name + * rfkill_find_type - Helper for finding rfkill type by name * @name: the name of the type * - * Returns enum rfkill_type that conrresponds the name. + * Returns enum rfkill_type that corresponds to the name. */ enum rfkill_type rfkill_find_type(const char *name); @@ -296,7 +296,7 @@ static inline enum rfkill_type rfkill_find_type(const char *name) const char *rfkill_get_led_trigger_name(struct rfkill *rfkill); /** - * rfkill_set_led_trigger_name -- set the LED trigger name + * rfkill_set_led_trigger_name - Set the LED trigger name * @rfkill: rfkill struct * @name: LED trigger name * -- cgit v1.2.3 From c4cbaf7973a794839af080f13748335976cf3f3f Mon Sep 17 00:00:00 2001 From: Luca Coelho Date: Sat, 9 Jun 2018 09:14:42 +0300 Subject: cfg80211: Add support for HE Add support for the HE in cfg80211 and also add userspace API to nl80211 to send rate information out, conforming with P802.11ax_D2.0. Signed-off-by: Liad Kaufman Signed-off-by: Johannes Berg Signed-off-by: Ilan Peer Signed-off-by: Ido Yariv Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 427 +++++++++++++++++++++++++++++++++++++++++++ include/net/cfg80211.h | 106 ++++++++++- include/uapi/linux/nl80211.h | 87 ++++++++- net/wireless/core.c | 21 ++- net/wireless/nl80211.c | 99 +++++++++- net/wireless/util.c | 82 +++++++++ 6 files changed, 817 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 8fe7e4306816..e6a6503bfa33 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1539,6 +1539,106 @@ struct ieee80211_vht_operation { __le16 basic_mcs_set; } __packed; +/** + * struct ieee80211_he_cap_elem - HE capabilities element + * + * This structure is the "HE capabilities element" fixed fields as + * described in P802.11ax_D2.0 section 9.4.2.237.2 and 9.4.2.237.3 + */ +struct ieee80211_he_cap_elem { + u8 mac_cap_info[5]; + u8 phy_cap_info[9]; +} __packed; + +#define IEEE80211_TX_RX_MCS_NSS_DESC_MAX_LEN 5 + +/** + * enum ieee80211_he_mcs_support - HE MCS support definitions + * @IEEE80211_HE_MCS_SUPPORT_0_7: MCSes 0-7 are supported for the + * number of streams + * @IEEE80211_HE_MCS_SUPPORT_0_9: MCSes 0-9 are supported + * @IEEE80211_HE_MCS_SUPPORT_0_11: MCSes 0-11 are supported + * @IEEE80211_HE_MCS_NOT_SUPPORTED: This number of streams isn't supported + * + * These definitions are used in each 2-bit subfield of the rx_mcs_* + * and tx_mcs_* fields of &struct ieee80211_he_mcs_nss_supp, which are + * both split into 8 subfields by number of streams. These values indicate + * which MCSes are supported for the number of streams the value appears + * for. + */ +enum ieee80211_he_mcs_support { + IEEE80211_HE_MCS_SUPPORT_0_7 = 0, + IEEE80211_HE_MCS_SUPPORT_0_9 = 1, + IEEE80211_HE_MCS_SUPPORT_0_11 = 2, + IEEE80211_HE_MCS_NOT_SUPPORTED = 3, +}; + +/** + * struct ieee80211_he_mcs_nss_supp - HE Tx/Rx HE MCS NSS Support Field + * + * This structure holds the data required for the Tx/Rx HE MCS NSS Support Field + * described in P802.11ax_D2.0 section 9.4.2.237.4 + * + * @rx_mcs_80: Rx MCS map 2 bits for each stream, total 8 streams, for channel + * widths less than 80MHz. + * @tx_mcs_80: Tx MCS map 2 bits for each stream, total 8 streams, for channel + * widths less than 80MHz. + * @rx_mcs_160: Rx MCS map 2 bits for each stream, total 8 streams, for channel + * width 160MHz. + * @tx_mcs_160: Tx MCS map 2 bits for each stream, total 8 streams, for channel + * width 160MHz. + * @rx_mcs_80p80: Rx MCS map 2 bits for each stream, total 8 streams, for + * channel width 80p80MHz. + * @tx_mcs_80p80: Tx MCS map 2 bits for each stream, total 8 streams, for + * channel width 80p80MHz. + */ +struct ieee80211_he_mcs_nss_supp { + __le16 rx_mcs_80; + __le16 tx_mcs_80; + __le16 rx_mcs_160; + __le16 tx_mcs_160; + __le16 rx_mcs_80p80; + __le16 tx_mcs_80p80; +} __packed; + +/** + * struct ieee80211_he_operation - HE capabilities element + * + * This structure is the "HE operation element" fields as + * described in P802.11ax_D2.0 section 9.4.2.238 + */ +struct ieee80211_he_operation { + __le32 he_oper_params; + __le16 he_mcs_nss_set; + /* Optional 0,1,3 or 4 bytes: depends on @he_oper_params */ + u8 optional[0]; +} __packed; + +/** + * struct ieee80211_he_mu_edca_param_ac_rec - MU AC Parameter Record field + * + * This structure is the "MU AC Parameter Record" fields as + * described in P802.11ax_D2.0 section 9.4.2.240 + */ +struct ieee80211_he_mu_edca_param_ac_rec { + u8 aifsn; + u8 ecw_min_max; + u8 mu_edca_timer; +} __packed; + +/** + * struct ieee80211_mu_edca_param_set - MU EDCA Parameter Set element + * + * This structure is the "MU EDCA Parameter Set element" fields as + * described in P802.11ax_D2.0 section 9.4.2.240 + */ +struct ieee80211_mu_edca_param_set { + u8 mu_qos_info; + struct ieee80211_he_mu_edca_param_ac_rec ac_be; + struct ieee80211_he_mu_edca_param_ac_rec ac_bk; + struct ieee80211_he_mu_edca_param_ac_rec ac_vi; + struct ieee80211_he_mu_edca_param_ac_rec ac_vo; +} __packed; /* 802.11ac VHT Capabilities */ #define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895 0x00000000 @@ -1577,6 +1677,328 @@ struct ieee80211_vht_operation { #define IEEE80211_VHT_CAP_RX_ANTENNA_PATTERN 0x10000000 #define IEEE80211_VHT_CAP_TX_ANTENNA_PATTERN 0x20000000 +/* 802.11ax HE MAC capabilities */ +#define IEEE80211_HE_MAC_CAP0_HTC_HE 0x01 +#define IEEE80211_HE_MAC_CAP0_TWT_REQ 0x02 +#define IEEE80211_HE_MAC_CAP0_TWT_RES 0x04 +#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_NOT_SUPP 0x00 +#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_LEVEL_1 0x08 +#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_LEVEL_2 0x10 +#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_LEVEL_3 0x18 +#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_MASK 0x18 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_1 0x00 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_2 0x20 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_4 0x40 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_8 0x60 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_16 0x80 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_32 0xa0 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_64 0xc0 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_UNLIMITED 0xe0 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_MASK 0xe0 + +#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_UNLIMITED 0x00 +#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_128 0x01 +#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_256 0x02 +#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_512 0x03 +#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_MASK 0x03 +#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_0US 0x00 +#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_8US 0x04 +#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US 0x08 +#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_MASK 0x0c +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_1 0x00 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_2 0x10 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_3 0x20 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_4 0x30 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_5 0x40 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_6 0x50 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_7 0x60 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_8 0x70 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_MASK 0x70 + +/* Link adaptation is split between byte HE_MAC_CAP1 and + * HE_MAC_CAP2. It should be set only if IEEE80211_HE_MAC_CAP0_HTC_HE + * in which case the following values apply: + * 0 = No feedback. + * 1 = reserved. + * 2 = Unsolicited feedback. + * 3 = both + */ +#define IEEE80211_HE_MAC_CAP1_LINK_ADAPTATION 0x80 + +#define IEEE80211_HE_MAC_CAP2_LINK_ADAPTATION 0x01 +#define IEEE80211_HE_MAC_CAP2_ALL_ACK 0x02 +#define IEEE80211_HE_MAC_CAP2_UL_MU_RESP_SCHED 0x04 +#define IEEE80211_HE_MAC_CAP2_BSR 0x08 +#define IEEE80211_HE_MAC_CAP2_BCAST_TWT 0x10 +#define IEEE80211_HE_MAC_CAP2_32BIT_BA_BITMAP 0x20 +#define IEEE80211_HE_MAC_CAP2_MU_CASCADING 0x40 +#define IEEE80211_HE_MAC_CAP2_ACK_EN 0x80 + +#define IEEE80211_HE_MAC_CAP3_GRP_ADDR_MULTI_STA_BA_DL_MU 0x01 +#define IEEE80211_HE_MAC_CAP3_OMI_CONTROL 0x02 +#define IEEE80211_HE_MAC_CAP3_OFDMA_RA 0x04 + +/* The maximum length of an A-MDPU is defined by the combination of the Maximum + * A-MDPU Length Exponent field in the HT capabilities, VHT capabilities and the + * same field in the HE capabilities. + */ +#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_USE_VHT 0x00 +#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_VHT_1 0x08 +#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_VHT_2 0x10 +#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_RESERVED 0x18 +#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_MASK 0x18 +#define IEEE80211_HE_MAC_CAP3_A_AMSDU_FRAG 0x20 +#define IEEE80211_HE_MAC_CAP3_FLEX_TWT_SCHED 0x40 +#define IEEE80211_HE_MAC_CAP3_RX_CTRL_FRAME_TO_MULTIBSS 0x80 + +#define IEEE80211_HE_MAC_CAP4_BSRP_BQRP_A_MPDU_AGG 0x01 +#define IEEE80211_HE_MAC_CAP4_QTP 0x02 +#define IEEE80211_HE_MAC_CAP4_BQR 0x04 +#define IEEE80211_HE_MAC_CAP4_SR_RESP 0x08 +#define IEEE80211_HE_MAC_CAP4_NDP_FB_REP 0x10 +#define IEEE80211_HE_MAC_CAP4_OPS 0x20 +#define IEEE80211_HE_MAC_CAP4_AMDSU_IN_AMPDU 0x40 + +/* 802.11ax HE PHY capabilities */ +#define IEEE80211_HE_PHY_CAP0_DUAL_BAND 0x01 +#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G 0x02 +#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G 0x04 +#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G 0x08 +#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G 0x10 +#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_RU_MAPPING_IN_2G 0x20 +#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_RU_MAPPING_IN_5G 0x40 +#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_MASK 0xfe + +#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_80MHZ_ONLY_SECOND_20MHZ 0x01 +#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_80MHZ_ONLY_SECOND_40MHZ 0x02 +#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_160MHZ_ONLY_SECOND_20MHZ 0x04 +#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_160MHZ_ONLY_SECOND_40MHZ 0x08 +#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK 0x0f +#define IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A 0x10 +#define IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD 0x20 +#define IEEE80211_HE_PHY_CAP1_HE_LTF_AND_GI_FOR_HE_PPDUS_0_8US 0x40 +/* Midamble RX Max NSTS is split between byte #2 and byte #3 */ +#define IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_MAX_NSTS 0x80 + +#define IEEE80211_HE_PHY_CAP2_MIDAMBLE_RX_MAX_NSTS 0x01 +#define IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US 0x02 +#define IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ 0x04 +#define IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ 0x08 +#define IEEE80211_HE_PHY_CAP2_DOPPLER_TX 0x10 +#define IEEE80211_HE_PHY_CAP2_DOPPLER_RX 0x20 + +/* Note that the meaning of UL MU below is different between an AP and a non-AP + * sta, where in the AP case it indicates support for Rx and in the non-AP sta + * case it indicates support for Tx. + */ +#define IEEE80211_HE_PHY_CAP2_UL_MU_FULL_MU_MIMO 0x40 +#define IEEE80211_HE_PHY_CAP2_UL_MU_PARTIAL_MU_MIMO 0x80 + +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_NO_DCM 0x00 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_BPSK 0x01 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_QPSK 0x02 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_16_QAM 0x03 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_MASK 0x03 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_TX_NSS_1 0x00 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_TX_NSS_2 0x04 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_NO_DCM 0x00 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_BPSK 0x08 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_QPSK 0x10 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_16_QAM 0x18 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_MASK 0x18 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_RX_NSS_1 0x00 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_RX_NSS_2 0x20 +#define IEEE80211_HE_PHY_CAP3_RX_HE_MU_PPDU_FROM_NON_AP_STA 0x40 +#define IEEE80211_HE_PHY_CAP3_SU_BEAMFORMER 0x80 + +#define IEEE80211_HE_PHY_CAP4_SU_BEAMFORMEE 0x01 +#define IEEE80211_HE_PHY_CAP4_MU_BEAMFORMER 0x02 + +/* Minimal allowed value of Max STS under 80MHz is 3 */ +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_4 0x0c +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_5 0x10 +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_6 0x14 +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_7 0x18 +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_8 0x1c +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_MASK 0x1c + +/* Minimal allowed value of Max STS above 80MHz is 3 */ +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_4 0x60 +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_5 0x80 +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_6 0xa0 +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_7 0xc0 +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_8 0xe0 +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_MASK 0xe0 + +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_1 0x00 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_2 0x01 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_3 0x02 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_4 0x03 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_5 0x04 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_6 0x05 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_7 0x06 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_8 0x07 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_MASK 0x07 + +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_1 0x00 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_2 0x08 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_3 0x10 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_4 0x18 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_5 0x20 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_6 0x28 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_7 0x30 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_8 0x38 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_MASK 0x38 + +#define IEEE80211_HE_PHY_CAP5_NG16_SU_FEEDBACK 0x40 +#define IEEE80211_HE_PHY_CAP5_NG16_MU_FEEDBACK 0x80 + +#define IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_42_SU 0x01 +#define IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_75_MU 0x02 +#define IEEE80211_HE_PHY_CAP6_TRIG_SU_BEAMFORMER_FB 0x04 +#define IEEE80211_HE_PHY_CAP6_TRIG_MU_BEAMFORMER_FB 0x08 +#define IEEE80211_HE_PHY_CAP6_TRIG_CQI_FB 0x10 +#define IEEE80211_HE_PHY_CAP6_PARTIAL_BW_EXT_RANGE 0x20 +#define IEEE80211_HE_PHY_CAP6_PARTIAL_BANDWIDTH_DL_MUMIMO 0x40 +#define IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT 0x80 + +#define IEEE80211_HE_PHY_CAP7_SRP_BASED_SR 0x01 +#define IEEE80211_HE_PHY_CAP7_POWER_BOOST_FACTOR_AR 0x02 +#define IEEE80211_HE_PHY_CAP7_HE_SU_MU_PPDU_4XLTF_AND_08_US_GI 0x04 +#define IEEE80211_HE_PHY_CAP7_MAX_NC_1 0x08 +#define IEEE80211_HE_PHY_CAP7_MAX_NC_2 0x10 +#define IEEE80211_HE_PHY_CAP7_MAX_NC_3 0x18 +#define IEEE80211_HE_PHY_CAP7_MAX_NC_4 0x20 +#define IEEE80211_HE_PHY_CAP7_MAX_NC_5 0x28 +#define IEEE80211_HE_PHY_CAP7_MAX_NC_6 0x30 +#define IEEE80211_HE_PHY_CAP7_MAX_NC_7 0x38 +#define IEEE80211_HE_PHY_CAP7_MAX_NC_MASK 0x38 +#define IEEE80211_HE_PHY_CAP7_STBC_TX_ABOVE_80MHZ 0x40 +#define IEEE80211_HE_PHY_CAP7_STBC_RX_ABOVE_80MHZ 0x80 + +#define IEEE80211_HE_PHY_CAP8_HE_ER_SU_PPDU_4XLTF_AND_08_US_GI 0x01 +#define IEEE80211_HE_PHY_CAP8_20MHZ_IN_40MHZ_HE_PPDU_IN_2G 0x02 +#define IEEE80211_HE_PHY_CAP8_20MHZ_IN_160MHZ_HE_PPDU 0x04 +#define IEEE80211_HE_PHY_CAP8_80MHZ_IN_160MHZ_HE_PPDU 0x08 +#define IEEE80211_HE_PHY_CAP8_HE_ER_SU_1XLTF_AND_08_US_GI 0x10 +#define IEEE80211_HE_PHY_CAP8_MIDAMBLE_RX_2X_AND_1XLTF 0x20 + +/* 802.11ax HE TX/RX MCS NSS Support */ +#define IEEE80211_TX_RX_MCS_NSS_SUPP_HIGHEST_MCS_POS (3) +#define IEEE80211_TX_RX_MCS_NSS_SUPP_TX_BITMAP_POS (6) +#define IEEE80211_TX_RX_MCS_NSS_SUPP_RX_BITMAP_POS (11) +#define IEEE80211_TX_RX_MCS_NSS_SUPP_TX_BITMAP_MASK 0x07c0 +#define IEEE80211_TX_RX_MCS_NSS_SUPP_RX_BITMAP_MASK 0xf800 + +/* TX/RX HE MCS Support field Highest MCS subfield encoding */ +enum ieee80211_he_highest_mcs_supported_subfield_enc { + HIGHEST_MCS_SUPPORTED_MCS7 = 0, + HIGHEST_MCS_SUPPORTED_MCS8, + HIGHEST_MCS_SUPPORTED_MCS9, + HIGHEST_MCS_SUPPORTED_MCS10, + HIGHEST_MCS_SUPPORTED_MCS11, +}; + +/* Calculate 802.11ax HE capabilities IE Tx/Rx HE MCS NSS Support Field size */ +static inline u8 +ieee80211_he_mcs_nss_size(const struct ieee80211_he_cap_elem *he_cap) +{ + u8 count = 4; + + if (he_cap->phy_cap_info[0] & + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G) + count += 4; + + if (he_cap->phy_cap_info[0] & + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G) + count += 4; + + return count; +} + +/* 802.11ax HE PPE Thresholds */ +#define IEEE80211_PPE_THRES_NSS_SUPPORT_2NSS (1) +#define IEEE80211_PPE_THRES_NSS_POS (0) +#define IEEE80211_PPE_THRES_NSS_MASK (7) +#define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_2x966_AND_966_RU \ + (BIT(5) | BIT(6)) +#define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_MASK 0x78 +#define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_POS (3) +#define IEEE80211_PPE_THRES_INFO_PPET_SIZE (3) + +/* + * Calculate 802.11ax HE capabilities IE PPE field size + * Input: Header byte of ppe_thres (first byte), and HE capa IE's PHY cap u8* + */ +static inline u8 +ieee80211_he_ppe_size(u8 ppe_thres_hdr, const u8 *phy_cap_info) +{ + u8 n; + + if ((phy_cap_info[6] & + IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT) == 0) + return 0; + + n = hweight8(ppe_thres_hdr & + IEEE80211_PPE_THRES_RU_INDEX_BITMASK_MASK); + n *= (1 + ((ppe_thres_hdr & IEEE80211_PPE_THRES_NSS_MASK) >> + IEEE80211_PPE_THRES_NSS_POS)); + + /* + * Each pair is 6 bits, and we need to add the 7 "header" bits to the + * total size. + */ + n = (n * IEEE80211_PPE_THRES_INFO_PPET_SIZE * 2) + 7; + n = DIV_ROUND_UP(n, 8); + + return n; +} + +/* HE Operation defines */ +#define IEEE80211_HE_OPERATION_BSS_COLOR_MASK 0x0000003f +#define IEEE80211_HE_OPERATION_DFLT_PE_DURATION_MASK 0x000001c0 +#define IEEE80211_HE_OPERATION_DFLT_PE_DURATION_OFFSET 6 +#define IEEE80211_HE_OPERATION_TWT_REQUIRED 0x00000200 +#define IEEE80211_HE_OPERATION_RTS_THRESHOLD_MASK 0x000ffc00 +#define IEEE80211_HE_OPERATION_RTS_THRESHOLD_OFFSET 10 +#define IEEE80211_HE_OPERATION_PARTIAL_BSS_COLOR 0x000100000 +#define IEEE80211_HE_OPERATION_VHT_OPER_INFO 0x000200000 +#define IEEE80211_HE_OPERATION_MULTI_BSSID_AP 0x10000000 +#define IEEE80211_HE_OPERATION_TX_BSSID_INDICATOR 0x20000000 +#define IEEE80211_HE_OPERATION_BSS_COLOR_DISABLED 0x40000000 + +/* + * ieee80211_he_oper_size - calculate 802.11ax HE Operations IE size + * @he_oper_ie: byte data of the He Operations IE, stating from the the byte + * after the ext ID byte. It is assumed that he_oper_ie has at least + * sizeof(struct ieee80211_he_operation) bytes, checked already in + * ieee802_11_parse_elems_crc() + * @return the actual size of the IE data (not including header), or 0 on error + */ +static inline u8 +ieee80211_he_oper_size(const u8 *he_oper_ie) +{ + struct ieee80211_he_operation *he_oper = (void *)he_oper_ie; + u8 oper_len = sizeof(struct ieee80211_he_operation); + u32 he_oper_params; + + /* Make sure the input is not NULL */ + if (!he_oper_ie) + return 0; + + /* Calc required length */ + he_oper_params = le32_to_cpu(he_oper->he_oper_params); + if (he_oper_params & IEEE80211_HE_OPERATION_VHT_OPER_INFO) + oper_len += 3; + if (he_oper_params & IEEE80211_HE_OPERATION_MULTI_BSSID_AP) + oper_len++; + + /* Add the first byte (extension ID) to the total length */ + oper_len++; + + return oper_len; +} + /* Authentication algorithms */ #define WLAN_AUTH_OPEN 0 #define WLAN_AUTH_SHARED_KEY 1 @@ -1992,6 +2414,11 @@ enum ieee80211_eid_ext { WLAN_EID_EXT_FILS_WRAPPED_DATA = 8, WLAN_EID_EXT_FILS_PUBLIC_KEY = 12, WLAN_EID_EXT_FILS_NONCE = 13, + WLAN_EID_EXT_FUTURE_CHAN_GUIDANCE = 14, + WLAN_EID_EXT_HE_CAPABILITY = 35, + WLAN_EID_EXT_HE_OPERATION = 36, + WLAN_EID_EXT_UORA = 37, + WLAN_EID_EXT_HE_MU_EDCA = 38, }; /* Action category code */ diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 5fbfe61f41c6..9ba1f289c439 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -285,6 +285,41 @@ struct ieee80211_sta_vht_cap { struct ieee80211_vht_mcs_info vht_mcs; }; +#define IEEE80211_HE_PPE_THRES_MAX_LEN 25 + +/** + * struct ieee80211_sta_he_cap - STA's HE capabilities + * + * This structure describes most essential parameters needed + * to describe 802.11ax HE capabilities for a STA. + * + * @has_he: true iff HE data is valid. + * @he_cap_elem: Fixed portion of the HE capabilities element. + * @he_mcs_nss_supp: The supported NSS/MCS combinations. + * @ppe_thres: Holds the PPE Thresholds data. + */ +struct ieee80211_sta_he_cap { + bool has_he; + struct ieee80211_he_cap_elem he_cap_elem; + struct ieee80211_he_mcs_nss_supp he_mcs_nss_supp; + u8 ppe_thres[IEEE80211_HE_PPE_THRES_MAX_LEN]; +}; + +/** + * struct ieee80211_sband_iftype_data + * + * This structure encapsulates sband data that is relevant for the + * interface types defined in @types_mask. Each type in the + * @types_mask must be unique across all instances of iftype_data. + * + * @types_mask: interface types mask + * @he_cap: holds the HE capabilities + */ +struct ieee80211_sband_iftype_data { + u16 types_mask; + struct ieee80211_sta_he_cap he_cap; +}; + /** * struct ieee80211_supported_band - frequency band definition * @@ -301,6 +336,11 @@ struct ieee80211_sta_vht_cap { * @n_bitrates: Number of bitrates in @bitrates * @ht_cap: HT capabilities in this band * @vht_cap: VHT capabilities in this band + * @n_iftype_data: number of iftype data entries + * @iftype_data: interface type data entries. Note that the bits in + * @types_mask inside this structure cannot overlap (i.e. only + * one occurrence of each type is allowed across all instances of + * iftype_data). */ struct ieee80211_supported_band { struct ieee80211_channel *channels; @@ -310,8 +350,55 @@ struct ieee80211_supported_band { int n_bitrates; struct ieee80211_sta_ht_cap ht_cap; struct ieee80211_sta_vht_cap vht_cap; + u16 n_iftype_data; + const struct ieee80211_sband_iftype_data *iftype_data; }; +/** + * ieee80211_get_sband_iftype_data - return sband data for a given iftype + * @sband: the sband to search for the STA on + * @iftype: enum nl80211_iftype + * + * Return: pointer to struct ieee80211_sband_iftype_data, or NULL is none found + */ +static inline const struct ieee80211_sband_iftype_data * +ieee80211_get_sband_iftype_data(const struct ieee80211_supported_band *sband, + u8 iftype) +{ + int i; + + if (WARN_ON(iftype >= NL80211_IFTYPE_MAX)) + return NULL; + + for (i = 0; i < sband->n_iftype_data; i++) { + const struct ieee80211_sband_iftype_data *data = + &sband->iftype_data[i]; + + if (data->types_mask & BIT(iftype)) + return data; + } + + return NULL; +} + +/** + * ieee80211_get_he_sta_cap - return HE capabilities for an sband's STA + * @sband: the sband to search for the STA on + * + * Return: pointer to the struct ieee80211_sta_he_cap, or NULL is none found + */ +static inline const struct ieee80211_sta_he_cap * +ieee80211_get_he_sta_cap(const struct ieee80211_supported_band *sband) +{ + const struct ieee80211_sband_iftype_data *data = + ieee80211_get_sband_iftype_data(sband, NL80211_IFTYPE_STATION); + + if (data && data->he_cap.has_he) + return &data->he_cap; + + return NULL; +} + /** * wiphy_read_of_freq_limits - read frequency limits from device tree * @@ -899,6 +986,8 @@ enum station_parameters_apply_mask { * @opmode_notif: operating mode field from Operating Mode Notification * @opmode_notif_used: information if operating mode field is used * @support_p2p_ps: information if station supports P2P PS mechanism + * @he_capa: HE capabilities of station + * @he_capa_len: the length of the HE capabilities */ struct station_parameters { const u8 *supported_rates; @@ -926,6 +1015,8 @@ struct station_parameters { u8 opmode_notif; bool opmode_notif_used; int support_p2p_ps; + const struct ieee80211_he_cap_elem *he_capa; + u8 he_capa_len; }; /** @@ -1000,12 +1091,14 @@ int cfg80211_check_station_change(struct wiphy *wiphy, * @RATE_INFO_FLAGS_VHT_MCS: mcs field filled with VHT MCS * @RATE_INFO_FLAGS_SHORT_GI: 400ns guard interval * @RATE_INFO_FLAGS_60G: 60GHz MCS + * @RATE_INFO_FLAGS_HE_MCS: HE MCS information */ enum rate_info_flags { RATE_INFO_FLAGS_MCS = BIT(0), RATE_INFO_FLAGS_VHT_MCS = BIT(1), RATE_INFO_FLAGS_SHORT_GI = BIT(2), RATE_INFO_FLAGS_60G = BIT(3), + RATE_INFO_FLAGS_HE_MCS = BIT(4), }; /** @@ -1019,6 +1112,7 @@ enum rate_info_flags { * @RATE_INFO_BW_40: 40 MHz bandwidth * @RATE_INFO_BW_80: 80 MHz bandwidth * @RATE_INFO_BW_160: 160 MHz bandwidth + * @RATE_INFO_BW_HE_RU: bandwidth determined by HE RU allocation */ enum rate_info_bw { RATE_INFO_BW_20 = 0, @@ -1027,6 +1121,7 @@ enum rate_info_bw { RATE_INFO_BW_40, RATE_INFO_BW_80, RATE_INFO_BW_160, + RATE_INFO_BW_HE_RU, }; /** @@ -1035,10 +1130,14 @@ enum rate_info_bw { * Information about a receiving or transmitting bitrate * * @flags: bitflag of flags from &enum rate_info_flags - * @mcs: mcs index if struct describes a 802.11n bitrate + * @mcs: mcs index if struct describes an HT/VHT/HE rate * @legacy: bitrate in 100kbit/s for 802.11abg - * @nss: number of streams (VHT only) + * @nss: number of streams (VHT & HE only) * @bw: bandwidth (from &enum rate_info_bw) + * @he_gi: HE guard interval (from &enum nl80211_he_gi) + * @he_dcm: HE DCM value + * @he_ru_alloc: HE RU allocation (from &enum nl80211_he_ru_alloc, + * only valid if bw is %RATE_INFO_BW_HE_RU) */ struct rate_info { u8 flags; @@ -1046,6 +1145,9 @@ struct rate_info { u16 legacy; u8 nss; u8 bw; + u8 he_gi; + u8 he_dcm; + u8 he_ru_alloc; }; /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 49f718e821a3..f82ce3c89ab7 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -2237,6 +2237,9 @@ enum nl80211_commands { * enforced. * @NL80211_ATTR_TXQ_QUANTUM: TXQ scheduler quantum (bytes). Number of bytes * a flow is assigned on each round of the DRR scheduler. + * @NL80211_ATTR_HE_CAPABILITY: HE Capability information element (from + * association request when used with NL80211_CMD_NEW_STATION). Can be set + * only if %NL80211_STA_FLAG_WME is set. * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined @@ -2677,6 +2680,8 @@ enum nl80211_attrs { NL80211_ATTR_TXQ_MEMORY_LIMIT, NL80211_ATTR_TXQ_QUANTUM, + NL80211_ATTR_HE_CAPABILITY, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -2726,7 +2731,8 @@ enum nl80211_attrs { #define NL80211_TKIP_DATA_OFFSET_RX_MIC_KEY 24 #define NL80211_HT_CAPABILITY_LEN 26 #define NL80211_VHT_CAPABILITY_LEN 12 - +#define NL80211_HE_MIN_CAPABILITY_LEN 16 +#define NL80211_HE_MAX_CAPABILITY_LEN 51 #define NL80211_MAX_NR_CIPHER_SUITES 5 #define NL80211_MAX_NR_AKM_SUITES 2 @@ -2853,6 +2859,38 @@ struct nl80211_sta_flag_update { __u32 set; } __attribute__((packed)); +/** + * enum nl80211_he_gi - HE guard interval + * @NL80211_RATE_INFO_HE_GI_0_8: 0.8 usec + * @NL80211_RATE_INFO_HE_GI_1_6: 1.6 usec + * @NL80211_RATE_INFO_HE_GI_3_2: 3.2 usec + */ +enum nl80211_he_gi { + NL80211_RATE_INFO_HE_GI_0_8, + NL80211_RATE_INFO_HE_GI_1_6, + NL80211_RATE_INFO_HE_GI_3_2, +}; + +/** + * enum nl80211_he_ru_alloc - HE RU allocation values + * @NL80211_RATE_INFO_HE_RU_ALLOC_26: 26-tone RU allocation + * @NL80211_RATE_INFO_HE_RU_ALLOC_52: 52-tone RU allocation + * @NL80211_RATE_INFO_HE_RU_ALLOC_106: 106-tone RU allocation + * @NL80211_RATE_INFO_HE_RU_ALLOC_242: 242-tone RU allocation + * @NL80211_RATE_INFO_HE_RU_ALLOC_484: 484-tone RU allocation + * @NL80211_RATE_INFO_HE_RU_ALLOC_996: 996-tone RU allocation + * @NL80211_RATE_INFO_HE_RU_ALLOC_2x996: 2x996-tone RU allocation + */ +enum nl80211_he_ru_alloc { + NL80211_RATE_INFO_HE_RU_ALLOC_26, + NL80211_RATE_INFO_HE_RU_ALLOC_52, + NL80211_RATE_INFO_HE_RU_ALLOC_106, + NL80211_RATE_INFO_HE_RU_ALLOC_242, + NL80211_RATE_INFO_HE_RU_ALLOC_484, + NL80211_RATE_INFO_HE_RU_ALLOC_996, + NL80211_RATE_INFO_HE_RU_ALLOC_2x996, +}; + /** * enum nl80211_rate_info - bitrate information * @@ -2885,6 +2923,13 @@ struct nl80211_sta_flag_update { * @NL80211_RATE_INFO_5_MHZ_WIDTH: 5 MHz width - note that this is * a legacy rate and will be reported as the actual bitrate, i.e. * a quarter of the base (20 MHz) rate + * @NL80211_RATE_INFO_HE_MCS: HE MCS index (u8, 0-11) + * @NL80211_RATE_INFO_HE_NSS: HE NSS value (u8, 1-8) + * @NL80211_RATE_INFO_HE_GI: HE guard interval identifier + * (u8, see &enum nl80211_he_gi) + * @NL80211_RATE_INFO_HE_DCM: HE DCM value (u8, 0/1) + * @NL80211_RATE_INFO_RU_ALLOC: HE RU allocation, if not present then + * non-OFDMA was used (u8, see &enum nl80211_he_ru_alloc) * @__NL80211_RATE_INFO_AFTER_LAST: internal use */ enum nl80211_rate_info { @@ -2901,6 +2946,11 @@ enum nl80211_rate_info { NL80211_RATE_INFO_160_MHZ_WIDTH, NL80211_RATE_INFO_10_MHZ_WIDTH, NL80211_RATE_INFO_5_MHZ_WIDTH, + NL80211_RATE_INFO_HE_MCS, + NL80211_RATE_INFO_HE_NSS, + NL80211_RATE_INFO_HE_GI, + NL80211_RATE_INFO_HE_DCM, + NL80211_RATE_INFO_HE_RU_ALLOC, /* keep last */ __NL80211_RATE_INFO_AFTER_LAST, @@ -3166,6 +3216,38 @@ enum nl80211_mpath_info { NL80211_MPATH_INFO_MAX = __NL80211_MPATH_INFO_AFTER_LAST - 1 }; +/** + * enum nl80211_band_iftype_attr - Interface type data attributes + * + * @__NL80211_BAND_IFTYPE_ATTR_INVALID: attribute number 0 is reserved + * @NL80211_BAND_IFTYPE_ATTR_IFTYPES: nested attribute containing a flag attribute + * for each interface type that supports the band data + * @NL80211_BAND_IFTYPE_ATTR_HE_CAP_MAC: HE MAC capabilities as in HE + * capabilities IE + * @NL80211_BAND_IFTYPE_ATTR_HE_CAP_PHY: HE PHY capabilities as in HE + * capabilities IE + * @NL80211_BAND_IFTYPE_ATTR_HE_CAP_MCS_SET: HE supported NSS/MCS as in HE + * capabilities IE + * @NL80211_BAND_IFTYPE_ATTR_HE_CAP_PPE: HE PPE thresholds information as + * defined in HE capabilities IE + * @NL80211_BAND_IFTYPE_ATTR_MAX: highest band HE capability attribute currently + * defined + * @__NL80211_BAND_IFTYPE_ATTR_AFTER_LAST: internal use + */ +enum nl80211_band_iftype_attr { + __NL80211_BAND_IFTYPE_ATTR_INVALID, + + NL80211_BAND_IFTYPE_ATTR_IFTYPES, + NL80211_BAND_IFTYPE_ATTR_HE_CAP_MAC, + NL80211_BAND_IFTYPE_ATTR_HE_CAP_PHY, + NL80211_BAND_IFTYPE_ATTR_HE_CAP_MCS_SET, + NL80211_BAND_IFTYPE_ATTR_HE_CAP_PPE, + + /* keep last */ + __NL80211_BAND_IFTYPE_ATTR_AFTER_LAST, + NL80211_BAND_IFTYPE_ATTR_MAX = __NL80211_BAND_IFTYPE_ATTR_AFTER_LAST - 1 +}; + /** * enum nl80211_band_attr - band attributes * @__NL80211_BAND_ATTR_INVALID: attribute number 0 is reserved @@ -3181,6 +3263,8 @@ enum nl80211_mpath_info { * @NL80211_BAND_ATTR_VHT_MCS_SET: 32-byte attribute containing the MCS set as * defined in 802.11ac * @NL80211_BAND_ATTR_VHT_CAPA: VHT capabilities, as in the HT information IE + * @NL80211_BAND_ATTR_IFTYPE_DATA: nested array attribute, with each entry using + * attributes from &enum nl80211_band_iftype_attr * @NL80211_BAND_ATTR_MAX: highest band attribute currently defined * @__NL80211_BAND_ATTR_AFTER_LAST: internal use */ @@ -3196,6 +3280,7 @@ enum nl80211_band_attr { NL80211_BAND_ATTR_VHT_MCS_SET, NL80211_BAND_ATTR_VHT_CAPA, + NL80211_BAND_ATTR_IFTYPE_DATA, /* keep last */ __NL80211_BAND_ATTR_AFTER_LAST, diff --git a/net/wireless/core.c b/net/wireless/core.c index 5fe35aafdd9c..d23abc619e77 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -3,7 +3,7 @@ * * Copyright 2006-2010 Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH - * Copyright 2015 Intel Deutschland GmbH + * Copyright 2015-2017 Intel Deutschland GmbH */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -744,6 +744,8 @@ int wiphy_register(struct wiphy *wiphy) /* sanity check supported bands/channels */ for (band = 0; band < NUM_NL80211_BANDS; band++) { + u16 types = 0; + sband = wiphy->bands[band]; if (!sband) continue; @@ -788,6 +790,23 @@ int wiphy_register(struct wiphy *wiphy) sband->channels[i].band = band; } + for (i = 0; i < sband->n_iftype_data; i++) { + const struct ieee80211_sband_iftype_data *iftd; + + iftd = &sband->iftype_data[i]; + + if (WARN_ON(!iftd->types_mask)) + return -EINVAL; + if (WARN_ON(types & iftd->types_mask)) + return -EINVAL; + + /* at least one piece of information must be present */ + if (WARN_ON(!iftd->he_cap.has_he)) + return -EINVAL; + + types |= iftd->types_mask; + } + have_band = true; } diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 7b21914ae18b..0ccce338a66e 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -428,6 +428,8 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_TXQ_LIMIT] = { .type = NLA_U32 }, [NL80211_ATTR_TXQ_MEMORY_LIMIT] = { .type = NLA_U32 }, [NL80211_ATTR_TXQ_QUANTUM] = { .type = NLA_U32 }, + [NL80211_ATTR_HE_CAPABILITY] = { .type = NLA_BINARY, + .len = NL80211_HE_MAX_CAPABILITY_LEN }, }; /* policy for the key attributes */ @@ -1324,6 +1326,34 @@ static int nl80211_send_coalesce(struct sk_buff *msg, return 0; } +static int +nl80211_send_iftype_data(struct sk_buff *msg, + const struct ieee80211_sband_iftype_data *iftdata) +{ + const struct ieee80211_sta_he_cap *he_cap = &iftdata->he_cap; + + if (nl80211_put_iftypes(msg, NL80211_BAND_IFTYPE_ATTR_IFTYPES, + iftdata->types_mask)) + return -ENOBUFS; + + if (he_cap->has_he) { + if (nla_put(msg, NL80211_BAND_IFTYPE_ATTR_HE_CAP_MAC, + sizeof(he_cap->he_cap_elem.mac_cap_info), + he_cap->he_cap_elem.mac_cap_info) || + nla_put(msg, NL80211_BAND_IFTYPE_ATTR_HE_CAP_PHY, + sizeof(he_cap->he_cap_elem.phy_cap_info), + he_cap->he_cap_elem.phy_cap_info) || + nla_put(msg, NL80211_BAND_IFTYPE_ATTR_HE_CAP_MCS_SET, + sizeof(he_cap->he_mcs_nss_supp), + &he_cap->he_mcs_nss_supp) || + nla_put(msg, NL80211_BAND_IFTYPE_ATTR_HE_CAP_PPE, + sizeof(he_cap->ppe_thres), he_cap->ppe_thres)) + return -ENOBUFS; + } + + return 0; +} + static int nl80211_send_band_rateinfo(struct sk_buff *msg, struct ieee80211_supported_band *sband) { @@ -1353,6 +1383,32 @@ static int nl80211_send_band_rateinfo(struct sk_buff *msg, sband->vht_cap.cap))) return -ENOBUFS; + if (sband->n_iftype_data) { + struct nlattr *nl_iftype_data = + nla_nest_start(msg, NL80211_BAND_ATTR_IFTYPE_DATA); + int err; + + if (!nl_iftype_data) + return -ENOBUFS; + + for (i = 0; i < sband->n_iftype_data; i++) { + struct nlattr *iftdata; + + iftdata = nla_nest_start(msg, i + 1); + if (!iftdata) + return -ENOBUFS; + + err = nl80211_send_iftype_data(msg, + &sband->iftype_data[i]); + if (err) + return err; + + nla_nest_end(msg, iftdata); + } + + nla_nest_end(msg, nl_iftype_data); + } + /* add bitrates */ nl_rates = nla_nest_start(msg, NL80211_BAND_ATTR_RATES); if (!nl_rates) @@ -4472,6 +4528,9 @@ static bool nl80211_put_sta_rate(struct sk_buff *msg, struct rate_info *info, case RATE_INFO_BW_160: rate_flg = NL80211_RATE_INFO_160_MHZ_WIDTH; break; + case RATE_INFO_BW_HE_RU: + rate_flg = 0; + WARN_ON(!(info->flags & RATE_INFO_FLAGS_HE_MCS)); } if (rate_flg && nla_put_flag(msg, rate_flg)) @@ -4491,6 +4550,19 @@ static bool nl80211_put_sta_rate(struct sk_buff *msg, struct rate_info *info, if (info->flags & RATE_INFO_FLAGS_SHORT_GI && nla_put_flag(msg, NL80211_RATE_INFO_SHORT_GI)) return false; + } else if (info->flags & RATE_INFO_FLAGS_HE_MCS) { + if (nla_put_u8(msg, NL80211_RATE_INFO_HE_MCS, info->mcs)) + return false; + if (nla_put_u8(msg, NL80211_RATE_INFO_HE_NSS, info->nss)) + return false; + if (nla_put_u8(msg, NL80211_RATE_INFO_HE_GI, info->he_gi)) + return false; + if (nla_put_u8(msg, NL80211_RATE_INFO_HE_DCM, info->he_dcm)) + return false; + if (info->bw == RATE_INFO_BW_HE_RU && + nla_put_u8(msg, NL80211_RATE_INFO_HE_RU_ALLOC, + info->he_ru_alloc)) + return false; } nla_nest_end(msg, rate); @@ -4887,7 +4959,8 @@ int cfg80211_check_station_change(struct wiphy *wiphy, return -EINVAL; if (params->supported_rates) return -EINVAL; - if (params->ext_capab || params->ht_capa || params->vht_capa) + if (params->ext_capab || params->ht_capa || params->vht_capa || + params->he_capa) return -EINVAL; } @@ -5093,6 +5166,15 @@ static int nl80211_set_station_tdls(struct genl_info *info, if (info->attrs[NL80211_ATTR_VHT_CAPABILITY]) params->vht_capa = nla_data(info->attrs[NL80211_ATTR_VHT_CAPABILITY]); + if (info->attrs[NL80211_ATTR_HE_CAPABILITY]) { + params->he_capa = + nla_data(info->attrs[NL80211_ATTR_HE_CAPABILITY]); + params->he_capa_len = + nla_len(info->attrs[NL80211_ATTR_HE_CAPABILITY]); + + if (params->he_capa_len < NL80211_HE_MIN_CAPABILITY_LEN) + return -EINVAL; + } err = nl80211_parse_sta_channel_info(info, params); if (err) @@ -5320,6 +5402,17 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) params.vht_capa = nla_data(info->attrs[NL80211_ATTR_VHT_CAPABILITY]); + if (info->attrs[NL80211_ATTR_HE_CAPABILITY]) { + params.he_capa = + nla_data(info->attrs[NL80211_ATTR_HE_CAPABILITY]); + params.he_capa_len = + nla_len(info->attrs[NL80211_ATTR_HE_CAPABILITY]); + + /* max len is validated in nla policy */ + if (params.he_capa_len < NL80211_HE_MIN_CAPABILITY_LEN) + return -EINVAL; + } + if (info->attrs[NL80211_ATTR_OPMODE_NOTIF]) { params.opmode_notif_used = true; params.opmode_notif = @@ -5352,6 +5445,10 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) if (!(params.sta_flags_set & BIT(NL80211_STA_FLAG_WME))) { params.ht_capa = NULL; params.vht_capa = NULL; + + /* HE requires WME */ + if (params.he_capa_len) + return -EINVAL; } /* When you run into this, adjust the code below for the new flag */ diff --git a/net/wireless/util.c b/net/wireless/util.c index b91597a8baa2..4ed06b271f32 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -4,6 +4,7 @@ * * Copyright 2007-2009 Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH + * Copyright 2017 Intel Deutschland GmbH */ #include #include @@ -1142,6 +1143,85 @@ static u32 cfg80211_calculate_bitrate_vht(struct rate_info *rate) return 0; } +static u32 cfg80211_calculate_bitrate_he(struct rate_info *rate) +{ +#define SCALE 2048 + u16 mcs_divisors[12] = { + 34133, /* 16.666666... */ + 17067, /* 8.333333... */ + 11378, /* 5.555555... */ + 8533, /* 4.166666... */ + 5689, /* 2.777777... */ + 4267, /* 2.083333... */ + 3923, /* 1.851851... */ + 3413, /* 1.666666... */ + 2844, /* 1.388888... */ + 2560, /* 1.250000... */ + 2276, /* 1.111111... */ + 2048, /* 1.000000... */ + }; + u32 rates_160M[3] = { 960777777, 907400000, 816666666 }; + u32 rates_969[3] = { 480388888, 453700000, 408333333 }; + u32 rates_484[3] = { 229411111, 216666666, 195000000 }; + u32 rates_242[3] = { 114711111, 108333333, 97500000 }; + u32 rates_106[3] = { 40000000, 37777777, 34000000 }; + u32 rates_52[3] = { 18820000, 17777777, 16000000 }; + u32 rates_26[3] = { 9411111, 8888888, 8000000 }; + u64 tmp; + u32 result; + + if (WARN_ON_ONCE(rate->mcs > 11)) + return 0; + + if (WARN_ON_ONCE(rate->he_gi > NL80211_RATE_INFO_HE_GI_3_2)) + return 0; + if (WARN_ON_ONCE(rate->he_ru_alloc > + NL80211_RATE_INFO_HE_RU_ALLOC_2x996)) + return 0; + if (WARN_ON_ONCE(rate->nss < 1 || rate->nss > 8)) + return 0; + + if (rate->bw == RATE_INFO_BW_160) + result = rates_160M[rate->he_gi]; + else if (rate->bw == RATE_INFO_BW_80 || + (rate->bw == RATE_INFO_BW_HE_RU && + rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_996)) + result = rates_969[rate->he_gi]; + else if (rate->bw == RATE_INFO_BW_40 || + (rate->bw == RATE_INFO_BW_HE_RU && + rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_484)) + result = rates_484[rate->he_gi]; + else if (rate->bw == RATE_INFO_BW_20 || + (rate->bw == RATE_INFO_BW_HE_RU && + rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_242)) + result = rates_242[rate->he_gi]; + else if (rate->bw == RATE_INFO_BW_HE_RU && + rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_106) + result = rates_106[rate->he_gi]; + else if (rate->bw == RATE_INFO_BW_HE_RU && + rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_52) + result = rates_52[rate->he_gi]; + else if (rate->bw == RATE_INFO_BW_HE_RU && + rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_26) + result = rates_26[rate->he_gi]; + else if (WARN(1, "invalid HE MCS: bw:%d, ru:%d\n", + rate->bw, rate->he_ru_alloc)) + return 0; + + /* now scale to the appropriate MCS */ + tmp = result; + tmp *= SCALE; + do_div(tmp, mcs_divisors[rate->mcs]); + result = tmp; + + /* and take NSS, DCM into account */ + result = (result * rate->nss) / 8; + if (rate->he_dcm) + result /= 2; + + return result; +} + u32 cfg80211_calculate_bitrate(struct rate_info *rate) { if (rate->flags & RATE_INFO_FLAGS_MCS) @@ -1150,6 +1230,8 @@ u32 cfg80211_calculate_bitrate(struct rate_info *rate) return cfg80211_calculate_bitrate_60g(rate); if (rate->flags & RATE_INFO_FLAGS_VHT_MCS) return cfg80211_calculate_bitrate_vht(rate); + if (rate->flags & RATE_INFO_FLAGS_HE_MCS) + return cfg80211_calculate_bitrate_he(rate); return rate->legacy; } -- cgit v1.2.3 From 95a28eeaf1491bcb8bf521bad4784683333705ee Mon Sep 17 00:00:00 2001 From: Luca Coelho Date: Sat, 9 Jun 2018 09:14:43 +0300 Subject: radiotap: add structs for HE Add radiotap structures for HE. Signed-off-by: Liad Kaufman Signed-off-by: Johannes Berg Signed-off-by: Ilan Peer Signed-off-by: Ido Yariv Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- include/net/ieee80211_radiotap.h | 123 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 123 insertions(+) (limited to 'include') diff --git a/include/net/ieee80211_radiotap.h b/include/net/ieee80211_radiotap.h index 960236fb1681..feef706e1158 100644 --- a/include/net/ieee80211_radiotap.h +++ b/include/net/ieee80211_radiotap.h @@ -1,5 +1,6 @@ /* * Copyright (c) 2017 Intel Deutschland GmbH + * Copyright (c) 2018 Intel Corporation * * Permission to use, copy, modify, and/or distribute this software for any * purpose with or without fee is hereby granted, provided that the above @@ -72,6 +73,8 @@ enum ieee80211_radiotap_presence { IEEE80211_RADIOTAP_AMPDU_STATUS = 20, IEEE80211_RADIOTAP_VHT = 21, IEEE80211_RADIOTAP_TIMESTAMP = 22, + IEEE80211_RADIOTAP_HE = 23, + IEEE80211_RADIOTAP_HE_MU = 24, /* valid in every it_present bitmap, even vendor namespaces */ IEEE80211_RADIOTAP_RADIOTAP_NAMESPACE = 29, @@ -202,6 +205,126 @@ enum ieee80211_radiotap_timestamp_flags { IEEE80211_RADIOTAP_TIMESTAMP_FLAG_ACCURACY = 0x02, }; +struct ieee80211_radiotap_he { + __le16 data1, data2, data3, data4, data5, data6; +}; + +enum ieee80211_radiotap_he_bits { + IEEE80211_RADIOTAP_HE_DATA1_FORMAT_MASK = 3, + IEEE80211_RADIOTAP_HE_DATA1_FORMAT_SU = 0, + IEEE80211_RADIOTAP_HE_DATA1_FORMAT_EXT_SU = 1, + IEEE80211_RADIOTAP_HE_DATA1_FORMAT_MU = 2, + IEEE80211_RADIOTAP_HE_DATA1_FORMAT_TRIG = 3, + + IEEE80211_RADIOTAP_HE_DATA1_BSS_COLOR_KNOWN = 0x0004, + IEEE80211_RADIOTAP_HE_DATA1_BEAM_CHANGE_KNOWN = 0x0008, + IEEE80211_RADIOTAP_HE_DATA1_UL_DL_KNOWN = 0x0010, + IEEE80211_RADIOTAP_HE_DATA1_DATA_MCS_KNOWN = 0x0020, + IEEE80211_RADIOTAP_HE_DATA1_DATA_DCM_KNOWN = 0x0040, + IEEE80211_RADIOTAP_HE_DATA1_CODING_KNOWN = 0x0080, + IEEE80211_RADIOTAP_HE_DATA1_LDPC_XSYMSEG_KNOWN = 0x0100, + IEEE80211_RADIOTAP_HE_DATA1_STBC_KNOWN = 0x0200, + IEEE80211_RADIOTAP_HE_DATA1_SPTL_REUSE_KNOWN = 0x0400, + IEEE80211_RADIOTAP_HE_DATA1_SPTL_REUSE2_KNOWN = 0x0800, + IEEE80211_RADIOTAP_HE_DATA1_SPTL_REUSE3_KNOWN = 0x1000, + IEEE80211_RADIOTAP_HE_DATA1_SPTL_REUSE4_KNOWN = 0x2000, + IEEE80211_RADIOTAP_HE_DATA1_BW_RU_ALLOC_KNOWN = 0x4000, + IEEE80211_RADIOTAP_HE_DATA1_DOPPLER_KNOWN = 0x8000, + + IEEE80211_RADIOTAP_HE_DATA2_PRISEC_80_KNOWN = 0x0001, + IEEE80211_RADIOTAP_HE_DATA2_GI_KNOWN = 0x0002, + IEEE80211_RADIOTAP_HE_DATA2_NUM_LTF_SYMS_KNOWN = 0x0004, + IEEE80211_RADIOTAP_HE_DATA2_PRE_FEC_PAD_KNOWN = 0x0008, + IEEE80211_RADIOTAP_HE_DATA2_TXBF_KNOWN = 0x0010, + IEEE80211_RADIOTAP_HE_DATA2_PE_DISAMBIG_KNOWN = 0x0020, + IEEE80211_RADIOTAP_HE_DATA2_TXOP_KNOWN = 0x0040, + IEEE80211_RADIOTAP_HE_DATA2_MIDAMBLE_KNOWN = 0x0080, + IEEE80211_RADIOTAP_HE_DATA2_RU_OFFSET = 0x3f00, + IEEE80211_RADIOTAP_HE_DATA2_RU_OFFSET_KNOWN = 0x4000, + IEEE80211_RADIOTAP_HE_DATA2_PRISEC_80_SEC = 0x8000, + + IEEE80211_RADIOTAP_HE_DATA3_BSS_COLOR = 0x003f, + IEEE80211_RADIOTAP_HE_DATA3_BEAM_CHANGE = 0x0040, + IEEE80211_RADIOTAP_HE_DATA3_UL_DL = 0x0080, + IEEE80211_RADIOTAP_HE_DATA3_DATA_MCS = 0x0f00, + IEEE80211_RADIOTAP_HE_DATA3_DATA_DCM = 0x1000, + IEEE80211_RADIOTAP_HE_DATA3_CODING = 0x2000, + IEEE80211_RADIOTAP_HE_DATA3_LDPC_XSYMSEG = 0x4000, + IEEE80211_RADIOTAP_HE_DATA3_STBC = 0x8000, + + IEEE80211_RADIOTAP_HE_DATA4_SU_MU_SPTL_REUSE = 0x000f, + IEEE80211_RADIOTAP_HE_DATA4_MU_STA_ID = 0x7ff0, + IEEE80211_RADIOTAP_HE_DATA4_TB_SPTL_REUSE1 = 0x000f, + IEEE80211_RADIOTAP_HE_DATA4_TB_SPTL_REUSE2 = 0x00f0, + IEEE80211_RADIOTAP_HE_DATA4_TB_SPTL_REUSE3 = 0x0f00, + IEEE80211_RADIOTAP_HE_DATA4_TB_SPTL_REUSE4 = 0xf000, + + IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC = 0x000f, + IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_20MHZ = 0, + IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_40MHZ = 1, + IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_80MHZ = 2, + IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_160MHZ = 3, + IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_26T = 4, + IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_52T = 5, + IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_106T = 6, + IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_242T = 7, + IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_484T = 8, + IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_996T = 9, + IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_2x996T = 10, + + IEEE80211_RADIOTAP_HE_DATA5_GI = 0x0030, + IEEE80211_RADIOTAP_HE_DATA5_GI_0_8 = 0, + IEEE80211_RADIOTAP_HE_DATA5_GI_1_6 = 1, + IEEE80211_RADIOTAP_HE_DATA5_GI_3_2 = 2, + + IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE = 0x00c0, + IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE_UNKNOWN = 0, + IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE_1X = 1, + IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE_2X = 2, + IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE_4X = 3, + IEEE80211_RADIOTAP_HE_DATA5_NUM_LTF_SYMS = 0x0700, + IEEE80211_RADIOTAP_HE_DATA5_PRE_FEC_PAD = 0x3000, + IEEE80211_RADIOTAP_HE_DATA5_TXBF = 0x4000, + IEEE80211_RADIOTAP_HE_DATA5_PE_DISAMBIG = 0x8000, + + IEEE80211_RADIOTAP_HE_DATA6_NSTS = 0x000f, + IEEE80211_RADIOTAP_HE_DATA6_DOPPLER = 0x0010, + IEEE80211_RADIOTAP_HE_DATA6_TXOP = 0x7f00, + IEEE80211_RADIOTAP_HE_DATA6_MIDAMBLE_PDCTY = 0x8000, +}; + +struct ieee80211_radiotap_he_mu { + __le16 flags1, flags2; + u8 ru_ch1[4]; + u8 ru_ch2[4]; +}; + +enum ieee80211_radiotap_he_mu_bits { + IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_MCS = 0x000f, + IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_MCS_KNOWN = 0x0010, + IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_DCM = 0x0020, + IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_DCM_KNOWN = 0x0040, + IEEE80211_RADIOTAP_HE_MU_FLAGS1_CH2_CTR_26T_RU_KNOWN = 0x0080, + IEEE80211_RADIOTAP_HE_MU_FLAGS1_CH1_RU_KNOWN = 0x0100, + IEEE80211_RADIOTAP_HE_MU_FLAGS1_CH2_RU_KNOWN = 0x0200, + IEEE80211_RADIOTAP_HE_MU_FLAGS1_CH1_CTR_26T_RU_KNOWN = 0x1000, + IEEE80211_RADIOTAP_HE_MU_FLAGS1_CH1_CTR_26T_RU = 0x2000, + IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_COMP_KNOWN = 0x4000, + IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_SYMS_USERS_KNOWN = 0x8000, + + IEEE80211_RADIOTAP_HE_MU_FLAGS2_BW_FROM_SIG_A_BW = 0x0003, + IEEE80211_RADIOTAP_HE_MU_FLAGS2_BW_FROM_SIG_A_BW_20MHZ = 0x0000, + IEEE80211_RADIOTAP_HE_MU_FLAGS2_BW_FROM_SIG_A_BW_40MHZ = 0x0001, + IEEE80211_RADIOTAP_HE_MU_FLAGS2_BW_FROM_SIG_A_BW_80MHZ = 0x0002, + IEEE80211_RADIOTAP_HE_MU_FLAGS2_BW_FROM_SIG_A_BW_160MHZ = 0x0003, + IEEE80211_RADIOTAP_HE_MU_FLAGS2_BW_FROM_SIG_A_BW_KNOWN = 0x0004, + IEEE80211_RADIOTAP_HE_MU_FLAGS2_SIG_B_COMP = 0x0008, + IEEE80211_RADIOTAP_HE_MU_FLAGS2_SIG_B_SYMS_USERS = 0x00f0, + IEEE80211_RADIOTAP_HE_MU_FLAGS2_PUNC_FROM_SIG_A_BW = 0x0300, + IEEE80211_RADIOTAP_HE_MU_FLAGS2_PUNC_FROM_SIG_A_BW_KNOWN= 0x0400, + IEEE80211_RADIOTAP_HE_MU_FLAGS2_CH2_CTR_26T_RU = 0x0800, +}; + /** * ieee80211_get_radiotap_len - get radiotap header length */ -- cgit v1.2.3 From 2d33948e4e00b501b91367fed21243a948426591 Mon Sep 17 00:00:00 2001 From: Nayan Deshmukh Date: Tue, 29 May 2018 11:23:07 +0530 Subject: drm/scheduler: add documentation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit convert existing raw comments into kernel-doc format as well as add new documentation v2: reword the overview Signed-off-by: Alex Deucher Signed-off-by: Nayan Deshmukh Reviewed-by: Alex Deucher Reviewed-by: Christian König Acked-by: Daniel Vetter --- drivers/gpu/drm/scheduler/gpu_scheduler.c | 214 ++++++++++++++++++++++++------ include/drm/gpu_scheduler.h | 153 +++++++++++++++++---- 2 files changed, 296 insertions(+), 71 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/scheduler/gpu_scheduler.c b/drivers/gpu/drm/scheduler/gpu_scheduler.c index 44d480768dfe..8c1e80c9b674 100644 --- a/drivers/gpu/drm/scheduler/gpu_scheduler.c +++ b/drivers/gpu/drm/scheduler/gpu_scheduler.c @@ -21,6 +21,29 @@ * */ +/** + * DOC: Overview + * + * The GPU scheduler provides entities which allow userspace to push jobs + * into software queues which are then scheduled on a hardware run queue. + * The software queues have a priority among them. The scheduler selects the entities + * from the run queue using a FIFO. The scheduler provides dependency handling + * features among jobs. The driver is supposed to provide callback functions for + * backend operations to the scheduler like submitting a job to hardware run queue, + * returning the dependencies of a job etc. + * + * The organisation of the scheduler is the following: + * + * 1. Each hw run queue has one scheduler + * 2. Each scheduler has multiple run queues with different priorities + * (e.g., HIGH_HW,HIGH_SW, KERNEL, NORMAL) + * 3. Each scheduler run queue has a queue of entities to schedule + * 4. Entities themselves maintain a queue of jobs that will be scheduled on + * the hardware. + * + * The jobs in a entity are always scheduled in the order that they were pushed. + */ + #include #include #include @@ -39,7 +62,13 @@ static bool drm_sched_entity_is_ready(struct drm_sched_entity *entity); static void drm_sched_wakeup(struct drm_gpu_scheduler *sched); static void drm_sched_process_job(struct dma_fence *f, struct dma_fence_cb *cb); -/* Initialize a given run queue struct */ +/** + * drm_sched_rq_init - initialize a given run queue struct + * + * @rq: scheduler run queue + * + * Initializes a scheduler runqueue. + */ static void drm_sched_rq_init(struct drm_sched_rq *rq) { spin_lock_init(&rq->lock); @@ -47,6 +76,14 @@ static void drm_sched_rq_init(struct drm_sched_rq *rq) rq->current_entity = NULL; } +/** + * drm_sched_rq_add_entity - add an entity + * + * @rq: scheduler run queue + * @entity: scheduler entity + * + * Adds a scheduler entity to the run queue. + */ static void drm_sched_rq_add_entity(struct drm_sched_rq *rq, struct drm_sched_entity *entity) { @@ -57,6 +94,14 @@ static void drm_sched_rq_add_entity(struct drm_sched_rq *rq, spin_unlock(&rq->lock); } +/** + * drm_sched_rq_remove_entity - remove an entity + * + * @rq: scheduler run queue + * @entity: scheduler entity + * + * Removes a scheduler entity from the run queue. + */ static void drm_sched_rq_remove_entity(struct drm_sched_rq *rq, struct drm_sched_entity *entity) { @@ -70,9 +115,9 @@ static void drm_sched_rq_remove_entity(struct drm_sched_rq *rq, } /** - * Select an entity which could provide a job to run + * drm_sched_rq_select_entity - Select an entity which could provide a job to run * - * @rq The run queue to check. + * @rq: scheduler run queue to check. * * Try to find a ready entity, returns NULL if none found. */ @@ -112,15 +157,16 @@ drm_sched_rq_select_entity(struct drm_sched_rq *rq) } /** - * Init a context entity used by scheduler when submit to HW ring. + * drm_sched_entity_init - Init a context entity used by scheduler when + * submit to HW ring. * - * @sched The pointer to the scheduler - * @entity The pointer to a valid drm_sched_entity - * @rq The run queue this entity belongs - * @guilty atomic_t set to 1 when a job on this queue - * is found to be guilty causing a timeout + * @sched: scheduler instance + * @entity: scheduler entity to init + * @rq: the run queue this entity belongs + * @guilty: atomic_t set to 1 when a job on this queue + * is found to be guilty causing a timeout * - * return 0 if succeed. negative error code on failure + * Returns 0 on success or a negative error code on failure. */ int drm_sched_entity_init(struct drm_gpu_scheduler *sched, struct drm_sched_entity *entity, @@ -149,10 +195,10 @@ int drm_sched_entity_init(struct drm_gpu_scheduler *sched, EXPORT_SYMBOL(drm_sched_entity_init); /** - * Query if entity is initialized + * drm_sched_entity_is_initialized - Query if entity is initialized * - * @sched Pointer to scheduler instance - * @entity The pointer to a valid scheduler entity + * @sched: Pointer to scheduler instance + * @entity: The pointer to a valid scheduler entity * * return true if entity is initialized, false otherwise */ @@ -164,11 +210,11 @@ static bool drm_sched_entity_is_initialized(struct drm_gpu_scheduler *sched, } /** - * Check if entity is idle + * drm_sched_entity_is_idle - Check if entity is idle * - * @entity The pointer to a valid scheduler entity + * @entity: scheduler entity * - * Return true if entity don't has any unscheduled jobs. + * Returns true if the entity does not have any unscheduled jobs. */ static bool drm_sched_entity_is_idle(struct drm_sched_entity *entity) { @@ -180,9 +226,9 @@ static bool drm_sched_entity_is_idle(struct drm_sched_entity *entity) } /** - * Check if entity is ready + * drm_sched_entity_is_ready - Check if entity is ready * - * @entity The pointer to a valid scheduler entity + * @entity: scheduler entity * * Return true if entity could provide a job. */ @@ -210,12 +256,12 @@ static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f, /** - * Destroy a context entity + * drm_sched_entity_do_release - Destroy a context entity * - * @sched Pointer to scheduler instance - * @entity The pointer to a valid scheduler entity + * @sched: scheduler instance + * @entity: scheduler entity * - * Splitting drm_sched_entity_fini() into two functions, The first one is does the waiting, + * Splitting drm_sched_entity_fini() into two functions, The first one does the waiting, * removes the entity from the runqueue and returns an error when the process was killed. */ void drm_sched_entity_do_release(struct drm_gpu_scheduler *sched, @@ -237,12 +283,13 @@ void drm_sched_entity_do_release(struct drm_gpu_scheduler *sched, EXPORT_SYMBOL(drm_sched_entity_do_release); /** - * Destroy a context entity + * drm_sched_entity_cleanup - Destroy a context entity * - * @sched Pointer to scheduler instance - * @entity The pointer to a valid scheduler entity + * @sched: scheduler instance + * @entity: scheduler entity * - * The second one then goes over the entity and signals all jobs with an error code. + * This should be called after @drm_sched_entity_do_release. It goes over the + * entity and signals all jobs with an error code if the process was killed. */ void drm_sched_entity_cleanup(struct drm_gpu_scheduler *sched, struct drm_sched_entity *entity) @@ -281,6 +328,14 @@ void drm_sched_entity_cleanup(struct drm_gpu_scheduler *sched, } EXPORT_SYMBOL(drm_sched_entity_cleanup); +/** + * drm_sched_entity_fini - Destroy a context entity + * + * @sched: scheduler instance + * @entity: scheduler entity + * + * Calls drm_sched_entity_do_release() and drm_sched_entity_cleanup() + */ void drm_sched_entity_fini(struct drm_gpu_scheduler *sched, struct drm_sched_entity *entity) { @@ -306,6 +361,15 @@ static void drm_sched_entity_clear_dep(struct dma_fence *f, struct dma_fence_cb dma_fence_put(f); } +/** + * drm_sched_entity_set_rq - Sets the run queue for an entity + * + * @entity: scheduler entity + * @rq: scheduler run queue + * + * Sets the run queue for an entity and removes the entity from the previous + * run queue in which was present. + */ void drm_sched_entity_set_rq(struct drm_sched_entity *entity, struct drm_sched_rq *rq) { @@ -325,6 +389,14 @@ void drm_sched_entity_set_rq(struct drm_sched_entity *entity, } EXPORT_SYMBOL(drm_sched_entity_set_rq); +/** + * drm_sched_dependency_optimized + * + * @fence: the dependency fence + * @entity: the entity which depends on the above fence + * + * Returns true if the dependency can be optimized and false otherwise + */ bool drm_sched_dependency_optimized(struct dma_fence* fence, struct drm_sched_entity *entity) { @@ -413,9 +485,10 @@ drm_sched_entity_pop_job(struct drm_sched_entity *entity) } /** - * Submit a job to the job queue + * drm_sched_entity_push_job - Submit a job to the entity's job queue * - * @sched_job The pointer to job required to submit + * @sched_job: job to submit + * @entity: scheduler entity * * Note: To guarantee that the order of insertion to queue matches * the job's fence sequence number this function should be @@ -506,6 +579,13 @@ static void drm_sched_job_timedout(struct work_struct *work) job->sched->ops->timedout_job(job); } +/** + * drm_sched_hw_job_reset - stop the scheduler if it contains the bad job + * + * @sched: scheduler instance + * @bad: bad scheduler job + * + */ void drm_sched_hw_job_reset(struct drm_gpu_scheduler *sched, struct drm_sched_job *bad) { struct drm_sched_job *s_job; @@ -550,6 +630,12 @@ void drm_sched_hw_job_reset(struct drm_gpu_scheduler *sched, struct drm_sched_jo } EXPORT_SYMBOL(drm_sched_hw_job_reset); +/** + * drm_sched_job_recovery - recover jobs after a reset + * + * @sched: scheduler instance + * + */ void drm_sched_job_recovery(struct drm_gpu_scheduler *sched) { struct drm_sched_job *s_job, *tmp; @@ -599,10 +685,17 @@ void drm_sched_job_recovery(struct drm_gpu_scheduler *sched) EXPORT_SYMBOL(drm_sched_job_recovery); /** - * Init a sched_job with basic field + * drm_sched_job_init - init a scheduler job * - * Note: Refer to drm_sched_entity_push_job documentation + * @job: scheduler job to init + * @sched: scheduler instance + * @entity: scheduler entity to use + * @owner: job owner for debugging + * + * Refer to drm_sched_entity_push_job() documentation * for locking considerations. + * + * Returns 0 for success, negative error code otherwise. */ int drm_sched_job_init(struct drm_sched_job *job, struct drm_gpu_scheduler *sched, @@ -626,7 +719,11 @@ int drm_sched_job_init(struct drm_sched_job *job, EXPORT_SYMBOL(drm_sched_job_init); /** - * Return ture if we can push more jobs to the hw. + * drm_sched_ready - is the scheduler ready + * + * @sched: scheduler instance + * + * Return true if we can push more jobs to the hw, otherwise false. */ static bool drm_sched_ready(struct drm_gpu_scheduler *sched) { @@ -635,7 +732,10 @@ static bool drm_sched_ready(struct drm_gpu_scheduler *sched) } /** - * Wake up the scheduler when it is ready + * drm_sched_wakeup - Wake up the scheduler when it is ready + * + * @sched: scheduler instance + * */ static void drm_sched_wakeup(struct drm_gpu_scheduler *sched) { @@ -644,8 +744,12 @@ static void drm_sched_wakeup(struct drm_gpu_scheduler *sched) } /** - * Select next entity to process -*/ + * drm_sched_select_entity - Select next entity to process + * + * @sched: scheduler instance + * + * Returns the entity to process or NULL if none are found. + */ static struct drm_sched_entity * drm_sched_select_entity(struct drm_gpu_scheduler *sched) { @@ -665,6 +769,14 @@ drm_sched_select_entity(struct drm_gpu_scheduler *sched) return entity; } +/** + * drm_sched_process_job - process a job + * + * @f: fence + * @cb: fence callbacks + * + * Called after job has finished execution. + */ static void drm_sched_process_job(struct dma_fence *f, struct dma_fence_cb *cb) { struct drm_sched_fence *s_fence = @@ -680,6 +792,13 @@ static void drm_sched_process_job(struct dma_fence *f, struct dma_fence_cb *cb) wake_up_interruptible(&sched->wake_up_worker); } +/** + * drm_sched_blocked - check if the scheduler is blocked + * + * @sched: scheduler instance + * + * Returns true if blocked, otherwise false. + */ static bool drm_sched_blocked(struct drm_gpu_scheduler *sched) { if (kthread_should_park()) { @@ -690,6 +809,13 @@ static bool drm_sched_blocked(struct drm_gpu_scheduler *sched) return false; } +/** + * drm_sched_main - main scheduler thread + * + * @param: scheduler instance + * + * Returns 0. + */ static int drm_sched_main(void *param) { struct sched_param sparam = {.sched_priority = 1}; @@ -744,15 +870,17 @@ static int drm_sched_main(void *param) } /** - * Init a gpu scheduler instance + * drm_sched_init - Init a gpu scheduler instance * - * @sched The pointer to the scheduler - * @ops The backend operations for this scheduler. - * @hw_submissions Number of hw submissions to do. - * @name Name used for debugging + * @sched: scheduler instance + * @ops: backend operations for this scheduler + * @hw_submission: number of hw submissions that can be in flight + * @hang_limit: number of times to allow a job to hang before dropping it + * @timeout: timeout value in jiffies for the scheduler + * @name: name used for debugging * * Return 0 on success, otherwise error code. -*/ + */ int drm_sched_init(struct drm_gpu_scheduler *sched, const struct drm_sched_backend_ops *ops, unsigned hw_submission, @@ -788,9 +916,11 @@ int drm_sched_init(struct drm_gpu_scheduler *sched, EXPORT_SYMBOL(drm_sched_init); /** - * Destroy a gpu scheduler + * drm_sched_fini - Destroy a gpu scheduler + * + * @sched: scheduler instance * - * @sched The pointer to the scheduler + * Tears down and cleans up the scheduler. */ void drm_sched_fini(struct drm_gpu_scheduler *sched) { diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index dec655894d08..496442f12bff 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -43,13 +43,33 @@ enum drm_sched_priority { }; /** - * drm_sched_entity - A wrapper around a job queue (typically attached - * to the DRM file_priv). + * struct drm_sched_entity - A wrapper around a job queue (typically + * attached to the DRM file_priv). + * + * @list: used to append this struct to the list of entities in the + * runqueue. + * @rq: runqueue to which this entity belongs. + * @rq_lock: lock to modify the runqueue to which this entity belongs. + * @sched: the scheduler instance to which this entity is enqueued. + * @job_queue: the list of jobs of this entity. + * @fence_seq: a linearly increasing seqno incremented with each + * new &drm_sched_fence which is part of the entity. + * @fence_context: a unique context for all the fences which belong + * to this entity. + * The &drm_sched_fence.scheduled uses the + * fence_context but &drm_sched_fence.finished uses + * fence_context + 1. + * @dependency: the dependency fence of the job which is on the top + * of the job queue. + * @cb: callback for the dependency fence above. + * @guilty: points to ctx's guilty. + * @fini_status: contains the exit status in case the process was signalled. + * @last_scheduled: points to the finished fence of the last scheduled job. * * Entities will emit jobs in order to their corresponding hardware * ring, and the scheduler will alternate between entities based on * scheduling policy. -*/ + */ struct drm_sched_entity { struct list_head list; struct drm_sched_rq *rq; @@ -63,47 +83,96 @@ struct drm_sched_entity { struct dma_fence *dependency; struct dma_fence_cb cb; - atomic_t *guilty; /* points to ctx's guilty */ - int fini_status; - struct dma_fence *last_scheduled; + atomic_t *guilty; + int fini_status; + struct dma_fence *last_scheduled; }; /** + * struct drm_sched_rq - queue of entities to be scheduled. + * + * @lock: to modify the entities list. + * @entities: list of the entities to be scheduled. + * @current_entity: the entity which is to be scheduled. + * * Run queue is a set of entities scheduling command submissions for * one specific ring. It implements the scheduling policy that selects * the next entity to emit commands from. -*/ + */ struct drm_sched_rq { spinlock_t lock; struct list_head entities; struct drm_sched_entity *current_entity; }; +/** + * struct drm_sched_fence - fences corresponding to the scheduling of a job. + */ struct drm_sched_fence { + /** + * @scheduled: this fence is what will be signaled by the scheduler + * when the job is scheduled. + */ struct dma_fence scheduled; - /* This fence is what will be signaled by the scheduler when - * the job is completed. - * - * When setting up an out fence for the job, you should use - * this, since it's available immediately upon - * drm_sched_job_init(), and the fence returned by the driver - * from run_job() won't be created until the dependencies have - * resolved. - */ + /** + * @finished: this fence is what will be signaled by the scheduler + * when the job is completed. + * + * When setting up an out fence for the job, you should use + * this, since it's available immediately upon + * drm_sched_job_init(), and the fence returned by the driver + * from run_job() won't be created until the dependencies have + * resolved. + */ struct dma_fence finished; + /** + * @cb: the callback for the parent fence below. + */ struct dma_fence_cb cb; + /** + * @parent: the fence returned by &drm_sched_backend_ops.run_job + * when scheduling the job on hardware. We signal the + * &drm_sched_fence.finished fence once parent is signalled. + */ struct dma_fence *parent; + /** + * @sched: the scheduler instance to which the job having this struct + * belongs to. + */ struct drm_gpu_scheduler *sched; + /** + * @lock: the lock used by the scheduled and the finished fences. + */ spinlock_t lock; + /** + * @owner: job owner for debugging + */ void *owner; }; struct drm_sched_fence *to_drm_sched_fence(struct dma_fence *f); /** - * drm_sched_job - A job to be run by an entity. + * struct drm_sched_job - A job to be run by an entity. + * + * @queue_node: used to append this struct to the queue of jobs in an entity. + * @sched: the scheduler instance on which this job is scheduled. + * @s_fence: contains the fences for the scheduling of job. + * @finish_cb: the callback for the finished fence. + * @finish_work: schedules the function @drm_sched_job_finish once the job has + * finished to remove the job from the + * @drm_gpu_scheduler.ring_mirror_list. + * @node: used to append this struct to the @drm_gpu_scheduler.ring_mirror_list. + * @work_tdr: schedules a delayed call to @drm_sched_job_timedout after the timeout + * interval is over. + * @id: a unique id assigned to each job scheduled on the scheduler. + * @karma: increment on every hang caused by this job. If this exceeds the hang + * limit of the scheduler then the job is marked guilty and will not + * be scheduled further. + * @s_priority: the priority of the job. + * @entity: the entity to which this job belongs. * * A job is created by the driver using drm_sched_job_init(), and * should call drm_sched_entity_push_job() once it wants the scheduler @@ -130,38 +199,64 @@ static inline bool drm_sched_invalidate_job(struct drm_sched_job *s_job, } /** + * struct drm_sched_backend_ops + * * Define the backend operations called by the scheduler, - * these functions should be implemented in driver side -*/ + * these functions should be implemented in driver side. + */ struct drm_sched_backend_ops { - /* Called when the scheduler is considering scheduling this - * job next, to get another struct dma_fence for this job to + /** + * @dependency: Called when the scheduler is considering scheduling + * this job next, to get another struct dma_fence for this job to * block on. Once it returns NULL, run_job() may be called. */ struct dma_fence *(*dependency)(struct drm_sched_job *sched_job, struct drm_sched_entity *s_entity); - /* Called to execute the job once all of the dependencies have - * been resolved. This may be called multiple times, if + /** + * @run_job: Called to execute the job once all of the dependencies + * have been resolved. This may be called multiple times, if * timedout_job() has happened and drm_sched_job_recovery() * decides to try it again. */ struct dma_fence *(*run_job)(struct drm_sched_job *sched_job); - /* Called when a job has taken too long to execute, to trigger - * GPU recovery. + /** + * @timedout_job: Called when a job has taken too long to execute, + * to trigger GPU recovery. */ void (*timedout_job)(struct drm_sched_job *sched_job); - /* Called once the job's finished fence has been signaled and - * it's time to clean it up. + /** + * @free_job: Called once the job's finished fence has been signaled + * and it's time to clean it up. */ void (*free_job)(struct drm_sched_job *sched_job); }; /** - * One scheduler is implemented for each hardware ring -*/ + * struct drm_gpu_scheduler + * + * @ops: backend operations provided by the driver. + * @hw_submission_limit: the max size of the hardware queue. + * @timeout: the time after which a job is removed from the scheduler. + * @name: name of the ring for which this scheduler is being used. + * @sched_rq: priority wise array of run queues. + * @wake_up_worker: the wait queue on which the scheduler sleeps until a job + * is ready to be scheduled. + * @job_scheduled: once @drm_sched_entity_do_release is called the scheduler + * waits on this wait queue until all the scheduled jobs are + * finished. + * @hw_rq_count: the number of jobs currently in the hardware queue. + * @job_id_count: used to assign unique id to the each job. + * @thread: the kthread on which the scheduler which run. + * @ring_mirror_list: the list of jobs which are currently in the job queue. + * @job_list_lock: lock to protect the ring_mirror_list. + * @hang_limit: once the hangs by a job crosses this limit then it is marked + * guilty and it will be considered for scheduling further. + * + * One scheduler is implemented for each hardware ring. + */ struct drm_gpu_scheduler { const struct drm_sched_backend_ops *ops; uint32_t hw_submission_limit; -- cgit v1.2.3 From b646c1dc835b6b73884a88643c2534f1a4a1928f Mon Sep 17 00:00:00 2001 From: Samuel Li Date: Thu, 24 May 2018 14:32:49 -0400 Subject: drm/amdgpu: add kernel doc for memory domains. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Document the GEM domains exposed to userspace. Suggested-by: Alex Deucher Signed-off-by: Samuel Li Reviewed-by: Christian König Signed-off-by: Alex Deucher --- include/uapi/drm/amdgpu_drm.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include') diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index 78b4dd89fcb4..0dc9e606114e 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -72,6 +72,29 @@ extern "C" { #define DRM_IOCTL_AMDGPU_FENCE_TO_HANDLE DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_FENCE_TO_HANDLE, union drm_amdgpu_fence_to_handle) #define DRM_IOCTL_AMDGPU_SCHED DRM_IOW(DRM_COMMAND_BASE + DRM_AMDGPU_SCHED, union drm_amdgpu_sched) +/** + * DOC: memory domains + * + * %AMDGPU_GEM_DOMAIN_CPU System memory that is not GPU accessible. + * Memory in this pool could be swapped out to disk if there is pressure. + * + * %AMDGPU_GEM_DOMAIN_GTT GPU accessible system memory, mapped into the + * GPU's virtual address space via gart. Gart memory linearizes non-contiguous + * pages of system memory, allows GPU access system memory in a linezrized + * fashion. + * + * %AMDGPU_GEM_DOMAIN_VRAM Local video memory. For APUs, it is memory + * carved out by the BIOS. + * + * %AMDGPU_GEM_DOMAIN_GDS Global on-chip data storage used to share data + * across shader threads. + * + * %AMDGPU_GEM_DOMAIN_GWS Global wave sync, used to synchronize the + * execution of all the waves on a device. + * + * %AMDGPU_GEM_DOMAIN_OA Ordered append, used by 3D or Compute engines + * for appending data. + */ #define AMDGPU_GEM_DOMAIN_CPU 0x1 #define AMDGPU_GEM_DOMAIN_GTT 0x2 #define AMDGPU_GEM_DOMAIN_VRAM 0x4 -- cgit v1.2.3 From 741f01e636b72ff3f81204fd595ac1078907671b Mon Sep 17 00:00:00 2001 From: Andrey Grodzovsky Date: Wed, 30 May 2018 15:11:01 -0400 Subject: drm/scheduler: Avoid using wait_event_killable for dying process (V4) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Dying process might be blocked from receiving any more signals so avoid using it. Also retire enity->fini_status and just check the SW queue, if it's not empty do the fallback cleanup. Also handle entity->last_scheduled == NULL use case which happens when HW ring is already hangged whem a new entity tried to enqeue jobs. v2: Return the remaining timeout and use that as parameter for the next call. This way when we need to cleanup multiple queues we don't wait for the entire TO period for each queue but rather in total. Styling comments. Rebase. v3: Update types from unsigned to long. Work with jiffies instead of ms. Return 0 when TO expires. Rebase. v4: Remove unnecessary timeout calculation. Signed-off-by: Andrey Grodzovsky Reviewed-by: Christian König Signed-off-by: Alex Deucher --- drivers/gpu/drm/scheduler/gpu_scheduler.c | 67 ++++++++++++++++++++++--------- include/drm/gpu_scheduler.h | 7 ++-- 2 files changed, 53 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/scheduler/gpu_scheduler.c b/drivers/gpu/drm/scheduler/gpu_scheduler.c index 8c1e80c9b674..6a316701da73 100644 --- a/drivers/gpu/drm/scheduler/gpu_scheduler.c +++ b/drivers/gpu/drm/scheduler/gpu_scheduler.c @@ -181,7 +181,6 @@ int drm_sched_entity_init(struct drm_gpu_scheduler *sched, entity->rq = rq; entity->sched = sched; entity->guilty = guilty; - entity->fini_status = 0; entity->last_scheduled = NULL; spin_lock_init(&entity->rq_lock); @@ -219,7 +218,8 @@ static bool drm_sched_entity_is_initialized(struct drm_gpu_scheduler *sched, static bool drm_sched_entity_is_idle(struct drm_sched_entity *entity) { rmb(); - if (spsc_queue_peek(&entity->job_queue) == NULL) + + if (!entity->rq || spsc_queue_peek(&entity->job_queue) == NULL) return true; return false; @@ -260,25 +260,39 @@ static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f, * * @sched: scheduler instance * @entity: scheduler entity + * @timeout: time to wait in for Q to become empty in jiffies. * * Splitting drm_sched_entity_fini() into two functions, The first one does the waiting, * removes the entity from the runqueue and returns an error when the process was killed. + * + * Returns the remaining time in jiffies left from the input timeout */ -void drm_sched_entity_do_release(struct drm_gpu_scheduler *sched, - struct drm_sched_entity *entity) +long drm_sched_entity_do_release(struct drm_gpu_scheduler *sched, + struct drm_sched_entity *entity, long timeout) { + long ret = timeout; + if (!drm_sched_entity_is_initialized(sched, entity)) - return; + return ret; /** * The client will not queue more IBs during this fini, consume existing * queued IBs or discard them on SIGKILL */ - if ((current->flags & PF_SIGNALED) && current->exit_code == SIGKILL) - entity->fini_status = -ERESTARTSYS; - else - entity->fini_status = wait_event_killable(sched->job_scheduled, - drm_sched_entity_is_idle(entity)); - drm_sched_entity_set_rq(entity, NULL); + if (current->flags & PF_EXITING) { + if (timeout) + ret = wait_event_timeout( + sched->job_scheduled, + drm_sched_entity_is_idle(entity), + timeout); + } else + wait_event_killable(sched->job_scheduled, drm_sched_entity_is_idle(entity)); + + + /* For killed process disable any more IBs enqueue right now */ + if ((current->flags & PF_EXITING) && (current->exit_code == SIGKILL)) + drm_sched_entity_set_rq(entity, NULL); + + return ret; } EXPORT_SYMBOL(drm_sched_entity_do_release); @@ -290,11 +304,18 @@ EXPORT_SYMBOL(drm_sched_entity_do_release); * * This should be called after @drm_sched_entity_do_release. It goes over the * entity and signals all jobs with an error code if the process was killed. + * */ void drm_sched_entity_cleanup(struct drm_gpu_scheduler *sched, struct drm_sched_entity *entity) { - if (entity->fini_status) { + + drm_sched_entity_set_rq(entity, NULL); + + /* Consumption of existing IBs wasn't completed. Forcefully + * remove them here. + */ + if (spsc_queue_peek(&entity->job_queue)) { struct drm_sched_job *job; int r; @@ -314,12 +335,22 @@ void drm_sched_entity_cleanup(struct drm_gpu_scheduler *sched, struct drm_sched_fence *s_fence = job->s_fence; drm_sched_fence_scheduled(s_fence); dma_fence_set_error(&s_fence->finished, -ESRCH); - r = dma_fence_add_callback(entity->last_scheduled, &job->finish_cb, - drm_sched_entity_kill_jobs_cb); - if (r == -ENOENT) + + /* + * When pipe is hanged by older entity, new entity might + * not even have chance to submit it's first job to HW + * and so entity->last_scheduled will remain NULL + */ + if (!entity->last_scheduled) { drm_sched_entity_kill_jobs_cb(NULL, &job->finish_cb); - else if (r) - DRM_ERROR("fence add callback failed (%d)\n", r); + } else { + r = dma_fence_add_callback(entity->last_scheduled, &job->finish_cb, + drm_sched_entity_kill_jobs_cb); + if (r == -ENOENT) + drm_sched_entity_kill_jobs_cb(NULL, &job->finish_cb); + else if (r) + DRM_ERROR("fence add callback failed (%d)\n", r); + } } } @@ -339,7 +370,7 @@ EXPORT_SYMBOL(drm_sched_entity_cleanup); void drm_sched_entity_fini(struct drm_gpu_scheduler *sched, struct drm_sched_entity *entity) { - drm_sched_entity_do_release(sched, entity); + drm_sched_entity_do_release(sched, entity, MAX_WAIT_SCHED_ENTITY_Q_EMPTY); drm_sched_entity_cleanup(sched, entity); } EXPORT_SYMBOL(drm_sched_entity_fini); diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index 496442f12bff..7c2dfd6cc1af 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -27,6 +27,8 @@ #include #include +#define MAX_WAIT_SCHED_ENTITY_Q_EMPTY msecs_to_jiffies(1000) + struct drm_gpu_scheduler; struct drm_sched_rq; @@ -84,7 +86,6 @@ struct drm_sched_entity { struct dma_fence *dependency; struct dma_fence_cb cb; atomic_t *guilty; - int fini_status; struct dma_fence *last_scheduled; }; @@ -283,8 +284,8 @@ int drm_sched_entity_init(struct drm_gpu_scheduler *sched, struct drm_sched_entity *entity, struct drm_sched_rq *rq, atomic_t *guilty); -void drm_sched_entity_do_release(struct drm_gpu_scheduler *sched, - struct drm_sched_entity *entity); +long drm_sched_entity_do_release(struct drm_gpu_scheduler *sched, + struct drm_sched_entity *entity, long timeout); void drm_sched_entity_cleanup(struct drm_gpu_scheduler *sched, struct drm_sched_entity *entity); void drm_sched_entity_fini(struct drm_gpu_scheduler *sched, -- cgit v1.2.3 From 81d350144bd4590ae546d83344421106e8faf69a Mon Sep 17 00:00:00 2001 From: Boyuan Zhang Date: Tue, 1 May 2018 14:47:31 -0400 Subject: uapi/drm: add AMDGPU_HW_IP_VCN_JPEG for jpeg CS MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add AMDGPU_HW_IP_VCN_JPEG define for jpeg CS Signed-off-by: Boyuan Zhang Reviewed-by: Christian König Signed-off-by: Alex Deucher --- include/uapi/drm/amdgpu_drm.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index 0dc9e606114e..784b0fe470ee 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -506,7 +506,8 @@ struct drm_amdgpu_gem_va { #define AMDGPU_HW_IP_UVD_ENC 5 #define AMDGPU_HW_IP_VCN_DEC 6 #define AMDGPU_HW_IP_VCN_ENC 7 -#define AMDGPU_HW_IP_NUM 8 +#define AMDGPU_HW_IP_VCN_JPEG 8 +#define AMDGPU_HW_IP_NUM 9 #define AMDGPU_HW_IP_INSTANCE_MAX_COUNT 1 -- cgit v1.2.3 From eb3744a2dd01cb07ce9f556d56d6fe451f0c313a Mon Sep 17 00:00:00 2001 From: Keerthy Date: Wed, 13 Jun 2018 09:10:37 +0530 Subject: gpio: davinci: Do not assume continuous IRQ numbering Currently the driver assumes that the interrupts are continuous and does platform_get_irq only once and assumes the rest are continuous, instead call platform_get_irq for all the interrupts and store them in an array for later use. Signed-off-by: Keerthy Reviewed-by: Grygorii Strashko Signed-off-by: Linus Walleij --- drivers/gpio/gpio-davinci.c | 63 ++++++++++++++++++++---------- include/linux/platform_data/gpio-davinci.h | 3 +- 2 files changed, 44 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/drivers/gpio/gpio-davinci.c b/drivers/gpio/gpio-davinci.c index 423d37c95e6b..a5ece8ea79bc 100644 --- a/drivers/gpio/gpio-davinci.c +++ b/drivers/gpio/gpio-davinci.c @@ -55,7 +55,7 @@ static inline struct davinci_gpio_regs __iomem *irq2regs(struct irq_data *d) return g; } -static int davinci_gpio_irq_setup(struct platform_device *pdev, int bank_irq); +static int davinci_gpio_irq_setup(struct platform_device *pdev); /*--------------------------------------------------------------------------*/ @@ -167,8 +167,8 @@ of_err: static int davinci_gpio_probe(struct platform_device *pdev) { static int ctrl_num, bank_base; - int gpio, bank, bank_irq, ret = 0; - unsigned ngpio, nbank; + int gpio, bank, i, ret = 0; + unsigned int ngpio, nbank, nirq; struct davinci_gpio_controller *chips; struct davinci_gpio_platform_data *pdata; struct device *dev = &pdev->dev; @@ -197,6 +197,16 @@ static int davinci_gpio_probe(struct platform_device *pdev) if (WARN_ON(ARCH_NR_GPIOS < ngpio)) ngpio = ARCH_NR_GPIOS; + /* + * If there are unbanked interrupts then the number of + * interrupts is equal to number of gpios else all are banked so + * number of interrupts is equal to number of banks(each with 16 gpios) + */ + if (pdata->gpio_unbanked) + nirq = pdata->gpio_unbanked; + else + nirq = DIV_ROUND_UP(ngpio, 16); + nbank = DIV_ROUND_UP(ngpio, 32); chips = devm_kcalloc(dev, nbank, sizeof(struct davinci_gpio_controller), @@ -209,10 +219,13 @@ static int davinci_gpio_probe(struct platform_device *pdev) if (IS_ERR(gpio_base)) return PTR_ERR(gpio_base); - bank_irq = platform_get_irq(pdev, 0); - if (bank_irq < 0) { - dev_dbg(dev, "IRQ not populated\n"); - return bank_irq; + for (i = 0; i < nirq; i++) { + chips->irqs[i] = platform_get_irq(pdev, i); + if (chips->irqs[i] < 0) { + dev_info(dev, "IRQ not populated, err = %d\n", + chips->irqs[i]); + return chips->irqs[i]; + } } snprintf(label, MAX_LABEL_SIZE, "davinci_gpio.%d", ctrl_num++); @@ -249,7 +262,7 @@ static int davinci_gpio_probe(struct platform_device *pdev) goto err; platform_set_drvdata(pdev, chips); - ret = davinci_gpio_irq_setup(pdev, bank_irq); + ret = davinci_gpio_irq_setup(pdev); if (ret) goto err; @@ -383,7 +396,7 @@ static int gpio_to_irq_unbanked(struct gpio_chip *chip, unsigned offset) * can provide direct-mapped IRQs to AINTC (up to 32 GPIOs). */ if (offset < d->gpio_unbanked) - return d->base_irq + offset; + return d->irqs[offset]; else return -ENODEV; } @@ -392,11 +405,18 @@ static int gpio_irq_type_unbanked(struct irq_data *data, unsigned trigger) { struct davinci_gpio_controller *d; struct davinci_gpio_regs __iomem *g; - u32 mask; + u32 mask, i; d = (struct davinci_gpio_controller *)irq_data_get_irq_handler_data(data); g = (struct davinci_gpio_regs __iomem *)d->regs[0]; - mask = __gpio_mask(data->irq - d->base_irq); + for (i = 0; i < MAX_INT_PER_BANK; i++) + if (data->irq == d->irqs[i]) + break; + + if (i == MAX_INT_PER_BANK) + return -EINVAL; + + mask = __gpio_mask(i); if (trigger & ~(IRQ_TYPE_EDGE_FALLING | IRQ_TYPE_EDGE_RISING)) return -EINVAL; @@ -458,7 +478,7 @@ static const struct of_device_id davinci_gpio_ids[]; * (dm6446) can be set appropriately for GPIOV33 pins. */ -static int davinci_gpio_irq_setup(struct platform_device *pdev, int bank_irq) +static int davinci_gpio_irq_setup(struct platform_device *pdev) { unsigned gpio, bank; int irq; @@ -492,6 +512,7 @@ static int davinci_gpio_irq_setup(struct platform_device *pdev, int bank_irq) dev_err(dev, "Error %ld getting gpio clock\n", PTR_ERR(clk)); return PTR_ERR(clk); } + ret = clk_prepare_enable(clk); if (ret) return ret; @@ -531,12 +552,11 @@ static int davinci_gpio_irq_setup(struct platform_device *pdev, int bank_irq) if (pdata->gpio_unbanked) { /* pass "bank 0" GPIO IRQs to AINTC */ chips->chip.to_irq = gpio_to_irq_unbanked; - chips->base_irq = bank_irq; chips->gpio_unbanked = pdata->gpio_unbanked; binten = GENMASK(pdata->gpio_unbanked / 16, 0); /* AINTC handles mask/unmask; GPIO handles triggering */ - irq = bank_irq; + irq = chips->irqs[0]; irq_chip = gpio_get_irq_chip(irq); irq_chip->name = "GPIO-AINTC"; irq_chip->irq_set_type = gpio_irq_type_unbanked; @@ -547,10 +567,11 @@ static int davinci_gpio_irq_setup(struct platform_device *pdev, int bank_irq) writel_relaxed(~0, &g->set_rising); /* set the direct IRQs up to use that irqchip */ - for (gpio = 0; gpio < pdata->gpio_unbanked; gpio++, irq++) { - irq_set_chip(irq, irq_chip); - irq_set_handler_data(irq, chips); - irq_set_status_flags(irq, IRQ_TYPE_EDGE_BOTH); + for (gpio = 0; gpio < pdata->gpio_unbanked; gpio++) { + irq_set_chip(chips->irqs[gpio], irq_chip); + irq_set_handler_data(chips->irqs[gpio], chips); + irq_set_status_flags(chips->irqs[gpio], + IRQ_TYPE_EDGE_BOTH); } goto done; @@ -560,7 +581,7 @@ static int davinci_gpio_irq_setup(struct platform_device *pdev, int bank_irq) * Or, AINTC can handle IRQs for banks of 16 GPIO IRQs, which we * then chain through our own handler. */ - for (gpio = 0, bank = 0; gpio < ngpio; bank++, bank_irq++, gpio += 16) { + for (gpio = 0, bank = 0; gpio < ngpio; bank++, gpio += 16) { /* disabled by default, enabled only as needed * There are register sets for 32 GPIOs. 2 banks of 16 * GPIOs are covered by each set of registers hence divide by 2 @@ -587,8 +608,8 @@ static int davinci_gpio_irq_setup(struct platform_device *pdev, int bank_irq) irqdata->bank_num = bank; irqdata->chip = chips; - irq_set_chained_handler_and_data(bank_irq, gpio_irq_handler, - irqdata); + irq_set_chained_handler_and_data(chips->irqs[bank], + gpio_irq_handler, irqdata); binten |= BIT(bank); } diff --git a/include/linux/platform_data/gpio-davinci.h b/include/linux/platform_data/gpio-davinci.h index 90ae19ca828f..57a5a35e0073 100644 --- a/include/linux/platform_data/gpio-davinci.h +++ b/include/linux/platform_data/gpio-davinci.h @@ -22,6 +22,7 @@ #include #define MAX_REGS_BANKS 5 +#define MAX_INT_PER_BANK 32 struct davinci_gpio_platform_data { u32 ngpio; @@ -41,7 +42,7 @@ struct davinci_gpio_controller { spinlock_t lock; void __iomem *regs[MAX_REGS_BANKS]; int gpio_unbanked; - unsigned int base_irq; + int irqs[MAX_INT_PER_BANK]; unsigned int base; }; -- cgit v1.2.3 From 90b39402e9f31c4aab48dc1a43d85a724065793f Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 1 Jun 2018 13:21:27 +0200 Subject: gpio: Add API to explicitly name a consumer The GPIO (descriptor) API registers a "label" naming what is currently using the GPIO line. Typically this is taken from things like the device tree node, so "reset-gpios" will result in he line being labeled "reset". The technical effect is pretty much zero: the use is for debug and introspection, such as "lsgpio" and debugfs files. However sometimes the user want this cuddly feeling of listing all GPIO lines and seeing exactly what they are for and it gives a very fulfilling sense of control. Especially in the cases when the device tree node doesn't provide a good name, or anonymous GPIO lines assigned just to "gpios" in the device tree because the usage is implicit. For these cases it may be nice to be able to label the line directly and explicitly. Signed-off-by: Linus Walleij --- drivers/gpio/gpiolib.c | 13 +++++++++++++ include/linux/gpio/consumer.h | 7 +++++++ 2 files changed, 20 insertions(+) (limited to 'include') diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index e11a3bb03820..c6f77e806cb8 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -3193,6 +3193,19 @@ int gpiod_cansleep(const struct gpio_desc *desc) } EXPORT_SYMBOL_GPL(gpiod_cansleep); +/** + * gpiod_set_consumer_name() - set the consumer name for the descriptor + * @desc: gpio to set the consumer name on + * @name: the new consumer name + */ +void gpiod_set_consumer_name(struct gpio_desc *desc, const char *name) +{ + VALIDATE_DESC_VOID(desc); + /* Just overwrite whatever the previous name was */ + desc->label = name; +} +EXPORT_SYMBOL_GPL(gpiod_set_consumer_name); + /** * gpiod_to_irq() - return the IRQ corresponding to a GPIO * @desc: gpio whose IRQ will be returned (already requested) diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index 243112c7fa7d..e8aaf34dd65d 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -145,6 +145,7 @@ int gpiod_is_active_low(const struct gpio_desc *desc); int gpiod_cansleep(const struct gpio_desc *desc); int gpiod_to_irq(const struct gpio_desc *desc); +void gpiod_set_consumer_name(struct gpio_desc *desc, const char *name); /* Convert between the old gpio_ and new gpiod_ interfaces */ struct gpio_desc *gpio_to_desc(unsigned gpio); @@ -467,6 +468,12 @@ static inline int gpiod_to_irq(const struct gpio_desc *desc) return -EINVAL; } +static inline void gpiod_set_consumer_name(struct gpio_desc *desc, const char *name) +{ + /* GPIO can never have been requested */ + WARN_ON(1); +} + static inline struct gpio_desc *gpio_to_desc(unsigned gpio) { return ERR_PTR(-EINVAL); -- cgit v1.2.3 From ba1f665f161ce112a2703649317bfdc9b6521613 Mon Sep 17 00:00:00 2001 From: Haneen Mohammed Date: Fri, 25 May 2018 04:25:55 +0300 Subject: drm: Add checks for atomic_[duplicate/destroy]_state with atomic drivers This patch add checks for atomic_[duplicate/destroy]_state of drm_[connector/crtc/plane]_funcs for atomic drivers in the relevant drm_*_init functions since these callback are mandatory for atomic drivers. Update the kerneldoc comments for those callbacks. Signed-off-by: Haneen Mohammed Reviewed-by: Sean Paul Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20180525012555.GA8448@haneen-vb --- drivers/gpu/drm/drm_connector.c | 4 ++++ drivers/gpu/drm/drm_crtc.c | 4 ++++ drivers/gpu/drm/drm_plane.c | 4 ++++ include/drm/drm_connector.h | 4 ++++ include/drm/drm_crtc.h | 4 ++++ include/drm/drm_plane.h | 4 ++++ 6 files changed, 24 insertions(+) (limited to 'include') diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c index 002b244391f9..549b89501e01 100644 --- a/drivers/gpu/drm/drm_connector.c +++ b/drivers/gpu/drm/drm_connector.c @@ -195,6 +195,10 @@ int drm_connector_init(struct drm_device *dev, struct ida *connector_ida = &drm_connector_enum_list[connector_type].ida; + WARN_ON(drm_drv_uses_atomic_modeset(dev) && + (!funcs->atomic_destroy_state || + !funcs->atomic_duplicate_state)); + ret = __drm_mode_object_add(dev, &connector->base, DRM_MODE_OBJECT_CONNECTOR, false, drm_connector_free); diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c index 163d82ac7d76..f45e7a8d4acd 100644 --- a/drivers/gpu/drm/drm_crtc.c +++ b/drivers/gpu/drm/drm_crtc.c @@ -286,6 +286,10 @@ int drm_crtc_init_with_planes(struct drm_device *dev, struct drm_crtc *crtc, if (WARN_ON(config->num_crtc >= 32)) return -EINVAL; + WARN_ON(drm_drv_uses_atomic_modeset(dev) && + (!funcs->atomic_destroy_state || + !funcs->atomic_duplicate_state)); + crtc->dev = dev; crtc->funcs = funcs; diff --git a/drivers/gpu/drm/drm_plane.c b/drivers/gpu/drm/drm_plane.c index 534b57933576..df0b4ebbedbf 100644 --- a/drivers/gpu/drm/drm_plane.c +++ b/drivers/gpu/drm/drm_plane.c @@ -177,6 +177,10 @@ int drm_universal_plane_init(struct drm_device *dev, struct drm_plane *plane, if (WARN_ON(config->num_total_plane >= 32)) return -EINVAL; + WARN_ON(drm_drv_uses_atomic_modeset(dev) && + (!funcs->atomic_destroy_state || + !funcs->atomic_duplicate_state)); + ret = drm_mode_object_add(dev, &plane->base, DRM_MODE_OBJECT_PLANE); if (ret) return ret; diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h index ee4c48218c85..c5797c24edd3 100644 --- a/include/drm/drm_connector.h +++ b/include/drm/drm_connector.h @@ -616,6 +616,8 @@ struct drm_connector_funcs { * cleaned up by calling the @atomic_destroy_state hook in this * structure. * + * This callback is mandatory for atomic drivers. + * * Atomic drivers which don't subclass &struct drm_connector_state should use * drm_atomic_helper_connector_duplicate_state(). Drivers that subclass the * state structure to extend it with driver-private state should use @@ -642,6 +644,8 @@ struct drm_connector_funcs { * * Destroy a state duplicated with @atomic_duplicate_state and release * or unreference all resources it references + * + * This callback is mandatory for atomic drivers. */ void (*atomic_destroy_state)(struct drm_connector *connector, struct drm_connector_state *state); diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h index 5cf7adeae6a5..23eddbccab10 100644 --- a/include/drm/drm_crtc.h +++ b/include/drm/drm_crtc.h @@ -506,6 +506,8 @@ struct drm_crtc_funcs { * cleaned up by calling the @atomic_destroy_state hook in this * structure. * + * This callback is mandatory for atomic drivers. + * * Atomic drivers which don't subclass &struct drm_crtc_state should use * drm_atomic_helper_crtc_duplicate_state(). Drivers that subclass the * state structure to extend it with driver-private state should use @@ -532,6 +534,8 @@ struct drm_crtc_funcs { * * Destroy a state duplicated with @atomic_duplicate_state and release * or unreference all resources it references + * + * This callback is mandatory for atomic drivers. */ void (*atomic_destroy_state)(struct drm_crtc *crtc, struct drm_crtc_state *state); diff --git a/include/drm/drm_plane.h b/include/drm/drm_plane.h index 14b1607aba4b..7d4d6c7f0afd 100644 --- a/include/drm/drm_plane.h +++ b/include/drm/drm_plane.h @@ -288,6 +288,8 @@ struct drm_plane_funcs { * cleaned up by calling the @atomic_destroy_state hook in this * structure. * + * This callback is mandatory for atomic drivers. + * * Atomic drivers which don't subclass &struct drm_plane_state should use * drm_atomic_helper_plane_duplicate_state(). Drivers that subclass the * state structure to extend it with driver-private state should use @@ -314,6 +316,8 @@ struct drm_plane_funcs { * * Destroy a state duplicated with @atomic_duplicate_state and release * or unreference all resources it references + * + * This callback is mandatory for atomic drivers. */ void (*atomic_destroy_state)(struct drm_plane *plane, struct drm_plane_state *state); -- cgit v1.2.3 From c60b613a7097cff20fdd05e2891ce69542f0d5a3 Mon Sep 17 00:00:00 2001 From: Liam Girdwood Date: Thu, 14 Jun 2018 20:50:37 +0100 Subject: ASoC: topology: Give more data to clients via callbacks Give topology clients more access to the topology data by passing index, pcm, link_config and dai_driver to clients. This allows clients to fully instantiate and track topology objects. The SOF driver is the first user of these new APIs and needs them to build component topology driver and FW objects. Signed-off-by: Liam Girdwood Signed-off-by: Mark Brown --- include/sound/soc-topology.h | 23 ++++++++++++++--------- sound/soc/intel/skylake/skl-pcm.c | 7 ++++--- sound/soc/intel/skylake/skl-topology.c | 5 +++-- sound/soc/intel/skylake/skl-topology.h | 5 +++-- sound/soc/soc-topology.c | 31 ++++++++++++++++++------------- 5 files changed, 42 insertions(+), 29 deletions(-) (limited to 'include') diff --git a/include/sound/soc-topology.h b/include/sound/soc-topology.h index f552c3f56368..e1f265e21ee1 100644 --- a/include/sound/soc-topology.h +++ b/include/sound/soc-topology.h @@ -30,6 +30,8 @@ struct snd_soc_dapm_context; struct snd_soc_card; struct snd_kcontrol_new; struct snd_soc_dai_link; +struct snd_soc_dai_driver; +struct snd_soc_dai; /* object scan be loaded and unloaded in groups with identfying indexes */ #define SND_SOC_TPLG_INDEX_ALL 0 /* ID that matches all FW objects */ @@ -109,35 +111,38 @@ struct snd_soc_tplg_widget_events { struct snd_soc_tplg_ops { /* external kcontrol init - used for any driver specific init */ - int (*control_load)(struct snd_soc_component *, + int (*control_load)(struct snd_soc_component *, int index, struct snd_kcontrol_new *, struct snd_soc_tplg_ctl_hdr *); int (*control_unload)(struct snd_soc_component *, struct snd_soc_dobj *); /* external widget init - used for any driver specific init */ - int (*widget_load)(struct snd_soc_component *, + int (*widget_load)(struct snd_soc_component *, int index, struct snd_soc_dapm_widget *, struct snd_soc_tplg_dapm_widget *); - int (*widget_ready)(struct snd_soc_component *, + int (*widget_ready)(struct snd_soc_component *, int index, struct snd_soc_dapm_widget *, struct snd_soc_tplg_dapm_widget *); int (*widget_unload)(struct snd_soc_component *, struct snd_soc_dobj *); /* FE DAI - used for any driver specific init */ - int (*dai_load)(struct snd_soc_component *, - struct snd_soc_dai_driver *dai_drv); + int (*dai_load)(struct snd_soc_component *, int index, + struct snd_soc_dai_driver *dai_drv, + struct snd_soc_tplg_pcm *pcm, struct snd_soc_dai *dai); + int (*dai_unload)(struct snd_soc_component *, struct snd_soc_dobj *); /* DAI link - used for any driver specific init */ - int (*link_load)(struct snd_soc_component *, - struct snd_soc_dai_link *link); + int (*link_load)(struct snd_soc_component *, int index, + struct snd_soc_dai_link *link, + struct snd_soc_tplg_link_config *cfg); int (*link_unload)(struct snd_soc_component *, struct snd_soc_dobj *); /* callback to handle vendor bespoke data */ - int (*vendor_load)(struct snd_soc_component *, + int (*vendor_load)(struct snd_soc_component *, int index, struct snd_soc_tplg_hdr *); int (*vendor_unload)(struct snd_soc_component *, struct snd_soc_tplg_hdr *); @@ -146,7 +151,7 @@ struct snd_soc_tplg_ops { void (*complete)(struct snd_soc_component *); /* manifest - optional to inform component of manifest */ - int (*manifest)(struct snd_soc_component *, + int (*manifest)(struct snd_soc_component *, int index, struct snd_soc_tplg_manifest *); /* vendor specific kcontrol handlers available for binding */ diff --git a/sound/soc/intel/skylake/skl-pcm.c b/sound/soc/intel/skylake/skl-pcm.c index afa86b9e4dcf..1f4dd08d36c5 100644 --- a/sound/soc/intel/skylake/skl-pcm.c +++ b/sound/soc/intel/skylake/skl-pcm.c @@ -1017,10 +1017,11 @@ static struct snd_soc_dai_driver skl_platform_dai[] = { }, }; -int skl_dai_load(struct snd_soc_component *cmp, - struct snd_soc_dai_driver *pcm_dai) +int skl_dai_load(struct snd_soc_component *cmp, int index, + struct snd_soc_dai_driver *dai_drv, + struct snd_soc_tplg_pcm *pcm, struct snd_soc_dai *dai) { - pcm_dai->ops = &skl_pcm_dai_ops; + dai_drv->ops = &skl_pcm_dai_ops; return 0; } diff --git a/sound/soc/intel/skylake/skl-topology.c b/sound/soc/intel/skylake/skl-topology.c index fcdc716754b6..647e52aecdc3 100644 --- a/sound/soc/intel/skylake/skl-topology.c +++ b/sound/soc/intel/skylake/skl-topology.c @@ -3024,7 +3024,7 @@ void skl_cleanup_resources(struct skl *skl) * information to the driver about module and pipeline parameters which DSP * FW expects like ids, resource values, formats etc */ -static int skl_tplg_widget_load(struct snd_soc_component *cmpnt, +static int skl_tplg_widget_load(struct snd_soc_component *cmpnt, int index, struct snd_soc_dapm_widget *w, struct snd_soc_tplg_dapm_widget *tplg_w) { @@ -3131,6 +3131,7 @@ static int skl_init_enum_data(struct device *dev, struct soc_enum *se, } static int skl_tplg_control_load(struct snd_soc_component *cmpnt, + int index, struct snd_kcontrol_new *kctl, struct snd_soc_tplg_ctl_hdr *hdr) { @@ -3619,7 +3620,7 @@ static int skl_tplg_get_manifest_data(struct snd_soc_tplg_manifest *manifest, return 0; } -static int skl_manifest_load(struct snd_soc_component *cmpnt, +static int skl_manifest_load(struct snd_soc_component *cmpnt, int index, struct snd_soc_tplg_manifest *manifest) { struct hdac_ext_bus *ebus = snd_soc_component_get_drvdata(cmpnt); diff --git a/sound/soc/intel/skylake/skl-topology.h b/sound/soc/intel/skylake/skl-topology.h index 6d7e0569695f..af198ea0379e 100644 --- a/sound/soc/intel/skylake/skl-topology.h +++ b/sound/soc/intel/skylake/skl-topology.h @@ -512,8 +512,9 @@ int skl_pcm_host_dma_prepare(struct device *dev, int skl_pcm_link_dma_prepare(struct device *dev, struct skl_pipe_params *params); -int skl_dai_load(struct snd_soc_component *cmp, - struct snd_soc_dai_driver *pcm_dai); +int skl_dai_load(struct snd_soc_component *cmp, int index, + struct snd_soc_dai_driver *dai_drv, + struct snd_soc_tplg_pcm *pcm, struct snd_soc_dai *dai); void skl_tplg_add_moduleid_in_bind_params(struct skl *skl, struct snd_soc_dapm_widget *w); #endif diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c index 53f121a50c97..9b33260fd537 100644 --- a/sound/soc/soc-topology.c +++ b/sound/soc/soc-topology.c @@ -259,7 +259,7 @@ static int soc_tplg_vendor_load_(struct soc_tplg *tplg, int ret = 0; if (tplg->comp && tplg->ops && tplg->ops->vendor_load) - ret = tplg->ops->vendor_load(tplg->comp, hdr); + ret = tplg->ops->vendor_load(tplg->comp, tplg->index, hdr); else { dev_err(tplg->dev, "ASoC: no vendor load callback for ID %d\n", hdr->vendor_type); @@ -291,7 +291,8 @@ static int soc_tplg_widget_load(struct soc_tplg *tplg, struct snd_soc_dapm_widget *w, struct snd_soc_tplg_dapm_widget *tplg_w) { if (tplg->comp && tplg->ops && tplg->ops->widget_load) - return tplg->ops->widget_load(tplg->comp, w, tplg_w); + return tplg->ops->widget_load(tplg->comp, tplg->index, w, + tplg_w); return 0; } @@ -302,27 +303,30 @@ static int soc_tplg_widget_ready(struct soc_tplg *tplg, struct snd_soc_dapm_widget *w, struct snd_soc_tplg_dapm_widget *tplg_w) { if (tplg->comp && tplg->ops && tplg->ops->widget_ready) - return tplg->ops->widget_ready(tplg->comp, w, tplg_w); + return tplg->ops->widget_ready(tplg->comp, tplg->index, w, + tplg_w); return 0; } /* pass DAI configurations to component driver for extra initialization */ static int soc_tplg_dai_load(struct soc_tplg *tplg, - struct snd_soc_dai_driver *dai_drv) + struct snd_soc_dai_driver *dai_drv, + struct snd_soc_tplg_pcm *pcm, struct snd_soc_dai *dai) { if (tplg->comp && tplg->ops && tplg->ops->dai_load) - return tplg->ops->dai_load(tplg->comp, dai_drv); + return tplg->ops->dai_load(tplg->comp, tplg->index, dai_drv, + pcm, dai); return 0; } /* pass link configurations to component driver for extra initialization */ static int soc_tplg_dai_link_load(struct soc_tplg *tplg, - struct snd_soc_dai_link *link) + struct snd_soc_dai_link *link, struct snd_soc_tplg_link_config *cfg) { if (tplg->comp && tplg->ops && tplg->ops->link_load) - return tplg->ops->link_load(tplg->comp, link); + return tplg->ops->link_load(tplg->comp, tplg->index, link, cfg); return 0; } @@ -643,7 +647,8 @@ static int soc_tplg_init_kcontrol(struct soc_tplg *tplg, struct snd_kcontrol_new *k, struct snd_soc_tplg_ctl_hdr *hdr) { if (tplg->comp && tplg->ops && tplg->ops->control_load) - return tplg->ops->control_load(tplg->comp, k, hdr); + return tplg->ops->control_load(tplg->comp, tplg->index, k, + hdr); return 0; } @@ -1702,7 +1707,7 @@ static int soc_tplg_dai_create(struct soc_tplg *tplg, dai_drv->compress_new = snd_soc_new_compress; /* pass control to component driver for optional further init */ - ret = soc_tplg_dai_load(tplg, dai_drv); + ret = soc_tplg_dai_load(tplg, dai_drv, pcm, NULL); if (ret < 0) { dev_err(tplg->comp->dev, "ASoC: DAI loading failed\n"); kfree(dai_drv); @@ -1772,7 +1777,7 @@ static int soc_tplg_fe_link_create(struct soc_tplg *tplg, set_link_flags(link, pcm->flag_mask, pcm->flags); /* pass control to component driver for optional further init */ - ret = soc_tplg_dai_link_load(tplg, link); + ret = soc_tplg_dai_link_load(tplg, link, NULL); if (ret < 0) { dev_err(tplg->comp->dev, "ASoC: FE link loading failed\n"); kfree(link); @@ -2080,7 +2085,7 @@ static int soc_tplg_link_config(struct soc_tplg *tplg, set_link_flags(link, cfg->flag_mask, cfg->flags); /* pass control to component driver for optional further init */ - ret = soc_tplg_dai_link_load(tplg, link); + ret = soc_tplg_dai_link_load(tplg, link, cfg); if (ret < 0) { dev_err(tplg->dev, "ASoC: physical link loading failed\n"); return ret; @@ -2202,7 +2207,7 @@ static int soc_tplg_dai_config(struct soc_tplg *tplg, set_dai_flags(dai_drv, d->flag_mask, d->flags); /* pass control to component driver for optional further init */ - ret = soc_tplg_dai_load(tplg, dai_drv); + ret = soc_tplg_dai_load(tplg, dai_drv, NULL, dai); if (ret < 0) { dev_err(tplg->comp->dev, "ASoC: DAI loading failed\n"); return ret; @@ -2311,7 +2316,7 @@ static int soc_tplg_manifest_load(struct soc_tplg *tplg, /* pass control to component driver for optional further init */ if (tplg->comp && tplg->ops && tplg->ops->manifest) - return tplg->ops->manifest(tplg->comp, _manifest); + return tplg->ops->manifest(tplg->comp, tplg->index, _manifest); if (!abi_match) /* free the duplicated one */ kfree(_manifest); -- cgit v1.2.3 From 503e79b793fea5de626db73accf8e8994bc4289d Mon Sep 17 00:00:00 2001 From: Liam Girdwood Date: Thu, 14 Jun 2018 20:53:59 +0100 Subject: ASoC: topology: Add callback for DAPM route load/unload Add a callback fro clients for notification about DAPM route loading and unloading. Signed-off-by: Liam Girdwood Signed-off-by: Mark Brown --- include/sound/soc-topology.h | 7 +++++++ sound/soc/soc-topology.c | 13 +++++++++++++ 2 files changed, 20 insertions(+) (limited to 'include') diff --git a/include/sound/soc-topology.h b/include/sound/soc-topology.h index e1f265e21ee1..401ef2c45d6c 100644 --- a/include/sound/soc-topology.h +++ b/include/sound/soc-topology.h @@ -32,6 +32,7 @@ struct snd_kcontrol_new; struct snd_soc_dai_link; struct snd_soc_dai_driver; struct snd_soc_dai; +struct snd_soc_dapm_route; /* object scan be loaded and unloaded in groups with identfying indexes */ #define SND_SOC_TPLG_INDEX_ALL 0 /* ID that matches all FW objects */ @@ -116,6 +117,12 @@ struct snd_soc_tplg_ops { int (*control_unload)(struct snd_soc_component *, struct snd_soc_dobj *); + /* DAPM graph route element loading and unloading */ + int (*dapm_route_load)(struct snd_soc_component *, int index, + struct snd_soc_dapm_route *route); + int (*dapm_route_unload)(struct snd_soc_component *, + struct snd_soc_dobj *); + /* external widget init - used for any driver specific init */ int (*widget_load)(struct snd_soc_component *, int index, struct snd_soc_dapm_widget *, diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c index 9b33260fd537..05d177d689e2 100644 --- a/sound/soc/soc-topology.c +++ b/sound/soc/soc-topology.c @@ -1105,6 +1105,17 @@ static int soc_tplg_kcontrol_elems_load(struct soc_tplg *tplg, return 0; } +/* optionally pass new dynamic kcontrol to component driver. */ +static int soc_tplg_add_route(struct soc_tplg *tplg, + struct snd_soc_dapm_route *route) +{ + if (tplg->comp && tplg->ops && tplg->ops->dapm_route_load) + return tplg->ops->dapm_route_load(tplg->comp, tplg->index, + route); + + return 0; +} + static int soc_tplg_dapm_graph_elems_load(struct soc_tplg *tplg, struct snd_soc_tplg_hdr *hdr) { @@ -1153,6 +1164,8 @@ static int soc_tplg_dapm_graph_elems_load(struct soc_tplg *tplg, else route.control = elem->control; + soc_tplg_add_route(tplg, &route); + /* add route, but keep going if some fail */ snd_soc_dapm_add_routes(dapm, &route, 1); } -- cgit v1.2.3 From 297101ab85841319aac2c7843ca755d650c1964f Mon Sep 17 00:00:00 2001 From: Stefan Wahren Date: Fri, 15 Jun 2018 13:44:53 +0200 Subject: regulator: pfuze100: add pfuze3001 support This extends the pfuze100 driver with pfuze3001 support. Latest datasheet: https://www.nxp.com/docs/en/data-sheet/PF3001.pdf Signed-off-by: Robin Gong Signed-off-by: Stefan Wahren Signed-off-by: Mark Brown --- drivers/regulator/Kconfig | 4 +- drivers/regulator/pfuze100-regulator.c | 78 +++++++++++++++++++++++++++++++--- include/linux/regulator/pfuze100.h | 11 +++++ 3 files changed, 84 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig index 5dbccf5f3037..2964eaea94c0 100644 --- a/drivers/regulator/Kconfig +++ b/drivers/regulator/Kconfig @@ -633,12 +633,12 @@ config REGULATOR_PCF50633 on PCF50633 config REGULATOR_PFUZE100 - tristate "Freescale PFUZE100/200/3000 regulator driver" + tristate "Freescale PFUZE100/200/3000/3001 regulator driver" depends on I2C select REGMAP_I2C help Say y here to support the regulators found on the Freescale - PFUZE100/200/3000 PMIC. + PFUZE100/200/3000/3001 PMIC. config REGULATOR_PV88060 tristate "Powerventure Semiconductor PV88060 regulator" diff --git a/drivers/regulator/pfuze100-regulator.c b/drivers/regulator/pfuze100-regulator.c index 8d9dbcc775ea..32f9af7f87c4 100644 --- a/drivers/regulator/pfuze100-regulator.c +++ b/drivers/regulator/pfuze100-regulator.c @@ -44,7 +44,7 @@ #define PFUZE100_VGEN5VOL 0x70 #define PFUZE100_VGEN6VOL 0x71 -enum chips { PFUZE100, PFUZE200, PFUZE3000 = 3 }; +enum chips { PFUZE100, PFUZE200, PFUZE3000 = 3, PFUZE3001 = 0x31, }; struct pfuze_regulator { struct regulator_desc desc; @@ -92,6 +92,7 @@ static const struct i2c_device_id pfuze_device_id[] = { {.name = "pfuze100", .driver_data = PFUZE100}, {.name = "pfuze200", .driver_data = PFUZE200}, {.name = "pfuze3000", .driver_data = PFUZE3000}, + {.name = "pfuze3001", .driver_data = PFUZE3001}, { } }; MODULE_DEVICE_TABLE(i2c, pfuze_device_id); @@ -100,6 +101,7 @@ static const struct of_device_id pfuze_dt_ids[] = { { .compatible = "fsl,pfuze100", .data = (void *)PFUZE100}, { .compatible = "fsl,pfuze200", .data = (void *)PFUZE200}, { .compatible = "fsl,pfuze3000", .data = (void *)PFUZE3000}, + { .compatible = "fsl,pfuze3001", .data = (void *)PFUZE3001}, { } }; MODULE_DEVICE_TABLE(of, pfuze_dt_ids); @@ -108,10 +110,28 @@ static int pfuze100_set_ramp_delay(struct regulator_dev *rdev, int ramp_delay) { struct pfuze_chip *pfuze100 = rdev_get_drvdata(rdev); int id = rdev_get_id(rdev); + bool reg_has_ramp_delay; unsigned int ramp_bits; int ret; - if (id < PFUZE100_SWBST) { + switch (pfuze100->chip_id) { + case PFUZE3001: + /* no dynamic voltage scaling for PF3001 */ + reg_has_ramp_delay = false; + break; + case PFUZE3000: + reg_has_ramp_delay = (id < PFUZE3000_SWBST); + break; + case PFUZE200: + reg_has_ramp_delay = (id < PFUZE200_SWBST); + break; + case PFUZE100: + default: + reg_has_ramp_delay = (id < PFUZE100_SWBST); + break; + } + + if (reg_has_ramp_delay) { ramp_delay = 12500 / ramp_delay; ramp_bits = (ramp_delay >> 1) - (ramp_delay >> 3); ret = regmap_update_bits(pfuze100->regmap, @@ -119,8 +139,9 @@ static int pfuze100_set_ramp_delay(struct regulator_dev *rdev, int ramp_delay) 0xc0, ramp_bits << 6); if (ret < 0) dev_err(pfuze100->dev, "ramp failed, err %d\n", ret); - } else + } else { ret = -EACCES; + } return ret; } @@ -361,6 +382,19 @@ static struct pfuze_regulator pfuze3000_regulators[] = { PFUZE100_VGEN_REG(PFUZE3000, VLDO4, PFUZE100_VGEN6VOL, 1800000, 3300000, 100000), }; +static struct pfuze_regulator pfuze3001_regulators[] = { + PFUZE100_SWB_REG(PFUZE3001, SW1, PFUZE100_SW1ABVOL, 0x1f, pfuze3000_sw1a), + PFUZE100_SWB_REG(PFUZE3001, SW2, PFUZE100_SW2VOL, 0x7, pfuze3000_sw2lo), + PFUZE3000_SW3_REG(PFUZE3001, SW3, PFUZE100_SW3AVOL, 900000, 1650000, 50000), + PFUZE100_SWB_REG(PFUZE3001, VSNVS, PFUZE100_VSNVSVOL, 0x7, pfuze100_vsnvs), + PFUZE100_VGEN_REG(PFUZE3001, VLDO1, PFUZE100_VGEN1VOL, 1800000, 3300000, 100000), + PFUZE100_VGEN_REG(PFUZE3001, VLDO2, PFUZE100_VGEN2VOL, 800000, 1550000, 50000), + PFUZE3000_VCC_REG(PFUZE3001, VCCSD, PFUZE100_VGEN3VOL, 2850000, 3300000, 150000), + PFUZE3000_VCC_REG(PFUZE3001, V33, PFUZE100_VGEN4VOL, 2850000, 3300000, 150000), + PFUZE100_VGEN_REG(PFUZE3001, VLDO3, PFUZE100_VGEN5VOL, 1800000, 3300000, 100000), + PFUZE100_VGEN_REG(PFUZE3001, VLDO4, PFUZE100_VGEN6VOL, 1800000, 3300000, 100000), +}; + #ifdef CONFIG_OF /* PFUZE100 */ static struct of_regulator_match pfuze100_matches[] = { @@ -418,6 +452,21 @@ static struct of_regulator_match pfuze3000_matches[] = { { .name = "vldo4", }, }; +/* PFUZE3001 */ +static struct of_regulator_match pfuze3001_matches[] = { + + { .name = "sw1", }, + { .name = "sw2", }, + { .name = "sw3", }, + { .name = "vsnvs", }, + { .name = "vldo1", }, + { .name = "vldo2", }, + { .name = "vccsd", }, + { .name = "v33", }, + { .name = "vldo3", }, + { .name = "vldo4", }, +}; + static struct of_regulator_match *pfuze_matches; static int pfuze_parse_regulators_dt(struct pfuze_chip *chip) @@ -437,6 +486,11 @@ static int pfuze_parse_regulators_dt(struct pfuze_chip *chip) } switch (chip->chip_id) { + case PFUZE3001: + pfuze_matches = pfuze3001_matches; + ret = of_regulator_match(dev, parent, pfuze3001_matches, + ARRAY_SIZE(pfuze3001_matches)); + break; case PFUZE3000: pfuze_matches = pfuze3000_matches; ret = of_regulator_match(dev, parent, pfuze3000_matches, @@ -508,7 +562,8 @@ static int pfuze_identify(struct pfuze_chip *pfuze_chip) */ dev_info(pfuze_chip->dev, "Assuming misprogrammed ID=0x8"); } else if ((value & 0x0f) != pfuze_chip->chip_id && - (value & 0xf0) >> 4 != pfuze_chip->chip_id) { + (value & 0xf0) >> 4 != pfuze_chip->chip_id && + (value != pfuze_chip->chip_id)) { /* device id NOT match with your setting */ dev_warn(pfuze_chip->dev, "Illegal ID: %x\n", value); return -ENODEV; @@ -588,6 +643,13 @@ static int pfuze100_regulator_probe(struct i2c_client *client, /* use the right regulators after identify the right device */ switch (pfuze_chip->chip_id) { + case PFUZE3001: + pfuze_chip->pfuze_regulators = pfuze3001_regulators; + regulator_num = ARRAY_SIZE(pfuze3001_regulators); + sw_check_start = PFUZE3001_SW2; + sw_check_end = PFUZE3001_SW2; + sw_hi = 1 << 3; + break; case PFUZE3000: pfuze_chip->pfuze_regulators = pfuze3000_regulators; regulator_num = ARRAY_SIZE(pfuze3000_regulators); @@ -611,7 +673,8 @@ static int pfuze100_regulator_probe(struct i2c_client *client, } dev_info(&client->dev, "pfuze%s found.\n", (pfuze_chip->chip_id == PFUZE100) ? "100" : - ((pfuze_chip->chip_id == PFUZE200) ? "200" : "3000")); + (((pfuze_chip->chip_id == PFUZE200) ? "200" : + ((pfuze_chip->chip_id == PFUZE3000) ? "3000" : "3001")))); memcpy(pfuze_chip->regulator_descs, pfuze_chip->pfuze_regulators, sizeof(pfuze_chip->regulator_descs)); @@ -636,7 +699,8 @@ static int pfuze100_regulator_probe(struct i2c_client *client, if (i >= sw_check_start && i <= sw_check_end) { regmap_read(pfuze_chip->regmap, desc->vsel_reg, &val); if (val & sw_hi) { - if (pfuze_chip->chip_id == PFUZE3000) { + if (pfuze_chip->chip_id == PFUZE3000 || + pfuze_chip->chip_id == PFUZE3001) { desc->volt_table = pfuze3000_sw2hi; desc->n_voltages = ARRAY_SIZE(pfuze3000_sw2hi); } else { @@ -675,5 +739,5 @@ static struct i2c_driver pfuze_driver = { module_i2c_driver(pfuze_driver); MODULE_AUTHOR("Robin Gong "); -MODULE_DESCRIPTION("Regulator Driver for Freescale PFUZE100/200/3000 PMIC"); +MODULE_DESCRIPTION("Regulator Driver for Freescale PFUZE100/200/3000/3001 PMIC"); MODULE_LICENSE("GPL v2"); diff --git a/include/linux/regulator/pfuze100.h b/include/linux/regulator/pfuze100.h index e0ccf46f66cf..cb5aecd40f07 100644 --- a/include/linux/regulator/pfuze100.h +++ b/include/linux/regulator/pfuze100.h @@ -64,6 +64,17 @@ #define PFUZE3000_VLDO3 11 #define PFUZE3000_VLDO4 12 +#define PFUZE3001_SW1 0 +#define PFUZE3001_SW2 1 +#define PFUZE3001_SW3 2 +#define PFUZE3001_VSNVS 3 +#define PFUZE3001_VLDO1 4 +#define PFUZE3001_VLDO2 5 +#define PFUZE3001_VCCSD 6 +#define PFUZE3001_V33 7 +#define PFUZE3001_VLDO3 8 +#define PFUZE3001_VLDO4 9 + struct regulator_init_data; struct pfuze_regulator_platform_data { -- cgit v1.2.3 From 7bd0c7ba62e8a9840f15fc4ff0122b29fe1b6413 Mon Sep 17 00:00:00 2001 From: Matthias Kaehlcke Date: Thu, 7 Jun 2018 16:51:38 -0700 Subject: regulator: Fix typo in comment of struct regulator_linear_range regulator_map_linar_range() => regulator_map_linear_range() Signed-off-by: Matthias Kaehlcke Signed-off-by: Mark Brown --- include/linux/regulator/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index fc2dc8df476f..dea96ee39fdc 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -46,7 +46,7 @@ enum regulator_status { /** * struct regulator_linear_range - specify linear voltage ranges * - * Specify a range of voltages for regulator_map_linar_range() and + * Specify a range of voltages for regulator_map_linear_range() and * regulator_list_linear_range(). * * @min_uV: Lowest voltage in range -- cgit v1.2.3 From 3e247b0fb540a9a503a71ef6b918a3443e49655f Mon Sep 17 00:00:00 2001 From: Corentin Labbe Date: Thu, 7 Jun 2018 19:40:32 +0000 Subject: spi: remove unused adi_spi3.h header include/linux/spi/adi_spi3.h is unused since commit 47838669de9d ("spi: remove blackfin related host drivers") Finish the cleaning by removing it. Signed-off-by: Corentin Labbe Signed-off-by: Mark Brown --- include/linux/spi/adi_spi3.h | 254 ------------------------------------------- 1 file changed, 254 deletions(-) delete mode 100644 include/linux/spi/adi_spi3.h (limited to 'include') diff --git a/include/linux/spi/adi_spi3.h b/include/linux/spi/adi_spi3.h deleted file mode 100644 index c84123aa1d06..000000000000 --- a/include/linux/spi/adi_spi3.h +++ /dev/null @@ -1,254 +0,0 @@ -/* - * Analog Devices SPI3 controller driver - * - * Copyright (c) 2014 Analog Devices Inc. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - */ - -#ifndef _ADI_SPI3_H_ -#define _ADI_SPI3_H_ - -#include - -/* SPI_CONTROL */ -#define SPI_CTL_EN 0x00000001 /* Enable */ -#define SPI_CTL_MSTR 0x00000002 /* Master/Slave */ -#define SPI_CTL_PSSE 0x00000004 /* controls modf error in master mode */ -#define SPI_CTL_ODM 0x00000008 /* Open Drain Mode */ -#define SPI_CTL_CPHA 0x00000010 /* Clock Phase */ -#define SPI_CTL_CPOL 0x00000020 /* Clock Polarity */ -#define SPI_CTL_ASSEL 0x00000040 /* Slave Select Pin Control */ -#define SPI_CTL_SELST 0x00000080 /* Slave Select Polarity in-between transfers */ -#define SPI_CTL_EMISO 0x00000100 /* Enable MISO */ -#define SPI_CTL_SIZE 0x00000600 /* Word Transfer Size */ -#define SPI_CTL_SIZE08 0x00000000 /* SIZE: 8 bits */ -#define SPI_CTL_SIZE16 0x00000200 /* SIZE: 16 bits */ -#define SPI_CTL_SIZE32 0x00000400 /* SIZE: 32 bits */ -#define SPI_CTL_LSBF 0x00001000 /* LSB First */ -#define SPI_CTL_FCEN 0x00002000 /* Flow-Control Enable */ -#define SPI_CTL_FCCH 0x00004000 /* Flow-Control Channel Selection */ -#define SPI_CTL_FCPL 0x00008000 /* Flow-Control Polarity */ -#define SPI_CTL_FCWM 0x00030000 /* Flow-Control Water-Mark */ -#define SPI_CTL_FIFO0 0x00000000 /* FCWM: TFIFO empty or RFIFO Full */ -#define SPI_CTL_FIFO1 0x00010000 /* FCWM: TFIFO 75% or more empty or RFIFO 75% or more full */ -#define SPI_CTL_FIFO2 0x00020000 /* FCWM: TFIFO 50% or more empty or RFIFO 50% or more full */ -#define SPI_CTL_FMODE 0x00040000 /* Fast-mode Enable */ -#define SPI_CTL_MIOM 0x00300000 /* Multiple I/O Mode */ -#define SPI_CTL_MIO_DIS 0x00000000 /* MIOM: Disable */ -#define SPI_CTL_MIO_DUAL 0x00100000 /* MIOM: Enable DIOM (Dual I/O Mode) */ -#define SPI_CTL_MIO_QUAD 0x00200000 /* MIOM: Enable QUAD (Quad SPI Mode) */ -#define SPI_CTL_SOSI 0x00400000 /* Start on MOSI */ -/* SPI_RX_CONTROL */ -#define SPI_RXCTL_REN 0x00000001 /* Receive Channel Enable */ -#define SPI_RXCTL_RTI 0x00000004 /* Receive Transfer Initiate */ -#define SPI_RXCTL_RWCEN 0x00000008 /* Receive Word Counter Enable */ -#define SPI_RXCTL_RDR 0x00000070 /* Receive Data Request */ -#define SPI_RXCTL_RDR_DIS 0x00000000 /* RDR: Disabled */ -#define SPI_RXCTL_RDR_NE 0x00000010 /* RDR: RFIFO not empty */ -#define SPI_RXCTL_RDR_25 0x00000020 /* RDR: RFIFO 25% full */ -#define SPI_RXCTL_RDR_50 0x00000030 /* RDR: RFIFO 50% full */ -#define SPI_RXCTL_RDR_75 0x00000040 /* RDR: RFIFO 75% full */ -#define SPI_RXCTL_RDR_FULL 0x00000050 /* RDR: RFIFO full */ -#define SPI_RXCTL_RDO 0x00000100 /* Receive Data Over-Run */ -#define SPI_RXCTL_RRWM 0x00003000 /* FIFO Regular Water-Mark */ -#define SPI_RXCTL_RWM_0 0x00000000 /* RRWM: RFIFO Empty */ -#define SPI_RXCTL_RWM_25 0x00001000 /* RRWM: RFIFO 25% full */ -#define SPI_RXCTL_RWM_50 0x00002000 /* RRWM: RFIFO 50% full */ -#define SPI_RXCTL_RWM_75 0x00003000 /* RRWM: RFIFO 75% full */ -#define SPI_RXCTL_RUWM 0x00070000 /* FIFO Urgent Water-Mark */ -#define SPI_RXCTL_UWM_DIS 0x00000000 /* RUWM: Disabled */ -#define SPI_RXCTL_UWM_25 0x00010000 /* RUWM: RFIFO 25% full */ -#define SPI_RXCTL_UWM_50 0x00020000 /* RUWM: RFIFO 50% full */ -#define SPI_RXCTL_UWM_75 0x00030000 /* RUWM: RFIFO 75% full */ -#define SPI_RXCTL_UWM_FULL 0x00040000 /* RUWM: RFIFO full */ -/* SPI_TX_CONTROL */ -#define SPI_TXCTL_TEN 0x00000001 /* Transmit Channel Enable */ -#define SPI_TXCTL_TTI 0x00000004 /* Transmit Transfer Initiate */ -#define SPI_TXCTL_TWCEN 0x00000008 /* Transmit Word Counter Enable */ -#define SPI_TXCTL_TDR 0x00000070 /* Transmit Data Request */ -#define SPI_TXCTL_TDR_DIS 0x00000000 /* TDR: Disabled */ -#define SPI_TXCTL_TDR_NF 0x00000010 /* TDR: TFIFO not full */ -#define SPI_TXCTL_TDR_25 0x00000020 /* TDR: TFIFO 25% empty */ -#define SPI_TXCTL_TDR_50 0x00000030 /* TDR: TFIFO 50% empty */ -#define SPI_TXCTL_TDR_75 0x00000040 /* TDR: TFIFO 75% empty */ -#define SPI_TXCTL_TDR_EMPTY 0x00000050 /* TDR: TFIFO empty */ -#define SPI_TXCTL_TDU 0x00000100 /* Transmit Data Under-Run */ -#define SPI_TXCTL_TRWM 0x00003000 /* FIFO Regular Water-Mark */ -#define SPI_TXCTL_RWM_FULL 0x00000000 /* TRWM: TFIFO full */ -#define SPI_TXCTL_RWM_25 0x00001000 /* TRWM: TFIFO 25% empty */ -#define SPI_TXCTL_RWM_50 0x00002000 /* TRWM: TFIFO 50% empty */ -#define SPI_TXCTL_RWM_75 0x00003000 /* TRWM: TFIFO 75% empty */ -#define SPI_TXCTL_TUWM 0x00070000 /* FIFO Urgent Water-Mark */ -#define SPI_TXCTL_UWM_DIS 0x00000000 /* TUWM: Disabled */ -#define SPI_TXCTL_UWM_25 0x00010000 /* TUWM: TFIFO 25% empty */ -#define SPI_TXCTL_UWM_50 0x00020000 /* TUWM: TFIFO 50% empty */ -#define SPI_TXCTL_UWM_75 0x00030000 /* TUWM: TFIFO 75% empty */ -#define SPI_TXCTL_UWM_EMPTY 0x00040000 /* TUWM: TFIFO empty */ -/* SPI_CLOCK */ -#define SPI_CLK_BAUD 0x0000FFFF /* Baud Rate */ -/* SPI_DELAY */ -#define SPI_DLY_STOP 0x000000FF /* Transfer delay time in multiples of SCK period */ -#define SPI_DLY_LEADX 0x00000100 /* Extended (1 SCK) LEAD Control */ -#define SPI_DLY_LAGX 0x00000200 /* Extended (1 SCK) LAG control */ -/* SPI_SSEL */ -#define SPI_SLVSEL_SSE1 0x00000002 /* SPISSEL1 Enable */ -#define SPI_SLVSEL_SSE2 0x00000004 /* SPISSEL2 Enable */ -#define SPI_SLVSEL_SSE3 0x00000008 /* SPISSEL3 Enable */ -#define SPI_SLVSEL_SSE4 0x00000010 /* SPISSEL4 Enable */ -#define SPI_SLVSEL_SSE5 0x00000020 /* SPISSEL5 Enable */ -#define SPI_SLVSEL_SSE6 0x00000040 /* SPISSEL6 Enable */ -#define SPI_SLVSEL_SSE7 0x00000080 /* SPISSEL7 Enable */ -#define SPI_SLVSEL_SSEL1 0x00000200 /* SPISSEL1 Value */ -#define SPI_SLVSEL_SSEL2 0x00000400 /* SPISSEL2 Value */ -#define SPI_SLVSEL_SSEL3 0x00000800 /* SPISSEL3 Value */ -#define SPI_SLVSEL_SSEL4 0x00001000 /* SPISSEL4 Value */ -#define SPI_SLVSEL_SSEL5 0x00002000 /* SPISSEL5 Value */ -#define SPI_SLVSEL_SSEL6 0x00004000 /* SPISSEL6 Value */ -#define SPI_SLVSEL_SSEL7 0x00008000 /* SPISSEL7 Value */ -/* SPI_RWC */ -#define SPI_RWC_VALUE 0x0000FFFF /* Received Word-Count */ -/* SPI_RWCR */ -#define SPI_RWCR_VALUE 0x0000FFFF /* Received Word-Count Reload */ -/* SPI_TWC */ -#define SPI_TWC_VALUE 0x0000FFFF /* Transmitted Word-Count */ -/* SPI_TWCR */ -#define SPI_TWCR_VALUE 0x0000FFFF /* Transmitted Word-Count Reload */ -/* SPI_IMASK */ -#define SPI_IMSK_RUWM 0x00000002 /* Receive Urgent Water-Mark Interrupt Mask */ -#define SPI_IMSK_TUWM 0x00000004 /* Transmit Urgent Water-Mark Interrupt Mask */ -#define SPI_IMSK_ROM 0x00000010 /* Receive Over-Run Error Interrupt Mask */ -#define SPI_IMSK_TUM 0x00000020 /* Transmit Under-Run Error Interrupt Mask */ -#define SPI_IMSK_TCM 0x00000040 /* Transmit Collision Error Interrupt Mask */ -#define SPI_IMSK_MFM 0x00000080 /* Mode Fault Error Interrupt Mask */ -#define SPI_IMSK_RSM 0x00000100 /* Receive Start Interrupt Mask */ -#define SPI_IMSK_TSM 0x00000200 /* Transmit Start Interrupt Mask */ -#define SPI_IMSK_RFM 0x00000400 /* Receive Finish Interrupt Mask */ -#define SPI_IMSK_TFM 0x00000800 /* Transmit Finish Interrupt Mask */ -/* SPI_IMASKCL */ -#define SPI_IMSK_CLR_RUW 0x00000002 /* Receive Urgent Water-Mark Interrupt Mask */ -#define SPI_IMSK_CLR_TUWM 0x00000004 /* Transmit Urgent Water-Mark Interrupt Mask */ -#define SPI_IMSK_CLR_ROM 0x00000010 /* Receive Over-Run Error Interrupt Mask */ -#define SPI_IMSK_CLR_TUM 0x00000020 /* Transmit Under-Run Error Interrupt Mask */ -#define SPI_IMSK_CLR_TCM 0x00000040 /* Transmit Collision Error Interrupt Mask */ -#define SPI_IMSK_CLR_MFM 0x00000080 /* Mode Fault Error Interrupt Mask */ -#define SPI_IMSK_CLR_RSM 0x00000100 /* Receive Start Interrupt Mask */ -#define SPI_IMSK_CLR_TSM 0x00000200 /* Transmit Start Interrupt Mask */ -#define SPI_IMSK_CLR_RFM 0x00000400 /* Receive Finish Interrupt Mask */ -#define SPI_IMSK_CLR_TFM 0x00000800 /* Transmit Finish Interrupt Mask */ -/* SPI_IMASKST */ -#define SPI_IMSK_SET_RUWM 0x00000002 /* Receive Urgent Water-Mark Interrupt Mask */ -#define SPI_IMSK_SET_TUWM 0x00000004 /* Transmit Urgent Water-Mark Interrupt Mask */ -#define SPI_IMSK_SET_ROM 0x00000010 /* Receive Over-Run Error Interrupt Mask */ -#define SPI_IMSK_SET_TUM 0x00000020 /* Transmit Under-Run Error Interrupt Mask */ -#define SPI_IMSK_SET_TCM 0x00000040 /* Transmit Collision Error Interrupt Mask */ -#define SPI_IMSK_SET_MFM 0x00000080 /* Mode Fault Error Interrupt Mask */ -#define SPI_IMSK_SET_RSM 0x00000100 /* Receive Start Interrupt Mask */ -#define SPI_IMSK_SET_TSM 0x00000200 /* Transmit Start Interrupt Mask */ -#define SPI_IMSK_SET_RFM 0x00000400 /* Receive Finish Interrupt Mask */ -#define SPI_IMSK_SET_TFM 0x00000800 /* Transmit Finish Interrupt Mask */ -/* SPI_STATUS */ -#define SPI_STAT_SPIF 0x00000001 /* SPI Finished */ -#define SPI_STAT_RUWM 0x00000002 /* Receive Urgent Water-Mark Breached */ -#define SPI_STAT_TUWM 0x00000004 /* Transmit Urgent Water-Mark Breached */ -#define SPI_STAT_ROE 0x00000010 /* Receive Over-Run Error Indication */ -#define SPI_STAT_TUE 0x00000020 /* Transmit Under-Run Error Indication */ -#define SPI_STAT_TCE 0x00000040 /* Transmit Collision Error Indication */ -#define SPI_STAT_MODF 0x00000080 /* Mode Fault Error Indication */ -#define SPI_STAT_RS 0x00000100 /* Receive Start Indication */ -#define SPI_STAT_TS 0x00000200 /* Transmit Start Indication */ -#define SPI_STAT_RF 0x00000400 /* Receive Finish Indication */ -#define SPI_STAT_TF 0x00000800 /* Transmit Finish Indication */ -#define SPI_STAT_RFS 0x00007000 /* SPI_RFIFO status */ -#define SPI_STAT_RFIFO_EMPTY 0x00000000 /* RFS: RFIFO Empty */ -#define SPI_STAT_RFIFO_25 0x00001000 /* RFS: RFIFO 25% Full */ -#define SPI_STAT_RFIFO_50 0x00002000 /* RFS: RFIFO 50% Full */ -#define SPI_STAT_RFIFO_75 0x00003000 /* RFS: RFIFO 75% Full */ -#define SPI_STAT_RFIFO_FULL 0x00004000 /* RFS: RFIFO Full */ -#define SPI_STAT_TFS 0x00070000 /* SPI_TFIFO status */ -#define SPI_STAT_TFIFO_FULL 0x00000000 /* TFS: TFIFO full */ -#define SPI_STAT_TFIFO_25 0x00010000 /* TFS: TFIFO 25% empty */ -#define SPI_STAT_TFIFO_50 0x00020000 /* TFS: TFIFO 50% empty */ -#define SPI_STAT_TFIFO_75 0x00030000 /* TFS: TFIFO 75% empty */ -#define SPI_STAT_TFIFO_EMPTY 0x00040000 /* TFS: TFIFO empty */ -#define SPI_STAT_FCS 0x00100000 /* Flow-Control Stall Indication */ -#define SPI_STAT_RFE 0x00400000 /* SPI_RFIFO Empty */ -#define SPI_STAT_TFF 0x00800000 /* SPI_TFIFO Full */ -/* SPI_ILAT */ -#define SPI_ILAT_RUWMI 0x00000002 /* Receive Urgent Water Mark Interrupt */ -#define SPI_ILAT_TUWMI 0x00000004 /* Transmit Urgent Water Mark Interrupt */ -#define SPI_ILAT_ROI 0x00000010 /* Receive Over-Run Error Indication */ -#define SPI_ILAT_TUI 0x00000020 /* Transmit Under-Run Error Indication */ -#define SPI_ILAT_TCI 0x00000040 /* Transmit Collision Error Indication */ -#define SPI_ILAT_MFI 0x00000080 /* Mode Fault Error Indication */ -#define SPI_ILAT_RSI 0x00000100 /* Receive Start Indication */ -#define SPI_ILAT_TSI 0x00000200 /* Transmit Start Indication */ -#define SPI_ILAT_RFI 0x00000400 /* Receive Finish Indication */ -#define SPI_ILAT_TFI 0x00000800 /* Transmit Finish Indication */ -/* SPI_ILATCL */ -#define SPI_ILAT_CLR_RUWMI 0x00000002 /* Receive Urgent Water Mark Interrupt */ -#define SPI_ILAT_CLR_TUWMI 0x00000004 /* Transmit Urgent Water Mark Interrupt */ -#define SPI_ILAT_CLR_ROI 0x00000010 /* Receive Over-Run Error Indication */ -#define SPI_ILAT_CLR_TUI 0x00000020 /* Transmit Under-Run Error Indication */ -#define SPI_ILAT_CLR_TCI 0x00000040 /* Transmit Collision Error Indication */ -#define SPI_ILAT_CLR_MFI 0x00000080 /* Mode Fault Error Indication */ -#define SPI_ILAT_CLR_RSI 0x00000100 /* Receive Start Indication */ -#define SPI_ILAT_CLR_TSI 0x00000200 /* Transmit Start Indication */ -#define SPI_ILAT_CLR_RFI 0x00000400 /* Receive Finish Indication */ -#define SPI_ILAT_CLR_TFI 0x00000800 /* Transmit Finish Indication */ - -/* - * adi spi3 registers layout - */ -struct adi_spi_regs { - u32 revid; - u32 control; - u32 rx_control; - u32 tx_control; - u32 clock; - u32 delay; - u32 ssel; - u32 rwc; - u32 rwcr; - u32 twc; - u32 twcr; - u32 reserved0; - u32 emask; - u32 emaskcl; - u32 emaskst; - u32 reserved1; - u32 status; - u32 elat; - u32 elatcl; - u32 reserved2; - u32 rfifo; - u32 reserved3; - u32 tfifo; -}; - -#define MAX_CTRL_CS 8 /* cs in spi controller */ - -/* device.platform_data for SSP controller devices */ -struct adi_spi3_master { - u16 num_chipselect; - u16 pin_req[7]; -}; - -/* spi_board_info.controller_data for SPI slave devices, - * copied to spi_device.platform_data ... mostly for dma tuning - */ -struct adi_spi3_chip { - u32 control; - u16 cs_chg_udelay; /* Some devices require 16-bit delays */ - u32 tx_dummy_val; /* tx value for rx only transfer */ - bool enable_dma; -}; - -#endif /* _ADI_SPI3_H_ */ -- cgit v1.2.3 From 62c2c9fcac4341d306dda4cf400b77e7e124480a Mon Sep 17 00:00:00 2001 From: Katsuhiro Suzuki Date: Mon, 11 Jun 2018 17:32:12 +0900 Subject: ASoC: simple-card-utils: move hp and mic detect gpios from simple-card This patch moves headphone and microphone jack detection gpios from simple-card driver. It is preparing for using this feature from other drivers. Signed-off-by: Katsuhiro Suzuki Acked-by: Kuninori Morimoto Signed-off-by: Mark Brown --- include/sound/simple_card_utils.h | 15 ++++++++ sound/soc/generic/simple-card-utils.c | 59 ++++++++++++++++++++++++++++++++ sound/soc/generic/simple-card.c | 64 ----------------------------------- 3 files changed, 74 insertions(+), 64 deletions(-) (limited to 'include') diff --git a/include/sound/simple_card_utils.h b/include/sound/simple_card_utils.h index 7e25afce6566..f82acef3b992 100644 --- a/include/sound/simple_card_utils.h +++ b/include/sound/simple_card_utils.h @@ -12,6 +12,11 @@ #include +#define asoc_simple_card_init_hp(card, sjack, prefix) \ + asoc_simple_card_init_jack(card, sjack, 1, prefix) +#define asoc_simple_card_init_mic(card, sjack, prefix) \ + asoc_simple_card_init_jack(card, sjack, 0, prefix) + struct asoc_simple_dai { const char *name; unsigned int sysclk; @@ -28,6 +33,12 @@ struct asoc_simple_card_data { u32 convert_channels; }; +struct asoc_simple_jack { + struct snd_soc_jack jack; + struct snd_soc_jack_pin pin; + struct snd_soc_jack_gpio gpio; +}; + int asoc_simple_card_parse_daifmt(struct device *dev, struct device_node *node, struct device_node *codec, @@ -107,4 +118,8 @@ int asoc_simple_card_of_parse_routing(struct snd_soc_card *card, int asoc_simple_card_of_parse_widgets(struct snd_soc_card *card, char *prefix); +int asoc_simple_card_init_jack(struct snd_soc_card *card, + struct asoc_simple_jack *sjack, + int is_hp, char *prefix); + #endif /* __SIMPLE_CARD_UTILS_H */ diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c index 3751a07de6aa..4398c9580929 100644 --- a/sound/soc/generic/simple-card-utils.c +++ b/sound/soc/generic/simple-card-utils.c @@ -8,9 +8,13 @@ * published by the Free Software Foundation. */ #include +#include +#include #include #include +#include #include +#include #include void asoc_simple_card_convert_fixup(struct asoc_simple_card_data *data, @@ -419,6 +423,61 @@ int asoc_simple_card_of_parse_widgets(struct snd_soc_card *card, } EXPORT_SYMBOL_GPL(asoc_simple_card_of_parse_widgets); +int asoc_simple_card_init_jack(struct snd_soc_card *card, + struct asoc_simple_jack *sjack, + int is_hp, char *prefix) +{ + struct device *dev = card->dev; + enum of_gpio_flags flags; + char prop[128]; + char *pin_name; + char *gpio_name; + int mask; + int det; + + if (!prefix) + prefix = ""; + + sjack->gpio.gpio = -ENOENT; + + if (is_hp) { + snprintf(prop, sizeof(prop), "%shp-det-gpio", prefix); + pin_name = "Headphones"; + gpio_name = "Headphone detection"; + mask = SND_JACK_HEADPHONE; + } else { + snprintf(prop, sizeof(prop), "%smic-det-gpio", prefix); + pin_name = "Mic Jack"; + gpio_name = "Mic detection"; + mask = SND_JACK_MICROPHONE; + } + + det = of_get_named_gpio_flags(dev->of_node, prop, 0, &flags); + if (det == -EPROBE_DEFER) + return -EPROBE_DEFER; + + if (gpio_is_valid(det)) { + sjack->pin.pin = pin_name; + sjack->pin.mask = mask; + + sjack->gpio.name = gpio_name; + sjack->gpio.report = mask; + sjack->gpio.gpio = det; + sjack->gpio.invert = !!(flags & OF_GPIO_ACTIVE_LOW); + sjack->gpio.debounce_time = 150; + + snd_soc_card_jack_new(card, pin_name, mask, + &sjack->jack, + &sjack->pin, 1); + + snd_soc_jack_add_gpios(&sjack->jack, 1, + &sjack->gpio); + } + + return 0; +} +EXPORT_SYMBOL_GPL(asoc_simple_card_init_jack); + /* Module information */ MODULE_AUTHOR("Kuninori Morimoto "); MODULE_DESCRIPTION("ALSA SoC Simple Card Utils"); diff --git a/sound/soc/generic/simple-card.c b/sound/soc/generic/simple-card.c index 8b374af86a6e..a6477a022156 100644 --- a/sound/soc/generic/simple-card.c +++ b/sound/soc/generic/simple-card.c @@ -10,23 +10,14 @@ */ #include #include -#include #include #include -#include #include #include -#include #include #include #include -struct asoc_simple_jack { - struct snd_soc_jack jack; - struct snd_soc_jack_pin pin; - struct snd_soc_jack_gpio gpio; -}; - struct simple_card_data { struct snd_soc_card snd_card; struct simple_dai_props { @@ -49,61 +40,6 @@ struct simple_card_data { #define CELL "#sound-dai-cells" #define PREFIX "simple-audio-card," -#define asoc_simple_card_init_hp(card, sjack, prefix)\ - asoc_simple_card_init_jack(card, sjack, 1, prefix) -#define asoc_simple_card_init_mic(card, sjack, prefix)\ - asoc_simple_card_init_jack(card, sjack, 0, prefix) -static int asoc_simple_card_init_jack(struct snd_soc_card *card, - struct asoc_simple_jack *sjack, - int is_hp, char *prefix) -{ - struct device *dev = card->dev; - enum of_gpio_flags flags; - char prop[128]; - char *pin_name; - char *gpio_name; - int mask; - int det; - - sjack->gpio.gpio = -ENOENT; - - if (is_hp) { - snprintf(prop, sizeof(prop), "%shp-det-gpio", prefix); - pin_name = "Headphones"; - gpio_name = "Headphone detection"; - mask = SND_JACK_HEADPHONE; - } else { - snprintf(prop, sizeof(prop), "%smic-det-gpio", prefix); - pin_name = "Mic Jack"; - gpio_name = "Mic detection"; - mask = SND_JACK_MICROPHONE; - } - - det = of_get_named_gpio_flags(dev->of_node, prop, 0, &flags); - if (det == -EPROBE_DEFER) - return -EPROBE_DEFER; - - if (gpio_is_valid(det)) { - sjack->pin.pin = pin_name; - sjack->pin.mask = mask; - - sjack->gpio.name = gpio_name; - sjack->gpio.report = mask; - sjack->gpio.gpio = det; - sjack->gpio.invert = !!(flags & OF_GPIO_ACTIVE_LOW); - sjack->gpio.debounce_time = 150; - - snd_soc_card_jack_new(card, pin_name, mask, - &sjack->jack, - &sjack->pin, 1); - - snd_soc_jack_add_gpios(&sjack->jack, 1, - &sjack->gpio); - } - - return 0; -} - static int asoc_simple_card_startup(struct snd_pcm_substream *substream) { struct snd_soc_pcm_runtime *rtd = substream->private_data; -- cgit v1.2.3 From 0ddce71c21f03fd19867c4939d3ca710f37cdf1a Mon Sep 17 00:00:00 2001 From: Bard Liao Date: Thu, 7 Jun 2018 16:37:38 +0800 Subject: ASoC: rt5682: add rt5682 codec driver This is the initial codec driver for rt5682. Signed-off-by: Bard Liao Signed-off-by: Mark Brown --- Documentation/devicetree/bindings/sound/rt5682.txt | 50 + include/sound/rt5682.h | 40 + sound/soc/codecs/Kconfig | 6 + sound/soc/codecs/Makefile | 2 + sound/soc/codecs/rt5682.c | 2682 ++++++++++++++++++++ sound/soc/codecs/rt5682.h | 1324 ++++++++++ 6 files changed, 4104 insertions(+) create mode 100644 Documentation/devicetree/bindings/sound/rt5682.txt create mode 100644 include/sound/rt5682.h create mode 100644 sound/soc/codecs/rt5682.c create mode 100644 sound/soc/codecs/rt5682.h (limited to 'include') diff --git a/Documentation/devicetree/bindings/sound/rt5682.txt b/Documentation/devicetree/bindings/sound/rt5682.txt new file mode 100644 index 000000000000..312e9a129530 --- /dev/null +++ b/Documentation/devicetree/bindings/sound/rt5682.txt @@ -0,0 +1,50 @@ +RT5682 audio CODEC + +This device supports I2C only. + +Required properties: + +- compatible : "realtek,rt5682" or "realtek,rt5682i" + +- reg : The I2C address of the device. + +Optional properties: + +- interrupts : The CODEC's interrupt output. + +- realtek,dmic1-data-pin + 0: dmic1 is not used + 1: using GPIO2 pin as dmic1 data pin + 2: using GPIO5 pin as dmic1 data pin + +- realtek,dmic1-clk-pin + 0: using GPIO1 pin as dmic1 clock pin + 1: using GPIO3 pin as dmic1 clock pin + +- realtek,jd-src + 0: No JD is used + 1: using JD1 as JD source + +- realtek,ldo1-en-gpios : The GPIO that controls the CODEC's LDO1_EN pin. + +Pins on the device (for linking into audio routes) for RT5682: + + * DMIC L1 + * DMIC R1 + * IN1P + * HPOL + * HPOR + +Example: + +rt5682 { + compatible = "realtek,rt5682i"; + reg = <0x1a>; + interrupt-parent = <&gpio>; + interrupts = ; + realtek,ldo1-en-gpios = + <&gpio TEGRA_GPIO(R, 2) GPIO_ACTIVE_HIGH>; + realtek,dmic1-data-pin = <1>; + realtek,dmic1-clk-pin = <1>; + realtek,jd-src = <1>; +}; diff --git a/include/sound/rt5682.h b/include/sound/rt5682.h new file mode 100644 index 000000000000..0251797ab438 --- /dev/null +++ b/include/sound/rt5682.h @@ -0,0 +1,40 @@ +/* + * linux/sound/rt5682.h -- Platform data for RT5682 + * + * Copyright 2018 Realtek Microelectronics + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __LINUX_SND_RT5682_H +#define __LINUX_SND_RT5682_H + +enum rt5682_dmic1_data_pin { + RT5682_DMIC1_NULL, + RT5682_DMIC1_DATA_GPIO2, + RT5682_DMIC1_DATA_GPIO5, +}; + +enum rt5682_dmic1_clk_pin { + RT5682_DMIC1_CLK_GPIO1, + RT5682_DMIC1_CLK_GPIO3, +}; + +enum rt5682_jd_src { + RT5682_JD_NULL, + RT5682_JD1, +}; + +struct rt5682_platform_data { + + int ldo1_en; /* GPIO for LDO1_EN */ + + enum rt5682_dmic1_data_pin dmic1_data_pin; + enum rt5682_dmic1_clk_pin dmic1_clk_pin; + enum rt5682_jd_src jd_src; +}; + +#endif + diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig index 63cf62e9c9aa..f6b8d4bf8796 100644 --- a/sound/soc/codecs/Kconfig +++ b/sound/soc/codecs/Kconfig @@ -141,6 +141,7 @@ config SND_SOC_ALL_CODECS select SND_SOC_RT5668 if I2C select SND_SOC_RT5670 if I2C select SND_SOC_RT5677 if I2C && SPI_MASTER + select SND_SOC_RT5682 if I2C select SND_SOC_SGTL5000 if I2C select SND_SOC_SI476X if MFD_SI476X_CORE select SND_SOC_SIRF_AUDIO_CODEC @@ -778,6 +779,7 @@ config SND_SOC_RL6231 default y if SND_SOC_RT5668=y default y if SND_SOC_RT5670=y default y if SND_SOC_RT5677=y + default y if SND_SOC_RT5682=y default y if SND_SOC_RT1305=y default m if SND_SOC_RT5514=m default m if SND_SOC_RT5616=m @@ -791,6 +793,7 @@ config SND_SOC_RL6231 default m if SND_SOC_RT5668=m default m if SND_SOC_RT5670=m default m if SND_SOC_RT5677=m + default m if SND_SOC_RT5682=m default m if SND_SOC_RT1305=m config SND_SOC_RL6347A @@ -871,6 +874,9 @@ config SND_SOC_RT5677_SPI tristate default SND_SOC_RT5677 && SPI +config SND_SOC_RT5682 + tristate + #Freescale sgtl5000 codec config SND_SOC_SGTL5000 tristate "Freescale SGTL5000 CODEC" diff --git a/sound/soc/codecs/Makefile b/sound/soc/codecs/Makefile index e023fdf85221..e43d99a039d3 100644 --- a/sound/soc/codecs/Makefile +++ b/sound/soc/codecs/Makefile @@ -146,6 +146,7 @@ snd-soc-rt5668-objs := rt5668.o snd-soc-rt5670-objs := rt5670.o snd-soc-rt5677-objs := rt5677.o snd-soc-rt5677-spi-objs := rt5677-spi.o +snd-soc-rt5682-objs := rt5682.o snd-soc-sgtl5000-objs := sgtl5000.o snd-soc-alc5623-objs := alc5623.o snd-soc-alc5632-objs := alc5632.o @@ -405,6 +406,7 @@ obj-$(CONFIG_SND_SOC_RT5668) += snd-soc-rt5668.o obj-$(CONFIG_SND_SOC_RT5670) += snd-soc-rt5670.o obj-$(CONFIG_SND_SOC_RT5677) += snd-soc-rt5677.o obj-$(CONFIG_SND_SOC_RT5677_SPI) += snd-soc-rt5677-spi.o +obj-$(CONFIG_SND_SOC_RT5682) += snd-soc-rt5682.o obj-$(CONFIG_SND_SOC_SGTL5000) += snd-soc-sgtl5000.o obj-$(CONFIG_SND_SOC_SIGMADSP) += snd-soc-sigmadsp.o obj-$(CONFIG_SND_SOC_SIGMADSP_I2C) += snd-soc-sigmadsp-i2c.o diff --git a/sound/soc/codecs/rt5682.c b/sound/soc/codecs/rt5682.c new file mode 100644 index 000000000000..61a97301bcfa --- /dev/null +++ b/sound/soc/codecs/rt5682.c @@ -0,0 +1,2682 @@ +/* + * rt5682.c -- RT5682 ALSA SoC audio component driver + * + * Copyright 2018 Realtek Semiconductor Corp. + * Author: Bard Liao + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "rl6231.h" +#include "rt5682.h" + +#define RT5682_NUM_SUPPLIES 3 + +static const char *rt5682_supply_names[RT5682_NUM_SUPPLIES] = { + "AVDD", + "MICVDD", + "VBAT", +}; + +struct rt5682_priv { + struct snd_soc_component *component; + struct rt5682_platform_data pdata; + struct regmap *regmap; + struct snd_soc_jack *hs_jack; + struct regulator_bulk_data supplies[RT5682_NUM_SUPPLIES]; + struct delayed_work jack_detect_work; + struct delayed_work jd_check_work; + struct mutex calibrate_mutex; + + int sysclk; + int sysclk_src; + int lrck[RT5682_AIFS]; + int bclk[RT5682_AIFS]; + int master[RT5682_AIFS]; + + int pll_src; + int pll_in; + int pll_out; + + int jack_type; +}; + +static const struct reg_sequence patch_list[] = { + {0x01c1, 0x1000}, +}; + +static const struct reg_default rt5682_reg[] = { + {0x0002, 0x8080}, + {0x0003, 0x8000}, + {0x0005, 0x0000}, + {0x0006, 0x0000}, + {0x0008, 0x800f}, + {0x000b, 0x0000}, + {0x0010, 0x4040}, + {0x0011, 0x0000}, + {0x0012, 0x1404}, + {0x0013, 0x1000}, + {0x0014, 0xa00a}, + {0x0015, 0x0404}, + {0x0016, 0x0404}, + {0x0019, 0xafaf}, + {0x001c, 0x2f2f}, + {0x001f, 0x0000}, + {0x0022, 0x5757}, + {0x0023, 0x0039}, + {0x0024, 0x000b}, + {0x0026, 0xc0c4}, + {0x0029, 0x8080}, + {0x002a, 0xa0a0}, + {0x002b, 0x0300}, + {0x0030, 0x0000}, + {0x003c, 0x0080}, + {0x0044, 0x0c0c}, + {0x0049, 0x0000}, + {0x0061, 0x0000}, + {0x0062, 0x0000}, + {0x0063, 0x003f}, + {0x0064, 0x0000}, + {0x0065, 0x0000}, + {0x0066, 0x0030}, + {0x0067, 0x0000}, + {0x006b, 0x0000}, + {0x006c, 0x0000}, + {0x006d, 0x2200}, + {0x006e, 0x0a10}, + {0x0070, 0x8000}, + {0x0071, 0x8000}, + {0x0073, 0x0000}, + {0x0074, 0x0000}, + {0x0075, 0x0002}, + {0x0076, 0x0001}, + {0x0079, 0x0000}, + {0x007a, 0x0000}, + {0x007b, 0x0000}, + {0x007c, 0x0100}, + {0x007e, 0x0000}, + {0x0080, 0x0000}, + {0x0081, 0x0000}, + {0x0082, 0x0000}, + {0x0083, 0x0000}, + {0x0084, 0x0000}, + {0x0085, 0x0000}, + {0x0086, 0x0005}, + {0x0087, 0x0000}, + {0x0088, 0x0000}, + {0x008c, 0x0003}, + {0x008d, 0x0000}, + {0x008e, 0x0060}, + {0x008f, 0x1000}, + {0x0091, 0x0c26}, + {0x0092, 0x0073}, + {0x0093, 0x0000}, + {0x0094, 0x0080}, + {0x0098, 0x0000}, + {0x009a, 0x0000}, + {0x009b, 0x0000}, + {0x009c, 0x0000}, + {0x009d, 0x0000}, + {0x009e, 0x100c}, + {0x009f, 0x0000}, + {0x00a0, 0x0000}, + {0x00a3, 0x0002}, + {0x00a4, 0x0001}, + {0x00ae, 0x2040}, + {0x00af, 0x0000}, + {0x00b6, 0x0000}, + {0x00b7, 0x0000}, + {0x00b8, 0x0000}, + {0x00b9, 0x0002}, + {0x00be, 0x0000}, + {0x00c0, 0x0160}, + {0x00c1, 0x82a0}, + {0x00c2, 0x0000}, + {0x00d0, 0x0000}, + {0x00d1, 0x2244}, + {0x00d2, 0x3300}, + {0x00d3, 0x2200}, + {0x00d4, 0x0000}, + {0x00d9, 0x0009}, + {0x00da, 0x0000}, + {0x00db, 0x0000}, + {0x00dc, 0x00c0}, + {0x00dd, 0x2220}, + {0x00de, 0x3131}, + {0x00df, 0x3131}, + {0x00e0, 0x3131}, + {0x00e2, 0x0000}, + {0x00e3, 0x4000}, + {0x00e4, 0x0aa0}, + {0x00e5, 0x3131}, + {0x00e6, 0x3131}, + {0x00e7, 0x3131}, + {0x00e8, 0x3131}, + {0x00ea, 0xb320}, + {0x00eb, 0x0000}, + {0x00f0, 0x0000}, + {0x00f1, 0x00d0}, + {0x00f2, 0x00d0}, + {0x00f6, 0x0000}, + {0x00fa, 0x0000}, + {0x00fb, 0x0000}, + {0x00fc, 0x0000}, + {0x00fd, 0x0000}, + {0x00fe, 0x10ec}, + {0x00ff, 0x6530}, + {0x0100, 0xa0a0}, + {0x010b, 0x0000}, + {0x010c, 0xae00}, + {0x010d, 0xaaa0}, + {0x010e, 0x8aa2}, + {0x010f, 0x02a2}, + {0x0110, 0xc000}, + {0x0111, 0x04a2}, + {0x0112, 0x2800}, + {0x0113, 0x0000}, + {0x0117, 0x0100}, + {0x0125, 0x0410}, + {0x0132, 0x6026}, + {0x0136, 0x5555}, + {0x0138, 0x3700}, + {0x013a, 0x2000}, + {0x013b, 0x2000}, + {0x013c, 0x2005}, + {0x013f, 0x0000}, + {0x0142, 0x0000}, + {0x0145, 0x0002}, + {0x0146, 0x0000}, + {0x0147, 0x0000}, + {0x0148, 0x0000}, + {0x0149, 0x0000}, + {0x0150, 0x79a1}, + {0x0151, 0x0000}, + {0x0160, 0x4ec0}, + {0x0161, 0x0080}, + {0x0162, 0x0200}, + {0x0163, 0x0800}, + {0x0164, 0x0000}, + {0x0165, 0x0000}, + {0x0166, 0x0000}, + {0x0167, 0x000f}, + {0x0168, 0x000f}, + {0x0169, 0x0021}, + {0x0190, 0x413d}, + {0x0194, 0x0000}, + {0x0195, 0x0000}, + {0x0197, 0x0022}, + {0x0198, 0x0000}, + {0x0199, 0x0000}, + {0x01af, 0x0000}, + {0x01b0, 0x0400}, + {0x01b1, 0x0000}, + {0x01b2, 0x0000}, + {0x01b3, 0x0000}, + {0x01b4, 0x0000}, + {0x01b5, 0x0000}, + {0x01b6, 0x01c3}, + {0x01b7, 0x02a0}, + {0x01b8, 0x03e9}, + {0x01b9, 0x1389}, + {0x01ba, 0xc351}, + {0x01bb, 0x0009}, + {0x01bc, 0x0018}, + {0x01bd, 0x002a}, + {0x01be, 0x004c}, + {0x01bf, 0x0097}, + {0x01c0, 0x433d}, + {0x01c2, 0x0000}, + {0x01c3, 0x0000}, + {0x01c4, 0x0000}, + {0x01c5, 0x0000}, + {0x01c6, 0x0000}, + {0x01c7, 0x0000}, + {0x01c8, 0x40af}, + {0x01c9, 0x0702}, + {0x01ca, 0x0000}, + {0x01cb, 0x0000}, + {0x01cc, 0x5757}, + {0x01cd, 0x5757}, + {0x01ce, 0x5757}, + {0x01cf, 0x5757}, + {0x01d0, 0x5757}, + {0x01d1, 0x5757}, + {0x01d2, 0x5757}, + {0x01d3, 0x5757}, + {0x01d4, 0x5757}, + {0x01d5, 0x5757}, + {0x01d6, 0x0000}, + {0x01d7, 0x0008}, + {0x01d8, 0x0029}, + {0x01d9, 0x3333}, + {0x01da, 0x0000}, + {0x01db, 0x0004}, + {0x01dc, 0x0000}, + {0x01de, 0x7c00}, + {0x01df, 0x0320}, + {0x01e0, 0x06a1}, + {0x01e1, 0x0000}, + {0x01e2, 0x0000}, + {0x01e3, 0x0000}, + {0x01e4, 0x0000}, + {0x01e6, 0x0001}, + {0x01e7, 0x0000}, + {0x01e8, 0x0000}, + {0x01ea, 0x0000}, + {0x01eb, 0x0000}, + {0x01ec, 0x0000}, + {0x01ed, 0x0000}, + {0x01ee, 0x0000}, + {0x01ef, 0x0000}, + {0x01f0, 0x0000}, + {0x01f1, 0x0000}, + {0x01f2, 0x0000}, + {0x01f3, 0x0000}, + {0x01f4, 0x0000}, + {0x0210, 0x6297}, + {0x0211, 0xa005}, + {0x0212, 0x824c}, + {0x0213, 0xf7ff}, + {0x0214, 0xf24c}, + {0x0215, 0x0102}, + {0x0216, 0x00a3}, + {0x0217, 0x0048}, + {0x0218, 0xa2c0}, + {0x0219, 0x0400}, + {0x021a, 0x00c8}, + {0x021b, 0x00c0}, + {0x021c, 0x0000}, + {0x0250, 0x4500}, + {0x0251, 0x40b3}, + {0x0252, 0x0000}, + {0x0253, 0x0000}, + {0x0254, 0x0000}, + {0x0255, 0x0000}, + {0x0256, 0x0000}, + {0x0257, 0x0000}, + {0x0258, 0x0000}, + {0x0259, 0x0000}, + {0x025a, 0x0005}, + {0x0270, 0x0000}, + {0x02ff, 0x0110}, + {0x0300, 0x001f}, + {0x0301, 0x032c}, + {0x0302, 0x5f21}, + {0x0303, 0x4000}, + {0x0304, 0x4000}, + {0x0305, 0x06d5}, + {0x0306, 0x8000}, + {0x0307, 0x0700}, + {0x0310, 0x4560}, + {0x0311, 0xa4a8}, + {0x0312, 0x7418}, + {0x0313, 0x0000}, + {0x0314, 0x0006}, + {0x0315, 0xffff}, + {0x0316, 0xc400}, + {0x0317, 0x0000}, + {0x03c0, 0x7e00}, + {0x03c1, 0x8000}, + {0x03c2, 0x8000}, + {0x03c3, 0x8000}, + {0x03c4, 0x8000}, + {0x03c5, 0x8000}, + {0x03c6, 0x8000}, + {0x03c7, 0x8000}, + {0x03c8, 0x8000}, + {0x03c9, 0x8000}, + {0x03ca, 0x8000}, + {0x03cb, 0x8000}, + {0x03cc, 0x8000}, + {0x03d0, 0x0000}, + {0x03d1, 0x0000}, + {0x03d2, 0x0000}, + {0x03d3, 0x0000}, + {0x03d4, 0x2000}, + {0x03d5, 0x2000}, + {0x03d6, 0x0000}, + {0x03d7, 0x0000}, + {0x03d8, 0x2000}, + {0x03d9, 0x2000}, + {0x03da, 0x2000}, + {0x03db, 0x2000}, + {0x03dc, 0x0000}, + {0x03dd, 0x0000}, + {0x03de, 0x0000}, + {0x03df, 0x2000}, + {0x03e0, 0x0000}, + {0x03e1, 0x0000}, + {0x03e2, 0x0000}, + {0x03e3, 0x0000}, + {0x03e4, 0x0000}, + {0x03e5, 0x0000}, + {0x03e6, 0x0000}, + {0x03e7, 0x0000}, + {0x03e8, 0x0000}, + {0x03e9, 0x0000}, + {0x03ea, 0x0000}, + {0x03eb, 0x0000}, + {0x03ec, 0x0000}, + {0x03ed, 0x0000}, + {0x03ee, 0x0000}, + {0x03ef, 0x0000}, + {0x03f0, 0x0800}, + {0x03f1, 0x0800}, + {0x03f2, 0x0800}, + {0x03f3, 0x0800}, +}; + +static bool rt5682_volatile_register(struct device *dev, unsigned int reg) +{ + switch (reg) { + case RT5682_RESET: + case RT5682_CBJ_CTRL_2: + case RT5682_INT_ST_1: + case RT5682_4BTN_IL_CMD_1: + case RT5682_AJD1_CTRL: + case RT5682_HP_CALIB_CTRL_1: + case RT5682_DEVICE_ID: + case RT5682_I2C_MODE: + case RT5682_HP_CALIB_CTRL_10: + case RT5682_EFUSE_CTRL_2: + case RT5682_JD_TOP_VC_VTRL: + case RT5682_HP_IMP_SENS_CTRL_19: + case RT5682_IL_CMD_1: + case RT5682_SAR_IL_CMD_2: + case RT5682_SAR_IL_CMD_4: + case RT5682_SAR_IL_CMD_10: + case RT5682_SAR_IL_CMD_11: + case RT5682_EFUSE_CTRL_6...RT5682_EFUSE_CTRL_11: + case RT5682_HP_CALIB_STA_1...RT5682_HP_CALIB_STA_11: + return true; + default: + return false; + } +} + +static bool rt5682_readable_register(struct device *dev, unsigned int reg) +{ + switch (reg) { + case RT5682_RESET: + case RT5682_VERSION_ID: + case RT5682_VENDOR_ID: + case RT5682_DEVICE_ID: + case RT5682_HP_CTRL_1: + case RT5682_HP_CTRL_2: + case RT5682_HPL_GAIN: + case RT5682_HPR_GAIN: + case RT5682_I2C_CTRL: + case RT5682_CBJ_BST_CTRL: + case RT5682_CBJ_CTRL_1: + case RT5682_CBJ_CTRL_2: + case RT5682_CBJ_CTRL_3: + case RT5682_CBJ_CTRL_4: + case RT5682_CBJ_CTRL_5: + case RT5682_CBJ_CTRL_6: + case RT5682_CBJ_CTRL_7: + case RT5682_DAC1_DIG_VOL: + case RT5682_STO1_ADC_DIG_VOL: + case RT5682_STO1_ADC_BOOST: + case RT5682_HP_IMP_GAIN_1: + case RT5682_HP_IMP_GAIN_2: + case RT5682_SIDETONE_CTRL: + case RT5682_STO1_ADC_MIXER: + case RT5682_AD_DA_MIXER: + case RT5682_STO1_DAC_MIXER: + case RT5682_A_DAC1_MUX: + case RT5682_DIG_INF2_DATA: + case RT5682_REC_MIXER: + case RT5682_CAL_REC: + case RT5682_ALC_BACK_GAIN: + case RT5682_PWR_DIG_1: + case RT5682_PWR_DIG_2: + case RT5682_PWR_ANLG_1: + case RT5682_PWR_ANLG_2: + case RT5682_PWR_ANLG_3: + case RT5682_PWR_MIXER: + case RT5682_PWR_VOL: + case RT5682_CLK_DET: + case RT5682_RESET_LPF_CTRL: + case RT5682_RESET_HPF_CTRL: + case RT5682_DMIC_CTRL_1: + case RT5682_I2S1_SDP: + case RT5682_I2S2_SDP: + case RT5682_ADDA_CLK_1: + case RT5682_ADDA_CLK_2: + case RT5682_I2S1_F_DIV_CTRL_1: + case RT5682_I2S1_F_DIV_CTRL_2: + case RT5682_TDM_CTRL: + case RT5682_TDM_ADDA_CTRL_1: + case RT5682_TDM_ADDA_CTRL_2: + case RT5682_DATA_SEL_CTRL_1: + case RT5682_TDM_TCON_CTRL: + case RT5682_GLB_CLK: + case RT5682_PLL_CTRL_1: + case RT5682_PLL_CTRL_2: + case RT5682_PLL_TRACK_1: + case RT5682_PLL_TRACK_2: + case RT5682_PLL_TRACK_3: + case RT5682_PLL_TRACK_4: + case RT5682_PLL_TRACK_5: + case RT5682_PLL_TRACK_6: + case RT5682_PLL_TRACK_11: + case RT5682_SDW_REF_CLK: + case RT5682_DEPOP_1: + case RT5682_DEPOP_2: + case RT5682_HP_CHARGE_PUMP_1: + case RT5682_HP_CHARGE_PUMP_2: + case RT5682_MICBIAS_1: + case RT5682_MICBIAS_2: + case RT5682_PLL_TRACK_12: + case RT5682_PLL_TRACK_14: + case RT5682_PLL2_CTRL_1: + case RT5682_PLL2_CTRL_2: + case RT5682_PLL2_CTRL_3: + case RT5682_PLL2_CTRL_4: + case RT5682_RC_CLK_CTRL: + case RT5682_I2S_M_CLK_CTRL_1: + case RT5682_I2S2_F_DIV_CTRL_1: + case RT5682_I2S2_F_DIV_CTRL_2: + case RT5682_EQ_CTRL_1: + case RT5682_EQ_CTRL_2: + case RT5682_IRQ_CTRL_1: + case RT5682_IRQ_CTRL_2: + case RT5682_IRQ_CTRL_3: + case RT5682_IRQ_CTRL_4: + case RT5682_INT_ST_1: + case RT5682_GPIO_CTRL_1: + case RT5682_GPIO_CTRL_2: + case RT5682_GPIO_CTRL_3: + case RT5682_HP_AMP_DET_CTRL_1: + case RT5682_HP_AMP_DET_CTRL_2: + case RT5682_MID_HP_AMP_DET: + case RT5682_LOW_HP_AMP_DET: + case RT5682_DELAY_BUF_CTRL: + case RT5682_SV_ZCD_1: + case RT5682_SV_ZCD_2: + case RT5682_IL_CMD_1: + case RT5682_IL_CMD_2: + case RT5682_IL_CMD_3: + case RT5682_IL_CMD_4: + case RT5682_IL_CMD_5: + case RT5682_IL_CMD_6: + case RT5682_4BTN_IL_CMD_1: + case RT5682_4BTN_IL_CMD_2: + case RT5682_4BTN_IL_CMD_3: + case RT5682_4BTN_IL_CMD_4: + case RT5682_4BTN_IL_CMD_5: + case RT5682_4BTN_IL_CMD_6: + case RT5682_4BTN_IL_CMD_7: + case RT5682_ADC_STO1_HP_CTRL_1: + case RT5682_ADC_STO1_HP_CTRL_2: + case RT5682_AJD1_CTRL: + case RT5682_JD1_THD: + case RT5682_JD2_THD: + case RT5682_JD_CTRL_1: + case RT5682_DUMMY_1: + case RT5682_DUMMY_2: + case RT5682_DUMMY_3: + case RT5682_DAC_ADC_DIG_VOL1: + case RT5682_BIAS_CUR_CTRL_2: + case RT5682_BIAS_CUR_CTRL_3: + case RT5682_BIAS_CUR_CTRL_4: + case RT5682_BIAS_CUR_CTRL_5: + case RT5682_BIAS_CUR_CTRL_6: + case RT5682_BIAS_CUR_CTRL_7: + case RT5682_BIAS_CUR_CTRL_8: + case RT5682_BIAS_CUR_CTRL_9: + case RT5682_BIAS_CUR_CTRL_10: + case RT5682_VREF_REC_OP_FB_CAP_CTRL: + case RT5682_CHARGE_PUMP_1: + case RT5682_DIG_IN_CTRL_1: + case RT5682_PAD_DRIVING_CTRL: + case RT5682_SOFT_RAMP_DEPOP: + case RT5682_CHOP_DAC: + case RT5682_CHOP_ADC: + case RT5682_CALIB_ADC_CTRL: + case RT5682_VOL_TEST: + case RT5682_SPKVDD_DET_STA: + case RT5682_TEST_MODE_CTRL_1: + case RT5682_TEST_MODE_CTRL_2: + case RT5682_TEST_MODE_CTRL_3: + case RT5682_TEST_MODE_CTRL_4: + case RT5682_TEST_MODE_CTRL_5: + case RT5682_PLL1_INTERNAL: + case RT5682_PLL2_INTERNAL: + case RT5682_STO_NG2_CTRL_1: + case RT5682_STO_NG2_CTRL_2: + case RT5682_STO_NG2_CTRL_3: + case RT5682_STO_NG2_CTRL_4: + case RT5682_STO_NG2_CTRL_5: + case RT5682_STO_NG2_CTRL_6: + case RT5682_STO_NG2_CTRL_7: + case RT5682_STO_NG2_CTRL_8: + case RT5682_STO_NG2_CTRL_9: + case RT5682_STO_NG2_CTRL_10: + case RT5682_STO1_DAC_SIL_DET: + case RT5682_SIL_PSV_CTRL1: + case RT5682_SIL_PSV_CTRL2: + case RT5682_SIL_PSV_CTRL3: + case RT5682_SIL_PSV_CTRL4: + case RT5682_SIL_PSV_CTRL5: + case RT5682_HP_IMP_SENS_CTRL_01: + case RT5682_HP_IMP_SENS_CTRL_02: + case RT5682_HP_IMP_SENS_CTRL_03: + case RT5682_HP_IMP_SENS_CTRL_04: + case RT5682_HP_IMP_SENS_CTRL_05: + case RT5682_HP_IMP_SENS_CTRL_06: + case RT5682_HP_IMP_SENS_CTRL_07: + case RT5682_HP_IMP_SENS_CTRL_08: + case RT5682_HP_IMP_SENS_CTRL_09: + case RT5682_HP_IMP_SENS_CTRL_10: + case RT5682_HP_IMP_SENS_CTRL_11: + case RT5682_HP_IMP_SENS_CTRL_12: + case RT5682_HP_IMP_SENS_CTRL_13: + case RT5682_HP_IMP_SENS_CTRL_14: + case RT5682_HP_IMP_SENS_CTRL_15: + case RT5682_HP_IMP_SENS_CTRL_16: + case RT5682_HP_IMP_SENS_CTRL_17: + case RT5682_HP_IMP_SENS_CTRL_18: + case RT5682_HP_IMP_SENS_CTRL_19: + case RT5682_HP_IMP_SENS_CTRL_20: + case RT5682_HP_IMP_SENS_CTRL_21: + case RT5682_HP_IMP_SENS_CTRL_22: + case RT5682_HP_IMP_SENS_CTRL_23: + case RT5682_HP_IMP_SENS_CTRL_24: + case RT5682_HP_IMP_SENS_CTRL_25: + case RT5682_HP_IMP_SENS_CTRL_26: + case RT5682_HP_IMP_SENS_CTRL_27: + case RT5682_HP_IMP_SENS_CTRL_28: + case RT5682_HP_IMP_SENS_CTRL_29: + case RT5682_HP_IMP_SENS_CTRL_30: + case RT5682_HP_IMP_SENS_CTRL_31: + case RT5682_HP_IMP_SENS_CTRL_32: + case RT5682_HP_IMP_SENS_CTRL_33: + case RT5682_HP_IMP_SENS_CTRL_34: + case RT5682_HP_IMP_SENS_CTRL_35: + case RT5682_HP_IMP_SENS_CTRL_36: + case RT5682_HP_IMP_SENS_CTRL_37: + case RT5682_HP_IMP_SENS_CTRL_38: + case RT5682_HP_IMP_SENS_CTRL_39: + case RT5682_HP_IMP_SENS_CTRL_40: + case RT5682_HP_IMP_SENS_CTRL_41: + case RT5682_HP_IMP_SENS_CTRL_42: + case RT5682_HP_IMP_SENS_CTRL_43: + case RT5682_HP_LOGIC_CTRL_1: + case RT5682_HP_LOGIC_CTRL_2: + case RT5682_HP_LOGIC_CTRL_3: + case RT5682_HP_CALIB_CTRL_1: + case RT5682_HP_CALIB_CTRL_2: + case RT5682_HP_CALIB_CTRL_3: + case RT5682_HP_CALIB_CTRL_4: + case RT5682_HP_CALIB_CTRL_5: + case RT5682_HP_CALIB_CTRL_6: + case RT5682_HP_CALIB_CTRL_7: + case RT5682_HP_CALIB_CTRL_9: + case RT5682_HP_CALIB_CTRL_10: + case RT5682_HP_CALIB_CTRL_11: + case RT5682_HP_CALIB_STA_1: + case RT5682_HP_CALIB_STA_2: + case RT5682_HP_CALIB_STA_3: + case RT5682_HP_CALIB_STA_4: + case RT5682_HP_CALIB_STA_5: + case RT5682_HP_CALIB_STA_6: + case RT5682_HP_CALIB_STA_7: + case RT5682_HP_CALIB_STA_8: + case RT5682_HP_CALIB_STA_9: + case RT5682_HP_CALIB_STA_10: + case RT5682_HP_CALIB_STA_11: + case RT5682_SAR_IL_CMD_1: + case RT5682_SAR_IL_CMD_2: + case RT5682_SAR_IL_CMD_3: + case RT5682_SAR_IL_CMD_4: + case RT5682_SAR_IL_CMD_5: + case RT5682_SAR_IL_CMD_6: + case RT5682_SAR_IL_CMD_7: + case RT5682_SAR_IL_CMD_8: + case RT5682_SAR_IL_CMD_9: + case RT5682_SAR_IL_CMD_10: + case RT5682_SAR_IL_CMD_11: + case RT5682_SAR_IL_CMD_12: + case RT5682_SAR_IL_CMD_13: + case RT5682_EFUSE_CTRL_1: + case RT5682_EFUSE_CTRL_2: + case RT5682_EFUSE_CTRL_3: + case RT5682_EFUSE_CTRL_4: + case RT5682_EFUSE_CTRL_5: + case RT5682_EFUSE_CTRL_6: + case RT5682_EFUSE_CTRL_7: + case RT5682_EFUSE_CTRL_8: + case RT5682_EFUSE_CTRL_9: + case RT5682_EFUSE_CTRL_10: + case RT5682_EFUSE_CTRL_11: + case RT5682_JD_TOP_VC_VTRL: + case RT5682_DRC1_CTRL_0: + case RT5682_DRC1_CTRL_1: + case RT5682_DRC1_CTRL_2: + case RT5682_DRC1_CTRL_3: + case RT5682_DRC1_CTRL_4: + case RT5682_DRC1_CTRL_5: + case RT5682_DRC1_CTRL_6: + case RT5682_DRC1_HARD_LMT_CTRL_1: + case RT5682_DRC1_HARD_LMT_CTRL_2: + case RT5682_DRC1_PRIV_1: + case RT5682_DRC1_PRIV_2: + case RT5682_DRC1_PRIV_3: + case RT5682_DRC1_PRIV_4: + case RT5682_DRC1_PRIV_5: + case RT5682_DRC1_PRIV_6: + case RT5682_DRC1_PRIV_7: + case RT5682_DRC1_PRIV_8: + case RT5682_EQ_AUTO_RCV_CTRL1: + case RT5682_EQ_AUTO_RCV_CTRL2: + case RT5682_EQ_AUTO_RCV_CTRL3: + case RT5682_EQ_AUTO_RCV_CTRL4: + case RT5682_EQ_AUTO_RCV_CTRL5: + case RT5682_EQ_AUTO_RCV_CTRL6: + case RT5682_EQ_AUTO_RCV_CTRL7: + case RT5682_EQ_AUTO_RCV_CTRL8: + case RT5682_EQ_AUTO_RCV_CTRL9: + case RT5682_EQ_AUTO_RCV_CTRL10: + case RT5682_EQ_AUTO_RCV_CTRL11: + case RT5682_EQ_AUTO_RCV_CTRL12: + case RT5682_EQ_AUTO_RCV_CTRL13: + case RT5682_ADC_L_EQ_LPF1_A1: + case RT5682_R_EQ_LPF1_A1: + case RT5682_L_EQ_LPF1_H0: + case RT5682_R_EQ_LPF1_H0: + case RT5682_L_EQ_BPF1_A1: + case RT5682_R_EQ_BPF1_A1: + case RT5682_L_EQ_BPF1_A2: + case RT5682_R_EQ_BPF1_A2: + case RT5682_L_EQ_BPF1_H0: + case RT5682_R_EQ_BPF1_H0: + case RT5682_L_EQ_BPF2_A1: + case RT5682_R_EQ_BPF2_A1: + case RT5682_L_EQ_BPF2_A2: + case RT5682_R_EQ_BPF2_A2: + case RT5682_L_EQ_BPF2_H0: + case RT5682_R_EQ_BPF2_H0: + case RT5682_L_EQ_BPF3_A1: + case RT5682_R_EQ_BPF3_A1: + case RT5682_L_EQ_BPF3_A2: + case RT5682_R_EQ_BPF3_A2: + case RT5682_L_EQ_BPF3_H0: + case RT5682_R_EQ_BPF3_H0: + case RT5682_L_EQ_BPF4_A1: + case RT5682_R_EQ_BPF4_A1: + case RT5682_L_EQ_BPF4_A2: + case RT5682_R_EQ_BPF4_A2: + case RT5682_L_EQ_BPF4_H0: + case RT5682_R_EQ_BPF4_H0: + case RT5682_L_EQ_HPF1_A1: + case RT5682_R_EQ_HPF1_A1: + case RT5682_L_EQ_HPF1_H0: + case RT5682_R_EQ_HPF1_H0: + case RT5682_L_EQ_PRE_VOL: + case RT5682_R_EQ_PRE_VOL: + case RT5682_L_EQ_POST_VOL: + case RT5682_R_EQ_POST_VOL: + case RT5682_I2C_MODE: + return true; + default: + return false; + } +} + +static const DECLARE_TLV_DB_SCALE(hp_vol_tlv, -2250, 150, 0); +static const DECLARE_TLV_DB_SCALE(dac_vol_tlv, -65625, 375, 0); +static const DECLARE_TLV_DB_SCALE(adc_vol_tlv, -17625, 375, 0); +static const DECLARE_TLV_DB_SCALE(adc_bst_tlv, 0, 1200, 0); + +/* {0, +20, +24, +30, +35, +40, +44, +50, +52} dB */ +static const DECLARE_TLV_DB_RANGE(bst_tlv, + 0, 0, TLV_DB_SCALE_ITEM(0, 0, 0), + 1, 1, TLV_DB_SCALE_ITEM(2000, 0, 0), + 2, 2, TLV_DB_SCALE_ITEM(2400, 0, 0), + 3, 5, TLV_DB_SCALE_ITEM(3000, 500, 0), + 6, 6, TLV_DB_SCALE_ITEM(4400, 0, 0), + 7, 7, TLV_DB_SCALE_ITEM(5000, 0, 0), + 8, 8, TLV_DB_SCALE_ITEM(5200, 0, 0) +); + +/* Interface data select */ +static const char * const rt5682_data_select[] = { + "L/R", "R/L", "L/L", "R/R" +}; + +static SOC_ENUM_SINGLE_DECL(rt5682_if2_adc_enum, + RT5682_DIG_INF2_DATA, RT5682_IF2_ADC_SEL_SFT, rt5682_data_select); + +static SOC_ENUM_SINGLE_DECL(rt5682_if1_01_adc_enum, + RT5682_TDM_ADDA_CTRL_1, RT5682_IF1_ADC1_SEL_SFT, rt5682_data_select); + +static SOC_ENUM_SINGLE_DECL(rt5682_if1_23_adc_enum, + RT5682_TDM_ADDA_CTRL_1, RT5682_IF1_ADC2_SEL_SFT, rt5682_data_select); + +static SOC_ENUM_SINGLE_DECL(rt5682_if1_45_adc_enum, + RT5682_TDM_ADDA_CTRL_1, RT5682_IF1_ADC3_SEL_SFT, rt5682_data_select); + +static SOC_ENUM_SINGLE_DECL(rt5682_if1_67_adc_enum, + RT5682_TDM_ADDA_CTRL_1, RT5682_IF1_ADC4_SEL_SFT, rt5682_data_select); + +static const struct snd_kcontrol_new rt5682_if2_adc_swap_mux = + SOC_DAPM_ENUM("IF2 ADC Swap Mux", rt5682_if2_adc_enum); + +static const struct snd_kcontrol_new rt5682_if1_01_adc_swap_mux = + SOC_DAPM_ENUM("IF1 01 ADC Swap Mux", rt5682_if1_01_adc_enum); + +static const struct snd_kcontrol_new rt5682_if1_23_adc_swap_mux = + SOC_DAPM_ENUM("IF1 23 ADC Swap Mux", rt5682_if1_23_adc_enum); + +static const struct snd_kcontrol_new rt5682_if1_45_adc_swap_mux = + SOC_DAPM_ENUM("IF1 45 ADC Swap Mux", rt5682_if1_45_adc_enum); + +static const struct snd_kcontrol_new rt5682_if1_67_adc_swap_mux = + SOC_DAPM_ENUM("IF1 67 ADC Swap Mux", rt5682_if1_67_adc_enum); + +static void rt5682_reset(struct regmap *regmap) +{ + regmap_write(regmap, RT5682_RESET, 0); + regmap_write(regmap, RT5682_I2C_MODE, 1); +} +/** + * rt5682_sel_asrc_clk_src - select ASRC clock source for a set of filters + * @component: SoC audio component device. + * @filter_mask: mask of filters. + * @clk_src: clock source + * + * The ASRC function is for asynchronous MCLK and LRCK. Also, since RT5682 can + * only support standard 32fs or 64fs i2s format, ASRC should be enabled to + * support special i2s clock format such as Intel's 100fs(100 * sampling rate). + * ASRC function will track i2s clock and generate a corresponding system clock + * for codec. This function provides an API to select the clock source for a + * set of filters specified by the mask. And the component driver will turn on + * ASRC for these filters if ASRC is selected as their clock source. + */ +int rt5682_sel_asrc_clk_src(struct snd_soc_component *component, + unsigned int filter_mask, unsigned int clk_src) +{ + + switch (clk_src) { + case RT5682_CLK_SEL_SYS: + case RT5682_CLK_SEL_I2S1_ASRC: + case RT5682_CLK_SEL_I2S2_ASRC: + break; + + default: + return -EINVAL; + } + + if (filter_mask & RT5682_DA_STEREO1_FILTER) { + snd_soc_component_update_bits(component, RT5682_PLL_TRACK_2, + RT5682_FILTER_CLK_SEL_MASK, + clk_src << RT5682_FILTER_CLK_SEL_SFT); + } + + if (filter_mask & RT5682_AD_STEREO1_FILTER) { + snd_soc_component_update_bits(component, RT5682_PLL_TRACK_3, + RT5682_FILTER_CLK_SEL_MASK, + clk_src << RT5682_FILTER_CLK_SEL_SFT); + } + + return 0; +} +EXPORT_SYMBOL_GPL(rt5682_sel_asrc_clk_src); + +static int rt5682_button_detect(struct snd_soc_component *component) +{ + int btn_type, val; + + val = snd_soc_component_read32(component, RT5682_4BTN_IL_CMD_1); + btn_type = val & 0xfff0; + snd_soc_component_write(component, RT5682_4BTN_IL_CMD_1, val); + pr_debug("%s btn_type=%x\n", __func__, btn_type); + + return btn_type; +} + +static void rt5682_enable_push_button_irq(struct snd_soc_component *component, + bool enable) +{ + if (enable) { + snd_soc_component_update_bits(component, RT5682_SAR_IL_CMD_1, + RT5682_SAR_BUTT_DET_MASK, RT5682_SAR_BUTT_DET_EN); + snd_soc_component_update_bits(component, RT5682_SAR_IL_CMD_13, + RT5682_SAR_SOUR_MASK, RT5682_SAR_SOUR_BTN); + snd_soc_component_write(component, RT5682_IL_CMD_1, 0x0040); + snd_soc_component_update_bits(component, RT5682_4BTN_IL_CMD_2, + RT5682_4BTN_IL_MASK | RT5682_4BTN_IL_RST_MASK, + RT5682_4BTN_IL_EN | RT5682_4BTN_IL_NOR); + snd_soc_component_update_bits(component, RT5682_IRQ_CTRL_3, + RT5682_IL_IRQ_MASK, RT5682_IL_IRQ_EN); + } else { + snd_soc_component_update_bits(component, RT5682_IRQ_CTRL_3, + RT5682_IL_IRQ_MASK, RT5682_IL_IRQ_DIS); + snd_soc_component_update_bits(component, RT5682_SAR_IL_CMD_1, + RT5682_SAR_BUTT_DET_MASK, RT5682_SAR_BUTT_DET_DIS); + snd_soc_component_update_bits(component, RT5682_4BTN_IL_CMD_2, + RT5682_4BTN_IL_MASK, RT5682_4BTN_IL_DIS); + snd_soc_component_update_bits(component, RT5682_4BTN_IL_CMD_2, + RT5682_4BTN_IL_RST_MASK, RT5682_4BTN_IL_RST); + snd_soc_component_update_bits(component, RT5682_SAR_IL_CMD_13, + RT5682_SAR_SOUR_MASK, RT5682_SAR_SOUR_TYPE); + } +} + +/** + * rt5682_headset_detect - Detect headset. + * @component: SoC audio component device. + * @jack_insert: Jack insert or not. + * + * Detect whether is headset or not when jack inserted. + * + * Returns detect status. + */ +static int rt5682_headset_detect(struct snd_soc_component *component, + int jack_insert) +{ + struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component); + struct snd_soc_dapm_context *dapm = + snd_soc_component_get_dapm(component); + unsigned int val, count; + + if (jack_insert) { + snd_soc_dapm_force_enable_pin(dapm, "CBJ Power"); + snd_soc_dapm_sync(dapm); + snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_1, + RT5682_TRIG_JD_MASK, RT5682_TRIG_JD_HIGH); + + count = 0; + val = snd_soc_component_read32(component, RT5682_CBJ_CTRL_2) + & RT5682_JACK_TYPE_MASK; + while (val == 0 && count < 50) { + usleep_range(10000, 15000); + val = snd_soc_component_read32(component, + RT5682_CBJ_CTRL_2) & RT5682_JACK_TYPE_MASK; + count++; + } + + switch (val) { + case 0x1: + case 0x2: + rt5682->jack_type = SND_JACK_HEADSET; + rt5682_enable_push_button_irq(component, true); + break; + default: + rt5682->jack_type = SND_JACK_HEADPHONE; + } + + } else { + rt5682_enable_push_button_irq(component, false); + snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_1, + RT5682_TRIG_JD_MASK, RT5682_TRIG_JD_LOW); + snd_soc_dapm_disable_pin(dapm, "CBJ Power"); + snd_soc_dapm_sync(dapm); + + rt5682->jack_type = 0; + } + + dev_dbg(component->dev, "jack_type = %d\n", rt5682->jack_type); + return rt5682->jack_type; +} + +static irqreturn_t rt5682_irq(int irq, void *data) +{ + struct rt5682_priv *rt5682 = data; + + mod_delayed_work(system_power_efficient_wq, + &rt5682->jack_detect_work, msecs_to_jiffies(250)); + + return IRQ_HANDLED; +} + +static void rt5682_jd_check_handler(struct work_struct *work) +{ + struct rt5682_priv *rt5682 = container_of(work, struct rt5682_priv, + jd_check_work.work); + + if (snd_soc_component_read32(rt5682->component, RT5682_AJD1_CTRL) + & RT5682_JDH_RS_MASK) { + /* jack out */ + rt5682->jack_type = rt5682_headset_detect(rt5682->component, 0); + + snd_soc_jack_report(rt5682->hs_jack, rt5682->jack_type, + SND_JACK_HEADSET | + SND_JACK_BTN_0 | SND_JACK_BTN_1 | + SND_JACK_BTN_2 | SND_JACK_BTN_3); + } else { + schedule_delayed_work(&rt5682->jd_check_work, 500); + } +} + +static int rt5682_set_jack_detect(struct snd_soc_component *component, + struct snd_soc_jack *hs_jack, void *data) +{ + struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component); + + switch (rt5682->pdata.jd_src) { + case RT5682_JD1: + snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_2, + RT5682_EXT_JD_SRC, RT5682_EXT_JD_SRC_MANUAL); + snd_soc_component_write(component, RT5682_CBJ_CTRL_1, 0xd042); + snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_3, + RT5682_CBJ_IN_BUF_EN, RT5682_CBJ_IN_BUF_EN); + snd_soc_component_update_bits(component, RT5682_SAR_IL_CMD_1, + RT5682_SAR_POW_MASK, RT5682_SAR_POW_EN); + regmap_update_bits(rt5682->regmap, RT5682_GPIO_CTRL_1, + RT5682_GP1_PIN_MASK, RT5682_GP1_PIN_IRQ); + regmap_update_bits(rt5682->regmap, RT5682_RC_CLK_CTRL, + RT5682_POW_IRQ | RT5682_POW_JDH | + RT5682_POW_ANA, RT5682_POW_IRQ | + RT5682_POW_JDH | RT5682_POW_ANA); + regmap_update_bits(rt5682->regmap, RT5682_PWR_ANLG_2, + RT5682_PWR_JDH | RT5682_PWR_JDL, + RT5682_PWR_JDH | RT5682_PWR_JDL); + regmap_update_bits(rt5682->regmap, RT5682_IRQ_CTRL_2, + RT5682_JD1_EN_MASK | RT5682_JD1_POL_MASK, + RT5682_JD1_EN | RT5682_JD1_POL_NOR); + mod_delayed_work(system_power_efficient_wq, + &rt5682->jack_detect_work, msecs_to_jiffies(250)); + break; + + case RT5682_JD_NULL: + regmap_update_bits(rt5682->regmap, RT5682_IRQ_CTRL_2, + RT5682_JD1_EN_MASK, RT5682_JD1_DIS); + regmap_update_bits(rt5682->regmap, RT5682_RC_CLK_CTRL, + RT5682_POW_JDH | RT5682_POW_JDL, 0); + break; + + default: + dev_warn(component->dev, "Wrong JD source\n"); + break; + } + + rt5682->hs_jack = hs_jack; + + return 0; +} + +static void rt5682_jack_detect_handler(struct work_struct *work) +{ + struct rt5682_priv *rt5682 = + container_of(work, struct rt5682_priv, jack_detect_work.work); + int val, btn_type; + + while (!rt5682->component) + usleep_range(10000, 15000); + + while (!rt5682->component->card->instantiated) + usleep_range(10000, 15000); + + mutex_lock(&rt5682->calibrate_mutex); + + val = snd_soc_component_read32(rt5682->component, RT5682_AJD1_CTRL) + & RT5682_JDH_RS_MASK; + if (!val) { + /* jack in */ + if (rt5682->jack_type == 0) { + /* jack was out, report jack type */ + rt5682->jack_type = + rt5682_headset_detect(rt5682->component, 1); + } else { + /* jack is already in, report button event */ + rt5682->jack_type = SND_JACK_HEADSET; + btn_type = rt5682_button_detect(rt5682->component); + /** + * rt5682 can report three kinds of button behavior, + * one click, double click and hold. However, + * currently we will report button pressed/released + * event. So all the three button behaviors are + * treated as button pressed. + */ + switch (btn_type) { + case 0x8000: + case 0x4000: + case 0x2000: + rt5682->jack_type |= SND_JACK_BTN_0; + break; + case 0x1000: + case 0x0800: + case 0x0400: + rt5682->jack_type |= SND_JACK_BTN_1; + break; + case 0x0200: + case 0x0100: + case 0x0080: + rt5682->jack_type |= SND_JACK_BTN_2; + break; + case 0x0040: + case 0x0020: + case 0x0010: + rt5682->jack_type |= SND_JACK_BTN_3; + break; + case 0x0000: /* unpressed */ + break; + default: + btn_type = 0; + dev_err(rt5682->component->dev, + "Unexpected button code 0x%04x\n", + btn_type); + break; + } + } + } else { + /* jack out */ + rt5682->jack_type = rt5682_headset_detect(rt5682->component, 0); + } + + snd_soc_jack_report(rt5682->hs_jack, rt5682->jack_type, + SND_JACK_HEADSET | + SND_JACK_BTN_0 | SND_JACK_BTN_1 | + SND_JACK_BTN_2 | SND_JACK_BTN_3); + + if (rt5682->jack_type & (SND_JACK_BTN_0 | SND_JACK_BTN_1 | + SND_JACK_BTN_2 | SND_JACK_BTN_3)) + schedule_delayed_work(&rt5682->jd_check_work, 0); + else + cancel_delayed_work_sync(&rt5682->jd_check_work); + + mutex_unlock(&rt5682->calibrate_mutex); +} + +static const struct snd_kcontrol_new rt5682_snd_controls[] = { + /* Headphone Output Volume */ + SOC_DOUBLE_R_TLV("Headphone Playback Volume", RT5682_HPL_GAIN, + RT5682_HPR_GAIN, RT5682_G_HP_SFT, 15, 1, hp_vol_tlv), + + /* DAC Digital Volume */ + SOC_DOUBLE_TLV("DAC1 Playback Volume", RT5682_DAC1_DIG_VOL, + RT5682_L_VOL_SFT, RT5682_R_VOL_SFT, 175, 0, dac_vol_tlv), + + /* IN Boost Volume */ + SOC_SINGLE_TLV("CBJ Boost Volume", RT5682_CBJ_BST_CTRL, + RT5682_BST_CBJ_SFT, 8, 0, bst_tlv), + + /* ADC Digital Volume Control */ + SOC_DOUBLE("STO1 ADC Capture Switch", RT5682_STO1_ADC_DIG_VOL, + RT5682_L_MUTE_SFT, RT5682_R_MUTE_SFT, 1, 1), + SOC_DOUBLE_TLV("STO1 ADC Capture Volume", RT5682_STO1_ADC_DIG_VOL, + RT5682_L_VOL_SFT, RT5682_R_VOL_SFT, 127, 0, adc_vol_tlv), + + /* ADC Boost Volume Control */ + SOC_DOUBLE_TLV("STO1 ADC Boost Gain Volume", RT5682_STO1_ADC_BOOST, + RT5682_STO1_ADC_L_BST_SFT, RT5682_STO1_ADC_R_BST_SFT, + 3, 0, adc_bst_tlv), +}; + + +static int rt5682_div_sel(struct rt5682_priv *rt5682, + int target, const int div[], int size) +{ + int i; + + if (rt5682->sysclk < target) { + pr_err("sysclk rate %d is too low\n", + rt5682->sysclk); + return 0; + } + + for (i = 0; i < size - 1; i++) { + pr_info("div[%d]=%d\n", i, div[i]); + if (target * div[i] == rt5682->sysclk) + return i; + if (target * div[i + 1] > rt5682->sysclk) { + pr_err("can't find div for sysclk %d\n", + rt5682->sysclk); + return i; + } + } + + if (target * div[i] < rt5682->sysclk) + pr_err("sysclk rate %d is too high\n", + rt5682->sysclk); + + return size - 1; + +} + +/** + * set_dmic_clk - Set parameter of dmic. + * + * @w: DAPM widget. + * @kcontrol: The kcontrol of this widget. + * @event: Event id. + * + * Choose dmic clock between 1MHz and 3MHz. + * It is better for clock to approximate 3MHz. + */ +static int set_dmic_clk(struct snd_soc_dapm_widget *w, + struct snd_kcontrol *kcontrol, int event) +{ + struct snd_soc_component *component = + snd_soc_dapm_to_component(w->dapm); + struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component); + int idx = -EINVAL; + static const int div[] = {2, 4, 6, 8, 12, 16, 24, 32, 48, 64, 96, 128}; + + idx = rt5682_div_sel(rt5682, 1500000, div, ARRAY_SIZE(div)); + + snd_soc_component_update_bits(component, RT5682_DMIC_CTRL_1, + RT5682_DMIC_CLK_MASK, idx << RT5682_DMIC_CLK_SFT); + + return 0; +} + +static int set_filter_clk(struct snd_soc_dapm_widget *w, + struct snd_kcontrol *kcontrol, int event) +{ + struct snd_soc_component *component = + snd_soc_dapm_to_component(w->dapm); + struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component); + int ref, val, reg, sft, mask, idx = -EINVAL; + static const int div_f[] = {1, 2, 3, 4, 6, 8, 12, 16, 24, 32, 48}; + static const int div_o[] = {1, 2, 4, 6, 8, 12, 16, 24, 32, 48}; + + val = snd_soc_component_read32(component, RT5682_GPIO_CTRL_1) & + RT5682_GP4_PIN_MASK; + if (w->shift == RT5682_PWR_ADC_S1F_BIT && + val == RT5682_GP4_PIN_ADCDAT2) + ref = 256 * rt5682->lrck[RT5682_AIF2]; + else + ref = 256 * rt5682->lrck[RT5682_AIF1]; + + idx = rt5682_div_sel(rt5682, ref, div_f, ARRAY_SIZE(div_f)); + + if (w->shift == RT5682_PWR_ADC_S1F_BIT) { + reg = RT5682_PLL_TRACK_3; + sft = RT5682_ADC_OSR_SFT; + mask = RT5682_ADC_OSR_MASK; + } else { + reg = RT5682_PLL_TRACK_2; + sft = RT5682_DAC_OSR_SFT; + mask = RT5682_DAC_OSR_MASK; + } + + snd_soc_component_update_bits(component, reg, + RT5682_FILTER_CLK_DIV_MASK, idx << RT5682_FILTER_CLK_DIV_SFT); + + /* select over sample rate */ + for (idx = 0; idx < ARRAY_SIZE(div_o); idx++) { + if (rt5682->sysclk <= 12288000 * div_o[idx]) + break; + } + + snd_soc_component_update_bits(component, RT5682_ADDA_CLK_1, + mask, idx << sft); + + return 0; +} + +static int is_sys_clk_from_pll1(struct snd_soc_dapm_widget *w, + struct snd_soc_dapm_widget *sink) +{ + unsigned int val; + struct snd_soc_component *component = + snd_soc_dapm_to_component(w->dapm); + + val = snd_soc_component_read32(component, RT5682_GLB_CLK); + val &= RT5682_SCLK_SRC_MASK; + if (val == RT5682_SCLK_SRC_PLL1) + return 1; + else + return 0; +} + +static int is_using_asrc(struct snd_soc_dapm_widget *w, + struct snd_soc_dapm_widget *sink) +{ + unsigned int reg, shift, val; + struct snd_soc_component *component = + snd_soc_dapm_to_component(w->dapm); + + switch (w->shift) { + case RT5682_ADC_STO1_ASRC_SFT: + reg = RT5682_PLL_TRACK_3; + shift = RT5682_FILTER_CLK_SEL_SFT; + break; + case RT5682_DAC_STO1_ASRC_SFT: + reg = RT5682_PLL_TRACK_2; + shift = RT5682_FILTER_CLK_SEL_SFT; + break; + default: + return 0; + } + + val = (snd_soc_component_read32(component, reg) >> shift) & 0xf; + switch (val) { + case RT5682_CLK_SEL_I2S1_ASRC: + case RT5682_CLK_SEL_I2S2_ASRC: + return 1; + default: + return 0; + } + +} + +/* Digital Mixer */ +static const struct snd_kcontrol_new rt5682_sto1_adc_l_mix[] = { + SOC_DAPM_SINGLE("ADC1 Switch", RT5682_STO1_ADC_MIXER, + RT5682_M_STO1_ADC_L1_SFT, 1, 1), + SOC_DAPM_SINGLE("ADC2 Switch", RT5682_STO1_ADC_MIXER, + RT5682_M_STO1_ADC_L2_SFT, 1, 1), +}; + +static const struct snd_kcontrol_new rt5682_sto1_adc_r_mix[] = { + SOC_DAPM_SINGLE("ADC1 Switch", RT5682_STO1_ADC_MIXER, + RT5682_M_STO1_ADC_R1_SFT, 1, 1), + SOC_DAPM_SINGLE("ADC2 Switch", RT5682_STO1_ADC_MIXER, + RT5682_M_STO1_ADC_R2_SFT, 1, 1), +}; + +static const struct snd_kcontrol_new rt5682_dac_l_mix[] = { + SOC_DAPM_SINGLE("Stereo ADC Switch", RT5682_AD_DA_MIXER, + RT5682_M_ADCMIX_L_SFT, 1, 1), + SOC_DAPM_SINGLE("DAC1 Switch", RT5682_AD_DA_MIXER, + RT5682_M_DAC1_L_SFT, 1, 1), +}; + +static const struct snd_kcontrol_new rt5682_dac_r_mix[] = { + SOC_DAPM_SINGLE("Stereo ADC Switch", RT5682_AD_DA_MIXER, + RT5682_M_ADCMIX_R_SFT, 1, 1), + SOC_DAPM_SINGLE("DAC1 Switch", RT5682_AD_DA_MIXER, + RT5682_M_DAC1_R_SFT, 1, 1), +}; + +static const struct snd_kcontrol_new rt5682_sto1_dac_l_mix[] = { + SOC_DAPM_SINGLE("DAC L1 Switch", RT5682_STO1_DAC_MIXER, + RT5682_M_DAC_L1_STO_L_SFT, 1, 1), + SOC_DAPM_SINGLE("DAC R1 Switch", RT5682_STO1_DAC_MIXER, + RT5682_M_DAC_R1_STO_L_SFT, 1, 1), +}; + +static const struct snd_kcontrol_new rt5682_sto1_dac_r_mix[] = { + SOC_DAPM_SINGLE("DAC L1 Switch", RT5682_STO1_DAC_MIXER, + RT5682_M_DAC_L1_STO_R_SFT, 1, 1), + SOC_DAPM_SINGLE("DAC R1 Switch", RT5682_STO1_DAC_MIXER, + RT5682_M_DAC_R1_STO_R_SFT, 1, 1), +}; + +/* Analog Input Mixer */ +static const struct snd_kcontrol_new rt5682_rec1_l_mix[] = { + SOC_DAPM_SINGLE("CBJ Switch", RT5682_REC_MIXER, + RT5682_M_CBJ_RM1_L_SFT, 1, 1), +}; + +/* STO1 ADC1 Source */ +/* MX-26 [13] [5] */ +static const char * const rt5682_sto1_adc1_src[] = { + "DAC MIX", "ADC" +}; + +static SOC_ENUM_SINGLE_DECL( + rt5682_sto1_adc1l_enum, RT5682_STO1_ADC_MIXER, + RT5682_STO1_ADC1L_SRC_SFT, rt5682_sto1_adc1_src); + +static const struct snd_kcontrol_new rt5682_sto1_adc1l_mux = + SOC_DAPM_ENUM("Stereo1 ADC1L Source", rt5682_sto1_adc1l_enum); + +static SOC_ENUM_SINGLE_DECL( + rt5682_sto1_adc1r_enum, RT5682_STO1_ADC_MIXER, + RT5682_STO1_ADC1R_SRC_SFT, rt5682_sto1_adc1_src); + +static const struct snd_kcontrol_new rt5682_sto1_adc1r_mux = + SOC_DAPM_ENUM("Stereo1 ADC1L Source", rt5682_sto1_adc1r_enum); + +/* STO1 ADC Source */ +/* MX-26 [11:10] [3:2] */ +static const char * const rt5682_sto1_adc_src[] = { + "ADC1 L", "ADC1 R" +}; + +static SOC_ENUM_SINGLE_DECL( + rt5682_sto1_adcl_enum, RT5682_STO1_ADC_MIXER, + RT5682_STO1_ADCL_SRC_SFT, rt5682_sto1_adc_src); + +static const struct snd_kcontrol_new rt5682_sto1_adcl_mux = + SOC_DAPM_ENUM("Stereo1 ADCL Source", rt5682_sto1_adcl_enum); + +static SOC_ENUM_SINGLE_DECL( + rt5682_sto1_adcr_enum, RT5682_STO1_ADC_MIXER, + RT5682_STO1_ADCR_SRC_SFT, rt5682_sto1_adc_src); + +static const struct snd_kcontrol_new rt5682_sto1_adcr_mux = + SOC_DAPM_ENUM("Stereo1 ADCR Source", rt5682_sto1_adcr_enum); + +/* STO1 ADC2 Source */ +/* MX-26 [12] [4] */ +static const char * const rt5682_sto1_adc2_src[] = { + "DAC MIX", "DMIC" +}; + +static SOC_ENUM_SINGLE_DECL( + rt5682_sto1_adc2l_enum, RT5682_STO1_ADC_MIXER, + RT5682_STO1_ADC2L_SRC_SFT, rt5682_sto1_adc2_src); + +static const struct snd_kcontrol_new rt5682_sto1_adc2l_mux = + SOC_DAPM_ENUM("Stereo1 ADC2L Source", rt5682_sto1_adc2l_enum); + +static SOC_ENUM_SINGLE_DECL( + rt5682_sto1_adc2r_enum, RT5682_STO1_ADC_MIXER, + RT5682_STO1_ADC2R_SRC_SFT, rt5682_sto1_adc2_src); + +static const struct snd_kcontrol_new rt5682_sto1_adc2r_mux = + SOC_DAPM_ENUM("Stereo1 ADC2R Source", rt5682_sto1_adc2r_enum); + +/* MX-79 [6:4] I2S1 ADC data location */ +static const unsigned int rt5682_if1_adc_slot_values[] = { + 0, + 2, + 4, + 6, +}; + +static const char * const rt5682_if1_adc_slot_src[] = { + "Slot 0", "Slot 2", "Slot 4", "Slot 6" +}; + +static SOC_VALUE_ENUM_SINGLE_DECL(rt5682_if1_adc_slot_enum, + RT5682_TDM_CTRL, RT5682_TDM_ADC_LCA_SFT, RT5682_TDM_ADC_LCA_MASK, + rt5682_if1_adc_slot_src, rt5682_if1_adc_slot_values); + +static const struct snd_kcontrol_new rt5682_if1_adc_slot_mux = + SOC_DAPM_ENUM("IF1 ADC Slot location", rt5682_if1_adc_slot_enum); + +/* Analog DAC L1 Source, Analog DAC R1 Source*/ +/* MX-2B [4], MX-2B [0]*/ +static const char * const rt5682_alg_dac1_src[] = { + "Stereo1 DAC Mixer", "DAC1" +}; + +static SOC_ENUM_SINGLE_DECL( + rt5682_alg_dac_l1_enum, RT5682_A_DAC1_MUX, + RT5682_A_DACL1_SFT, rt5682_alg_dac1_src); + +static const struct snd_kcontrol_new rt5682_alg_dac_l1_mux = + SOC_DAPM_ENUM("Analog DAC L1 Source", rt5682_alg_dac_l1_enum); + +static SOC_ENUM_SINGLE_DECL( + rt5682_alg_dac_r1_enum, RT5682_A_DAC1_MUX, + RT5682_A_DACR1_SFT, rt5682_alg_dac1_src); + +static const struct snd_kcontrol_new rt5682_alg_dac_r1_mux = + SOC_DAPM_ENUM("Analog DAC R1 Source", rt5682_alg_dac_r1_enum); + +/* Out Switch */ +static const struct snd_kcontrol_new hpol_switch = + SOC_DAPM_SINGLE_AUTODISABLE("Switch", RT5682_HP_CTRL_1, + RT5682_L_MUTE_SFT, 1, 1); +static const struct snd_kcontrol_new hpor_switch = + SOC_DAPM_SINGLE_AUTODISABLE("Switch", RT5682_HP_CTRL_1, + RT5682_R_MUTE_SFT, 1, 1); + +static int rt5682_hp_event(struct snd_soc_dapm_widget *w, + struct snd_kcontrol *kcontrol, int event) +{ + struct snd_soc_component *component = + snd_soc_dapm_to_component(w->dapm); + + switch (event) { + case SND_SOC_DAPM_PRE_PMU: + snd_soc_component_write(component, + RT5682_HP_LOGIC_CTRL_2, 0x0012); + snd_soc_component_write(component, + RT5682_HP_CTRL_2, 0x6000); + snd_soc_component_update_bits(component, RT5682_STO_NG2_CTRL_1, + RT5682_NG2_EN_MASK, RT5682_NG2_EN); + snd_soc_component_update_bits(component, + RT5682_DEPOP_1, 0x60, 0x60); + break; + + case SND_SOC_DAPM_POST_PMD: + snd_soc_component_update_bits(component, + RT5682_DEPOP_1, 0x60, 0x0); + snd_soc_component_write(component, + RT5682_HP_CTRL_2, 0x0000); + break; + + default: + return 0; + } + + return 0; + +} + +static int set_dmic_power(struct snd_soc_dapm_widget *w, + struct snd_kcontrol *kcontrol, int event) +{ + switch (event) { + case SND_SOC_DAPM_POST_PMU: + /*Add delay to avoid pop noise*/ + msleep(150); + break; + + default: + return 0; + } + + return 0; +} + +static int rt5655_set_verf(struct snd_soc_dapm_widget *w, + struct snd_kcontrol *kcontrol, int event) +{ + struct snd_soc_component *component = + snd_soc_dapm_to_component(w->dapm); + + switch (event) { + case SND_SOC_DAPM_PRE_PMU: + switch (w->shift) { + case RT5682_PWR_VREF1_BIT: + snd_soc_component_update_bits(component, + RT5682_PWR_ANLG_1, RT5682_PWR_FV1, 0); + break; + + case RT5682_PWR_VREF2_BIT: + snd_soc_component_update_bits(component, + RT5682_PWR_ANLG_1, RT5682_PWR_FV2, 0); + break; + + default: + break; + } + break; + + case SND_SOC_DAPM_POST_PMU: + usleep_range(15000, 20000); + switch (w->shift) { + case RT5682_PWR_VREF1_BIT: + snd_soc_component_update_bits(component, + RT5682_PWR_ANLG_1, RT5682_PWR_FV1, + RT5682_PWR_FV1); + break; + + case RT5682_PWR_VREF2_BIT: + snd_soc_component_update_bits(component, + RT5682_PWR_ANLG_1, RT5682_PWR_FV2, + RT5682_PWR_FV2); + break; + + default: + break; + } + break; + + default: + return 0; + } + + return 0; +} + +static const unsigned int rt5682_adcdat_pin_values[] = { + 1, + 3, +}; + +static const char * const rt5682_adcdat_pin_select[] = { + "ADCDAT1", + "ADCDAT2", +}; + +static SOC_VALUE_ENUM_SINGLE_DECL(rt5682_adcdat_pin_enum, + RT5682_GPIO_CTRL_1, RT5682_GP4_PIN_SFT, RT5682_GP4_PIN_MASK, + rt5682_adcdat_pin_select, rt5682_adcdat_pin_values); + +static const struct snd_kcontrol_new rt5682_adcdat_pin_ctrl = + SOC_DAPM_ENUM("ADCDAT", rt5682_adcdat_pin_enum); + +static const struct snd_soc_dapm_widget rt5682_dapm_widgets[] = { + SND_SOC_DAPM_SUPPLY("LDO2", RT5682_PWR_ANLG_3, RT5682_PWR_LDO2_BIT, + 0, NULL, 0), + SND_SOC_DAPM_SUPPLY("PLL1", RT5682_PWR_ANLG_3, RT5682_PWR_PLL_BIT, + 0, NULL, 0), + SND_SOC_DAPM_SUPPLY("PLL2B", RT5682_PWR_ANLG_3, RT5682_PWR_PLL2B_BIT, + 0, NULL, 0), + SND_SOC_DAPM_SUPPLY("PLL2F", RT5682_PWR_ANLG_3, RT5682_PWR_PLL2F_BIT, + 0, NULL, 0), + SND_SOC_DAPM_SUPPLY("Vref1", RT5682_PWR_ANLG_1, RT5682_PWR_VREF1_BIT, 0, + rt5655_set_verf, SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMU), + SND_SOC_DAPM_SUPPLY("Vref2", RT5682_PWR_ANLG_1, RT5682_PWR_VREF2_BIT, 0, + rt5655_set_verf, SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMU), + + /* ASRC */ + SND_SOC_DAPM_SUPPLY_S("DAC STO1 ASRC", 1, RT5682_PLL_TRACK_1, + RT5682_DAC_STO1_ASRC_SFT, 0, NULL, 0), + SND_SOC_DAPM_SUPPLY_S("ADC STO1 ASRC", 1, RT5682_PLL_TRACK_1, + RT5682_ADC_STO1_ASRC_SFT, 0, NULL, 0), + SND_SOC_DAPM_SUPPLY_S("AD ASRC", 1, RT5682_PLL_TRACK_1, + RT5682_AD_ASRC_SFT, 0, NULL, 0), + SND_SOC_DAPM_SUPPLY_S("DA ASRC", 1, RT5682_PLL_TRACK_1, + RT5682_DA_ASRC_SFT, 0, NULL, 0), + SND_SOC_DAPM_SUPPLY_S("DMIC ASRC", 1, RT5682_PLL_TRACK_1, + RT5682_DMIC_ASRC_SFT, 0, NULL, 0), + + /* Input Side */ + SND_SOC_DAPM_SUPPLY("MICBIAS1", RT5682_PWR_ANLG_2, RT5682_PWR_MB1_BIT, + 0, NULL, 0), + SND_SOC_DAPM_SUPPLY("MICBIAS2", RT5682_PWR_ANLG_2, RT5682_PWR_MB2_BIT, + 0, NULL, 0), + + /* Input Lines */ + SND_SOC_DAPM_INPUT("DMIC L1"), + SND_SOC_DAPM_INPUT("DMIC R1"), + + SND_SOC_DAPM_INPUT("IN1P"), + + SND_SOC_DAPM_SUPPLY("DMIC CLK", SND_SOC_NOPM, 0, 0, + set_dmic_clk, SND_SOC_DAPM_PRE_PMU), + SND_SOC_DAPM_SUPPLY("DMIC1 Power", RT5682_DMIC_CTRL_1, + RT5682_DMIC_1_EN_SFT, 0, set_dmic_power, SND_SOC_DAPM_POST_PMU), + + /* Boost */ + SND_SOC_DAPM_PGA("BST1 CBJ", SND_SOC_NOPM, + 0, 0, NULL, 0), + + SND_SOC_DAPM_SUPPLY("CBJ Power", RT5682_PWR_ANLG_3, + RT5682_PWR_CBJ_BIT, 0, NULL, 0), + + /* REC Mixer */ + SND_SOC_DAPM_MIXER("RECMIX1L", SND_SOC_NOPM, 0, 0, rt5682_rec1_l_mix, + ARRAY_SIZE(rt5682_rec1_l_mix)), + SND_SOC_DAPM_SUPPLY("RECMIX1L Power", RT5682_PWR_ANLG_2, + RT5682_PWR_RM1_L_BIT, 0, NULL, 0), + + /* ADCs */ + SND_SOC_DAPM_ADC("ADC1 L", NULL, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_ADC("ADC1 R", NULL, SND_SOC_NOPM, 0, 0), + + SND_SOC_DAPM_SUPPLY("ADC1 L Power", RT5682_PWR_DIG_1, + RT5682_PWR_ADC_L1_BIT, 0, NULL, 0), + SND_SOC_DAPM_SUPPLY("ADC1 R Power", RT5682_PWR_DIG_1, + RT5682_PWR_ADC_R1_BIT, 0, NULL, 0), + SND_SOC_DAPM_SUPPLY("ADC1 clock", RT5682_CHOP_ADC, + RT5682_CKGEN_ADC1_SFT, 0, NULL, 0), + + /* ADC Mux */ + SND_SOC_DAPM_MUX("Stereo1 ADC L1 Mux", SND_SOC_NOPM, 0, 0, + &rt5682_sto1_adc1l_mux), + SND_SOC_DAPM_MUX("Stereo1 ADC R1 Mux", SND_SOC_NOPM, 0, 0, + &rt5682_sto1_adc1r_mux), + SND_SOC_DAPM_MUX("Stereo1 ADC L2 Mux", SND_SOC_NOPM, 0, 0, + &rt5682_sto1_adc2l_mux), + SND_SOC_DAPM_MUX("Stereo1 ADC R2 Mux", SND_SOC_NOPM, 0, 0, + &rt5682_sto1_adc2r_mux), + SND_SOC_DAPM_MUX("Stereo1 ADC L Mux", SND_SOC_NOPM, 0, 0, + &rt5682_sto1_adcl_mux), + SND_SOC_DAPM_MUX("Stereo1 ADC R Mux", SND_SOC_NOPM, 0, 0, + &rt5682_sto1_adcr_mux), + SND_SOC_DAPM_MUX("IF1_ADC Mux", SND_SOC_NOPM, 0, 0, + &rt5682_if1_adc_slot_mux), + + /* ADC Mixer */ + SND_SOC_DAPM_SUPPLY("ADC Stereo1 Filter", RT5682_PWR_DIG_2, + RT5682_PWR_ADC_S1F_BIT, 0, set_filter_clk, + SND_SOC_DAPM_PRE_PMU), + SND_SOC_DAPM_MIXER("Stereo1 ADC MIXL", RT5682_STO1_ADC_DIG_VOL, + RT5682_L_MUTE_SFT, 1, rt5682_sto1_adc_l_mix, + ARRAY_SIZE(rt5682_sto1_adc_l_mix)), + SND_SOC_DAPM_MIXER("Stereo1 ADC MIXR", RT5682_STO1_ADC_DIG_VOL, + RT5682_R_MUTE_SFT, 1, rt5682_sto1_adc_r_mix, + ARRAY_SIZE(rt5682_sto1_adc_r_mix)), + + /* ADC PGA */ + SND_SOC_DAPM_PGA("Stereo1 ADC MIX", SND_SOC_NOPM, 0, 0, NULL, 0), + + /* Digital Interface */ + SND_SOC_DAPM_SUPPLY("I2S1", RT5682_PWR_DIG_1, RT5682_PWR_I2S1_BIT, + 0, NULL, 0), + SND_SOC_DAPM_SUPPLY("I2S2", RT5682_PWR_DIG_1, RT5682_PWR_I2S2_BIT, + 0, NULL, 0), + SND_SOC_DAPM_PGA("IF1 DAC1", SND_SOC_NOPM, 0, 0, NULL, 0), + SND_SOC_DAPM_PGA("IF1 DAC1 L", SND_SOC_NOPM, 0, 0, NULL, 0), + SND_SOC_DAPM_PGA("IF1 DAC1 R", SND_SOC_NOPM, 0, 0, NULL, 0), + + /* Digital Interface Select */ + SND_SOC_DAPM_MUX("IF1 01 ADC Swap Mux", SND_SOC_NOPM, 0, 0, + &rt5682_if1_01_adc_swap_mux), + SND_SOC_DAPM_MUX("IF1 23 ADC Swap Mux", SND_SOC_NOPM, 0, 0, + &rt5682_if1_23_adc_swap_mux), + SND_SOC_DAPM_MUX("IF1 45 ADC Swap Mux", SND_SOC_NOPM, 0, 0, + &rt5682_if1_45_adc_swap_mux), + SND_SOC_DAPM_MUX("IF1 67 ADC Swap Mux", SND_SOC_NOPM, 0, 0, + &rt5682_if1_67_adc_swap_mux), + SND_SOC_DAPM_MUX("IF2 ADC Swap Mux", SND_SOC_NOPM, 0, 0, + &rt5682_if2_adc_swap_mux), + + SND_SOC_DAPM_MUX("ADCDAT Mux", SND_SOC_NOPM, 0, 0, + &rt5682_adcdat_pin_ctrl), + + /* Audio Interface */ + SND_SOC_DAPM_AIF_OUT("AIF1TX", "AIF1 Capture", 0, + RT5682_I2S1_SDP, RT5682_SEL_ADCDAT_SFT, 1), + SND_SOC_DAPM_AIF_OUT("AIF2TX", "AIF2 Capture", 0, + RT5682_I2S2_SDP, RT5682_I2S2_PIN_CFG_SFT, 1), + SND_SOC_DAPM_AIF_IN("AIF1RX", "AIF1 Playback", 0, SND_SOC_NOPM, 0, 0), + + /* Output Side */ + /* DAC mixer before sound effect */ + SND_SOC_DAPM_MIXER("DAC1 MIXL", SND_SOC_NOPM, 0, 0, + rt5682_dac_l_mix, ARRAY_SIZE(rt5682_dac_l_mix)), + SND_SOC_DAPM_MIXER("DAC1 MIXR", SND_SOC_NOPM, 0, 0, + rt5682_dac_r_mix, ARRAY_SIZE(rt5682_dac_r_mix)), + + /* DAC channel Mux */ + SND_SOC_DAPM_MUX("DAC L1 Source", SND_SOC_NOPM, 0, 0, + &rt5682_alg_dac_l1_mux), + SND_SOC_DAPM_MUX("DAC R1 Source", SND_SOC_NOPM, 0, 0, + &rt5682_alg_dac_r1_mux), + + /* DAC Mixer */ + SND_SOC_DAPM_SUPPLY("DAC Stereo1 Filter", RT5682_PWR_DIG_2, + RT5682_PWR_DAC_S1F_BIT, 0, set_filter_clk, + SND_SOC_DAPM_PRE_PMU), + SND_SOC_DAPM_MIXER("Stereo1 DAC MIXL", SND_SOC_NOPM, 0, 0, + rt5682_sto1_dac_l_mix, ARRAY_SIZE(rt5682_sto1_dac_l_mix)), + SND_SOC_DAPM_MIXER("Stereo1 DAC MIXR", SND_SOC_NOPM, 0, 0, + rt5682_sto1_dac_r_mix, ARRAY_SIZE(rt5682_sto1_dac_r_mix)), + + /* DACs */ + SND_SOC_DAPM_DAC("DAC L1", NULL, RT5682_PWR_DIG_1, + RT5682_PWR_DAC_L1_BIT, 0), + SND_SOC_DAPM_DAC("DAC R1", NULL, RT5682_PWR_DIG_1, + RT5682_PWR_DAC_R1_BIT, 0), + SND_SOC_DAPM_SUPPLY_S("DAC 1 Clock", 3, RT5682_CHOP_DAC, + RT5682_CKGEN_DAC1_SFT, 0, NULL, 0), + + /* HPO */ + SND_SOC_DAPM_PGA_S("HP Amp", 1, SND_SOC_NOPM, 0, 0, rt5682_hp_event, + SND_SOC_DAPM_POST_PMD | SND_SOC_DAPM_PRE_PMU), + + SND_SOC_DAPM_SUPPLY("HP Amp L", RT5682_PWR_ANLG_1, + RT5682_PWR_HA_L_BIT, 0, NULL, 0), + SND_SOC_DAPM_SUPPLY("HP Amp R", RT5682_PWR_ANLG_1, + RT5682_PWR_HA_R_BIT, 0, NULL, 0), + SND_SOC_DAPM_SUPPLY_S("Charge Pump", 1, RT5682_DEPOP_1, + RT5682_PUMP_EN_SFT, 0, NULL, 0), + SND_SOC_DAPM_SUPPLY_S("Capless", 2, RT5682_DEPOP_1, + RT5682_CAPLESS_EN_SFT, 0, NULL, 0), + + SND_SOC_DAPM_SWITCH("HPOL Playback", SND_SOC_NOPM, 0, 0, + &hpol_switch), + SND_SOC_DAPM_SWITCH("HPOR Playback", SND_SOC_NOPM, 0, 0, + &hpor_switch), + + /* CLK DET */ + SND_SOC_DAPM_SUPPLY("CLKDET SYS", RT5682_CLK_DET, + RT5682_SYS_CLK_DET_SFT, 0, NULL, 0), + SND_SOC_DAPM_SUPPLY("CLKDET PLL1", RT5682_CLK_DET, + RT5682_PLL1_CLK_DET_SFT, 0, NULL, 0), + SND_SOC_DAPM_SUPPLY("CLKDET PLL2", RT5682_CLK_DET, + RT5682_PLL2_CLK_DET_SFT, 0, NULL, 0), + SND_SOC_DAPM_SUPPLY("CLKDET", RT5682_CLK_DET, + RT5682_POW_CLK_DET_SFT, 0, NULL, 0), + + /* Output Lines */ + SND_SOC_DAPM_OUTPUT("HPOL"), + SND_SOC_DAPM_OUTPUT("HPOR"), + +}; + +static const struct snd_soc_dapm_route rt5682_dapm_routes[] = { + /*PLL*/ + {"ADC Stereo1 Filter", NULL, "PLL1", is_sys_clk_from_pll1}, + {"DAC Stereo1 Filter", NULL, "PLL1", is_sys_clk_from_pll1}, + + /*ASRC*/ + {"ADC Stereo1 Filter", NULL, "ADC STO1 ASRC", is_using_asrc}, + {"DAC Stereo1 Filter", NULL, "DAC STO1 ASRC", is_using_asrc}, + {"ADC STO1 ASRC", NULL, "AD ASRC"}, + {"ADC STO1 ASRC", NULL, "CLKDET"}, + {"DAC STO1 ASRC", NULL, "DA ASRC"}, + {"DAC STO1 ASRC", NULL, "CLKDET"}, + + /*Vref*/ + {"MICBIAS1", NULL, "Vref1"}, + {"MICBIAS1", NULL, "Vref2"}, + {"MICBIAS2", NULL, "Vref1"}, + {"MICBIAS2", NULL, "Vref2"}, + + {"CLKDET SYS", NULL, "CLKDET"}, + + {"IN1P", NULL, "LDO2"}, + + {"BST1 CBJ", NULL, "IN1P"}, + {"BST1 CBJ", NULL, "CBJ Power"}, + {"CBJ Power", NULL, "Vref2"}, + + {"RECMIX1L", "CBJ Switch", "BST1 CBJ"}, + {"RECMIX1L", NULL, "RECMIX1L Power"}, + + {"ADC1 L", NULL, "RECMIX1L"}, + {"ADC1 L", NULL, "ADC1 L Power"}, + {"ADC1 L", NULL, "ADC1 clock"}, + + {"DMIC L1", NULL, "DMIC CLK"}, + {"DMIC L1", NULL, "DMIC1 Power"}, + {"DMIC R1", NULL, "DMIC CLK"}, + {"DMIC R1", NULL, "DMIC1 Power"}, + {"DMIC CLK", NULL, "DMIC ASRC"}, + + {"Stereo1 ADC L Mux", "ADC1 L", "ADC1 L"}, + {"Stereo1 ADC L Mux", "ADC1 R", "ADC1 R"}, + {"Stereo1 ADC R Mux", "ADC1 L", "ADC1 L"}, + {"Stereo1 ADC R Mux", "ADC1 R", "ADC1 R"}, + + {"Stereo1 ADC L1 Mux", "ADC", "Stereo1 ADC L Mux"}, + {"Stereo1 ADC L1 Mux", "DAC MIX", "Stereo1 DAC MIXL"}, + {"Stereo1 ADC L2 Mux", "DMIC", "DMIC L1"}, + {"Stereo1 ADC L2 Mux", "DAC MIX", "Stereo1 DAC MIXL"}, + + {"Stereo1 ADC R1 Mux", "ADC", "Stereo1 ADC R Mux"}, + {"Stereo1 ADC R1 Mux", "DAC MIX", "Stereo1 DAC MIXR"}, + {"Stereo1 ADC R2 Mux", "DMIC", "DMIC R1"}, + {"Stereo1 ADC R2 Mux", "DAC MIX", "Stereo1 DAC MIXR"}, + + {"Stereo1 ADC MIXL", "ADC1 Switch", "Stereo1 ADC L1 Mux"}, + {"Stereo1 ADC MIXL", "ADC2 Switch", "Stereo1 ADC L2 Mux"}, + {"Stereo1 ADC MIXL", NULL, "ADC Stereo1 Filter"}, + + {"Stereo1 ADC MIXR", "ADC1 Switch", "Stereo1 ADC R1 Mux"}, + {"Stereo1 ADC MIXR", "ADC2 Switch", "Stereo1 ADC R2 Mux"}, + {"Stereo1 ADC MIXR", NULL, "ADC Stereo1 Filter"}, + + {"Stereo1 ADC MIX", NULL, "Stereo1 ADC MIXL"}, + {"Stereo1 ADC MIX", NULL, "Stereo1 ADC MIXR"}, + + {"IF1 01 ADC Swap Mux", "L/R", "Stereo1 ADC MIX"}, + {"IF1 01 ADC Swap Mux", "L/L", "Stereo1 ADC MIX"}, + {"IF1 01 ADC Swap Mux", "R/L", "Stereo1 ADC MIX"}, + {"IF1 01 ADC Swap Mux", "R/R", "Stereo1 ADC MIX"}, + {"IF1 23 ADC Swap Mux", "L/R", "Stereo1 ADC MIX"}, + {"IF1 23 ADC Swap Mux", "R/L", "Stereo1 ADC MIX"}, + {"IF1 23 ADC Swap Mux", "L/L", "Stereo1 ADC MIX"}, + {"IF1 23 ADC Swap Mux", "R/R", "Stereo1 ADC MIX"}, + {"IF1 45 ADC Swap Mux", "L/R", "Stereo1 ADC MIX"}, + {"IF1 45 ADC Swap Mux", "R/L", "Stereo1 ADC MIX"}, + {"IF1 45 ADC Swap Mux", "L/L", "Stereo1 ADC MIX"}, + {"IF1 45 ADC Swap Mux", "R/R", "Stereo1 ADC MIX"}, + {"IF1 67 ADC Swap Mux", "L/R", "Stereo1 ADC MIX"}, + {"IF1 67 ADC Swap Mux", "R/L", "Stereo1 ADC MIX"}, + {"IF1 67 ADC Swap Mux", "L/L", "Stereo1 ADC MIX"}, + {"IF1 67 ADC Swap Mux", "R/R", "Stereo1 ADC MIX"}, + + {"IF1_ADC Mux", "Slot 0", "IF1 01 ADC Swap Mux"}, + {"IF1_ADC Mux", "Slot 2", "IF1 23 ADC Swap Mux"}, + {"IF1_ADC Mux", "Slot 4", "IF1 45 ADC Swap Mux"}, + {"IF1_ADC Mux", "Slot 6", "IF1 67 ADC Swap Mux"}, + {"IF1_ADC Mux", NULL, "I2S1"}, + {"ADCDAT Mux", "ADCDAT1", "IF1_ADC Mux"}, + {"AIF1TX", NULL, "ADCDAT Mux"}, + {"IF2 ADC Swap Mux", "L/R", "Stereo1 ADC MIX"}, + {"IF2 ADC Swap Mux", "R/L", "Stereo1 ADC MIX"}, + {"IF2 ADC Swap Mux", "L/L", "Stereo1 ADC MIX"}, + {"IF2 ADC Swap Mux", "R/R", "Stereo1 ADC MIX"}, + {"ADCDAT Mux", "ADCDAT2", "IF2 ADC Swap Mux"}, + {"AIF2TX", NULL, "ADCDAT Mux"}, + + {"IF1 DAC1 L", NULL, "AIF1RX"}, + {"IF1 DAC1 L", NULL, "I2S1"}, + {"IF1 DAC1 L", NULL, "DAC Stereo1 Filter"}, + {"IF1 DAC1 R", NULL, "AIF1RX"}, + {"IF1 DAC1 R", NULL, "I2S1"}, + {"IF1 DAC1 R", NULL, "DAC Stereo1 Filter"}, + + {"DAC1 MIXL", "Stereo ADC Switch", "Stereo1 ADC MIXL"}, + {"DAC1 MIXL", "DAC1 Switch", "IF1 DAC1 L"}, + {"DAC1 MIXR", "Stereo ADC Switch", "Stereo1 ADC MIXR"}, + {"DAC1 MIXR", "DAC1 Switch", "IF1 DAC1 R"}, + + {"Stereo1 DAC MIXL", "DAC L1 Switch", "DAC1 MIXL"}, + {"Stereo1 DAC MIXL", "DAC R1 Switch", "DAC1 MIXR"}, + + {"Stereo1 DAC MIXR", "DAC R1 Switch", "DAC1 MIXR"}, + {"Stereo1 DAC MIXR", "DAC L1 Switch", "DAC1 MIXL"}, + + {"DAC L1 Source", "DAC1", "DAC1 MIXL"}, + {"DAC L1 Source", "Stereo1 DAC Mixer", "Stereo1 DAC MIXL"}, + {"DAC R1 Source", "DAC1", "DAC1 MIXR"}, + {"DAC R1 Source", "Stereo1 DAC Mixer", "Stereo1 DAC MIXR"}, + + {"DAC L1", NULL, "DAC L1 Source"}, + {"DAC R1", NULL, "DAC R1 Source"}, + + {"DAC L1", NULL, "DAC 1 Clock"}, + {"DAC R1", NULL, "DAC 1 Clock"}, + + {"HP Amp", NULL, "DAC L1"}, + {"HP Amp", NULL, "DAC R1"}, + {"HP Amp", NULL, "HP Amp L"}, + {"HP Amp", NULL, "HP Amp R"}, + {"HP Amp", NULL, "Capless"}, + {"HP Amp", NULL, "Charge Pump"}, + {"HP Amp", NULL, "CLKDET SYS"}, + {"HP Amp", NULL, "CBJ Power"}, + {"HP Amp", NULL, "Vref2"}, + {"HPOL Playback", "Switch", "HP Amp"}, + {"HPOR Playback", "Switch", "HP Amp"}, + {"HPOL", NULL, "HPOL Playback"}, + {"HPOR", NULL, "HPOR Playback"}, +}; + +static int rt5682_set_tdm_slot(struct snd_soc_dai *dai, unsigned int tx_mask, + unsigned int rx_mask, int slots, int slot_width) +{ + struct snd_soc_component *component = dai->component; + unsigned int cl, val = 0; + + if (tx_mask || rx_mask) + snd_soc_component_update_bits(component, RT5682_TDM_ADDA_CTRL_2, + RT5682_TDM_EN, RT5682_TDM_EN); + else + snd_soc_component_update_bits(component, RT5682_TDM_ADDA_CTRL_2, + RT5682_TDM_EN, 0); + + switch (slots) { + case 4: + val |= RT5682_TDM_TX_CH_4; + val |= RT5682_TDM_RX_CH_4; + break; + case 6: + val |= RT5682_TDM_TX_CH_6; + val |= RT5682_TDM_RX_CH_6; + break; + case 8: + val |= RT5682_TDM_TX_CH_8; + val |= RT5682_TDM_RX_CH_8; + break; + case 2: + break; + default: + return -EINVAL; + } + + snd_soc_component_update_bits(component, RT5682_TDM_CTRL, + RT5682_TDM_TX_CH_MASK | RT5682_TDM_RX_CH_MASK, val); + + switch (slot_width) { + case 8: + if (tx_mask || rx_mask) + return -EINVAL; + cl = RT5682_I2S1_TX_CHL_8 | RT5682_I2S1_RX_CHL_8; + break; + case 16: + val = RT5682_TDM_CL_16; + cl = RT5682_I2S1_TX_CHL_16 | RT5682_I2S1_RX_CHL_16; + break; + case 20: + val = RT5682_TDM_CL_20; + cl = RT5682_I2S1_TX_CHL_20 | RT5682_I2S1_RX_CHL_20; + break; + case 24: + val = RT5682_TDM_CL_24; + cl = RT5682_I2S1_TX_CHL_24 | RT5682_I2S1_RX_CHL_24; + break; + case 32: + val = RT5682_TDM_CL_32; + cl = RT5682_I2S1_TX_CHL_32 | RT5682_I2S1_RX_CHL_32; + break; + default: + return -EINVAL; + } + + snd_soc_component_update_bits(component, RT5682_TDM_TCON_CTRL, + RT5682_TDM_CL_MASK, val); + snd_soc_component_update_bits(component, RT5682_I2S1_SDP, + RT5682_I2S1_TX_CHL_MASK | RT5682_I2S1_RX_CHL_MASK, cl); + + return 0; +} + + +static int rt5682_hw_params(struct snd_pcm_substream *substream, + struct snd_pcm_hw_params *params, struct snd_soc_dai *dai) +{ + struct snd_soc_component *component = dai->component; + struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component); + unsigned int len_1 = 0, len_2 = 0; + int pre_div, frame_size; + + rt5682->lrck[dai->id] = params_rate(params); + pre_div = rl6231_get_clk_info(rt5682->sysclk, rt5682->lrck[dai->id]); + + frame_size = snd_soc_params_to_frame_size(params); + if (frame_size < 0) { + dev_err(component->dev, "Unsupported frame size: %d\n", + frame_size); + return -EINVAL; + } + + dev_dbg(dai->dev, "lrck is %dHz and pre_div is %d for iis %d\n", + rt5682->lrck[dai->id], pre_div, dai->id); + + switch (params_width(params)) { + case 16: + break; + case 20: + len_1 |= RT5682_I2S1_DL_20; + len_2 |= RT5682_I2S2_DL_20; + break; + case 24: + len_1 |= RT5682_I2S1_DL_24; + len_2 |= RT5682_I2S2_DL_24; + break; + case 32: + len_1 |= RT5682_I2S1_DL_32; + len_2 |= RT5682_I2S2_DL_24; + break; + case 8: + len_1 |= RT5682_I2S2_DL_8; + len_2 |= RT5682_I2S2_DL_8; + break; + default: + return -EINVAL; + } + + switch (dai->id) { + case RT5682_AIF1: + snd_soc_component_update_bits(component, RT5682_I2S1_SDP, + RT5682_I2S1_DL_MASK, len_1); + if (rt5682->master[RT5682_AIF1]) { + snd_soc_component_update_bits(component, + RT5682_ADDA_CLK_1, RT5682_I2S_M_DIV_MASK, + pre_div << RT5682_I2S_M_DIV_SFT); + } + if (params_channels(params) == 1) /* mono mode */ + snd_soc_component_update_bits(component, + RT5682_I2S1_SDP, RT5682_I2S1_MONO_MASK, + RT5682_I2S1_MONO_EN); + else + snd_soc_component_update_bits(component, + RT5682_I2S1_SDP, RT5682_I2S1_MONO_MASK, + RT5682_I2S1_MONO_DIS); + break; + case RT5682_AIF2: + snd_soc_component_update_bits(component, RT5682_I2S2_SDP, + RT5682_I2S2_DL_MASK, len_2); + if (rt5682->master[RT5682_AIF2]) { + snd_soc_component_update_bits(component, + RT5682_I2S_M_CLK_CTRL_1, RT5682_I2S2_M_PD_MASK, + pre_div << RT5682_I2S2_M_PD_SFT); + } + if (params_channels(params) == 1) /* mono mode */ + snd_soc_component_update_bits(component, + RT5682_I2S2_SDP, RT5682_I2S2_MONO_MASK, + RT5682_I2S2_MONO_EN); + else + snd_soc_component_update_bits(component, + RT5682_I2S2_SDP, RT5682_I2S2_MONO_MASK, + RT5682_I2S2_MONO_DIS); + break; + default: + dev_err(component->dev, "Invalid dai->id: %d\n", dai->id); + return -EINVAL; + } + + return 0; +} + +static int rt5682_set_dai_fmt(struct snd_soc_dai *dai, unsigned int fmt) +{ + struct snd_soc_component *component = dai->component; + struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component); + unsigned int reg_val = 0, tdm_ctrl = 0; + + switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) { + case SND_SOC_DAIFMT_CBM_CFM: + rt5682->master[dai->id] = 1; + break; + case SND_SOC_DAIFMT_CBS_CFS: + rt5682->master[dai->id] = 0; + break; + default: + return -EINVAL; + } + + switch (fmt & SND_SOC_DAIFMT_INV_MASK) { + case SND_SOC_DAIFMT_NB_NF: + break; + case SND_SOC_DAIFMT_IB_NF: + reg_val |= RT5682_I2S_BP_INV; + tdm_ctrl |= RT5682_TDM_S_BP_INV; + break; + case SND_SOC_DAIFMT_NB_IF: + if (dai->id == RT5682_AIF1) + tdm_ctrl |= RT5682_TDM_S_LP_INV | RT5682_TDM_M_BP_INV; + else + return -EINVAL; + break; + case SND_SOC_DAIFMT_IB_IF: + if (dai->id == RT5682_AIF1) + tdm_ctrl |= RT5682_TDM_S_BP_INV | RT5682_TDM_S_LP_INV | + RT5682_TDM_M_BP_INV | RT5682_TDM_M_LP_INV; + else + return -EINVAL; + break; + default: + return -EINVAL; + } + + switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) { + case SND_SOC_DAIFMT_I2S: + break; + case SND_SOC_DAIFMT_LEFT_J: + reg_val |= RT5682_I2S_DF_LEFT; + tdm_ctrl |= RT5682_TDM_DF_LEFT; + break; + case SND_SOC_DAIFMT_DSP_A: + reg_val |= RT5682_I2S_DF_PCM_A; + tdm_ctrl |= RT5682_TDM_DF_PCM_A; + break; + case SND_SOC_DAIFMT_DSP_B: + reg_val |= RT5682_I2S_DF_PCM_B; + tdm_ctrl |= RT5682_TDM_DF_PCM_B; + break; + default: + return -EINVAL; + } + + switch (dai->id) { + case RT5682_AIF1: + snd_soc_component_update_bits(component, RT5682_I2S1_SDP, + RT5682_I2S_DF_MASK, reg_val); + snd_soc_component_update_bits(component, RT5682_TDM_TCON_CTRL, + RT5682_TDM_MS_MASK | RT5682_TDM_S_BP_MASK | + RT5682_TDM_DF_MASK | RT5682_TDM_M_BP_MASK | + RT5682_TDM_M_LP_MASK | RT5682_TDM_S_LP_MASK, + tdm_ctrl | rt5682->master[dai->id]); + break; + case RT5682_AIF2: + if (rt5682->master[dai->id] == 0) + reg_val |= RT5682_I2S2_MS_S; + snd_soc_component_update_bits(component, RT5682_I2S2_SDP, + RT5682_I2S2_MS_MASK | RT5682_I2S_BP_MASK | + RT5682_I2S_DF_MASK, reg_val); + break; + default: + dev_err(component->dev, "Invalid dai->id: %d\n", dai->id); + return -EINVAL; + } + return 0; +} + +static int rt5682_set_component_sysclk(struct snd_soc_component *component, + int clk_id, int source, unsigned int freq, int dir) +{ + struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component); + unsigned int reg_val = 0, src = 0; + + if (freq == rt5682->sysclk && clk_id == rt5682->sysclk_src) + return 0; + + switch (clk_id) { + case RT5682_SCLK_S_MCLK: + reg_val |= RT5682_SCLK_SRC_MCLK; + src = RT5682_CLK_SRC_MCLK; + break; + case RT5682_SCLK_S_PLL1: + reg_val |= RT5682_SCLK_SRC_PLL1; + src = RT5682_CLK_SRC_PLL1; + break; + case RT5682_SCLK_S_PLL2: + reg_val |= RT5682_SCLK_SRC_PLL2; + src = RT5682_CLK_SRC_PLL2; + break; + case RT5682_SCLK_S_RCCLK: + reg_val |= RT5682_SCLK_SRC_RCCLK; + src = RT5682_CLK_SRC_RCCLK; + break; + default: + dev_err(component->dev, "Invalid clock id (%d)\n", clk_id); + return -EINVAL; + } + snd_soc_component_update_bits(component, RT5682_GLB_CLK, + RT5682_SCLK_SRC_MASK, reg_val); + + if (rt5682->master[RT5682_AIF2]) { + snd_soc_component_update_bits(component, + RT5682_I2S_M_CLK_CTRL_1, RT5682_I2S2_SRC_MASK, + src << RT5682_I2S2_SRC_SFT); + } + + rt5682->sysclk = freq; + rt5682->sysclk_src = clk_id; + + dev_dbg(component->dev, "Sysclk is %dHz and clock id is %d\n", + freq, clk_id); + + return 0; +} + +static int rt5682_set_component_pll(struct snd_soc_component *component, + int pll_id, int source, unsigned int freq_in, + unsigned int freq_out) +{ + struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component); + struct rl6231_pll_code pll_code; + int ret; + + if (source == rt5682->pll_src && freq_in == rt5682->pll_in && + freq_out == rt5682->pll_out) + return 0; + + if (!freq_in || !freq_out) { + dev_dbg(component->dev, "PLL disabled\n"); + + rt5682->pll_in = 0; + rt5682->pll_out = 0; + snd_soc_component_update_bits(component, RT5682_GLB_CLK, + RT5682_SCLK_SRC_MASK, RT5682_SCLK_SRC_MCLK); + return 0; + } + + switch (source) { + case RT5682_PLL1_S_MCLK: + snd_soc_component_update_bits(component, RT5682_GLB_CLK, + RT5682_PLL1_SRC_MASK, RT5682_PLL1_SRC_MCLK); + break; + case RT5682_PLL1_S_BCLK1: + snd_soc_component_update_bits(component, RT5682_GLB_CLK, + RT5682_PLL1_SRC_MASK, RT5682_PLL1_SRC_BCLK1); + break; + default: + dev_err(component->dev, "Unknown PLL Source %d\n", source); + return -EINVAL; + } + + ret = rl6231_pll_calc(freq_in, freq_out, &pll_code); + if (ret < 0) { + dev_err(component->dev, "Unsupport input clock %d\n", freq_in); + return ret; + } + + dev_dbg(component->dev, "bypass=%d m=%d n=%d k=%d\n", + pll_code.m_bp, (pll_code.m_bp ? 0 : pll_code.m_code), + pll_code.n_code, pll_code.k_code); + + snd_soc_component_write(component, RT5682_PLL_CTRL_1, + pll_code.n_code << RT5682_PLL_N_SFT | pll_code.k_code); + snd_soc_component_write(component, RT5682_PLL_CTRL_2, + (pll_code.m_bp ? 0 : pll_code.m_code) << RT5682_PLL_M_SFT | + pll_code.m_bp << RT5682_PLL_M_BP_SFT | RT5682_PLL_RST); + + rt5682->pll_in = freq_in; + rt5682->pll_out = freq_out; + rt5682->pll_src = source; + + return 0; +} + +static int rt5682_set_bclk_ratio(struct snd_soc_dai *dai, unsigned int ratio) +{ + struct snd_soc_component *component = dai->component; + struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component); + + rt5682->bclk[dai->id] = ratio; + + switch (ratio) { + case 64: + snd_soc_component_update_bits(component, RT5682_ADDA_CLK_2, + RT5682_I2S2_BCLK_MS2_MASK, + RT5682_I2S2_BCLK_MS2_64); + break; + case 32: + snd_soc_component_update_bits(component, RT5682_ADDA_CLK_2, + RT5682_I2S2_BCLK_MS2_MASK, + RT5682_I2S2_BCLK_MS2_32); + break; + default: + dev_err(dai->dev, "Invalid bclk ratio %d\n", ratio); + return -EINVAL; + } + + return 0; +} + +static int rt5682_set_bias_level(struct snd_soc_component *component, + enum snd_soc_bias_level level) +{ + struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component); + + switch (level) { + case SND_SOC_BIAS_PREPARE: + regmap_update_bits(rt5682->regmap, RT5682_PWR_ANLG_1, + RT5682_PWR_MB | RT5682_PWR_BG, + RT5682_PWR_MB | RT5682_PWR_BG); + regmap_update_bits(rt5682->regmap, RT5682_PWR_DIG_1, + RT5682_DIG_GATE_CTRL | RT5682_PWR_LDO, + RT5682_DIG_GATE_CTRL | RT5682_PWR_LDO); + break; + + case SND_SOC_BIAS_STANDBY: + regmap_update_bits(rt5682->regmap, RT5682_PWR_ANLG_1, + RT5682_PWR_MB, RT5682_PWR_MB); + regmap_update_bits(rt5682->regmap, RT5682_PWR_DIG_1, + RT5682_DIG_GATE_CTRL, RT5682_DIG_GATE_CTRL); + break; + case SND_SOC_BIAS_OFF: + regmap_update_bits(rt5682->regmap, RT5682_PWR_DIG_1, + RT5682_DIG_GATE_CTRL | RT5682_PWR_LDO, 0); + regmap_update_bits(rt5682->regmap, RT5682_PWR_ANLG_1, + RT5682_PWR_MB | RT5682_PWR_BG, 0); + break; + + default: + break; + } + + return 0; +} + +static int rt5682_probe(struct snd_soc_component *component) +{ + struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component); + + rt5682->component = component; + + return 0; +} + +static void rt5682_remove(struct snd_soc_component *component) +{ + struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component); + + rt5682_reset(rt5682->regmap); +} + +#ifdef CONFIG_PM +static int rt5682_suspend(struct snd_soc_component *component) +{ + struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component); + + regcache_cache_only(rt5682->regmap, true); + regcache_mark_dirty(rt5682->regmap); + return 0; +} + +static int rt5682_resume(struct snd_soc_component *component) +{ + struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component); + + regcache_cache_only(rt5682->regmap, false); + regcache_sync(rt5682->regmap); + + return 0; +} +#else +#define rt5682_suspend NULL +#define rt5682_resume NULL +#endif + +#define RT5682_STEREO_RATES SNDRV_PCM_RATE_8000_192000 +#define RT5682_FORMATS (SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S20_3LE | \ + SNDRV_PCM_FMTBIT_S24_LE | SNDRV_PCM_FMTBIT_S8) + +static const struct snd_soc_dai_ops rt5682_aif1_dai_ops = { + .hw_params = rt5682_hw_params, + .set_fmt = rt5682_set_dai_fmt, + .set_tdm_slot = rt5682_set_tdm_slot, +}; + +static const struct snd_soc_dai_ops rt5682_aif2_dai_ops = { + .hw_params = rt5682_hw_params, + .set_fmt = rt5682_set_dai_fmt, + .set_bclk_ratio = rt5682_set_bclk_ratio, +}; + +static struct snd_soc_dai_driver rt5682_dai[] = { + { + .name = "rt5682-aif1", + .id = RT5682_AIF1, + .playback = { + .stream_name = "AIF1 Playback", + .channels_min = 1, + .channels_max = 2, + .rates = RT5682_STEREO_RATES, + .formats = RT5682_FORMATS, + }, + .capture = { + .stream_name = "AIF1 Capture", + .channels_min = 1, + .channels_max = 2, + .rates = RT5682_STEREO_RATES, + .formats = RT5682_FORMATS, + }, + .ops = &rt5682_aif1_dai_ops, + }, + { + .name = "rt5682-aif2", + .id = RT5682_AIF2, + .capture = { + .stream_name = "AIF2 Capture", + .channels_min = 1, + .channels_max = 2, + .rates = RT5682_STEREO_RATES, + .formats = RT5682_FORMATS, + }, + .ops = &rt5682_aif2_dai_ops, + }, +}; + +static const struct snd_soc_component_driver soc_component_dev_rt5682 = { + .probe = rt5682_probe, + .remove = rt5682_remove, + .suspend = rt5682_suspend, + .resume = rt5682_resume, + .set_bias_level = rt5682_set_bias_level, + .controls = rt5682_snd_controls, + .num_controls = ARRAY_SIZE(rt5682_snd_controls), + .dapm_widgets = rt5682_dapm_widgets, + .num_dapm_widgets = ARRAY_SIZE(rt5682_dapm_widgets), + .dapm_routes = rt5682_dapm_routes, + .num_dapm_routes = ARRAY_SIZE(rt5682_dapm_routes), + .set_sysclk = rt5682_set_component_sysclk, + .set_pll = rt5682_set_component_pll, + .set_jack = rt5682_set_jack_detect, + .use_pmdown_time = 1, + .endianness = 1, + .non_legacy_dai_naming = 1, +}; + +static const struct regmap_config rt5682_regmap = { + .reg_bits = 16, + .val_bits = 16, + .max_register = RT5682_I2C_MODE, + .volatile_reg = rt5682_volatile_register, + .readable_reg = rt5682_readable_register, + .cache_type = REGCACHE_RBTREE, + .reg_defaults = rt5682_reg, + .num_reg_defaults = ARRAY_SIZE(rt5682_reg), + .use_single_rw = true, +}; + +static const struct i2c_device_id rt5682_i2c_id[] = { + {"rt5682", 0}, + {} +}; +MODULE_DEVICE_TABLE(i2c, rt5682_i2c_id); + +static int rt5682_parse_dt(struct rt5682_priv *rt5682, struct device *dev) +{ + + device_property_read_u32(dev, "realtek,dmic1-data-pin", + &rt5682->pdata.dmic1_data_pin); + device_property_read_u32(dev, "realtek,dmic1-clk-pin", + &rt5682->pdata.dmic1_clk_pin); + device_property_read_u32(dev, "realtek,jd-src", + &rt5682->pdata.jd_src); + + rt5682->pdata.ldo1_en = of_get_named_gpio(dev->of_node, + "realtek,ldo1-en-gpios", 0); + + return 0; +} + +static void rt5682_calibrate(struct rt5682_priv *rt5682) +{ + int value, count; + + mutex_lock(&rt5682->calibrate_mutex); + + rt5682_reset(rt5682->regmap); + regmap_write(rt5682->regmap, RT5682_PWR_ANLG_1, 0xa2bf); + usleep_range(15000, 20000); + regmap_write(rt5682->regmap, RT5682_PWR_ANLG_1, 0xf2bf); + regmap_write(rt5682->regmap, RT5682_MICBIAS_2, 0x0380); + regmap_write(rt5682->regmap, RT5682_PWR_DIG_1, 0x8001); + regmap_write(rt5682->regmap, RT5682_TEST_MODE_CTRL_1, 0x0000); + regmap_write(rt5682->regmap, RT5682_STO1_DAC_MIXER, 0x2080); + regmap_write(rt5682->regmap, RT5682_STO1_ADC_MIXER, 0x4040); + regmap_write(rt5682->regmap, RT5682_DEPOP_1, 0x0069); + regmap_write(rt5682->regmap, RT5682_CHOP_DAC, 0x3000); + regmap_write(rt5682->regmap, RT5682_HP_CTRL_2, 0x6000); + regmap_write(rt5682->regmap, RT5682_HP_CHARGE_PUMP_1, 0x0f26); + regmap_write(rt5682->regmap, RT5682_CALIB_ADC_CTRL, 0x7f05); + regmap_write(rt5682->regmap, RT5682_STO1_ADC_MIXER, 0x686c); + regmap_write(rt5682->regmap, RT5682_CAL_REC, 0x0d0d); + regmap_write(rt5682->regmap, RT5682_HP_CALIB_CTRL_9, 0x000f); + regmap_write(rt5682->regmap, RT5682_PWR_DIG_1, 0x8d01); + regmap_write(rt5682->regmap, RT5682_HP_CALIB_CTRL_2, 0x0321); + regmap_write(rt5682->regmap, RT5682_HP_LOGIC_CTRL_2, 0x0004); + regmap_write(rt5682->regmap, RT5682_HP_CALIB_CTRL_1, 0x7c00); + regmap_write(rt5682->regmap, RT5682_HP_CALIB_CTRL_3, 0x06a1); + regmap_write(rt5682->regmap, RT5682_A_DAC1_MUX, 0x0311); + regmap_write(rt5682->regmap, RT5682_RESET_HPF_CTRL, 0x0000); + regmap_write(rt5682->regmap, RT5682_ADC_STO1_HP_CTRL_1, 0x3320); + + regmap_write(rt5682->regmap, RT5682_HP_CALIB_CTRL_1, 0xfc00); + + for (count = 0; count < 60; count++) { + regmap_read(rt5682->regmap, RT5682_HP_CALIB_STA_1, &value); + if (!(value & 0x8000)) + break; + + usleep_range(10000, 10005); + } + + if (count >= 60) + pr_err("HP Calibration Failure\n"); + + /* restore settings */ + regmap_write(rt5682->regmap, RT5682_STO1_ADC_MIXER, 0xc0c4); + regmap_write(rt5682->regmap, RT5682_PWR_DIG_1, 0x0000); + + mutex_unlock(&rt5682->calibrate_mutex); + +} + +static int rt5682_i2c_probe(struct i2c_client *i2c, + const struct i2c_device_id *id) +{ + struct rt5682_platform_data *pdata = dev_get_platdata(&i2c->dev); + struct rt5682_priv *rt5682; + int i, ret; + unsigned int val; + + rt5682 = devm_kzalloc(&i2c->dev, sizeof(struct rt5682_priv), + GFP_KERNEL); + + if (rt5682 == NULL) + return -ENOMEM; + + i2c_set_clientdata(i2c, rt5682); + + if (pdata) + rt5682->pdata = *pdata; + else + rt5682_parse_dt(rt5682, &i2c->dev); + + rt5682->regmap = devm_regmap_init_i2c(i2c, &rt5682_regmap); + if (IS_ERR(rt5682->regmap)) { + ret = PTR_ERR(rt5682->regmap); + dev_err(&i2c->dev, "Failed to allocate register map: %d\n", + ret); + return ret; + } + + for (i = 0; i < ARRAY_SIZE(rt5682->supplies); i++) + rt5682->supplies[i].supply = rt5682_supply_names[i]; + + ret = devm_regulator_bulk_get(&i2c->dev, ARRAY_SIZE(rt5682->supplies), + rt5682->supplies); + if (ret != 0) { + dev_err(&i2c->dev, "Failed to request supplies: %d\n", ret); + return ret; + } + + ret = regulator_bulk_enable(ARRAY_SIZE(rt5682->supplies), + rt5682->supplies); + if (ret != 0) { + dev_err(&i2c->dev, "Failed to enable supplies: %d\n", ret); + return ret; + } + + if (gpio_is_valid(rt5682->pdata.ldo1_en)) { + if (devm_gpio_request_one(&i2c->dev, rt5682->pdata.ldo1_en, + GPIOF_OUT_INIT_HIGH, "rt5682")) + dev_err(&i2c->dev, "Fail gpio_request gpio_ldo\n"); + } + + /* Sleep for 300 ms miniumum */ + usleep_range(300000, 350000); + + regmap_write(rt5682->regmap, RT5682_I2C_MODE, 0x1); + usleep_range(10000, 15000); + + regmap_read(rt5682->regmap, RT5682_DEVICE_ID, &val); + if (val != DEVICE_ID) { + pr_err("Device with ID register %x is not rt5682\n", val); + return -ENODEV; + } + + rt5682_reset(rt5682->regmap); + + rt5682_calibrate(rt5682); + + ret = regmap_register_patch(rt5682->regmap, patch_list, + ARRAY_SIZE(patch_list)); + if (ret != 0) + dev_warn(&i2c->dev, "Failed to apply regmap patch: %d\n", ret); + + regmap_write(rt5682->regmap, RT5682_DEPOP_1, 0x0000); + + /* DMIC pin*/ + if (rt5682->pdata.dmic1_data_pin != RT5682_DMIC1_NULL) { + switch (rt5682->pdata.dmic1_data_pin) { + case RT5682_DMIC1_DATA_GPIO2: /* share with LRCK2 */ + regmap_update_bits(rt5682->regmap, RT5682_DMIC_CTRL_1, + RT5682_DMIC_1_DP_MASK, RT5682_DMIC_1_DP_GPIO2); + regmap_update_bits(rt5682->regmap, RT5682_GPIO_CTRL_1, + RT5682_GP2_PIN_MASK, RT5682_GP2_PIN_DMIC_SDA); + break; + + case RT5682_DMIC1_DATA_GPIO5: /* share with DACDAT1 */ + regmap_update_bits(rt5682->regmap, RT5682_DMIC_CTRL_1, + RT5682_DMIC_1_DP_MASK, RT5682_DMIC_1_DP_GPIO5); + regmap_update_bits(rt5682->regmap, RT5682_GPIO_CTRL_1, + RT5682_GP5_PIN_MASK, RT5682_GP5_PIN_DMIC_SDA); + break; + + default: + dev_warn(&i2c->dev, "invalid DMIC_DAT pin\n"); + break; + } + + switch (rt5682->pdata.dmic1_clk_pin) { + case RT5682_DMIC1_CLK_GPIO1: /* share with IRQ */ + regmap_update_bits(rt5682->regmap, RT5682_GPIO_CTRL_1, + RT5682_GP1_PIN_MASK, RT5682_GP1_PIN_DMIC_CLK); + break; + + case RT5682_DMIC1_CLK_GPIO3: /* share with BCLK2 */ + regmap_update_bits(rt5682->regmap, RT5682_GPIO_CTRL_1, + RT5682_GP3_PIN_MASK, RT5682_GP3_PIN_DMIC_CLK); + break; + + default: + dev_warn(&i2c->dev, "invalid DMIC_CLK pin\n"); + break; + } + } + + regmap_update_bits(rt5682->regmap, RT5682_PWR_ANLG_1, + RT5682_LDO1_DVO_MASK | RT5682_HP_DRIVER_MASK, + RT5682_LDO1_DVO_12 | RT5682_HP_DRIVER_5X); + regmap_write(rt5682->regmap, RT5682_MICBIAS_2, 0x0380); + regmap_update_bits(rt5682->regmap, RT5682_GPIO_CTRL_1, + RT5682_GP4_PIN_MASK | RT5682_GP5_PIN_MASK, + RT5682_GP4_PIN_ADCDAT1 | RT5682_GP5_PIN_DACDAT1); + regmap_write(rt5682->regmap, RT5682_TEST_MODE_CTRL_1, 0x0000); + + INIT_DELAYED_WORK(&rt5682->jack_detect_work, + rt5682_jack_detect_handler); + INIT_DELAYED_WORK(&rt5682->jd_check_work, + rt5682_jd_check_handler); + + mutex_init(&rt5682->calibrate_mutex); + + if (i2c->irq) { + ret = devm_request_threaded_irq(&i2c->dev, i2c->irq, NULL, + rt5682_irq, IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING + | IRQF_ONESHOT, "rt5682", rt5682); + if (ret) + dev_err(&i2c->dev, "Failed to reguest IRQ: %d\n", ret); + + } + + return snd_soc_register_component(&i2c->dev, &soc_component_dev_rt5682, + rt5682_dai, ARRAY_SIZE(rt5682_dai)); +} + +static int rt5682_i2c_remove(struct i2c_client *i2c) +{ + snd_soc_unregister_component(&i2c->dev); + + return 0; +} + +static void rt5682_i2c_shutdown(struct i2c_client *client) +{ + struct rt5682_priv *rt5682 = i2c_get_clientdata(client); + + rt5682_reset(rt5682->regmap); +} + +#ifdef CONFIG_OF +static const struct of_device_id rt5682_of_match[] = { + {.compatible = "realtek,rt5682i"}, + {}, +}; +MODULE_DEVICE_TABLE(of, rt5682_of_match); +#endif + +#ifdef CONFIG_ACPI +static const struct acpi_device_id rt5682_acpi_match[] = { + {"10EC5682", 0,}, + {}, +}; +MODULE_DEVICE_TABLE(acpi, rt5682_acpi_match); +#endif + +static struct i2c_driver rt5682_i2c_driver = { + .driver = { + .name = "rt5682", + .of_match_table = of_match_ptr(rt5682_of_match), + .acpi_match_table = ACPI_PTR(rt5682_acpi_match), + }, + .probe = rt5682_i2c_probe, + .remove = rt5682_i2c_remove, + .shutdown = rt5682_i2c_shutdown, + .id_table = rt5682_i2c_id, +}; +module_i2c_driver(rt5682_i2c_driver); + +MODULE_DESCRIPTION("ASoC RT5682 driver"); +MODULE_AUTHOR("Bard Liao "); +MODULE_LICENSE("GPL v2"); diff --git a/sound/soc/codecs/rt5682.h b/sound/soc/codecs/rt5682.h new file mode 100644 index 000000000000..8068140ebe3f --- /dev/null +++ b/sound/soc/codecs/rt5682.h @@ -0,0 +1,1324 @@ +/* + * rt5682.h -- RT5682/RT5658 ALSA SoC audio driver + * + * Copyright 2018 Realtek Microelectronics + * Author: Bard Liao + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __RT5682_H__ +#define __RT5682_H__ + +#include + +#define DEVICE_ID 0x6530 + +/* Info */ +#define RT5682_RESET 0x0000 +#define RT5682_VERSION_ID 0x00fd +#define RT5682_VENDOR_ID 0x00fe +#define RT5682_DEVICE_ID 0x00ff +/* I/O - Output */ +#define RT5682_HP_CTRL_1 0x0002 +#define RT5682_HP_CTRL_2 0x0003 +#define RT5682_HPL_GAIN 0x0005 +#define RT5682_HPR_GAIN 0x0006 + +#define RT5682_I2C_CTRL 0x0008 + +/* I/O - Input */ +#define RT5682_CBJ_BST_CTRL 0x000b +#define RT5682_CBJ_CTRL_1 0x0010 +#define RT5682_CBJ_CTRL_2 0x0011 +#define RT5682_CBJ_CTRL_3 0x0012 +#define RT5682_CBJ_CTRL_4 0x0013 +#define RT5682_CBJ_CTRL_5 0x0014 +#define RT5682_CBJ_CTRL_6 0x0015 +#define RT5682_CBJ_CTRL_7 0x0016 +/* I/O - ADC/DAC/DMIC */ +#define RT5682_DAC1_DIG_VOL 0x0019 +#define RT5682_STO1_ADC_DIG_VOL 0x001c +#define RT5682_STO1_ADC_BOOST 0x001f +#define RT5682_HP_IMP_GAIN_1 0x0022 +#define RT5682_HP_IMP_GAIN_2 0x0023 +/* Mixer - D-D */ +#define RT5682_SIDETONE_CTRL 0x0024 +#define RT5682_STO1_ADC_MIXER 0x0026 +#define RT5682_AD_DA_MIXER 0x0029 +#define RT5682_STO1_DAC_MIXER 0x002a +#define RT5682_A_DAC1_MUX 0x002b +#define RT5682_DIG_INF2_DATA 0x0030 +/* Mixer - ADC */ +#define RT5682_REC_MIXER 0x003c +#define RT5682_CAL_REC 0x0044 +#define RT5682_ALC_BACK_GAIN 0x0049 +/* Power */ +#define RT5682_PWR_DIG_1 0x0061 +#define RT5682_PWR_DIG_2 0x0062 +#define RT5682_PWR_ANLG_1 0x0063 +#define RT5682_PWR_ANLG_2 0x0064 +#define RT5682_PWR_ANLG_3 0x0065 +#define RT5682_PWR_MIXER 0x0066 +#define RT5682_PWR_VOL 0x0067 +/* Clock Detect */ +#define RT5682_CLK_DET 0x006b +/* Filter Auto Reset */ +#define RT5682_RESET_LPF_CTRL 0x006c +#define RT5682_RESET_HPF_CTRL 0x006d +/* DMIC */ +#define RT5682_DMIC_CTRL_1 0x006e +/* Format - ADC/DAC */ +#define RT5682_I2S1_SDP 0x0070 +#define RT5682_I2S2_SDP 0x0071 +#define RT5682_ADDA_CLK_1 0x0073 +#define RT5682_ADDA_CLK_2 0x0074 +#define RT5682_I2S1_F_DIV_CTRL_1 0x0075 +#define RT5682_I2S1_F_DIV_CTRL_2 0x0076 +/* Format - TDM Control */ +#define RT5682_TDM_CTRL 0x0079 +#define RT5682_TDM_ADDA_CTRL_1 0x007a +#define RT5682_TDM_ADDA_CTRL_2 0x007b +#define RT5682_DATA_SEL_CTRL_1 0x007c +#define RT5682_TDM_TCON_CTRL 0x007e +/* Function - Analog */ +#define RT5682_GLB_CLK 0x0080 +#define RT5682_PLL_CTRL_1 0x0081 +#define RT5682_PLL_CTRL_2 0x0082 +#define RT5682_PLL_TRACK_1 0x0083 +#define RT5682_PLL_TRACK_2 0x0084 +#define RT5682_PLL_TRACK_3 0x0085 +#define RT5682_PLL_TRACK_4 0x0086 +#define RT5682_PLL_TRACK_5 0x0087 +#define RT5682_PLL_TRACK_6 0x0088 +#define RT5682_PLL_TRACK_11 0x008c +#define RT5682_SDW_REF_CLK 0x008d +#define RT5682_DEPOP_1 0x008e +#define RT5682_DEPOP_2 0x008f +#define RT5682_HP_CHARGE_PUMP_1 0x0091 +#define RT5682_HP_CHARGE_PUMP_2 0x0092 +#define RT5682_MICBIAS_1 0x0093 +#define RT5682_MICBIAS_2 0x0094 +#define RT5682_PLL_TRACK_12 0x0098 +#define RT5682_PLL_TRACK_14 0x009a +#define RT5682_PLL2_CTRL_1 0x009b +#define RT5682_PLL2_CTRL_2 0x009c +#define RT5682_PLL2_CTRL_3 0x009d +#define RT5682_PLL2_CTRL_4 0x009e +#define RT5682_RC_CLK_CTRL 0x009f +#define RT5682_I2S_M_CLK_CTRL_1 0x00a0 +#define RT5682_I2S2_F_DIV_CTRL_1 0x00a3 +#define RT5682_I2S2_F_DIV_CTRL_2 0x00a4 +/* Function - Digital */ +#define RT5682_EQ_CTRL_1 0x00ae +#define RT5682_EQ_CTRL_2 0x00af +#define RT5682_IRQ_CTRL_1 0x00b6 +#define RT5682_IRQ_CTRL_2 0x00b7 +#define RT5682_IRQ_CTRL_3 0x00b8 +#define RT5682_IRQ_CTRL_4 0x00b9 +#define RT5682_INT_ST_1 0x00be +#define RT5682_GPIO_CTRL_1 0x00c0 +#define RT5682_GPIO_CTRL_2 0x00c1 +#define RT5682_GPIO_CTRL_3 0x00c2 +#define RT5682_HP_AMP_DET_CTRL_1 0x00d0 +#define RT5682_HP_AMP_DET_CTRL_2 0x00d1 +#define RT5682_MID_HP_AMP_DET 0x00d2 +#define RT5682_LOW_HP_AMP_DET 0x00d3 +#define RT5682_DELAY_BUF_CTRL 0x00d4 +#define RT5682_SV_ZCD_1 0x00d9 +#define RT5682_SV_ZCD_2 0x00da +#define RT5682_IL_CMD_1 0x00db +#define RT5682_IL_CMD_2 0x00dc +#define RT5682_IL_CMD_3 0x00dd +#define RT5682_IL_CMD_4 0x00de +#define RT5682_IL_CMD_5 0x00df +#define RT5682_IL_CMD_6 0x00e0 +#define RT5682_4BTN_IL_CMD_1 0x00e2 +#define RT5682_4BTN_IL_CMD_2 0x00e3 +#define RT5682_4BTN_IL_CMD_3 0x00e4 +#define RT5682_4BTN_IL_CMD_4 0x00e5 +#define RT5682_4BTN_IL_CMD_5 0x00e6 +#define RT5682_4BTN_IL_CMD_6 0x00e7 +#define RT5682_4BTN_IL_CMD_7 0x00e8 + +#define RT5682_ADC_STO1_HP_CTRL_1 0x00ea +#define RT5682_ADC_STO1_HP_CTRL_2 0x00eb +#define RT5682_AJD1_CTRL 0x00f0 +#define RT5682_JD1_THD 0x00f1 +#define RT5682_JD2_THD 0x00f2 +#define RT5682_JD_CTRL_1 0x00f6 +/* General Control */ +#define RT5682_DUMMY_1 0x00fa +#define RT5682_DUMMY_2 0x00fb +#define RT5682_DUMMY_3 0x00fc + +#define RT5682_DAC_ADC_DIG_VOL1 0x0100 +#define RT5682_BIAS_CUR_CTRL_2 0x010b +#define RT5682_BIAS_CUR_CTRL_3 0x010c +#define RT5682_BIAS_CUR_CTRL_4 0x010d +#define RT5682_BIAS_CUR_CTRL_5 0x010e +#define RT5682_BIAS_CUR_CTRL_6 0x010f +#define RT5682_BIAS_CUR_CTRL_7 0x0110 +#define RT5682_BIAS_CUR_CTRL_8 0x0111 +#define RT5682_BIAS_CUR_CTRL_9 0x0112 +#define RT5682_BIAS_CUR_CTRL_10 0x0113 +#define RT5682_VREF_REC_OP_FB_CAP_CTRL 0x0117 +#define RT5682_CHARGE_PUMP_1 0x0125 +#define RT5682_DIG_IN_CTRL_1 0x0132 +#define RT5682_PAD_DRIVING_CTRL 0x0136 +#define RT5682_SOFT_RAMP_DEPOP 0x0138 +#define RT5682_CHOP_DAC 0x013a +#define RT5682_CHOP_ADC 0x013b +#define RT5682_CALIB_ADC_CTRL 0x013c +#define RT5682_VOL_TEST 0x013f +#define RT5682_SPKVDD_DET_STA 0x0142 +#define RT5682_TEST_MODE_CTRL_1 0x0145 +#define RT5682_TEST_MODE_CTRL_2 0x0146 +#define RT5682_TEST_MODE_CTRL_3 0x0147 +#define RT5682_TEST_MODE_CTRL_4 0x0148 +#define RT5682_TEST_MODE_CTRL_5 0x0149 +#define RT5682_PLL1_INTERNAL 0x0150 +#define RT5682_PLL2_INTERNAL 0x0151 +#define RT5682_STO_NG2_CTRL_1 0x0160 +#define RT5682_STO_NG2_CTRL_2 0x0161 +#define RT5682_STO_NG2_CTRL_3 0x0162 +#define RT5682_STO_NG2_CTRL_4 0x0163 +#define RT5682_STO_NG2_CTRL_5 0x0164 +#define RT5682_STO_NG2_CTRL_6 0x0165 +#define RT5682_STO_NG2_CTRL_7 0x0166 +#define RT5682_STO_NG2_CTRL_8 0x0167 +#define RT5682_STO_NG2_CTRL_9 0x0168 +#define RT5682_STO_NG2_CTRL_10 0x0169 +#define RT5682_STO1_DAC_SIL_DET 0x0190 +#define RT5682_SIL_PSV_CTRL1 0x0194 +#define RT5682_SIL_PSV_CTRL2 0x0195 +#define RT5682_SIL_PSV_CTRL3 0x0197 +#define RT5682_SIL_PSV_CTRL4 0x0198 +#define RT5682_SIL_PSV_CTRL5 0x0199 +#define RT5682_HP_IMP_SENS_CTRL_01 0x01af +#define RT5682_HP_IMP_SENS_CTRL_02 0x01b0 +#define RT5682_HP_IMP_SENS_CTRL_03 0x01b1 +#define RT5682_HP_IMP_SENS_CTRL_04 0x01b2 +#define RT5682_HP_IMP_SENS_CTRL_05 0x01b3 +#define RT5682_HP_IMP_SENS_CTRL_06 0x01b4 +#define RT5682_HP_IMP_SENS_CTRL_07 0x01b5 +#define RT5682_HP_IMP_SENS_CTRL_08 0x01b6 +#define RT5682_HP_IMP_SENS_CTRL_09 0x01b7 +#define RT5682_HP_IMP_SENS_CTRL_10 0x01b8 +#define RT5682_HP_IMP_SENS_CTRL_11 0x01b9 +#define RT5682_HP_IMP_SENS_CTRL_12 0x01ba +#define RT5682_HP_IMP_SENS_CTRL_13 0x01bb +#define RT5682_HP_IMP_SENS_CTRL_14 0x01bc +#define RT5682_HP_IMP_SENS_CTRL_15 0x01bd +#define RT5682_HP_IMP_SENS_CTRL_16 0x01be +#define RT5682_HP_IMP_SENS_CTRL_17 0x01bf +#define RT5682_HP_IMP_SENS_CTRL_18 0x01c0 +#define RT5682_HP_IMP_SENS_CTRL_19 0x01c1 +#define RT5682_HP_IMP_SENS_CTRL_20 0x01c2 +#define RT5682_HP_IMP_SENS_CTRL_21 0x01c3 +#define RT5682_HP_IMP_SENS_CTRL_22 0x01c4 +#define RT5682_HP_IMP_SENS_CTRL_23 0x01c5 +#define RT5682_HP_IMP_SENS_CTRL_24 0x01c6 +#define RT5682_HP_IMP_SENS_CTRL_25 0x01c7 +#define RT5682_HP_IMP_SENS_CTRL_26 0x01c8 +#define RT5682_HP_IMP_SENS_CTRL_27 0x01c9 +#define RT5682_HP_IMP_SENS_CTRL_28 0x01ca +#define RT5682_HP_IMP_SENS_CTRL_29 0x01cb +#define RT5682_HP_IMP_SENS_CTRL_30 0x01cc +#define RT5682_HP_IMP_SENS_CTRL_31 0x01cd +#define RT5682_HP_IMP_SENS_CTRL_32 0x01ce +#define RT5682_HP_IMP_SENS_CTRL_33 0x01cf +#define RT5682_HP_IMP_SENS_CTRL_34 0x01d0 +#define RT5682_HP_IMP_SENS_CTRL_35 0x01d1 +#define RT5682_HP_IMP_SENS_CTRL_36 0x01d2 +#define RT5682_HP_IMP_SENS_CTRL_37 0x01d3 +#define RT5682_HP_IMP_SENS_CTRL_38 0x01d4 +#define RT5682_HP_IMP_SENS_CTRL_39 0x01d5 +#define RT5682_HP_IMP_SENS_CTRL_40 0x01d6 +#define RT5682_HP_IMP_SENS_CTRL_41 0x01d7 +#define RT5682_HP_IMP_SENS_CTRL_42 0x01d8 +#define RT5682_HP_IMP_SENS_CTRL_43 0x01d9 +#define RT5682_HP_LOGIC_CTRL_1 0x01da +#define RT5682_HP_LOGIC_CTRL_2 0x01db +#define RT5682_HP_LOGIC_CTRL_3 0x01dc +#define RT5682_HP_CALIB_CTRL_1 0x01de +#define RT5682_HP_CALIB_CTRL_2 0x01df +#define RT5682_HP_CALIB_CTRL_3 0x01e0 +#define RT5682_HP_CALIB_CTRL_4 0x01e1 +#define RT5682_HP_CALIB_CTRL_5 0x01e2 +#define RT5682_HP_CALIB_CTRL_6 0x01e3 +#define RT5682_HP_CALIB_CTRL_7 0x01e4 +#define RT5682_HP_CALIB_CTRL_9 0x01e6 +#define RT5682_HP_CALIB_CTRL_10 0x01e7 +#define RT5682_HP_CALIB_CTRL_11 0x01e8 +#define RT5682_HP_CALIB_STA_1 0x01ea +#define RT5682_HP_CALIB_STA_2 0x01eb +#define RT5682_HP_CALIB_STA_3 0x01ec +#define RT5682_HP_CALIB_STA_4 0x01ed +#define RT5682_HP_CALIB_STA_5 0x01ee +#define RT5682_HP_CALIB_STA_6 0x01ef +#define RT5682_HP_CALIB_STA_7 0x01f0 +#define RT5682_HP_CALIB_STA_8 0x01f1 +#define RT5682_HP_CALIB_STA_9 0x01f2 +#define RT5682_HP_CALIB_STA_10 0x01f3 +#define RT5682_HP_CALIB_STA_11 0x01f4 +#define RT5682_SAR_IL_CMD_1 0x0210 +#define RT5682_SAR_IL_CMD_2 0x0211 +#define RT5682_SAR_IL_CMD_3 0x0212 +#define RT5682_SAR_IL_CMD_4 0x0213 +#define RT5682_SAR_IL_CMD_5 0x0214 +#define RT5682_SAR_IL_CMD_6 0x0215 +#define RT5682_SAR_IL_CMD_7 0x0216 +#define RT5682_SAR_IL_CMD_8 0x0217 +#define RT5682_SAR_IL_CMD_9 0x0218 +#define RT5682_SAR_IL_CMD_10 0x0219 +#define RT5682_SAR_IL_CMD_11 0x021a +#define RT5682_SAR_IL_CMD_12 0x021b +#define RT5682_SAR_IL_CMD_13 0x021c +#define RT5682_EFUSE_CTRL_1 0x0250 +#define RT5682_EFUSE_CTRL_2 0x0251 +#define RT5682_EFUSE_CTRL_3 0x0252 +#define RT5682_EFUSE_CTRL_4 0x0253 +#define RT5682_EFUSE_CTRL_5 0x0254 +#define RT5682_EFUSE_CTRL_6 0x0255 +#define RT5682_EFUSE_CTRL_7 0x0256 +#define RT5682_EFUSE_CTRL_8 0x0257 +#define RT5682_EFUSE_CTRL_9 0x0258 +#define RT5682_EFUSE_CTRL_10 0x0259 +#define RT5682_EFUSE_CTRL_11 0x025a +#define RT5682_JD_TOP_VC_VTRL 0x0270 +#define RT5682_DRC1_CTRL_0 0x02ff +#define RT5682_DRC1_CTRL_1 0x0300 +#define RT5682_DRC1_CTRL_2 0x0301 +#define RT5682_DRC1_CTRL_3 0x0302 +#define RT5682_DRC1_CTRL_4 0x0303 +#define RT5682_DRC1_CTRL_5 0x0304 +#define RT5682_DRC1_CTRL_6 0x0305 +#define RT5682_DRC1_HARD_LMT_CTRL_1 0x0306 +#define RT5682_DRC1_HARD_LMT_CTRL_2 0x0307 +#define RT5682_DRC1_PRIV_1 0x0310 +#define RT5682_DRC1_PRIV_2 0x0311 +#define RT5682_DRC1_PRIV_3 0x0312 +#define RT5682_DRC1_PRIV_4 0x0313 +#define RT5682_DRC1_PRIV_5 0x0314 +#define RT5682_DRC1_PRIV_6 0x0315 +#define RT5682_DRC1_PRIV_7 0x0316 +#define RT5682_DRC1_PRIV_8 0x0317 +#define RT5682_EQ_AUTO_RCV_CTRL1 0x03c0 +#define RT5682_EQ_AUTO_RCV_CTRL2 0x03c1 +#define RT5682_EQ_AUTO_RCV_CTRL3 0x03c2 +#define RT5682_EQ_AUTO_RCV_CTRL4 0x03c3 +#define RT5682_EQ_AUTO_RCV_CTRL5 0x03c4 +#define RT5682_EQ_AUTO_RCV_CTRL6 0x03c5 +#define RT5682_EQ_AUTO_RCV_CTRL7 0x03c6 +#define RT5682_EQ_AUTO_RCV_CTRL8 0x03c7 +#define RT5682_EQ_AUTO_RCV_CTRL9 0x03c8 +#define RT5682_EQ_AUTO_RCV_CTRL10 0x03c9 +#define RT5682_EQ_AUTO_RCV_CTRL11 0x03ca +#define RT5682_EQ_AUTO_RCV_CTRL12 0x03cb +#define RT5682_EQ_AUTO_RCV_CTRL13 0x03cc +#define RT5682_ADC_L_EQ_LPF1_A1 0x03d0 +#define RT5682_R_EQ_LPF1_A1 0x03d1 +#define RT5682_L_EQ_LPF1_H0 0x03d2 +#define RT5682_R_EQ_LPF1_H0 0x03d3 +#define RT5682_L_EQ_BPF1_A1 0x03d4 +#define RT5682_R_EQ_BPF1_A1 0x03d5 +#define RT5682_L_EQ_BPF1_A2 0x03d6 +#define RT5682_R_EQ_BPF1_A2 0x03d7 +#define RT5682_L_EQ_BPF1_H0 0x03d8 +#define RT5682_R_EQ_BPF1_H0 0x03d9 +#define RT5682_L_EQ_BPF2_A1 0x03da +#define RT5682_R_EQ_BPF2_A1 0x03db +#define RT5682_L_EQ_BPF2_A2 0x03dc +#define RT5682_R_EQ_BPF2_A2 0x03dd +#define RT5682_L_EQ_BPF2_H0 0x03de +#define RT5682_R_EQ_BPF2_H0 0x03df +#define RT5682_L_EQ_BPF3_A1 0x03e0 +#define RT5682_R_EQ_BPF3_A1 0x03e1 +#define RT5682_L_EQ_BPF3_A2 0x03e2 +#define RT5682_R_EQ_BPF3_A2 0x03e3 +#define RT5682_L_EQ_BPF3_H0 0x03e4 +#define RT5682_R_EQ_BPF3_H0 0x03e5 +#define RT5682_L_EQ_BPF4_A1 0x03e6 +#define RT5682_R_EQ_BPF4_A1 0x03e7 +#define RT5682_L_EQ_BPF4_A2 0x03e8 +#define RT5682_R_EQ_BPF4_A2 0x03e9 +#define RT5682_L_EQ_BPF4_H0 0x03ea +#define RT5682_R_EQ_BPF4_H0 0x03eb +#define RT5682_L_EQ_HPF1_A1 0x03ec +#define RT5682_R_EQ_HPF1_A1 0x03ed +#define RT5682_L_EQ_HPF1_H0 0x03ee +#define RT5682_R_EQ_HPF1_H0 0x03ef +#define RT5682_L_EQ_PRE_VOL 0x03f0 +#define RT5682_R_EQ_PRE_VOL 0x03f1 +#define RT5682_L_EQ_POST_VOL 0x03f2 +#define RT5682_R_EQ_POST_VOL 0x03f3 +#define RT5682_I2C_MODE 0xffff + + +/* global definition */ +#define RT5682_L_MUTE (0x1 << 15) +#define RT5682_L_MUTE_SFT 15 +#define RT5682_VOL_L_MUTE (0x1 << 14) +#define RT5682_VOL_L_SFT 14 +#define RT5682_R_MUTE (0x1 << 7) +#define RT5682_R_MUTE_SFT 7 +#define RT5682_VOL_R_MUTE (0x1 << 6) +#define RT5682_VOL_R_SFT 6 +#define RT5682_L_VOL_MASK (0x3f << 8) +#define RT5682_L_VOL_SFT 8 +#define RT5682_R_VOL_MASK (0x3f) +#define RT5682_R_VOL_SFT 0 + +/*Headphone Amp L/R Analog Gain and Digital NG2 Gain Control (0x0005 0x0006)*/ +#define RT5682_G_HP (0xf << 8) +#define RT5682_G_HP_SFT 8 +#define RT5682_G_STO_DA_DMIX (0xf) +#define RT5682_G_STO_DA_SFT 0 + +/* CBJ Control (0x000b) */ +#define RT5682_BST_CBJ_MASK (0xf << 8) +#define RT5682_BST_CBJ_SFT 8 + +/* Embeeded Jack and Type Detection Control 1 (0x0010) */ +#define RT5682_EMB_JD_EN (0x1 << 15) +#define RT5682_EMB_JD_EN_SFT 15 +#define RT5682_EMB_JD_RST (0x1 << 14) +#define RT5682_JD_MODE (0x1 << 13) +#define RT5682_JD_MODE_SFT 13 +#define RT5682_DET_TYPE (0x1 << 12) +#define RT5682_DET_TYPE_SFT 12 +#define RT5682_POLA_EXT_JD_MASK (0x1 << 11) +#define RT5682_POLA_EXT_JD_LOW (0x1 << 11) +#define RT5682_POLA_EXT_JD_HIGH (0x0 << 11) +#define RT5682_EXT_JD_DIG (0x1 << 9) +#define RT5682_POL_FAST_OFF_MASK (0x1 << 8) +#define RT5682_POL_FAST_OFF_HIGH (0x1 << 8) +#define RT5682_POL_FAST_OFF_LOW (0x0 << 8) +#define RT5682_FAST_OFF_MASK (0x1 << 7) +#define RT5682_FAST_OFF_EN (0x1 << 7) +#define RT5682_FAST_OFF_DIS (0x0 << 7) +#define RT5682_VREF_POW_MASK (0x1 << 6) +#define RT5682_VREF_POW_FSM (0x0 << 6) +#define RT5682_VREF_POW_REG (0x1 << 6) +#define RT5682_MB1_PATH_MASK (0x1 << 5) +#define RT5682_CTRL_MB1_REG (0x1 << 5) +#define RT5682_CTRL_MB1_FSM (0x0 << 5) +#define RT5682_MB2_PATH_MASK (0x1 << 4) +#define RT5682_CTRL_MB2_REG (0x1 << 4) +#define RT5682_CTRL_MB2_FSM (0x0 << 4) +#define RT5682_TRIG_JD_MASK (0x1 << 3) +#define RT5682_TRIG_JD_HIGH (0x1 << 3) +#define RT5682_TRIG_JD_LOW (0x0 << 3) +#define RT5682_MIC_CAP_MASK (0x1 << 1) +#define RT5682_MIC_CAP_HS (0x1 << 1) +#define RT5682_MIC_CAP_HP (0x0 << 1) +#define RT5682_MIC_CAP_SRC_MASK (0x1) +#define RT5682_MIC_CAP_SRC_REG (0x1) +#define RT5682_MIC_CAP_SRC_ANA (0x0) + +/* Embeeded Jack and Type Detection Control 2 (0x0011) */ +#define RT5682_EXT_JD_SRC (0x7 << 4) +#define RT5682_EXT_JD_SRC_SFT 4 +#define RT5682_EXT_JD_SRC_GPIO_JD1 (0x0 << 4) +#define RT5682_EXT_JD_SRC_GPIO_JD2 (0x1 << 4) +#define RT5682_EXT_JD_SRC_JDH (0x2 << 4) +#define RT5682_EXT_JD_SRC_JDL (0x3 << 4) +#define RT5682_EXT_JD_SRC_MANUAL (0x4 << 4) +#define RT5682_JACK_TYPE_MASK (0x3) + +/* Combo Jack and Type Detection Control 3 (0x0012) */ +#define RT5682_CBJ_IN_BUF_EN (0x1 << 7) + +/* Combo Jack and Type Detection Control 4 (0x0013) */ +#define RT5682_SEL_SHT_MID_TON_MASK (0x3 << 12) +#define RT5682_SEL_SHT_MID_TON_2 (0x0 << 12) +#define RT5682_SEL_SHT_MID_TON_3 (0x1 << 12) +#define RT5682_CBJ_JD_TEST_MASK (0x1 << 6) +#define RT5682_CBJ_JD_TEST_NORM (0x0 << 6) +#define RT5682_CBJ_JD_TEST_MODE (0x1 << 6) + +/* DAC1 Digital Volume (0x0019) */ +#define RT5682_DAC_L1_VOL_MASK (0xff << 8) +#define RT5682_DAC_L1_VOL_SFT 8 +#define RT5682_DAC_R1_VOL_MASK (0xff) +#define RT5682_DAC_R1_VOL_SFT 0 + +/* ADC Digital Volume Control (0x001c) */ +#define RT5682_ADC_L_VOL_MASK (0x7f << 8) +#define RT5682_ADC_L_VOL_SFT 8 +#define RT5682_ADC_R_VOL_MASK (0x7f) +#define RT5682_ADC_R_VOL_SFT 0 + +/* Stereo1 ADC Boost Gain Control (0x001f) */ +#define RT5682_STO1_ADC_L_BST_MASK (0x3 << 14) +#define RT5682_STO1_ADC_L_BST_SFT 14 +#define RT5682_STO1_ADC_R_BST_MASK (0x3 << 12) +#define RT5682_STO1_ADC_R_BST_SFT 12 + +/* Sidetone Control (0x0024) */ +#define RT5682_ST_SRC_SEL (0x1 << 8) +#define RT5682_ST_SRC_SFT 8 +#define RT5682_ST_EN_MASK (0x1 << 6) +#define RT5682_ST_DIS (0x0 << 6) +#define RT5682_ST_EN (0x1 << 6) +#define RT5682_ST_EN_SFT 6 + +/* Stereo1 ADC Mixer Control (0x0026) */ +#define RT5682_M_STO1_ADC_L1 (0x1 << 15) +#define RT5682_M_STO1_ADC_L1_SFT 15 +#define RT5682_M_STO1_ADC_L2 (0x1 << 14) +#define RT5682_M_STO1_ADC_L2_SFT 14 +#define RT5682_STO1_ADC1L_SRC_MASK (0x1 << 13) +#define RT5682_STO1_ADC1L_SRC_SFT 13 +#define RT5682_STO1_ADC1_SRC_ADC (0x1 << 13) +#define RT5682_STO1_ADC1_SRC_DACMIX (0x0 << 13) +#define RT5682_STO1_ADC2L_SRC_MASK (0x1 << 12) +#define RT5682_STO1_ADC2L_SRC_SFT 12 +#define RT5682_STO1_ADCL_SRC_MASK (0x3 << 10) +#define RT5682_STO1_ADCL_SRC_SFT 10 +#define RT5682_STO1_DD_L_SRC_MASK (0x1 << 9) +#define RT5682_STO1_DD_L_SRC_SFT 9 +#define RT5682_STO1_DMIC_SRC_MASK (0x1 << 8) +#define RT5682_STO1_DMIC_SRC_SFT 8 +#define RT5682_STO1_DMIC_SRC_DMIC2 (0x1 << 8) +#define RT5682_STO1_DMIC_SRC_DMIC1 (0x0 << 8) +#define RT5682_M_STO1_ADC_R1 (0x1 << 7) +#define RT5682_M_STO1_ADC_R1_SFT 7 +#define RT5682_M_STO1_ADC_R2 (0x1 << 6) +#define RT5682_M_STO1_ADC_R2_SFT 6 +#define RT5682_STO1_ADC1R_SRC_MASK (0x1 << 5) +#define RT5682_STO1_ADC1R_SRC_SFT 5 +#define RT5682_STO1_ADC2R_SRC_MASK (0x1 << 4) +#define RT5682_STO1_ADC2R_SRC_SFT 4 +#define RT5682_STO1_ADCR_SRC_MASK (0x3 << 2) +#define RT5682_STO1_ADCR_SRC_SFT 2 + +/* ADC Mixer to DAC Mixer Control (0x0029) */ +#define RT5682_M_ADCMIX_L (0x1 << 15) +#define RT5682_M_ADCMIX_L_SFT 15 +#define RT5682_M_DAC1_L (0x1 << 14) +#define RT5682_M_DAC1_L_SFT 14 +#define RT5682_DAC1_R_SEL_MASK (0x1 << 10) +#define RT5682_DAC1_R_SEL_SFT 10 +#define RT5682_DAC1_L_SEL_MASK (0x1 << 8) +#define RT5682_DAC1_L_SEL_SFT 8 +#define RT5682_M_ADCMIX_R (0x1 << 7) +#define RT5682_M_ADCMIX_R_SFT 7 +#define RT5682_M_DAC1_R (0x1 << 6) +#define RT5682_M_DAC1_R_SFT 6 + +/* Stereo1 DAC Mixer Control (0x002a) */ +#define RT5682_M_DAC_L1_STO_L (0x1 << 15) +#define RT5682_M_DAC_L1_STO_L_SFT 15 +#define RT5682_G_DAC_L1_STO_L_MASK (0x1 << 14) +#define RT5682_G_DAC_L1_STO_L_SFT 14 +#define RT5682_M_DAC_R1_STO_L (0x1 << 13) +#define RT5682_M_DAC_R1_STO_L_SFT 13 +#define RT5682_G_DAC_R1_STO_L_MASK (0x1 << 12) +#define RT5682_G_DAC_R1_STO_L_SFT 12 +#define RT5682_M_DAC_L1_STO_R (0x1 << 7) +#define RT5682_M_DAC_L1_STO_R_SFT 7 +#define RT5682_G_DAC_L1_STO_R_MASK (0x1 << 6) +#define RT5682_G_DAC_L1_STO_R_SFT 6 +#define RT5682_M_DAC_R1_STO_R (0x1 << 5) +#define RT5682_M_DAC_R1_STO_R_SFT 5 +#define RT5682_G_DAC_R1_STO_R_MASK (0x1 << 4) +#define RT5682_G_DAC_R1_STO_R_SFT 4 + +/* Analog DAC1 Input Source Control (0x002b) */ +#define RT5682_M_ST_STO_L (0x1 << 9) +#define RT5682_M_ST_STO_L_SFT 9 +#define RT5682_M_ST_STO_R (0x1 << 8) +#define RT5682_M_ST_STO_R_SFT 8 +#define RT5682_DAC_L1_SRC_MASK (0x3 << 4) +#define RT5682_A_DACL1_SFT 4 +#define RT5682_DAC_R1_SRC_MASK (0x3) +#define RT5682_A_DACR1_SFT 0 + +/* Digital Interface Data Control (0x0030) */ +#define RT5682_IF2_ADC_SEL_MASK (0x3 << 0) +#define RT5682_IF2_ADC_SEL_SFT 0 + +/* REC Left Mixer Control 2 (0x003c) */ +#define RT5682_G_CBJ_RM1_L (0x7 << 10) +#define RT5682_G_CBJ_RM1_L_SFT 10 +#define RT5682_M_CBJ_RM1_L (0x1 << 7) +#define RT5682_M_CBJ_RM1_L_SFT 7 + +/* Power Management for Digital 1 (0x0061) */ +#define RT5682_PWR_I2S1 (0x1 << 15) +#define RT5682_PWR_I2S1_BIT 15 +#define RT5682_PWR_I2S2 (0x1 << 14) +#define RT5682_PWR_I2S2_BIT 14 +#define RT5682_PWR_DAC_L1 (0x1 << 11) +#define RT5682_PWR_DAC_L1_BIT 11 +#define RT5682_PWR_DAC_R1 (0x1 << 10) +#define RT5682_PWR_DAC_R1_BIT 10 +#define RT5682_PWR_LDO (0x1 << 8) +#define RT5682_PWR_LDO_BIT 8 +#define RT5682_PWR_ADC_L1 (0x1 << 4) +#define RT5682_PWR_ADC_L1_BIT 4 +#define RT5682_PWR_ADC_R1 (0x1 << 3) +#define RT5682_PWR_ADC_R1_BIT 3 +#define RT5682_DIG_GATE_CTRL (0x1 << 0) +#define RT5682_DIG_GATE_CTRL_SFT 0 + + +/* Power Management for Digital 2 (0x0062) */ +#define RT5682_PWR_ADC_S1F (0x1 << 15) +#define RT5682_PWR_ADC_S1F_BIT 15 +#define RT5682_PWR_DAC_S1F (0x1 << 10) +#define RT5682_PWR_DAC_S1F_BIT 10 + +/* Power Management for Analog 1 (0x0063) */ +#define RT5682_PWR_VREF1 (0x1 << 15) +#define RT5682_PWR_VREF1_BIT 15 +#define RT5682_PWR_FV1 (0x1 << 14) +#define RT5682_PWR_FV1_BIT 14 +#define RT5682_PWR_VREF2 (0x1 << 13) +#define RT5682_PWR_VREF2_BIT 13 +#define RT5682_PWR_FV2 (0x1 << 12) +#define RT5682_PWR_FV2_BIT 12 +#define RT5682_LDO1_DBG_MASK (0x3 << 10) +#define RT5682_PWR_MB (0x1 << 9) +#define RT5682_PWR_MB_BIT 9 +#define RT5682_PWR_BG (0x1 << 7) +#define RT5682_PWR_BG_BIT 7 +#define RT5682_LDO1_BYPASS_MASK (0x1 << 6) +#define RT5682_LDO1_BYPASS (0x1 << 6) +#define RT5682_LDO1_NOT_BYPASS (0x0 << 6) +#define RT5682_PWR_MA_BIT 6 +#define RT5682_LDO1_DVO_MASK (0x3 << 4) +#define RT5682_LDO1_DVO_09 (0x0 << 4) +#define RT5682_LDO1_DVO_10 (0x1 << 4) +#define RT5682_LDO1_DVO_12 (0x2 << 4) +#define RT5682_LDO1_DVO_14 (0x3 << 4) +#define RT5682_HP_DRIVER_MASK (0x3 << 2) +#define RT5682_HP_DRIVER_1X (0x0 << 2) +#define RT5682_HP_DRIVER_3X (0x1 << 2) +#define RT5682_HP_DRIVER_5X (0x3 << 2) +#define RT5682_PWR_HA_L (0x1 << 1) +#define RT5682_PWR_HA_L_BIT 1 +#define RT5682_PWR_HA_R (0x1 << 0) +#define RT5682_PWR_HA_R_BIT 0 + +/* Power Management for Analog 2 (0x0064) */ +#define RT5682_PWR_MB1 (0x1 << 11) +#define RT5682_PWR_MB1_PWR_DOWN (0x0 << 11) +#define RT5682_PWR_MB1_BIT 11 +#define RT5682_PWR_MB2 (0x1 << 10) +#define RT5682_PWR_MB2_PWR_DOWN (0x0 << 10) +#define RT5682_PWR_MB2_BIT 10 +#define RT5682_PWR_JDH (0x1 << 3) +#define RT5682_PWR_JDH_BIT 3 +#define RT5682_PWR_JDL (0x1 << 2) +#define RT5682_PWR_JDL_BIT 2 +#define RT5682_PWR_RM1_L (0x1 << 1) +#define RT5682_PWR_RM1_L_BIT 1 + +/* Power Management for Analog 3 (0x0065) */ +#define RT5682_PWR_CBJ (0x1 << 9) +#define RT5682_PWR_CBJ_BIT 9 +#define RT5682_PWR_PLL (0x1 << 6) +#define RT5682_PWR_PLL_BIT 6 +#define RT5682_PWR_PLL2B (0x1 << 5) +#define RT5682_PWR_PLL2B_BIT 5 +#define RT5682_PWR_PLL2F (0x1 << 4) +#define RT5682_PWR_PLL2F_BIT 4 +#define RT5682_PWR_LDO2 (0x1 << 2) +#define RT5682_PWR_LDO2_BIT 2 +#define RT5682_PWR_DET_SPKVDD (0x1 << 1) +#define RT5682_PWR_DET_SPKVDD_BIT 1 + +/* Power Management for Mixer (0x0066) */ +#define RT5682_PWR_STO1_DAC_L (0x1 << 5) +#define RT5682_PWR_STO1_DAC_L_BIT 5 +#define RT5682_PWR_STO1_DAC_R (0x1 << 4) +#define RT5682_PWR_STO1_DAC_R_BIT 4 + +/* MCLK and System Clock Detection Control (0x006b) */ +#define RT5682_SYS_CLK_DET (0x1 << 15) +#define RT5682_SYS_CLK_DET_SFT 15 +#define RT5682_PLL1_CLK_DET (0x1 << 14) +#define RT5682_PLL1_CLK_DET_SFT 14 +#define RT5682_PLL2_CLK_DET (0x1 << 13) +#define RT5682_PLL2_CLK_DET_SFT 13 +#define RT5682_POW_CLK_DET2_SFT 8 +#define RT5682_POW_CLK_DET_SFT 0 + +/* Digital Microphone Control 1 (0x006e) */ +#define RT5682_DMIC_1_EN_MASK (0x1 << 15) +#define RT5682_DMIC_1_EN_SFT 15 +#define RT5682_DMIC_1_DIS (0x0 << 15) +#define RT5682_DMIC_1_EN (0x1 << 15) +#define RT5682_DMIC_1_DP_MASK (0x3 << 4) +#define RT5682_DMIC_1_DP_SFT 4 +#define RT5682_DMIC_1_DP_GPIO2 (0x0 << 4) +#define RT5682_DMIC_1_DP_GPIO5 (0x1 << 4) +#define RT5682_DMIC_CLK_MASK (0xf << 0) +#define RT5682_DMIC_CLK_SFT 0 + +/* I2S1 Audio Serial Data Port Control (0x0070) */ +#define RT5682_SEL_ADCDAT_MASK (0x1 << 15) +#define RT5682_SEL_ADCDAT_OUT (0x0 << 15) +#define RT5682_SEL_ADCDAT_IN (0x1 << 15) +#define RT5682_SEL_ADCDAT_SFT 15 +#define RT5682_I2S1_TX_CHL_MASK (0x7 << 12) +#define RT5682_I2S1_TX_CHL_SFT 12 +#define RT5682_I2S1_TX_CHL_16 (0x0 << 12) +#define RT5682_I2S1_TX_CHL_20 (0x1 << 12) +#define RT5682_I2S1_TX_CHL_24 (0x2 << 12) +#define RT5682_I2S1_TX_CHL_32 (0x3 << 12) +#define RT5682_I2S1_TX_CHL_8 (0x4 << 12) +#define RT5682_I2S1_RX_CHL_MASK (0x7 << 8) +#define RT5682_I2S1_RX_CHL_SFT 8 +#define RT5682_I2S1_RX_CHL_16 (0x0 << 8) +#define RT5682_I2S1_RX_CHL_20 (0x1 << 8) +#define RT5682_I2S1_RX_CHL_24 (0x2 << 8) +#define RT5682_I2S1_RX_CHL_32 (0x3 << 8) +#define RT5682_I2S1_RX_CHL_8 (0x4 << 8) +#define RT5682_I2S1_MONO_MASK (0x1 << 7) +#define RT5682_I2S1_MONO_EN (0x1 << 7) +#define RT5682_I2S1_MONO_DIS (0x0 << 7) +#define RT5682_I2S2_MONO_MASK (0x1 << 6) +#define RT5682_I2S2_MONO_EN (0x1 << 6) +#define RT5682_I2S2_MONO_DIS (0x0 << 6) +#define RT5682_I2S1_DL_MASK (0x7 << 4) +#define RT5682_I2S1_DL_SFT 4 +#define RT5682_I2S1_DL_16 (0x0 << 4) +#define RT5682_I2S1_DL_20 (0x1 << 4) +#define RT5682_I2S1_DL_24 (0x2 << 4) +#define RT5682_I2S1_DL_32 (0x3 << 4) +#define RT5682_I2S1_DL_8 (0x4 << 4) + +/* I2S1/2 Audio Serial Data Port Control (0x0070)(0x0071) */ +#define RT5682_I2S2_MS_MASK (0x1 << 15) +#define RT5682_I2S2_MS_SFT 15 +#define RT5682_I2S2_MS_M (0x0 << 15) +#define RT5682_I2S2_MS_S (0x1 << 15) +#define RT5682_I2S2_PIN_CFG_MASK (0x1 << 14) +#define RT5682_I2S2_PIN_CFG_SFT 14 +#define RT5682_I2S2_CLK_SEL_MASK (0x1 << 11) +#define RT5682_I2S2_CLK_SEL_SFT 11 +#define RT5682_I2S2_OUT_MASK (0x1 << 9) +#define RT5682_I2S2_OUT_SFT 9 +#define RT5682_I2S2_OUT_UM (0x0 << 9) +#define RT5682_I2S2_OUT_M (0x1 << 9) +#define RT5682_I2S_BP_MASK (0x1 << 8) +#define RT5682_I2S_BP_SFT 8 +#define RT5682_I2S_BP_NOR (0x0 << 8) +#define RT5682_I2S_BP_INV (0x1 << 8) +#define RT5682_I2S2_MONO_EN (0x1 << 6) +#define RT5682_I2S2_MONO_DIS (0x0 << 6) +#define RT5682_I2S2_DL_MASK (0x3 << 4) +#define RT5682_I2S2_DL_SFT 4 +#define RT5682_I2S2_DL_16 (0x0 << 4) +#define RT5682_I2S2_DL_20 (0x1 << 4) +#define RT5682_I2S2_DL_24 (0x2 << 4) +#define RT5682_I2S2_DL_8 (0x3 << 4) +#define RT5682_I2S_DF_MASK (0x7) +#define RT5682_I2S_DF_SFT 0 +#define RT5682_I2S_DF_I2S (0x0) +#define RT5682_I2S_DF_LEFT (0x1) +#define RT5682_I2S_DF_PCM_A (0x2) +#define RT5682_I2S_DF_PCM_B (0x3) +#define RT5682_I2S_DF_PCM_A_N (0x6) +#define RT5682_I2S_DF_PCM_B_N (0x7) + +/* ADC/DAC Clock Control 1 (0x0073) */ +#define RT5682_ADC_OSR_MASK (0xf << 12) +#define RT5682_ADC_OSR_SFT 12 +#define RT5682_ADC_OSR_D_1 (0x0 << 12) +#define RT5682_ADC_OSR_D_2 (0x1 << 12) +#define RT5682_ADC_OSR_D_4 (0x2 << 12) +#define RT5682_ADC_OSR_D_6 (0x3 << 12) +#define RT5682_ADC_OSR_D_8 (0x4 << 12) +#define RT5682_ADC_OSR_D_12 (0x5 << 12) +#define RT5682_ADC_OSR_D_16 (0x6 << 12) +#define RT5682_ADC_OSR_D_24 (0x7 << 12) +#define RT5682_ADC_OSR_D_32 (0x8 << 12) +#define RT5682_ADC_OSR_D_48 (0x9 << 12) +#define RT5682_I2S_M_DIV_MASK (0xf << 12) +#define RT5682_I2S_M_DIV_SFT 8 +#define RT5682_I2S_M_D_1 (0x0 << 8) +#define RT5682_I2S_M_D_2 (0x1 << 8) +#define RT5682_I2S_M_D_3 (0x2 << 8) +#define RT5682_I2S_M_D_4 (0x3 << 8) +#define RT5682_I2S_M_D_6 (0x4 << 8) +#define RT5682_I2S_M_D_8 (0x5 << 8) +#define RT5682_I2S_M_D_12 (0x6 << 8) +#define RT5682_I2S_M_D_16 (0x7 << 8) +#define RT5682_I2S_M_D_24 (0x8 << 8) +#define RT5682_I2S_M_D_32 (0x9 << 8) +#define RT5682_I2S_M_D_48 (0x10 << 8) +#define RT5682_I2S_CLK_SRC_MASK (0x7 << 4) +#define RT5682_I2S_CLK_SRC_SFT 4 +#define RT5682_I2S_CLK_SRC_MCLK (0x0 << 4) +#define RT5682_I2S_CLK_SRC_PLL1 (0x1 << 4) +#define RT5682_I2S_CLK_SRC_PLL2 (0x2 << 4) +#define RT5682_I2S_CLK_SRC_SDW (0x3 << 4) +#define RT5682_I2S_CLK_SRC_RCCLK (0x4 << 4) /* 25M */ +#define RT5682_DAC_OSR_MASK (0xf << 0) +#define RT5682_DAC_OSR_SFT 0 +#define RT5682_DAC_OSR_D_1 (0x0 << 0) +#define RT5682_DAC_OSR_D_2 (0x1 << 0) +#define RT5682_DAC_OSR_D_4 (0x2 << 0) +#define RT5682_DAC_OSR_D_6 (0x3 << 0) +#define RT5682_DAC_OSR_D_8 (0x4 << 0) +#define RT5682_DAC_OSR_D_12 (0x5 << 0) +#define RT5682_DAC_OSR_D_16 (0x6 << 0) +#define RT5682_DAC_OSR_D_24 (0x7 << 0) +#define RT5682_DAC_OSR_D_32 (0x8 << 0) +#define RT5682_DAC_OSR_D_48 (0x9 << 0) + +/* ADC/DAC Clock Control 2 (0x0074) */ +#define RT5682_I2S2_BCLK_MS2_MASK (0x1 << 11) +#define RT5682_I2S2_BCLK_MS2_SFT 11 +#define RT5682_I2S2_BCLK_MS2_32 (0x0 << 11) +#define RT5682_I2S2_BCLK_MS2_64 (0x1 << 11) + + +/* TDM control 1 (0x0079) */ +#define RT5682_TDM_TX_CH_MASK (0x3 << 12) +#define RT5682_TDM_TX_CH_2 (0x0 << 12) +#define RT5682_TDM_TX_CH_4 (0x1 << 12) +#define RT5682_TDM_TX_CH_6 (0x2 << 12) +#define RT5682_TDM_TX_CH_8 (0x3 << 12) +#define RT5682_TDM_RX_CH_MASK (0x3 << 8) +#define RT5682_TDM_RX_CH_2 (0x0 << 8) +#define RT5682_TDM_RX_CH_4 (0x1 << 8) +#define RT5682_TDM_RX_CH_6 (0x2 << 8) +#define RT5682_TDM_RX_CH_8 (0x3 << 8) +#define RT5682_TDM_ADC_LCA_MASK (0xf << 4) +#define RT5682_TDM_ADC_LCA_SFT 4 +#define RT5682_TDM_ADC_DL_SFT 0 + +/* TDM control 2 (0x007a) */ +#define RT5682_IF1_ADC1_SEL_SFT 14 +#define RT5682_IF1_ADC2_SEL_SFT 12 +#define RT5682_IF1_ADC3_SEL_SFT 10 +#define RT5682_IF1_ADC4_SEL_SFT 8 +#define RT5682_TDM_ADC_SEL_SFT 4 + +/* TDM control 3 (0x007b) */ +#define RT5682_TDM_EN (0x1 << 7) + +/* TDM/I2S control (0x007e) */ +#define RT5682_TDM_S_BP_MASK (0x1 << 15) +#define RT5682_TDM_S_BP_SFT 15 +#define RT5682_TDM_S_BP_NOR (0x0 << 15) +#define RT5682_TDM_S_BP_INV (0x1 << 15) +#define RT5682_TDM_S_LP_MASK (0x1 << 14) +#define RT5682_TDM_S_LP_SFT 14 +#define RT5682_TDM_S_LP_NOR (0x0 << 14) +#define RT5682_TDM_S_LP_INV (0x1 << 14) +#define RT5682_TDM_DF_MASK (0x7 << 11) +#define RT5682_TDM_DF_SFT 11 +#define RT5682_TDM_DF_I2S (0x0 << 11) +#define RT5682_TDM_DF_LEFT (0x1 << 11) +#define RT5682_TDM_DF_PCM_A (0x2 << 11) +#define RT5682_TDM_DF_PCM_B (0x3 << 11) +#define RT5682_TDM_DF_PCM_A_N (0x6 << 11) +#define RT5682_TDM_DF_PCM_B_N (0x7 << 11) +#define RT5682_TDM_CL_MASK (0x3 << 4) +#define RT5682_TDM_CL_16 (0x0 << 4) +#define RT5682_TDM_CL_20 (0x1 << 4) +#define RT5682_TDM_CL_24 (0x2 << 4) +#define RT5682_TDM_CL_32 (0x3 << 4) +#define RT5682_TDM_M_BP_MASK (0x1 << 2) +#define RT5682_TDM_M_BP_SFT 2 +#define RT5682_TDM_M_BP_NOR (0x0 << 2) +#define RT5682_TDM_M_BP_INV (0x1 << 2) +#define RT5682_TDM_M_LP_MASK (0x1 << 1) +#define RT5682_TDM_M_LP_SFT 1 +#define RT5682_TDM_M_LP_NOR (0x0 << 1) +#define RT5682_TDM_M_LP_INV (0x1 << 1) +#define RT5682_TDM_MS_MASK (0x1 << 0) +#define RT5682_TDM_MS_SFT 0 +#define RT5682_TDM_MS_M (0x0 << 0) +#define RT5682_TDM_MS_S (0x1 << 0) + +/* Global Clock Control (0x0080) */ +#define RT5682_SCLK_SRC_MASK (0x7 << 13) +#define RT5682_SCLK_SRC_SFT 13 +#define RT5682_SCLK_SRC_MCLK (0x0 << 13) +#define RT5682_SCLK_SRC_PLL1 (0x1 << 13) +#define RT5682_SCLK_SRC_PLL2 (0x2 << 13) +#define RT5682_SCLK_SRC_SDW (0x3 << 13) +#define RT5682_SCLK_SRC_RCCLK (0x4 << 13) +#define RT5682_PLL1_SRC_MASK (0x3 << 10) +#define RT5682_PLL1_SRC_SFT 10 +#define RT5682_PLL1_SRC_MCLK (0x0 << 10) +#define RT5682_PLL1_SRC_BCLK1 (0x1 << 10) +#define RT5682_PLL1_SRC_SDW (0x2 << 10) +#define RT5682_PLL1_SRC_RC (0x3 << 10) +#define RT5682_PLL2_SRC_MASK (0x3 << 8) +#define RT5682_PLL2_SRC_SFT 8 +#define RT5682_PLL2_SRC_MCLK (0x0 << 8) +#define RT5682_PLL2_SRC_BCLK1 (0x1 << 8) +#define RT5682_PLL2_SRC_SDW (0x2 << 8) +#define RT5682_PLL2_SRC_RC (0x3 << 8) + + + +#define RT5682_PLL_INP_MAX 40000000 +#define RT5682_PLL_INP_MIN 256000 +/* PLL M/N/K Code Control 1 (0x0081) */ +#define RT5682_PLL_N_MAX 0x001ff +#define RT5682_PLL_N_MASK (RT5682_PLL_N_MAX << 7) +#define RT5682_PLL_N_SFT 7 +#define RT5682_PLL_K_MAX 0x001f +#define RT5682_PLL_K_MASK (RT5682_PLL_K_MAX) +#define RT5682_PLL_K_SFT 0 + +/* PLL M/N/K Code Control 2 (0x0082) */ +#define RT5682_PLL_M_MAX 0x00f +#define RT5682_PLL_M_MASK (RT5682_PLL_M_MAX << 12) +#define RT5682_PLL_M_SFT 12 +#define RT5682_PLL_M_BP (0x1 << 11) +#define RT5682_PLL_M_BP_SFT 11 +#define RT5682_PLL_K_BP (0x1 << 10) +#define RT5682_PLL_K_BP_SFT 10 +#define RT5682_PLL_RST (0x1 << 1) + +/* PLL tracking mode 1 (0x0083) */ +#define RT5682_DA_ASRC_MASK (0x1 << 13) +#define RT5682_DA_ASRC_SFT 13 +#define RT5682_DAC_STO1_ASRC_MASK (0x1 << 12) +#define RT5682_DAC_STO1_ASRC_SFT 12 +#define RT5682_AD_ASRC_MASK (0x1 << 8) +#define RT5682_AD_ASRC_SFT 8 +#define RT5682_AD_ASRC_SEL_MASK (0x1 << 4) +#define RT5682_AD_ASRC_SEL_SFT 4 +#define RT5682_DMIC_ASRC_MASK (0x1 << 3) +#define RT5682_DMIC_ASRC_SFT 3 +#define RT5682_ADC_STO1_ASRC_MASK (0x1 << 2) +#define RT5682_ADC_STO1_ASRC_SFT 2 +#define RT5682_DA_ASRC_SEL_MASK (0x1 << 0) +#define RT5682_DA_ASRC_SEL_SFT 0 + +/* PLL tracking mode 2 3 (0x0084)(0x0085)*/ +#define RT5682_FILTER_CLK_SEL_MASK (0x7 << 12) +#define RT5682_FILTER_CLK_SEL_SFT 12 +#define RT5682_FILTER_CLK_DIV_MASK (0xf << 8) +#define RT5682_FILTER_CLK_DIV_SFT 8 + +/* ASRC Control 4 (0x0086) */ +#define RT5682_ASRCIN_FTK_N1_MASK (0x3 << 14) +#define RT5682_ASRCIN_FTK_N1_SFT 14 +#define RT5682_ASRCIN_FTK_N2_MASK (0x3 << 12) +#define RT5682_ASRCIN_FTK_N2_SFT 12 +#define RT5682_ASRCIN_FTK_M1_MASK (0x7 << 8) +#define RT5682_ASRCIN_FTK_M1_SFT 8 +#define RT5682_ASRCIN_FTK_M2_MASK (0x7 << 4) +#define RT5682_ASRCIN_FTK_M2_SFT 4 + +/* SoundWire reference clk (0x008d) */ +#define RT5682_PLL2_OUT_MASK (0x1 << 8) +#define RT5682_PLL2_OUT_98M (0x0 << 8) +#define RT5682_PLL2_OUT_49M (0x1 << 8) +#define RT5682_SDW_REF_2_MASK (0xf << 4) +#define RT5682_SDW_REF_2_SFT 4 +#define RT5682_SDW_REF_2_48K (0x0 << 4) +#define RT5682_SDW_REF_2_96K (0x1 << 4) +#define RT5682_SDW_REF_2_192K (0x2 << 4) +#define RT5682_SDW_REF_2_32K (0x3 << 4) +#define RT5682_SDW_REF_2_24K (0x4 << 4) +#define RT5682_SDW_REF_2_16K (0x5 << 4) +#define RT5682_SDW_REF_2_12K (0x6 << 4) +#define RT5682_SDW_REF_2_8K (0x7 << 4) +#define RT5682_SDW_REF_2_44K (0x8 << 4) +#define RT5682_SDW_REF_2_88K (0x9 << 4) +#define RT5682_SDW_REF_2_176K (0xa << 4) +#define RT5682_SDW_REF_2_353K (0xb << 4) +#define RT5682_SDW_REF_2_22K (0xc << 4) +#define RT5682_SDW_REF_2_384K (0xd << 4) +#define RT5682_SDW_REF_2_11K (0xe << 4) +#define RT5682_SDW_REF_1_MASK (0xf << 0) +#define RT5682_SDW_REF_1_SFT 0 +#define RT5682_SDW_REF_1_48K (0x0 << 0) +#define RT5682_SDW_REF_1_96K (0x1 << 0) +#define RT5682_SDW_REF_1_192K (0x2 << 0) +#define RT5682_SDW_REF_1_32K (0x3 << 0) +#define RT5682_SDW_REF_1_24K (0x4 << 0) +#define RT5682_SDW_REF_1_16K (0x5 << 0) +#define RT5682_SDW_REF_1_12K (0x6 << 0) +#define RT5682_SDW_REF_1_8K (0x7 << 0) +#define RT5682_SDW_REF_1_44K (0x8 << 0) +#define RT5682_SDW_REF_1_88K (0x9 << 0) +#define RT5682_SDW_REF_1_176K (0xa << 0) +#define RT5682_SDW_REF_1_353K (0xb << 0) +#define RT5682_SDW_REF_1_22K (0xc << 0) +#define RT5682_SDW_REF_1_384K (0xd << 0) +#define RT5682_SDW_REF_1_11K (0xe << 0) + +/* Depop Mode Control 1 (0x008e) */ +#define RT5682_PUMP_EN (0x1 << 3) +#define RT5682_PUMP_EN_SFT 3 +#define RT5682_CAPLESS_EN (0x1 << 0) +#define RT5682_CAPLESS_EN_SFT 0 + +/* Depop Mode Control 2 (0x8f) */ +#define RT5682_RAMP_MASK (0x1 << 12) +#define RT5682_RAMP_SFT 12 +#define RT5682_RAMP_DIS (0x0 << 12) +#define RT5682_RAMP_EN (0x1 << 12) +#define RT5682_BPS_MASK (0x1 << 11) +#define RT5682_BPS_SFT 11 +#define RT5682_BPS_DIS (0x0 << 11) +#define RT5682_BPS_EN (0x1 << 11) +#define RT5682_FAST_UPDN_MASK (0x1 << 10) +#define RT5682_FAST_UPDN_SFT 10 +#define RT5682_FAST_UPDN_DIS (0x0 << 10) +#define RT5682_FAST_UPDN_EN (0x1 << 10) +#define RT5682_VLO_MASK (0x1 << 7) +#define RT5682_VLO_SFT 7 +#define RT5682_VLO_3V (0x0 << 7) +#define RT5682_VLO_33V (0x1 << 7) + +/* HPOUT charge pump 1 (0x0091) */ +#define RT5682_OSW_L_MASK (0x1 << 11) +#define RT5682_OSW_L_SFT 11 +#define RT5682_OSW_L_DIS (0x0 << 11) +#define RT5682_OSW_L_EN (0x1 << 11) +#define RT5682_OSW_R_MASK (0x1 << 10) +#define RT5682_OSW_R_SFT 10 +#define RT5682_OSW_R_DIS (0x0 << 10) +#define RT5682_OSW_R_EN (0x1 << 10) +#define RT5682_PM_HP_MASK (0x3 << 8) +#define RT5682_PM_HP_SFT 8 +#define RT5682_PM_HP_LV (0x0 << 8) +#define RT5682_PM_HP_MV (0x1 << 8) +#define RT5682_PM_HP_HV (0x2 << 8) +#define RT5682_IB_HP_MASK (0x3 << 6) +#define RT5682_IB_HP_SFT 6 +#define RT5682_IB_HP_125IL (0x0 << 6) +#define RT5682_IB_HP_25IL (0x1 << 6) +#define RT5682_IB_HP_5IL (0x2 << 6) +#define RT5682_IB_HP_1IL (0x3 << 6) + +/* Micbias Control1 (0x93) */ +#define RT5682_MIC1_OV_MASK (0x3 << 14) +#define RT5682_MIC1_OV_SFT 14 +#define RT5682_MIC1_OV_2V7 (0x0 << 14) +#define RT5682_MIC1_OV_2V4 (0x1 << 14) +#define RT5682_MIC1_OV_2V25 (0x3 << 14) +#define RT5682_MIC1_OV_1V8 (0x4 << 14) +#define RT5682_MIC1_CLK_MASK (0x1 << 13) +#define RT5682_MIC1_CLK_SFT 13 +#define RT5682_MIC1_CLK_DIS (0x0 << 13) +#define RT5682_MIC1_CLK_EN (0x1 << 13) +#define RT5682_MIC1_OVCD_MASK (0x1 << 12) +#define RT5682_MIC1_OVCD_SFT 12 +#define RT5682_MIC1_OVCD_DIS (0x0 << 12) +#define RT5682_MIC1_OVCD_EN (0x1 << 12) +#define RT5682_MIC1_OVTH_MASK (0x3 << 10) +#define RT5682_MIC1_OVTH_SFT 10 +#define RT5682_MIC1_OVTH_768UA (0x0 << 10) +#define RT5682_MIC1_OVTH_960UA (0x1 << 10) +#define RT5682_MIC1_OVTH_1152UA (0x2 << 10) +#define RT5682_MIC1_OVTH_1960UA (0x3 << 10) +#define RT5682_MIC2_OV_MASK (0x3 << 8) +#define RT5682_MIC2_OV_SFT 8 +#define RT5682_MIC2_OV_2V7 (0x0 << 8) +#define RT5682_MIC2_OV_2V4 (0x1 << 8) +#define RT5682_MIC2_OV_2V25 (0x3 << 8) +#define RT5682_MIC2_OV_1V8 (0x4 << 8) +#define RT5682_MIC2_CLK_MASK (0x1 << 7) +#define RT5682_MIC2_CLK_SFT 7 +#define RT5682_MIC2_CLK_DIS (0x0 << 7) +#define RT5682_MIC2_CLK_EN (0x1 << 7) +#define RT5682_MIC2_OVTH_MASK (0x3 << 4) +#define RT5682_MIC2_OVTH_SFT 4 +#define RT5682_MIC2_OVTH_768UA (0x0 << 4) +#define RT5682_MIC2_OVTH_960UA (0x1 << 4) +#define RT5682_MIC2_OVTH_1152UA (0x2 << 4) +#define RT5682_MIC2_OVTH_1960UA (0x3 << 4) +#define RT5682_PWR_MB_MASK (0x1 << 3) +#define RT5682_PWR_MB_SFT 3 +#define RT5682_PWR_MB_PD (0x0 << 3) +#define RT5682_PWR_MB_PU (0x1 << 3) + +/* Micbias Control2 (0x0094) */ +#define RT5682_PWR_CLK25M_MASK (0x1 << 9) +#define RT5682_PWR_CLK25M_SFT 9 +#define RT5682_PWR_CLK25M_PD (0x0 << 9) +#define RT5682_PWR_CLK25M_PU (0x1 << 9) +#define RT5682_PWR_CLK1M_MASK (0x1 << 8) +#define RT5682_PWR_CLK1M_SFT 8 +#define RT5682_PWR_CLK1M_PD (0x0 << 8) +#define RT5682_PWR_CLK1M_PU (0x1 << 8) + +/* RC Clock Control (0x009f) */ +#define RT5682_POW_IRQ (0x1 << 15) +#define RT5682_POW_JDH (0x1 << 14) +#define RT5682_POW_JDL (0x1 << 13) +#define RT5682_POW_ANA (0x1 << 12) + +/* I2S Master Mode Clock Control 1 (0x00a0) */ +#define RT5682_CLK_SRC_MCLK (0x0) +#define RT5682_CLK_SRC_PLL1 (0x1) +#define RT5682_CLK_SRC_PLL2 (0x2) +#define RT5682_CLK_SRC_SDW (0x3) +#define RT5682_CLK_SRC_RCCLK (0x4) +#define RT5682_I2S_PD_1 (0x0) +#define RT5682_I2S_PD_2 (0x1) +#define RT5682_I2S_PD_3 (0x2) +#define RT5682_I2S_PD_4 (0x3) +#define RT5682_I2S_PD_6 (0x4) +#define RT5682_I2S_PD_8 (0x5) +#define RT5682_I2S_PD_12 (0x6) +#define RT5682_I2S_PD_16 (0x7) +#define RT5682_I2S_PD_24 (0x8) +#define RT5682_I2S_PD_32 (0x9) +#define RT5682_I2S_PD_48 (0xa) +#define RT5682_I2S2_SRC_MASK (0x3 << 4) +#define RT5682_I2S2_SRC_SFT 4 +#define RT5682_I2S2_M_PD_MASK (0xf << 0) +#define RT5682_I2S2_M_PD_SFT 0 + +/* IRQ Control 1 (0x00b6) */ +#define RT5682_JD1_PULSE_EN_MASK (0x1 << 10) +#define RT5682_JD1_PULSE_EN_SFT 10 +#define RT5682_JD1_PULSE_DIS (0x0 << 10) +#define RT5682_JD1_PULSE_EN (0x1 << 10) + +/* IRQ Control 2 (0x00b7) */ +#define RT5682_JD1_EN_MASK (0x1 << 15) +#define RT5682_JD1_EN_SFT 15 +#define RT5682_JD1_DIS (0x0 << 15) +#define RT5682_JD1_EN (0x1 << 15) +#define RT5682_JD1_POL_MASK (0x1 << 13) +#define RT5682_JD1_POL_NOR (0x0 << 13) +#define RT5682_JD1_POL_INV (0x1 << 13) + +/* IRQ Control 3 (0x00b8) */ +#define RT5682_IL_IRQ_MASK (0x1 << 7) +#define RT5682_IL_IRQ_DIS (0x0 << 7) +#define RT5682_IL_IRQ_EN (0x1 << 7) + +/* GPIO Control 1 (0x00c0) */ +#define RT5682_GP1_PIN_MASK (0x3 << 14) +#define RT5682_GP1_PIN_SFT 14 +#define RT5682_GP1_PIN_GPIO1 (0x0 << 14) +#define RT5682_GP1_PIN_IRQ (0x1 << 14) +#define RT5682_GP1_PIN_DMIC_CLK (0x2 << 14) +#define RT5682_GP2_PIN_MASK (0x3 << 12) +#define RT5682_GP2_PIN_SFT 12 +#define RT5682_GP2_PIN_GPIO2 (0x0 << 12) +#define RT5682_GP2_PIN_LRCK2 (0x1 << 12) +#define RT5682_GP2_PIN_DMIC_SDA (0x2 << 12) +#define RT5682_GP3_PIN_MASK (0x3 << 10) +#define RT5682_GP3_PIN_SFT 10 +#define RT5682_GP3_PIN_GPIO3 (0x0 << 10) +#define RT5682_GP3_PIN_BCLK2 (0x1 << 10) +#define RT5682_GP3_PIN_DMIC_CLK (0x2 << 10) +#define RT5682_GP4_PIN_MASK (0x3 << 8) +#define RT5682_GP4_PIN_SFT 8 +#define RT5682_GP4_PIN_GPIO4 (0x0 << 8) +#define RT5682_GP4_PIN_ADCDAT1 (0x1 << 8) +#define RT5682_GP4_PIN_DMIC_CLK (0x2 << 8) +#define RT5682_GP4_PIN_ADCDAT2 (0x3 << 8) +#define RT5682_GP5_PIN_MASK (0x3 << 6) +#define RT5682_GP5_PIN_SFT 6 +#define RT5682_GP5_PIN_GPIO5 (0x0 << 6) +#define RT5682_GP5_PIN_DACDAT1 (0x1 << 6) +#define RT5682_GP5_PIN_DMIC_SDA (0x2 << 6) +#define RT5682_GP6_PIN_MASK (0x1 << 5) +#define RT5682_GP6_PIN_SFT 5 +#define RT5682_GP6_PIN_GPIO6 (0x0 << 5) +#define RT5682_GP6_PIN_LRCK1 (0x1 << 5) + +/* GPIO Control 2 (0x00c1)*/ +#define RT5682_GP1_PF_MASK (0x1 << 15) +#define RT5682_GP1_PF_IN (0x0 << 15) +#define RT5682_GP1_PF_OUT (0x1 << 15) +#define RT5682_GP1_OUT_MASK (0x1 << 14) +#define RT5682_GP1_OUT_L (0x0 << 14) +#define RT5682_GP1_OUT_H (0x1 << 14) +#define RT5682_GP2_PF_MASK (0x1 << 13) +#define RT5682_GP2_PF_IN (0x0 << 13) +#define RT5682_GP2_PF_OUT (0x1 << 13) +#define RT5682_GP2_OUT_MASK (0x1 << 12) +#define RT5682_GP2_OUT_L (0x0 << 12) +#define RT5682_GP2_OUT_H (0x1 << 12) +#define RT5682_GP3_PF_MASK (0x1 << 11) +#define RT5682_GP3_PF_IN (0x0 << 11) +#define RT5682_GP3_PF_OUT (0x1 << 11) +#define RT5682_GP3_OUT_MASK (0x1 << 10) +#define RT5682_GP3_OUT_L (0x0 << 10) +#define RT5682_GP3_OUT_H (0x1 << 10) +#define RT5682_GP4_PF_MASK (0x1 << 9) +#define RT5682_GP4_PF_IN (0x0 << 9) +#define RT5682_GP4_PF_OUT (0x1 << 9) +#define RT5682_GP4_OUT_MASK (0x1 << 8) +#define RT5682_GP4_OUT_L (0x0 << 8) +#define RT5682_GP4_OUT_H (0x1 << 8) +#define RT5682_GP5_PF_MASK (0x1 << 7) +#define RT5682_GP5_PF_IN (0x0 << 7) +#define RT5682_GP5_PF_OUT (0x1 << 7) +#define RT5682_GP5_OUT_MASK (0x1 << 6) +#define RT5682_GP5_OUT_L (0x0 << 6) +#define RT5682_GP5_OUT_H (0x1 << 6) +#define RT5682_GP6_PF_MASK (0x1 << 5) +#define RT5682_GP6_PF_IN (0x0 << 5) +#define RT5682_GP6_PF_OUT (0x1 << 5) +#define RT5682_GP6_OUT_MASK (0x1 << 4) +#define RT5682_GP6_OUT_L (0x0 << 4) +#define RT5682_GP6_OUT_H (0x1 << 4) + + +/* GPIO Status (0x00c2) */ +#define RT5682_GP6_STA (0x1 << 6) +#define RT5682_GP5_STA (0x1 << 5) +#define RT5682_GP4_STA (0x1 << 4) +#define RT5682_GP3_STA (0x1 << 3) +#define RT5682_GP2_STA (0x1 << 2) +#define RT5682_GP1_STA (0x1 << 1) + +/* Soft volume and zero cross control 1 (0x00d9) */ +#define RT5682_SV_MASK (0x1 << 15) +#define RT5682_SV_SFT 15 +#define RT5682_SV_DIS (0x0 << 15) +#define RT5682_SV_EN (0x1 << 15) +#define RT5682_ZCD_MASK (0x1 << 10) +#define RT5682_ZCD_SFT 10 +#define RT5682_ZCD_PD (0x0 << 10) +#define RT5682_ZCD_PU (0x1 << 10) +#define RT5682_SV_DLY_MASK (0xf) +#define RT5682_SV_DLY_SFT 0 + +/* Soft volume and zero cross control 2 (0x00da) */ +#define RT5682_ZCD_BST1_CBJ_MASK (0x1 << 7) +#define RT5682_ZCD_BST1_CBJ_SFT 7 +#define RT5682_ZCD_BST1_CBJ_DIS (0x0 << 7) +#define RT5682_ZCD_BST1_CBJ_EN (0x1 << 7) +#define RT5682_ZCD_RECMIX_MASK (0x1) +#define RT5682_ZCD_RECMIX_SFT 0 +#define RT5682_ZCD_RECMIX_DIS (0x0) +#define RT5682_ZCD_RECMIX_EN (0x1) + +/* 4 Button Inline Command Control 2 (0x00e3) */ +#define RT5682_4BTN_IL_MASK (0x1 << 15) +#define RT5682_4BTN_IL_EN (0x1 << 15) +#define RT5682_4BTN_IL_DIS (0x0 << 15) +#define RT5682_4BTN_IL_RST_MASK (0x1 << 14) +#define RT5682_4BTN_IL_NOR (0x1 << 14) +#define RT5682_4BTN_IL_RST (0x0 << 14) + +/* Analog JD Control (0x00f0) */ +#define RT5682_JDH_RS_MASK (0x1 << 4) +#define RT5682_JDH_NO_PLUG (0x1 << 4) +#define RT5682_JDH_PLUG (0x0 << 4) + +/* Chopper and Clock control for DAC (0x013a)*/ +#define RT5682_CKXEN_DAC1_MASK (0x1 << 13) +#define RT5682_CKXEN_DAC1_SFT 13 +#define RT5682_CKGEN_DAC1_MASK (0x1 << 12) +#define RT5682_CKGEN_DAC1_SFT 12 + +/* Chopper and Clock control for ADC (0x013b)*/ +#define RT5682_CKXEN_ADC1_MASK (0x1 << 13) +#define RT5682_CKXEN_ADC1_SFT 13 +#define RT5682_CKGEN_ADC1_MASK (0x1 << 12) +#define RT5682_CKGEN_ADC1_SFT 12 + +/* Volume test (0x013f)*/ +#define RT5682_SEL_CLK_VOL_MASK (0x1 << 15) +#define RT5682_SEL_CLK_VOL_EN (0x1 << 15) +#define RT5682_SEL_CLK_VOL_DIS (0x0 << 15) + +/* Test Mode Control 1 (0x0145) */ +#define RT5682_AD2DA_LB_MASK (0x1 << 10) +#define RT5682_AD2DA_LB_SFT 10 + +/* Stereo Noise Gate Control 1 (0x0160) */ +#define RT5682_NG2_EN_MASK (0x1 << 15) +#define RT5682_NG2_EN (0x1 << 15) +#define RT5682_NG2_DIS (0x0 << 15) + +/* Stereo1 DAC Silence Detection Control (0x0190) */ +#define RT5682_DEB_STO_DAC_MASK (0x7 << 4) +#define RT5682_DEB_80_MS (0x0 << 4) + +/* SAR ADC Inline Command Control 1 (0x0210) */ +#define RT5682_SAR_BUTT_DET_MASK (0x1 << 15) +#define RT5682_SAR_BUTT_DET_EN (0x1 << 15) +#define RT5682_SAR_BUTT_DET_DIS (0x0 << 15) +#define RT5682_SAR_BUTDET_MODE_MASK (0x1 << 14) +#define RT5682_SAR_BUTDET_POW_SAV (0x1 << 14) +#define RT5682_SAR_BUTDET_POW_NORM (0x0 << 14) +#define RT5682_SAR_BUTDET_RST_MASK (0x1 << 13) +#define RT5682_SAR_BUTDET_RST_NORMAL (0x1 << 13) +#define RT5682_SAR_BUTDET_RST (0x0 << 13) +#define RT5682_SAR_POW_MASK (0x1 << 12) +#define RT5682_SAR_POW_EN (0x1 << 12) +#define RT5682_SAR_POW_DIS (0x0 << 12) +#define RT5682_SAR_RST_MASK (0x1 << 11) +#define RT5682_SAR_RST_NORMAL (0x1 << 11) +#define RT5682_SAR_RST (0x0 << 11) +#define RT5682_SAR_BYPASS_MASK (0x1 << 10) +#define RT5682_SAR_BYPASS_EN (0x1 << 10) +#define RT5682_SAR_BYPASS_DIS (0x0 << 10) +#define RT5682_SAR_SEL_MB1_MASK (0x1 << 9) +#define RT5682_SAR_SEL_MB1_SEL (0x1 << 9) +#define RT5682_SAR_SEL_MB1_NOSEL (0x0 << 9) +#define RT5682_SAR_SEL_MB2_MASK (0x1 << 8) +#define RT5682_SAR_SEL_MB2_SEL (0x1 << 8) +#define RT5682_SAR_SEL_MB2_NOSEL (0x0 << 8) +#define RT5682_SAR_SEL_MODE_MASK (0x1 << 7) +#define RT5682_SAR_SEL_MODE_CMP (0x1 << 7) +#define RT5682_SAR_SEL_MODE_ADC (0x0 << 7) +#define RT5682_SAR_SEL_MB1_MB2_MASK (0x1 << 5) +#define RT5682_SAR_SEL_MB1_MB2_AUTO (0x1 << 5) +#define RT5682_SAR_SEL_MB1_MB2_MANU (0x0 << 5) +#define RT5682_SAR_SEL_SIGNAL_MASK (0x1 << 4) +#define RT5682_SAR_SEL_SIGNAL_AUTO (0x1 << 4) +#define RT5682_SAR_SEL_SIGNAL_MANU (0x0 << 4) + +/* SAR ADC Inline Command Control 13 (0x021c) */ +#define RT5682_SAR_SOUR_MASK (0x3f) +#define RT5682_SAR_SOUR_BTN (0x3f) +#define RT5682_SAR_SOUR_TYPE (0x0) + + +/* System Clock Source */ +enum { + RT5682_SCLK_S_MCLK, + RT5682_SCLK_S_PLL1, + RT5682_SCLK_S_PLL2, + RT5682_SCLK_S_RCCLK, +}; + +/* PLL Source */ +enum { + RT5682_PLL1_S_MCLK, + RT5682_PLL1_S_BCLK1, + RT5682_PLL1_S_RCCLK, +}; + +enum { + RT5682_AIF1, + RT5682_AIF2, + RT5682_AIFS +}; + +/* filter mask */ +enum { + RT5682_DA_STEREO1_FILTER = 0x1, + RT5682_AD_STEREO1_FILTER = (0x1 << 1), +}; + +enum { + RT5682_CLK_SEL_SYS, + RT5682_CLK_SEL_I2S1_ASRC, + RT5682_CLK_SEL_I2S2_ASRC, +}; + +int rt5682_sel_asrc_clk_src(struct snd_soc_component *component, + unsigned int filter_mask, unsigned int clk_src); + +#endif /* __RT5682_H__ */ -- cgit v1.2.3 From cf85ec88701610f0de2e959ac447d9613462fbc7 Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Sat, 9 Jun 2018 16:18:16 +0300 Subject: removed extra extern file_fdatawait_range Jeff added this extern twice in commit a823e4589e68 Fixes: a823e4589e68 ("mm: add file_fdatawait_range and file_write_and_wait") Signed-off-by: Vasily Averin Signed-off-by: Al Viro --- include/linux/fs.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 5c91108846db..f140c11d35dd 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2623,8 +2623,6 @@ static inline int filemap_fdatawait(struct address_space *mapping) extern bool filemap_range_has_page(struct address_space *, loff_t lstart, loff_t lend); -extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart, - loff_t lend); extern int filemap_write_and_wait(struct address_space *mapping); extern int filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend); -- cgit v1.2.3 From b9be78531d2710f4302545aa80e0678ed0a3dd09 Mon Sep 17 00:00:00 2001 From: José Roberto de Souza Date: Thu, 14 Jun 2018 16:37:19 -0700 Subject: drm/i915/whl: Introducing Whiskey Lake platform MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Whiskey Lake uses the same gen graphics as Coffe Lake, including some ids that were previously marked as reserved on Coffe Lake, but that now are moved to WHL page. So, let's just move them to WHL macros that will feed into CFL macro just to keep it better organized to make easier future code review but it will be handled as a CFL. v2: Fixing GT level of some ids Cc: Rodrigo Vivi Signed-off-by: José Roberto de Souza Reviewed-by: Rodrigo Vivi Signed-off-by: Rodrigo Vivi Link: https://patchwork.freedesktop.org/patch/msgid/20180614233720.30517-1-jose.souza@intel.com --- drivers/gpu/drm/i915/i915_pci.c | 4 +++- include/drm/i915_pciids.h | 28 ++++++++++++++++++---------- 2 files changed, 21 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c index 97a91e6af7e3..92e98773e53d 100644 --- a/drivers/gpu/drm/i915/i915_pci.c +++ b/drivers/gpu/drm/i915/i915_pci.c @@ -660,9 +660,11 @@ static const struct pci_device_id pciidlist[] = { INTEL_CFL_S_GT1_IDS(&intel_coffeelake_gt1_info), INTEL_CFL_S_GT2_IDS(&intel_coffeelake_gt2_info), INTEL_CFL_H_GT2_IDS(&intel_coffeelake_gt2_info), - INTEL_CFL_U_GT1_IDS(&intel_coffeelake_gt1_info), INTEL_CFL_U_GT2_IDS(&intel_coffeelake_gt2_info), INTEL_CFL_U_GT3_IDS(&intel_coffeelake_gt3_info), + INTEL_WHL_U_GT1_IDS(&intel_coffeelake_gt1_info), + INTEL_WHL_U_GT2_IDS(&intel_coffeelake_gt2_info), + INTEL_WHL_U_GT3_IDS(&intel_coffeelake_gt3_info), INTEL_CNL_IDS(&intel_cannonlake_info), INTEL_ICL_11_IDS(&intel_icelake_11_info), {0, 0, 0} diff --git a/include/drm/i915_pciids.h b/include/drm/i915_pciids.h index bab70ff6e78b..d03350a38025 100644 --- a/include/drm/i915_pciids.h +++ b/include/drm/i915_pciids.h @@ -388,32 +388,40 @@ INTEL_VGA_DEVICE(0x3E9B, info), /* Halo GT2 */ \ INTEL_VGA_DEVICE(0x3E94, info) /* Halo GT2 */ -/* CFL U GT1 */ -#define INTEL_CFL_U_GT1_IDS(info) \ - INTEL_VGA_DEVICE(0x3EA1, info), \ - INTEL_VGA_DEVICE(0x3EA4, info) - /* CFL U GT2 */ #define INTEL_CFL_U_GT2_IDS(info) \ - INTEL_VGA_DEVICE(0x3EA0, info), \ - INTEL_VGA_DEVICE(0x3EA3, info), \ INTEL_VGA_DEVICE(0x3EA9, info) /* CFL U GT3 */ #define INTEL_CFL_U_GT3_IDS(info) \ - INTEL_VGA_DEVICE(0x3EA2, info), /* ULT GT3 */ \ INTEL_VGA_DEVICE(0x3EA5, info), /* ULT GT3 */ \ INTEL_VGA_DEVICE(0x3EA6, info), /* ULT GT3 */ \ INTEL_VGA_DEVICE(0x3EA7, info), /* ULT GT3 */ \ INTEL_VGA_DEVICE(0x3EA8, info) /* ULT GT3 */ +/* WHL/CFL U GT1 */ +#define INTEL_WHL_U_GT1_IDS(info) \ + INTEL_VGA_DEVICE(0x3EA1, info) + +/* WHL/CFL U GT2 */ +#define INTEL_WHL_U_GT2_IDS(info) \ + INTEL_VGA_DEVICE(0x3EA0, info) + +/* WHL/CFL U GT3 */ +#define INTEL_WHL_U_GT3_IDS(info) \ + INTEL_VGA_DEVICE(0x3EA2, info), \ + INTEL_VGA_DEVICE(0x3EA3, info), \ + INTEL_VGA_DEVICE(0x3EA4, info) + #define INTEL_CFL_IDS(info) \ INTEL_CFL_S_GT1_IDS(info), \ INTEL_CFL_S_GT2_IDS(info), \ INTEL_CFL_H_GT2_IDS(info), \ - INTEL_CFL_U_GT1_IDS(info), \ INTEL_CFL_U_GT2_IDS(info), \ - INTEL_CFL_U_GT3_IDS(info) + INTEL_CFL_U_GT3_IDS(info), \ + INTEL_WHL_U_GT1_IDS(info), \ + INTEL_WHL_U_GT2_IDS(info), \ + INTEL_WHL_U_GT3_IDS(info) /* CNL */ #define INTEL_CNL_IDS(info) \ -- cgit v1.2.3 From e364672477a105029346f0888bfa797b1ec3eee4 Mon Sep 17 00:00:00 2001 From: José Roberto de Souza Date: Thu, 14 Jun 2018 16:37:20 -0700 Subject: drm/i915/aml: Introducing Amber Lake platform MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Amber Lake uses the same gen graphics as Kaby Lake, including a id that were previously marked as reserved on Kaby Lake, but that now is moved to AML page. So, let's just move it to AML macro that will feed into KBL macro just to keep it better organized to make easier future code review but it will be handled as a KBL. Reviewed-by: Rodrigo Vivi Signed-off-by: José Roberto de Souza Signed-off-by: Rodrigo Vivi Link: https://patchwork.freedesktop.org/patch/msgid/20180614233720.30517-2-jose.souza@intel.com --- drivers/gpu/drm/i915/i915_pci.c | 1 + include/drm/i915_pciids.h | 9 +++++++-- 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c index 92e98773e53d..55543f1b0236 100644 --- a/drivers/gpu/drm/i915/i915_pci.c +++ b/drivers/gpu/drm/i915/i915_pci.c @@ -657,6 +657,7 @@ static const struct pci_device_id pciidlist[] = { INTEL_KBL_GT2_IDS(&intel_kabylake_gt2_info), INTEL_KBL_GT3_IDS(&intel_kabylake_gt3_info), INTEL_KBL_GT4_IDS(&intel_kabylake_gt3_info), + INTEL_AML_GT2_IDS(&intel_kabylake_gt2_info), INTEL_CFL_S_GT1_IDS(&intel_coffeelake_gt1_info), INTEL_CFL_S_GT2_IDS(&intel_coffeelake_gt2_info), INTEL_CFL_H_GT2_IDS(&intel_coffeelake_gt2_info), diff --git a/include/drm/i915_pciids.h b/include/drm/i915_pciids.h index d03350a38025..fbf5cfc9b352 100644 --- a/include/drm/i915_pciids.h +++ b/include/drm/i915_pciids.h @@ -349,7 +349,6 @@ #define INTEL_KBL_GT2_IDS(info) \ INTEL_VGA_DEVICE(0x5916, info), /* ULT GT2 */ \ INTEL_VGA_DEVICE(0x5917, info), /* Mobile GT2 */ \ - INTEL_VGA_DEVICE(0x591C, info), /* ULX GT2 */ \ INTEL_VGA_DEVICE(0x5921, info), /* ULT GT2F */ \ INTEL_VGA_DEVICE(0x591E, info), /* ULX GT2 */ \ INTEL_VGA_DEVICE(0x5912, info), /* DT GT2 */ \ @@ -365,11 +364,17 @@ #define INTEL_KBL_GT4_IDS(info) \ INTEL_VGA_DEVICE(0x593B, info) /* Halo GT4 */ +/* AML/KBL Y GT2 */ +#define INTEL_AML_GT2_IDS(info) \ + INTEL_VGA_DEVICE(0x591C, info), /* ULX GT2 */ \ + INTEL_VGA_DEVICE(0x87C0, info) /* ULX GT2 */ + #define INTEL_KBL_IDS(info) \ INTEL_KBL_GT1_IDS(info), \ INTEL_KBL_GT2_IDS(info), \ INTEL_KBL_GT3_IDS(info), \ - INTEL_KBL_GT4_IDS(info) + INTEL_KBL_GT4_IDS(info), \ + INTEL_AML_GT2_IDS(info) /* CFL S */ #define INTEL_CFL_S_GT1_IDS(info) \ -- cgit v1.2.3 From 420c0117db25db38b72b6230223f7a976d3070ea Mon Sep 17 00:00:00 2001 From: Robert Jarzmik Date: Sun, 17 Jun 2018 19:02:04 +0200 Subject: dmaengine: pxa: use a dma slave map In order to remove the specific knowledge of the dma mapping from PXA drivers, add a default slave map for pxa architectures. This won't impact MMP architecture, but is aimed only at all PXA boards. This is the first step, and once all drivers are converted, pxad_filter_fn() will be made static, and the DMA resources removed from device.c. Signed-off-by: Robert Jarzmik Reported-by: Arnd Bergmann Acked-by: Vinod Koul --- drivers/dma/pxa_dma.c | 10 +++++++++- include/linux/platform_data/mmp_dma.h | 4 ++++ 2 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/dma/pxa_dma.c b/drivers/dma/pxa_dma.c index b53fb618bbf6..9505334f9c6e 100644 --- a/drivers/dma/pxa_dma.c +++ b/drivers/dma/pxa_dma.c @@ -179,6 +179,8 @@ static unsigned int pxad_drcmr(unsigned int line) return 0x1000 + line * 4; } +bool pxad_filter_fn(struct dma_chan *chan, void *param); + /* * Debug fs */ @@ -1396,9 +1398,10 @@ static int pxad_probe(struct platform_device *op) { struct pxad_device *pdev; const struct of_device_id *of_id; + const struct dma_slave_map *slave_map = NULL; struct mmp_dma_platdata *pdata = dev_get_platdata(&op->dev); struct resource *iores; - int ret, dma_channels = 0, nb_requestors = 0; + int ret, dma_channels = 0, nb_requestors = 0, slave_map_cnt = 0; const enum dma_slave_buswidth widths = DMA_SLAVE_BUSWIDTH_1_BYTE | DMA_SLAVE_BUSWIDTH_2_BYTES | DMA_SLAVE_BUSWIDTH_4_BYTES; @@ -1429,6 +1432,8 @@ static int pxad_probe(struct platform_device *op) } else if (pdata && pdata->dma_channels) { dma_channels = pdata->dma_channels; nb_requestors = pdata->nb_requestors; + slave_map = pdata->slave_map; + slave_map_cnt = pdata->slave_map_cnt; } else { dma_channels = 32; /* default 32 channel */ } @@ -1440,6 +1445,9 @@ static int pxad_probe(struct platform_device *op) pdev->slave.device_prep_dma_memcpy = pxad_prep_memcpy; pdev->slave.device_prep_slave_sg = pxad_prep_slave_sg; pdev->slave.device_prep_dma_cyclic = pxad_prep_dma_cyclic; + pdev->slave.filter.map = slave_map; + pdev->slave.filter.mapcnt = slave_map_cnt; + pdev->slave.filter.fn = pxad_filter_fn; pdev->slave.copy_align = PDMA_ALIGNMENT; pdev->slave.src_addr_widths = widths; diff --git a/include/linux/platform_data/mmp_dma.h b/include/linux/platform_data/mmp_dma.h index d1397c8ed94e..6397b9c8149a 100644 --- a/include/linux/platform_data/mmp_dma.h +++ b/include/linux/platform_data/mmp_dma.h @@ -12,9 +12,13 @@ #ifndef MMP_DMA_H #define MMP_DMA_H +struct dma_slave_map; + struct mmp_dma_platdata { int dma_channels; int nb_requestors; + int slave_map_cnt; + const struct dma_slave_map *slave_map; }; #endif /* MMP_DMA_H */ -- cgit v1.2.3 From b6d1a17f4729e4fda5740a855da91d202db2c118 Mon Sep 17 00:00:00 2001 From: Robert Jarzmik Date: Sun, 17 Jun 2018 19:02:14 +0200 Subject: dmaengine: pxa: document pxad_param Add some documentation for the pxad_param structure, and describe the contract behind the minimal required priority of a DMA channel. Signed-off-by: Robert Jarzmik Acked-by: Vinod Koul --- include/linux/dma/pxa-dma.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/dma/pxa-dma.h b/include/linux/dma/pxa-dma.h index e56ec7af4fd7..9fc594f69eff 100644 --- a/include/linux/dma/pxa-dma.h +++ b/include/linux/dma/pxa-dma.h @@ -9,6 +9,15 @@ enum pxad_chan_prio { PXAD_PRIO_LOWEST, }; +/** + * struct pxad_param - dma channel request parameters + * @drcmr: requestor line number + * @prio: minimal mandatory priority of the channel + * + * If a requested channel is granted, its priority will be at least @prio, + * ie. if PXAD_PRIO_LOW is required, the requested channel will be either + * PXAD_PRIO_LOW, PXAD_PRIO_NORMAL or PXAD_PRIO_HIGHEST. + */ struct pxad_param { unsigned int drcmr; enum pxad_chan_prio prio; -- cgit v1.2.3 From cd31b80736852d34bc1072f3e579a6fd73a244e7 Mon Sep 17 00:00:00 2001 From: Robert Jarzmik Date: Sun, 17 Jun 2018 19:02:17 +0200 Subject: ARM: pxa: change SSP DMA channels allocation Now the dma_slave_map is available for PXA architecture, switch the SSP device to it. This specifically means that : - for platform data based machines, the DMA requestor channels are extracted from the slave map, where pxa-ssp-dai. is a 1-1 match to ssp., and the channels are either "rx" or "tx". - for device tree platforms, the dma node should be hooked into the pxa2xx-ac97 or pxa-ssp-dai node. Signed-off-by: Robert Jarzmik Acked-by: Daniel Mack --- arch/arm/plat-pxa/ssp.c | 47 ---------------------------------------------- include/linux/pxa2xx_ssp.h | 2 -- sound/soc/pxa/pxa-ssp.c | 5 ++--- 3 files changed, 2 insertions(+), 52 deletions(-) (limited to 'include') diff --git a/arch/arm/plat-pxa/ssp.c b/arch/arm/plat-pxa/ssp.c index ba13f793fbce..ed36dcab80f1 100644 --- a/arch/arm/plat-pxa/ssp.c +++ b/arch/arm/plat-pxa/ssp.c @@ -127,53 +127,6 @@ static int pxa_ssp_probe(struct platform_device *pdev) if (IS_ERR(ssp->clk)) return PTR_ERR(ssp->clk); - if (dev->of_node) { - struct of_phandle_args dma_spec; - struct device_node *np = dev->of_node; - int ret; - - /* - * FIXME: we should allocate the DMA channel from this - * context and pass the channel down to the ssp users. - * For now, we lookup the rx and tx indices manually - */ - - /* rx */ - ret = of_parse_phandle_with_args(np, "dmas", "#dma-cells", - 0, &dma_spec); - - if (ret) { - dev_err(dev, "Can't parse dmas property\n"); - return -ENODEV; - } - ssp->drcmr_rx = dma_spec.args[0]; - of_node_put(dma_spec.np); - - /* tx */ - ret = of_parse_phandle_with_args(np, "dmas", "#dma-cells", - 1, &dma_spec); - if (ret) { - dev_err(dev, "Can't parse dmas property\n"); - return -ENODEV; - } - ssp->drcmr_tx = dma_spec.args[0]; - of_node_put(dma_spec.np); - } else { - res = platform_get_resource(pdev, IORESOURCE_DMA, 0); - if (res == NULL) { - dev_err(dev, "no SSP RX DRCMR defined\n"); - return -ENODEV; - } - ssp->drcmr_rx = res->start; - - res = platform_get_resource(pdev, IORESOURCE_DMA, 1); - if (res == NULL) { - dev_err(dev, "no SSP TX DRCMR defined\n"); - return -ENODEV; - } - ssp->drcmr_tx = res->start; - } - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); if (res == NULL) { dev_err(dev, "no memory resource defined\n"); diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h index 8461b18e4608..03a7ca46735b 100644 --- a/include/linux/pxa2xx_ssp.h +++ b/include/linux/pxa2xx_ssp.h @@ -212,8 +212,6 @@ struct ssp_device { int type; int use_count; int irq; - int drcmr_rx; - int drcmr_tx; struct device_node *of_node; }; diff --git a/sound/soc/pxa/pxa-ssp.c b/sound/soc/pxa/pxa-ssp.c index 6fc986080130..0b441338bdd4 100644 --- a/sound/soc/pxa/pxa-ssp.c +++ b/sound/soc/pxa/pxa-ssp.c @@ -105,9 +105,8 @@ static int pxa_ssp_startup(struct snd_pcm_substream *substream, dma = kzalloc(sizeof(struct snd_dmaengine_dai_dma_data), GFP_KERNEL); if (!dma) return -ENOMEM; - - dma->filter_data = substream->stream == SNDRV_PCM_STREAM_PLAYBACK ? - &ssp->drcmr_tx : &ssp->drcmr_rx; + dma->chan_name = substream->stream == SNDRV_PCM_STREAM_PLAYBACK ? + "tx" : "rx"; snd_soc_dai_set_dma_data(cpu_dai, substream, dma); -- cgit v1.2.3 From b8042b3da925f390c1482bf9dc0898dc0b3ea7b5 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 18 Jun 2018 22:39:29 +0200 Subject: ieee80211: bump IEEE80211_MAX_AMPDU_BUF to support HE Bump the IEEE80211_MAX_AMPDU_BUF size to 0x100 for HE support and - for now - use IEEE80211_MAX_AMPDU_BUF_HT everywhere. This is derived from my internal patch, parts of which Luca had sent upstream. Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- drivers/net/wireless/realtek/rtlwifi/base.c | 2 +- drivers/staging/rtl8188eu/include/wifi.h | 1 - drivers/staging/rtl8712/wifi.h | 1 - drivers/staging/rtl8723bs/include/wifi.h | 1 - drivers/staging/rtlwifi/base.c | 2 +- include/linux/ieee80211.h | 10 ++++++---- net/mac80211/agg-rx.c | 4 ++-- net/mac80211/agg-tx.c | 2 +- net/mac80211/ht.c | 2 +- net/mac80211/main.c | 4 ++-- 10 files changed, 14 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/drivers/net/wireless/realtek/rtlwifi/base.c b/drivers/net/wireless/realtek/rtlwifi/base.c index 39c817eddd78..31bd6f714052 100644 --- a/drivers/net/wireless/realtek/rtlwifi/base.c +++ b/drivers/net/wireless/realtek/rtlwifi/base.c @@ -1904,7 +1904,7 @@ void rtl_rx_ampdu_apply(struct rtl_priv *rtlpriv) reject_agg, ctrl_agg_size, agg_size); rtlpriv->hw->max_rx_aggregation_subframes = - (ctrl_agg_size ? agg_size : IEEE80211_MAX_AMPDU_BUF); + (ctrl_agg_size ? agg_size : IEEE80211_MAX_AMPDU_BUF_HT); } EXPORT_SYMBOL(rtl_rx_ampdu_apply); diff --git a/drivers/staging/rtl8188eu/include/wifi.h b/drivers/staging/rtl8188eu/include/wifi.h index 084a246eec19..6790b7c8cfb1 100644 --- a/drivers/staging/rtl8188eu/include/wifi.h +++ b/drivers/staging/rtl8188eu/include/wifi.h @@ -575,7 +575,6 @@ enum ht_cap_ampdu_factor { * According to IEEE802.11n spec size varies from 8K to 64K (in powers of 2) */ #define IEEE80211_MIN_AMPDU_BUF 0x8 -#define IEEE80211_MAX_AMPDU_BUF 0x40 #define OP_MODE_PURE 0 diff --git a/drivers/staging/rtl8712/wifi.h b/drivers/staging/rtl8712/wifi.h index 0ed2f44ab4e9..00a4302e9983 100644 --- a/drivers/staging/rtl8712/wifi.h +++ b/drivers/staging/rtl8712/wifi.h @@ -574,7 +574,6 @@ struct ieee80211_ht_addt_info { * According to IEEE802.11n spec size varies from 8K to 64K (in powers of 2) */ #define IEEE80211_MIN_AMPDU_BUF 0x8 -#define IEEE80211_MAX_AMPDU_BUF 0x40 /* Spatial Multiplexing Power Save Modes */ diff --git a/drivers/staging/rtl8723bs/include/wifi.h b/drivers/staging/rtl8723bs/include/wifi.h index 08bc79840b23..559bf2606fb7 100644 --- a/drivers/staging/rtl8723bs/include/wifi.h +++ b/drivers/staging/rtl8723bs/include/wifi.h @@ -799,7 +799,6 @@ enum HT_CAP_AMPDU_FACTOR { * According to IEEE802.11n spec size varies from 8K to 64K (in powers of 2) */ #define IEEE80211_MIN_AMPDU_BUF 0x8 -#define IEEE80211_MAX_AMPDU_BUF 0x40 /* Spatial Multiplexing Power Save Modes */ diff --git a/drivers/staging/rtlwifi/base.c b/drivers/staging/rtlwifi/base.c index e46e47d93d7d..094827c1879a 100644 --- a/drivers/staging/rtlwifi/base.c +++ b/drivers/staging/rtlwifi/base.c @@ -1838,7 +1838,7 @@ void rtl_rx_ampdu_apply(struct rtl_priv *rtlpriv) reject_agg, ctrl_agg_size, agg_size); rtlpriv->hw->max_rx_aggregation_subframes = - (ctrl_agg_size ? agg_size : IEEE80211_MAX_AMPDU_BUF); + (ctrl_agg_size ? agg_size : IEEE80211_MAX_AMPDU_BUF_HT); } /********************************************************* diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index e6a6503bfa33..9c03a7d5e400 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1433,11 +1433,13 @@ struct ieee80211_ht_operation { #define IEEE80211_DELBA_PARAM_INITIATOR_MASK 0x0800 /* - * A-PMDU buffer sizes - * According to IEEE802.11n spec size varies from 8K to 64K (in powers of 2) + * A-MPDU buffer sizes + * According to HT size varies from 8 to 64 frames + * HE adds the ability to have up to 256 frames. */ -#define IEEE80211_MIN_AMPDU_BUF 0x8 -#define IEEE80211_MAX_AMPDU_BUF 0x40 +#define IEEE80211_MIN_AMPDU_BUF 0x8 +#define IEEE80211_MAX_AMPDU_BUF_HT 0x40 +#define IEEE80211_MAX_AMPDU_BUF 0x100 /* Spatial Multiplexing Power Save Modes (for capability) */ diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index e83c19d4c292..3ffd853b483f 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -274,7 +274,7 @@ void ___ieee80211_start_rx_ba_session(struct sta_info *sta, /* XXX: check own ht delayed BA capability?? */ if (((ba_policy != 1) && (!(sta->sta.ht_cap.cap & IEEE80211_HT_CAP_DELAY_BA))) || - (buf_size > IEEE80211_MAX_AMPDU_BUF)) { + (buf_size > IEEE80211_MAX_AMPDU_BUF_HT)) { status = WLAN_STATUS_INVALID_QOS_PARAM; ht_dbg_ratelimited(sta->sdata, "AddBA Req with bad params from %pM on tid %u. policy %d, buffer size %d\n", @@ -283,7 +283,7 @@ void ___ieee80211_start_rx_ba_session(struct sta_info *sta, } /* determine default buffer size */ if (buf_size == 0) - buf_size = IEEE80211_MAX_AMPDU_BUF; + buf_size = IEEE80211_MAX_AMPDU_BUF_HT; /* make sure the size doesn't exceed the maximum supported by the hw */ if (buf_size > sta->sta.max_rx_aggregation_subframes) diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index ac4295296514..86c6bc0432ba 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -514,7 +514,7 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) /* send AddBA request */ ieee80211_send_addba_request(sdata, sta->sta.addr, tid, tid_tx->dialog_token, params.ssn, - IEEE80211_MAX_AMPDU_BUF, + IEEE80211_MAX_AMPDU_BUF_HT, tid_tx->timeout); } diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index 26a7ba3b698f..f849ea814993 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -352,7 +352,7 @@ void ieee80211_ba_session_work(struct work_struct *work) test_and_clear_bit(tid, sta->ampdu_mlme.tid_rx_manage_offl)) ___ieee80211_start_rx_ba_session(sta, 0, 0, 0, 1, tid, - IEEE80211_MAX_AMPDU_BUF, + IEEE80211_MAX_AMPDU_BUF_HT, false, true); if (test_and_clear_bit(tid + IEEE80211_NUM_TIDS, diff --git a/net/mac80211/main.c b/net/mac80211/main.c index a6f8e3a646d4..070f77862014 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -597,8 +597,8 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, local->hw.queues = 1; local->hw.max_rates = 1; local->hw.max_report_rates = 0; - local->hw.max_rx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF; - local->hw.max_tx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF; + local->hw.max_rx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF_HT; + local->hw.max_tx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF_HT; local->hw.offchannel_tx_hw_queue = IEEE80211_INVAL_HW_QUEUE; local->hw.conf.long_frame_max_tx_count = wiphy->retry_long; local->hw.conf.short_frame_max_tx_count = wiphy->retry_short; -- cgit v1.2.3 From 41cbb0f5a29592874355e4159489eb08337cd50e Mon Sep 17 00:00:00 2001 From: Luca Coelho Date: Sat, 9 Jun 2018 09:14:44 +0300 Subject: mac80211: add support for HE Add support for HE in mac80211 conforming with P802.11ax_D1.4. Johannes: Fix another bug with the buf_size comparison in agg-rx.c. Signed-off-by: Liad Kaufman Signed-off-by: Johannes Berg Signed-off-by: Ilan Peer Signed-off-by: Ido Yariv Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- include/net/mac80211.h | 64 ++++++++-- net/mac80211/Makefile | 1 + net/mac80211/agg-rx.c | 10 +- net/mac80211/agg-tx.c | 19 ++- net/mac80211/cfg.c | 5 + net/mac80211/he.c | 55 +++++++++ net/mac80211/ieee80211_i.h | 16 +++ net/mac80211/main.c | 19 ++- net/mac80211/mlme.c | 288 ++++++++++++++++++++++++++++++++++++++++++--- net/mac80211/rx.c | 127 +++++++++++++++++++- net/mac80211/sta_info.c | 15 ++- net/mac80211/sta_info.h | 20 +++- net/mac80211/trace.h | 2 +- net/mac80211/util.c | 120 ++++++++++++++++++- 14 files changed, 716 insertions(+), 45 deletions(-) create mode 100644 net/mac80211/he.c (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 851a5e19ae32..5790f55c241d 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -23,6 +23,7 @@ #include #include #include +#include #include /** @@ -162,6 +163,8 @@ enum ieee80211_ac_numbers { * @txop: maximum burst time in units of 32 usecs, 0 meaning disabled * @acm: is mandatory admission control required for the access category * @uapsd: is U-APSD mode enabled for the queue + * @mu_edca: is the MU EDCA configured + * @mu_edca_param_rec: MU EDCA Parameter Record for HE */ struct ieee80211_tx_queue_params { u16 txop; @@ -170,6 +173,8 @@ struct ieee80211_tx_queue_params { u8 aifs; bool acm; bool uapsd; + bool mu_edca; + struct ieee80211_he_mu_edca_param_ac_rec mu_edca_param_rec; }; struct ieee80211_low_level_stats { @@ -463,6 +468,15 @@ struct ieee80211_mu_group_data { * This structure keeps information about a BSS (and an association * to that BSS) that can change during the lifetime of the BSS. * + * @bss_color: 6-bit value to mark inter-BSS frame, if BSS supports HE + * @htc_trig_based_pkt_ext: default PE in 4us units, if BSS supports HE + * @multi_sta_back_32bit: supports BA bitmap of 32-bits in Multi-STA BACK + * @uora_exists: is the UORA element advertised by AP + * @ack_enabled: indicates support to receive a multi-TID that solicits either + * ACK, BACK or both + * @uora_ocw_range: UORA element's OCW Range field + * @frame_time_rts_th: HE duration RTS threshold, in units of 32us + * @he_support: does this BSS support HE * @assoc: association status * @ibss_joined: indicates whether this station is part of an IBSS * or not @@ -550,6 +564,14 @@ struct ieee80211_mu_group_data { */ struct ieee80211_bss_conf { const u8 *bssid; + u8 bss_color; + u8 htc_trig_based_pkt_ext; + bool multi_sta_back_32bit; + bool uora_exists; + bool ack_enabled; + u8 uora_ocw_range; + u16 frame_time_rts_th; + bool he_support; /* association related data */ bool assoc, ibss_joined; bool ibss_creator; @@ -1106,6 +1128,18 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info) * @RX_FLAG_AMPDU_EOF_BIT: Value of the EOF bit in the A-MPDU delimiter for this * frame * @RX_FLAG_AMPDU_EOF_BIT_KNOWN: The EOF value is known + * @RX_FLAG_RADIOTAP_HE: HE radiotap data is present + * (&struct ieee80211_radiotap_he, mac80211 will fill in + * - DATA3_DATA_MCS + * - DATA3_DATA_DCM + * - DATA3_CODING + * - DATA5_GI + * - DATA5_DATA_BW_RU_ALLOC + * - DATA6_NSTS + * - DATA3_STBC + * from the RX info data, so leave those zeroed when building this data) + * @RX_FLAG_RADIOTAP_HE_MU: HE MU radiotap data is present + * (&struct ieee80211_radiotap_he_mu) */ enum mac80211_rx_flags { RX_FLAG_MMIC_ERROR = BIT(0), @@ -1134,6 +1168,8 @@ enum mac80211_rx_flags { RX_FLAG_ICV_STRIPPED = BIT(23), RX_FLAG_AMPDU_EOF_BIT = BIT(24), RX_FLAG_AMPDU_EOF_BIT_KNOWN = BIT(25), + RX_FLAG_RADIOTAP_HE = BIT(26), + RX_FLAG_RADIOTAP_HE_MU = BIT(27), }; /** @@ -1164,6 +1200,7 @@ enum mac80211_rx_encoding { RX_ENC_LEGACY = 0, RX_ENC_HT, RX_ENC_VHT, + RX_ENC_HE, }; /** @@ -1198,6 +1235,9 @@ enum mac80211_rx_encoding { * @encoding: &enum mac80211_rx_encoding * @bw: &enum rate_info_bw * @enc_flags: uses bits from &enum mac80211_rx_encoding_flags + * @he_ru: HE RU, from &enum nl80211_he_ru_alloc + * @he_gi: HE GI, from &enum nl80211_he_gi + * @he_dcm: HE DCM value * @rx_flags: internal RX flags for mac80211 * @ampdu_reference: A-MPDU reference number, must be a different value for * each A-MPDU but the same for each subframe within one A-MPDU @@ -1211,7 +1251,8 @@ struct ieee80211_rx_status { u32 flag; u16 freq; u8 enc_flags; - u8 encoding:2, bw:3; + u8 encoding:2, bw:3, he_ru:3; + u8 he_gi:2, he_dcm:1; u8 rate_idx; u8 nss; u8 rx_flags; @@ -1770,6 +1811,7 @@ struct ieee80211_sta_rates { * @supp_rates: Bitmap of supported rates (per band) * @ht_cap: HT capabilities of this STA; restricted to our own capabilities * @vht_cap: VHT capabilities of this STA; restricted to our own capabilities + * @he_cap: HE capabilities of this STA * @max_rx_aggregation_subframes: maximal amount of frames in a single AMPDU * that this station is allowed to transmit to us. * Can be modified by driver. @@ -1805,7 +1847,8 @@ struct ieee80211_sta { u16 aid; struct ieee80211_sta_ht_cap ht_cap; struct ieee80211_sta_vht_cap vht_cap; - u8 max_rx_aggregation_subframes; + struct ieee80211_sta_he_cap he_cap; + u16 max_rx_aggregation_subframes; bool wme; u8 uapsd_queues; u8 max_sp; @@ -2196,10 +2239,11 @@ enum ieee80211_hw_flags { * it shouldn't be set. * * @max_tx_aggregation_subframes: maximum number of subframes in an - * aggregate an HT driver will transmit. Though ADDBA will advertise - * a constant value of 64 as some older APs can crash if the window - * size is smaller (an example is LinkSys WRT120N with FW v1.0.07 - * build 002 Jun 18 2012). + * aggregate an HT/HE device will transmit. In HT AddBA we'll + * advertise a constant value of 64 as some older APs crash if + * the window size is smaller (an example is LinkSys WRT120N + * with FW v1.0.07 build 002 Jun 18 2012). + * For AddBA to HE capable peers this value will be used. * * @max_tx_fragments: maximum number of tx buffers per (A)-MSDU, sum * of 1 + skb_shinfo(skb)->nr_frags for each skb in the frag_list. @@ -2216,6 +2260,8 @@ enum ieee80211_hw_flags { * the default is _GI | _BANDWIDTH. * Use the %IEEE80211_RADIOTAP_VHT_KNOWN_\* values. * + * @radiotap_he: HE radiotap validity flags + * * @radiotap_timestamp: Information for the radiotap timestamp field; if the * 'units_pos' member is set to a non-negative value it must be set to * a combination of a IEEE80211_RADIOTAP_TIMESTAMP_UNIT_* and a @@ -2263,8 +2309,8 @@ struct ieee80211_hw { u8 max_rates; u8 max_report_rates; u8 max_rate_tries; - u8 max_rx_aggregation_subframes; - u8 max_tx_aggregation_subframes; + u16 max_rx_aggregation_subframes; + u16 max_tx_aggregation_subframes; u8 max_tx_fragments; u8 offchannel_tx_hw_queue; u8 radiotap_mcs_details; @@ -2904,7 +2950,7 @@ struct ieee80211_ampdu_params { struct ieee80211_sta *sta; u16 tid; u16 ssn; - u8 buf_size; + u16 buf_size; bool amsdu; u16 timeout; }; diff --git a/net/mac80211/Makefile b/net/mac80211/Makefile index e3589ade62e0..bb707789ef2b 100644 --- a/net/mac80211/Makefile +++ b/net/mac80211/Makefile @@ -12,6 +12,7 @@ mac80211-y := \ scan.o offchannel.o \ ht.o agg-tx.o agg-rx.o \ vht.o \ + he.o \ ibss.o \ iface.o \ rate.o \ diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 3ffd853b483f..6a4f154c99f6 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -245,6 +245,7 @@ void ___ieee80211_start_rx_ba_session(struct sta_info *sta, }; int i, ret = -EOPNOTSUPP; u16 status = WLAN_STATUS_REQUEST_DECLINED; + u16 max_buf_size; if (tid >= IEEE80211_FIRST_TSPEC_TSID) { ht_dbg(sta->sdata, @@ -268,13 +269,18 @@ void ___ieee80211_start_rx_ba_session(struct sta_info *sta, goto end; } + if (sta->sta.he_cap.has_he) + max_buf_size = IEEE80211_MAX_AMPDU_BUF; + else + max_buf_size = IEEE80211_MAX_AMPDU_BUF_HT; + /* sanity check for incoming parameters: * check if configuration can support the BA policy * and if buffer size does not exceeds max value */ /* XXX: check own ht delayed BA capability?? */ if (((ba_policy != 1) && (!(sta->sta.ht_cap.cap & IEEE80211_HT_CAP_DELAY_BA))) || - (buf_size > IEEE80211_MAX_AMPDU_BUF_HT)) { + (buf_size > max_buf_size)) { status = WLAN_STATUS_INVALID_QOS_PARAM; ht_dbg_ratelimited(sta->sdata, "AddBA Req with bad params from %pM on tid %u. policy %d, buffer size %d\n", @@ -283,7 +289,7 @@ void ___ieee80211_start_rx_ba_session(struct sta_info *sta, } /* determine default buffer size */ if (buf_size == 0) - buf_size = IEEE80211_MAX_AMPDU_BUF_HT; + buf_size = max_buf_size; /* make sure the size doesn't exceed the maximum supported by the hw */ if (buf_size > sta->sta.max_rx_aggregation_subframes) diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index 86c6bc0432ba..69e831bc317b 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -463,6 +463,7 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) .timeout = 0, }; int ret; + u16 buf_size; tid_tx = rcu_dereference_protected_tid_tx(sta, tid); @@ -511,11 +512,22 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) sta->ampdu_mlme.addba_req_num[tid]++; spin_unlock_bh(&sta->lock); + if (sta->sta.he_cap.has_he) { + buf_size = local->hw.max_tx_aggregation_subframes; + } else { + /* + * We really should use what the driver told us it will + * transmit as the maximum, but certain APs (e.g. the + * LinkSys WRT120N with FW v1.0.07 build 002 Jun 18 2012) + * will crash when we use a lower number. + */ + buf_size = IEEE80211_MAX_AMPDU_BUF_HT; + } + /* send AddBA request */ ieee80211_send_addba_request(sdata, sta->sta.addr, tid, tid_tx->dialog_token, params.ssn, - IEEE80211_MAX_AMPDU_BUF_HT, - tid_tx->timeout); + buf_size, tid_tx->timeout); } /* @@ -905,8 +917,7 @@ void ieee80211_process_addba_resp(struct ieee80211_local *local, { struct tid_ampdu_tx *tid_tx; struct ieee80211_txq *txq; - u16 capab, tid; - u8 buf_size; + u16 capab, tid, buf_size; bool amsdu; capab = le16_to_cpu(mgmt->u.action.u.addba_resp.capab); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index c4e2f7d2bcb8..02f3672e7b5e 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1412,6 +1412,11 @@ static int sta_apply_parameters(struct ieee80211_local *local, ieee80211_vht_cap_ie_to_sta_vht_cap(sdata, sband, params->vht_capa, sta); + if (params->he_capa) + ieee80211_he_cap_ie_to_sta_he_cap(sdata, sband, + (void *)params->he_capa, + params->he_capa_len, sta); + if (params->opmode_notif_used) { /* returned value is only needed for rc update, but the * rc isn't initialized here yet, so ignore it diff --git a/net/mac80211/he.c b/net/mac80211/he.c new file mode 100644 index 000000000000..769078ed5a12 --- /dev/null +++ b/net/mac80211/he.c @@ -0,0 +1,55 @@ +/* + * HE handling + * + * Copyright(c) 2017 Intel Deutschland GmbH + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "ieee80211_i.h" + +void +ieee80211_he_cap_ie_to_sta_he_cap(struct ieee80211_sub_if_data *sdata, + struct ieee80211_supported_band *sband, + const u8 *he_cap_ie, u8 he_cap_len, + struct sta_info *sta) +{ + struct ieee80211_sta_he_cap *he_cap = &sta->sta.he_cap; + struct ieee80211_he_cap_elem *he_cap_ie_elem = (void *)he_cap_ie; + u8 he_ppe_size; + u8 mcs_nss_size; + u8 he_total_size; + + memset(he_cap, 0, sizeof(*he_cap)); + + if (!he_cap_ie || !ieee80211_get_he_sta_cap(sband)) + return; + + /* Make sure size is OK */ + mcs_nss_size = ieee80211_he_mcs_nss_size(he_cap_ie_elem); + he_ppe_size = + ieee80211_he_ppe_size(he_cap_ie[sizeof(he_cap->he_cap_elem) + + mcs_nss_size], + he_cap_ie_elem->phy_cap_info); + he_total_size = sizeof(he_cap->he_cap_elem) + mcs_nss_size + + he_ppe_size; + if (he_cap_len < he_total_size) + return; + + memcpy(&he_cap->he_cap_elem, he_cap_ie, sizeof(he_cap->he_cap_elem)); + + /* HE Tx/Rx HE MCS NSS Support Field */ + memcpy(&he_cap->he_mcs_nss_supp, + &he_cap_ie[sizeof(he_cap->he_cap_elem)], mcs_nss_size); + + /* Check if there are (optional) PPE Thresholds */ + if (he_cap->he_cap_elem.phy_cap_info[6] & + IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT) + memcpy(he_cap->ppe_thres, + &he_cap_ie[sizeof(he_cap->he_cap_elem) + mcs_nss_size], + he_ppe_size); + + he_cap->has_he = true; +} diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index a6c12c104c38..172aeae21ae9 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -365,6 +365,7 @@ enum ieee80211_sta_flags { IEEE80211_STA_DISABLE_160MHZ = BIT(13), IEEE80211_STA_DISABLE_WMM = BIT(14), IEEE80211_STA_ENABLE_RRM = BIT(15), + IEEE80211_STA_DISABLE_HE = BIT(16), }; struct ieee80211_mgd_auth_data { @@ -1454,6 +1455,10 @@ struct ieee802_11_elems { const struct ieee80211_vht_cap *vht_cap_elem; const struct ieee80211_vht_operation *vht_operation; const struct ieee80211_meshconf_ie *mesh_config; + const u8 *he_cap; + const struct ieee80211_he_operation *he_operation; + const struct ieee80211_mu_edca_param_set *mu_edca_param_set; + const u8 *uora_element; const u8 *mesh_id; const u8 *peering; const __le16 *awake_window; @@ -1483,6 +1488,7 @@ struct ieee802_11_elems { u8 ext_supp_rates_len; u8 wmm_info_len; u8 wmm_param_len; + u8 he_cap_len; u8 mesh_id_len; u8 peering_len; u8 preq_len; @@ -1825,6 +1831,13 @@ void ieee80211_get_vht_mask_from_cap(__le16 vht_cap, enum nl80211_chan_width ieee80211_sta_rx_bw_to_chan_width(struct sta_info *sta); +/* HE */ +void +ieee80211_he_cap_ie_to_sta_he_cap(struct ieee80211_sub_if_data *sdata, + struct ieee80211_supported_band *sband, + const u8 *he_cap_ie, u8 he_cap_len, + struct sta_info *sta); + /* Spectrum management */ void ieee80211_process_measurement_req(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt, @@ -2076,6 +2089,9 @@ u8 *ieee80211_ie_build_vht_cap(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap, u32 cap); u8 *ieee80211_ie_build_vht_oper(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap, const struct cfg80211_chan_def *chandef); +u8 *ieee80211_ie_build_he_cap(u8 *pos, + const struct ieee80211_sta_he_cap *he_cap, + u8 *end); int ieee80211_parse_bitrates(struct cfg80211_chan_def *chandef, const struct ieee80211_supported_band *sband, const u8 *srates, int srates_len, u32 *rates); diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 070f77862014..b33faba8cbbe 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -3,6 +3,7 @@ * Copyright 2005-2006, Devicescape Software, Inc. * Copyright 2006-2007 Jiri Benc * Copyright 2013-2014 Intel Mobile Communications GmbH + * Copyright (C) 2017 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -825,7 +826,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) int result, i; enum nl80211_band band; int channels, max_bitrates; - bool supp_ht, supp_vht; + bool supp_ht, supp_vht, supp_he; netdev_features_t feature_whitelist; struct cfg80211_chan_def dflt_chandef = {}; @@ -905,6 +906,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) max_bitrates = 0; supp_ht = false; supp_vht = false; + supp_he = false; for (band = 0; band < NUM_NL80211_BANDS; band++) { struct ieee80211_supported_band *sband; @@ -931,6 +933,9 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) supp_ht = supp_ht || sband->ht_cap.ht_supported; supp_vht = supp_vht || sband->vht_cap.vht_supported; + if (!supp_he) + supp_he = !!ieee80211_get_he_sta_cap(sband); + if (!sband->ht_cap.ht_supported) continue; @@ -1020,6 +1025,18 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) local->scan_ies_len += 2 + sizeof(struct ieee80211_vht_cap); + /* HE cap element is variable in size - set len to allow max size */ + /* + * TODO: 1 is added at the end of the calculation to accommodate for + * the temporary placing of the HE capabilities IE under EXT. + * Remove it once it is placed in the final place. + */ + if (supp_he) + local->scan_ies_len += + 2 + sizeof(struct ieee80211_he_cap_elem) + + sizeof(struct ieee80211_he_mcs_nss_supp) + + IEEE80211_HE_PPE_THRES_MAX_LEN + 1; + if (!local->ops->hw_scan) { /* For hw_scan, driver needs to set these up. */ local->hw.wiphy->max_scan_ssids = 4; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index a44e5b4aaeda..0322d78007ad 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -149,6 +149,7 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, struct ieee80211_channel *channel, const struct ieee80211_ht_operation *ht_oper, const struct ieee80211_vht_operation *vht_oper, + const struct ieee80211_he_operation *he_oper, struct cfg80211_chan_def *chandef, bool tracking) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; @@ -207,7 +208,27 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, } vht_chandef = *chandef; - if (!ieee80211_chandef_vht_oper(vht_oper, &vht_chandef)) { + if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HE) && he_oper && + (le32_to_cpu(he_oper->he_oper_params) & + IEEE80211_HE_OPERATION_VHT_OPER_INFO)) { + struct ieee80211_vht_operation he_oper_vht_cap; + + /* + * Set only first 3 bytes (other 2 aren't used in + * ieee80211_chandef_vht_oper() anyway) + */ + memcpy(&he_oper_vht_cap, he_oper->optional, 3); + he_oper_vht_cap.basic_mcs_set = cpu_to_le16(0); + + if (!ieee80211_chandef_vht_oper(&he_oper_vht_cap, + &vht_chandef)) { + if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HE)) + sdata_info(sdata, + "HE AP VHT information is invalid, disable HE\n"); + ret = IEEE80211_STA_DISABLE_HE; + goto out; + } + } else if (!ieee80211_chandef_vht_oper(vht_oper, &vht_chandef)) { if (!(ifmgd->flags & IEEE80211_STA_DISABLE_VHT)) sdata_info(sdata, "AP VHT information is invalid, disable VHT\n"); @@ -300,12 +321,14 @@ static int ieee80211_config_bw(struct ieee80211_sub_if_data *sdata, const struct ieee80211_ht_cap *ht_cap, const struct ieee80211_ht_operation *ht_oper, const struct ieee80211_vht_operation *vht_oper, + const struct ieee80211_he_operation *he_oper, const u8 *bssid, u32 *changed) { struct ieee80211_local *local = sdata->local; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - struct ieee80211_supported_band *sband; - struct ieee80211_channel *chan; + struct ieee80211_channel *chan = sdata->vif.bss_conf.chandef.chan; + struct ieee80211_supported_band *sband = + local->hw.wiphy->bands[chan->band]; struct cfg80211_chan_def chandef; u16 ht_opmode; u32 flags; @@ -320,6 +343,11 @@ static int ieee80211_config_bw(struct ieee80211_sub_if_data *sdata, if (ifmgd->flags & IEEE80211_STA_DISABLE_VHT) vht_oper = NULL; + /* don't check HE if we associated as non-HE station */ + if (ifmgd->flags & IEEE80211_STA_DISABLE_HE || + !ieee80211_get_he_sta_cap(sband)) + he_oper = NULL; + if (WARN_ON_ONCE(!sta)) return -EINVAL; @@ -333,12 +361,9 @@ static int ieee80211_config_bw(struct ieee80211_sub_if_data *sdata, sdata->vif.bss_conf.ht_operation_mode = ht_opmode; } - chan = sdata->vif.bss_conf.chandef.chan; - sband = local->hw.wiphy->bands[chan->band]; - - /* calculate new channel (type) based on HT/VHT operation IEs */ + /* calculate new channel (type) based on HT/VHT/HE operation IEs */ flags = ieee80211_determine_chantype(sdata, sband, chan, - ht_oper, vht_oper, + ht_oper, vht_oper, he_oper, &chandef, true); /* @@ -582,6 +607,34 @@ static void ieee80211_add_vht_ie(struct ieee80211_sub_if_data *sdata, ieee80211_ie_build_vht_cap(pos, &vht_cap, cap); } +/* This function determines HE capability flags for the association + * and builds the IE. + */ +static void ieee80211_add_he_ie(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb, + struct ieee80211_supported_band *sband) +{ + u8 *pos; + const struct ieee80211_sta_he_cap *he_cap = NULL; + u8 he_cap_size; + + he_cap = ieee80211_get_he_sta_cap(sband); + if (!he_cap) + return; + + /* + * TODO: the 1 added is because this temporarily is under the EXTENSION + * IE. Get rid of it when it moves. + */ + he_cap_size = + 2 + 1 + sizeof(he_cap->he_cap_elem) + + ieee80211_he_mcs_nss_size(&he_cap->he_cap_elem) + + ieee80211_he_ppe_size(he_cap->ppe_thres[0], + he_cap->he_cap_elem.phy_cap_info); + pos = skb_put(skb, he_cap_size); + ieee80211_ie_build_he_cap(pos, he_cap, pos + he_cap_size); +} + static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) { struct ieee80211_local *local = sdata->local; @@ -643,6 +696,9 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) 2 + 2 * sband->n_channels + /* supported channels */ 2 + sizeof(struct ieee80211_ht_cap) + /* HT */ 2 + sizeof(struct ieee80211_vht_cap) + /* VHT */ + 2 + 1 + sizeof(struct ieee80211_he_cap_elem) + /* HE */ + sizeof(struct ieee80211_he_mcs_nss_supp) + + IEEE80211_HE_PPE_THRES_MAX_LEN + assoc_data->ie_len + /* extra IEs */ (assoc_data->fils_kek_len ? 16 /* AES-SIV */ : 0) + 9, /* WMM */ @@ -827,11 +883,41 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) offset = noffset; } + /* if present, add any custom IEs that go before HE */ + if (assoc_data->ie_len) { + static const u8 before_he[] = { + /* + * no need to list the ones split off before VHT + * or generated here + */ + WLAN_EID_OPMODE_NOTIF, + WLAN_EID_EXTENSION, WLAN_EID_EXT_FUTURE_CHAN_GUIDANCE, + /* 11ai elements */ + WLAN_EID_EXTENSION, WLAN_EID_EXT_FILS_SESSION, + WLAN_EID_EXTENSION, WLAN_EID_EXT_FILS_PUBLIC_KEY, + WLAN_EID_EXTENSION, WLAN_EID_EXT_FILS_KEY_CONFIRM, + WLAN_EID_EXTENSION, WLAN_EID_EXT_FILS_HLP_CONTAINER, + WLAN_EID_EXTENSION, WLAN_EID_EXT_FILS_IP_ADDR_ASSIGN, + /* TODO: add 11ah/11aj/11ak elements */ + }; + + /* RIC already taken above, so no need to handle here anymore */ + noffset = ieee80211_ie_split(assoc_data->ie, assoc_data->ie_len, + before_he, ARRAY_SIZE(before_he), + offset); + pos = skb_put(skb, noffset - offset); + memcpy(pos, assoc_data->ie + offset, noffset - offset); + offset = noffset; + } + if (!(ifmgd->flags & IEEE80211_STA_DISABLE_VHT)) ieee80211_add_vht_ie(sdata, skb, sband, &assoc_data->ap_vht_cap); - /* if present, add any custom non-vendor IEs that go after HT */ + if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HE)) + ieee80211_add_he_ie(sdata, skb, sband); + + /* if present, add any custom non-vendor IEs that go after HE */ if (assoc_data->ie_len) { noffset = ieee80211_ie_split_vendor(assoc_data->ie, assoc_data->ie_len, @@ -898,6 +984,11 @@ void ieee80211_send_nullfunc(struct ieee80211_local *local, struct ieee80211_hdr_3addr *nullfunc; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + /* Don't send NDPs when STA is connected HE */ + if (sdata->vif.type == NL80211_IFTYPE_STATION && + !(ifmgd->flags & IEEE80211_STA_DISABLE_HE)) + return; + skb = ieee80211_nullfunc_get(&local->hw, &sdata->vif, !ieee80211_hw_check(&local->hw, DOESNT_SUPPORT_QOS_NDP)); if (!skb) @@ -929,6 +1020,10 @@ static void ieee80211_send_4addr_nullfunc(struct ieee80211_local *local, if (WARN_ON(sdata->vif.type != NL80211_IFTYPE_STATION)) return; + /* Don't send NDPs when connected HE */ + if (!(sdata->u.mgd.flags & IEEE80211_STA_DISABLE_HE)) + return; + skb = dev_alloc_skb(local->hw.extra_tx_headroom + 30); if (!skb) return; @@ -1700,9 +1795,11 @@ static void ieee80211_sta_handle_tspec_ac_params_wk(struct work_struct *work) } /* MLME */ -static bool ieee80211_sta_wmm_params(struct ieee80211_local *local, - struct ieee80211_sub_if_data *sdata, - const u8 *wmm_param, size_t wmm_param_len) +static bool +ieee80211_sta_wmm_params(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + const u8 *wmm_param, size_t wmm_param_len, + const struct ieee80211_mu_edca_param_set *mu_edca) { struct ieee80211_tx_queue_params params[IEEE80211_NUM_ACS]; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; @@ -1749,6 +1846,9 @@ static bool ieee80211_sta_wmm_params(struct ieee80211_local *local, sdata->wmm_acm |= BIT(1) | BIT(2); /* BK/- */ if (uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_BK) uapsd = true; + params[ac].mu_edca = !!mu_edca; + if (mu_edca) + params[ac].mu_edca_param_rec = mu_edca->ac_bk; break; case 2: /* AC_VI */ ac = IEEE80211_AC_VI; @@ -1756,6 +1856,9 @@ static bool ieee80211_sta_wmm_params(struct ieee80211_local *local, sdata->wmm_acm |= BIT(4) | BIT(5); /* CL/VI */ if (uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_VI) uapsd = true; + params[ac].mu_edca = !!mu_edca; + if (mu_edca) + params[ac].mu_edca_param_rec = mu_edca->ac_vi; break; case 3: /* AC_VO */ ac = IEEE80211_AC_VO; @@ -1763,6 +1866,9 @@ static bool ieee80211_sta_wmm_params(struct ieee80211_local *local, sdata->wmm_acm |= BIT(6) | BIT(7); /* VO/NC */ if (uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_VO) uapsd = true; + params[ac].mu_edca = !!mu_edca; + if (mu_edca) + params[ac].mu_edca_param_rec = mu_edca->ac_vo; break; case 0: /* AC_BE */ default: @@ -1771,6 +1877,9 @@ static bool ieee80211_sta_wmm_params(struct ieee80211_local *local, sdata->wmm_acm |= BIT(0) | BIT(3); /* BE/EE */ if (uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_BE) uapsd = true; + params[ac].mu_edca = !!mu_edca; + if (mu_edca) + params[ac].mu_edca_param_rec = mu_edca->ac_be; break; } @@ -3021,6 +3130,25 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, goto out; } + /* + * If AP doesn't support HT, or it doesn't have HE mandatory IEs, mark + * HE as disabled. If on the 5GHz band, make sure it supports VHT. + */ + if (ifmgd->flags & IEEE80211_STA_DISABLE_HT || + (sband->band == NL80211_BAND_5GHZ && + ifmgd->flags & IEEE80211_STA_DISABLE_VHT) || + (!elems.he_cap && !elems.he_operation)) + ifmgd->flags |= IEEE80211_STA_DISABLE_HE; + + if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HE) && + (!elems.he_cap || !elems.he_operation)) { + mutex_unlock(&sdata->local->sta_mtx); + sdata_info(sdata, + "HE AP is missing HE capability/operation\n"); + ret = false; + goto out; + } + /* Set up internal HT/VHT capabilities */ if (elems.ht_cap_elem && !(ifmgd->flags & IEEE80211_STA_DISABLE_HT)) ieee80211_ht_cap_ie_to_sta_ht_cap(sdata, sband, @@ -3030,6 +3158,48 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, ieee80211_vht_cap_ie_to_sta_vht_cap(sdata, sband, elems.vht_cap_elem, sta); + if (elems.he_operation && !(ifmgd->flags & IEEE80211_STA_DISABLE_HE) && + elems.he_cap) { + ieee80211_he_cap_ie_to_sta_he_cap(sdata, sband, + elems.he_cap, + elems.he_cap_len, + sta); + + bss_conf->he_support = sta->sta.he_cap.has_he; + } else { + bss_conf->he_support = false; + } + + if (bss_conf->he_support) { + u32 he_oper_params = + le32_to_cpu(elems.he_operation->he_oper_params); + + bss_conf->bss_color = he_oper_params & + IEEE80211_HE_OPERATION_BSS_COLOR_MASK; + bss_conf->htc_trig_based_pkt_ext = + (he_oper_params & + IEEE80211_HE_OPERATION_DFLT_PE_DURATION_MASK) << + IEEE80211_HE_OPERATION_DFLT_PE_DURATION_OFFSET; + bss_conf->frame_time_rts_th = + (he_oper_params & + IEEE80211_HE_OPERATION_RTS_THRESHOLD_MASK) << + IEEE80211_HE_OPERATION_RTS_THRESHOLD_OFFSET; + + bss_conf->multi_sta_back_32bit = + sta->sta.he_cap.he_cap_elem.mac_cap_info[2] & + IEEE80211_HE_MAC_CAP2_32BIT_BA_BITMAP; + + bss_conf->ack_enabled = + sta->sta.he_cap.he_cap_elem.mac_cap_info[2] & + IEEE80211_HE_MAC_CAP2_ACK_EN; + + bss_conf->uora_exists = !!elems.uora_element; + if (elems.uora_element) + bss_conf->uora_ocw_range = elems.uora_element[0]; + + /* TODO: OPEN: what happens if BSS color disable is set? */ + } + /* * Some APs, e.g. Netgear WNDR3700, report invalid HT operation data * in their association response, so ignore that data for our own @@ -3089,7 +3259,8 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, if (ifmgd->flags & IEEE80211_STA_DISABLE_WMM) { ieee80211_set_wmm_default(sdata, false, false); } else if (!ieee80211_sta_wmm_params(local, sdata, elems.wmm_param, - elems.wmm_param_len)) { + elems.wmm_param_len, + elems.mu_edca_param_set)) { /* still enable QoS since we might have HT/VHT */ ieee80211_set_wmm_default(sdata, false, true); /* set the disable-WMM flag in this case to disable @@ -3603,7 +3774,8 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, if (!(ifmgd->flags & IEEE80211_STA_DISABLE_WMM) && ieee80211_sta_wmm_params(local, sdata, elems.wmm_param, - elems.wmm_param_len)) + elems.wmm_param_len, + elems.mu_edca_param_set)) changed |= BSS_CHANGED_QOS; /* @@ -3642,7 +3814,8 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, if (ieee80211_config_bw(sdata, sta, elems.ht_cap_elem, elems.ht_operation, - elems.vht_operation, bssid, &changed)) { + elems.vht_operation, elems.he_operation, + bssid, &changed)) { mutex_unlock(&local->sta_mtx); sdata_info(sdata, "failed to follow AP %pM bandwidth change, disconnect\n", @@ -4279,6 +4452,66 @@ static u8 ieee80211_ht_vht_rx_chains(struct ieee80211_sub_if_data *sdata, return chains; } +static bool +ieee80211_verify_sta_he_mcs_support(struct ieee80211_supported_band *sband, + const struct ieee80211_he_operation *he_op) +{ + const struct ieee80211_sta_he_cap *sta_he_cap = + ieee80211_get_he_sta_cap(sband); + u16 ap_min_req_set = le16_to_cpu(he_op->he_mcs_nss_set); + int i; + + if (!sta_he_cap || !he_op) + return false; + + /* Need to go over for 80MHz, 160MHz and for 80+80 */ + for (i = 0; i < 3; i++) { + const struct ieee80211_he_mcs_nss_supp *sta_mcs_nss_supp = + &sta_he_cap->he_mcs_nss_supp; + u16 sta_mcs_map_rx = + le16_to_cpu(((__le16 *)sta_mcs_nss_supp)[2 * i]); + u16 sta_mcs_map_tx = + le16_to_cpu(((__le16 *)sta_mcs_nss_supp)[2 * i + 1]); + u8 nss; + bool verified = true; + + /* + * For each band there is a maximum of 8 spatial streams + * possible. Each of the sta_mcs_map_* is a 16-bit struct built + * of 2 bits per NSS (1-8), with the values defined in enum + * ieee80211_he_mcs_support. Need to make sure STA TX and RX + * capabilities aren't less than the AP's minimum requirements + * for this HE BSS per SS. + * It is enough to find one such band that meets the reqs. + */ + for (nss = 8; nss > 0; nss--) { + u8 sta_rx_val = (sta_mcs_map_rx >> (2 * (nss - 1))) & 3; + u8 sta_tx_val = (sta_mcs_map_tx >> (2 * (nss - 1))) & 3; + u8 ap_val = (ap_min_req_set >> (2 * (nss - 1))) & 3; + + if (ap_val == IEEE80211_HE_MCS_NOT_SUPPORTED) + continue; + + /* + * Make sure the HE AP doesn't require MCSs that aren't + * supported by the client + */ + if (sta_rx_val == IEEE80211_HE_MCS_NOT_SUPPORTED || + sta_tx_val == IEEE80211_HE_MCS_NOT_SUPPORTED || + (ap_val > sta_rx_val) || (ap_val > sta_tx_val)) { + verified = false; + break; + } + } + + if (verified) + return true; + } + + /* If here, STA doesn't meet AP's HE min requirements */ + return false; +} + static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, struct cfg80211_bss *cbss) { @@ -4287,6 +4520,7 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, const struct ieee80211_ht_cap *ht_cap = NULL; const struct ieee80211_ht_operation *ht_oper = NULL; const struct ieee80211_vht_operation *vht_oper = NULL; + const struct ieee80211_he_operation *he_oper = NULL; struct ieee80211_supported_band *sband; struct cfg80211_chan_def chandef; int ret; @@ -4342,6 +4576,25 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, } } + if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HE) && + ieee80211_get_he_sta_cap(sband)) { + const struct cfg80211_bss_ies *ies; + const u8 *he_oper_ie; + + ies = rcu_dereference(cbss->ies); + he_oper_ie = cfg80211_find_ext_ie(WLAN_EID_EXT_HE_OPERATION, + ies->data, ies->len); + if (he_oper_ie && + he_oper_ie[1] == ieee80211_he_oper_size(&he_oper_ie[3])) + he_oper = (void *)(he_oper_ie + 3); + else + he_oper = NULL; + + if (!he_oper || + !ieee80211_verify_sta_he_mcs_support(sband, he_oper)) + ifmgd->flags |= IEEE80211_STA_DISABLE_HE; + } + /* Allow VHT if at least one channel on the sband supports 80 MHz */ have_80mhz = false; for (i = 0; i < sband->n_channels; i++) { @@ -4358,7 +4611,7 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, ifmgd->flags |= ieee80211_determine_chantype(sdata, sband, cbss->channel, - ht_oper, vht_oper, + ht_oper, vht_oper, he_oper, &chandef, false); sdata->needed_rx_chains = min(ieee80211_ht_vht_rx_chains(sdata, cbss), @@ -4764,8 +5017,9 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, req->crypto.ciphers_pairwise[i] == WLAN_CIPHER_SUITE_WEP104) { ifmgd->flags |= IEEE80211_STA_DISABLE_HT; ifmgd->flags |= IEEE80211_STA_DISABLE_VHT; + ifmgd->flags |= IEEE80211_STA_DISABLE_HE; netdev_info(sdata->dev, - "disabling HT/VHT due to WEP/TKIP use\n"); + "disabling HE/HT/VHT due to WEP/TKIP use\n"); } } diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 756ba176db1e..a16ba568e2a3 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -175,6 +175,20 @@ ieee80211_rx_radiotap_hdrlen(struct ieee80211_local *local, len += 12; } + if (status->encoding == RX_ENC_HE && + status->flag & RX_FLAG_RADIOTAP_HE) { + len = ALIGN(len, 2); + len += 12; + BUILD_BUG_ON(sizeof(struct ieee80211_radiotap_he) != 12); + } + + if (status->encoding == RX_ENC_HE && + status->flag & RX_FLAG_RADIOTAP_HE_MU) { + len = ALIGN(len, 2); + len += 12; + BUILD_BUG_ON(sizeof(struct ieee80211_radiotap_he_mu) != 12); + } + if (status->chains) { /* antenna and antenna signal fields */ len += 2 * hweight8(status->chains); @@ -263,6 +277,19 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, int mpdulen, chain; unsigned long chains = status->chains; struct ieee80211_vendor_radiotap rtap = {}; + struct ieee80211_radiotap_he he = {}; + struct ieee80211_radiotap_he_mu he_mu = {}; + + if (status->flag & RX_FLAG_RADIOTAP_HE) { + he = *(struct ieee80211_radiotap_he *)skb->data; + skb_pull(skb, sizeof(he)); + WARN_ON_ONCE(status->encoding != RX_ENC_HE); + } + + if (status->flag & RX_FLAG_RADIOTAP_HE_MU) { + he_mu = *(struct ieee80211_radiotap_he_mu *)skb->data; + skb_pull(skb, sizeof(he_mu)); + } if (status->flag & RX_FLAG_RADIOTAP_VENDOR_DATA) { rtap = *(struct ieee80211_vendor_radiotap *)skb->data; @@ -520,6 +547,89 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, *pos++ = flags; } + if (status->encoding == RX_ENC_HE && + status->flag & RX_FLAG_RADIOTAP_HE) { +#define HE_PREP(f, val) cpu_to_le16(FIELD_PREP(IEEE80211_RADIOTAP_HE_##f, val)) + + if (status->enc_flags & RX_ENC_FLAG_STBC_MASK) { + he.data6 |= HE_PREP(DATA6_NSTS, + FIELD_GET(RX_ENC_FLAG_STBC_MASK, + status->enc_flags)); + he.data3 |= HE_PREP(DATA3_STBC, 1); + } else { + he.data6 |= HE_PREP(DATA6_NSTS, status->nss); + } + +#define CHECK_GI(s) \ + BUILD_BUG_ON(IEEE80211_RADIOTAP_HE_DATA5_GI_##s != \ + (int)NL80211_RATE_INFO_HE_GI_##s) + + CHECK_GI(0_8); + CHECK_GI(1_6); + CHECK_GI(3_2); + + he.data3 |= HE_PREP(DATA3_DATA_MCS, status->rate_idx); + he.data3 |= HE_PREP(DATA3_DATA_DCM, status->he_dcm); + he.data3 |= HE_PREP(DATA3_CODING, + !!(status->enc_flags & RX_ENC_FLAG_LDPC)); + + he.data5 |= HE_PREP(DATA5_GI, status->he_gi); + + switch (status->bw) { + case RATE_INFO_BW_20: + he.data5 |= HE_PREP(DATA5_DATA_BW_RU_ALLOC, + IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_20MHZ); + break; + case RATE_INFO_BW_40: + he.data5 |= HE_PREP(DATA5_DATA_BW_RU_ALLOC, + IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_40MHZ); + break; + case RATE_INFO_BW_80: + he.data5 |= HE_PREP(DATA5_DATA_BW_RU_ALLOC, + IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_80MHZ); + break; + case RATE_INFO_BW_160: + he.data5 |= HE_PREP(DATA5_DATA_BW_RU_ALLOC, + IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_160MHZ); + break; + case RATE_INFO_BW_HE_RU: +#define CHECK_RU_ALLOC(s) \ + BUILD_BUG_ON(IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_##s##T != \ + NL80211_RATE_INFO_HE_RU_ALLOC_##s + 4) + + CHECK_RU_ALLOC(26); + CHECK_RU_ALLOC(52); + CHECK_RU_ALLOC(106); + CHECK_RU_ALLOC(242); + CHECK_RU_ALLOC(484); + CHECK_RU_ALLOC(996); + CHECK_RU_ALLOC(2x996); + + he.data5 |= HE_PREP(DATA5_DATA_BW_RU_ALLOC, + status->he_ru + 4); + break; + default: + WARN_ONCE(1, "Invalid SU BW %d\n", status->bw); + } + + /* ensure 2 byte alignment */ + while ((pos - (u8 *)rthdr) & 1) + pos++; + rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_HE); + memcpy(pos, &he, sizeof(he)); + pos += sizeof(he); + } + + if (status->encoding == RX_ENC_HE && + status->flag & RX_FLAG_RADIOTAP_HE_MU) { + /* ensure 2 byte alignment */ + while ((pos - (u8 *)rthdr) & 1) + pos++; + rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_HE_MU); + memcpy(pos, &he_mu, sizeof(he_mu)); + pos += sizeof(he_mu); + } + for_each_set_bit(chain, &chains, IEEE80211_MAX_CHAINS) { *pos++ = status->chain_signal[chain]; *pos++ = chain; @@ -613,6 +723,12 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb, rcu_dereference(local->monitor_sdata); bool only_monitor = false; + if (status->flag & RX_FLAG_RADIOTAP_HE) + rtap_space += sizeof(struct ieee80211_radiotap_he); + + if (status->flag & RX_FLAG_RADIOTAP_HE_MU) + rtap_space += sizeof(struct ieee80211_radiotap_he_mu); + if (unlikely(status->flag & RX_FLAG_RADIOTAP_VENDOR_DATA)) { struct ieee80211_vendor_radiotap *rtap = (void *)origskb->data; @@ -3386,8 +3502,7 @@ static void ieee80211_rx_handlers_result(struct ieee80211_rx_data *rx, status = IEEE80211_SKB_RXCB((rx->skb)); sband = rx->local->hw.wiphy->bands[status->band]; - if (!(status->encoding == RX_ENC_HT) && - !(status->encoding == RX_ENC_VHT)) + if (status->encoding == RX_ENC_LEGACY) rate = &sband->bitrates[status->rate_idx]; ieee80211_rx_cooked_monitor(rx, rate); @@ -4386,6 +4501,14 @@ void ieee80211_rx_napi(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta, status->rate_idx, status->nss)) goto drop; break; + case RX_ENC_HE: + if (WARN_ONCE(status->rate_idx > 11 || + !status->nss || + status->nss > 8, + "Rate marked as an HE rate but data is invalid: MCS: %d, NSS: %d\n", + status->rate_idx, status->nss)) + goto drop; + break; default: WARN_ON_ONCE(1); /* fall through */ diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index aa96fddfbfc2..aa8fe771a8db 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -1323,6 +1323,11 @@ static void ieee80211_send_null_response(struct sta_info *sta, int tid, struct ieee80211_tx_info *info; struct ieee80211_chanctx_conf *chanctx_conf; + /* Don't send NDPs when STA is connected HE */ + if (sdata->vif.type == NL80211_IFTYPE_STATION && + !(sdata->u.mgd.flags & IEEE80211_STA_DISABLE_HE)) + return; + if (qos) { fc = cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_QOS_NULLFUNC | @@ -1968,7 +1973,7 @@ sta_get_last_rx_stats(struct sta_info *sta) return stats; } -static void sta_stats_decode_rate(struct ieee80211_local *local, u16 rate, +static void sta_stats_decode_rate(struct ieee80211_local *local, u32 rate, struct rate_info *rinfo) { rinfo->bw = STA_STATS_GET(BW, rate); @@ -2005,6 +2010,14 @@ static void sta_stats_decode_rate(struct ieee80211_local *local, u16 rate, rinfo->legacy = DIV_ROUND_UP(brate, 1 << shift); break; } + case STA_STATS_RATE_TYPE_HE: + rinfo->flags = RATE_INFO_FLAGS_HE_MCS; + rinfo->mcs = STA_STATS_GET(HE_MCS, rate); + rinfo->nss = STA_STATS_GET(HE_NSS, rate); + rinfo->he_gi = STA_STATS_GET(HE_GI, rate); + rinfo->he_ru_alloc = STA_STATS_GET(HE_RU, rate); + rinfo->he_dcm = STA_STATS_GET(HE_DCM, rate); + break; } } diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 81b35f623792..9a04327d71d1 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -170,7 +170,7 @@ struct tid_ampdu_tx { u8 dialog_token; u8 stop_initiator; bool tx_stop; - u8 buf_size; + u16 buf_size; u16 failed_bar_ssn; bool bar_pending; @@ -405,7 +405,7 @@ struct ieee80211_sta_rx_stats { int last_signal; u8 chains; s8 chain_signal_last[IEEE80211_MAX_CHAINS]; - u16 last_rate; + u32 last_rate; struct u64_stats_sync syncp; u64 bytes; u64 msdu[IEEE80211_NUM_TIDS + 1]; @@ -764,6 +764,7 @@ enum sta_stats_type { STA_STATS_RATE_TYPE_LEGACY, STA_STATS_RATE_TYPE_HT, STA_STATS_RATE_TYPE_VHT, + STA_STATS_RATE_TYPE_HE, }; #define STA_STATS_FIELD_HT_MCS GENMASK( 7, 0) @@ -771,9 +772,14 @@ enum sta_stats_type { #define STA_STATS_FIELD_LEGACY_BAND GENMASK( 7, 4) #define STA_STATS_FIELD_VHT_MCS GENMASK( 3, 0) #define STA_STATS_FIELD_VHT_NSS GENMASK( 7, 4) +#define STA_STATS_FIELD_HE_MCS GENMASK( 3, 0) +#define STA_STATS_FIELD_HE_NSS GENMASK( 7, 4) #define STA_STATS_FIELD_BW GENMASK(11, 8) #define STA_STATS_FIELD_SGI GENMASK(12, 12) #define STA_STATS_FIELD_TYPE GENMASK(15, 13) +#define STA_STATS_FIELD_HE_RU GENMASK(18, 16) +#define STA_STATS_FIELD_HE_GI GENMASK(20, 19) +#define STA_STATS_FIELD_HE_DCM GENMASK(21, 21) #define STA_STATS_FIELD(_n, _v) FIELD_PREP(STA_STATS_FIELD_ ## _n, _v) #define STA_STATS_GET(_n, _v) FIELD_GET(STA_STATS_FIELD_ ## _n, _v) @@ -782,7 +788,7 @@ enum sta_stats_type { static inline u32 sta_stats_encode_rate(struct ieee80211_rx_status *s) { - u16 r; + u32 r; r = STA_STATS_FIELD(BW, s->bw); @@ -804,6 +810,14 @@ static inline u32 sta_stats_encode_rate(struct ieee80211_rx_status *s) r |= STA_STATS_FIELD(LEGACY_BAND, s->band); r |= STA_STATS_FIELD(LEGACY_IDX, s->rate_idx); break; + case RX_ENC_HE: + r |= STA_STATS_FIELD(TYPE, STA_STATS_RATE_TYPE_HE); + r |= STA_STATS_FIELD(HE_NSS, s->nss); + r |= STA_STATS_FIELD(HE_MCS, s->rate_idx); + r |= STA_STATS_FIELD(HE_GI, s->he_gi); + r |= STA_STATS_FIELD(HE_RU, s->he_ru); + r |= STA_STATS_FIELD(HE_DCM, s->he_dcm); + break; default: WARN_ON(1); return STA_STATS_RATE_INVALID; diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h index 80a7edf8d314..0ab69a1964f8 100644 --- a/net/mac80211/trace.h +++ b/net/mac80211/trace.h @@ -92,7 +92,7 @@ STA_ENTRY \ __field(u16, tid) \ __field(u16, ssn) \ - __field(u8, buf_size) \ + __field(u16, buf_size) \ __field(bool, amsdu) \ __field(u16, timeout) \ __field(u16, action) diff --git a/net/mac80211/util.c b/net/mac80211/util.c index b744b10465c3..c77c84325348 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1095,6 +1095,21 @@ u32 ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, if (elen >= sizeof(*elems->max_idle_period_ie)) elems->max_idle_period_ie = (void *)pos; break; + case WLAN_EID_EXTENSION: + if (pos[0] == WLAN_EID_EXT_HE_MU_EDCA && + elen >= (sizeof(*elems->mu_edca_param_set) + 1)) { + elems->mu_edca_param_set = (void *)&pos[1]; + } else if (pos[0] == WLAN_EID_EXT_HE_CAPABILITY) { + elems->he_cap = (void *)&pos[1]; + elems->he_cap_len = elen - 1; + } else if (pos[0] == WLAN_EID_EXT_HE_OPERATION && + elen >= sizeof(*elems->he_operation) && + elen >= ieee80211_he_oper_size(&pos[1])) { + elems->he_operation = (void *)&pos[1]; + } else if (pos[0] == WLAN_EID_EXT_UORA && elen >= 1) { + elems->uora_element = (void *)&pos[1]; + } + break; default: break; } @@ -1356,6 +1371,7 @@ static int ieee80211_build_preq_ies_band(struct ieee80211_local *local, size_t *offset, u32 flags) { struct ieee80211_supported_band *sband; + const struct ieee80211_sta_he_cap *he_cap; u8 *pos = buffer, *end = buffer + buffer_len; size_t noffset; int supp_rates_len, i; @@ -1463,11 +1479,6 @@ static int ieee80211_build_preq_ies_band(struct ieee80211_local *local, sband->ht_cap.cap); } - /* - * If adding more here, adjust code in main.c - * that calculates local->scan_ies_len. - */ - /* insert custom IEs that go before VHT */ if (ie && ie_len) { static const u8 before_vht[] = { @@ -1510,6 +1521,39 @@ static int ieee80211_build_preq_ies_band(struct ieee80211_local *local, sband->vht_cap.cap); } + /* insert custom IEs that go before HE */ + if (ie && ie_len) { + static const u8 before_he[] = { + /* + * no need to list the ones split off before VHT + * or generated here + */ + WLAN_EID_EXTENSION, WLAN_EID_EXT_FILS_REQ_PARAMS, + WLAN_EID_AP_CSN, + /* TODO: add 11ah/11aj/11ak elements */ + }; + noffset = ieee80211_ie_split(ie, ie_len, + before_he, ARRAY_SIZE(before_he), + *offset); + if (end - pos < noffset - *offset) + goto out_err; + memcpy(pos, ie + *offset, noffset - *offset); + pos += noffset - *offset; + *offset = noffset; + } + + he_cap = ieee80211_get_he_sta_cap(sband); + if (he_cap) { + pos = ieee80211_ie_build_he_cap(pos, he_cap, end); + if (!pos) + goto out_err; + } + + /* + * If adding more here, adjust code in main.c + * that calculates local->scan_ies_len. + */ + return pos - buffer; out_err: WARN_ONCE(1, "not enough space for preq IEs\n"); @@ -2396,6 +2440,72 @@ u8 *ieee80211_ie_build_vht_cap(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap, return pos; } +u8 *ieee80211_ie_build_he_cap(u8 *pos, + const struct ieee80211_sta_he_cap *he_cap, + u8 *end) +{ + u8 n; + u8 ie_len; + u8 *orig_pos = pos; + + /* Make sure we have place for the IE */ + /* + * TODO: the 1 added is because this temporarily is under the EXTENSION + * IE. Get rid of it when it moves. + */ + if (!he_cap) + return orig_pos; + + n = ieee80211_he_mcs_nss_size(&he_cap->he_cap_elem); + ie_len = 2 + 1 + + sizeof(he_cap->he_cap_elem) + n + + ieee80211_he_ppe_size(he_cap->ppe_thres[0], + he_cap->he_cap_elem.phy_cap_info); + + if ((end - pos) < ie_len) + return orig_pos; + + *pos++ = WLAN_EID_EXTENSION; + pos++; /* We'll set the size later below */ + *pos++ = WLAN_EID_EXT_HE_CAPABILITY; + + /* Fixed data */ + memcpy(pos, &he_cap->he_cap_elem, sizeof(he_cap->he_cap_elem)); + pos += sizeof(he_cap->he_cap_elem); + + memcpy(pos, &he_cap->he_mcs_nss_supp, n); + pos += n; + + /* Check if PPE Threshold should be present */ + if ((he_cap->he_cap_elem.phy_cap_info[6] & + IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT) == 0) + goto end; + + /* + * Calculate how many PPET16/PPET8 pairs are to come. Algorithm: + * (NSS_M1 + 1) x (num of 1 bits in RU_INDEX_BITMASK) + */ + n = hweight8(he_cap->ppe_thres[0] & + IEEE80211_PPE_THRES_RU_INDEX_BITMASK_MASK); + n *= (1 + ((he_cap->ppe_thres[0] & IEEE80211_PPE_THRES_NSS_MASK) >> + IEEE80211_PPE_THRES_NSS_POS)); + + /* + * Each pair is 6 bits, and we need to add the 7 "header" bits to the + * total size. + */ + n = (n * IEEE80211_PPE_THRES_INFO_PPET_SIZE * 2) + 7; + n = DIV_ROUND_UP(n, 8); + + /* Copy PPE Thresholds */ + memcpy(pos, &he_cap->ppe_thres, n); + pos += n; + +end: + orig_pos[1] = (pos - orig_pos) - 2; + return pos; +} + u8 *ieee80211_ie_build_ht_oper(u8 *pos, struct ieee80211_sta_ht_cap *ht_cap, const struct cfg80211_chan_def *chandef, u16 prot_mode, bool rifs_mode) -- cgit v1.2.3 From d904ac0320d3c4ff4e9d80e4294ca5dde803696f Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Tue, 5 Jun 2018 11:45:07 -0400 Subject: audit: rename FILTER_TYPE to FILTER_EXCLUDE The AUDIT_FILTER_TYPE name is vague and misleading due to not describing where or when the filter is applied and obsolete due to its available filter fields having been expanded. Userspace has already renamed it from AUDIT_FILTER_TYPE to AUDIT_FILTER_EXCLUDE without checking if it already exists. The userspace maintainer assures that as long as it is set to the same value it will not be a problem since the userspace code does not treat compiler warnings as errors. If this policy changes then checks if it already exists can be added at the same time. See: https://github.com/linux-audit/audit-kernel/issues/89 Signed-off-by: Richard Guy Briggs Signed-off-by: Paul Moore --- include/uapi/linux/audit.h | 3 ++- kernel/audit.c | 2 +- kernel/auditfilter.c | 10 +++++----- 3 files changed, 8 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index c35aee9ad4a6..4e3eaba84175 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -157,7 +157,8 @@ #define AUDIT_FILTER_ENTRY 0x02 /* Apply rule at syscall entry */ #define AUDIT_FILTER_WATCH 0x03 /* Apply rule to file system watches */ #define AUDIT_FILTER_EXIT 0x04 /* Apply rule at syscall exit */ -#define AUDIT_FILTER_TYPE 0x05 /* Apply rule at audit_log_start */ +#define AUDIT_FILTER_EXCLUDE 0x05 /* Apply rule before record creation */ +#define AUDIT_FILTER_TYPE AUDIT_FILTER_EXCLUDE /* obsolete misleading naming */ #define AUDIT_FILTER_FS 0x06 /* Apply rule at __audit_inode_child */ #define AUDIT_NR_FILTERS 7 diff --git a/kernel/audit.c b/kernel/audit.c index e7478cb58079..5c0a1d7b0c7b 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -1754,7 +1754,7 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, if (audit_initialized != AUDIT_INITIALIZED) return NULL; - if (unlikely(!audit_filter(type, AUDIT_FILTER_TYPE))) + if (unlikely(!audit_filter(type, AUDIT_FILTER_EXCLUDE))) return NULL; /* NOTE: don't ever fail/sleep on these two conditions: diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index 6db9847ca031..bf309f2592c4 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -264,7 +264,7 @@ static inline struct audit_entry *audit_to_entry_common(struct audit_rule_data * case AUDIT_FILTER_TASK: #endif case AUDIT_FILTER_USER: - case AUDIT_FILTER_TYPE: + case AUDIT_FILTER_EXCLUDE: case AUDIT_FILTER_FS: ; } @@ -337,7 +337,7 @@ static int audit_field_valid(struct audit_entry *entry, struct audit_field *f) { switch(f->type) { case AUDIT_MSGTYPE: - if (entry->rule.listnr != AUDIT_FILTER_TYPE && + if (entry->rule.listnr != AUDIT_FILTER_EXCLUDE && entry->rule.listnr != AUDIT_FILTER_USER) return -EINVAL; break; @@ -929,7 +929,7 @@ static inline int audit_add_rule(struct audit_entry *entry) /* If any of these, don't count towards total */ switch(entry->rule.listnr) { case AUDIT_FILTER_USER: - case AUDIT_FILTER_TYPE: + case AUDIT_FILTER_EXCLUDE: case AUDIT_FILTER_FS: dont_count = 1; } @@ -1011,7 +1011,7 @@ int audit_del_rule(struct audit_entry *entry) /* If any of these, don't count towards total */ switch(entry->rule.listnr) { case AUDIT_FILTER_USER: - case AUDIT_FILTER_TYPE: + case AUDIT_FILTER_EXCLUDE: case AUDIT_FILTER_FS: dont_count = 1; } @@ -1372,7 +1372,7 @@ int audit_filter(int msgtype, unsigned int listtype) break; } if (result > 0) { - if (e->rule.action == AUDIT_NEVER || listtype == AUDIT_FILTER_TYPE) + if (e->rule.action == AUDIT_NEVER || listtype == AUDIT_FILTER_EXCLUDE) ret = 0; break; } -- cgit v1.2.3 From f7859590d97614815b35a755c8213dfb8f2766bd Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Tue, 5 Jun 2018 19:20:39 -0400 Subject: audit: eliminate audit_enabled magic number comparison Remove comparison of audit_enabled to magic numbers outside of audit. Related: https://github.com/linux-audit/audit-kernel/issues/86 Signed-off-by: Richard Guy Briggs Signed-off-by: Paul Moore --- drivers/tty/tty_audit.c | 2 +- include/linux/audit.h | 5 ++++- include/net/xfrm.h | 2 +- kernel/audit.c | 3 --- net/netfilter/xt_AUDIT.c | 2 +- net/netlabel/netlabel_user.c | 2 +- 6 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/drivers/tty/tty_audit.c b/drivers/tty/tty_audit.c index e30aa6bf9ff9..50f567b6a66e 100644 --- a/drivers/tty/tty_audit.c +++ b/drivers/tty/tty_audit.c @@ -92,7 +92,7 @@ static void tty_audit_buf_push(struct tty_audit_buf *buf) { if (buf->valid == 0) return; - if (audit_enabled == 0) { + if (audit_enabled == AUDIT_OFF) { buf->valid = 0; return; } diff --git a/include/linux/audit.h b/include/linux/audit.h index 69c78477590b..9334fbef7bae 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -117,6 +117,9 @@ struct filename; extern void audit_log_session_info(struct audit_buffer *ab); +#define AUDIT_OFF 0 +#define AUDIT_ON 1 +#define AUDIT_LOCKED 2 #ifdef CONFIG_AUDIT /* These are defined in audit.c */ /* Public API */ @@ -202,7 +205,7 @@ static inline int audit_log_task_context(struct audit_buffer *ab) static inline void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk) { } -#define audit_enabled 0 +#define audit_enabled AUDIT_OFF #endif /* CONFIG_AUDIT */ #ifdef CONFIG_AUDIT_COMPAT_GENERIC diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 557122846e0e..f7f297727ed8 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -735,7 +735,7 @@ static inline struct audit_buffer *xfrm_audit_start(const char *op) { struct audit_buffer *audit_buf = NULL; - if (audit_enabled == 0) + if (audit_enabled == AUDIT_OFF) return NULL; audit_buf = audit_log_start(audit_context(), GFP_ATOMIC, AUDIT_MAC_IPSEC_EVENT); diff --git a/kernel/audit.c b/kernel/audit.c index 5c0a1d7b0c7b..0f3222e4edde 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -83,9 +83,6 @@ #define AUDIT_INITIALIZED 1 static int audit_initialized; -#define AUDIT_OFF 0 -#define AUDIT_ON 1 -#define AUDIT_LOCKED 2 u32 audit_enabled = AUDIT_OFF; bool audit_ever_enabled = !!AUDIT_OFF; diff --git a/net/netfilter/xt_AUDIT.c b/net/netfilter/xt_AUDIT.c index f368ee6741db..af883f1b64f9 100644 --- a/net/netfilter/xt_AUDIT.c +++ b/net/netfilter/xt_AUDIT.c @@ -72,7 +72,7 @@ audit_tg(struct sk_buff *skb, const struct xt_action_param *par) struct audit_buffer *ab; int fam = -1; - if (audit_enabled == 0) + if (audit_enabled == AUDIT_OFF) goto errout; ab = audit_log_start(NULL, GFP_ATOMIC, AUDIT_NETFILTER_PKT); if (ab == NULL) diff --git a/net/netlabel/netlabel_user.c b/net/netlabel/netlabel_user.c index 2f328af91a52..4676f5bb16ae 100644 --- a/net/netlabel/netlabel_user.c +++ b/net/netlabel/netlabel_user.c @@ -101,7 +101,7 @@ struct audit_buffer *netlbl_audit_start_common(int type, char *secctx; u32 secctx_len; - if (audit_enabled == 0) + if (audit_enabled == AUDIT_OFF) return NULL; audit_buf = audit_log_start(audit_context(), GFP_ATOMIC, type); -- cgit v1.2.3 From cbaa7f0bdbee1969bb311c641abbd0d2af6ba861 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Mon, 18 Jun 2018 13:29:37 -0500 Subject: ASoC: Intel: move SKL+ codec ACPI tables to common directory No functionality change, just move to common tables to make it easier to deal with SOF and share the same machine drivers - as done previously for BYT/CHT/HSW/BDW. Signed-off-by: Pierre-Louis Bossart Signed-off-by: Mark Brown --- include/sound/soc-acpi-intel-match.h | 5 + sound/soc/intel/common/Makefile | 6 +- sound/soc/intel/common/soc-acpi-intel-bxt-match.c | 35 +++++ sound/soc/intel/common/soc-acpi-intel-cnl-match.c | 29 ++++ sound/soc/intel/common/soc-acpi-intel-glk-match.c | 23 +++ sound/soc/intel/common/soc-acpi-intel-kbl-match.c | 91 ++++++++++++ sound/soc/intel/common/soc-acpi-intel-skl-match.c | 47 +++++++ sound/soc/intel/skylake/skl.c | 162 +--------------------- 8 files changed, 241 insertions(+), 157 deletions(-) create mode 100644 sound/soc/intel/common/soc-acpi-intel-bxt-match.c create mode 100644 sound/soc/intel/common/soc-acpi-intel-cnl-match.c create mode 100644 sound/soc/intel/common/soc-acpi-intel-glk-match.c create mode 100644 sound/soc/intel/common/soc-acpi-intel-kbl-match.c create mode 100644 sound/soc/intel/common/soc-acpi-intel-skl-match.c (limited to 'include') diff --git a/include/sound/soc-acpi-intel-match.h b/include/sound/soc-acpi-intel-match.h index 9da6388c20a1..917ddd0f2762 100644 --- a/include/sound/soc-acpi-intel-match.h +++ b/include/sound/soc-acpi-intel-match.h @@ -29,5 +29,10 @@ extern struct snd_soc_acpi_mach snd_soc_acpi_intel_broadwell_machines[]; extern struct snd_soc_acpi_mach snd_soc_acpi_intel_baytrail_legacy_machines[]; extern struct snd_soc_acpi_mach snd_soc_acpi_intel_baytrail_machines[]; extern struct snd_soc_acpi_mach snd_soc_acpi_intel_cherrytrail_machines[]; +extern struct snd_soc_acpi_mach snd_soc_acpi_intel_skl_machines[]; +extern struct snd_soc_acpi_mach snd_soc_acpi_intel_kbl_machines[]; +extern struct snd_soc_acpi_mach snd_soc_acpi_intel_bxt_machines[]; +extern struct snd_soc_acpi_mach snd_soc_acpi_intel_glk_machines[]; +extern struct snd_soc_acpi_mach snd_soc_acpi_intel_cnl_machines[]; #endif diff --git a/sound/soc/intel/common/Makefile b/sound/soc/intel/common/Makefile index 7379d8830c39..915a34cdc8ac 100644 --- a/sound/soc/intel/common/Makefile +++ b/sound/soc/intel/common/Makefile @@ -3,7 +3,11 @@ snd-soc-sst-dsp-objs := sst-dsp.o snd-soc-sst-acpi-objs := sst-acpi.o snd-soc-sst-ipc-objs := sst-ipc.o snd-soc-sst-firmware-objs := sst-firmware.o -snd-soc-acpi-intel-match-objs := soc-acpi-intel-byt-match.o soc-acpi-intel-cht-match.o soc-acpi-intel-hsw-bdw-match.o +snd-soc-acpi-intel-match-objs := soc-acpi-intel-byt-match.o soc-acpi-intel-cht-match.o \ + soc-acpi-intel-hsw-bdw-match.o \ + soc-acpi-intel-skl-match.o soc-acpi-intel-kbl-match.o \ + soc-acpi-intel-bxt-match.o soc-acpi-intel-glk-match.o \ + soc-acpi-intel-cnl-match.o obj-$(CONFIG_SND_SOC_INTEL_SST) += snd-soc-sst-dsp.o snd-soc-sst-ipc.o obj-$(CONFIG_SND_SOC_INTEL_SST_ACPI) += snd-soc-sst-acpi.o diff --git a/sound/soc/intel/common/soc-acpi-intel-bxt-match.c b/sound/soc/intel/common/soc-acpi-intel-bxt-match.c new file mode 100644 index 000000000000..569f1de97e82 --- /dev/null +++ b/sound/soc/intel/common/soc-acpi-intel-bxt-match.c @@ -0,0 +1,35 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * soc-apci-intel-bxt-match.c - tables and support for BXT ACPI enumeration. + * + * Copyright (c) 2018, Intel Corporation. + * + */ + +#include +#include + +static struct snd_soc_acpi_codecs bxt_codecs = { + .num_codecs = 1, + .codecs = {"MX98357A"} +}; + +struct snd_soc_acpi_mach snd_soc_acpi_intel_bxt_machines[] = { + { + .id = "INT343A", + .drv_name = "bxt_alc298s_i2s", + .fw_filename = "intel/dsp_fw_bxtn.bin", + }, + { + .id = "DLGS7219", + .drv_name = "bxt_da7219_max98357a", + .fw_filename = "intel/dsp_fw_bxtn.bin", + .machine_quirk = snd_soc_acpi_codec_list, + .quirk_data = &bxt_codecs, + }, + {}, +}; +EXPORT_SYMBOL_GPL(snd_soc_acpi_intel_bxt_machines); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("Intel Common ACPI Match module"); diff --git a/sound/soc/intel/common/soc-acpi-intel-cnl-match.c b/sound/soc/intel/common/soc-acpi-intel-cnl-match.c new file mode 100644 index 000000000000..b83ee053d417 --- /dev/null +++ b/sound/soc/intel/common/soc-acpi-intel-cnl-match.c @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * soc-apci-intel-cnl-match.c - tables and support for CNL ACPI enumeration. + * + * Copyright (c) 2018, Intel Corporation. + * + */ + +#include +#include +#include "../skylake/skl.h" + +static struct skl_machine_pdata cnl_pdata = { + .use_tplg_pcm = true, +}; + +struct snd_soc_acpi_mach snd_soc_acpi_intel_cnl_machines[] = { + { + .id = "INT34C2", + .drv_name = "cnl_rt274", + .fw_filename = "intel/dsp_fw_cnl.bin", + .pdata = &cnl_pdata, + }, + {}, +}; +EXPORT_SYMBOL_GPL(snd_soc_acpi_intel_cnl_machines); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("Intel Common ACPI Match module"); diff --git a/sound/soc/intel/common/soc-acpi-intel-glk-match.c b/sound/soc/intel/common/soc-acpi-intel-glk-match.c new file mode 100644 index 000000000000..dee09439e7cb --- /dev/null +++ b/sound/soc/intel/common/soc-acpi-intel-glk-match.c @@ -0,0 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * soc-apci-intel-glk-match.c - tables and support for GLK ACPI enumeration. + * + * Copyright (c) 2018, Intel Corporation. + * + */ + +#include +#include + +struct snd_soc_acpi_mach snd_soc_acpi_intel_glk_machines[] = { + { + .id = "INT343A", + .drv_name = "glk_alc298s_i2s", + .fw_filename = "intel/dsp_fw_glk.bin", + }, + {}, +}; +EXPORT_SYMBOL_GPL(snd_soc_acpi_intel_glk_machines); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("Intel Common ACPI Match module"); diff --git a/sound/soc/intel/common/soc-acpi-intel-kbl-match.c b/sound/soc/intel/common/soc-acpi-intel-kbl-match.c new file mode 100644 index 000000000000..0ee173ca437d --- /dev/null +++ b/sound/soc/intel/common/soc-acpi-intel-kbl-match.c @@ -0,0 +1,91 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * soc-apci-intel-kbl-match.c - tables and support for KBL ACPI enumeration. + * + * Copyright (c) 2018, Intel Corporation. + * + */ + +#include +#include +#include "../skylake/skl.h" + +static struct skl_machine_pdata skl_dmic_data; + +static struct snd_soc_acpi_codecs kbl_codecs = { + .num_codecs = 1, + .codecs = {"10508825"} +}; + +static struct snd_soc_acpi_codecs kbl_poppy_codecs = { + .num_codecs = 1, + .codecs = {"10EC5663"} +}; + +static struct snd_soc_acpi_codecs kbl_5663_5514_codecs = { + .num_codecs = 2, + .codecs = {"10EC5663", "10EC5514"} +}; + +static struct snd_soc_acpi_codecs kbl_7219_98357_codecs = { + .num_codecs = 1, + .codecs = {"MX98357A"} +}; + +struct snd_soc_acpi_mach snd_soc_acpi_intel_kbl_machines[] = { + { + .id = "INT343A", + .drv_name = "kbl_alc286s_i2s", + .fw_filename = "intel/dsp_fw_kbl.bin", + }, + { + .id = "INT343B", + .drv_name = "kbl_n88l25_s4567", + .fw_filename = "intel/dsp_fw_kbl.bin", + .machine_quirk = snd_soc_acpi_codec_list, + .quirk_data = &kbl_codecs, + .pdata = &skl_dmic_data, + }, + { + .id = "MX98357A", + .drv_name = "kbl_n88l25_m98357a", + .fw_filename = "intel/dsp_fw_kbl.bin", + .machine_quirk = snd_soc_acpi_codec_list, + .quirk_data = &kbl_codecs, + .pdata = &skl_dmic_data, + }, + { + .id = "MX98927", + .drv_name = "kbl_r5514_5663_max", + .fw_filename = "intel/dsp_fw_kbl.bin", + .machine_quirk = snd_soc_acpi_codec_list, + .quirk_data = &kbl_5663_5514_codecs, + .pdata = &skl_dmic_data, + }, + { + .id = "MX98927", + .drv_name = "kbl_rt5663_m98927", + .fw_filename = "intel/dsp_fw_kbl.bin", + .machine_quirk = snd_soc_acpi_codec_list, + .quirk_data = &kbl_poppy_codecs, + .pdata = &skl_dmic_data, + }, + { + .id = "10EC5663", + .drv_name = "kbl_rt5663", + .fw_filename = "intel/dsp_fw_kbl.bin", + }, + { + .id = "DLGS7219", + .drv_name = "kbl_da7219_max98357a", + .fw_filename = "intel/dsp_fw_kbl.bin", + .machine_quirk = snd_soc_acpi_codec_list, + .quirk_data = &kbl_7219_98357_codecs, + .pdata = &skl_dmic_data, + }, + {}, +}; +EXPORT_SYMBOL_GPL(snd_soc_acpi_intel_kbl_machines); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("Intel Common ACPI Match module"); diff --git a/sound/soc/intel/common/soc-acpi-intel-skl-match.c b/sound/soc/intel/common/soc-acpi-intel-skl-match.c new file mode 100644 index 000000000000..0c9c0edd35b3 --- /dev/null +++ b/sound/soc/intel/common/soc-acpi-intel-skl-match.c @@ -0,0 +1,47 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * soc-apci-intel-skl-match.c - tables and support for SKL ACPI enumeration. + * + * Copyright (c) 2018, Intel Corporation. + * + */ + +#include +#include +#include "../skylake/skl.h" + +static struct skl_machine_pdata skl_dmic_data; + +static struct snd_soc_acpi_codecs skl_codecs = { + .num_codecs = 1, + .codecs = {"10508825"} +}; + +struct snd_soc_acpi_mach snd_soc_acpi_intel_skl_machines[] = { + { + .id = "INT343A", + .drv_name = "skl_alc286s_i2s", + .fw_filename = "intel/dsp_fw_release.bin", + }, + { + .id = "INT343B", + .drv_name = "skl_n88l25_s4567", + .fw_filename = "intel/dsp_fw_release.bin", + .machine_quirk = snd_soc_acpi_codec_list, + .quirk_data = &skl_codecs, + .pdata = &skl_dmic_data, + }, + { + .id = "MX98357A", + .drv_name = "skl_n88l25_m98357a", + .fw_filename = "intel/dsp_fw_release.bin", + .machine_quirk = snd_soc_acpi_codec_list, + .quirk_data = &skl_codecs, + .pdata = &skl_dmic_data, + }, + {}, +}; +EXPORT_SYMBOL_GPL(snd_soc_acpi_intel_skl_machines); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("Intel Common ACPI Match module"); diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c index 6dec748e8949..670ff9aaca55 100644 --- a/sound/soc/intel/skylake/skl.c +++ b/sound/soc/intel/skylake/skl.c @@ -29,6 +29,7 @@ #include #include #include +#include #include #include #include @@ -36,8 +37,6 @@ #include "skl-sst-dsp.h" #include "skl-sst-ipc.h" -static struct skl_machine_pdata skl_dmic_data; - /* * initialize the PCI registers */ @@ -1026,172 +1025,23 @@ static void skl_remove(struct pci_dev *pci) dev_set_drvdata(&pci->dev, NULL); } -static struct snd_soc_acpi_codecs skl_codecs = { - .num_codecs = 1, - .codecs = {"10508825"} -}; - -static struct snd_soc_acpi_codecs kbl_codecs = { - .num_codecs = 1, - .codecs = {"10508825"} -}; - -static struct snd_soc_acpi_codecs bxt_codecs = { - .num_codecs = 1, - .codecs = {"MX98357A"} -}; - -static struct snd_soc_acpi_codecs kbl_poppy_codecs = { - .num_codecs = 1, - .codecs = {"10EC5663"} -}; - -static struct snd_soc_acpi_codecs kbl_5663_5514_codecs = { - .num_codecs = 2, - .codecs = {"10EC5663", "10EC5514"} -}; - -static struct snd_soc_acpi_codecs kbl_7219_98357_codecs = { - .num_codecs = 1, - .codecs = {"MX98357A"} -}; - -static struct skl_machine_pdata cnl_pdata = { - .use_tplg_pcm = true, -}; - -static struct snd_soc_acpi_mach sst_skl_devdata[] = { - { - .id = "INT343A", - .drv_name = "skl_alc286s_i2s", - .fw_filename = "intel/dsp_fw_release.bin", - }, - { - .id = "INT343B", - .drv_name = "skl_n88l25_s4567", - .fw_filename = "intel/dsp_fw_release.bin", - .machine_quirk = snd_soc_acpi_codec_list, - .quirk_data = &skl_codecs, - .pdata = &skl_dmic_data - }, - { - .id = "MX98357A", - .drv_name = "skl_n88l25_m98357a", - .fw_filename = "intel/dsp_fw_release.bin", - .machine_quirk = snd_soc_acpi_codec_list, - .quirk_data = &skl_codecs, - .pdata = &skl_dmic_data - }, - {} -}; - -static struct snd_soc_acpi_mach sst_bxtp_devdata[] = { - { - .id = "INT343A", - .drv_name = "bxt_alc298s_i2s", - .fw_filename = "intel/dsp_fw_bxtn.bin", - }, - { - .id = "DLGS7219", - .drv_name = "bxt_da7219_max98357a", - .fw_filename = "intel/dsp_fw_bxtn.bin", - .machine_quirk = snd_soc_acpi_codec_list, - .quirk_data = &bxt_codecs, - }, - {} -}; - -static struct snd_soc_acpi_mach sst_kbl_devdata[] = { - { - .id = "INT343A", - .drv_name = "kbl_alc286s_i2s", - .fw_filename = "intel/dsp_fw_kbl.bin", - }, - { - .id = "INT343B", - .drv_name = "kbl_n88l25_s4567", - .fw_filename = "intel/dsp_fw_kbl.bin", - .machine_quirk = snd_soc_acpi_codec_list, - .quirk_data = &kbl_codecs, - .pdata = &skl_dmic_data - }, - { - .id = "MX98357A", - .drv_name = "kbl_n88l25_m98357a", - .fw_filename = "intel/dsp_fw_kbl.bin", - .machine_quirk = snd_soc_acpi_codec_list, - .quirk_data = &kbl_codecs, - .pdata = &skl_dmic_data - }, - { - .id = "MX98927", - .drv_name = "kbl_r5514_5663_max", - .fw_filename = "intel/dsp_fw_kbl.bin", - .machine_quirk = snd_soc_acpi_codec_list, - .quirk_data = &kbl_5663_5514_codecs, - .pdata = &skl_dmic_data - }, - { - .id = "MX98927", - .drv_name = "kbl_rt5663_m98927", - .fw_filename = "intel/dsp_fw_kbl.bin", - .machine_quirk = snd_soc_acpi_codec_list, - .quirk_data = &kbl_poppy_codecs, - .pdata = &skl_dmic_data - }, - { - .id = "10EC5663", - .drv_name = "kbl_rt5663", - .fw_filename = "intel/dsp_fw_kbl.bin", - }, - { - .id = "DLGS7219", - .drv_name = "kbl_da7219_max98357a", - .fw_filename = "intel/dsp_fw_kbl.bin", - .machine_quirk = snd_soc_acpi_codec_list, - .quirk_data = &kbl_7219_98357_codecs, - .pdata = &skl_dmic_data - }, - - {} -}; - -static struct snd_soc_acpi_mach sst_glk_devdata[] = { - { - .id = "INT343A", - .drv_name = "glk_alc298s_i2s", - .fw_filename = "intel/dsp_fw_glk.bin", - }, - {} -}; - -static const struct snd_soc_acpi_mach sst_cnl_devdata[] = { - { - .id = "INT34C2", - .drv_name = "cnl_rt274", - .fw_filename = "intel/dsp_fw_cnl.bin", - .pdata = &cnl_pdata, - }, - {} -}; - /* PCI IDs */ static const struct pci_device_id skl_ids[] = { /* Sunrise Point-LP */ { PCI_DEVICE(0x8086, 0x9d70), - .driver_data = (unsigned long)&sst_skl_devdata}, + .driver_data = (unsigned long)&snd_soc_acpi_intel_skl_machines}, /* BXT-P */ { PCI_DEVICE(0x8086, 0x5a98), - .driver_data = (unsigned long)&sst_bxtp_devdata}, + .driver_data = (unsigned long)&snd_soc_acpi_intel_bxt_machines}, /* KBL */ { PCI_DEVICE(0x8086, 0x9D71), - .driver_data = (unsigned long)&sst_kbl_devdata}, + .driver_data = (unsigned long)&snd_soc_acpi_intel_kbl_machines}, /* GLK */ { PCI_DEVICE(0x8086, 0x3198), - .driver_data = (unsigned long)&sst_glk_devdata}, + .driver_data = (unsigned long)&snd_soc_acpi_intel_glk_machines}, /* CNL */ { PCI_DEVICE(0x8086, 0x9dc8), - .driver_data = (unsigned long)&sst_cnl_devdata}, + .driver_data = (unsigned long)&snd_soc_acpi_intel_cnl_machines}, { 0, } }; MODULE_DEVICE_TABLE(pci, skl_ids); -- cgit v1.2.3 From 9fba738a53dda20e748d6ee240b6c017c8146b4b Mon Sep 17 00:00:00 2001 From: Jerome Brunet Date: Tue, 19 Jun 2018 16:41:41 +0200 Subject: clk: add duty cycle support Add the possibility to apply and query the clock signal duty cycle ratio. This is useful when the duty cycle of the clock signal depends on some other parameters controlled by the clock framework. For example, the duty cycle of a divider may depends on the raw divider setting (ratio = N / div) , which is controlled by the CCF. In such case, going through the pwm framework to control the duty cycle ratio of this clock would be a burden. A clock provider is not required to implement the operation to set and get the duty cycle. If it does not implement .get_duty_cycle(), the ratio is assumed to be 50%. This change also adds a new flag, CLK_DUTY_CYCLE_PARENT. This flag should be used to indicate that a clock, such as gates and muxes, may inherit the duty cycle ratio of its parent clock. If a clock does not provide a get_duty_cycle() callback and has CLK_DUTY_CYCLE_PARENT, then the call will be directly forwarded to its parent clock, if any. For set_duty_cycle(), the clock should also have CLK_SET_RATE_PARENT for the call to be forwarded Signed-off-by: Jerome Brunet Signed-off-by: Michael Turquette Link: lkml.kernel.org/r/20180619144141.8506-1-jbrunet@baylibre.com --- drivers/clk/clk.c | 199 +++++++++++++++++++++++++++++++++++++++++-- include/linux/clk-provider.h | 26 ++++++ include/linux/clk.h | 33 +++++++ include/trace/events/clk.h | 36 ++++++++ 4 files changed, 289 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index 9760b526ca31..b0a2719d86f3 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -68,6 +68,7 @@ struct clk_core { unsigned long max_rate; unsigned long accuracy; int phase; + struct clk_duty duty; struct hlist_head children; struct hlist_node child_node; struct hlist_head clks; @@ -2402,6 +2403,172 @@ int clk_get_phase(struct clk *clk) } EXPORT_SYMBOL_GPL(clk_get_phase); +static void clk_core_reset_duty_cycle_nolock(struct clk_core *core) +{ + /* Assume a default value of 50% */ + core->duty.num = 1; + core->duty.den = 2; +} + +static int clk_core_update_duty_cycle_parent_nolock(struct clk_core *core); + +static int clk_core_update_duty_cycle_nolock(struct clk_core *core) +{ + struct clk_duty *duty = &core->duty; + int ret = 0; + + if (!core->ops->get_duty_cycle) + return clk_core_update_duty_cycle_parent_nolock(core); + + ret = core->ops->get_duty_cycle(core->hw, duty); + if (ret) + goto reset; + + /* Don't trust the clock provider too much */ + if (duty->den == 0 || duty->num > duty->den) { + ret = -EINVAL; + goto reset; + } + + return 0; + +reset: + clk_core_reset_duty_cycle_nolock(core); + return ret; +} + +static int clk_core_update_duty_cycle_parent_nolock(struct clk_core *core) +{ + int ret = 0; + + if (core->parent && + core->flags & CLK_DUTY_CYCLE_PARENT) { + ret = clk_core_update_duty_cycle_nolock(core->parent); + memcpy(&core->duty, &core->parent->duty, sizeof(core->duty)); + } else { + clk_core_reset_duty_cycle_nolock(core); + } + + return ret; +} + +static int clk_core_set_duty_cycle_parent_nolock(struct clk_core *core, + struct clk_duty *duty); + +static int clk_core_set_duty_cycle_nolock(struct clk_core *core, + struct clk_duty *duty) +{ + int ret; + + lockdep_assert_held(&prepare_lock); + + if (clk_core_rate_is_protected(core)) + return -EBUSY; + + trace_clk_set_duty_cycle(core, duty); + + if (!core->ops->set_duty_cycle) + return clk_core_set_duty_cycle_parent_nolock(core, duty); + + ret = core->ops->set_duty_cycle(core->hw, duty); + if (!ret) + memcpy(&core->duty, duty, sizeof(*duty)); + + trace_clk_set_duty_cycle_complete(core, duty); + + return ret; +} + +static int clk_core_set_duty_cycle_parent_nolock(struct clk_core *core, + struct clk_duty *duty) +{ + int ret = 0; + + if (core->parent && + core->flags & (CLK_DUTY_CYCLE_PARENT | CLK_SET_RATE_PARENT)) { + ret = clk_core_set_duty_cycle_nolock(core->parent, duty); + memcpy(&core->duty, &core->parent->duty, sizeof(core->duty)); + } + + return ret; +} + +/** + * clk_set_duty_cycle - adjust the duty cycle ratio of a clock signal + * @clk: clock signal source + * @num: numerator of the duty cycle ratio to be applied + * @den: denominator of the duty cycle ratio to be applied + * + * Apply the duty cycle ratio if the ratio is valid and the clock can + * perform this operation + * + * Returns (0) on success, a negative errno otherwise. + */ +int clk_set_duty_cycle(struct clk *clk, unsigned int num, unsigned int den) +{ + int ret; + struct clk_duty duty; + + if (!clk) + return 0; + + /* sanity check the ratio */ + if (den == 0 || num > den) + return -EINVAL; + + duty.num = num; + duty.den = den; + + clk_prepare_lock(); + + if (clk->exclusive_count) + clk_core_rate_unprotect(clk->core); + + ret = clk_core_set_duty_cycle_nolock(clk->core, &duty); + + if (clk->exclusive_count) + clk_core_rate_protect(clk->core); + + clk_prepare_unlock(); + + return ret; +} +EXPORT_SYMBOL_GPL(clk_set_duty_cycle); + +static int clk_core_get_scaled_duty_cycle(struct clk_core *core, + unsigned int scale) +{ + struct clk_duty *duty = &core->duty; + int ret; + + clk_prepare_lock(); + + ret = clk_core_update_duty_cycle_nolock(core); + if (!ret) + ret = mult_frac(scale, duty->num, duty->den); + + clk_prepare_unlock(); + + return ret; +} + +/** + * clk_get_scaled_duty_cycle - return the duty cycle ratio of a clock signal + * @clk: clock signal source + * @scale: scaling factor to be applied to represent the ratio as an integer + * + * Returns the duty cycle ratio of a clock node multiplied by the provided + * scaling factor, or negative errno on error. + */ +int clk_get_scaled_duty_cycle(struct clk *clk, unsigned int scale) +{ + if (!clk) + return 0; + + return clk_core_get_scaled_duty_cycle(clk->core, scale); +} +EXPORT_SYMBOL_GPL(clk_get_scaled_duty_cycle); + /** * clk_is_match - check if two clk's point to the same hardware clock * @p: clk compared against q @@ -2455,12 +2622,13 @@ static void clk_summary_show_one(struct seq_file *s, struct clk_core *c, if (!c) return; - seq_printf(s, "%*s%-*s %7d %8d %8d %11lu %10lu %-3d\n", + seq_printf(s, "%*s%-*s %7d %8d %8d %11lu %10lu %5d %6d\n", level * 3 + 1, "", 30 - level * 3, c->name, c->enable_count, c->prepare_count, c->protect_count, clk_core_get_rate(c), clk_core_get_accuracy(c), - clk_core_get_phase(c)); + clk_core_get_phase(c), + clk_core_get_scaled_duty_cycle(c, 100000)); } static void clk_summary_show_subtree(struct seq_file *s, struct clk_core *c, @@ -2482,9 +2650,9 @@ static int clk_summary_show(struct seq_file *s, void *data) struct clk_core *c; struct hlist_head **lists = (struct hlist_head **)s->private; - seq_puts(s, " enable prepare protect \n"); - seq_puts(s, " clock count count count rate accuracy phase\n"); - seq_puts(s, "----------------------------------------------------------------------------------------\n"); + seq_puts(s, " enable prepare protect duty\n"); + seq_puts(s, " clock count count count rate accuracy phase cycle\n"); + seq_puts(s, "---------------------------------------------------------------------------------------------\n"); clk_prepare_lock(); @@ -2511,6 +2679,8 @@ static void clk_dump_one(struct seq_file *s, struct clk_core *c, int level) seq_printf(s, "\"rate\": %lu,", clk_core_get_rate(c)); seq_printf(s, "\"accuracy\": %lu,", clk_core_get_accuracy(c)); seq_printf(s, "\"phase\": %d", clk_core_get_phase(c)); + seq_printf(s, "\"duty_cycle\": %u", + clk_core_get_scaled_duty_cycle(c, 100000)); } static void clk_dump_subtree(struct seq_file *s, struct clk_core *c, int level) @@ -2572,6 +2742,7 @@ static const struct { ENTRY(CLK_SET_RATE_UNGATE), ENTRY(CLK_IS_CRITICAL), ENTRY(CLK_OPS_PARENT_ENABLE), + ENTRY(CLK_DUTY_CYCLE_PARENT), #undef ENTRY }; @@ -2610,6 +2781,17 @@ static int possible_parents_show(struct seq_file *s, void *data) } DEFINE_SHOW_ATTRIBUTE(possible_parents); +static int clk_duty_cycle_show(struct seq_file *s, void *data) +{ + struct clk_core *core = s->private; + struct clk_duty *duty = &core->duty; + + seq_printf(s, "%u/%u\n", duty->num, duty->den); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(clk_duty_cycle); + static void clk_debug_create_one(struct clk_core *core, struct dentry *pdentry) { struct dentry *root; @@ -2628,6 +2810,8 @@ static void clk_debug_create_one(struct clk_core *core, struct dentry *pdentry) debugfs_create_u32("clk_enable_count", 0444, root, &core->enable_count); debugfs_create_u32("clk_protect_count", 0444, root, &core->protect_count); debugfs_create_u32("clk_notifier_count", 0444, root, &core->notifier_count); + debugfs_create_file("clk_duty_cycle", 0444, root, core, + &clk_duty_cycle_fops); if (core->num_parents > 1) debugfs_create_file("clk_possible_parents", 0444, root, core, @@ -2845,6 +3029,11 @@ static int __clk_core_init(struct clk_core *core) else core->phase = 0; + /* + * Set clk's duty cycle. + */ + clk_core_update_duty_cycle_nolock(core); + /* * Set clk's rate. The preferred method is to use .recalc_rate. For * simple clocks and lazy developers the default fallback is to use the diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index b7cfa037e593..08b1aa70a38d 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -38,6 +38,8 @@ #define CLK_IS_CRITICAL BIT(11) /* do not gate, ever */ /* parents need enable during gate/ungate, set rate and re-parent */ #define CLK_OPS_PARENT_ENABLE BIT(12) +/* duty cycle call may be forwarded to the parent clock */ +#define CLK_DUTY_CYCLE_PARENT BIT(13) struct clk; struct clk_hw; @@ -66,6 +68,17 @@ struct clk_rate_request { struct clk_hw *best_parent_hw; }; +/** + * struct clk_duty - Struture encoding the duty cycle ratio of a clock + * + * @num: Numerator of the duty cycle ratio + * @den: Denominator of the duty cycle ratio + */ +struct clk_duty { + unsigned int num; + unsigned int den; +}; + /** * struct clk_ops - Callback operations for hardware clocks; these are to * be provided by the clock implementation, and will be called by drivers @@ -169,6 +182,15 @@ struct clk_rate_request { * by the second argument. Valid values for degrees are * 0-359. Return 0 on success, otherwise -EERROR. * + * @get_duty_cycle: Queries the hardware to get the current duty cycle ratio + * of a clock. Returned values denominator cannot be 0 and must be + * superior or equal to the numerator. + * + * @set_duty_cycle: Apply the duty cycle ratio to this clock signal specified by + * the numerator (2nd argurment) and denominator (3rd argument). + * Argument must be a valid ratio (denominator > 0 + * and >= numerator) Return 0 on success, otherwise -EERROR. + * * @init: Perform platform-specific initialization magic. * This is not not used by any of the basic clock types. * Please consider other ways of solving initialization problems @@ -218,6 +240,10 @@ struct clk_ops { unsigned long parent_accuracy); int (*get_phase)(struct clk_hw *hw); int (*set_phase)(struct clk_hw *hw, int degrees); + int (*get_duty_cycle)(struct clk_hw *hw, + struct clk_duty *duty); + int (*set_duty_cycle)(struct clk_hw *hw, + struct clk_duty *duty); void (*init)(struct clk_hw *hw); void (*debug_init)(struct clk_hw *hw, struct dentry *dentry); }; diff --git a/include/linux/clk.h b/include/linux/clk.h index 0dbd0885b2c2..4f750c481b82 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -141,6 +141,27 @@ int clk_set_phase(struct clk *clk, int degrees); */ int clk_get_phase(struct clk *clk); +/** + * clk_set_duty_cycle - adjust the duty cycle ratio of a clock signal + * @clk: clock signal source + * @num: numerator of the duty cycle ratio to be applied + * @den: denominator of the duty cycle ratio to be applied + * + * Adjust the duty cycle of a clock signal by the specified ratio. Returns 0 on + * success, -EERROR otherwise. + */ +int clk_set_duty_cycle(struct clk *clk, unsigned int num, unsigned int den); + +/** + * clk_get_duty_cycle - return the duty cycle ratio of a clock signal + * @clk: clock signal source + * @scale: scaling factor to be applied to represent the ratio as an integer + * + * Returns the duty cycle ratio multiplied by the scale provided, otherwise + * returns -EERROR. + */ +int clk_get_scaled_duty_cycle(struct clk *clk, unsigned int scale); + /** * clk_is_match - check if two clk's point to the same hardware clock * @p: clk compared against q @@ -183,6 +204,18 @@ static inline long clk_get_phase(struct clk *clk) return -ENOTSUPP; } +static inline int clk_set_duty_cycle(struct clk *clk, unsigned int num, + unsigned int den) +{ + return -ENOTSUPP; +} + +static inline unsigned int clk_get_scaled_duty_cycle(struct clk *clk, + unsigned int scale) +{ + return 0; +} + static inline bool clk_is_match(const struct clk *p, const struct clk *q) { return p == q; diff --git a/include/trace/events/clk.h b/include/trace/events/clk.h index 2cd449328aee..9004ffff7f32 100644 --- a/include/trace/events/clk.h +++ b/include/trace/events/clk.h @@ -192,6 +192,42 @@ DEFINE_EVENT(clk_phase, clk_set_phase_complete, TP_ARGS(core, phase) ); +DECLARE_EVENT_CLASS(clk_duty_cycle, + + TP_PROTO(struct clk_core *core, struct clk_duty *duty), + + TP_ARGS(core, duty), + + TP_STRUCT__entry( + __string( name, core->name ) + __field( unsigned int, num ) + __field( unsigned int, den ) + ), + + TP_fast_assign( + __assign_str(name, core->name); + __entry->num = duty->num; + __entry->den = duty->den; + ), + + TP_printk("%s %u/%u", __get_str(name), (unsigned int)__entry->num, + (unsigned int)__entry->den) +); + +DEFINE_EVENT(clk_duty_cycle, clk_set_duty_cycle, + + TP_PROTO(struct clk_core *core, struct clk_duty *duty), + + TP_ARGS(core, duty) +); + +DEFINE_EVENT(clk_duty_cycle, clk_set_duty_cycle_complete, + + TP_PROTO(struct clk_core *core, struct clk_duty *duty), + + TP_ARGS(core, duty) +); + #endif /* _TRACE_CLK_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 19e0c58f6552638c86395f0717210326fdf14fd2 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Tue, 19 Jun 2018 15:10:56 -0700 Subject: iomap: generic inline data handling Add generic inline data handling by adding a pointer to the inline data region to struct iomap. When handling a buffered IOMAP_INLINE write, iomap_write_begin will copy the current inline data from the inline data region into the page cache, and iomap_write_end will copy the changes in the page cache back to the inline data region. This doesn't cover inline data reads and direct I/O yet because so far, we have no users. Signed-off-by: Andreas Gruenbacher [hch: small cleanups to better fit in with other iomap work] Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/iomap.c | 62 +++++++++++++++++++++++++++++++++++++++++++++------ include/linux/iomap.h | 1 + 2 files changed, 56 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/fs/iomap.c b/fs/iomap.c index 9c454459a1e9..4aecd7c5dbd8 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -103,6 +103,26 @@ iomap_sector(struct iomap *iomap, loff_t pos) return (iomap->addr + pos - iomap->offset) >> SECTOR_SHIFT; } +static void +iomap_read_inline_data(struct inode *inode, struct page *page, + struct iomap *iomap) +{ + size_t size = i_size_read(inode); + void *addr; + + if (PageUptodate(page)) + return; + + BUG_ON(page->index); + BUG_ON(size > PAGE_SIZE - offset_in_page(iomap->inline_data)); + + addr = kmap_atomic(page); + memcpy(addr, iomap->inline_data, size); + memset(addr + size, 0, PAGE_SIZE - size); + kunmap_atomic(addr); + SetPageUptodate(page); +} + static void iomap_write_failed(struct inode *inode, loff_t pos, unsigned len) { @@ -133,7 +153,11 @@ iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags, if (!page) return -ENOMEM; - status = __block_write_begin_int(page, pos, len, NULL, iomap); + if (iomap->type == IOMAP_INLINE) + iomap_read_inline_data(inode, page, iomap); + else + status = __block_write_begin_int(page, pos, len, NULL, iomap); + if (unlikely(status)) { unlock_page(page); put_page(page); @@ -146,14 +170,37 @@ iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags, return status; } +static int +iomap_write_end_inline(struct inode *inode, struct page *page, + struct iomap *iomap, loff_t pos, unsigned copied) +{ + void *addr; + + WARN_ON_ONCE(!PageUptodate(page)); + BUG_ON(pos + copied > PAGE_SIZE - offset_in_page(iomap->inline_data)); + + addr = kmap_atomic(page); + memcpy(iomap->inline_data + pos, addr + pos, copied); + kunmap_atomic(addr); + + mark_inode_dirty(inode); + __generic_write_end(inode, pos, copied, page); + return copied; +} + static int iomap_write_end(struct inode *inode, loff_t pos, unsigned len, - unsigned copied, struct page *page) + unsigned copied, struct page *page, struct iomap *iomap) { int ret; - ret = generic_write_end(NULL, inode->i_mapping, pos, len, - copied, page, NULL); + if (iomap->type == IOMAP_INLINE) { + ret = iomap_write_end_inline(inode, page, iomap, pos, copied); + } else { + ret = generic_write_end(NULL, inode->i_mapping, pos, len, + copied, page, NULL); + } + if (ret < len) iomap_write_failed(inode, pos, len); return ret; @@ -208,7 +255,8 @@ again: flush_dcache_page(page); - status = iomap_write_end(inode, pos, bytes, copied, page); + status = iomap_write_end(inode, pos, bytes, copied, page, + iomap); if (unlikely(status < 0)) break; copied = status; @@ -302,7 +350,7 @@ iomap_dirty_actor(struct inode *inode, loff_t pos, loff_t length, void *data, WARN_ON_ONCE(!PageUptodate(page)); - status = iomap_write_end(inode, pos, bytes, bytes, page); + status = iomap_write_end(inode, pos, bytes, bytes, page, iomap); if (unlikely(status <= 0)) { if (WARN_ON_ONCE(status == 0)) return -EIO; @@ -354,7 +402,7 @@ static int iomap_zero(struct inode *inode, loff_t pos, unsigned offset, zero_user(page, offset, bytes); mark_page_accessed(page); - return iomap_write_end(inode, pos, bytes, bytes, page); + return iomap_write_end(inode, pos, bytes, bytes, page, iomap); } static int iomap_dax_zero(loff_t pos, unsigned offset, unsigned bytes, diff --git a/include/linux/iomap.h b/include/linux/iomap.h index a044a824da85..10d6cff7f69a 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -55,6 +55,7 @@ struct iomap { u16 flags; /* flags for mapping */ struct block_device *bdev; /* block device for I/O */ struct dax_device *dax_dev; /* dax_dev for dax operations */ + void *inline_data; }; /* -- cgit v1.2.3 From 63899c6f8851c32214b19390254fa1ae90b582df Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 19 Jun 2018 15:10:56 -0700 Subject: iomap: add a page_done callback This will be used by gfs2 to attach data to transactions for the journaled data mode. But the concept is generic enough that we might be able to use it for other purposes like encryption/integrity post-processing in the future. Based on a patch from Andreas Gruenbacher. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/iomap.c | 3 +++ include/linux/iomap.h | 9 +++++++++ 2 files changed, 12 insertions(+) (limited to 'include') diff --git a/fs/iomap.c b/fs/iomap.c index 4aecd7c5dbd8..a1f71e64ea49 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -201,6 +201,9 @@ iomap_write_end(struct inode *inode, loff_t pos, unsigned len, copied, page, NULL); } + if (iomap->page_done) + iomap->page_done(inode, pos, copied, page, iomap); + if (ret < len) iomap_write_failed(inode, pos, len); return ret; diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 10d6cff7f69a..45f43865b0f0 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -9,6 +9,7 @@ struct fiemap_extent_info; struct inode; struct iov_iter; struct kiocb; +struct page; struct vm_area_struct; struct vm_fault; @@ -56,6 +57,14 @@ struct iomap { struct block_device *bdev; /* block device for I/O */ struct dax_device *dax_dev; /* dax_dev for dax operations */ void *inline_data; + + /* + * Called when finished processing a page in the mapping returned in + * this iomap. At least for now this is only supported in the buffered + * write path. + */ + void (*page_done)(struct inode *inode, loff_t pos, unsigned copied, + struct page *page, struct iomap *iomap); }; /* -- cgit v1.2.3 From e184fde6f3f5353040dd4b5637f823fc87436e55 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Tue, 19 Jun 2018 15:10:57 -0700 Subject: iomap: add private pointer to struct iomap Add a private pointer to struct iomap to allow filesystems to pass data from iomap_begin to iomap_end. Will be used by gfs2 for passing on the on-disk inode buffer head. Signed-off-by: Andreas Gruenbacher Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- include/linux/iomap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 45f43865b0f0..1f36523d448a 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -57,6 +57,7 @@ struct iomap { struct block_device *bdev; /* block device for I/O */ struct dax_device *dax_dev; /* dax_dev for dax operations */ void *inline_data; + void *private; /* filesystem private */ /* * Called when finished processing a page in the mapping returned in -- cgit v1.2.3 From 72b4daa241295440f98e80ae21294a67b27ca091 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 19 Jun 2018 15:10:57 -0700 Subject: iomap: add an iomap-based readpage and readpages implementation Simply use iomap_apply to iterate over the file and a submit a bio for each non-uptodate but mapped region and zero everything else. Note that as-is this can not be used for file systems with a blocksize smaller than the page size, but that support will be added later. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/iomap.c | 214 +++++++++++++++++++++++++++++++++++++++++++++++++- include/linux/iomap.h | 3 + 2 files changed, 216 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/fs/iomap.c b/fs/iomap.c index a1f71e64ea49..4f10c6b1cf6d 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -1,6 +1,6 @@ /* * Copyright (C) 2010 Red Hat, Inc. - * Copyright (c) 2016 Christoph Hellwig. + * Copyright (c) 2016-2018 Christoph Hellwig. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -123,6 +124,217 @@ iomap_read_inline_data(struct inode *inode, struct page *page, SetPageUptodate(page); } +static void +iomap_read_end_io(struct bio *bio) +{ + int error = blk_status_to_errno(bio->bi_status); + struct bio_vec *bvec; + int i; + + bio_for_each_segment_all(bvec, bio, i) + page_endio(bvec->bv_page, false, error); + bio_put(bio); +} + +struct iomap_readpage_ctx { + struct page *cur_page; + bool cur_page_in_bio; + bool is_readahead; + struct bio *bio; + struct list_head *pages; +}; + +static loff_t +iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data, + struct iomap *iomap) +{ + struct iomap_readpage_ctx *ctx = data; + struct page *page = ctx->cur_page; + unsigned poff = pos & (PAGE_SIZE - 1); + unsigned plen = min_t(loff_t, PAGE_SIZE - poff, length); + bool is_contig = false; + sector_t sector; + + /* we don't support blocksize < PAGE_SIZE quite yet. */ + WARN_ON_ONCE(pos != page_offset(page)); + WARN_ON_ONCE(plen != PAGE_SIZE); + + if (iomap->type != IOMAP_MAPPED || pos >= i_size_read(inode)) { + zero_user(page, poff, plen); + SetPageUptodate(page); + goto done; + } + + ctx->cur_page_in_bio = true; + + /* + * Try to merge into a previous segment if we can. + */ + sector = iomap_sector(iomap, pos); + if (ctx->bio && bio_end_sector(ctx->bio) == sector) { + if (__bio_try_merge_page(ctx->bio, page, plen, poff)) + goto done; + is_contig = true; + } + + if (!ctx->bio || !is_contig || bio_full(ctx->bio)) { + gfp_t gfp = mapping_gfp_constraint(page->mapping, GFP_KERNEL); + int nr_vecs = (length + PAGE_SIZE - 1) >> PAGE_SHIFT; + + if (ctx->bio) + submit_bio(ctx->bio); + + if (ctx->is_readahead) /* same as readahead_gfp_mask */ + gfp |= __GFP_NORETRY | __GFP_NOWARN; + ctx->bio = bio_alloc(gfp, min(BIO_MAX_PAGES, nr_vecs)); + ctx->bio->bi_opf = REQ_OP_READ; + if (ctx->is_readahead) + ctx->bio->bi_opf |= REQ_RAHEAD; + ctx->bio->bi_iter.bi_sector = sector; + bio_set_dev(ctx->bio, iomap->bdev); + ctx->bio->bi_end_io = iomap_read_end_io; + } + + __bio_add_page(ctx->bio, page, plen, poff); +done: + return plen; +} + +int +iomap_readpage(struct page *page, const struct iomap_ops *ops) +{ + struct iomap_readpage_ctx ctx = { .cur_page = page }; + struct inode *inode = page->mapping->host; + unsigned poff; + loff_t ret; + + WARN_ON_ONCE(page_has_buffers(page)); + + for (poff = 0; poff < PAGE_SIZE; poff += ret) { + ret = iomap_apply(inode, page_offset(page) + poff, + PAGE_SIZE - poff, 0, ops, &ctx, + iomap_readpage_actor); + if (ret <= 0) { + WARN_ON_ONCE(ret == 0); + SetPageError(page); + break; + } + } + + if (ctx.bio) { + submit_bio(ctx.bio); + WARN_ON_ONCE(!ctx.cur_page_in_bio); + } else { + WARN_ON_ONCE(ctx.cur_page_in_bio); + unlock_page(page); + } + + /* + * Just like mpage_readpages and block_read_full_page we always + * return 0 and just mark the page as PageError on errors. This + * should be cleaned up all through the stack eventually. + */ + return 0; +} +EXPORT_SYMBOL_GPL(iomap_readpage); + +static struct page * +iomap_next_page(struct inode *inode, struct list_head *pages, loff_t pos, + loff_t length, loff_t *done) +{ + while (!list_empty(pages)) { + struct page *page = lru_to_page(pages); + + if (page_offset(page) >= (u64)pos + length) + break; + + list_del(&page->lru); + if (!add_to_page_cache_lru(page, inode->i_mapping, page->index, + GFP_NOFS)) + return page; + + /* + * If we already have a page in the page cache at index we are + * done. Upper layers don't care if it is uptodate after the + * readpages call itself as every page gets checked again once + * actually needed. + */ + *done += PAGE_SIZE; + put_page(page); + } + + return NULL; +} + +static loff_t +iomap_readpages_actor(struct inode *inode, loff_t pos, loff_t length, + void *data, struct iomap *iomap) +{ + struct iomap_readpage_ctx *ctx = data; + loff_t done, ret; + + for (done = 0; done < length; done += ret) { + if (ctx->cur_page && ((pos + done) & (PAGE_SIZE - 1)) == 0) { + if (!ctx->cur_page_in_bio) + unlock_page(ctx->cur_page); + put_page(ctx->cur_page); + ctx->cur_page = NULL; + } + if (!ctx->cur_page) { + ctx->cur_page = iomap_next_page(inode, ctx->pages, + pos, length, &done); + if (!ctx->cur_page) + break; + ctx->cur_page_in_bio = false; + } + ret = iomap_readpage_actor(inode, pos + done, length - done, + ctx, iomap); + } + + return done; +} + +int +iomap_readpages(struct address_space *mapping, struct list_head *pages, + unsigned nr_pages, const struct iomap_ops *ops) +{ + struct iomap_readpage_ctx ctx = { + .pages = pages, + .is_readahead = true, + }; + loff_t pos = page_offset(list_entry(pages->prev, struct page, lru)); + loff_t last = page_offset(list_entry(pages->next, struct page, lru)); + loff_t length = last - pos + PAGE_SIZE, ret = 0; + + while (length > 0) { + ret = iomap_apply(mapping->host, pos, length, 0, ops, + &ctx, iomap_readpages_actor); + if (ret <= 0) { + WARN_ON_ONCE(ret == 0); + goto done; + } + pos += ret; + length -= ret; + } + ret = 0; +done: + if (ctx.bio) + submit_bio(ctx.bio); + if (ctx.cur_page) { + if (!ctx.cur_page_in_bio) + unlock_page(ctx.cur_page); + put_page(ctx.cur_page); + } + + /* + * Check that we didn't lose a page due to the arcance calling + * conventions.. + */ + WARN_ON_ONCE(!ret && !list_empty(ctx.pages)); + return ret; +} +EXPORT_SYMBOL_GPL(iomap_readpages); + static void iomap_write_failed(struct inode *inode, loff_t pos, unsigned len) { diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 1f36523d448a..30d314407f66 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -99,6 +99,9 @@ struct iomap_ops { ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from, const struct iomap_ops *ops); +int iomap_readpage(struct page *page, const struct iomap_ops *ops); +int iomap_readpages(struct address_space *mapping, struct list_head *pages, + unsigned nr_pages, const struct iomap_ops *ops); int iomap_file_dirty(struct inode *inode, loff_t pos, loff_t len, const struct iomap_ops *ops); int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, -- cgit v1.2.3 From 83c2b54b9295a5fc0d9c8f1751aaf8099d1760f6 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 12 Jun 2018 12:05:43 -0700 Subject: scsi: target: Abstract tag freeing Introduce target_free_tag() and convert all drivers to use it. Signed-off-by: Matthew Wilcox Reviewed-by: Jens Axboe Signed-off-by: Martin K. Petersen --- drivers/scsi/qla2xxx/qla_target.c | 4 ++-- drivers/target/iscsi/iscsi_target_util.c | 2 +- drivers/target/sbp/sbp_target.c | 2 +- drivers/target/tcm_fc/tfc_cmd.c | 4 ++-- drivers/usb/gadget/function/f_tcm.c | 2 +- drivers/vhost/scsi.c | 2 +- drivers/xen/xen-scsiback.c | 4 +--- include/target/target_core_base.h | 5 +++++ 8 files changed, 14 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 0fea2e2326be..11274317118a 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -3783,7 +3783,7 @@ void qlt_free_cmd(struct qla_tgt_cmd *cmd) return; } cmd->jiffies_at_free = get_jiffies_64(); - percpu_ida_free(&sess->se_sess->sess_tag_pool, cmd->se_cmd.map_tag); + target_free_tag(sess->se_sess, &cmd->se_cmd); } EXPORT_SYMBOL(qlt_free_cmd); @@ -4146,7 +4146,7 @@ out_term: qlt_send_term_exchange(qpair, NULL, &cmd->atio, 1, 0); qlt_decr_num_pend_cmds(vha); - percpu_ida_free(&sess->se_sess->sess_tag_pool, cmd->se_cmd.map_tag); + target_free_tag(sess->se_sess, &cmd->se_cmd); spin_unlock_irqrestore(qpair->qp_lock_ptr, flags); spin_lock_irqsave(&ha->tgt.sess_lock, flags); diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c index 4435bf374d2d..7e98697cfb8e 100644 --- a/drivers/target/iscsi/iscsi_target_util.c +++ b/drivers/target/iscsi/iscsi_target_util.c @@ -711,7 +711,7 @@ void iscsit_release_cmd(struct iscsi_cmd *cmd) kfree(cmd->iov_data); kfree(cmd->text_in_ptr); - percpu_ida_free(&sess->se_sess->sess_tag_pool, se_cmd->map_tag); + target_free_tag(sess->se_sess, se_cmd); } EXPORT_SYMBOL(iscsit_release_cmd); diff --git a/drivers/target/sbp/sbp_target.c b/drivers/target/sbp/sbp_target.c index fb1003921d85..679ae29d25ab 100644 --- a/drivers/target/sbp/sbp_target.c +++ b/drivers/target/sbp/sbp_target.c @@ -1460,7 +1460,7 @@ static void sbp_free_request(struct sbp_target_request *req) kfree(req->pg_tbl); kfree(req->cmd_buf); - percpu_ida_free(&se_sess->sess_tag_pool, se_cmd->map_tag); + target_free_tag(se_sess, se_cmd); } static void sbp_mgt_agent_process(struct work_struct *work) diff --git a/drivers/target/tcm_fc/tfc_cmd.c b/drivers/target/tcm_fc/tfc_cmd.c index ec372860106f..13e4efbe1ce7 100644 --- a/drivers/target/tcm_fc/tfc_cmd.c +++ b/drivers/target/tcm_fc/tfc_cmd.c @@ -92,7 +92,7 @@ static void ft_free_cmd(struct ft_cmd *cmd) if (fr_seq(fp)) fc_seq_release(fr_seq(fp)); fc_frame_free(fp); - percpu_ida_free(&sess->se_sess->sess_tag_pool, cmd->se_cmd.map_tag); + target_free_tag(sess->se_sess, &cmd->se_cmd); ft_sess_put(sess); /* undo get from lookup at recv */ } @@ -461,7 +461,7 @@ static void ft_recv_cmd(struct ft_sess *sess, struct fc_frame *fp) cmd->sess = sess; cmd->seq = fc_seq_assign(lport, fp); if (!cmd->seq) { - percpu_ida_free(&se_sess->sess_tag_pool, tag); + target_free_tag(se_sess, &cmd->se_cmd); goto busy; } cmd->req_frame = fp; /* hold frame during cmd */ diff --git a/drivers/usb/gadget/function/f_tcm.c b/drivers/usb/gadget/function/f_tcm.c index d78dbb73bde8..9f670d9224b9 100644 --- a/drivers/usb/gadget/function/f_tcm.c +++ b/drivers/usb/gadget/function/f_tcm.c @@ -1288,7 +1288,7 @@ static void usbg_release_cmd(struct se_cmd *se_cmd) struct se_session *se_sess = se_cmd->se_sess; kfree(cmd->data_buf); - percpu_ida_free(&se_sess->sess_tag_pool, se_cmd->map_tag); + target_free_tag(se_sess, se_cmd); } static u32 usbg_sess_get_index(struct se_session *se_sess) diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index 17fcd3b2e686..7aaf0e5512ed 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -324,7 +324,7 @@ static void vhost_scsi_release_cmd(struct se_cmd *se_cmd) } vhost_scsi_put_inflight(tv_cmd->inflight); - percpu_ida_free(&se_sess->sess_tag_pool, se_cmd->map_tag); + target_free_tag(se_sess, se_cmd); } static u32 vhost_scsi_sess_get_index(struct se_session *se_sess) diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c index 7bc88fd43cfc..ec6635258ed8 100644 --- a/drivers/xen/xen-scsiback.c +++ b/drivers/xen/xen-scsiback.c @@ -1377,9 +1377,7 @@ static int scsiback_check_stop_free(struct se_cmd *se_cmd) static void scsiback_release_cmd(struct se_cmd *se_cmd) { - struct se_session *se_sess = se_cmd->se_sess; - - percpu_ida_free(&se_sess->sess_tag_pool, se_cmd->map_tag); + target_free_tag(se_cmd->se_sess, se_cmd); } static u32 scsiback_sess_get_index(struct se_session *se_sess) diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index 922a39f45abc..260c2f3e9460 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -934,4 +934,9 @@ static inline void atomic_dec_mb(atomic_t *v) smp_mb__after_atomic(); } +static inline void target_free_tag(struct se_session *sess, struct se_cmd *cmd) +{ + percpu_ida_free(&sess->sess_tag_pool, cmd->map_tag); +} + #endif /* TARGET_CORE_BASE_H */ -- cgit v1.2.3 From 10e9cbb6b531117be0c4a79f2c7fa9a45a0dd532 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 12 Jun 2018 12:05:44 -0700 Subject: scsi: target: Convert target drivers to use sbitmap The sbitmap and the percpu_ida perform essentially the same task, allocating tags for commands. The sbitmap outperforms the percpu_ida as documented here: https://lkml.org/lkml/2014/4/22/553 The sbitmap interface is a little harder to use, but being able to remove the percpu_ida code and getting better performance justifies the additional complexity. Signed-off-by: Matthew Wilcox Acked-by: Felipe Balbi # f_tcm Reviewed-by: Jens Axboe Signed-off-by: Martin K. Petersen --- drivers/scsi/qla2xxx/qla_target.c | 10 ++++++---- drivers/target/iscsi/iscsi_target_util.c | 33 +++++++++++++++++++++++++++++--- drivers/target/sbp/sbp_target.c | 5 +++-- drivers/target/target_core_transport.c | 5 +++-- drivers/target/tcm_fc/tfc_cmd.c | 6 +++--- drivers/usb/gadget/function/f_tcm.c | 5 +++-- drivers/vhost/scsi.c | 6 +++--- drivers/xen/xen-scsiback.c | 5 +++-- include/target/iscsi/iscsi_target_core.h | 1 + include/target/target_core_base.h | 7 ++++--- 10 files changed, 59 insertions(+), 24 deletions(-) (limited to 'include') diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 11274317118a..3de11153d1d3 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -4277,9 +4277,9 @@ static struct qla_tgt_cmd *qlt_get_tag(scsi_qla_host_t *vha, { struct se_session *se_sess = sess->se_sess; struct qla_tgt_cmd *cmd; - int tag; + int tag, cpu; - tag = percpu_ida_alloc(&se_sess->sess_tag_pool, TASK_RUNNING); + tag = sbitmap_queue_get(&se_sess->sess_tag_pool, &cpu); if (tag < 0) return NULL; @@ -4292,6 +4292,7 @@ static struct qla_tgt_cmd *qlt_get_tag(scsi_qla_host_t *vha, qlt_incr_num_pend_cmds(vha); cmd->vha = vha; cmd->se_cmd.map_tag = tag; + cmd->se_cmd.map_cpu = cpu; cmd->sess = sess; cmd->loop_id = sess->loop_id; cmd->conf_compl_supported = sess->conf_compl_supported; @@ -5294,7 +5295,7 @@ qlt_alloc_qfull_cmd(struct scsi_qla_host *vha, struct fc_port *sess; struct se_session *se_sess; struct qla_tgt_cmd *cmd; - int tag; + int tag, cpu; unsigned long flags; if (unlikely(tgt->tgt_stop)) { @@ -5326,7 +5327,7 @@ qlt_alloc_qfull_cmd(struct scsi_qla_host *vha, se_sess = sess->se_sess; - tag = percpu_ida_alloc(&se_sess->sess_tag_pool, TASK_RUNNING); + tag = sbitmap_queue_get(&se_sess->sess_tag_pool, &cpu); if (tag < 0) return; @@ -5357,6 +5358,7 @@ qlt_alloc_qfull_cmd(struct scsi_qla_host *vha, cmd->reset_count = ha->base_qpair->chip_reset; cmd->q_full = 1; cmd->qpair = ha->base_qpair; + cmd->se_cmd.map_cpu = cpu; if (qfull) { cmd->q_full = 1; diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c index 7e98697cfb8e..8cfcf9033507 100644 --- a/drivers/target/iscsi/iscsi_target_util.c +++ b/drivers/target/iscsi/iscsi_target_util.c @@ -17,7 +17,7 @@ ******************************************************************************/ #include -#include +#include #include /* ipv6_addr_equal() */ #include #include @@ -147,6 +147,30 @@ void iscsit_free_r2ts_from_list(struct iscsi_cmd *cmd) spin_unlock_bh(&cmd->r2t_lock); } +static int iscsit_wait_for_tag(struct se_session *se_sess, int state, int *cpup) +{ + int tag = -1; + DEFINE_WAIT(wait); + struct sbq_wait_state *ws; + + if (state == TASK_RUNNING) + return tag; + + ws = &se_sess->sess_tag_pool.ws[0]; + for (;;) { + prepare_to_wait_exclusive(&ws->wait, &wait, state); + if (signal_pending_state(state, current)) + break; + tag = sbitmap_queue_get(&se_sess->sess_tag_pool, cpup); + if (tag >= 0) + break; + schedule(); + } + + finish_wait(&ws->wait, &wait); + return tag; +} + /* * May be called from software interrupt (timer) context for allocating * iSCSI NopINs. @@ -155,9 +179,11 @@ struct iscsi_cmd *iscsit_allocate_cmd(struct iscsi_conn *conn, int state) { struct iscsi_cmd *cmd; struct se_session *se_sess = conn->sess->se_sess; - int size, tag; + int size, tag, cpu; - tag = percpu_ida_alloc(&se_sess->sess_tag_pool, state); + tag = sbitmap_queue_get(&se_sess->sess_tag_pool, &cpu); + if (tag < 0) + tag = iscsit_wait_for_tag(se_sess, state, &cpu); if (tag < 0) return NULL; @@ -166,6 +192,7 @@ struct iscsi_cmd *iscsit_allocate_cmd(struct iscsi_conn *conn, int state) memset(cmd, 0, size); cmd->se_cmd.map_tag = tag; + cmd->se_cmd.map_cpu = cpu; cmd->conn = conn; cmd->data_direction = DMA_NONE; INIT_LIST_HEAD(&cmd->i_conn_node); diff --git a/drivers/target/sbp/sbp_target.c b/drivers/target/sbp/sbp_target.c index 679ae29d25ab..42b21f2ac8b0 100644 --- a/drivers/target/sbp/sbp_target.c +++ b/drivers/target/sbp/sbp_target.c @@ -926,15 +926,16 @@ static struct sbp_target_request *sbp_mgt_get_req(struct sbp_session *sess, { struct se_session *se_sess = sess->se_sess; struct sbp_target_request *req; - int tag; + int tag, cpu; - tag = percpu_ida_alloc(&se_sess->sess_tag_pool, TASK_RUNNING); + tag = sbitmap_queue_get(&se_sess->sess_tag_pool, &cpu); if (tag < 0) return ERR_PTR(-ENOMEM); req = &((struct sbp_target_request *)se_sess->sess_cmd_map)[tag]; memset(req, 0, sizeof(*req)); req->se_cmd.map_tag = tag; + req->se_cmd.map_cpu = cpu; req->se_cmd.tag = next_orb; return req; diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index ee5081ba5313..89dd475d0a8f 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -260,7 +260,8 @@ int transport_alloc_session_tags(struct se_session *se_sess, } } - rc = percpu_ida_init(&se_sess->sess_tag_pool, tag_num); + rc = sbitmap_queue_init_node(&se_sess->sess_tag_pool, tag_num, -1, + false, GFP_KERNEL, NUMA_NO_NODE); if (rc < 0) { pr_err("Unable to init se_sess->sess_tag_pool," " tag_num: %u\n", tag_num); @@ -547,7 +548,7 @@ void transport_free_session(struct se_session *se_sess) target_put_nacl(se_nacl); } if (se_sess->sess_cmd_map) { - percpu_ida_destroy(&se_sess->sess_tag_pool); + sbitmap_queue_free(&se_sess->sess_tag_pool); kvfree(se_sess->sess_cmd_map); } kmem_cache_free(se_sess_cache, se_sess); diff --git a/drivers/target/tcm_fc/tfc_cmd.c b/drivers/target/tcm_fc/tfc_cmd.c index 13e4efbe1ce7..a183d4da7db2 100644 --- a/drivers/target/tcm_fc/tfc_cmd.c +++ b/drivers/target/tcm_fc/tfc_cmd.c @@ -28,7 +28,6 @@ #include #include #include -#include #include #include #include @@ -448,9 +447,9 @@ static void ft_recv_cmd(struct ft_sess *sess, struct fc_frame *fp) struct ft_cmd *cmd; struct fc_lport *lport = sess->tport->lport; struct se_session *se_sess = sess->se_sess; - int tag; + int tag, cpu; - tag = percpu_ida_alloc(&se_sess->sess_tag_pool, TASK_RUNNING); + tag = sbitmap_queue_get(&se_sess->sess_tag_pool, &cpu); if (tag < 0) goto busy; @@ -458,6 +457,7 @@ static void ft_recv_cmd(struct ft_sess *sess, struct fc_frame *fp) memset(cmd, 0, sizeof(struct ft_cmd)); cmd->se_cmd.map_tag = tag; + cmd->se_cmd.map_cpu = cpu; cmd->sess = sess; cmd->seq = fc_seq_assign(lport, fp); if (!cmd->seq) { diff --git a/drivers/usb/gadget/function/f_tcm.c b/drivers/usb/gadget/function/f_tcm.c index 9f670d9224b9..5003e857dce7 100644 --- a/drivers/usb/gadget/function/f_tcm.c +++ b/drivers/usb/gadget/function/f_tcm.c @@ -1071,15 +1071,16 @@ static struct usbg_cmd *usbg_get_cmd(struct f_uas *fu, { struct se_session *se_sess = tv_nexus->tvn_se_sess; struct usbg_cmd *cmd; - int tag; + int tag, cpu; - tag = percpu_ida_alloc(&se_sess->sess_tag_pool, TASK_RUNNING); + tag = sbitmap_queue_get(&se_sess->sess_tag_pool, &cpu); if (tag < 0) return ERR_PTR(-ENOMEM); cmd = &((struct usbg_cmd *)se_sess->sess_cmd_map)[tag]; memset(cmd, 0, sizeof(*cmd)); cmd->se_cmd.map_tag = tag; + cmd->se_cmd.map_cpu = cpu; cmd->se_cmd.tag = cmd->tag = scsi_tag; cmd->fu = fu; diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index 7aaf0e5512ed..ebaf831285ea 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -46,7 +46,6 @@ #include #include #include -#include #include "vhost.h" @@ -567,7 +566,7 @@ vhost_scsi_get_tag(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg, struct se_session *se_sess; struct scatterlist *sg, *prot_sg; struct page **pages; - int tag; + int tag, cpu; tv_nexus = tpg->tpg_nexus; if (!tv_nexus) { @@ -576,7 +575,7 @@ vhost_scsi_get_tag(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg, } se_sess = tv_nexus->tvn_se_sess; - tag = percpu_ida_alloc(&se_sess->sess_tag_pool, TASK_RUNNING); + tag = sbitmap_queue_get(&se_sess->sess_tag_pool, &cpu); if (tag < 0) { pr_err("Unable to obtain tag for vhost_scsi_cmd\n"); return ERR_PTR(-ENOMEM); @@ -591,6 +590,7 @@ vhost_scsi_get_tag(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg, cmd->tvc_prot_sgl = prot_sg; cmd->tvc_upages = pages; cmd->tvc_se_cmd.map_tag = tag; + cmd->tvc_se_cmd.map_cpu = cpu; cmd->tvc_tag = scsi_tag; cmd->tvc_lun = lun; cmd->tvc_task_attr = task_attr; diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c index ec6635258ed8..764dd9aa0131 100644 --- a/drivers/xen/xen-scsiback.c +++ b/drivers/xen/xen-scsiback.c @@ -654,9 +654,9 @@ static struct vscsibk_pend *scsiback_get_pend_req(struct vscsiif_back_ring *ring struct scsiback_nexus *nexus = tpg->tpg_nexus; struct se_session *se_sess = nexus->tvn_se_sess; struct vscsibk_pend *req; - int tag, i; + int tag, cpu, i; - tag = percpu_ida_alloc(&se_sess->sess_tag_pool, TASK_RUNNING); + tag = sbitmap_queue_get(&se_sess->sess_tag_pool, &cpu); if (tag < 0) { pr_err("Unable to obtain tag for vscsiif_request\n"); return ERR_PTR(-ENOMEM); @@ -665,6 +665,7 @@ static struct vscsibk_pend *scsiback_get_pend_req(struct vscsiif_back_ring *ring req = &((struct vscsibk_pend *)se_sess->sess_cmd_map)[tag]; memset(req, 0, sizeof(*req)); req->se_cmd.map_tag = tag; + req->se_cmd.map_cpu = cpu; for (i = 0; i < VSCSI_MAX_GRANTS; i++) req->grant_handles[i] = SCSIBACK_INVALID_HANDLE; diff --git a/include/target/iscsi/iscsi_target_core.h b/include/target/iscsi/iscsi_target_core.h index cf5f3fff1f1a..f2e6abea8490 100644 --- a/include/target/iscsi/iscsi_target_core.h +++ b/include/target/iscsi/iscsi_target_core.h @@ -4,6 +4,7 @@ #include /* enum dma_data_direction */ #include /* struct list_head */ +#include #include /* struct sockaddr_storage */ #include /* u8 */ #include /* itt_t */ diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index 260c2f3e9460..448f291125c2 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -4,7 +4,7 @@ #include /* struct config_group */ #include /* enum dma_data_direction */ -#include /* struct percpu_ida */ +#include #include #include /* struct semaphore */ #include @@ -455,6 +455,7 @@ struct se_cmd { int sam_task_attr; /* Used for se_sess->sess_tag_pool */ unsigned int map_tag; + int map_cpu; /* Transport protocol dependent state, see transport_state_table */ enum transport_state_table t_state; /* See se_cmd_flags_table */ @@ -608,7 +609,7 @@ struct se_session { struct list_head sess_wait_list; spinlock_t sess_cmd_lock; void *sess_cmd_map; - struct percpu_ida sess_tag_pool; + struct sbitmap_queue sess_tag_pool; }; struct se_device; @@ -936,7 +937,7 @@ static inline void atomic_dec_mb(atomic_t *v) static inline void target_free_tag(struct se_session *sess, struct se_cmd *cmd) { - percpu_ida_free(&sess->sess_tag_pool, cmd->map_tag); + sbitmap_queue_clear(&sess->sess_tag_pool, cmd->map_tag, cmd->map_cpu); } #endif /* TARGET_CORE_BASE_H */ -- cgit v1.2.3 From 693ba15c9202fe0283404abe4066e1b986e284eb Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 12 Jun 2018 12:05:45 -0700 Subject: scsi: Remove percpu_ida With its one user gone, remove the library code. Signed-off-by: Matthew Wilcox Reviewed-by: Jens Axboe Signed-off-by: Martin K. Petersen --- include/linux/percpu_ida.h | 83 ---------- lib/Makefile | 2 +- lib/percpu_ida.c | 370 --------------------------------------------- 3 files changed, 1 insertion(+), 454 deletions(-) delete mode 100644 include/linux/percpu_ida.h delete mode 100644 lib/percpu_ida.c (limited to 'include') diff --git a/include/linux/percpu_ida.h b/include/linux/percpu_ida.h deleted file mode 100644 index 07d78e4653bc..000000000000 --- a/include/linux/percpu_ida.h +++ /dev/null @@ -1,83 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __PERCPU_IDA_H__ -#define __PERCPU_IDA_H__ - -#include -#include -#include -#include -#include -#include -#include - -struct percpu_ida_cpu; - -struct percpu_ida { - /* - * number of tags available to be allocated, as passed to - * percpu_ida_init() - */ - unsigned nr_tags; - unsigned percpu_max_size; - unsigned percpu_batch_size; - - struct percpu_ida_cpu __percpu *tag_cpu; - - /* - * Bitmap of cpus that (may) have tags on their percpu freelists: - * steal_tags() uses this to decide when to steal tags, and which cpus - * to try stealing from. - * - * It's ok for a freelist to be empty when its bit is set - steal_tags() - * will just keep looking - but the bitmap _must_ be set whenever a - * percpu freelist does have tags. - */ - cpumask_t cpus_have_tags; - - struct { - spinlock_t lock; - /* - * When we go to steal tags from another cpu (see steal_tags()), - * we want to pick a cpu at random. Cycling through them every - * time we steal is a bit easier and more or less equivalent: - */ - unsigned cpu_last_stolen; - - /* For sleeping on allocation failure */ - wait_queue_head_t wait; - - /* - * Global freelist - it's a stack where nr_free points to the - * top - */ - unsigned nr_free; - unsigned *freelist; - } ____cacheline_aligned_in_smp; -}; - -/* - * Number of tags we move between the percpu freelist and the global freelist at - * a time - */ -#define IDA_DEFAULT_PCPU_BATCH_MOVE 32U -/* Max size of percpu freelist, */ -#define IDA_DEFAULT_PCPU_SIZE ((IDA_DEFAULT_PCPU_BATCH_MOVE * 3) / 2) - -int percpu_ida_alloc(struct percpu_ida *pool, int state); -void percpu_ida_free(struct percpu_ida *pool, unsigned tag); - -void percpu_ida_destroy(struct percpu_ida *pool); -int __percpu_ida_init(struct percpu_ida *pool, unsigned long nr_tags, - unsigned long max_size, unsigned long batch_size); -static inline int percpu_ida_init(struct percpu_ida *pool, unsigned long nr_tags) -{ - return __percpu_ida_init(pool, nr_tags, IDA_DEFAULT_PCPU_SIZE, - IDA_DEFAULT_PCPU_BATCH_MOVE); -} - -typedef int (*percpu_ida_cb)(unsigned, void *); -int percpu_ida_for_each_free(struct percpu_ida *pool, percpu_ida_cb fn, - void *data); - -unsigned percpu_ida_free_tags(struct percpu_ida *pool, int cpu); -#endif /* __PERCPU_IDA_H__ */ diff --git a/lib/Makefile b/lib/Makefile index 956b320292fe..055420101965 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -40,7 +40,7 @@ obj-y += bcd.o div64.o sort.o parser.o debug_locks.o random32.o \ bust_spinlocks.o kasprintf.o bitmap.o scatterlist.o \ gcd.o lcm.o list_sort.o uuid.o flex_array.o iov_iter.o clz_ctz.o \ bsearch.o find_bit.o llist.o memweight.o kfifo.o \ - percpu-refcount.o percpu_ida.o rhashtable.o reciprocal_div.o \ + percpu-refcount.o rhashtable.o reciprocal_div.o \ once.o refcount.o usercopy.o errseq.o bucket_locks.o obj-$(CONFIG_STRING_SELFTEST) += test_string.o obj-y += string_helpers.o diff --git a/lib/percpu_ida.c b/lib/percpu_ida.c deleted file mode 100644 index 9bbd9c5d375a..000000000000 --- a/lib/percpu_ida.c +++ /dev/null @@ -1,370 +0,0 @@ -/* - * Percpu IDA library - * - * Copyright (C) 2013 Datera, Inc. Kent Overstreet - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation; either version 2, or (at - * your option) any later version. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -struct percpu_ida_cpu { - /* - * Even though this is percpu, we need a lock for tag stealing by remote - * CPUs: - */ - spinlock_t lock; - - /* nr_free/freelist form a stack of free IDs */ - unsigned nr_free; - unsigned freelist[]; -}; - -static inline void move_tags(unsigned *dst, unsigned *dst_nr, - unsigned *src, unsigned *src_nr, - unsigned nr) -{ - *src_nr -= nr; - memcpy(dst + *dst_nr, src + *src_nr, sizeof(unsigned) * nr); - *dst_nr += nr; -} - -/* - * Try to steal tags from a remote cpu's percpu freelist. - * - * We first check how many percpu freelists have tags - * - * Then we iterate through the cpus until we find some tags - we don't attempt - * to find the "best" cpu to steal from, to keep cacheline bouncing to a - * minimum. - */ -static inline void steal_tags(struct percpu_ida *pool, - struct percpu_ida_cpu *tags) -{ - unsigned cpus_have_tags, cpu = pool->cpu_last_stolen; - struct percpu_ida_cpu *remote; - - for (cpus_have_tags = cpumask_weight(&pool->cpus_have_tags); - cpus_have_tags; cpus_have_tags--) { - cpu = cpumask_next(cpu, &pool->cpus_have_tags); - - if (cpu >= nr_cpu_ids) { - cpu = cpumask_first(&pool->cpus_have_tags); - if (cpu >= nr_cpu_ids) - BUG(); - } - - pool->cpu_last_stolen = cpu; - remote = per_cpu_ptr(pool->tag_cpu, cpu); - - cpumask_clear_cpu(cpu, &pool->cpus_have_tags); - - if (remote == tags) - continue; - - spin_lock(&remote->lock); - - if (remote->nr_free) { - memcpy(tags->freelist, - remote->freelist, - sizeof(unsigned) * remote->nr_free); - - tags->nr_free = remote->nr_free; - remote->nr_free = 0; - } - - spin_unlock(&remote->lock); - - if (tags->nr_free) - break; - } -} - -/* - * Pop up to IDA_PCPU_BATCH_MOVE IDs off the global freelist, and push them onto - * our percpu freelist: - */ -static inline void alloc_global_tags(struct percpu_ida *pool, - struct percpu_ida_cpu *tags) -{ - move_tags(tags->freelist, &tags->nr_free, - pool->freelist, &pool->nr_free, - min(pool->nr_free, pool->percpu_batch_size)); -} - -/** - * percpu_ida_alloc - allocate a tag - * @pool: pool to allocate from - * @state: task state for prepare_to_wait - * - * Returns a tag - an integer in the range [0..nr_tags) (passed to - * tag_pool_init()), or otherwise -ENOSPC on allocation failure. - * - * Safe to be called from interrupt context (assuming it isn't passed - * TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE, of course). - * - * @gfp indicates whether or not to wait until a free id is available (it's not - * used for internal memory allocations); thus if passed __GFP_RECLAIM we may sleep - * however long it takes until another thread frees an id (same semantics as a - * mempool). - * - * Will not fail if passed TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE. - */ -int percpu_ida_alloc(struct percpu_ida *pool, int state) -{ - DEFINE_WAIT(wait); - struct percpu_ida_cpu *tags; - unsigned long flags; - int tag = -ENOSPC; - - tags = raw_cpu_ptr(pool->tag_cpu); - spin_lock_irqsave(&tags->lock, flags); - - /* Fastpath */ - if (likely(tags->nr_free >= 0)) { - tag = tags->freelist[--tags->nr_free]; - spin_unlock_irqrestore(&tags->lock, flags); - return tag; - } - spin_unlock_irqrestore(&tags->lock, flags); - - while (1) { - spin_lock_irqsave(&pool->lock, flags); - tags = this_cpu_ptr(pool->tag_cpu); - - /* - * prepare_to_wait() must come before steal_tags(), in case - * percpu_ida_free() on another cpu flips a bit in - * cpus_have_tags - * - * global lock held and irqs disabled, don't need percpu lock - */ - if (state != TASK_RUNNING) - prepare_to_wait(&pool->wait, &wait, state); - - if (!tags->nr_free) - alloc_global_tags(pool, tags); - if (!tags->nr_free) - steal_tags(pool, tags); - - if (tags->nr_free) { - tag = tags->freelist[--tags->nr_free]; - if (tags->nr_free) - cpumask_set_cpu(smp_processor_id(), - &pool->cpus_have_tags); - } - - spin_unlock_irqrestore(&pool->lock, flags); - - if (tag >= 0 || state == TASK_RUNNING) - break; - - if (signal_pending_state(state, current)) { - tag = -ERESTARTSYS; - break; - } - - schedule(); - } - if (state != TASK_RUNNING) - finish_wait(&pool->wait, &wait); - - return tag; -} -EXPORT_SYMBOL_GPL(percpu_ida_alloc); - -/** - * percpu_ida_free - free a tag - * @pool: pool @tag was allocated from - * @tag: a tag previously allocated with percpu_ida_alloc() - * - * Safe to be called from interrupt context. - */ -void percpu_ida_free(struct percpu_ida *pool, unsigned tag) -{ - struct percpu_ida_cpu *tags; - unsigned long flags; - unsigned nr_free; - - BUG_ON(tag >= pool->nr_tags); - - tags = raw_cpu_ptr(pool->tag_cpu); - - spin_lock_irqsave(&tags->lock, flags); - tags->freelist[tags->nr_free++] = tag; - - nr_free = tags->nr_free; - - if (nr_free == 1) { - cpumask_set_cpu(smp_processor_id(), - &pool->cpus_have_tags); - wake_up(&pool->wait); - } - spin_unlock_irqrestore(&tags->lock, flags); - - if (nr_free == pool->percpu_max_size) { - spin_lock_irqsave(&pool->lock, flags); - spin_lock(&tags->lock); - - if (tags->nr_free == pool->percpu_max_size) { - move_tags(pool->freelist, &pool->nr_free, - tags->freelist, &tags->nr_free, - pool->percpu_batch_size); - - wake_up(&pool->wait); - } - spin_unlock(&tags->lock); - spin_unlock_irqrestore(&pool->lock, flags); - } -} -EXPORT_SYMBOL_GPL(percpu_ida_free); - -/** - * percpu_ida_destroy - release a tag pool's resources - * @pool: pool to free - * - * Frees the resources allocated by percpu_ida_init(). - */ -void percpu_ida_destroy(struct percpu_ida *pool) -{ - free_percpu(pool->tag_cpu); - free_pages((unsigned long) pool->freelist, - get_order(pool->nr_tags * sizeof(unsigned))); -} -EXPORT_SYMBOL_GPL(percpu_ida_destroy); - -/** - * percpu_ida_init - initialize a percpu tag pool - * @pool: pool to initialize - * @nr_tags: number of tags that will be available for allocation - * - * Initializes @pool so that it can be used to allocate tags - integers in the - * range [0, nr_tags). Typically, they'll be used by driver code to refer to a - * preallocated array of tag structures. - * - * Allocation is percpu, but sharding is limited by nr_tags - for best - * performance, the workload should not span more cpus than nr_tags / 128. - */ -int __percpu_ida_init(struct percpu_ida *pool, unsigned long nr_tags, - unsigned long max_size, unsigned long batch_size) -{ - unsigned i, cpu, order; - - memset(pool, 0, sizeof(*pool)); - - init_waitqueue_head(&pool->wait); - spin_lock_init(&pool->lock); - pool->nr_tags = nr_tags; - pool->percpu_max_size = max_size; - pool->percpu_batch_size = batch_size; - - /* Guard against overflow */ - if (nr_tags > (unsigned) INT_MAX + 1) { - pr_err("percpu_ida_init(): nr_tags too large\n"); - return -EINVAL; - } - - order = get_order(nr_tags * sizeof(unsigned)); - pool->freelist = (void *) __get_free_pages(GFP_KERNEL, order); - if (!pool->freelist) - return -ENOMEM; - - for (i = 0; i < nr_tags; i++) - pool->freelist[i] = i; - - pool->nr_free = nr_tags; - - pool->tag_cpu = __alloc_percpu(sizeof(struct percpu_ida_cpu) + - pool->percpu_max_size * sizeof(unsigned), - sizeof(unsigned)); - if (!pool->tag_cpu) - goto err; - - for_each_possible_cpu(cpu) - spin_lock_init(&per_cpu_ptr(pool->tag_cpu, cpu)->lock); - - return 0; -err: - percpu_ida_destroy(pool); - return -ENOMEM; -} -EXPORT_SYMBOL_GPL(__percpu_ida_init); - -/** - * percpu_ida_for_each_free - iterate free ids of a pool - * @pool: pool to iterate - * @fn: interate callback function - * @data: parameter for @fn - * - * Note, this doesn't guarantee to iterate all free ids restrictly. Some free - * ids might be missed, some might be iterated duplicated, and some might - * be iterated and not free soon. - */ -int percpu_ida_for_each_free(struct percpu_ida *pool, percpu_ida_cb fn, - void *data) -{ - unsigned long flags; - struct percpu_ida_cpu *remote; - unsigned cpu, i, err = 0; - - for_each_possible_cpu(cpu) { - remote = per_cpu_ptr(pool->tag_cpu, cpu); - spin_lock_irqsave(&remote->lock, flags); - for (i = 0; i < remote->nr_free; i++) { - err = fn(remote->freelist[i], data); - if (err) - break; - } - spin_unlock_irqrestore(&remote->lock, flags); - if (err) - goto out; - } - - spin_lock_irqsave(&pool->lock, flags); - for (i = 0; i < pool->nr_free; i++) { - err = fn(pool->freelist[i], data); - if (err) - break; - } - spin_unlock_irqrestore(&pool->lock, flags); -out: - return err; -} -EXPORT_SYMBOL_GPL(percpu_ida_for_each_free); - -/** - * percpu_ida_free_tags - return free tags number of a specific cpu or global pool - * @pool: pool related - * @cpu: specific cpu or global pool if @cpu == nr_cpu_ids - * - * Note: this just returns a snapshot of free tags number. - */ -unsigned percpu_ida_free_tags(struct percpu_ida *pool, int cpu) -{ - struct percpu_ida_cpu *remote; - if (cpu == nr_cpu_ids) - return pool->nr_free; - remote = per_cpu_ptr(pool->tag_cpu, cpu); - return remote->nr_free; -} -EXPORT_SYMBOL_GPL(percpu_ida_free_tags); -- cgit v1.2.3 From 2fa4a32613c9182b00e46872755b0662374424a7 Mon Sep 17 00:00:00 2001 From: Jason Yan Date: Thu, 10 May 2018 11:05:16 +0800 Subject: scsi: libsas: dynamically allocate and free ata host Commit 2623c7a5f2 ("libata: add refcounting to ata_host") v4.17+ introduced refcounting to ata_host and will increase or decrease the refcount when adding or deleting transport ATA port. Now the ata host for libsas is embedded in domain_device, and the ->kref member is not initialized. Afer we add ata transport class, ata_host_get() will be called when adding transport ATA port and a warning will be triggered as below: refcount_t: increment on 0; use-after-free. WARNING: CPU: 2 PID: 103 at lib/refcount.c:153 refcount_inc+0x40/0x48 ...... Call trace: refcount_inc+0x40/0x48 ata_host_get+0x10/0x18 ata_tport_add+0x40/0x120 ata_sas_tport_add+0xc/0x14 sas_ata_init+0x7c/0xc8 sas_discover_domain+0x380/0x53c process_one_work+0x12c/0x288 worker_thread+0x58/0x3f0 kthread+0xfc/0x128 ret_from_fork+0x10/0x18 And also when removing transport ATA port ata_host_put() will be called and another similar warning will be triggered. If the refcount decreased to zero, the ata host will be freed. But this ata host is only part of domain_device, it cannot be freed directly. So we have to change this embedded static ata host to a dynamically allocated ata host and initialize the ->kref member. To use ata_host_get() and ata_host_put() in libsas, we need to move the declaration of these functions to the public libata.h and export them. Fixes: b6240a4df018 ("scsi: libsas: add transport class for ATA devices") Signed-off-by: Jason Yan CC: John Garry CC: Taras Kondratiuk CC: Tejun Heo Acked-by: Tejun Heo Signed-off-by: Martin K. Petersen --- drivers/ata/libata-core.c | 3 +++ drivers/ata/libata.h | 2 -- drivers/scsi/libsas/sas_ata.c | 40 +++++++++++++++++++++++++------------- drivers/scsi/libsas/sas_discover.c | 2 ++ include/linux/libata.h | 2 ++ include/scsi/libsas.h | 2 +- 6 files changed, 34 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 27d15ed7fa3d..89cb4872a09c 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -6421,6 +6421,7 @@ void ata_host_init(struct ata_host *host, struct device *dev, host->n_tags = ATA_MAX_QUEUE; host->dev = dev; host->ops = ops; + kref_init(&host->kref); } void __ata_port_probe(struct ata_port *ap) @@ -7388,3 +7389,5 @@ EXPORT_SYMBOL_GPL(ata_cable_80wire); EXPORT_SYMBOL_GPL(ata_cable_unknown); EXPORT_SYMBOL_GPL(ata_cable_ignore); EXPORT_SYMBOL_GPL(ata_cable_sata); +EXPORT_SYMBOL_GPL(ata_host_get); +EXPORT_SYMBOL_GPL(ata_host_put); \ No newline at end of file diff --git a/drivers/ata/libata.h b/drivers/ata/libata.h index 9e21c49cf6be..f953cb4bb1ba 100644 --- a/drivers/ata/libata.h +++ b/drivers/ata/libata.h @@ -100,8 +100,6 @@ extern int ata_port_probe(struct ata_port *ap); extern void __ata_port_probe(struct ata_port *ap); extern unsigned int ata_read_log_page(struct ata_device *dev, u8 log, u8 page, void *buf, unsigned int sectors); -extern void ata_host_get(struct ata_host *host); -extern void ata_host_put(struct ata_host *host); #define to_ata_port(d) container_of(d, struct ata_port, tdev) diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c index 2ac7395112b4..64a958a99f6a 100644 --- a/drivers/scsi/libsas/sas_ata.c +++ b/drivers/scsi/libsas/sas_ata.c @@ -552,34 +552,46 @@ int sas_ata_init(struct domain_device *found_dev) { struct sas_ha_struct *ha = found_dev->port->ha; struct Scsi_Host *shost = ha->core.shost; + struct ata_host *ata_host; struct ata_port *ap; int rc; - ata_host_init(&found_dev->sata_dev.ata_host, ha->dev, &sas_sata_ops); - ap = ata_sas_port_alloc(&found_dev->sata_dev.ata_host, - &sata_port_info, - shost); + ata_host = kzalloc(sizeof(*ata_host), GFP_KERNEL); + if (!ata_host) { + SAS_DPRINTK("ata host alloc failed.\n"); + return -ENOMEM; + } + + ata_host_init(ata_host, ha->dev, &sas_sata_ops); + + ap = ata_sas_port_alloc(ata_host, &sata_port_info, shost); if (!ap) { SAS_DPRINTK("ata_sas_port_alloc failed.\n"); - return -ENODEV; + rc = -ENODEV; + goto free_host; } ap->private_data = found_dev; ap->cbl = ATA_CBL_SATA; ap->scsi_host = shost; rc = ata_sas_port_init(ap); - if (rc) { - ata_sas_port_destroy(ap); - return rc; - } - rc = ata_sas_tport_add(found_dev->sata_dev.ata_host.dev, ap); - if (rc) { - ata_sas_port_destroy(ap); - return rc; - } + if (rc) + goto destroy_port; + + rc = ata_sas_tport_add(ata_host->dev, ap); + if (rc) + goto destroy_port; + + found_dev->sata_dev.ata_host = ata_host; found_dev->sata_dev.ap = ap; return 0; + +destroy_port: + ata_sas_port_destroy(ap); +free_host: + ata_host_put(ata_host); + return rc; } void sas_ata_task_abort(struct sas_task *task) diff --git a/drivers/scsi/libsas/sas_discover.c b/drivers/scsi/libsas/sas_discover.c index 1ffca28fe6a8..0148ae62a52a 100644 --- a/drivers/scsi/libsas/sas_discover.c +++ b/drivers/scsi/libsas/sas_discover.c @@ -316,6 +316,8 @@ void sas_free_device(struct kref *kref) if (dev_is_sata(dev) && dev->sata_dev.ap) { ata_sas_tport_delete(dev->sata_dev.ap); ata_sas_port_destroy(dev->sata_dev.ap); + ata_host_put(dev->sata_dev.ata_host); + dev->sata_dev.ata_host = NULL; dev->sata_dev.ap = NULL; } diff --git a/include/linux/libata.h b/include/linux/libata.h index 8b8946dd63b9..33e9718397e2 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1110,6 +1110,8 @@ extern struct ata_host *ata_host_alloc(struct device *dev, int max_ports); extern struct ata_host *ata_host_alloc_pinfo(struct device *dev, const struct ata_port_info * const * ppi, int n_ports); extern int ata_slave_link_init(struct ata_port *ap); +extern void ata_host_get(struct ata_host *host); +extern void ata_host_put(struct ata_host *host); extern int ata_host_start(struct ata_host *host); extern int ata_host_register(struct ata_host *host, struct scsi_host_template *sht); diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h index 225ab7783dfd..3de3b10da19a 100644 --- a/include/scsi/libsas.h +++ b/include/scsi/libsas.h @@ -161,7 +161,7 @@ struct sata_device { u8 port_no; /* port number, if this is a PM (Port) */ struct ata_port *ap; - struct ata_host ata_host; + struct ata_host *ata_host; struct smp_resp rps_resp ____cacheline_aligned; /* report_phy_sata_resp */ u8 fis[ATA_RESP_FIS_SIZE]; }; -- cgit v1.2.3 From 6519750210d9d3330e85d12e0128652edde448d2 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 12 Jun 2018 10:34:50 +0200 Subject: sched/swait: Remove __prepare_to_swait There is no public user of this API, remove it. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Acked-by: Linus Torvalds Cc: bigeasy@linutronix.de Cc: oleg@redhat.com Cc: paulmck@linux.vnet.ibm.com Cc: pbonzini@redhat.com Link: https://lkml.kernel.org/r/20180612083909.157076812@infradead.org --- include/linux/swait.h | 1 - kernel/sched/swait.c | 2 +- 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/swait.h b/include/linux/swait.h index bf8cb0dee23c..d6a5e949e4ca 100644 --- a/include/linux/swait.h +++ b/include/linux/swait.h @@ -161,7 +161,6 @@ extern void swake_up(struct swait_queue_head *q); extern void swake_up_all(struct swait_queue_head *q); extern void swake_up_locked(struct swait_queue_head *q); -extern void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait); extern void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state); extern long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state); diff --git a/kernel/sched/swait.c b/kernel/sched/swait.c index b6fb2c3b3ff7..e68bb1398b05 100644 --- a/kernel/sched/swait.c +++ b/kernel/sched/swait.c @@ -69,7 +69,7 @@ void swake_up_all(struct swait_queue_head *q) } EXPORT_SYMBOL(swake_up_all); -void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait) +static void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait) { wait->task = current; if (list_empty(&wait->task_list)) -- cgit v1.2.3 From 0abf17bc7790dd0467ed0e38522242f23c5da1c4 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 12 Jun 2018 10:34:51 +0200 Subject: sched/swait: Switch to full exclusive mode Linus noted that swait basically implements exclusive mode -- because swake_up() only wakes a single waiter. And because of that it should take care to properly deal with the interruptible case. In short, the problem is that swake_up() can race with a signal. In this this case it is possible the swake_up() 'wakes' the waiter that is already on the way out because it just got a signal and the wakeup gets lost. The normal wait code is very careful and avoids this situation, make sure we do too. Copy the exact exclusive semantics from wait. Suggested-by: Linus Torvalds Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Acked-by: Linus Torvalds Cc: bigeasy@linutronix.de Cc: oleg@redhat.com Cc: paulmck@linux.vnet.ibm.com Cc: pbonzini@redhat.com Link: https://lkml.kernel.org/r/20180612083909.209762413@infradead.org --- include/linux/swait.h | 11 ++++++----- kernel/sched/swait.c | 22 +++++++++++++++++----- 2 files changed, 23 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/swait.h b/include/linux/swait.h index d6a5e949e4ca..dd032061112d 100644 --- a/include/linux/swait.h +++ b/include/linux/swait.h @@ -38,8 +38,8 @@ * all wakeups are TASK_NORMAL in order to avoid O(n) lookups for the right * sleeper state. * - * - the exclusive mode; because this requires preserving the list order - * and this is hard. + * - the !exclusive mode; because that leads to O(n) wakeups, everything is + * exclusive. * * - custom wake callback functions; because you cannot give any guarantees * about random code. This also allows swait to be used in RT, such that @@ -167,9 +167,10 @@ extern long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queu extern void __finish_swait(struct swait_queue_head *q, struct swait_queue *wait); extern void finish_swait(struct swait_queue_head *q, struct swait_queue *wait); -/* as per ___wait_event() but for swait, therefore "exclusive == 0" */ +/* as per ___wait_event() but for swait, therefore "exclusive == 1" */ #define ___swait_event(wq, condition, state, ret, cmd) \ ({ \ + __label__ __out; \ struct swait_queue __wait; \ long __ret = ret; \ \ @@ -182,13 +183,13 @@ extern void finish_swait(struct swait_queue_head *q, struct swait_queue *wait); \ if (___wait_is_interruptible(state) && __int) { \ __ret = __int; \ - break; \ + goto __out; \ } \ \ cmd; \ } \ finish_swait(&wq, &__wait); \ - __ret; \ +__out: __ret; \ }) #define __swait_event(wq, condition) \ diff --git a/kernel/sched/swait.c b/kernel/sched/swait.c index e68bb1398b05..66890de93ee5 100644 --- a/kernel/sched/swait.c +++ b/kernel/sched/swait.c @@ -73,7 +73,7 @@ static void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *w { wait->task = current; if (list_empty(&wait->task_list)) - list_add(&wait->task_list, &q->task_list); + list_add_tail(&wait->task_list, &q->task_list); } void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state) @@ -89,12 +89,24 @@ EXPORT_SYMBOL(prepare_to_swait); long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state) { - if (signal_pending_state(state, current)) - return -ERESTARTSYS; + unsigned long flags; + long ret = 0; - prepare_to_swait(q, wait, state); + raw_spin_lock_irqsave(&q->lock, flags); + if (unlikely(signal_pending_state(state, current))) { + /* + * See prepare_to_wait_event(). TL;DR, subsequent swake_up() + * must not see us. + */ + list_del_init(&wait->task_list); + ret = -ERESTARTSYS; + } else { + __prepare_to_swait(q, wait); + set_current_state(state); + } + raw_spin_unlock_irqrestore(&q->lock, flags); - return 0; + return ret; } EXPORT_SYMBOL(prepare_to_swait_event); -- cgit v1.2.3 From b3dae109fa89d67334bf3349babab3ad9b6f233f Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 12 Jun 2018 10:34:52 +0200 Subject: sched/swait: Rename to exclusive Since swait basically implemented exclusive waits only, make sure the API reflects that. $ git grep -l -e "\" -e "\" | while read file; do sed -i -e 's/\/&_one/g' -e 's/\/&_exclusive/g' $file; done With a few manual touch-ups. Suggested-by: Linus Torvalds Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Acked-by: Linus Torvalds Cc: bigeasy@linutronix.de Cc: oleg@redhat.com Cc: paulmck@linux.vnet.ibm.com Cc: pbonzini@redhat.com Link: https://lkml.kernel.org/r/20180612083909.261946548@infradead.org --- arch/mips/kvm/mips.c | 4 ++-- arch/powerpc/kvm/book3s_hv.c | 6 +++--- arch/s390/kvm/interrupt.c | 2 +- arch/x86/kernel/kvm.c | 4 ++-- arch/x86/kvm/lapic.c | 2 +- include/linux/swait.h | 24 ++++++++++++------------ kernel/power/suspend.c | 4 ++-- kernel/rcu/srcutiny.c | 4 ++-- kernel/rcu/tree.c | 8 ++++---- kernel/rcu/tree_exp.h | 4 ++-- kernel/rcu/tree_plugin.h | 12 ++++++------ kernel/sched/swait.c | 10 +++++----- virt/kvm/arm/arm.c | 4 ++-- virt/kvm/arm/psci.c | 2 +- virt/kvm/async_pf.c | 2 +- virt/kvm/kvm_main.c | 4 ++-- 16 files changed, 48 insertions(+), 48 deletions(-) (limited to 'include') diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index 7cd76f93a438..f7ea8e21656b 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -515,7 +515,7 @@ int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, dvcpu->arch.wait = 0; if (swq_has_sleeper(&dvcpu->wq)) - swake_up(&dvcpu->wq); + swake_up_one(&dvcpu->wq); return 0; } @@ -1204,7 +1204,7 @@ static void kvm_mips_comparecount_func(unsigned long data) vcpu->arch.wait = 0; if (swq_has_sleeper(&vcpu->wq)) - swake_up(&vcpu->wq); + swake_up_one(&vcpu->wq); } /* low level hrtimer wake routine */ diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index de686b340f4a..ee4a8854985e 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -216,7 +216,7 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu) wqp = kvm_arch_vcpu_wq(vcpu); if (swq_has_sleeper(wqp)) { - swake_up(wqp); + swake_up_one(wqp); ++vcpu->stat.halt_wakeup; } @@ -3188,7 +3188,7 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc) } } - prepare_to_swait(&vc->wq, &wait, TASK_INTERRUPTIBLE); + prepare_to_swait_exclusive(&vc->wq, &wait, TASK_INTERRUPTIBLE); if (kvmppc_vcore_check_block(vc)) { finish_swait(&vc->wq, &wait); @@ -3311,7 +3311,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) kvmppc_start_thread(vcpu, vc); trace_kvm_guest_enter(vcpu); } else if (vc->vcore_state == VCORE_SLEEPING) { - swake_up(&vc->wq); + swake_up_one(&vc->wq); } } diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index daa09f89ca2d..fcb55b02990e 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -1145,7 +1145,7 @@ void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu) * yield-candidate. */ vcpu->preempted = true; - swake_up(&vcpu->wq); + swake_up_one(&vcpu->wq); vcpu->stat.halt_wakeup++; } /* diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 5b2300b818af..a37bda38d205 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -154,7 +154,7 @@ void kvm_async_pf_task_wait(u32 token, int interrupt_kernel) for (;;) { if (!n.halted) - prepare_to_swait(&n.wq, &wait, TASK_UNINTERRUPTIBLE); + prepare_to_swait_exclusive(&n.wq, &wait, TASK_UNINTERRUPTIBLE); if (hlist_unhashed(&n.link)) break; @@ -188,7 +188,7 @@ static void apf_task_wake_one(struct kvm_task_sleep_node *n) if (n->halted) smp_send_reschedule(n->cpu); else if (swq_has_sleeper(&n->wq)) - swake_up(&n->wq); + swake_up_one(&n->wq); } static void apf_task_wake_all(void) diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index b5cd8465d44f..d536d457517b 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1379,7 +1379,7 @@ static void apic_timer_expired(struct kvm_lapic *apic) * using swait_active() is safe. */ if (swait_active(q)) - swake_up(q); + swake_up_one(q); if (apic_lvtt_tscdeadline(apic)) ktimer->expired_tscdeadline = ktimer->tscdeadline; diff --git a/include/linux/swait.h b/include/linux/swait.h index dd032061112d..73e06e9986d4 100644 --- a/include/linux/swait.h +++ b/include/linux/swait.h @@ -16,7 +16,7 @@ * wait-queues, but the semantics are actually completely different, and * every single user we have ever had has been buggy (or pointless). * - * A "swake_up()" only wakes up _one_ waiter, which is not at all what + * A "swake_up_one()" only wakes up _one_ waiter, which is not at all what * "wake_up()" does, and has led to problems. In other cases, it has * been fine, because there's only ever one waiter (kvm), but in that * case gthe whole "simple" wait-queue is just pointless to begin with, @@ -115,7 +115,7 @@ extern void __init_swait_queue_head(struct swait_queue_head *q, const char *name * CPU0 - waker CPU1 - waiter * * for (;;) { - * @cond = true; prepare_to_swait(&wq_head, &wait, state); + * @cond = true; prepare_to_swait_exclusive(&wq_head, &wait, state); * smp_mb(); // smp_mb() from set_current_state() * if (swait_active(wq_head)) if (@cond) * wake_up(wq_head); break; @@ -157,11 +157,11 @@ static inline bool swq_has_sleeper(struct swait_queue_head *wq) return swait_active(wq); } -extern void swake_up(struct swait_queue_head *q); +extern void swake_up_one(struct swait_queue_head *q); extern void swake_up_all(struct swait_queue_head *q); extern void swake_up_locked(struct swait_queue_head *q); -extern void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state); +extern void prepare_to_swait_exclusive(struct swait_queue_head *q, struct swait_queue *wait, int state); extern long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state); extern void __finish_swait(struct swait_queue_head *q, struct swait_queue *wait); @@ -196,7 +196,7 @@ __out: __ret; \ (void)___swait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, \ schedule()) -#define swait_event(wq, condition) \ +#define swait_event_exclusive(wq, condition) \ do { \ if (condition) \ break; \ @@ -208,7 +208,7 @@ do { \ TASK_UNINTERRUPTIBLE, timeout, \ __ret = schedule_timeout(__ret)) -#define swait_event_timeout(wq, condition, timeout) \ +#define swait_event_timeout_exclusive(wq, condition, timeout) \ ({ \ long __ret = timeout; \ if (!___wait_cond_timeout(condition)) \ @@ -220,7 +220,7 @@ do { \ ___swait_event(wq, condition, TASK_INTERRUPTIBLE, 0, \ schedule()) -#define swait_event_interruptible(wq, condition) \ +#define swait_event_interruptible_exclusive(wq, condition) \ ({ \ int __ret = 0; \ if (!(condition)) \ @@ -233,7 +233,7 @@ do { \ TASK_INTERRUPTIBLE, timeout, \ __ret = schedule_timeout(__ret)) -#define swait_event_interruptible_timeout(wq, condition, timeout) \ +#define swait_event_interruptible_timeout_exclusive(wq, condition, timeout)\ ({ \ long __ret = timeout; \ if (!___wait_cond_timeout(condition)) \ @@ -246,7 +246,7 @@ do { \ (void)___swait_event(wq, condition, TASK_IDLE, 0, schedule()) /** - * swait_event_idle - wait without system load contribution + * swait_event_idle_exclusive - wait without system load contribution * @wq: the waitqueue to wait on * @condition: a C expression for the event to wait for * @@ -257,7 +257,7 @@ do { \ * condition and doesn't want to contribute to system load. Signals are * ignored. */ -#define swait_event_idle(wq, condition) \ +#define swait_event_idle_exclusive(wq, condition) \ do { \ if (condition) \ break; \ @@ -270,7 +270,7 @@ do { \ __ret = schedule_timeout(__ret)) /** - * swait_event_idle_timeout - wait up to timeout without load contribution + * swait_event_idle_timeout_exclusive - wait up to timeout without load contribution * @wq: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout at which we'll give up in jiffies @@ -288,7 +288,7 @@ do { \ * or the remaining jiffies (at least 1) if the @condition evaluated * to %true before the @timeout elapsed. */ -#define swait_event_idle_timeout(wq, condition, timeout) \ +#define swait_event_idle_timeout_exclusive(wq, condition, timeout) \ ({ \ long __ret = timeout; \ if (!___wait_cond_timeout(condition)) \ diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 87331565e505..70178f6ffdc4 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -92,7 +92,7 @@ static void s2idle_enter(void) /* Push all the CPUs into the idle loop. */ wake_up_all_idle_cpus(); /* Make the current CPU wait so it can enter the idle loop too. */ - swait_event(s2idle_wait_head, + swait_event_exclusive(s2idle_wait_head, s2idle_state == S2IDLE_STATE_WAKE); cpuidle_pause(); @@ -160,7 +160,7 @@ void s2idle_wake(void) raw_spin_lock_irqsave(&s2idle_lock, flags); if (s2idle_state > S2IDLE_STATE_NONE) { s2idle_state = S2IDLE_STATE_WAKE; - swake_up(&s2idle_wait_head); + swake_up_one(&s2idle_wait_head); } raw_spin_unlock_irqrestore(&s2idle_lock, flags); } diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c index 622792abe41a..04fc2ed71af8 100644 --- a/kernel/rcu/srcutiny.c +++ b/kernel/rcu/srcutiny.c @@ -110,7 +110,7 @@ void __srcu_read_unlock(struct srcu_struct *sp, int idx) WRITE_ONCE(sp->srcu_lock_nesting[idx], newval); if (!newval && READ_ONCE(sp->srcu_gp_waiting)) - swake_up(&sp->srcu_wq); + swake_up_one(&sp->srcu_wq); } EXPORT_SYMBOL_GPL(__srcu_read_unlock); @@ -140,7 +140,7 @@ void srcu_drive_gp(struct work_struct *wp) idx = sp->srcu_idx; WRITE_ONCE(sp->srcu_idx, !sp->srcu_idx); WRITE_ONCE(sp->srcu_gp_waiting, true); /* srcu_read_unlock() wakes! */ - swait_event(sp->srcu_wq, !READ_ONCE(sp->srcu_lock_nesting[idx])); + swait_event_exclusive(sp->srcu_wq, !READ_ONCE(sp->srcu_lock_nesting[idx])); WRITE_ONCE(sp->srcu_gp_waiting, false); /* srcu_read_unlock() cheap. */ /* Invoke the callbacks we removed above. */ diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index aa7cade1b9f3..91f888d3b23a 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -1727,7 +1727,7 @@ static void rcu_gp_kthread_wake(struct rcu_state *rsp) !READ_ONCE(rsp->gp_flags) || !rsp->gp_kthread) return; - swake_up(&rsp->gp_wq); + swake_up_one(&rsp->gp_wq); } /* @@ -2002,7 +2002,7 @@ static bool rcu_gp_init(struct rcu_state *rsp) } /* - * Helper function for swait_event_idle() wakeup at force-quiescent-state + * Helper function for swait_event_idle_exclusive() wakeup at force-quiescent-state * time. */ static bool rcu_gp_fqs_check_wake(struct rcu_state *rsp, int *gfp) @@ -2144,7 +2144,7 @@ static int __noreturn rcu_gp_kthread(void *arg) READ_ONCE(rsp->gpnum), TPS("reqwait")); rsp->gp_state = RCU_GP_WAIT_GPS; - swait_event_idle(rsp->gp_wq, READ_ONCE(rsp->gp_flags) & + swait_event_idle_exclusive(rsp->gp_wq, READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_INIT); rsp->gp_state = RCU_GP_DONE_GPS; /* Locking provides needed memory barrier. */ @@ -2176,7 +2176,7 @@ static int __noreturn rcu_gp_kthread(void *arg) READ_ONCE(rsp->gpnum), TPS("fqswait")); rsp->gp_state = RCU_GP_WAIT_FQS; - ret = swait_event_idle_timeout(rsp->gp_wq, + ret = swait_event_idle_timeout_exclusive(rsp->gp_wq, rcu_gp_fqs_check_wake(rsp, &gf), j); rsp->gp_state = RCU_GP_DOING_FQS; /* Locking provides needed memory barriers. */ diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index d40708e8c5d6..d428cc1064c8 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -212,7 +212,7 @@ static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, raw_spin_unlock_irqrestore_rcu_node(rnp, flags); if (wake) { smp_mb(); /* EGP done before wake_up(). */ - swake_up(&rsp->expedited_wq); + swake_up_one(&rsp->expedited_wq); } break; } @@ -518,7 +518,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp) jiffies_start = jiffies; for (;;) { - ret = swait_event_timeout( + ret = swait_event_timeout_exclusive( rsp->expedited_wq, sync_rcu_preempt_exp_done_unlocked(rnp_root), jiffies_stall); diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 7fd12039e512..ad53d133f709 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -1854,8 +1854,8 @@ static void __wake_nocb_leader(struct rcu_data *rdp, bool force, WRITE_ONCE(rdp_leader->nocb_leader_sleep, false); del_timer(&rdp->nocb_timer); raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags); - smp_mb(); /* ->nocb_leader_sleep before swake_up(). */ - swake_up(&rdp_leader->nocb_wq); + smp_mb(); /* ->nocb_leader_sleep before swake_up_one(). */ + swake_up_one(&rdp_leader->nocb_wq); } else { raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags); } @@ -2082,7 +2082,7 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp) */ trace_rcu_this_gp(rnp, rdp, c, TPS("StartWait")); for (;;) { - swait_event_interruptible( + swait_event_interruptible_exclusive( rnp->nocb_gp_wq[c & 0x1], (d = ULONG_CMP_GE(READ_ONCE(rnp->completed), c))); if (likely(d)) @@ -2111,7 +2111,7 @@ wait_again: /* Wait for callbacks to appear. */ if (!rcu_nocb_poll) { trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, TPS("Sleep")); - swait_event_interruptible(my_rdp->nocb_wq, + swait_event_interruptible_exclusive(my_rdp->nocb_wq, !READ_ONCE(my_rdp->nocb_leader_sleep)); raw_spin_lock_irqsave(&my_rdp->nocb_lock, flags); my_rdp->nocb_leader_sleep = true; @@ -2176,7 +2176,7 @@ wait_again: raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags); if (rdp != my_rdp && tail == &rdp->nocb_follower_head) { /* List was empty, so wake up the follower. */ - swake_up(&rdp->nocb_wq); + swake_up_one(&rdp->nocb_wq); } } @@ -2193,7 +2193,7 @@ static void nocb_follower_wait(struct rcu_data *rdp) { for (;;) { trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("FollowerSleep")); - swait_event_interruptible(rdp->nocb_wq, + swait_event_interruptible_exclusive(rdp->nocb_wq, READ_ONCE(rdp->nocb_follower_head)); if (smp_load_acquire(&rdp->nocb_follower_head)) { /* ^^^ Ensure CB invocation follows _head test. */ diff --git a/kernel/sched/swait.c b/kernel/sched/swait.c index 66890de93ee5..66b59ac77c22 100644 --- a/kernel/sched/swait.c +++ b/kernel/sched/swait.c @@ -32,7 +32,7 @@ void swake_up_locked(struct swait_queue_head *q) } EXPORT_SYMBOL(swake_up_locked); -void swake_up(struct swait_queue_head *q) +void swake_up_one(struct swait_queue_head *q) { unsigned long flags; @@ -40,7 +40,7 @@ void swake_up(struct swait_queue_head *q) swake_up_locked(q); raw_spin_unlock_irqrestore(&q->lock, flags); } -EXPORT_SYMBOL(swake_up); +EXPORT_SYMBOL(swake_up_one); /* * Does not allow usage from IRQ disabled, since we must be able to @@ -76,7 +76,7 @@ static void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *w list_add_tail(&wait->task_list, &q->task_list); } -void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state) +void prepare_to_swait_exclusive(struct swait_queue_head *q, struct swait_queue *wait, int state) { unsigned long flags; @@ -85,7 +85,7 @@ void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int set_current_state(state); raw_spin_unlock_irqrestore(&q->lock, flags); } -EXPORT_SYMBOL(prepare_to_swait); +EXPORT_SYMBOL(prepare_to_swait_exclusive); long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state) { @@ -95,7 +95,7 @@ long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait raw_spin_lock_irqsave(&q->lock, flags); if (unlikely(signal_pending_state(state, current))) { /* - * See prepare_to_wait_event(). TL;DR, subsequent swake_up() + * See prepare_to_wait_event(). TL;DR, subsequent swake_up_one() * must not see us. */ list_del_init(&wait->task_list); diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index 04e554cae3a2..108250e4d376 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -604,7 +604,7 @@ void kvm_arm_resume_guest(struct kvm *kvm) kvm_for_each_vcpu(i, vcpu, kvm) { vcpu->arch.pause = false; - swake_up(kvm_arch_vcpu_wq(vcpu)); + swake_up_one(kvm_arch_vcpu_wq(vcpu)); } } @@ -612,7 +612,7 @@ static void vcpu_req_sleep(struct kvm_vcpu *vcpu) { struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu); - swait_event_interruptible(*wq, ((!vcpu->arch.power_off) && + swait_event_interruptible_exclusive(*wq, ((!vcpu->arch.power_off) && (!vcpu->arch.pause))); if (vcpu->arch.power_off || vcpu->arch.pause) { diff --git a/virt/kvm/arm/psci.c b/virt/kvm/arm/psci.c index c95ab4c5a475..9b73d3ad918a 100644 --- a/virt/kvm/arm/psci.c +++ b/virt/kvm/arm/psci.c @@ -155,7 +155,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) smp_mb(); /* Make sure the above is visible */ wq = kvm_arch_vcpu_wq(vcpu); - swake_up(wq); + swake_up_one(wq); return PSCI_RET_SUCCESS; } diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c index 57bcb27dcf30..23c2519c5b32 100644 --- a/virt/kvm/async_pf.c +++ b/virt/kvm/async_pf.c @@ -107,7 +107,7 @@ static void async_pf_execute(struct work_struct *work) trace_kvm_async_pf_completed(addr, gva); if (swq_has_sleeper(&vcpu->wq)) - swake_up(&vcpu->wq); + swake_up_one(&vcpu->wq); mmput(mm); kvm_put_kvm(vcpu->kvm); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index ada21f47f22b..940a4aed5b2d 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2167,7 +2167,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) kvm_arch_vcpu_blocking(vcpu); for (;;) { - prepare_to_swait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE); + prepare_to_swait_exclusive(&vcpu->wq, &wait, TASK_INTERRUPTIBLE); if (kvm_vcpu_check_block(vcpu) < 0) break; @@ -2209,7 +2209,7 @@ bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu) wqp = kvm_arch_vcpu_wq(vcpu); if (swq_has_sleeper(wqp)) { - swake_up(wqp); + swake_up_one(wqp); ++vcpu->stat.halt_wakeup; return true; } -- cgit v1.2.3 From a19741e5e5a9f1f02f8e3c037bde7d73d4bfae9c Mon Sep 17 00:00:00 2001 From: Christian König Date: Mon, 28 May 2018 11:47:52 +0200 Subject: dma_buf: remove device parameter from attach callback v2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The device parameter is completely unused because it is available in the attachment structure as well. v2: fix kerneldoc as well Signed-off-by: Christian König Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/226643/ --- drivers/dma-buf/dma-buf.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c | 3 +-- drivers/gpu/drm/drm_prime.c | 3 +-- drivers/gpu/drm/udl/udl_dmabuf.c | 1 - drivers/gpu/drm/vmwgfx/vmwgfx_prime.c | 1 - drivers/media/common/videobuf2/videobuf2-dma-contig.c | 2 +- drivers/media/common/videobuf2/videobuf2-dma-sg.c | 2 +- drivers/media/common/videobuf2/videobuf2-vmalloc.c | 2 +- include/drm/drm_prime.h | 2 +- include/linux/dma-buf.h | 13 ++++++------- 10 files changed, 13 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index 4c45e31258f0..50771063c617 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -568,7 +568,7 @@ struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf, mutex_lock(&dmabuf->lock); if (dmabuf->ops->attach) { - ret = dmabuf->ops->attach(dmabuf, dev, attach); + ret = dmabuf->ops->attach(dmabuf, attach); if (ret) goto err_attach; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c index 4b584cb75bf4..bbbb4f9578db 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c @@ -127,7 +127,6 @@ error: } static int amdgpu_gem_map_attach(struct dma_buf *dma_buf, - struct device *target_dev, struct dma_buf_attachment *attach) { struct drm_gem_object *obj = dma_buf->priv; @@ -135,7 +134,7 @@ static int amdgpu_gem_map_attach(struct dma_buf *dma_buf, struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); long r; - r = drm_gem_map_attach(dma_buf, target_dev, attach); + r = drm_gem_map_attach(dma_buf, attach); if (r) return r; diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c index 397b46b33739..0055d919070c 100644 --- a/drivers/gpu/drm/drm_prime.c +++ b/drivers/gpu/drm/drm_prime.c @@ -186,7 +186,6 @@ static int drm_prime_lookup_buf_handle(struct drm_prime_file_private *prime_fpri /** * drm_gem_map_attach - dma_buf attach implementation for GEM * @dma_buf: buffer to attach device to - * @target_dev: not used * @attach: buffer attachment data * * Allocates &drm_prime_attachment and calls &drm_driver.gem_prime_pin for @@ -195,7 +194,7 @@ static int drm_prime_lookup_buf_handle(struct drm_prime_file_private *prime_fpri * * Returns 0 on success, negative error code on failure. */ -int drm_gem_map_attach(struct dma_buf *dma_buf, struct device *target_dev, +int drm_gem_map_attach(struct dma_buf *dma_buf, struct dma_buf_attachment *attach) { struct drm_prime_attachment *prime_attach; diff --git a/drivers/gpu/drm/udl/udl_dmabuf.c b/drivers/gpu/drm/udl/udl_dmabuf.c index 0a20695eb120..91ae60309d3e 100644 --- a/drivers/gpu/drm/udl/udl_dmabuf.c +++ b/drivers/gpu/drm/udl/udl_dmabuf.c @@ -29,7 +29,6 @@ struct udl_drm_dmabuf_attachment { }; static int udl_attach_dma_buf(struct dma_buf *dmabuf, - struct device *dev, struct dma_buf_attachment *attach) { struct udl_drm_dmabuf_attachment *udl_attach; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c b/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c index 0d42a46521fc..fbffb37ccf42 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c @@ -40,7 +40,6 @@ */ static int vmw_prime_map_attach(struct dma_buf *dma_buf, - struct device *target_dev, struct dma_buf_attachment *attach) { return -ENOSYS; diff --git a/drivers/media/common/videobuf2/videobuf2-dma-contig.c b/drivers/media/common/videobuf2/videobuf2-dma-contig.c index f1178f6f434d..12d0072c52c2 100644 --- a/drivers/media/common/videobuf2/videobuf2-dma-contig.c +++ b/drivers/media/common/videobuf2/videobuf2-dma-contig.c @@ -222,7 +222,7 @@ struct vb2_dc_attachment { enum dma_data_direction dma_dir; }; -static int vb2_dc_dmabuf_ops_attach(struct dma_buf *dbuf, struct device *dev, +static int vb2_dc_dmabuf_ops_attach(struct dma_buf *dbuf, struct dma_buf_attachment *dbuf_attach) { struct vb2_dc_attachment *attach; diff --git a/drivers/media/common/videobuf2/videobuf2-dma-sg.c b/drivers/media/common/videobuf2/videobuf2-dma-sg.c index 753ed3138dcc..cf94765e593f 100644 --- a/drivers/media/common/videobuf2/videobuf2-dma-sg.c +++ b/drivers/media/common/videobuf2/videobuf2-dma-sg.c @@ -371,7 +371,7 @@ struct vb2_dma_sg_attachment { enum dma_data_direction dma_dir; }; -static int vb2_dma_sg_dmabuf_ops_attach(struct dma_buf *dbuf, struct device *dev, +static int vb2_dma_sg_dmabuf_ops_attach(struct dma_buf *dbuf, struct dma_buf_attachment *dbuf_attach) { struct vb2_dma_sg_attachment *attach; diff --git a/drivers/media/common/videobuf2/videobuf2-vmalloc.c b/drivers/media/common/videobuf2/videobuf2-vmalloc.c index 359fb9804d16..cdec023a918d 100644 --- a/drivers/media/common/videobuf2/videobuf2-vmalloc.c +++ b/drivers/media/common/videobuf2/videobuf2-vmalloc.c @@ -209,7 +209,7 @@ struct vb2_vmalloc_attachment { enum dma_data_direction dma_dir; }; -static int vb2_vmalloc_dmabuf_ops_attach(struct dma_buf *dbuf, struct device *dev, +static int vb2_vmalloc_dmabuf_ops_attach(struct dma_buf *dbuf, struct dma_buf_attachment *dbuf_attach) { struct vb2_vmalloc_attachment *attach; diff --git a/include/drm/drm_prime.h b/include/drm/drm_prime.h index 4d5f5d6cf6a6..ef338151cea8 100644 --- a/include/drm/drm_prime.h +++ b/include/drm/drm_prime.h @@ -82,7 +82,7 @@ int drm_gem_prime_fd_to_handle(struct drm_device *dev, struct dma_buf *drm_gem_dmabuf_export(struct drm_device *dev, struct dma_buf_export_info *exp_info); void drm_gem_dmabuf_release(struct dma_buf *dma_buf); -int drm_gem_map_attach(struct dma_buf *dma_buf, struct device *target_dev, +int drm_gem_map_attach(struct dma_buf *dma_buf, struct dma_buf_attachment *attach); void drm_gem_map_detach(struct dma_buf *dma_buf, struct dma_buf_attachment *attach); diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 88917fa796e4..c0ad5bf61188 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -55,11 +55,11 @@ struct dma_buf_ops { * @attach: * * This is called from dma_buf_attach() to make sure that a given - * &device can access the provided &dma_buf. Exporters which support - * buffer objects in special locations like VRAM or device-specific - * carveout areas should check whether the buffer could be move to - * system memory (or directly accessed by the provided device), and - * otherwise need to fail the attach operation. + * &dma_buf_attachment.dev can access the provided &dma_buf. Exporters + * which support buffer objects in special locations like VRAM or + * device-specific carveout areas should check whether the buffer could + * be move to system memory (or directly accessed by the provided + * device), and otherwise need to fail the attach operation. * * The exporter should also in general check whether the current * allocation fullfills the DMA constraints of the new device. If this @@ -77,8 +77,7 @@ struct dma_buf_ops { * to signal that backing storage is already allocated and incompatible * with the requirements of requesting device. */ - int (*attach)(struct dma_buf *, struct device *, - struct dma_buf_attachment *); + int (*attach)(struct dma_buf *, struct dma_buf_attachment *); /** * @detach: -- cgit v1.2.3 From f664a52695429b68afb4e130a0f69cd5fd1fec86 Mon Sep 17 00:00:00 2001 From: Christian König Date: Mon, 28 May 2018 13:34:01 +0200 Subject: dma-buf: remove kmap_atomic interface MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Neither used nor correctly implemented anywhere. Just completely remove the interface. Signed-off-by: Christian König Reviewed-by: Daniel Vetter Acked-by: Sumit Semwal Link: https://patchwork.freedesktop.org/patch/226645/ --- drivers/dma-buf/dma-buf.c | 54 +--------------------- drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c | 2 - drivers/gpu/drm/armada/armada_gem.c | 2 - drivers/gpu/drm/drm_prime.c | 31 ------------- drivers/gpu/drm/i915/i915_gem_dmabuf.c | 11 ----- drivers/gpu/drm/i915/selftests/mock_dmabuf.c | 2 - drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c | 2 - drivers/gpu/drm/tegra/gem.c | 14 ------ drivers/gpu/drm/udl/udl_dmabuf.c | 17 ------- drivers/gpu/drm/vmwgfx/vmwgfx_prime.c | 13 ------ .../media/common/videobuf2/videobuf2-dma-contig.c | 1 - drivers/media/common/videobuf2/videobuf2-dma-sg.c | 1 - drivers/media/common/videobuf2/videobuf2-vmalloc.c | 1 - drivers/staging/android/ion/ion.c | 2 - drivers/tee/tee_shm.c | 6 --- include/drm/drm_prime.h | 4 -- include/linux/dma-buf.h | 4 -- 17 files changed, 2 insertions(+), 165 deletions(-) (limited to 'include') diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index 50771063c617..13884474d158 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -405,7 +405,6 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info) || !exp_info->ops->map_dma_buf || !exp_info->ops->unmap_dma_buf || !exp_info->ops->release - || !exp_info->ops->map_atomic || !exp_info->ops->map || !exp_info->ops->mmap)) { return ERR_PTR(-EINVAL); @@ -687,26 +686,14 @@ EXPORT_SYMBOL_GPL(dma_buf_unmap_attachment); * void \*dma_buf_kmap(struct dma_buf \*, unsigned long); * void dma_buf_kunmap(struct dma_buf \*, unsigned long, void \*); * - * There are also atomic variants of these interfaces. Like for kmap they - * facilitate non-blocking fast-paths. Neither the importer nor the exporter - * (in the callback) is allowed to block when using these. - * - * Interfaces:: - * void \*dma_buf_kmap_atomic(struct dma_buf \*, unsigned long); - * void dma_buf_kunmap_atomic(struct dma_buf \*, unsigned long, void \*); - * - * For importers all the restrictions of using kmap apply, like the limited - * supply of kmap_atomic slots. Hence an importer shall only hold onto at - * max 2 atomic dma_buf kmaps at the same time (in any given process context). + * Implementing the functions is optional for exporters and for importers all + * the restrictions of using kmap apply. * * dma_buf kmap calls outside of the range specified in begin_cpu_access are * undefined. If the range is not PAGE_SIZE aligned, kmap needs to succeed on * the partial chunks at the beginning and end but may return stale or bogus * data outside of the range (in these partial chunks). * - * Note that these calls need to always succeed. The exporter needs to - * complete any preparations that might fail in begin_cpu_access. - * * For some cases the overhead of kmap can be too high, a vmap interface * is introduced. This interface should be used very carefully, as vmalloc * space is a limited resources on many architectures. @@ -859,43 +846,6 @@ int dma_buf_end_cpu_access(struct dma_buf *dmabuf, } EXPORT_SYMBOL_GPL(dma_buf_end_cpu_access); -/** - * dma_buf_kmap_atomic - Map a page of the buffer object into kernel address - * space. The same restrictions as for kmap_atomic and friends apply. - * @dmabuf: [in] buffer to map page from. - * @page_num: [in] page in PAGE_SIZE units to map. - * - * This call must always succeed, any necessary preparations that might fail - * need to be done in begin_cpu_access. - */ -void *dma_buf_kmap_atomic(struct dma_buf *dmabuf, unsigned long page_num) -{ - WARN_ON(!dmabuf); - - if (!dmabuf->ops->map_atomic) - return NULL; - return dmabuf->ops->map_atomic(dmabuf, page_num); -} -EXPORT_SYMBOL_GPL(dma_buf_kmap_atomic); - -/** - * dma_buf_kunmap_atomic - Unmap a page obtained by dma_buf_kmap_atomic. - * @dmabuf: [in] buffer to unmap page from. - * @page_num: [in] page in PAGE_SIZE units to unmap. - * @vaddr: [in] kernel space pointer obtained from dma_buf_kmap_atomic. - * - * This call must always succeed. - */ -void dma_buf_kunmap_atomic(struct dma_buf *dmabuf, unsigned long page_num, - void *vaddr) -{ - WARN_ON(!dmabuf); - - if (dmabuf->ops->unmap_atomic) - dmabuf->ops->unmap_atomic(dmabuf, page_num, vaddr); -} -EXPORT_SYMBOL_GPL(dma_buf_kunmap_atomic); - /** * dma_buf_kmap - Map a page of the buffer object into kernel address space. The * same restrictions as for kmap and friends apply. diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c index bbbb4f9578db..0558da049827 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c @@ -238,9 +238,7 @@ static const struct dma_buf_ops amdgpu_dmabuf_ops = { .release = drm_gem_dmabuf_release, .begin_cpu_access = amdgpu_gem_begin_cpu_access, .map = drm_gem_dmabuf_kmap, - .map_atomic = drm_gem_dmabuf_kmap_atomic, .unmap = drm_gem_dmabuf_kunmap, - .unmap_atomic = drm_gem_dmabuf_kunmap_atomic, .mmap = drm_gem_dmabuf_mmap, .vmap = drm_gem_dmabuf_vmap, .vunmap = drm_gem_dmabuf_vunmap, diff --git a/drivers/gpu/drm/armada/armada_gem.c b/drivers/gpu/drm/armada/armada_gem.c index a97f509743a5..3fb37c75c065 100644 --- a/drivers/gpu/drm/armada/armada_gem.c +++ b/drivers/gpu/drm/armada/armada_gem.c @@ -490,8 +490,6 @@ static const struct dma_buf_ops armada_gem_prime_dmabuf_ops = { .map_dma_buf = armada_gem_prime_map_dma_buf, .unmap_dma_buf = armada_gem_prime_unmap_dma_buf, .release = drm_gem_dmabuf_release, - .map_atomic = armada_gem_dmabuf_no_kmap, - .unmap_atomic = armada_gem_dmabuf_no_kunmap, .map = armada_gem_dmabuf_no_kmap, .unmap = armada_gem_dmabuf_no_kunmap, .mmap = armada_gem_dmabuf_mmap, diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c index 0055d919070c..186db2e4c57a 100644 --- a/drivers/gpu/drm/drm_prime.c +++ b/drivers/gpu/drm/drm_prime.c @@ -433,35 +433,6 @@ void drm_gem_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr) } EXPORT_SYMBOL(drm_gem_dmabuf_vunmap); -/** - * drm_gem_dmabuf_kmap_atomic - map_atomic implementation for GEM - * @dma_buf: buffer to be mapped - * @page_num: page number within the buffer - * - * Not implemented. This can be used as the &dma_buf_ops.map_atomic callback. - */ -void *drm_gem_dmabuf_kmap_atomic(struct dma_buf *dma_buf, - unsigned long page_num) -{ - return NULL; -} -EXPORT_SYMBOL(drm_gem_dmabuf_kmap_atomic); - -/** - * drm_gem_dmabuf_kunmap_atomic - unmap_atomic implementation for GEM - * @dma_buf: buffer to be unmapped - * @page_num: page number within the buffer - * @addr: virtual address of the buffer - * - * Not implemented. This can be used as the &dma_buf_ops.unmap_atomic callback. - */ -void drm_gem_dmabuf_kunmap_atomic(struct dma_buf *dma_buf, - unsigned long page_num, void *addr) -{ - -} -EXPORT_SYMBOL(drm_gem_dmabuf_kunmap_atomic); - /** * drm_gem_dmabuf_kmap - map implementation for GEM * @dma_buf: buffer to be mapped @@ -519,9 +490,7 @@ static const struct dma_buf_ops drm_gem_prime_dmabuf_ops = { .unmap_dma_buf = drm_gem_unmap_dma_buf, .release = drm_gem_dmabuf_release, .map = drm_gem_dmabuf_kmap, - .map_atomic = drm_gem_dmabuf_kmap_atomic, .unmap = drm_gem_dmabuf_kunmap, - .unmap_atomic = drm_gem_dmabuf_kunmap_atomic, .mmap = drm_gem_dmabuf_mmap, .vmap = drm_gem_dmabuf_vmap, .vunmap = drm_gem_dmabuf_vunmap, diff --git a/drivers/gpu/drm/i915/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/i915_gem_dmabuf.c index 69a7aec49e84..82e2ca17a441 100644 --- a/drivers/gpu/drm/i915/i915_gem_dmabuf.c +++ b/drivers/gpu/drm/i915/i915_gem_dmabuf.c @@ -111,15 +111,6 @@ static void i915_gem_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr) i915_gem_object_unpin_map(obj); } -static void *i915_gem_dmabuf_kmap_atomic(struct dma_buf *dma_buf, unsigned long page_num) -{ - return NULL; -} - -static void i915_gem_dmabuf_kunmap_atomic(struct dma_buf *dma_buf, unsigned long page_num, void *addr) -{ - -} static void *i915_gem_dmabuf_kmap(struct dma_buf *dma_buf, unsigned long page_num) { struct drm_i915_gem_object *obj = dma_buf_to_obj(dma_buf); @@ -225,9 +216,7 @@ static const struct dma_buf_ops i915_dmabuf_ops = { .unmap_dma_buf = i915_gem_unmap_dma_buf, .release = drm_gem_dmabuf_release, .map = i915_gem_dmabuf_kmap, - .map_atomic = i915_gem_dmabuf_kmap_atomic, .unmap = i915_gem_dmabuf_kunmap, - .unmap_atomic = i915_gem_dmabuf_kunmap_atomic, .mmap = i915_gem_dmabuf_mmap, .vmap = i915_gem_dmabuf_vmap, .vunmap = i915_gem_dmabuf_vunmap, diff --git a/drivers/gpu/drm/i915/selftests/mock_dmabuf.c b/drivers/gpu/drm/i915/selftests/mock_dmabuf.c index 302f7d103635..f81fda8ea45e 100644 --- a/drivers/gpu/drm/i915/selftests/mock_dmabuf.c +++ b/drivers/gpu/drm/i915/selftests/mock_dmabuf.c @@ -130,9 +130,7 @@ static const struct dma_buf_ops mock_dmabuf_ops = { .unmap_dma_buf = mock_unmap_dma_buf, .release = mock_dmabuf_release, .map = mock_dmabuf_kmap, - .map_atomic = mock_dmabuf_kmap_atomic, .unmap = mock_dmabuf_kunmap, - .unmap_atomic = mock_dmabuf_kunmap_atomic, .mmap = mock_dmabuf_mmap, .vmap = mock_dmabuf_vmap, .vunmap = mock_dmabuf_vunmap, diff --git a/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c b/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c index 8e41d649e248..1a073f9b2834 100644 --- a/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c +++ b/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c @@ -148,8 +148,6 @@ static const struct dma_buf_ops omap_dmabuf_ops = { .release = drm_gem_dmabuf_release, .begin_cpu_access = omap_gem_dmabuf_begin_cpu_access, .end_cpu_access = omap_gem_dmabuf_end_cpu_access, - .map_atomic = omap_gem_dmabuf_kmap_atomic, - .unmap_atomic = omap_gem_dmabuf_kunmap_atomic, .map = omap_gem_dmabuf_kmap, .unmap = omap_gem_dmabuf_kunmap, .mmap = omap_gem_dmabuf_mmap, diff --git a/drivers/gpu/drm/tegra/gem.c b/drivers/gpu/drm/tegra/gem.c index 8b0b4ff64bb4..d7661702c11c 100644 --- a/drivers/gpu/drm/tegra/gem.c +++ b/drivers/gpu/drm/tegra/gem.c @@ -596,18 +596,6 @@ static int tegra_gem_prime_end_cpu_access(struct dma_buf *buf, return 0; } -static void *tegra_gem_prime_kmap_atomic(struct dma_buf *buf, - unsigned long page) -{ - return NULL; -} - -static void tegra_gem_prime_kunmap_atomic(struct dma_buf *buf, - unsigned long page, - void *addr) -{ -} - static void *tegra_gem_prime_kmap(struct dma_buf *buf, unsigned long page) { return NULL; @@ -648,8 +636,6 @@ static const struct dma_buf_ops tegra_gem_prime_dmabuf_ops = { .release = tegra_gem_prime_release, .begin_cpu_access = tegra_gem_prime_begin_cpu_access, .end_cpu_access = tegra_gem_prime_end_cpu_access, - .map_atomic = tegra_gem_prime_kmap_atomic, - .unmap_atomic = tegra_gem_prime_kunmap_atomic, .map = tegra_gem_prime_kmap, .unmap = tegra_gem_prime_kunmap, .mmap = tegra_gem_prime_mmap, diff --git a/drivers/gpu/drm/udl/udl_dmabuf.c b/drivers/gpu/drm/udl/udl_dmabuf.c index 91ae60309d3e..556f62662aa9 100644 --- a/drivers/gpu/drm/udl/udl_dmabuf.c +++ b/drivers/gpu/drm/udl/udl_dmabuf.c @@ -157,27 +157,12 @@ static void *udl_dmabuf_kmap(struct dma_buf *dma_buf, unsigned long page_num) return NULL; } -static void *udl_dmabuf_kmap_atomic(struct dma_buf *dma_buf, - unsigned long page_num) -{ - /* TODO */ - - return NULL; -} - static void udl_dmabuf_kunmap(struct dma_buf *dma_buf, unsigned long page_num, void *addr) { /* TODO */ } -static void udl_dmabuf_kunmap_atomic(struct dma_buf *dma_buf, - unsigned long page_num, - void *addr) -{ - /* TODO */ -} - static int udl_dmabuf_mmap(struct dma_buf *dma_buf, struct vm_area_struct *vma) { @@ -192,9 +177,7 @@ static const struct dma_buf_ops udl_dmabuf_ops = { .map_dma_buf = udl_map_dma_buf, .unmap_dma_buf = udl_unmap_dma_buf, .map = udl_dmabuf_kmap, - .map_atomic = udl_dmabuf_kmap_atomic, .unmap = udl_dmabuf_kunmap, - .unmap_atomic = udl_dmabuf_kunmap_atomic, .mmap = udl_dmabuf_mmap, .release = drm_gem_dmabuf_release, }; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c b/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c index fbffb37ccf42..373bc6da2f84 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c @@ -71,17 +71,6 @@ static void vmw_prime_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr) { } -static void *vmw_prime_dmabuf_kmap_atomic(struct dma_buf *dma_buf, - unsigned long page_num) -{ - return NULL; -} - -static void vmw_prime_dmabuf_kunmap_atomic(struct dma_buf *dma_buf, - unsigned long page_num, void *addr) -{ - -} static void *vmw_prime_dmabuf_kmap(struct dma_buf *dma_buf, unsigned long page_num) { @@ -108,9 +97,7 @@ const struct dma_buf_ops vmw_prime_dmabuf_ops = { .unmap_dma_buf = vmw_prime_unmap_dma_buf, .release = NULL, .map = vmw_prime_dmabuf_kmap, - .map_atomic = vmw_prime_dmabuf_kmap_atomic, .unmap = vmw_prime_dmabuf_kunmap, - .unmap_atomic = vmw_prime_dmabuf_kunmap_atomic, .mmap = vmw_prime_dmabuf_mmap, .vmap = vmw_prime_dmabuf_vmap, .vunmap = vmw_prime_dmabuf_vunmap, diff --git a/drivers/media/common/videobuf2/videobuf2-dma-contig.c b/drivers/media/common/videobuf2/videobuf2-dma-contig.c index 12d0072c52c2..aff0ab7bf83d 100644 --- a/drivers/media/common/videobuf2/videobuf2-dma-contig.c +++ b/drivers/media/common/videobuf2/videobuf2-dma-contig.c @@ -358,7 +358,6 @@ static const struct dma_buf_ops vb2_dc_dmabuf_ops = { .map_dma_buf = vb2_dc_dmabuf_ops_map, .unmap_dma_buf = vb2_dc_dmabuf_ops_unmap, .map = vb2_dc_dmabuf_ops_kmap, - .map_atomic = vb2_dc_dmabuf_ops_kmap, .vmap = vb2_dc_dmabuf_ops_vmap, .mmap = vb2_dc_dmabuf_ops_mmap, .release = vb2_dc_dmabuf_ops_release, diff --git a/drivers/media/common/videobuf2/videobuf2-dma-sg.c b/drivers/media/common/videobuf2/videobuf2-dma-sg.c index cf94765e593f..015e737095cd 100644 --- a/drivers/media/common/videobuf2/videobuf2-dma-sg.c +++ b/drivers/media/common/videobuf2/videobuf2-dma-sg.c @@ -507,7 +507,6 @@ static const struct dma_buf_ops vb2_dma_sg_dmabuf_ops = { .map_dma_buf = vb2_dma_sg_dmabuf_ops_map, .unmap_dma_buf = vb2_dma_sg_dmabuf_ops_unmap, .map = vb2_dma_sg_dmabuf_ops_kmap, - .map_atomic = vb2_dma_sg_dmabuf_ops_kmap, .vmap = vb2_dma_sg_dmabuf_ops_vmap, .mmap = vb2_dma_sg_dmabuf_ops_mmap, .release = vb2_dma_sg_dmabuf_ops_release, diff --git a/drivers/media/common/videobuf2/videobuf2-vmalloc.c b/drivers/media/common/videobuf2/videobuf2-vmalloc.c index cdec023a918d..6dfbd5b05907 100644 --- a/drivers/media/common/videobuf2/videobuf2-vmalloc.c +++ b/drivers/media/common/videobuf2/videobuf2-vmalloc.c @@ -346,7 +346,6 @@ static const struct dma_buf_ops vb2_vmalloc_dmabuf_ops = { .map_dma_buf = vb2_vmalloc_dmabuf_ops_map, .unmap_dma_buf = vb2_vmalloc_dmabuf_ops_unmap, .map = vb2_vmalloc_dmabuf_ops_kmap, - .map_atomic = vb2_vmalloc_dmabuf_ops_kmap, .vmap = vb2_vmalloc_dmabuf_ops_vmap, .mmap = vb2_vmalloc_dmabuf_ops_mmap, .release = vb2_vmalloc_dmabuf_ops_release, diff --git a/drivers/staging/android/ion/ion.c b/drivers/staging/android/ion/ion.c index e74db7902549..a5220445b5e8 100644 --- a/drivers/staging/android/ion/ion.c +++ b/drivers/staging/android/ion/ion.c @@ -369,8 +369,6 @@ static const struct dma_buf_ops dma_buf_ops = { .detach = ion_dma_buf_detatch, .begin_cpu_access = ion_dma_buf_begin_cpu_access, .end_cpu_access = ion_dma_buf_end_cpu_access, - .map_atomic = ion_dma_buf_kmap, - .unmap_atomic = ion_dma_buf_kunmap, .map = ion_dma_buf_kmap, .unmap = ion_dma_buf_kunmap, }; diff --git a/drivers/tee/tee_shm.c b/drivers/tee/tee_shm.c index 556960a1bab3..df4a1553b78b 100644 --- a/drivers/tee/tee_shm.c +++ b/drivers/tee/tee_shm.c @@ -80,11 +80,6 @@ static void tee_shm_op_release(struct dma_buf *dmabuf) tee_shm_release(shm); } -static void *tee_shm_op_map_atomic(struct dma_buf *dmabuf, unsigned long pgnum) -{ - return NULL; -} - static void *tee_shm_op_map(struct dma_buf *dmabuf, unsigned long pgnum) { return NULL; @@ -107,7 +102,6 @@ static const struct dma_buf_ops tee_shm_dma_buf_ops = { .map_dma_buf = tee_shm_op_map_dma_buf, .unmap_dma_buf = tee_shm_op_unmap_dma_buf, .release = tee_shm_op_release, - .map_atomic = tee_shm_op_map_atomic, .map = tee_shm_op_map, .mmap = tee_shm_op_mmap, }; diff --git a/include/drm/drm_prime.h b/include/drm/drm_prime.h index ef338151cea8..d716d653b096 100644 --- a/include/drm/drm_prime.h +++ b/include/drm/drm_prime.h @@ -93,10 +93,6 @@ void drm_gem_unmap_dma_buf(struct dma_buf_attachment *attach, enum dma_data_direction dir); void *drm_gem_dmabuf_vmap(struct dma_buf *dma_buf); void drm_gem_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr); -void *drm_gem_dmabuf_kmap_atomic(struct dma_buf *dma_buf, - unsigned long page_num); -void drm_gem_dmabuf_kunmap_atomic(struct dma_buf *dma_buf, - unsigned long page_num, void *addr); void *drm_gem_dmabuf_kmap(struct dma_buf *dma_buf, unsigned long page_num); void drm_gem_dmabuf_kunmap(struct dma_buf *dma_buf, unsigned long page_num, void *addr); diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index c0ad5bf61188..58725f890b5b 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -205,8 +205,6 @@ struct dma_buf_ops { * to be restarted. */ int (*end_cpu_access)(struct dma_buf *, enum dma_data_direction); - void *(*map_atomic)(struct dma_buf *, unsigned long); - void (*unmap_atomic)(struct dma_buf *, unsigned long, void *); void *(*map)(struct dma_buf *, unsigned long); void (*unmap)(struct dma_buf *, unsigned long, void *); @@ -394,8 +392,6 @@ int dma_buf_begin_cpu_access(struct dma_buf *dma_buf, enum dma_data_direction dir); int dma_buf_end_cpu_access(struct dma_buf *dma_buf, enum dma_data_direction dir); -void *dma_buf_kmap_atomic(struct dma_buf *, unsigned long); -void dma_buf_kunmap_atomic(struct dma_buf *, unsigned long, void *); void *dma_buf_kmap(struct dma_buf *, unsigned long); void dma_buf_kunmap(struct dma_buf *, unsigned long, void *); -- cgit v1.2.3 From 935774cd71fe604cc8ed24adcb507d7784255672 Mon Sep 17 00:00:00 2001 From: Brian Starkey Date: Wed, 29 Mar 2017 17:42:32 +0100 Subject: drm: Add writeback connector type Writeback connectors represent writeback engines which can write the CRTC output to a memory framebuffer. Add a writeback connector type and related support functions. Drivers should initialize a writeback connector with drm_writeback_connector_init() which takes care of setting up all the writeback-specific details on top of the normal functionality of drm_connector_init(). Writeback connectors have a WRITEBACK_FB_ID property, used to set the output framebuffer, and a WRITEBACK_PIXEL_FORMATS blob used to expose the supported writeback formats to userspace. When a framebuffer is attached to a writeback connector with the WRITEBACK_FB_ID property, it is used only once (for the commit in which it was included), and userspace can never read back the value of WRITEBACK_FB_ID. WRITEBACK_FB_ID can only be set if the connector is attached to a CRTC. Changes since v1: - Added drm_writeback.c + documentation - Added helper to initialize writeback connector in one go - Added core checks - Squashed into a single commit - Dropped the client cap - Writeback framebuffers are no longer persistent Changes since v2: Daniel Vetter: - Subclass drm_connector to drm_writeback_connector - Relax check to allow CRTC to be set without an FB - Add some writeback_ prefixes - Drop PIXEL_FORMATS_SIZE property, as it was unnecessary Gustavo Padovan: - Add drm_writeback_job to handle writeback signalling centrally Changes since v3: - Rebased - Rename PIXEL_FORMATS -> WRITEBACK_PIXEL_FORMATS Chances since v4: - Embed a drm_encoder inside the drm_writeback_connector to reduce the amount of boilerplate code required from the drivers that are using it. Changes since v5: - Added Rob Clark's atomic_commit() vfunc to connector helper funcs, so that writeback jobs are committed from atomic helpers - Updated create_writeback_properties() signature to return an error code rather than a boolean false for failure. - Free writeback job with the connector state rather than when doing the cleanup_work() Changes since v7: - fix extraneous use of out_fence that is only introduced in a subsequent patch. Changes since v8: - whitespace changes pull from subsequent patch Changes since v9: - Revert the v6 changes that free the writeback job in the connector state cleanup and return to doing it in the cleanup_work() function Signed-off-by: Brian Starkey [rebased and fixed conflicts] Signed-off-by: Mihail Atanassov [rebased and added atomic_commit() vfunc for writeback jobs] Signed-off-by: Rob Clark Signed-off-by: Liviu Dudau Reviewed-by: Eric Anholt Link: https://patchwork.freedesktop.org/patch/229037/ --- Documentation/gpu/drm-kms.rst | 9 ++ drivers/gpu/drm/Makefile | 2 +- drivers/gpu/drm/drm_atomic.c | 124 ++++++++++++++++ drivers/gpu/drm/drm_atomic_helper.c | 25 ++++ drivers/gpu/drm/drm_connector.c | 4 +- drivers/gpu/drm/drm_writeback.c | 245 +++++++++++++++++++++++++++++++ include/drm/drm_atomic.h | 3 + include/drm/drm_connector.h | 13 ++ include/drm/drm_mode_config.h | 15 ++ include/drm/drm_modeset_helper_vtables.h | 11 ++ include/drm/drm_writeback.h | 91 ++++++++++++ include/uapi/drm/drm_mode.h | 1 + 12 files changed, 541 insertions(+), 2 deletions(-) create mode 100644 drivers/gpu/drm/drm_writeback.c create mode 100644 include/drm/drm_writeback.h (limited to 'include') diff --git a/Documentation/gpu/drm-kms.rst b/Documentation/gpu/drm-kms.rst index e233c2626bd0..4f6f113a7f5d 100644 --- a/Documentation/gpu/drm-kms.rst +++ b/Documentation/gpu/drm-kms.rst @@ -373,6 +373,15 @@ Connector Functions Reference .. kernel-doc:: drivers/gpu/drm/drm_connector.c :export: +Writeback Connectors +-------------------- + +.. kernel-doc:: drivers/gpu/drm/drm_writeback.c + :doc: overview + +.. kernel-doc:: drivers/gpu/drm/drm_writeback.c + :export: + Encoder Abstraction =================== diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile index ef9f3dab287f..69c13517ea3a 100644 --- a/drivers/gpu/drm/Makefile +++ b/drivers/gpu/drm/Makefile @@ -18,7 +18,7 @@ drm-y := drm_auth.o drm_bufs.o drm_cache.o \ drm_encoder.o drm_mode_object.o drm_property.o \ drm_plane.o drm_color_mgmt.o drm_print.o \ drm_dumb_buffers.o drm_mode_config.o drm_vblank.o \ - drm_syncobj.o drm_lease.o + drm_syncobj.o drm_lease.o drm_writeback.o drm-$(CONFIG_DRM_LIB_RANDOM) += lib/drm_random.o drm-$(CONFIG_DRM_VM) += drm_vm.o diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c index 9ec5c865a043..3e53d6e5c340 100644 --- a/drivers/gpu/drm/drm_atomic.c +++ b/drivers/gpu/drm/drm_atomic.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include "drm_crtc_internal.h" @@ -690,6 +691,45 @@ static void drm_atomic_crtc_print_state(struct drm_printer *p, crtc->funcs->atomic_print_state(p, state); } +/** + * drm_atomic_connector_check - check connector state + * @connector: connector to check + * @state: connector state to check + * + * Provides core sanity checks for connector state. + * + * RETURNS: + * Zero on success, error code on failure + */ +static int drm_atomic_connector_check(struct drm_connector *connector, + struct drm_connector_state *state) +{ + struct drm_crtc_state *crtc_state; + struct drm_writeback_job *writeback_job = state->writeback_job; + + if ((connector->connector_type != DRM_MODE_CONNECTOR_WRITEBACK) || !writeback_job) + return 0; + + if (writeback_job->fb && !state->crtc) { + DRM_DEBUG_ATOMIC("[CONNECTOR:%d:%s] framebuffer without CRTC\n", + connector->base.id, connector->name); + return -EINVAL; + } + + if (state->crtc) + crtc_state = drm_atomic_get_existing_crtc_state(state->state, + state->crtc); + + if (writeback_job->fb && !crtc_state->active) { + DRM_DEBUG_ATOMIC("[CONNECTOR:%d:%s] has framebuffer, but [CRTC:%d] is off\n", + connector->base.id, connector->name, + state->crtc->base.id); + return -EINVAL; + } + + return 0; +} + /** * drm_atomic_get_plane_state - get plane state * @state: global atomic state object @@ -1321,6 +1361,12 @@ static int drm_atomic_connector_set_property(struct drm_connector *connector, return -EINVAL; } state->content_protection = val; + } else if (property == config->writeback_fb_id_property) { + struct drm_framebuffer *fb = drm_framebuffer_lookup(dev, NULL, val); + int ret = drm_atomic_set_writeback_fb_for_connector(state, fb); + if (fb) + drm_framebuffer_put(fb); + return ret; } else if (connector->funcs->atomic_set_property) { return connector->funcs->atomic_set_property(connector, state, property, val); @@ -1407,6 +1453,9 @@ drm_atomic_connector_get_property(struct drm_connector *connector, *val = state->scaling_mode; } else if (property == connector->content_protection_property) { *val = state->content_protection; + } else if (property == config->writeback_fb_id_property) { + /* Writeback framebuffer is one-shot, write and forget */ + *val = 0; } else if (connector->funcs->atomic_get_property) { return connector->funcs->atomic_get_property(connector, state, property, val); @@ -1631,6 +1680,70 @@ drm_atomic_set_crtc_for_connector(struct drm_connector_state *conn_state, } EXPORT_SYMBOL(drm_atomic_set_crtc_for_connector); +/* + * drm_atomic_get_writeback_job - return or allocate a writeback job + * @conn_state: Connector state to get the job for + * + * Writeback jobs have a different lifetime to the atomic state they are + * associated with. This convenience function takes care of allocating a job + * if there isn't yet one associated with the connector state, otherwise + * it just returns the existing job. + * + * Returns: The writeback job for the given connector state + */ +static struct drm_writeback_job * +drm_atomic_get_writeback_job(struct drm_connector_state *conn_state) +{ + WARN_ON(conn_state->connector->connector_type != DRM_MODE_CONNECTOR_WRITEBACK); + + if (!conn_state->writeback_job) + conn_state->writeback_job = + kzalloc(sizeof(*conn_state->writeback_job), GFP_KERNEL); + + return conn_state->writeback_job; +} + +/** + * drm_atomic_set_writeback_fb_for_connector - set writeback framebuffer + * @conn_state: atomic state object for the connector + * @fb: fb to use for the connector + * + * This is used to set the framebuffer for a writeback connector, which outputs + * to a buffer instead of an actual physical connector. + * Changing the assigned framebuffer requires us to grab a reference to the new + * fb and drop the reference to the old fb, if there is one. This function + * takes care of all these details besides updating the pointer in the + * state object itself. + * + * Note: The only way conn_state can already have an fb set is if the commit + * sets the property more than once. + * + * See also: drm_writeback_connector_init() + * + * Returns: 0 on success + */ +int drm_atomic_set_writeback_fb_for_connector( + struct drm_connector_state *conn_state, + struct drm_framebuffer *fb) +{ + struct drm_writeback_job *job = + drm_atomic_get_writeback_job(conn_state); + if (!job) + return -ENOMEM; + + drm_framebuffer_assign(&job->fb, fb); + + if (fb) + DRM_DEBUG_ATOMIC("Set [FB:%d] for connector state %p\n", + fb->base.id, conn_state); + else + DRM_DEBUG_ATOMIC("Set [NOFB] for connector state %p\n", + conn_state); + + return 0; +} +EXPORT_SYMBOL(drm_atomic_set_writeback_fb_for_connector); + /** * drm_atomic_add_affected_connectors - add connectors for crtc * @state: atomic state @@ -1752,6 +1865,8 @@ int drm_atomic_check_only(struct drm_atomic_state *state) struct drm_plane_state *plane_state; struct drm_crtc *crtc; struct drm_crtc_state *crtc_state; + struct drm_connector *conn; + struct drm_connector_state *conn_state; int i, ret = 0; DRM_DEBUG_ATOMIC("checking %p\n", state); @@ -1774,6 +1889,15 @@ int drm_atomic_check_only(struct drm_atomic_state *state) } } + for_each_new_connector_in_state(state, conn, conn_state, i) { + ret = drm_atomic_connector_check(conn, conn_state); + if (ret) { + DRM_DEBUG_ATOMIC("[CONNECTOR:%d:%s] atomic core check failed\n", + conn->base.id, conn->name); + return ret; + } + } + if (config->funcs->atomic_check) ret = config->funcs->atomic_check(state->dev, state); diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index 232fa11a5e31..17baf5057132 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include "drm_crtc_helper_internal.h" @@ -1172,6 +1173,25 @@ void drm_atomic_helper_commit_modeset_disables(struct drm_device *dev, } EXPORT_SYMBOL(drm_atomic_helper_commit_modeset_disables); +static void drm_atomic_helper_commit_writebacks(struct drm_device *dev, + struct drm_atomic_state *old_state) +{ + struct drm_connector *connector; + struct drm_connector_state *new_conn_state; + int i; + + for_each_new_connector_in_state(old_state, connector, new_conn_state, i) { + const struct drm_connector_helper_funcs *funcs; + + funcs = connector->helper_private; + + if (new_conn_state->writeback_job && new_conn_state->writeback_job->fb) { + WARN_ON(connector->connector_type != DRM_MODE_CONNECTOR_WRITEBACK); + funcs->atomic_commit(connector, new_conn_state->writeback_job); + } + } +} + /** * drm_atomic_helper_commit_modeset_enables - modeset commit to enable outputs * @dev: DRM device @@ -1251,6 +1271,8 @@ void drm_atomic_helper_commit_modeset_enables(struct drm_device *dev, drm_bridge_enable(encoder->bridge); } + + drm_atomic_helper_commit_writebacks(dev, old_state); } EXPORT_SYMBOL(drm_atomic_helper_commit_modeset_enables); @@ -3647,6 +3669,9 @@ __drm_atomic_helper_connector_duplicate_state(struct drm_connector *connector, if (state->crtc) drm_connector_get(connector); state->commit = NULL; + + /* Don't copy over a writeback job, they are used only once */ + state->writeback_job = NULL; } EXPORT_SYMBOL(__drm_atomic_helper_connector_duplicate_state); diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c index 549b89501e01..2f9ebddd178e 100644 --- a/drivers/gpu/drm/drm_connector.c +++ b/drivers/gpu/drm/drm_connector.c @@ -87,6 +87,7 @@ static struct drm_conn_prop_enum_list drm_connector_enum_list[] = { { DRM_MODE_CONNECTOR_VIRTUAL, "Virtual" }, { DRM_MODE_CONNECTOR_DSI, "DSI" }, { DRM_MODE_CONNECTOR_DPI, "DPI" }, + { DRM_MODE_CONNECTOR_WRITEBACK, "Writeback" }, }; void drm_connector_ida_init(void) @@ -253,7 +254,8 @@ int drm_connector_init(struct drm_device *dev, config->num_connector++; spin_unlock_irq(&config->connector_list_lock); - if (connector_type != DRM_MODE_CONNECTOR_VIRTUAL) + if (connector_type != DRM_MODE_CONNECTOR_VIRTUAL && + connector_type != DRM_MODE_CONNECTOR_WRITEBACK) drm_object_attach_property(&connector->base, config->edid_property, 0); diff --git a/drivers/gpu/drm/drm_writeback.c b/drivers/gpu/drm/drm_writeback.c new file mode 100644 index 000000000000..e5b8a4b79724 --- /dev/null +++ b/drivers/gpu/drm/drm_writeback.c @@ -0,0 +1,245 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * (C) COPYRIGHT 2016 ARM Limited. All rights reserved. + * Author: Brian Starkey + * + * This program is free software and is provided to you under the terms of the + * GNU General Public License version 2 as published by the Free Software + * Foundation, and any use by you of this program is subject to the terms + * of such GNU licence. + */ + +#include +#include +#include +#include +#include + +/** + * DOC: overview + * + * Writeback connectors are used to expose hardware which can write the output + * from a CRTC to a memory buffer. They are used and act similarly to other + * types of connectors, with some important differences: + * - Writeback connectors don't provide a way to output visually to the user. + * - Writeback connectors should always report as "disconnected" (so that + * clients which don't understand them will ignore them). + * - Writeback connectors don't have EDID. + * + * A framebuffer may only be attached to a writeback connector when the + * connector is attached to a CRTC. The WRITEBACK_FB_ID property which sets the + * framebuffer applies only to a single commit (see below). A framebuffer may + * not be attached while the CRTC is off. + * + * Writeback connectors have some additional properties, which userspace + * can use to query and control them: + * + * "WRITEBACK_FB_ID": + * Write-only object property storing a DRM_MODE_OBJECT_FB: it stores the + * framebuffer to be written by the writeback connector. This property is + * similar to the FB_ID property on planes, but will always read as zero + * and is not preserved across commits. + * Userspace must set this property to an output buffer every time it + * wishes the buffer to get filled. + * + * "WRITEBACK_PIXEL_FORMATS": + * Immutable blob property to store the supported pixel formats table. The + * data is an array of u32 DRM_FORMAT_* fourcc values. + * Userspace can use this blob to find out what pixel formats are supported + * by the connector's writeback engine. + */ + +static int create_writeback_properties(struct drm_device *dev) +{ + struct drm_property *prop; + + if (!dev->mode_config.writeback_fb_id_property) { + prop = drm_property_create_object(dev, DRM_MODE_PROP_ATOMIC, + "WRITEBACK_FB_ID", + DRM_MODE_OBJECT_FB); + if (!prop) + return -ENOMEM; + dev->mode_config.writeback_fb_id_property = prop; + } + + if (!dev->mode_config.writeback_pixel_formats_property) { + prop = drm_property_create(dev, DRM_MODE_PROP_BLOB | + DRM_MODE_PROP_ATOMIC | + DRM_MODE_PROP_IMMUTABLE, + "WRITEBACK_PIXEL_FORMATS", 0); + if (!prop) + return -ENOMEM; + dev->mode_config.writeback_pixel_formats_property = prop; + } + + return 0; +} + +static const struct drm_encoder_funcs drm_writeback_encoder_funcs = { + .destroy = drm_encoder_cleanup, +}; + +/** + * drm_writeback_connector_init - Initialize a writeback connector and its properties + * @dev: DRM device + * @wb_connector: Writeback connector to initialize + * @con_funcs: Connector funcs vtable + * @enc_helper_funcs: Encoder helper funcs vtable to be used by the internal encoder + * @formats: Array of supported pixel formats for the writeback engine + * @n_formats: Length of the formats array + * + * This function creates the writeback-connector-specific properties if they + * have not been already created, initializes the connector as + * type DRM_MODE_CONNECTOR_WRITEBACK, and correctly initializes the property + * values. It will also create an internal encoder associated with the + * drm_writeback_connector and set it to use the @enc_helper_funcs vtable for + * the encoder helper. + * + * Drivers should always use this function instead of drm_connector_init() to + * set up writeback connectors. + * + * Returns: 0 on success, or a negative error code + */ +int drm_writeback_connector_init(struct drm_device *dev, + struct drm_writeback_connector *wb_connector, + const struct drm_connector_funcs *con_funcs, + const struct drm_encoder_helper_funcs *enc_helper_funcs, + const u32 *formats, int n_formats) +{ + struct drm_property_blob *blob; + struct drm_connector *connector = &wb_connector->base; + struct drm_mode_config *config = &dev->mode_config; + int ret = create_writeback_properties(dev); + + if (ret != 0) + return ret; + + blob = drm_property_create_blob(dev, n_formats * sizeof(*formats), + formats); + if (IS_ERR(blob)) + return PTR_ERR(blob); + + drm_encoder_helper_add(&wb_connector->encoder, enc_helper_funcs); + ret = drm_encoder_init(dev, &wb_connector->encoder, + &drm_writeback_encoder_funcs, + DRM_MODE_ENCODER_VIRTUAL, NULL); + if (ret) + goto fail; + + connector->interlace_allowed = 0; + + ret = drm_connector_init(dev, connector, con_funcs, + DRM_MODE_CONNECTOR_WRITEBACK); + if (ret) + goto connector_fail; + + ret = drm_mode_connector_attach_encoder(connector, + &wb_connector->encoder); + if (ret) + goto attach_fail; + + INIT_LIST_HEAD(&wb_connector->job_queue); + spin_lock_init(&wb_connector->job_lock); + + drm_object_attach_property(&connector->base, + config->writeback_fb_id_property, 0); + + drm_object_attach_property(&connector->base, + config->writeback_pixel_formats_property, + blob->base.id); + wb_connector->pixel_formats_blob_ptr = blob; + + return 0; + +attach_fail: + drm_connector_cleanup(connector); +connector_fail: + drm_encoder_cleanup(&wb_connector->encoder); +fail: + drm_property_blob_put(blob); + return ret; +} +EXPORT_SYMBOL(drm_writeback_connector_init); + +/** + * drm_writeback_queue_job - Queue a writeback job for later signalling + * @wb_connector: The writeback connector to queue a job on + * @job: The job to queue + * + * This function adds a job to the job_queue for a writeback connector. It + * should be considered to take ownership of the writeback job, and so any other + * references to the job must be cleared after calling this function. + * + * Drivers must ensure that for a given writeback connector, jobs are queued in + * exactly the same order as they will be completed by the hardware (and + * signaled via drm_writeback_signal_completion). + * + * For every call to drm_writeback_queue_job() there must be exactly one call to + * drm_writeback_signal_completion() + * + * See also: drm_writeback_signal_completion() + */ +void drm_writeback_queue_job(struct drm_writeback_connector *wb_connector, + struct drm_writeback_job *job) +{ + unsigned long flags; + + spin_lock_irqsave(&wb_connector->job_lock, flags); + list_add_tail(&job->list_entry, &wb_connector->job_queue); + spin_unlock_irqrestore(&wb_connector->job_lock, flags); +} +EXPORT_SYMBOL(drm_writeback_queue_job); + +/* + * @cleanup_work: deferred cleanup of a writeback job + * + * The job cannot be cleaned up directly in drm_writeback_signal_completion, + * because it may be called in interrupt context. Dropping the framebuffer + * reference can sleep, and so the cleanup is deferred to a workqueue. + */ +static void cleanup_work(struct work_struct *work) +{ + struct drm_writeback_job *job = container_of(work, + struct drm_writeback_job, + cleanup_work); + drm_framebuffer_put(job->fb); + kfree(job); +} + + +/** + * drm_writeback_signal_completion - Signal the completion of a writeback job + * @wb_connector: The writeback connector whose job is complete + * + * Drivers should call this to signal the completion of a previously queued + * writeback job. It should be called as soon as possible after the hardware + * has finished writing, and may be called from interrupt context. + * It is the driver's responsibility to ensure that for a given connector, the + * hardware completes writeback jobs in the same order as they are queued. + * + * Unless the driver is holding its own reference to the framebuffer, it must + * not be accessed after calling this function. + * + * See also: drm_writeback_queue_job() + */ +void +drm_writeback_signal_completion(struct drm_writeback_connector *wb_connector) +{ + unsigned long flags; + struct drm_writeback_job *job; + + spin_lock_irqsave(&wb_connector->job_lock, flags); + job = list_first_entry_or_null(&wb_connector->job_queue, + struct drm_writeback_job, + list_entry); + if (job) + list_del(&job->list_entry); + spin_unlock_irqrestore(&wb_connector->job_lock, flags); + + if (WARN_ON(!job)) + return; + + INIT_WORK(&job->cleanup_work, cleanup_work); + queue_work(system_long_wq, &job->cleanup_work); +} +EXPORT_SYMBOL(drm_writeback_signal_completion); diff --git a/include/drm/drm_atomic.h b/include/drm/drm_atomic.h index ca461b6cf71f..8254521b4583 100644 --- a/include/drm/drm_atomic.h +++ b/include/drm/drm_atomic.h @@ -594,6 +594,9 @@ void drm_atomic_set_fence_for_plane(struct drm_plane_state *plane_state, int __must_check drm_atomic_set_crtc_for_connector(struct drm_connector_state *conn_state, struct drm_crtc *crtc); +int drm_atomic_set_writeback_fb_for_connector( + struct drm_connector_state *conn_state, + struct drm_framebuffer *fb); int __must_check drm_atomic_add_affected_connectors(struct drm_atomic_state *state, struct drm_crtc *crtc); diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h index c5797c24edd3..716c3a0e0e1d 100644 --- a/include/drm/drm_connector.h +++ b/include/drm/drm_connector.h @@ -437,6 +437,19 @@ struct drm_connector_state { * protection. This is most commonly used for HDCP. */ unsigned int content_protection; + + /** + * @writeback_job: Writeback job for writeback connectors + * + * Holds the framebuffer for a writeback connector. As the writeback + * completion may be asynchronous to the normal commit cycle, the + * writeback job lifetime is managed separately from the normal atomic + * state by this object. + * + * See also: drm_writeback_queue_job() and + * drm_writeback_signal_completion() + */ + struct drm_writeback_job *writeback_job; }; /** diff --git a/include/drm/drm_mode_config.h b/include/drm/drm_mode_config.h index fb45839179dd..5f24329e6927 100644 --- a/include/drm/drm_mode_config.h +++ b/include/drm/drm_mode_config.h @@ -784,6 +784,21 @@ struct drm_mode_config { */ struct drm_property *panel_orientation_property; + /** + * @writeback_fb_id_property: Property for writeback connectors, storing + * the ID of the output framebuffer. + * See also: drm_writeback_connector_init() + */ + struct drm_property *writeback_fb_id_property; + + /** + * @writeback_pixel_formats_property: Property for writeback connectors, + * storing an array of the supported pixel formats for the writeback + * engine (read-only). + * See also: drm_writeback_connector_init() + */ + struct drm_property *writeback_pixel_formats_property; + /* dumb ioctl parameters */ uint32_t preferred_depth, prefer_shadow; diff --git a/include/drm/drm_modeset_helper_vtables.h b/include/drm/drm_modeset_helper_vtables.h index 35e2a3a79fc5..3b289773297c 100644 --- a/include/drm/drm_modeset_helper_vtables.h +++ b/include/drm/drm_modeset_helper_vtables.h @@ -974,6 +974,17 @@ struct drm_connector_helper_funcs { */ int (*atomic_check)(struct drm_connector *connector, struct drm_connector_state *state); + + /** + * @atomic_commit: + * + * This hook is to be used by drivers implementing writeback connectors + * that need a point when to commit the writeback job to the hardware. + * + * This callback is used by the atomic modeset helpers. + */ + void (*atomic_commit)(struct drm_connector *connector, + struct drm_writeback_job *writeback_job); }; /** diff --git a/include/drm/drm_writeback.h b/include/drm/drm_writeback.h new file mode 100644 index 000000000000..17cd1feecd7e --- /dev/null +++ b/include/drm/drm_writeback.h @@ -0,0 +1,91 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * (C) COPYRIGHT 2016 ARM Limited. All rights reserved. + * Author: Brian Starkey + * + * This program is free software and is provided to you under the terms of the + * GNU General Public License version 2 as published by the Free Software + * Foundation, and any use by you of this program is subject to the terms + * of such GNU licence. + */ + +#ifndef __DRM_WRITEBACK_H__ +#define __DRM_WRITEBACK_H__ +#include +#include +#include + +struct drm_writeback_connector { + struct drm_connector base; + + /** + * @encoder: Internal encoder used by the connector to fulfill + * the DRM framework requirements. The users of the + * @drm_writeback_connector control the behaviour of the @encoder + * by passing the @enc_funcs parameter to drm_writeback_connector_init() + * function. + */ + struct drm_encoder encoder; + + /** + * @pixel_formats_blob_ptr: + * + * DRM blob property data for the pixel formats list on writeback + * connectors + * See also drm_writeback_connector_init() + */ + struct drm_property_blob *pixel_formats_blob_ptr; + + /** @job_lock: Protects job_queue */ + spinlock_t job_lock; + + /** + * @job_queue: + * + * Holds a list of a connector's writeback jobs; the last item is the + * most recent. The first item may be either waiting for the hardware + * to begin writing, or currently being written. + * + * See also: drm_writeback_queue_job() and + * drm_writeback_signal_completion() + */ + struct list_head job_queue; +}; + +struct drm_writeback_job { + /** + * @cleanup_work: + * + * Used to allow drm_writeback_signal_completion to defer dropping the + * framebuffer reference to a workqueue + */ + struct work_struct cleanup_work; + + /** + * @list_entry: + * + * List item for the writeback connector's @job_queue + */ + struct list_head list_entry; + + /** + * @fb: + * + * Framebuffer to be written to by the writeback connector. Do not set + * directly, use drm_atomic_set_writeback_fb_for_connector() + */ + struct drm_framebuffer *fb; +}; + +int drm_writeback_connector_init(struct drm_device *dev, + struct drm_writeback_connector *wb_connector, + const struct drm_connector_funcs *con_funcs, + const struct drm_encoder_helper_funcs *enc_helper_funcs, + const u32 *formats, int n_formats); + +void drm_writeback_queue_job(struct drm_writeback_connector *wb_connector, + struct drm_writeback_job *job); + +void drm_writeback_cleanup_job(struct drm_writeback_job *job); +void drm_writeback_signal_completion(struct drm_writeback_connector *wb_connector); +#endif diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h index 971c016b368c..8d67243952f4 100644 --- a/include/uapi/drm/drm_mode.h +++ b/include/uapi/drm/drm_mode.h @@ -351,6 +351,7 @@ enum drm_mode_subconnector { #define DRM_MODE_CONNECTOR_VIRTUAL 15 #define DRM_MODE_CONNECTOR_DSI 16 #define DRM_MODE_CONNECTOR_DPI 17 +#define DRM_MODE_CONNECTOR_WRITEBACK 18 struct drm_mode_get_connector { -- cgit v1.2.3 From b13cc8dd588434e2aec781e6d12224e4c408ac18 Mon Sep 17 00:00:00 2001 From: Brian Starkey Date: Wed, 29 Mar 2017 17:42:33 +0100 Subject: drm: writeback: Add out-fences for writeback connectors Add the WRITEBACK_OUT_FENCE_PTR property to writeback connectors, to enable userspace to get a fence which will signal once the writeback is complete. It is not allowed to request an out-fence without a framebuffer attached to the connector. A timeline is added to drm_writeback_connector for use by the writeback out-fences. In the case of a commit failure or DRM_MODE_ATOMIC_TEST_ONLY, the fence is set to -1. Changes from v2: - Rebase onto Gustavo Padovan's v9 explicit sync series - Change out_fence_ptr type to s32 __user * - Set *out_fence_ptr to -1 in drm_atomic_connector_set_property - Store fence in drm_writeback_job Gustavo Padovan: - Move out_fence_ptr out of connector_state - Signal fence from drm_writeback_signal_completion instead of in driver directly Changes from v3: - Rebase onto commit 7e9081c5aac7 ("drm/fence: fix memory overwrite when setting out_fence fd") (change out_fence_ptr to s32 __user *, for real this time.) - Update documentation around WRITEBACK_OUT_FENCE_PTR Signed-off-by: Brian Starkey [rebased and fixed conflicts] Signed-off-by: Mihail Atanassov Signed-off-by: Liviu Dudau Reviewed-by: Eric Anholt Reviewed-by: Sean Paul Link: https://patchwork.freedesktop.org/patch/229036/ --- drivers/gpu/drm/drm_atomic.c | 99 ++++++++++++++++++++++++++++++++---- drivers/gpu/drm/drm_writeback.c | 109 +++++++++++++++++++++++++++++++++++++++- include/drm/drm_atomic.h | 8 +++ include/drm/drm_connector.h | 8 +-- include/drm/drm_mode_config.h | 8 +++ include/drm/drm_writeback.h | 41 ++++++++++++++- 6 files changed, 257 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c index 3e53d6e5c340..115719059434 100644 --- a/drivers/gpu/drm/drm_atomic.c +++ b/drivers/gpu/drm/drm_atomic.c @@ -318,6 +318,35 @@ static s32 __user *get_out_fence_for_crtc(struct drm_atomic_state *state, return fence_ptr; } +static int set_out_fence_for_connector(struct drm_atomic_state *state, + struct drm_connector *connector, + s32 __user *fence_ptr) +{ + unsigned int index = drm_connector_index(connector); + + if (!fence_ptr) + return 0; + + if (put_user(-1, fence_ptr)) + return -EFAULT; + + state->connectors[index].out_fence_ptr = fence_ptr; + + return 0; +} + +static s32 __user *get_out_fence_for_connector(struct drm_atomic_state *state, + struct drm_connector *connector) +{ + unsigned int index = drm_connector_index(connector); + s32 __user *fence_ptr; + + fence_ptr = state->connectors[index].out_fence_ptr; + state->connectors[index].out_fence_ptr = NULL; + + return fence_ptr; +} + /** * drm_atomic_set_mode_for_crtc - set mode for CRTC * @state: the CRTC whose incoming state to update @@ -727,6 +756,12 @@ static int drm_atomic_connector_check(struct drm_connector *connector, return -EINVAL; } + if (writeback_job->out_fence && !writeback_job->fb) { + DRM_DEBUG_ATOMIC("[CONNECTOR:%d:%s] requesting out-fence without framebuffer\n", + connector->base.id, connector->name); + return -EINVAL; + } + return 0; } @@ -1367,6 +1402,11 @@ static int drm_atomic_connector_set_property(struct drm_connector *connector, if (fb) drm_framebuffer_put(fb); return ret; + } else if (property == config->writeback_out_fence_ptr_property) { + s32 __user *fence_ptr = u64_to_user_ptr(val); + + return set_out_fence_for_connector(state->state, connector, + fence_ptr); } else if (connector->funcs->atomic_set_property) { return connector->funcs->atomic_set_property(connector, state, property, val); @@ -1456,6 +1496,8 @@ drm_atomic_connector_get_property(struct drm_connector *connector, } else if (property == config->writeback_fb_id_property) { /* Writeback framebuffer is one-shot, write and forget */ *val = 0; + } else if (property == config->writeback_out_fence_ptr_property) { + *val = 0; } else if (connector->funcs->atomic_get_property) { return connector->funcs->atomic_get_property(connector, state, property, val); @@ -2292,7 +2334,7 @@ static int setup_out_fence(struct drm_out_fence_state *fence_state, return 0; } -static int prepare_crtc_signaling(struct drm_device *dev, +static int prepare_signaling(struct drm_device *dev, struct drm_atomic_state *state, struct drm_mode_atomic *arg, struct drm_file *file_priv, @@ -2301,6 +2343,8 @@ static int prepare_crtc_signaling(struct drm_device *dev, { struct drm_crtc *crtc; struct drm_crtc_state *crtc_state; + struct drm_connector *conn; + struct drm_connector_state *conn_state; int i, c = 0, ret; if (arg->flags & DRM_MODE_ATOMIC_TEST_ONLY) @@ -2366,6 +2410,43 @@ static int prepare_crtc_signaling(struct drm_device *dev, c++; } + for_each_new_connector_in_state(state, conn, conn_state, i) { + struct drm_writeback_job *job; + struct drm_out_fence_state *f; + struct dma_fence *fence; + s32 __user *fence_ptr; + + fence_ptr = get_out_fence_for_connector(state, conn); + if (!fence_ptr) + continue; + + job = drm_atomic_get_writeback_job(conn_state); + if (!job) + return -ENOMEM; + + f = krealloc(*fence_state, sizeof(**fence_state) * + (*num_fences + 1), GFP_KERNEL); + if (!f) + return -ENOMEM; + + memset(&f[*num_fences], 0, sizeof(*f)); + + f[*num_fences].out_fence_ptr = fence_ptr; + *fence_state = f; + + fence = drm_writeback_get_out_fence((struct drm_writeback_connector *)conn); + if (!fence) + return -ENOMEM; + + ret = setup_out_fence(&f[(*num_fences)++], fence); + if (ret) { + dma_fence_put(fence); + return ret; + } + + job->out_fence = fence; + } + /* * Having this flag means user mode pends on event which will never * reach due to lack of at least one CRTC for signaling @@ -2376,11 +2457,11 @@ static int prepare_crtc_signaling(struct drm_device *dev, return 0; } -static void complete_crtc_signaling(struct drm_device *dev, - struct drm_atomic_state *state, - struct drm_out_fence_state *fence_state, - unsigned int num_fences, - bool install_fds) +static void complete_signaling(struct drm_device *dev, + struct drm_atomic_state *state, + struct drm_out_fence_state *fence_state, + unsigned int num_fences, + bool install_fds) { struct drm_crtc *crtc; struct drm_crtc_state *crtc_state; @@ -2550,8 +2631,8 @@ retry: drm_mode_object_put(obj); } - ret = prepare_crtc_signaling(dev, state, arg, file_priv, &fence_state, - &num_fences); + ret = prepare_signaling(dev, state, arg, file_priv, &fence_state, + &num_fences); if (ret) goto out; @@ -2567,7 +2648,7 @@ retry: } out: - complete_crtc_signaling(dev, state, fence_state, num_fences, !ret); + complete_signaling(dev, state, fence_state, num_fences, !ret); if (ret == -EDEADLK) { drm_atomic_state_clear(state); diff --git a/drivers/gpu/drm/drm_writeback.c b/drivers/gpu/drm/drm_writeback.c index e5b8a4b79724..827395071f0b 100644 --- a/drivers/gpu/drm/drm_writeback.c +++ b/drivers/gpu/drm/drm_writeback.c @@ -14,6 +14,7 @@ #include #include #include +#include /** * DOC: overview @@ -31,6 +32,16 @@ * framebuffer applies only to a single commit (see below). A framebuffer may * not be attached while the CRTC is off. * + * Unlike with planes, when a writeback framebuffer is removed by userspace DRM + * makes no attempt to remove it from active use by the connector. This is + * because no method is provided to abort a writeback operation, and in any + * case making a new commit whilst a writeback is ongoing is undefined (see + * WRITEBACK_OUT_FENCE_PTR below). As soon as the current writeback is finished, + * the framebuffer will automatically no longer be in active use. As it will + * also have already been removed from the framebuffer list, there will be no + * way for any userspace application to retrieve a reference to it in the + * intervening period. + * * Writeback connectors have some additional properties, which userspace * can use to query and control them: * @@ -47,8 +58,54 @@ * data is an array of u32 DRM_FORMAT_* fourcc values. * Userspace can use this blob to find out what pixel formats are supported * by the connector's writeback engine. + * + * "WRITEBACK_OUT_FENCE_PTR": + * Userspace can use this property to provide a pointer for the kernel to + * fill with a sync_file file descriptor, which will signal once the + * writeback is finished. The value should be the address of a 32-bit + * signed integer, cast to a u64. + * Userspace should wait for this fence to signal before making another + * commit affecting any of the same CRTCs, Planes or Connectors. + * **Failure to do so will result in undefined behaviour.** + * For this reason it is strongly recommended that all userspace + * applications making use of writeback connectors *always* retrieve an + * out-fence for the commit and use it appropriately. + * From userspace, this property will always read as zero. */ +#define fence_to_wb_connector(x) container_of(x->lock, \ + struct drm_writeback_connector, \ + fence_lock) + +static const char *drm_writeback_fence_get_driver_name(struct dma_fence *fence) +{ + struct drm_writeback_connector *wb_connector = + fence_to_wb_connector(fence); + + return wb_connector->base.dev->driver->name; +} + +static const char * +drm_writeback_fence_get_timeline_name(struct dma_fence *fence) +{ + struct drm_writeback_connector *wb_connector = + fence_to_wb_connector(fence); + + return wb_connector->timeline_name; +} + +static bool drm_writeback_fence_enable_signaling(struct dma_fence *fence) +{ + return true; +} + +static const struct dma_fence_ops drm_writeback_fence_ops = { + .get_driver_name = drm_writeback_fence_get_driver_name, + .get_timeline_name = drm_writeback_fence_get_timeline_name, + .enable_signaling = drm_writeback_fence_enable_signaling, + .wait = dma_fence_default_wait, +}; + static int create_writeback_properties(struct drm_device *dev) { struct drm_property *prop; @@ -72,6 +129,15 @@ static int create_writeback_properties(struct drm_device *dev) dev->mode_config.writeback_pixel_formats_property = prop; } + if (!dev->mode_config.writeback_out_fence_ptr_property) { + prop = drm_property_create_range(dev, DRM_MODE_PROP_ATOMIC, + "WRITEBACK_OUT_FENCE_PTR", 0, + U64_MAX); + if (!prop) + return -ENOMEM; + dev->mode_config.writeback_out_fence_ptr_property = prop; + } + return 0; } @@ -141,6 +207,15 @@ int drm_writeback_connector_init(struct drm_device *dev, INIT_LIST_HEAD(&wb_connector->job_queue); spin_lock_init(&wb_connector->job_lock); + wb_connector->fence_context = dma_fence_context_alloc(1); + spin_lock_init(&wb_connector->fence_lock); + snprintf(wb_connector->timeline_name, + sizeof(wb_connector->timeline_name), + "CONNECTOR:%d-%s", connector->base.id, connector->name); + + drm_object_attach_property(&connector->base, + config->writeback_out_fence_ptr_property, 0); + drm_object_attach_property(&connector->base, config->writeback_fb_id_property, 0); @@ -210,6 +285,7 @@ static void cleanup_work(struct work_struct *work) /** * drm_writeback_signal_completion - Signal the completion of a writeback job * @wb_connector: The writeback connector whose job is complete + * @status: Status code to set in the writeback out_fence (0 for success) * * Drivers should call this to signal the completion of a previously queued * writeback job. It should be called as soon as possible after the hardware @@ -223,7 +299,8 @@ static void cleanup_work(struct work_struct *work) * See also: drm_writeback_queue_job() */ void -drm_writeback_signal_completion(struct drm_writeback_connector *wb_connector) +drm_writeback_signal_completion(struct drm_writeback_connector *wb_connector, + int status) { unsigned long flags; struct drm_writeback_job *job; @@ -232,8 +309,15 @@ drm_writeback_signal_completion(struct drm_writeback_connector *wb_connector) job = list_first_entry_or_null(&wb_connector->job_queue, struct drm_writeback_job, list_entry); - if (job) + if (job) { list_del(&job->list_entry); + if (job->out_fence) { + if (status) + dma_fence_set_error(job->out_fence, status); + dma_fence_signal(job->out_fence); + dma_fence_put(job->out_fence); + } + } spin_unlock_irqrestore(&wb_connector->job_lock, flags); if (WARN_ON(!job)) @@ -243,3 +327,24 @@ drm_writeback_signal_completion(struct drm_writeback_connector *wb_connector) queue_work(system_long_wq, &job->cleanup_work); } EXPORT_SYMBOL(drm_writeback_signal_completion); + +struct dma_fence * +drm_writeback_get_out_fence(struct drm_writeback_connector *wb_connector) +{ + struct dma_fence *fence; + + if (WARN_ON(wb_connector->base.connector_type != + DRM_MODE_CONNECTOR_WRITEBACK)) + return NULL; + + fence = kzalloc(sizeof(*fence), GFP_KERNEL); + if (!fence) + return NULL; + + dma_fence_init(fence, &drm_writeback_fence_ops, + &wb_connector->fence_lock, wb_connector->fence_context, + ++wb_connector->fence_seqno); + + return fence; +} +EXPORT_SYMBOL(drm_writeback_get_out_fence); diff --git a/include/drm/drm_atomic.h b/include/drm/drm_atomic.h index 8254521b4583..da9d95a19580 100644 --- a/include/drm/drm_atomic.h +++ b/include/drm/drm_atomic.h @@ -160,6 +160,14 @@ struct __drm_crtcs_state { struct __drm_connnectors_state { struct drm_connector *ptr; struct drm_connector_state *state, *old_state, *new_state; + /** + * @out_fence_ptr: + * + * User-provided pointer which the kernel uses to return a sync_file + * file descriptor. Used by writeback connectors to signal completion of + * the writeback. + */ + s32 __user *out_fence_ptr; }; struct drm_private_obj; diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h index 716c3a0e0e1d..14ab58ade87f 100644 --- a/include/drm/drm_connector.h +++ b/include/drm/drm_connector.h @@ -441,10 +441,10 @@ struct drm_connector_state { /** * @writeback_job: Writeback job for writeback connectors * - * Holds the framebuffer for a writeback connector. As the writeback - * completion may be asynchronous to the normal commit cycle, the - * writeback job lifetime is managed separately from the normal atomic - * state by this object. + * Holds the framebuffer and out-fence for a writeback connector. As + * the writeback completion may be asynchronous to the normal commit + * cycle, the writeback job lifetime is managed separately from the + * normal atomic state by this object. * * See also: drm_writeback_queue_job() and * drm_writeback_signal_completion() diff --git a/include/drm/drm_mode_config.h b/include/drm/drm_mode_config.h index 5f24329e6927..f4a173c8d79c 100644 --- a/include/drm/drm_mode_config.h +++ b/include/drm/drm_mode_config.h @@ -798,6 +798,14 @@ struct drm_mode_config { * See also: drm_writeback_connector_init() */ struct drm_property *writeback_pixel_formats_property; + /** + * @writeback_out_fence_ptr_property: Property for writeback connectors, + * fd pointer representing the outgoing fences for a writeback + * connector. Userspace should provide a pointer to a value of type s32, + * and then cast that pointer to u64. + * See also: drm_writeback_connector_init() + */ + struct drm_property *writeback_out_fence_ptr_property; /* dumb ioctl parameters */ uint32_t preferred_depth, prefer_shadow; diff --git a/include/drm/drm_writeback.h b/include/drm/drm_writeback.h index 17cd1feecd7e..a10fe556dfd4 100644 --- a/include/drm/drm_writeback.h +++ b/include/drm/drm_writeback.h @@ -50,6 +50,32 @@ struct drm_writeback_connector { * drm_writeback_signal_completion() */ struct list_head job_queue; + + /** + * @fence_context: + * + * timeline context used for fence operations. + */ + unsigned int fence_context; + /** + * @fence_lock: + * + * spinlock to protect the fences in the fence_context. + */ + spinlock_t fence_lock; + /** + * @fence_seqno: + * + * Seqno variable used as monotonic counter for the fences + * created on the connector's timeline. + */ + unsigned long fence_seqno; + /** + * @timeline_name: + * + * The name of the connector's fence timeline. + */ + char timeline_name[32]; }; struct drm_writeback_job { @@ -75,6 +101,13 @@ struct drm_writeback_job { * directly, use drm_atomic_set_writeback_fb_for_connector() */ struct drm_framebuffer *fb; + + /** + * @out_fence: + * + * Fence which will signal once the writeback has completed + */ + struct dma_fence *out_fence; }; int drm_writeback_connector_init(struct drm_device *dev, @@ -87,5 +120,11 @@ void drm_writeback_queue_job(struct drm_writeback_connector *wb_connector, struct drm_writeback_job *job); void drm_writeback_cleanup_job(struct drm_writeback_job *job); -void drm_writeback_signal_completion(struct drm_writeback_connector *wb_connector); + +void +drm_writeback_signal_completion(struct drm_writeback_connector *wb_connector, + int status); + +struct dma_fence * +drm_writeback_get_out_fence(struct drm_writeback_connector *wb_connector); #endif -- cgit v1.2.3 From d67b6a2065076d763c7df626b8c54f16038ad862 Mon Sep 17 00:00:00 2001 From: Liviu Dudau Date: Wed, 28 Feb 2018 14:11:23 +0000 Subject: drm: writeback: Add client capability for exposing writeback connectors Due to the fact that writeback connectors behave in a special way in DRM (they always report being disconnected) we might confuse some userspace. Add a client capability for writeback connectors that will filter them out for clients that don't understand the capability. Changelog: - only accept the capability if the client has already set the DRM_CLIENT_CAP_ATOMIC one. Cc: Sean Paul Cc: Brian Starkey Signed-off-by: Liviu Dudau Reviewed-by: Eric Anholt Reviewed-by: Brian Starkey Link: https://patchwork.freedesktop.org/patch/229038/ --- drivers/gpu/drm/drm_ioctl.c | 7 +++++++ drivers/gpu/drm/drm_mode_config.c | 5 +++++ include/drm/drm_file.h | 7 +++++++ include/uapi/drm/drm.h | 9 +++++++++ 4 files changed, 28 insertions(+) (limited to 'include') diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c index 0d4cfb232576..fe49fb0356b5 100644 --- a/drivers/gpu/drm/drm_ioctl.c +++ b/drivers/gpu/drm/drm_ioctl.c @@ -334,6 +334,13 @@ drm_setclientcap(struct drm_device *dev, void *data, struct drm_file *file_priv) return -EINVAL; file_priv->aspect_ratio_allowed = req->value; break; + case DRM_CLIENT_CAP_WRITEBACK_CONNECTORS: + if (!file_priv->atomic) + return -EINVAL; + if (req->value > 1) + return -EINVAL; + file_priv->writeback_connectors = req->value; + break; default: return -EINVAL; } diff --git a/drivers/gpu/drm/drm_mode_config.c b/drivers/gpu/drm/drm_mode_config.c index e5c653357024..21e353bd3948 100644 --- a/drivers/gpu/drm/drm_mode_config.c +++ b/drivers/gpu/drm/drm_mode_config.c @@ -145,6 +145,11 @@ int drm_mode_getresources(struct drm_device *dev, void *data, count = 0; connector_id = u64_to_user_ptr(card_res->connector_id_ptr); drm_for_each_connector_iter(connector, &conn_iter) { + /* only expose writeback connectors if userspace understands them */ + if (!file_priv->writeback_connectors && + (connector->connector_type == DRM_MODE_CONNECTOR_WRITEBACK)) + continue; + if (drm_lease_held(file_priv, connector->base.id)) { if (count < card_res->count_connectors && put_user(connector->base.id, connector_id + count)) { diff --git a/include/drm/drm_file.h b/include/drm/drm_file.h index 027ac16da3d1..26485acc51d7 100644 --- a/include/drm/drm_file.h +++ b/include/drm/drm_file.h @@ -192,6 +192,13 @@ struct drm_file { */ unsigned aspect_ratio_allowed:1; + /** + * @writeback_connectors: + * + * True if client understands writeback connectors + */ + unsigned writeback_connectors:1; + /** * @is_master: * diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h index 9c660e1688ab..300f336633f2 100644 --- a/include/uapi/drm/drm.h +++ b/include/uapi/drm/drm.h @@ -687,6 +687,15 @@ struct drm_get_cap { */ #define DRM_CLIENT_CAP_ASPECT_RATIO 4 +/** + * DRM_CLIENT_CAP_WRITEBACK_CONNECTORS + * + * If set to 1, the DRM core will expose special connectors to be used for + * writing back to memory the scene setup in the commit. Depends on client + * also supporting DRM_CLIENT_CAP_ATOMIC + */ +#define DRM_CLIENT_CAP_WRITEBACK_CONNECTORS 5 + /** DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */ struct drm_set_client_cap { __u64 capability; -- cgit v1.2.3 From c03cea42149de56fbae2301d7123daaa2cfe80e2 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 19 Jun 2018 15:10:58 -0700 Subject: iomap: add initial support for writes without buffer heads For now just limited to blocksize == PAGE_SIZE, where we can simply read in the full page in write begin, and just set the whole page dirty after copying data into it. This code is enabled by default and XFS will now be feed pages without buffer heads in ->writepage and ->writepages. If a file system sets the IOMAP_F_BUFFER_HEAD flag on the iomap the old path will still be used, this both helps the transition in XFS and prepares for the gfs2 migration to the iomap infrastructure. Signed-off-by: Christoph Hellwig Reviewed-by: Brian Foster Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/iomap.c | 115 +++++++++++++++++++++++++++++++++++++++++++++++--- fs/xfs/xfs_iomap.c | 6 ++- include/linux/iomap.h | 2 + 3 files changed, 114 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/fs/iomap.c b/fs/iomap.c index 4f10c6b1cf6d..2ebff76039b5 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -348,6 +348,48 @@ iomap_write_failed(struct inode *inode, loff_t pos, unsigned len) truncate_pagecache_range(inode, max(pos, i_size), pos + len); } +static int +iomap_read_page_sync(struct inode *inode, loff_t block_start, struct page *page, + unsigned poff, unsigned plen, unsigned from, unsigned to, + struct iomap *iomap) +{ + struct bio_vec bvec; + struct bio bio; + + if (iomap->type != IOMAP_MAPPED || block_start >= i_size_read(inode)) { + zero_user_segments(page, poff, from, to, poff + plen); + return 0; + } + + bio_init(&bio, &bvec, 1); + bio.bi_opf = REQ_OP_READ; + bio.bi_iter.bi_sector = iomap_sector(iomap, block_start); + bio_set_dev(&bio, iomap->bdev); + __bio_add_page(&bio, page, plen, poff); + return submit_bio_wait(&bio); +} + +static int +__iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, + struct page *page, struct iomap *iomap) +{ + loff_t block_size = i_blocksize(inode); + loff_t block_start = pos & ~(block_size - 1); + loff_t block_end = (pos + len + block_size - 1) & ~(block_size - 1); + unsigned poff = block_start & (PAGE_SIZE - 1); + unsigned plen = min_t(loff_t, PAGE_SIZE - poff, block_end - block_start); + unsigned from = pos & (PAGE_SIZE - 1), to = from + len; + + WARN_ON_ONCE(i_blocksize(inode) < PAGE_SIZE); + + if (PageUptodate(page)) + return 0; + if (from <= poff && to >= poff + plen) + return 0; + return iomap_read_page_sync(inode, block_start, page, + poff, plen, from, to, iomap); +} + static int iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags, struct page **pagep, struct iomap *iomap) @@ -367,9 +409,10 @@ iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags, if (iomap->type == IOMAP_INLINE) iomap_read_inline_data(inode, page, iomap); - else + else if (iomap->flags & IOMAP_F_BUFFER_HEAD) status = __block_write_begin_int(page, pos, len, NULL, iomap); - + else + status = __iomap_write_begin(inode, pos, len, page, iomap); if (unlikely(status)) { unlock_page(page); put_page(page); @@ -382,6 +425,57 @@ iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags, return status; } +int +iomap_set_page_dirty(struct page *page) +{ + struct address_space *mapping = page_mapping(page); + int newly_dirty; + + if (unlikely(!mapping)) + return !TestSetPageDirty(page); + + /* + * Lock out page->mem_cgroup migration to keep PageDirty + * synchronized with per-memcg dirty page counters. + */ + lock_page_memcg(page); + newly_dirty = !TestSetPageDirty(page); + if (newly_dirty) + __set_page_dirty(page, mapping, 0); + unlock_page_memcg(page); + + if (newly_dirty) + __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); + return newly_dirty; +} +EXPORT_SYMBOL_GPL(iomap_set_page_dirty); + +static int +__iomap_write_end(struct inode *inode, loff_t pos, unsigned len, + unsigned copied, struct page *page, struct iomap *iomap) +{ + flush_dcache_page(page); + + /* + * The blocks that were entirely written will now be uptodate, so we + * don't have to worry about a readpage reading them and overwriting a + * partial write. However if we have encountered a short write and only + * partially written into a block, it will not be marked uptodate, so a + * readpage might come in and destroy our partial write. + * + * Do the simplest thing, and just treat any short write to a non + * uptodate page as a zero-length write, and force the caller to redo + * the whole thing. + */ + if (unlikely(copied < len && !PageUptodate(page))) { + copied = 0; + } else { + SetPageUptodate(page); + iomap_set_page_dirty(page); + } + return __generic_write_end(inode, pos, copied, page); +} + static int iomap_write_end_inline(struct inode *inode, struct page *page, struct iomap *iomap, loff_t pos, unsigned copied) @@ -408,9 +502,11 @@ iomap_write_end(struct inode *inode, loff_t pos, unsigned len, if (iomap->type == IOMAP_INLINE) { ret = iomap_write_end_inline(inode, page, iomap, pos, copied); - } else { + } else if (iomap->flags & IOMAP_F_BUFFER_HEAD) { ret = generic_write_end(NULL, inode->i_mapping, pos, len, copied, page, NULL); + } else { + ret = __iomap_write_end(inode, pos, len, copied, page, iomap); } if (iomap->page_done) @@ -703,11 +799,16 @@ iomap_page_mkwrite_actor(struct inode *inode, loff_t pos, loff_t length, struct page *page = data; int ret; - ret = __block_write_begin_int(page, pos, length, NULL, iomap); - if (ret) - return ret; + if (iomap->flags & IOMAP_F_BUFFER_HEAD) { + ret = __block_write_begin_int(page, pos, length, NULL, iomap); + if (ret) + return ret; + block_commit_write(page, 0, length); + } else { + WARN_ON_ONCE(!PageUptodate(page)); + WARN_ON_ONCE(i_blocksize(inode) < PAGE_SIZE); + } - block_commit_write(page, 0, length); return length; } diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 49f5492eed3b..8a3613d576af 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -626,7 +626,7 @@ retry: * Flag newly allocated delalloc blocks with IOMAP_F_NEW so we punch * them out if the write happens to fail. */ - iomap->flags = IOMAP_F_NEW; + iomap->flags |= IOMAP_F_NEW; trace_xfs_iomap_alloc(ip, offset, count, 0, &got); done: if (isnullstartblock(got.br_startblock)) @@ -1019,6 +1019,8 @@ xfs_file_iomap_begin( if (XFS_FORCED_SHUTDOWN(mp)) return -EIO; + iomap->flags |= IOMAP_F_BUFFER_HEAD; + if (((flags & (IOMAP_WRITE | IOMAP_DIRECT)) == IOMAP_WRITE) && !IS_DAX(inode) && !xfs_get_extsz_hint(ip)) { /* Reserve delalloc blocks for regular writeback. */ @@ -1119,7 +1121,7 @@ xfs_file_iomap_begin( if (error) return error; - iomap->flags = IOMAP_F_NEW; + iomap->flags |= IOMAP_F_NEW; trace_xfs_iomap_alloc(ip, offset, length, 0, &imap); out_finish: diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 30d314407f66..5eb9ca8d7ce5 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -30,6 +30,7 @@ struct vm_fault; */ #define IOMAP_F_NEW 0x01 /* blocks have been newly allocated */ #define IOMAP_F_DIRTY 0x02 /* uncommitted metadata */ +#define IOMAP_F_BUFFER_HEAD 0x04 /* file system requires buffer heads */ /* * Flags that only need to be reported for IOMAP_REPORT requests: @@ -102,6 +103,7 @@ ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from, int iomap_readpage(struct page *page, const struct iomap_ops *ops); int iomap_readpages(struct address_space *mapping, struct list_head *pages, unsigned nr_pages, const struct iomap_ops *ops); +int iomap_set_page_dirty(struct page *page); int iomap_file_dirty(struct inode *inode, loff_t pos, loff_t len, const struct iomap_ops *ops); int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, -- cgit v1.2.3 From 17dbca119312b4e8173d4e25ff64262119fcef38 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 13 Jun 2018 15:48:26 -0700 Subject: x86/speculation/l1tf: Add sysfs reporting for l1tf L1TF core kernel workarounds are cheap and normally always enabled, However they still should be reported in sysfs if the system is vulnerable or mitigated. Add the necessary CPU feature/bug bits. - Extend the existing checks for Meltdowns to determine if the system is vulnerable. All CPUs which are not vulnerable to Meltdown are also not vulnerable to L1TF - Check for 32bit non PAE and emit a warning as there is no practical way for mitigation due to the limited physical address bits - If the system has more than MAX_PA/2 physical memory the invert page workarounds don't protect the system against the L1TF attack anymore, because an inverted physical address will also point to valid memory. Print a warning in this case and report that the system is vulnerable. Add a function which returns the PFN limit for the L1TF mitigation, which will be used in follow up patches for sanity and range checks. [ tglx: Renamed the CPU feature bit to L1TF_PTEINV ] Signed-off-by: Andi Kleen Signed-off-by: Thomas Gleixner Reviewed-by: Josh Poimboeuf Acked-by: Dave Hansen --- arch/x86/include/asm/cpufeatures.h | 2 ++ arch/x86/include/asm/processor.h | 5 +++++ arch/x86/kernel/cpu/bugs.c | 40 ++++++++++++++++++++++++++++++++++++++ arch/x86/kernel/cpu/common.c | 20 +++++++++++++++++++ drivers/base/cpu.c | 8 ++++++++ include/linux/cpu.h | 2 ++ 6 files changed, 77 insertions(+) (limited to 'include') diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 5701f5cecd31..f41cf9df4a83 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -219,6 +219,7 @@ #define X86_FEATURE_IBPB ( 7*32+26) /* Indirect Branch Prediction Barrier */ #define X86_FEATURE_STIBP ( 7*32+27) /* Single Thread Indirect Branch Predictors */ #define X86_FEATURE_ZEN ( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */ +#define X86_FEATURE_L1TF_PTEINV ( 7*32+29) /* "" L1TF workaround PTE inversion */ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ @@ -373,5 +374,6 @@ #define X86_BUG_SPECTRE_V1 X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */ #define X86_BUG_SPECTRE_V2 X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */ #define X86_BUG_SPEC_STORE_BYPASS X86_BUG(17) /* CPU is affected by speculative store bypass attack */ +#define X86_BUG_L1TF X86_BUG(18) /* CPU is affected by L1 Terminal Fault */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index cfd29ee8c3da..7e3ac5eedcd6 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -181,6 +181,11 @@ extern const struct seq_operations cpuinfo_op; extern void cpu_detect(struct cpuinfo_x86 *c); +static inline unsigned long l1tf_pfn_limit(void) +{ + return BIT(boot_cpu_data.x86_phys_bits - 1 - PAGE_SHIFT) - 1; +} + extern void early_cpu_init(void); extern void identify_boot_cpu(void); extern void identify_secondary_cpu(struct cpuinfo_x86 *); diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index cd0fda1fff6d..3ce9674e4887 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -27,9 +27,11 @@ #include #include #include +#include static void __init spectre_v2_select_mitigation(void); static void __init ssb_select_mitigation(void); +static void __init l1tf_select_mitigation(void); /* * Our boot-time value of the SPEC_CTRL MSR. We read it once so that any @@ -81,6 +83,8 @@ void __init check_bugs(void) */ ssb_select_mitigation(); + l1tf_select_mitigation(); + #ifdef CONFIG_X86_32 /* * Check whether we are able to run this kernel safely on SMP. @@ -205,6 +209,32 @@ static void x86_amd_ssb_disable(void) wrmsrl(MSR_AMD64_LS_CFG, msrval); } +static void __init l1tf_select_mitigation(void) +{ + u64 half_pa; + + if (!boot_cpu_has_bug(X86_BUG_L1TF)) + return; + +#if CONFIG_PGTABLE_LEVELS == 2 + pr_warn("Kernel not compiled for PAE. No mitigation for L1TF\n"); + return; +#endif + + /* + * This is extremely unlikely to happen because almost all + * systems have far more MAX_PA/2 than RAM can be fit into + * DIMM slots. + */ + half_pa = (u64)l1tf_pfn_limit() << PAGE_SHIFT; + if (e820__mapped_any(half_pa, ULLONG_MAX - half_pa, E820_TYPE_RAM)) { + pr_warn("System has more than MAX_PA/2 memory. L1TF mitigation not effective.\n"); + return; + } + + setup_force_cpu_cap(X86_FEATURE_L1TF_PTEINV); +} + #ifdef RETPOLINE static bool spectre_v2_bad_module; @@ -678,6 +708,11 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_SPEC_STORE_BYPASS: return sprintf(buf, "%s\n", ssb_strings[ssb_mode]); + case X86_BUG_L1TF: + if (boot_cpu_has(X86_FEATURE_L1TF_PTEINV)) + return sprintf(buf, "Mitigation: Page Table Inversion\n"); + break; + default: break; } @@ -704,4 +739,9 @@ ssize_t cpu_show_spec_store_bypass(struct device *dev, struct device_attribute * { return cpu_show_common(dev, attr, buf, X86_BUG_SPEC_STORE_BYPASS); } + +ssize_t cpu_show_l1tf(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_L1TF); +} #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 0df7151cfef4..9baf684e2b55 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -984,6 +984,21 @@ static const __initconst struct x86_cpu_id cpu_no_spec_store_bypass[] = { {} }; +static const __initconst struct x86_cpu_id cpu_no_l1tf[] = { + /* in addition to cpu_no_speculation */ + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT1 }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT2 }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_AIRMONT }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_MERRIFIELD }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_MOOREFIELD }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GOLDMONT }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_DENVERTON }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GEMINI_LAKE }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNL }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNM }, + {} +}; + static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) { u64 ia32_cap = 0; @@ -1010,6 +1025,11 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) return; setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN); + + if (x86_match_cpu(cpu_no_l1tf)) + return; + + setup_force_cpu_bug(X86_BUG_L1TF); } /* diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 30cc9c877ebb..eb9443d5bae1 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -540,16 +540,24 @@ ssize_t __weak cpu_show_spec_store_bypass(struct device *dev, return sprintf(buf, "Not affected\n"); } +ssize_t __weak cpu_show_l1tf(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sprintf(buf, "Not affected\n"); +} + static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL); static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL); static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL); static DEVICE_ATTR(spec_store_bypass, 0444, cpu_show_spec_store_bypass, NULL); +static DEVICE_ATTR(l1tf, 0444, cpu_show_l1tf, NULL); static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_meltdown.attr, &dev_attr_spectre_v1.attr, &dev_attr_spectre_v2.attr, &dev_attr_spec_store_bypass.attr, + &dev_attr_l1tf.attr, NULL }; diff --git a/include/linux/cpu.h b/include/linux/cpu.h index a97a63eef59f..d3da5184aa1c 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -55,6 +55,8 @@ extern ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t cpu_show_spec_store_bypass(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_l1tf(struct device *dev, + struct device_attribute *attr, char *buf); extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, -- cgit v1.2.3 From 42e4089c7890725fcd329999252dc489b72f2921 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 13 Jun 2018 15:48:27 -0700 Subject: x86/speculation/l1tf: Disallow non privileged high MMIO PROT_NONE mappings For L1TF PROT_NONE mappings are protected by inverting the PFN in the page table entry. This sets the high bits in the CPU's address space, thus making sure to point to not point an unmapped entry to valid cached memory. Some server system BIOSes put the MMIO mappings high up in the physical address space. If such an high mapping was mapped to unprivileged users they could attack low memory by setting such a mapping to PROT_NONE. This could happen through a special device driver which is not access protected. Normal /dev/mem is of course access protected. To avoid this forbid PROT_NONE mappings or mprotect for high MMIO mappings. Valid page mappings are allowed because the system is then unsafe anyways. It's not expected that users commonly use PROT_NONE on MMIO. But to minimize any impact this is only enforced if the mapping actually refers to a high MMIO address (defined as the MAX_PA-1 bit being set), and also skip the check for root. For mmaps this is straight forward and can be handled in vm_insert_pfn and in remap_pfn_range(). For mprotect it's a bit trickier. At the point where the actual PTEs are accessed a lot of state has been changed and it would be difficult to undo on an error. Since this is a uncommon case use a separate early page talk walk pass for MMIO PROT_NONE mappings that checks for this condition early. For non MMIO and non PROT_NONE there are no changes. Signed-off-by: Andi Kleen Signed-off-by: Thomas Gleixner Reviewed-by: Josh Poimboeuf Acked-by: Dave Hansen --- arch/x86/include/asm/pgtable.h | 8 +++++++ arch/x86/mm/mmap.c | 21 ++++++++++++++++++ include/asm-generic/pgtable.h | 12 +++++++++++ mm/memory.c | 37 ++++++++++++++++++++++--------- mm/mprotect.c | 49 ++++++++++++++++++++++++++++++++++++++++++ 5 files changed, 117 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index a9c89cb1a9c5..6a090a76fdca 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -1338,6 +1338,14 @@ static inline bool pud_access_permitted(pud_t pud, bool write) return __pte_access_permitted(pud_val(pud), write); } +#define __HAVE_ARCH_PFN_MODIFY_ALLOWED 1 +extern bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot); + +static inline bool arch_has_pfn_modify_check(void) +{ + return boot_cpu_has_bug(X86_BUG_L1TF); +} + #include #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 48c591251600..f40ab8185d94 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -240,3 +240,24 @@ int valid_mmap_phys_addr_range(unsigned long pfn, size_t count) return phys_addr_valid(addr + count - 1); } + +/* + * Only allow root to set high MMIO mappings to PROT_NONE. + * This prevents an unpriv. user to set them to PROT_NONE and invert + * them, then pointing to valid memory for L1TF speculation. + * + * Note: for locked down kernels may want to disable the root override. + */ +bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot) +{ + if (!boot_cpu_has_bug(X86_BUG_L1TF)) + return true; + if (!__pte_needs_invert(pgprot_val(prot))) + return true; + /* If it's real memory always allow */ + if (pfn_valid(pfn)) + return true; + if (pfn > l1tf_pfn_limit() && !capable(CAP_SYS_ADMIN)) + return false; + return true; +} diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index f59639afaa39..0ecc1197084b 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -1097,4 +1097,16 @@ static inline void init_espfix_bsp(void) { } #endif #endif +#ifndef __HAVE_ARCH_PFN_MODIFY_ALLOWED +static inline bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot) +{ + return true; +} + +static inline bool arch_has_pfn_modify_check(void) +{ + return false; +} +#endif + #endif /* _ASM_GENERIC_PGTABLE_H */ diff --git a/mm/memory.c b/mm/memory.c index 7206a634270b..3ba81b44a542 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1886,6 +1886,9 @@ int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, if (addr < vma->vm_start || addr >= vma->vm_end) return -EFAULT; + if (!pfn_modify_allowed(pfn, pgprot)) + return -EACCES; + track_pfn_insert(vma, &pgprot, __pfn_to_pfn_t(pfn, PFN_DEV)); ret = insert_pfn(vma, addr, __pfn_to_pfn_t(pfn, PFN_DEV), pgprot, @@ -1921,6 +1924,9 @@ static int __vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, track_pfn_insert(vma, &pgprot, pfn); + if (!pfn_modify_allowed(pfn_t_to_pfn(pfn), pgprot)) + return -EACCES; + /* * If we don't have pte special, then we have to use the pfn_valid() * based VM_MIXEDMAP scheme (see vm_normal_page), and thus we *must* @@ -1982,6 +1988,7 @@ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd, { pte_t *pte; spinlock_t *ptl; + int err = 0; pte = pte_alloc_map_lock(mm, pmd, addr, &ptl); if (!pte) @@ -1989,12 +1996,16 @@ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd, arch_enter_lazy_mmu_mode(); do { BUG_ON(!pte_none(*pte)); + if (!pfn_modify_allowed(pfn, prot)) { + err = -EACCES; + break; + } set_pte_at(mm, addr, pte, pte_mkspecial(pfn_pte(pfn, prot))); pfn++; } while (pte++, addr += PAGE_SIZE, addr != end); arch_leave_lazy_mmu_mode(); pte_unmap_unlock(pte - 1, ptl); - return 0; + return err; } static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud, @@ -2003,6 +2014,7 @@ static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud, { pmd_t *pmd; unsigned long next; + int err; pfn -= addr >> PAGE_SHIFT; pmd = pmd_alloc(mm, pud, addr); @@ -2011,9 +2023,10 @@ static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud, VM_BUG_ON(pmd_trans_huge(*pmd)); do { next = pmd_addr_end(addr, end); - if (remap_pte_range(mm, pmd, addr, next, - pfn + (addr >> PAGE_SHIFT), prot)) - return -ENOMEM; + err = remap_pte_range(mm, pmd, addr, next, + pfn + (addr >> PAGE_SHIFT), prot); + if (err) + return err; } while (pmd++, addr = next, addr != end); return 0; } @@ -2024,6 +2037,7 @@ static inline int remap_pud_range(struct mm_struct *mm, p4d_t *p4d, { pud_t *pud; unsigned long next; + int err; pfn -= addr >> PAGE_SHIFT; pud = pud_alloc(mm, p4d, addr); @@ -2031,9 +2045,10 @@ static inline int remap_pud_range(struct mm_struct *mm, p4d_t *p4d, return -ENOMEM; do { next = pud_addr_end(addr, end); - if (remap_pmd_range(mm, pud, addr, next, - pfn + (addr >> PAGE_SHIFT), prot)) - return -ENOMEM; + err = remap_pmd_range(mm, pud, addr, next, + pfn + (addr >> PAGE_SHIFT), prot); + if (err) + return err; } while (pud++, addr = next, addr != end); return 0; } @@ -2044,6 +2059,7 @@ static inline int remap_p4d_range(struct mm_struct *mm, pgd_t *pgd, { p4d_t *p4d; unsigned long next; + int err; pfn -= addr >> PAGE_SHIFT; p4d = p4d_alloc(mm, pgd, addr); @@ -2051,9 +2067,10 @@ static inline int remap_p4d_range(struct mm_struct *mm, pgd_t *pgd, return -ENOMEM; do { next = p4d_addr_end(addr, end); - if (remap_pud_range(mm, p4d, addr, next, - pfn + (addr >> PAGE_SHIFT), prot)) - return -ENOMEM; + err = remap_pud_range(mm, p4d, addr, next, + pfn + (addr >> PAGE_SHIFT), prot); + if (err) + return err; } while (p4d++, addr = next, addr != end); return 0; } diff --git a/mm/mprotect.c b/mm/mprotect.c index 625608bc8962..6d331620b9e5 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -306,6 +306,42 @@ unsigned long change_protection(struct vm_area_struct *vma, unsigned long start, return pages; } +static int prot_none_pte_entry(pte_t *pte, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + return pfn_modify_allowed(pte_pfn(*pte), *(pgprot_t *)(walk->private)) ? + 0 : -EACCES; +} + +static int prot_none_hugetlb_entry(pte_t *pte, unsigned long hmask, + unsigned long addr, unsigned long next, + struct mm_walk *walk) +{ + return pfn_modify_allowed(pte_pfn(*pte), *(pgprot_t *)(walk->private)) ? + 0 : -EACCES; +} + +static int prot_none_test(unsigned long addr, unsigned long next, + struct mm_walk *walk) +{ + return 0; +} + +static int prot_none_walk(struct vm_area_struct *vma, unsigned long start, + unsigned long end, unsigned long newflags) +{ + pgprot_t new_pgprot = vm_get_page_prot(newflags); + struct mm_walk prot_none_walk = { + .pte_entry = prot_none_pte_entry, + .hugetlb_entry = prot_none_hugetlb_entry, + .test_walk = prot_none_test, + .mm = current->mm, + .private = &new_pgprot, + }; + + return walk_page_range(start, end, &prot_none_walk); +} + int mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev, unsigned long start, unsigned long end, unsigned long newflags) @@ -323,6 +359,19 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev, return 0; } + /* + * Do PROT_NONE PFN permission checks here when we can still + * bail out without undoing a lot of state. This is a rather + * uncommon case, so doesn't need to be very optimized. + */ + if (arch_has_pfn_modify_check() && + (vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) && + (newflags & (VM_READ|VM_WRITE|VM_EXEC)) == 0) { + error = prot_none_walk(vma, start, end, newflags); + if (error) + return error; + } + /* * If we make a private mapping writable we increase our commit; * but (without finer accounting) cannot reduce our commit if we -- cgit v1.2.3 From 377eeaa8e11fe815b1d07c81c4a0e2843a8c15eb Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 13 Jun 2018 15:48:28 -0700 Subject: x86/speculation/l1tf: Limit swap file size to MAX_PA/2 For the L1TF workaround its necessary to limit the swap file size to below MAX_PA/2, so that the higher bits of the swap offset inverted never point to valid memory. Add a mechanism for the architecture to override the swap file size check in swapfile.c and add a x86 specific max swapfile check function that enforces that limit. The check is only enabled if the CPU is vulnerable to L1TF. In VMs with 42bit MAX_PA the typical limit is 2TB now, on a native system with 46bit PA it is 32TB. The limit is only per individual swap file, so it's always possible to exceed these limits with multiple swap files or partitions. Signed-off-by: Andi Kleen Signed-off-by: Thomas Gleixner Reviewed-by: Josh Poimboeuf Acked-by: Michal Hocko Acked-by: Dave Hansen --- arch/x86/mm/init.c | 15 +++++++++++++++ include/linux/swapfile.h | 2 ++ mm/swapfile.c | 46 ++++++++++++++++++++++++++++++---------------- 3 files changed, 47 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index cee58a972cb2..1b530197d114 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -4,6 +4,8 @@ #include #include #include /* for max_low_pfn */ +#include +#include #include #include @@ -880,3 +882,16 @@ void update_cache_mode_entry(unsigned entry, enum page_cache_mode cache) __cachemode2pte_tbl[cache] = __cm_idx2pte(entry); __pte2cachemode_tbl[entry] = cache; } + +unsigned long max_swapfile_size(void) +{ + unsigned long pages; + + pages = generic_max_swapfile_size(); + + if (boot_cpu_has_bug(X86_BUG_L1TF)) { + /* Limit the swap file size to MAX_PA/2 for L1TF workaround */ + pages = min_t(unsigned long, l1tf_pfn_limit() + 1, pages); + } + return pages; +} diff --git a/include/linux/swapfile.h b/include/linux/swapfile.h index 06bd7b096167..e06febf62978 100644 --- a/include/linux/swapfile.h +++ b/include/linux/swapfile.h @@ -10,5 +10,7 @@ extern spinlock_t swap_lock; extern struct plist_head swap_active_head; extern struct swap_info_struct *swap_info[]; extern int try_to_unuse(unsigned int, bool, unsigned long); +extern unsigned long generic_max_swapfile_size(void); +extern unsigned long max_swapfile_size(void); #endif /* _LINUX_SWAPFILE_H */ diff --git a/mm/swapfile.c b/mm/swapfile.c index 2cc2972eedaf..18185ae4f223 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2909,6 +2909,35 @@ static int claim_swapfile(struct swap_info_struct *p, struct inode *inode) return 0; } + +/* + * Find out how many pages are allowed for a single swap device. There + * are two limiting factors: + * 1) the number of bits for the swap offset in the swp_entry_t type, and + * 2) the number of bits in the swap pte, as defined by the different + * architectures. + * + * In order to find the largest possible bit mask, a swap entry with + * swap type 0 and swap offset ~0UL is created, encoded to a swap pte, + * decoded to a swp_entry_t again, and finally the swap offset is + * extracted. + * + * This will mask all the bits from the initial ~0UL mask that can't + * be encoded in either the swp_entry_t or the architecture definition + * of a swap pte. + */ +unsigned long generic_max_swapfile_size(void) +{ + return swp_offset(pte_to_swp_entry( + swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1; +} + +/* Can be overridden by an architecture for additional checks. */ +__weak unsigned long max_swapfile_size(void) +{ + return generic_max_swapfile_size(); +} + static unsigned long read_swap_header(struct swap_info_struct *p, union swap_header *swap_header, struct inode *inode) @@ -2944,22 +2973,7 @@ static unsigned long read_swap_header(struct swap_info_struct *p, p->cluster_next = 1; p->cluster_nr = 0; - /* - * Find out how many pages are allowed for a single swap - * device. There are two limiting factors: 1) the number - * of bits for the swap offset in the swp_entry_t type, and - * 2) the number of bits in the swap pte as defined by the - * different architectures. In order to find the - * largest possible bit mask, a swap entry with swap type 0 - * and swap offset ~0UL is created, encoded to a swap pte, - * decoded to a swp_entry_t again, and finally the swap - * offset is extracted. This will mask all the bits from - * the initial ~0UL mask that can't be encoded in either - * the swp_entry_t or the architecture definition of a - * swap pte. - */ - maxpages = swp_offset(pte_to_swp_entry( - swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1; + maxpages = max_swapfile_size(); last_page = swap_header->info.last_page; if (!last_page) { pr_warn("Empty swap-file\n"); -- cgit v1.2.3 From 5a6cf77f5e35e7af35d36a1e7dc21a42f6412e4f Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Wed, 20 Jun 2018 01:05:07 +0900 Subject: kprobes: Remove jprobe API implementation Remove functionally empty jprobe API implementations and test cases. Signed-off-by: Masami Hiramatsu Acked-by: Thomas Gleixner Cc: Ananth N Mavinakayanahalli Cc: Andrew Morton Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Steven Rostedt Cc: linux-arch@vger.kernel.org Link: https://lore.kernel.org/lkml/152942430705.15209.2307050500995264322.stgit@devbox Signed-off-by: Ingo Molnar --- include/linux/kprobes.h | 3 -- kernel/kprobes.c | 78 +--------------------------------------- kernel/test_kprobes.c | 94 ------------------------------------------------- lib/Kconfig.debug | 2 +- 4 files changed, 2 insertions(+), 175 deletions(-) (limited to 'include') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 9440a2fc8893..b520baa65682 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -389,9 +389,6 @@ int register_kprobe(struct kprobe *p); void unregister_kprobe(struct kprobe *p); int register_kprobes(struct kprobe **kps, int num); void unregister_kprobes(struct kprobe **kps, int num); -int setjmp_pre_handler(struct kprobe *, struct pt_regs *); -int longjmp_break_handler(struct kprobe *, struct pt_regs *); -void jprobe_return(void); unsigned long arch_deref_entry_point(void *); int register_kretprobe(struct kretprobe *rp); diff --git a/kernel/kprobes.c b/kernel/kprobes.c index ea619021d901..69de130595f7 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1272,7 +1272,7 @@ NOKPROBE_SYMBOL(cleanup_rp_inst); /* * Add the new probe to ap->list. Fail if this is the -* second jprobe at the address - two jprobes can't coexist +* second break_handler at the address */ static int add_new_kprobe(struct kprobe *ap, struct kprobe *p) { @@ -1812,77 +1812,6 @@ unsigned long __weak arch_deref_entry_point(void *entry) return (unsigned long)entry; } -#if 0 -int register_jprobes(struct jprobe **jps, int num) -{ - int ret = 0, i; - - if (num <= 0) - return -EINVAL; - - for (i = 0; i < num; i++) { - ret = register_jprobe(jps[i]); - - if (ret < 0) { - if (i > 0) - unregister_jprobes(jps, i); - break; - } - } - - return ret; -} -EXPORT_SYMBOL_GPL(register_jprobes); - -int register_jprobe(struct jprobe *jp) -{ - unsigned long addr, offset; - struct kprobe *kp = &jp->kp; - - /* - * Verify probepoint as well as the jprobe handler are - * valid function entry points. - */ - addr = arch_deref_entry_point(jp->entry); - - if (kallsyms_lookup_size_offset(addr, NULL, &offset) && offset == 0 && - kprobe_on_func_entry(kp->addr, kp->symbol_name, kp->offset)) { - kp->pre_handler = setjmp_pre_handler; - kp->break_handler = longjmp_break_handler; - return register_kprobe(kp); - } - - return -EINVAL; -} -EXPORT_SYMBOL_GPL(register_jprobe); - -void unregister_jprobe(struct jprobe *jp) -{ - unregister_jprobes(&jp, 1); -} -EXPORT_SYMBOL_GPL(unregister_jprobe); - -void unregister_jprobes(struct jprobe **jps, int num) -{ - int i; - - if (num <= 0) - return; - mutex_lock(&kprobe_mutex); - for (i = 0; i < num; i++) - if (__unregister_kprobe_top(&jps[i]->kp) < 0) - jps[i]->kp.addr = NULL; - mutex_unlock(&kprobe_mutex); - - synchronize_sched(); - for (i = 0; i < num; i++) { - if (jps[i]->kp.addr) - __unregister_kprobe_bottom(&jps[i]->kp); - } -} -EXPORT_SYMBOL_GPL(unregister_jprobes); -#endif - #ifdef CONFIG_KRETPROBES /* * This kprobe pre_handler is registered with every kretprobe. When probe @@ -2329,8 +2258,6 @@ static void report_probe(struct seq_file *pi, struct kprobe *p, if (p->pre_handler == pre_handler_kretprobe) kprobe_type = "r"; - else if (p->pre_handler == setjmp_pre_handler) - kprobe_type = "j"; else kprobe_type = "k"; @@ -2637,6 +2564,3 @@ late_initcall(debugfs_kprobe_init); #endif /* CONFIG_DEBUG_FS */ module_init(init_kprobes); - -/* defined in arch/.../kernel/kprobes.c */ -EXPORT_SYMBOL_GPL(jprobe_return); diff --git a/kernel/test_kprobes.c b/kernel/test_kprobes.c index dd53e354f630..7bca480151b0 100644 --- a/kernel/test_kprobes.c +++ b/kernel/test_kprobes.c @@ -162,90 +162,6 @@ static int test_kprobes(void) } -#if 0 -static u32 jph_val; - -static u32 j_kprobe_target(u32 value) -{ - if (preemptible()) { - handler_errors++; - pr_err("jprobe-handler is preemptible\n"); - } - if (value != rand1) { - handler_errors++; - pr_err("incorrect value in jprobe handler\n"); - } - - jph_val = rand1; - jprobe_return(); - return 0; -} - -static struct jprobe jp = { - .entry = j_kprobe_target, - .kp.symbol_name = "kprobe_target" -}; - -static int test_jprobe(void) -{ - int ret; - - ret = register_jprobe(&jp); - if (ret < 0) { - pr_err("register_jprobe returned %d\n", ret); - return ret; - } - - ret = target(rand1); - unregister_jprobe(&jp); - if (jph_val == 0) { - pr_err("jprobe handler not called\n"); - handler_errors++; - } - - return 0; -} - -static struct jprobe jp2 = { - .entry = j_kprobe_target, - .kp.symbol_name = "kprobe_target2" -}; - -static int test_jprobes(void) -{ - int ret; - struct jprobe *jps[2] = {&jp, &jp2}; - - /* addr and flags should be cleard for reusing kprobe. */ - jp.kp.addr = NULL; - jp.kp.flags = 0; - ret = register_jprobes(jps, 2); - if (ret < 0) { - pr_err("register_jprobes returned %d\n", ret); - return ret; - } - - jph_val = 0; - ret = target(rand1); - if (jph_val == 0) { - pr_err("jprobe handler not called\n"); - handler_errors++; - } - - jph_val = 0; - ret = target2(rand1); - if (jph_val == 0) { - pr_err("jprobe handler2 not called\n"); - handler_errors++; - } - unregister_jprobes(jps, 2); - - return 0; -} -#else -#define test_jprobe() (0) -#define test_jprobes() (0) -#endif #ifdef CONFIG_KRETPROBES static u32 krph_val; @@ -383,16 +299,6 @@ int init_test_probes(void) if (ret < 0) errors++; - num_tests++; - ret = test_jprobe(); - if (ret < 0) - errors++; - - num_tests++; - ret = test_jprobes(); - if (ret < 0) - errors++; - #ifdef CONFIG_KRETPROBES num_tests++; ret = test_kretprobe(); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 8838d1158d19..0b066b3c9284 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1718,7 +1718,7 @@ config KPROBES_SANITY_TEST default n help This option provides for testing basic kprobes functionality on - boot. A sample kprobe, jprobe and kretprobe are inserted and + boot. Samples of kprobe and kretprobe are inserted and verified for functionality. Say N if you are unsure. -- cgit v1.2.3 From 4de58696de076d9bd2745d1cbe0930635c3f5ac9 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Wed, 20 Jun 2018 01:17:15 +0900 Subject: kprobes: Remove jprobe stub API Remove jprobe stub APIs from linux/kprobes.h since the jprobe implementation was completely gone. Signed-off-by: Masami Hiramatsu Acked-by: Thomas Gleixner Cc: Ananth N Mavinakayanahalli Cc: Andrew Morton Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Steven Rostedt Cc: linux-arch@vger.kernel.org Link: https://lore.kernel.org/lkml/152942503572.15209.1652552217914694917.stgit@devbox Signed-off-by: Ingo Molnar --- include/linux/kprobes.h | 50 ------------------------------------------------- 1 file changed, 50 deletions(-) (limited to 'include') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index b520baa65682..e909413e4e38 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -63,7 +63,6 @@ struct pt_regs; struct kretprobe; struct kretprobe_instance; typedef int (*kprobe_pre_handler_t) (struct kprobe *, struct pt_regs *); -typedef int (*kprobe_break_handler_t) (struct kprobe *, struct pt_regs *); typedef void (*kprobe_post_handler_t) (struct kprobe *, struct pt_regs *, unsigned long flags); typedef int (*kprobe_fault_handler_t) (struct kprobe *, struct pt_regs *, @@ -101,12 +100,6 @@ struct kprobe { */ kprobe_fault_handler_t fault_handler; - /* - * ... called if breakpoint trap occurs in probe handler. - * Return 1 if it handled break, otherwise kernel will see it. - */ - kprobe_break_handler_t break_handler; - /* Saved opcode (which has been replaced with breakpoint) */ kprobe_opcode_t opcode; @@ -154,24 +147,6 @@ static inline int kprobe_ftrace(struct kprobe *p) return p->flags & KPROBE_FLAG_FTRACE; } -/* - * Special probe type that uses setjmp-longjmp type tricks to resume - * execution at a specified entry with a matching prototype corresponding - * to the probed function - a trick to enable arguments to become - * accessible seamlessly by probe handling logic. - * Note: - * Because of the way compilers allocate stack space for local variables - * etc upfront, regardless of sub-scopes within a function, this mirroring - * principle currently works only for probes placed on function entry points. - */ -struct jprobe { - struct kprobe kp; - void *entry; /* probe handling code to jump to */ -}; - -/* For backward compatibility with old code using JPROBE_ENTRY() */ -#define JPROBE_ENTRY(handler) (handler) - /* * Function-return probe - * Note: @@ -436,9 +411,6 @@ static inline void unregister_kprobe(struct kprobe *p) static inline void unregister_kprobes(struct kprobe **kps, int num) { } -static inline void jprobe_return(void) -{ -} static inline int register_kretprobe(struct kretprobe *rp) { return -ENOSYS; @@ -465,20 +437,6 @@ static inline int enable_kprobe(struct kprobe *kp) return -ENOSYS; } #endif /* CONFIG_KPROBES */ -static inline int register_jprobe(struct jprobe *p) -{ - return -ENOSYS; -} -static inline int register_jprobes(struct jprobe **jps, int num) -{ - return -ENOSYS; -} -static inline void unregister_jprobe(struct jprobe *p) -{ -} -static inline void unregister_jprobes(struct jprobe **jps, int num) -{ -} static inline int disable_kretprobe(struct kretprobe *rp) { return disable_kprobe(&rp->kp); @@ -487,14 +445,6 @@ static inline int enable_kretprobe(struct kretprobe *rp) { return enable_kprobe(&rp->kp); } -static inline int disable_jprobe(struct jprobe *jp) -{ - return -ENOSYS; -} -static inline int enable_jprobe(struct jprobe *jp) -{ - return -ENOSYS; -} #ifndef CONFIG_KPROBES static inline bool is_kprobe_insn_slot(unsigned long addr) -- cgit v1.2.3 From 8bd9cb51daac89337295b6f037b0486911e1b408 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 19 Jun 2018 13:53:08 +0100 Subject: locking/atomics, asm-generic: Move some macros from to a new file In preparation for implementing the asm-generic atomic bitops in terms of atomic_long_*(), we need to prevent implementations from pulling in . A common reason for this include is for the BITS_PER_BYTE definition, so move this and some other BIT() and masking macros into a new header file, . Signed-off-by: Will Deacon Acked-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-arm-kernel@lists.infradead.org Cc: yamada.masahiro@socionext.com Link: https://lore.kernel.org/lkml/1529412794-17720-4-git-send-email-will.deacon@arm.com Signed-off-by: Ingo Molnar --- include/linux/bitops.h | 22 +--------------------- include/linux/bits.h | 26 ++++++++++++++++++++++++++ 2 files changed, 27 insertions(+), 21 deletions(-) create mode 100644 include/linux/bits.h (limited to 'include') diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 4cac4e1a72ff..af419012d77d 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -2,29 +2,9 @@ #ifndef _LINUX_BITOPS_H #define _LINUX_BITOPS_H #include +#include -#ifdef __KERNEL__ -#define BIT(nr) (1UL << (nr)) -#define BIT_ULL(nr) (1ULL << (nr)) -#define BIT_MASK(nr) (1UL << ((nr) % BITS_PER_LONG)) -#define BIT_WORD(nr) ((nr) / BITS_PER_LONG) -#define BIT_ULL_MASK(nr) (1ULL << ((nr) % BITS_PER_LONG_LONG)) -#define BIT_ULL_WORD(nr) ((nr) / BITS_PER_LONG_LONG) -#define BITS_PER_BYTE 8 #define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long)) -#endif - -/* - * Create a contiguous bitmask starting at bit position @l and ending at - * position @h. For example - * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000. - */ -#define GENMASK(h, l) \ - (((~0UL) - (1UL << (l)) + 1) & (~0UL >> (BITS_PER_LONG - 1 - (h)))) - -#define GENMASK_ULL(h, l) \ - (((~0ULL) - (1ULL << (l)) + 1) & \ - (~0ULL >> (BITS_PER_LONG_LONG - 1 - (h)))) extern unsigned int __sw_hweight8(unsigned int w); extern unsigned int __sw_hweight16(unsigned int w); diff --git a/include/linux/bits.h b/include/linux/bits.h new file mode 100644 index 000000000000..2b7b532c1d51 --- /dev/null +++ b/include/linux/bits.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_BITS_H +#define __LINUX_BITS_H +#include + +#define BIT(nr) (1UL << (nr)) +#define BIT_ULL(nr) (1ULL << (nr)) +#define BIT_MASK(nr) (1UL << ((nr) % BITS_PER_LONG)) +#define BIT_WORD(nr) ((nr) / BITS_PER_LONG) +#define BIT_ULL_MASK(nr) (1ULL << ((nr) % BITS_PER_LONG_LONG)) +#define BIT_ULL_WORD(nr) ((nr) / BITS_PER_LONG_LONG) +#define BITS_PER_BYTE 8 + +/* + * Create a contiguous bitmask starting at bit position @l and ending at + * position @h. For example + * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000. + */ +#define GENMASK(h, l) \ + (((~0UL) - (1UL << (l)) + 1) & (~0UL >> (BITS_PER_LONG - 1 - (h)))) + +#define GENMASK_ULL(h, l) \ + (((~0ULL) - (1ULL << (l)) + 1) & \ + (~0ULL >> (BITS_PER_LONG_LONG - 1 - (h)))) + +#endif /* __LINUX_BITS_H */ -- cgit v1.2.3 From e986a0d6cb36b54838b2f5f8ac2bb5f9baadd977 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 19 Jun 2018 13:53:11 +0100 Subject: locking/atomics, asm-generic/bitops/atomic.h: Rewrite using atomic_*() APIs The atomic bitops can actually be implemented pretty efficiently using the atomic_*() ops, rather than explicit use of spinlocks. Signed-off-by: Will Deacon Acked-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-arm-kernel@lists.infradead.org Cc: yamada.masahiro@socionext.com Link: https://lore.kernel.org/lkml/1529412794-17720-7-git-send-email-will.deacon@arm.com Signed-off-by: Ingo Molnar --- include/asm-generic/bitops/atomic.h | 188 +++++++----------------------------- 1 file changed, 33 insertions(+), 155 deletions(-) (limited to 'include') diff --git a/include/asm-generic/bitops/atomic.h b/include/asm-generic/bitops/atomic.h index 04deffaf5f7d..dd90c9792909 100644 --- a/include/asm-generic/bitops/atomic.h +++ b/include/asm-generic/bitops/atomic.h @@ -2,189 +2,67 @@ #ifndef _ASM_GENERIC_BITOPS_ATOMIC_H_ #define _ASM_GENERIC_BITOPS_ATOMIC_H_ -#include -#include - -#ifdef CONFIG_SMP -#include -#include /* we use L1_CACHE_BYTES */ - -/* Use an array of spinlocks for our atomic_ts. - * Hash function to index into a different SPINLOCK. - * Since "a" is usually an address, use one spinlock per cacheline. - */ -# define ATOMIC_HASH_SIZE 4 -# define ATOMIC_HASH(a) (&(__atomic_hash[ (((unsigned long) a)/L1_CACHE_BYTES) & (ATOMIC_HASH_SIZE-1) ])) - -extern arch_spinlock_t __atomic_hash[ATOMIC_HASH_SIZE] __lock_aligned; - -/* Can't use raw_spin_lock_irq because of #include problems, so - * this is the substitute */ -#define _atomic_spin_lock_irqsave(l,f) do { \ - arch_spinlock_t *s = ATOMIC_HASH(l); \ - local_irq_save(f); \ - arch_spin_lock(s); \ -} while(0) - -#define _atomic_spin_unlock_irqrestore(l,f) do { \ - arch_spinlock_t *s = ATOMIC_HASH(l); \ - arch_spin_unlock(s); \ - local_irq_restore(f); \ -} while(0) - - -#else -# define _atomic_spin_lock_irqsave(l,f) do { local_irq_save(f); } while (0) -# define _atomic_spin_unlock_irqrestore(l,f) do { local_irq_restore(f); } while (0) -#endif +#include +#include +#include /* - * NMI events can occur at any time, including when interrupts have been - * disabled by *_irqsave(). So you can get NMI events occurring while a - * *_bit function is holding a spin lock. If the NMI handler also wants - * to do bit manipulation (and they do) then you can get a deadlock - * between the original caller of *_bit() and the NMI handler. - * - * by Keith Owens + * Implementation of atomic bitops using atomic-fetch ops. + * See Documentation/atomic_bitops.txt for details. */ -/** - * set_bit - Atomically set a bit in memory - * @nr: the bit to set - * @addr: the address to start counting from - * - * This function is atomic and may not be reordered. See __set_bit() - * if you do not require the atomic guarantees. - * - * Note: there are no guarantees that this function will not be reordered - * on non x86 architectures, so if you are writing portable code, - * make sure not to rely on its reordering guarantees. - * - * Note that @nr may be almost arbitrarily large; this function is not - * restricted to acting on a single-word quantity. - */ -static inline void set_bit(int nr, volatile unsigned long *addr) +static inline void set_bit(unsigned int nr, volatile unsigned long *p) { - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); - unsigned long flags; - - _atomic_spin_lock_irqsave(p, flags); - *p |= mask; - _atomic_spin_unlock_irqrestore(p, flags); + p += BIT_WORD(nr); + atomic_long_or(BIT_MASK(nr), (atomic_long_t *)p); } -/** - * clear_bit - Clears a bit in memory - * @nr: Bit to clear - * @addr: Address to start counting from - * - * clear_bit() is atomic and may not be reordered. However, it does - * not contain a memory barrier, so if it is used for locking purposes, - * you should call smp_mb__before_atomic() and/or smp_mb__after_atomic() - * in order to ensure changes are visible on other processors. - */ -static inline void clear_bit(int nr, volatile unsigned long *addr) +static inline void clear_bit(unsigned int nr, volatile unsigned long *p) { - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); - unsigned long flags; - - _atomic_spin_lock_irqsave(p, flags); - *p &= ~mask; - _atomic_spin_unlock_irqrestore(p, flags); + p += BIT_WORD(nr); + atomic_long_andnot(BIT_MASK(nr), (atomic_long_t *)p); } -/** - * change_bit - Toggle a bit in memory - * @nr: Bit to change - * @addr: Address to start counting from - * - * change_bit() is atomic and may not be reordered. It may be - * reordered on other architectures than x86. - * Note that @nr may be almost arbitrarily large; this function is not - * restricted to acting on a single-word quantity. - */ -static inline void change_bit(int nr, volatile unsigned long *addr) +static inline void change_bit(unsigned int nr, volatile unsigned long *p) { - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); - unsigned long flags; - - _atomic_spin_lock_irqsave(p, flags); - *p ^= mask; - _atomic_spin_unlock_irqrestore(p, flags); + p += BIT_WORD(nr); + atomic_long_xor(BIT_MASK(nr), (atomic_long_t *)p); } -/** - * test_and_set_bit - Set a bit and return its old value - * @nr: Bit to set - * @addr: Address to count from - * - * This operation is atomic and cannot be reordered. - * It may be reordered on other architectures than x86. - * It also implies a memory barrier. - */ -static inline int test_and_set_bit(int nr, volatile unsigned long *addr) +static inline int test_and_set_bit(unsigned int nr, volatile unsigned long *p) { + long old; unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); - unsigned long old; - unsigned long flags; - _atomic_spin_lock_irqsave(p, flags); - old = *p; - *p = old | mask; - _atomic_spin_unlock_irqrestore(p, flags); + p += BIT_WORD(nr); + if (READ_ONCE(*p) & mask) + return 1; - return (old & mask) != 0; + old = atomic_long_fetch_or(mask, (atomic_long_t *)p); + return !!(old & mask); } -/** - * test_and_clear_bit - Clear a bit and return its old value - * @nr: Bit to clear - * @addr: Address to count from - * - * This operation is atomic and cannot be reordered. - * It can be reorderdered on other architectures other than x86. - * It also implies a memory barrier. - */ -static inline int test_and_clear_bit(int nr, volatile unsigned long *addr) +static inline int test_and_clear_bit(unsigned int nr, volatile unsigned long *p) { + long old; unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); - unsigned long old; - unsigned long flags; - _atomic_spin_lock_irqsave(p, flags); - old = *p; - *p = old & ~mask; - _atomic_spin_unlock_irqrestore(p, flags); + p += BIT_WORD(nr); + if (!(READ_ONCE(*p) & mask)) + return 0; - return (old & mask) != 0; + old = atomic_long_fetch_andnot(mask, (atomic_long_t *)p); + return !!(old & mask); } -/** - * test_and_change_bit - Change a bit and return its old value - * @nr: Bit to change - * @addr: Address to count from - * - * This operation is atomic and cannot be reordered. - * It also implies a memory barrier. - */ -static inline int test_and_change_bit(int nr, volatile unsigned long *addr) +static inline int test_and_change_bit(unsigned int nr, volatile unsigned long *p) { + long old; unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); - unsigned long old; - unsigned long flags; - - _atomic_spin_lock_irqsave(p, flags); - old = *p; - *p = old ^ mask; - _atomic_spin_unlock_irqrestore(p, flags); - return (old & mask) != 0; + p += BIT_WORD(nr); + old = atomic_long_fetch_xor(mask, (atomic_long_t *)p); + return !!(old & mask); } #endif /* _ASM_GENERIC_BITOPS_ATOMIC_H */ -- cgit v1.2.3 From 84c6591103dbeaf393a092a3fc7b09510825f6b9 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 19 Jun 2018 13:53:12 +0100 Subject: locking/atomics, asm-generic/bitops/lock.h: Rewrite using atomic_fetch_*() The lock bitops can be implemented more efficiently using the atomic_fetch_*() ops, which provide finer-grained control over the memory ordering semantics than the bitops. Signed-off-by: Will Deacon Acked-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-arm-kernel@lists.infradead.org Cc: yamada.masahiro@socionext.com Link: https://lore.kernel.org/lkml/1529412794-17720-8-git-send-email-will.deacon@arm.com Signed-off-by: Ingo Molnar --- include/asm-generic/bitops/lock.h | 68 ++++++++++++++++++++++++++++++++------- 1 file changed, 56 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/asm-generic/bitops/lock.h b/include/asm-generic/bitops/lock.h index 67ab280ad134..3ae021368f48 100644 --- a/include/asm-generic/bitops/lock.h +++ b/include/asm-generic/bitops/lock.h @@ -2,6 +2,10 @@ #ifndef _ASM_GENERIC_BITOPS_LOCK_H_ #define _ASM_GENERIC_BITOPS_LOCK_H_ +#include +#include +#include + /** * test_and_set_bit_lock - Set a bit and return its old value, for lock * @nr: Bit to set @@ -11,7 +15,20 @@ * the returned value is 0. * It can be used to implement bit locks. */ -#define test_and_set_bit_lock(nr, addr) test_and_set_bit(nr, addr) +static inline int test_and_set_bit_lock(unsigned int nr, + volatile unsigned long *p) +{ + long old; + unsigned long mask = BIT_MASK(nr); + + p += BIT_WORD(nr); + if (READ_ONCE(*p) & mask) + return 1; + + old = atomic_long_fetch_or_acquire(mask, (atomic_long_t *)p); + return !!(old & mask); +} + /** * clear_bit_unlock - Clear a bit in memory, for unlock @@ -20,11 +37,11 @@ * * This operation is atomic and provides release barrier semantics. */ -#define clear_bit_unlock(nr, addr) \ -do { \ - smp_mb__before_atomic(); \ - clear_bit(nr, addr); \ -} while (0) +static inline void clear_bit_unlock(unsigned int nr, volatile unsigned long *p) +{ + p += BIT_WORD(nr); + atomic_long_fetch_andnot_release(BIT_MASK(nr), (atomic_long_t *)p); +} /** * __clear_bit_unlock - Clear a bit in memory, for unlock @@ -37,11 +54,38 @@ do { \ * * See for example x86's implementation. */ -#define __clear_bit_unlock(nr, addr) \ -do { \ - smp_mb__before_atomic(); \ - clear_bit(nr, addr); \ -} while (0) +static inline void __clear_bit_unlock(unsigned int nr, + volatile unsigned long *p) +{ + unsigned long old; -#endif /* _ASM_GENERIC_BITOPS_LOCK_H_ */ + p += BIT_WORD(nr); + old = READ_ONCE(*p); + old &= ~BIT_MASK(nr); + atomic_long_set_release((atomic_long_t *)p, old); +} + +/** + * clear_bit_unlock_is_negative_byte - Clear a bit in memory and test if bottom + * byte is negative, for unlock. + * @nr: the bit to clear + * @addr: the address to start counting from + * + * This is a bit of a one-trick-pony for the filemap code, which clears + * PG_locked and tests PG_waiters, + */ +#ifndef clear_bit_unlock_is_negative_byte +static inline bool clear_bit_unlock_is_negative_byte(unsigned int nr, + volatile unsigned long *p) +{ + long old; + unsigned long mask = BIT_MASK(nr); + + p += BIT_WORD(nr); + old = atomic_long_fetch_andnot_release(mask, (atomic_long_t *)p); + return !!(old & BIT(7)); +} +#define clear_bit_unlock_is_negative_byte clear_bit_unlock_is_negative_byte +#endif +#endif /* _ASM_GENERIC_BITOPS_LOCK_H_ */ -- cgit v1.2.3 From 05736e4ac13c08a4a9b1ef2de26dd31a32cbee57 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 29 May 2018 17:48:27 +0200 Subject: cpu/hotplug: Provide knobs to control SMT Provide a command line and a sysfs knob to control SMT. The command line options are: 'nosmt': Enumerate secondary threads, but do not online them 'nosmt=force': Ignore secondary threads completely during enumeration via MP table and ACPI/MADT. The sysfs control file has the following states (read/write): 'on': SMT is enabled. Secondary threads can be freely onlined 'off': SMT is disabled. Secondary threads, even if enumerated cannot be onlined 'forceoff': SMT is permanentely disabled. Writes to the control file are rejected. 'notsupported': SMT is not supported by the CPU The command line option 'nosmt' sets the sysfs control to 'off'. This can be changed to 'on' to reenable SMT during runtime. The command line option 'nosmt=force' sets the sysfs control to 'forceoff'. This cannot be changed during runtime. When SMT is 'on' and the control file is changed to 'off' then all online secondary threads are offlined and attempts to online a secondary thread later on are rejected. When SMT is 'off' and the control file is changed to 'on' then secondary threads can be onlined again. The 'off' -> 'on' transition does not automatically online the secondary threads. When the control file is set to 'forceoff', the behaviour is the same as setting it to 'off', but the operation is irreversible and later writes to the control file are rejected. When the control status is 'notsupported' then writes to the control file are rejected. Signed-off-by: Thomas Gleixner Reviewed-by: Konrad Rzeszutek Wilk Acked-by: Ingo Molnar --- Documentation/ABI/testing/sysfs-devices-system-cpu | 20 +++ Documentation/admin-guide/kernel-parameters.txt | 8 + arch/Kconfig | 3 + arch/x86/Kconfig | 1 + include/linux/cpu.h | 13 ++ kernel/cpu.c | 170 +++++++++++++++++++++ 6 files changed, 215 insertions(+) (limited to 'include') diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index 9c5e7732d249..65d9b844ecfd 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -487,3 +487,23 @@ Description: Information about CPU vulnerabilities "Not affected" CPU is not affected by the vulnerability "Vulnerable" CPU is affected and no mitigation in effect "Mitigation: $M" CPU is affected and mitigation $M is in effect + +What: /sys/devices/system/cpu/smt + /sys/devices/system/cpu/smt/active + /sys/devices/system/cpu/smt/control +Date: June 2018 +Contact: Linux kernel mailing list +Description: Control Symetric Multi Threading (SMT) + + active: Tells whether SMT is active (enabled and siblings online) + + control: Read/write interface to control SMT. Possible + values: + + "on" SMT is enabled + "off" SMT is disabled + "forceoff" SMT is force disabled. Cannot be changed. + "notsupported" SMT is not supported by the CPU + + If control status is "forceoff" or "notsupported" writes + are rejected. diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index efc7aa7a0670..8e29c4b6756f 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2687,6 +2687,14 @@ nosmt [KNL,S390] Disable symmetric multithreading (SMT). Equivalent to smt=1. + [KNL,x86] Disable symmetric multithreading (SMT). + nosmt=force: Force disable SMT, similar to disabling + it in the BIOS except that some of the + resource partitioning effects which are + caused by having SMT enabled in the BIOS + cannot be undone. Depending on the CPU + type this might have a performance impact. + nospectre_v2 [X86] Disable all mitigations for the Spectre variant 2 (indirect branch prediction) vulnerability. System may allow data leaks with this option, which is equivalent diff --git a/arch/Kconfig b/arch/Kconfig index 1aa59063f1fd..d1f2ed462ac8 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -13,6 +13,9 @@ config KEXEC_CORE config HAVE_IMA_KEXEC bool +config HOTPLUG_SMT + bool + config OPROFILE tristate "OProfile system profiling" depends on PROFILING diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index f1dbb4ee19d7..7a34fdf8daf0 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -187,6 +187,7 @@ config X86 select HAVE_SYSCALL_TRACEPOINTS select HAVE_UNSTABLE_SCHED_CLOCK select HAVE_USER_RETURN_NOTIFIER + select HOTPLUG_SMT if SMP select IRQ_FORCED_THREADING select NEED_SG_DMA_LENGTH select PCI_LOCKLESS_CONFIG diff --git a/include/linux/cpu.h b/include/linux/cpu.h index d3da5184aa1c..7532cbf27b1d 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -168,4 +168,17 @@ void cpuhp_report_idle_dead(void); static inline void cpuhp_report_idle_dead(void) { } #endif /* #ifdef CONFIG_HOTPLUG_CPU */ +enum cpuhp_smt_control { + CPU_SMT_ENABLED, + CPU_SMT_DISABLED, + CPU_SMT_FORCE_DISABLED, + CPU_SMT_NOT_SUPPORTED, +}; + +#if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_SMT) +extern enum cpuhp_smt_control cpu_smt_control; +#else +# define cpu_smt_control (CPU_SMT_ENABLED) +#endif + #endif /* _LINUX_CPU_H_ */ diff --git a/kernel/cpu.c b/kernel/cpu.c index e266cb529c1a..d29fdd7e57bb 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -933,6 +933,29 @@ EXPORT_SYMBOL(cpu_down); #define takedown_cpu NULL #endif /*CONFIG_HOTPLUG_CPU*/ +#ifdef CONFIG_HOTPLUG_SMT +enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED; + +static int __init smt_cmdline_disable(char *str) +{ + cpu_smt_control = CPU_SMT_DISABLED; + if (str && !strcmp(str, "force")) { + pr_info("SMT: Force disabled\n"); + cpu_smt_control = CPU_SMT_FORCE_DISABLED; + } + return 0; +} +early_param("nosmt", smt_cmdline_disable); + +static inline bool cpu_smt_allowed(unsigned int cpu) +{ + return cpu_smt_control == CPU_SMT_ENABLED || + topology_is_primary_thread(cpu); +} +#else +static inline bool cpu_smt_allowed(unsigned int cpu) { return true; } +#endif + /** * notify_cpu_starting(cpu) - Invoke the callbacks on the starting CPU * @cpu: cpu that just started @@ -1056,6 +1079,10 @@ static int do_cpu_up(unsigned int cpu, enum cpuhp_state target) err = -EBUSY; goto out; } + if (!cpu_smt_allowed(cpu)) { + err = -EPERM; + goto out; + } err = _cpu_up(cpu, 0, target); out: @@ -1904,10 +1931,153 @@ static const struct attribute_group cpuhp_cpu_root_attr_group = { NULL }; +#ifdef CONFIG_HOTPLUG_SMT + +static const char *smt_states[] = { + [CPU_SMT_ENABLED] = "on", + [CPU_SMT_DISABLED] = "off", + [CPU_SMT_FORCE_DISABLED] = "forceoff", + [CPU_SMT_NOT_SUPPORTED] = "notsupported", +}; + +static ssize_t +show_smt_control(struct device *dev, struct device_attribute *attr, char *buf) +{ + return snprintf(buf, PAGE_SIZE - 2, "%s\n", smt_states[cpu_smt_control]); +} + +static void cpuhp_offline_cpu_device(unsigned int cpu) +{ + struct device *dev = get_cpu_device(cpu); + + dev->offline = true; + /* Tell user space about the state change */ + kobject_uevent(&dev->kobj, KOBJ_OFFLINE); +} + +static int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) +{ + int cpu, ret = 0; + + cpu_maps_update_begin(); + for_each_online_cpu(cpu) { + if (topology_is_primary_thread(cpu)) + continue; + ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE); + if (ret) + break; + /* + * As this needs to hold the cpu maps lock it's impossible + * to call device_offline() because that ends up calling + * cpu_down() which takes cpu maps lock. cpu maps lock + * needs to be held as this might race against in kernel + * abusers of the hotplug machinery (thermal management). + * + * So nothing would update device:offline state. That would + * leave the sysfs entry stale and prevent onlining after + * smt control has been changed to 'off' again. This is + * called under the sysfs hotplug lock, so it is properly + * serialized against the regular offline usage. + */ + cpuhp_offline_cpu_device(cpu); + } + if (!ret) + cpu_smt_control = ctrlval; + cpu_maps_update_done(); + return ret; +} + +static void cpuhp_smt_enable(void) +{ + cpu_maps_update_begin(); + cpu_smt_control = CPU_SMT_ENABLED; + cpu_maps_update_done(); +} + +static ssize_t +store_smt_control(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + int ctrlval, ret; + + if (sysfs_streq(buf, "on")) + ctrlval = CPU_SMT_ENABLED; + else if (sysfs_streq(buf, "off")) + ctrlval = CPU_SMT_DISABLED; + else if (sysfs_streq(buf, "forceoff")) + ctrlval = CPU_SMT_FORCE_DISABLED; + else + return -EINVAL; + + if (cpu_smt_control == CPU_SMT_FORCE_DISABLED) + return -EPERM; + + if (cpu_smt_control == CPU_SMT_NOT_SUPPORTED) + return -ENODEV; + + ret = lock_device_hotplug_sysfs(); + if (ret) + return ret; + + if (ctrlval != cpu_smt_control) { + switch (ctrlval) { + case CPU_SMT_ENABLED: + cpuhp_smt_enable(); + break; + case CPU_SMT_DISABLED: + case CPU_SMT_FORCE_DISABLED: + ret = cpuhp_smt_disable(ctrlval); + break; + } + } + + unlock_device_hotplug(); + return ret ? ret : count; +} +static DEVICE_ATTR(control, 0644, show_smt_control, store_smt_control); + +static ssize_t +show_smt_active(struct device *dev, struct device_attribute *attr, char *buf) +{ + bool active = topology_max_smt_threads() > 1; + + return snprintf(buf, PAGE_SIZE - 2, "%d\n", active); +} +static DEVICE_ATTR(active, 0444, show_smt_active, NULL); + +static struct attribute *cpuhp_smt_attrs[] = { + &dev_attr_control.attr, + &dev_attr_active.attr, + NULL +}; + +static const struct attribute_group cpuhp_smt_attr_group = { + .attrs = cpuhp_smt_attrs, + .name = "smt", + NULL +}; + +static int __init cpu_smt_state_init(void) +{ + if (!topology_smt_supported()) + cpu_smt_control = CPU_SMT_NOT_SUPPORTED; + + return sysfs_create_group(&cpu_subsys.dev_root->kobj, + &cpuhp_smt_attr_group); +} + +#else +static inline int cpu_smt_state_init(void) { return 0; } +#endif + static int __init cpuhp_sysfs_init(void) { int cpu, ret; + ret = cpu_smt_state_init(); + if (ret) + return ret; + ret = sysfs_create_group(&cpu_subsys.dev_root->kobj, &cpuhp_cpu_root_attr_group); if (ret) -- cgit v1.2.3 From bfc18e389c7a09fbbbed6bf4032396685b14246e Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Thu, 21 Jun 2018 13:13:04 +0100 Subject: atomics/treewide: Rename __atomic_add_unless() => atomic_fetch_add_unless() While __atomic_add_unless() was originally intended as a building-block for atomic_add_unless(), it's now used in a number of places around the kernel. It's the only common atomic operation named __atomic*(), rather than atomic_*(), and for consistency it would be better named atomic_fetch_add_unless(). This lack of consistency is slightly confusing, and gets in the way of scripting atomics. Given that, let's clean things up and promote it to an official part of the atomics API, in the form of atomic_fetch_add_unless(). This patch converts definitions and invocations over to the new name, including the instrumented version, using the following script: ---- git grep -w __atomic_add_unless | while read line; do sed -i '{s/\<__atomic_add_unless\>/atomic_fetch_add_unless/}' "${line%%:*}"; done git grep -w __arch_atomic_add_unless | while read line; do sed -i '{s/\<__arch_atomic_add_unless\>/arch_atomic_fetch_add_unless/}' "${line%%:*}"; done ---- Note that we do not have atomic{64,_long}_fetch_add_unless(), which will be introduced by later patches. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Reviewed-by: Will Deacon Acked-by: Geert Uytterhoeven Acked-by: Peter Zijlstra (Intel) Acked-by: Palmer Dabbelt Cc: Boqun Feng Cc: Linus Torvalds Cc: Thomas Gleixner Link: https://lore.kernel.org/lkml/20180621121321.4761-2-mark.rutland@arm.com Signed-off-by: Ingo Molnar --- arch/alpha/include/asm/atomic.h | 4 ++-- arch/arc/include/asm/atomic.h | 4 ++-- arch/arm/include/asm/atomic.h | 4 ++-- arch/arm64/include/asm/atomic.h | 2 +- arch/h8300/include/asm/atomic.h | 2 +- arch/hexagon/include/asm/atomic.h | 4 ++-- arch/ia64/include/asm/atomic.h | 2 +- arch/m68k/include/asm/atomic.h | 2 +- arch/mips/include/asm/atomic.h | 4 ++-- arch/openrisc/include/asm/atomic.h | 4 ++-- arch/parisc/include/asm/atomic.h | 4 ++-- arch/powerpc/include/asm/atomic.h | 8 ++++---- arch/riscv/include/asm/atomic.h | 4 ++-- arch/s390/include/asm/atomic.h | 2 +- arch/sh/include/asm/atomic.h | 4 ++-- arch/sparc/include/asm/atomic_32.h | 2 +- arch/sparc/include/asm/atomic_64.h | 2 +- arch/sparc/lib/atomic32.c | 4 ++-- arch/x86/include/asm/atomic.h | 4 ++-- arch/xtensa/include/asm/atomic.h | 4 ++-- drivers/block/rbd.c | 2 +- drivers/infiniband/core/rdma_core.c | 2 +- fs/afs/rxrpc.c | 2 +- include/asm-generic/atomic-instrumented.h | 4 ++-- include/asm-generic/atomic.h | 4 ++-- include/linux/atomic.h | 2 +- kernel/bpf/syscall.c | 4 ++-- net/rxrpc/call_object.c | 2 +- net/rxrpc/conn_object.c | 4 ++-- net/rxrpc/local_object.c | 2 +- net/rxrpc/peer_object.c | 2 +- 31 files changed, 50 insertions(+), 50 deletions(-) (limited to 'include') diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h index 767bfdd42992..392b15a4dd4f 100644 --- a/arch/alpha/include/asm/atomic.h +++ b/arch/alpha/include/asm/atomic.h @@ -206,7 +206,7 @@ ATOMIC_OPS(xor, xor) #define atomic_xchg(v, new) (xchg(&((v)->counter), new)) /** - * __atomic_add_unless - add unless the number is a given value + * atomic_fetch_add_unless - add unless the number is a given value * @v: pointer of type atomic_t * @a: the amount to add to v... * @u: ...unless v is equal to u. @@ -214,7 +214,7 @@ ATOMIC_OPS(xor, xor) * Atomically adds @a to @v, so long as it was not @u. * Returns the old value of @v. */ -static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u) +static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int c, new, old; smp_mb(); diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h index 11859287c52a..67121b5ff3a3 100644 --- a/arch/arc/include/asm/atomic.h +++ b/arch/arc/include/asm/atomic.h @@ -309,7 +309,7 @@ ATOMIC_OPS(xor, ^=, CTOP_INST_AXOR_DI_R2_R2_R3) #undef ATOMIC_OP /** - * __atomic_add_unless - add unless the number is a given value + * atomic_fetch_add_unless - add unless the number is a given value * @v: pointer of type atomic_t * @a: the amount to add to v... * @u: ...unless v is equal to u. @@ -317,7 +317,7 @@ ATOMIC_OPS(xor, ^=, CTOP_INST_AXOR_DI_R2_R2_R3) * Atomically adds @a to @v, so long as it was not @u. * Returns the old value of @v */ -#define __atomic_add_unless(v, a, u) \ +#define atomic_fetch_add_unless(v, a, u) \ ({ \ int c, old; \ \ diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h index 66d0e215a773..9d56d0727c9b 100644 --- a/arch/arm/include/asm/atomic.h +++ b/arch/arm/include/asm/atomic.h @@ -130,7 +130,7 @@ static inline int atomic_cmpxchg_relaxed(atomic_t *ptr, int old, int new) } #define atomic_cmpxchg_relaxed atomic_cmpxchg_relaxed -static inline int __atomic_add_unless(atomic_t *v, int a, int u) +static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int oldval, newval; unsigned long tmp; @@ -215,7 +215,7 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new) return ret; } -static inline int __atomic_add_unless(atomic_t *v, int a, int u) +static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int c, old; diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h index c0235e0ff849..264d20339f74 100644 --- a/arch/arm64/include/asm/atomic.h +++ b/arch/arm64/include/asm/atomic.h @@ -125,7 +125,7 @@ #define atomic_dec_and_test(v) (atomic_dec_return(v) == 0) #define atomic_sub_and_test(i, v) (atomic_sub_return((i), (v)) == 0) #define atomic_add_negative(i, v) (atomic_add_return((i), (v)) < 0) -#define __atomic_add_unless(v, a, u) ___atomic_add_unless(v, a, u,) +#define atomic_fetch_add_unless(v, a, u) ___atomic_add_unless(v, a, u,) #define atomic_andnot atomic_andnot /* diff --git a/arch/h8300/include/asm/atomic.h b/arch/h8300/include/asm/atomic.h index b174dec099bf..5c856887fdf2 100644 --- a/arch/h8300/include/asm/atomic.h +++ b/arch/h8300/include/asm/atomic.h @@ -94,7 +94,7 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new) return ret; } -static inline int __atomic_add_unless(atomic_t *v, int a, int u) +static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int ret; h8300flags flags; diff --git a/arch/hexagon/include/asm/atomic.h b/arch/hexagon/include/asm/atomic.h index fb3dfb2a667e..287aa9f394f3 100644 --- a/arch/hexagon/include/asm/atomic.h +++ b/arch/hexagon/include/asm/atomic.h @@ -164,7 +164,7 @@ ATOMIC_OPS(xor) #undef ATOMIC_OP /** - * __atomic_add_unless - add unless the number is a given value + * atomic_fetch_add_unless - add unless the number is a given value * @v: pointer to value * @a: amount to add * @u: unless value is equal to u @@ -173,7 +173,7 @@ ATOMIC_OPS(xor) * */ -static inline int __atomic_add_unless(atomic_t *v, int a, int u) +static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int __oldval; register int tmp; diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h index 2524fb60fbc2..9d2ddde5f9d5 100644 --- a/arch/ia64/include/asm/atomic.h +++ b/arch/ia64/include/asm/atomic.h @@ -215,7 +215,7 @@ ATOMIC64_FETCH_OP(xor, ^) (cmpxchg(&((v)->counter), old, new)) #define atomic64_xchg(v, new) (xchg(&((v)->counter), new)) -static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u) +static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int c, old; c = atomic_read(v); diff --git a/arch/m68k/include/asm/atomic.h b/arch/m68k/include/asm/atomic.h index e993e2860ee1..8022d9ea1213 100644 --- a/arch/m68k/include/asm/atomic.h +++ b/arch/m68k/include/asm/atomic.h @@ -211,7 +211,7 @@ static inline int atomic_add_negative(int i, atomic_t *v) return c != 0; } -static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u) +static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int c, old; c = atomic_read(v); diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h index 0ab176bdb8e8..02fc1553cf9b 100644 --- a/arch/mips/include/asm/atomic.h +++ b/arch/mips/include/asm/atomic.h @@ -275,7 +275,7 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v) #define atomic_xchg(v, new) (xchg(&((v)->counter), (new))) /** - * __atomic_add_unless - add unless the number is a given value + * atomic_fetch_add_unless - add unless the number is a given value * @v: pointer of type atomic_t * @a: the amount to add to v... * @u: ...unless v is equal to u. @@ -283,7 +283,7 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v) * Atomically adds @a to @v, so long as it was not @u. * Returns the old value of @v. */ -static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u) +static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int c, old; c = atomic_read(v); diff --git a/arch/openrisc/include/asm/atomic.h b/arch/openrisc/include/asm/atomic.h index 146e1660f00e..b589fac39b92 100644 --- a/arch/openrisc/include/asm/atomic.h +++ b/arch/openrisc/include/asm/atomic.h @@ -100,7 +100,7 @@ ATOMIC_OP(xor) * * This is often used through atomic_inc_not_zero() */ -static inline int __atomic_add_unless(atomic_t *v, int a, int u) +static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int old, tmp; @@ -119,7 +119,7 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u) return old; } -#define __atomic_add_unless __atomic_add_unless +#define atomic_fetch_add_unless atomic_fetch_add_unless #include diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h index 88bae6676c9b..7748abced766 100644 --- a/arch/parisc/include/asm/atomic.h +++ b/arch/parisc/include/asm/atomic.h @@ -78,7 +78,7 @@ static __inline__ int atomic_read(const atomic_t *v) #define atomic_xchg(v, new) (xchg(&((v)->counter), new)) /** - * __atomic_add_unless - add unless the number is a given value + * atomic_fetch_add_unless - add unless the number is a given value * @v: pointer of type atomic_t * @a: the amount to add to v... * @u: ...unless v is equal to u. @@ -86,7 +86,7 @@ static __inline__ int atomic_read(const atomic_t *v) * Atomically adds @a to @v, so long as it was not @u. * Returns the old value of @v. */ -static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u) +static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int c, old; c = atomic_read(v); diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h index 682b3e6a1e21..1483261080a1 100644 --- a/arch/powerpc/include/asm/atomic.h +++ b/arch/powerpc/include/asm/atomic.h @@ -218,7 +218,7 @@ static __inline__ int atomic_dec_return_relaxed(atomic_t *v) #define atomic_xchg_relaxed(v, new) xchg_relaxed(&((v)->counter), (new)) /** - * __atomic_add_unless - add unless the number is a given value + * atomic_fetch_add_unless - add unless the number is a given value * @v: pointer of type atomic_t * @a: the amount to add to v... * @u: ...unless v is equal to u. @@ -226,13 +226,13 @@ static __inline__ int atomic_dec_return_relaxed(atomic_t *v) * Atomically adds @a to @v, so long as it was not @u. * Returns the old value of @v. */ -static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u) +static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int t; __asm__ __volatile__ ( PPC_ATOMIC_ENTRY_BARRIER -"1: lwarx %0,0,%1 # __atomic_add_unless\n\ +"1: lwarx %0,0,%1 # atomic_fetch_add_unless\n\ cmpw 0,%0,%3 \n\ beq 2f \n\ add %0,%2,%0 \n" @@ -538,7 +538,7 @@ static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u) __asm__ __volatile__ ( PPC_ATOMIC_ENTRY_BARRIER -"1: ldarx %0,0,%1 # __atomic_add_unless\n\ +"1: ldarx %0,0,%1 # atomic_fetch_add_unless\n\ cmpd 0,%0,%3 \n\ beq 2f \n\ add %0,%2,%0 \n" diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h index 855115ace98c..739e810c857e 100644 --- a/arch/riscv/include/asm/atomic.h +++ b/arch/riscv/include/asm/atomic.h @@ -332,7 +332,7 @@ ATOMIC_OP(dec_and_test, dec, ==, 0, 64) #undef ATOMIC_OP /* This is required to provide a full barrier on success. */ -static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u) +static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int prev, rc; @@ -381,7 +381,7 @@ static __always_inline int atomic64_add_unless(atomic64_t *v, long a, long u) */ static __always_inline int atomic_inc_not_zero(atomic_t *v) { - return __atomic_add_unless(v, 1, 0); + return atomic_fetch_add_unless(v, 1, 0); } #ifndef CONFIG_GENERIC_ATOMIC64 diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h index 4b55532f15c4..c2858cdd8c29 100644 --- a/arch/s390/include/asm/atomic.h +++ b/arch/s390/include/asm/atomic.h @@ -90,7 +90,7 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new) return __atomic_cmpxchg(&v->counter, old, new); } -static inline int __atomic_add_unless(atomic_t *v, int a, int u) +static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int c, old; c = atomic_read(v); diff --git a/arch/sh/include/asm/atomic.h b/arch/sh/include/asm/atomic.h index 0fd0099f43cc..ef45931ebac5 100644 --- a/arch/sh/include/asm/atomic.h +++ b/arch/sh/include/asm/atomic.h @@ -46,7 +46,7 @@ #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n))) /** - * __atomic_add_unless - add unless the number is a given value + * atomic_fetch_add_unless - add unless the number is a given value * @v: pointer of type atomic_t * @a: the amount to add to v... * @u: ...unless v is equal to u. @@ -54,7 +54,7 @@ * Atomically adds @a to @v, so long as it was not @u. * Returns the old value of @v. */ -static inline int __atomic_add_unless(atomic_t *v, int a, int u) +static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int c, old; c = atomic_read(v); diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h index d13ce517f4b9..a58f4b43bcc7 100644 --- a/arch/sparc/include/asm/atomic_32.h +++ b/arch/sparc/include/asm/atomic_32.h @@ -27,7 +27,7 @@ int atomic_fetch_or(int, atomic_t *); int atomic_fetch_xor(int, atomic_t *); int atomic_cmpxchg(atomic_t *, int, int); int atomic_xchg(atomic_t *, int); -int __atomic_add_unless(atomic_t *, int, int); +int atomic_fetch_add_unless(atomic_t *, int, int); void atomic_set(atomic_t *, int); #define atomic_set_release(v, i) atomic_set((v), (i)) diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h index 28db058d471b..f416fd3d2708 100644 --- a/arch/sparc/include/asm/atomic_64.h +++ b/arch/sparc/include/asm/atomic_64.h @@ -89,7 +89,7 @@ static inline int atomic_xchg(atomic_t *v, int new) return xchg(&v->counter, new); } -static inline int __atomic_add_unless(atomic_t *v, int a, int u) +static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int c, old; c = atomic_read(v); diff --git a/arch/sparc/lib/atomic32.c b/arch/sparc/lib/atomic32.c index 465a901a0ada..281fa634bb1a 100644 --- a/arch/sparc/lib/atomic32.c +++ b/arch/sparc/lib/atomic32.c @@ -95,7 +95,7 @@ int atomic_cmpxchg(atomic_t *v, int old, int new) } EXPORT_SYMBOL(atomic_cmpxchg); -int __atomic_add_unless(atomic_t *v, int a, int u) +int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int ret; unsigned long flags; @@ -107,7 +107,7 @@ int __atomic_add_unless(atomic_t *v, int a, int u) spin_unlock_irqrestore(ATOMIC_HASH(v), flags); return ret; } -EXPORT_SYMBOL(__atomic_add_unless); +EXPORT_SYMBOL(atomic_fetch_add_unless); /* Atomic operations are already serializing */ void atomic_set(atomic_t *v, int i) diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h index 0db6bec95489..84ed0bd76aef 100644 --- a/arch/x86/include/asm/atomic.h +++ b/arch/x86/include/asm/atomic.h @@ -254,7 +254,7 @@ static inline int arch_atomic_fetch_xor(int i, atomic_t *v) } /** - * __arch_atomic_add_unless - add unless the number is already a given value + * arch_atomic_fetch_add_unless - add unless the number is already a given value * @v: pointer of type atomic_t * @a: the amount to add to v... * @u: ...unless v is equal to u. @@ -262,7 +262,7 @@ static inline int arch_atomic_fetch_xor(int i, atomic_t *v) * Atomically adds @a to @v, so long as @v was not already @u. * Returns the old value of @v. */ -static __always_inline int __arch_atomic_add_unless(atomic_t *v, int a, int u) +static __always_inline int arch_atomic_fetch_add_unless(atomic_t *v, int a, int u) { int c = arch_atomic_read(v); diff --git a/arch/xtensa/include/asm/atomic.h b/arch/xtensa/include/asm/atomic.h index e7a23f2a519a..4188e56c06c9 100644 --- a/arch/xtensa/include/asm/atomic.h +++ b/arch/xtensa/include/asm/atomic.h @@ -275,7 +275,7 @@ ATOMIC_OPS(xor) #define atomic_xchg(v, new) (xchg(&((v)->counter), new)) /** - * __atomic_add_unless - add unless the number is a given value + * atomic_fetch_add_unless - add unless the number is a given value * @v: pointer of type atomic_t * @a: the amount to add to v... * @u: ...unless v is equal to u. @@ -283,7 +283,7 @@ ATOMIC_OPS(xor) * Atomically adds @a to @v, so long as it was not @u. * Returns the old value of @v. */ -static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u) +static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int c, old; c = atomic_read(v); diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index fa0729c1e776..d81c653b9bf6 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -61,7 +61,7 @@ static int atomic_inc_return_safe(atomic_t *v) { unsigned int counter; - counter = (unsigned int)__atomic_add_unless(v, 1, 0); + counter = (unsigned int)atomic_fetch_add_unless(v, 1, 0); if (counter <= (unsigned int)INT_MAX) return (int)counter; diff --git a/drivers/infiniband/core/rdma_core.c b/drivers/infiniband/core/rdma_core.c index a6e904973ba8..475910ffbcb6 100644 --- a/drivers/infiniband/core/rdma_core.c +++ b/drivers/infiniband/core/rdma_core.c @@ -121,7 +121,7 @@ static int uverbs_try_lock_object(struct ib_uobject *uobj, bool exclusive) * this lock. */ if (!exclusive) - return __atomic_add_unless(&uobj->usecnt, 1, -1) == -1 ? + return atomic_fetch_add_unless(&uobj->usecnt, 1, -1) == -1 ? -EBUSY : 0; /* lock is either WRITE or DESTROY - should be exclusive */ diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index a1b18082991b..183cc5418722 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -648,7 +648,7 @@ static void afs_wake_up_async_call(struct sock *sk, struct rxrpc_call *rxcall, trace_afs_notify_call(rxcall, call); call->need_attention = true; - u = __atomic_add_unless(&call->usage, 1, 0); + u = atomic_fetch_add_unless(&call->usage, 1, 0); if (u != 0) { trace_afs_call(call, afs_call_trace_wake, u, atomic_read(&call->net->nr_outstanding_calls), diff --git a/include/asm-generic/atomic-instrumented.h b/include/asm-generic/atomic-instrumented.h index ec07f23678ea..b8b14cc2df6c 100644 --- a/include/asm-generic/atomic-instrumented.h +++ b/include/asm-generic/atomic-instrumented.h @@ -84,10 +84,10 @@ static __always_inline bool atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 ne } #endif -static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u) +static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { kasan_check_write(v, sizeof(*v)); - return __arch_atomic_add_unless(v, a, u); + return arch_atomic_fetch_add_unless(v, a, u); } diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h index abe6dd9ca2a8..10051ed6d088 100644 --- a/include/asm-generic/atomic.h +++ b/include/asm-generic/atomic.h @@ -221,8 +221,8 @@ static inline void atomic_dec(atomic_t *v) #define atomic_xchg(ptr, v) (xchg(&(ptr)->counter, (v))) #define atomic_cmpxchg(v, old, new) (cmpxchg(&((v)->counter), (old), (new))) -#ifndef __atomic_add_unless -static inline int __atomic_add_unless(atomic_t *v, int a, int u) +#ifndef atomic_fetch_add_unless +static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int c, old; c = atomic_read(v); diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 01ce3997cb42..9cc982936675 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -530,7 +530,7 @@ */ static inline int atomic_add_unless(atomic_t *v, int a, int u) { - return __atomic_add_unless(v, a, u) != u; + return atomic_fetch_add_unless(v, a, u) != u; } /** diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 35dc466641f2..f12db70d3bf3 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -575,7 +575,7 @@ static struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map, { int refold; - refold = __atomic_add_unless(&map->refcnt, 1, 0); + refold = atomic_fetch_add_unless(&map->refcnt, 1, 0); if (refold >= BPF_MAX_REFCNT) { __bpf_map_put(map, false); @@ -1142,7 +1142,7 @@ struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog) { int refold; - refold = __atomic_add_unless(&prog->aux->refcnt, 1, 0); + refold = atomic_fetch_add_unless(&prog->aux->refcnt, 1, 0); if (refold >= BPF_MAX_REFCNT) { __bpf_prog_put(prog, false); diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index f6734d8cb01a..9486293fef5c 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -415,7 +415,7 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx, bool rxrpc_queue_call(struct rxrpc_call *call) { const void *here = __builtin_return_address(0); - int n = __atomic_add_unless(&call->usage, 1, 0); + int n = atomic_fetch_add_unless(&call->usage, 1, 0); if (n == 0) return false; if (rxrpc_queue_work(&call->processor)) diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 4c77a78a252a..77440a356b14 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -266,7 +266,7 @@ void rxrpc_kill_connection(struct rxrpc_connection *conn) bool rxrpc_queue_conn(struct rxrpc_connection *conn) { const void *here = __builtin_return_address(0); - int n = __atomic_add_unless(&conn->usage, 1, 0); + int n = atomic_fetch_add_unless(&conn->usage, 1, 0); if (n == 0) return false; if (rxrpc_queue_work(&conn->processor)) @@ -309,7 +309,7 @@ rxrpc_get_connection_maybe(struct rxrpc_connection *conn) const void *here = __builtin_return_address(0); if (conn) { - int n = __atomic_add_unless(&conn->usage, 1, 0); + int n = atomic_fetch_add_unless(&conn->usage, 1, 0); if (n > 0) trace_rxrpc_conn(conn, rxrpc_conn_got, n + 1, here); else diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index b493e6b62740..777c3ed4cfc0 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -305,7 +305,7 @@ struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *local) const void *here = __builtin_return_address(0); if (local) { - int n = __atomic_add_unless(&local->usage, 1, 0); + int n = atomic_fetch_add_unless(&local->usage, 1, 0); if (n > 0) trace_rxrpc_local(local, rxrpc_local_got, n + 1, here); else diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index 1b7e8107b3ae..1cf3b408017a 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -406,7 +406,7 @@ struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *peer) const void *here = __builtin_return_address(0); if (peer) { - int n = __atomic_add_unless(&peer->usage, 1, 0); + int n = atomic_fetch_add_unless(&peer->usage, 1, 0); if (n > 0) trace_rxrpc_peer(peer, rxrpc_peer_got, n + 1, here); else -- cgit v1.2.3 From f74445b6dd6b8f33ed34e005d19ecbb49171dabf Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Thu, 21 Jun 2018 13:13:06 +0100 Subject: atomics/treewide: Remove atomic_inc_not_zero_hint() While documentation suggests atomic_inc_not_zero_hint() will perform better than atomic_inc_not_zero(), this is unlikely to be the case. No architectures implement atomic_inc_not_zero_hint() directly, and thus it either falls back to atomic_inc_not_zero(), or a loop using atomic_cmpxchg(). Whenever the hint does not match the value in memory, the repeated use of atomic_cmpxchg() will be more expensive than the read that atomic_inc_not_zero_hint() attempts to avoid. For architectures with LL/SC atomics, a read cannot be avoided, and it would always be better to use atomic_inc_not_zero() directly. For other architectures, their own atomic_inc_not_zero() is likely to be more optimal than an atomic_cmpxchg() loop regardless. Generally, atomic_inc_not_zero_hint() is liable to perform worse than atomic_inc_not_zero(). Further, atomic_inc_not_zero_hint() only exists for atomic_t, and not atomic64_t or atomic_long_t, and there is only one user in the kernel tree. Given all this, let's remove atomic_inc_not_zero_hint(), and migrate the existing user over to atomic_inc_not_zero(). There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Reviewed-by: Will Deacon Acked-by: Peter Zijlstra (Intel) Cc: Boqun Feng Cc: Linus Torvalds Cc: Thomas Gleixner Link: https://lore.kernel.org/lkml/20180621121321.4761-4-mark.rutland@arm.com Signed-off-by: Ingo Molnar --- include/linux/atomic.h | 32 -------------------------------- net/atm/pppoatm.c | 2 +- 2 files changed, 1 insertion(+), 33 deletions(-) (limited to 'include') diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 9cc982936675..5c5620ae5a35 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -571,38 +571,6 @@ static inline int atomic_fetch_andnot_release(int i, atomic_t *v) } #endif -/** - * atomic_inc_not_zero_hint - increment if not null - * @v: pointer of type atomic_t - * @hint: probable value of the atomic before the increment - * - * This version of atomic_inc_not_zero() gives a hint of probable - * value of the atomic. This helps processor to not read the memory - * before doing the atomic read/modify/write cycle, lowering - * number of bus transactions on some arches. - * - * Returns: 0 if increment was not done, 1 otherwise. - */ -#ifndef atomic_inc_not_zero_hint -static inline int atomic_inc_not_zero_hint(atomic_t *v, int hint) -{ - int val, c = hint; - - /* sanity test, should be removed by compiler if hint is a constant */ - if (!hint) - return atomic_inc_not_zero(v); - - do { - val = atomic_cmpxchg(v, c, c + 1); - if (val == c) - return 1; - c = val; - } while (c); - - return 0; -} -#endif - #ifndef atomic_inc_unless_negative static inline int atomic_inc_unless_negative(atomic_t *p) { diff --git a/net/atm/pppoatm.c b/net/atm/pppoatm.c index af8c4b38b746..d84227d75717 100644 --- a/net/atm/pppoatm.c +++ b/net/atm/pppoatm.c @@ -244,7 +244,7 @@ static int pppoatm_may_send(struct pppoatm_vcc *pvcc, int size) * the packet count limit, so... */ if (atm_may_send(pvcc->atmvcc, size) && - atomic_inc_not_zero_hint(&pvcc->inflight, NONE_INFLIGHT)) + atomic_inc_not_zero(&pvcc->inflight)) return 1; /* -- cgit v1.2.3 From ade5ef9280c33993099199c51e2e27c2c4013afd Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Thu, 21 Jun 2018 13:13:07 +0100 Subject: atomics: Make conditional ops return 'bool' Some of the atomics return a status value, which is a boolean value describing whether the operation was performed. To make it clear that this is a boolean value, let's update the common fallbacks to return bool, fixing up the return values and comments likewise. At the same time, let's simplify the description of the operations in their respective comments. The instrumented atomics and generic atomic64 implementation are updated accordingly. Note that atomic64_dec_if_positive() doesn't follow the usual test op pattern, and returns the would-be decremented value. This is not changed. Signed-off-by: Mark Rutland Reviewed-by: Will Deacon Acked-by: Peter Zijlstra (Intel) Cc: Boqun Feng Cc: Linus Torvalds Cc: Michael Ellerman Cc: Thomas Gleixner Link: https://lore.kernel.org/lkml/20180621121321.4761-5-mark.rutland@arm.com Signed-off-by: Ingo Molnar --- include/asm-generic/atomic-instrumented.h | 2 +- include/asm-generic/atomic64.h | 3 ++- include/linux/atomic.h | 24 +++++++++++++----------- lib/atomic64.c | 6 +++--- 4 files changed, 19 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/asm-generic/atomic-instrumented.h b/include/asm-generic/atomic-instrumented.h index b8b14cc2df6c..497faa4a05e3 100644 --- a/include/asm-generic/atomic-instrumented.h +++ b/include/asm-generic/atomic-instrumented.h @@ -205,7 +205,7 @@ static __always_inline s64 atomic64_dec_return(atomic64_t *v) return arch_atomic64_dec_return(v); } -static __always_inline s64 atomic64_inc_not_zero(atomic64_t *v) +static __always_inline bool atomic64_inc_not_zero(atomic64_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic64_inc_not_zero(v); diff --git a/include/asm-generic/atomic64.h b/include/asm-generic/atomic64.h index 8d28eb010d0d..a951a721e1bb 100644 --- a/include/asm-generic/atomic64.h +++ b/include/asm-generic/atomic64.h @@ -11,6 +11,7 @@ */ #ifndef _ASM_GENERIC_ATOMIC64_H #define _ASM_GENERIC_ATOMIC64_H +#include typedef struct { long long counter; @@ -52,7 +53,7 @@ ATOMIC64_OPS(xor) extern long long atomic64_dec_if_positive(atomic64_t *v); extern long long atomic64_cmpxchg(atomic64_t *v, long long o, long long n); extern long long atomic64_xchg(atomic64_t *v, long long new); -extern int atomic64_add_unless(atomic64_t *v, long long a, long long u); +extern bool atomic64_add_unless(atomic64_t *v, long long a, long long u); #define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0) #define atomic64_inc(v) atomic64_add(1LL, (v)) diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 5c5620ae5a35..307a7f6d619a 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -2,6 +2,8 @@ /* Atomic operations usable in machine independent code */ #ifndef _LINUX_ATOMIC_H #define _LINUX_ATOMIC_H +#include + #include #include @@ -525,10 +527,10 @@ * @a: the amount to add to v... * @u: ...unless v is equal to u. * - * Atomically adds @a to @v, so long as @v was not already @u. - * Returns non-zero if @v was not @u, and zero otherwise. + * Atomically adds @a to @v, if @v was not already @u. + * Returns true if the addition was done. */ -static inline int atomic_add_unless(atomic_t *v, int a, int u) +static inline bool atomic_add_unless(atomic_t *v, int a, int u) { return atomic_fetch_add_unless(v, a, u) != u; } @@ -537,8 +539,8 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u) * atomic_inc_not_zero - increment unless the number is zero * @v: pointer of type atomic_t * - * Atomically increments @v by 1, so long as @v is non-zero. - * Returns non-zero if @v was non-zero, and zero otherwise. + * Atomically increments @v by 1, if @v is non-zero. + * Returns true if the increment was done. */ #ifndef atomic_inc_not_zero #define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0) @@ -572,28 +574,28 @@ static inline int atomic_fetch_andnot_release(int i, atomic_t *v) #endif #ifndef atomic_inc_unless_negative -static inline int atomic_inc_unless_negative(atomic_t *p) +static inline bool atomic_inc_unless_negative(atomic_t *p) { int v, v1; for (v = 0; v >= 0; v = v1) { v1 = atomic_cmpxchg(p, v, v + 1); if (likely(v1 == v)) - return 1; + return true; } - return 0; + return false; } #endif #ifndef atomic_dec_unless_positive -static inline int atomic_dec_unless_positive(atomic_t *p) +static inline bool atomic_dec_unless_positive(atomic_t *p) { int v, v1; for (v = 0; v <= 0; v = v1) { v1 = atomic_cmpxchg(p, v, v - 1); if (likely(v1 == v)) - return 1; + return true; } - return 0; + return false; } #endif diff --git a/lib/atomic64.c b/lib/atomic64.c index 53c2d5edc826..4230f4b8906c 100644 --- a/lib/atomic64.c +++ b/lib/atomic64.c @@ -178,16 +178,16 @@ long long atomic64_xchg(atomic64_t *v, long long new) } EXPORT_SYMBOL(atomic64_xchg); -int atomic64_add_unless(atomic64_t *v, long long a, long long u) +bool atomic64_add_unless(atomic64_t *v, long long a, long long u) { unsigned long flags; raw_spinlock_t *lock = lock_addr(v); - int ret = 0; + bool ret = false; raw_spin_lock_irqsave(lock, flags); if (v->counter != u) { v->counter += a; - ret = 1; + ret = true; } raw_spin_unlock_irqrestore(lock, flags); return ret; -- cgit v1.2.3 From bef828204a1bc7a0fd3a24551c4265e9c2ab95ed Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Thu, 21 Jun 2018 13:13:08 +0100 Subject: atomics/treewide: Make atomic64_inc_not_zero() optional We define a trivial fallback for atomic_inc_not_zero(), but don't do the same for atomic64_inc_not_zero(), leading most architectures to define the same boilerplate. Let's add a fallback in , and remove the redundant implementations. Note that atomic64_add_unless() is always defined in , and promotes its arguments to the requisite types, so we need not do this explicitly. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Reviewed-by: Will Deacon Acked-by: Peter Zijlstra (Intel) Acked-by: Palmer Dabbelt Cc: Boqun Feng Cc: Linus Torvalds Cc: Thomas Gleixner Link: https://lore.kernel.org/lkml/20180621121321.4761-6-mark.rutland@arm.com Signed-off-by: Ingo Molnar --- arch/alpha/include/asm/atomic.h | 2 -- arch/arc/include/asm/atomic.h | 1 - arch/arm/include/asm/atomic.h | 1 - arch/arm64/include/asm/atomic.h | 2 -- arch/ia64/include/asm/atomic.h | 2 -- arch/mips/include/asm/atomic.h | 2 -- arch/parisc/include/asm/atomic.h | 2 -- arch/powerpc/include/asm/atomic.h | 1 + arch/riscv/include/asm/atomic.h | 7 ------- arch/s390/include/asm/atomic.h | 1 - arch/sparc/include/asm/atomic_64.h | 2 -- arch/x86/include/asm/atomic64_32.h | 2 +- arch/x86/include/asm/atomic64_64.h | 2 -- include/asm-generic/atomic-instrumented.h | 3 +++ include/asm-generic/atomic64.h | 1 - include/linux/atomic.h | 11 +++++++++++ 16 files changed, 16 insertions(+), 26 deletions(-) (limited to 'include') diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h index 392b15a4dd4f..eb0f25e4c5dd 100644 --- a/arch/alpha/include/asm/atomic.h +++ b/arch/alpha/include/asm/atomic.h @@ -296,8 +296,6 @@ static inline long atomic64_dec_if_positive(atomic64_t *v) return old - 1; } -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) - #define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0) #define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0) diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h index cecdf3403caf..1406825b5e7d 100644 --- a/arch/arc/include/asm/atomic.h +++ b/arch/arc/include/asm/atomic.h @@ -603,7 +603,6 @@ static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u) #define atomic64_dec(v) atomic64_sub(1LL, (v)) #define atomic64_dec_return(v) atomic64_sub_return(1LL, (v)) #define atomic64_dec_and_test(v) (atomic64_dec_return((v)) == 0) -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1LL, 0LL) #endif /* !CONFIG_GENERIC_ATOMIC64 */ diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h index 9d56d0727c9b..02f3894faa48 100644 --- a/arch/arm/include/asm/atomic.h +++ b/arch/arm/include/asm/atomic.h @@ -534,7 +534,6 @@ static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u) #define atomic64_dec(v) atomic64_sub(1LL, (v)) #define atomic64_dec_return_relaxed(v) atomic64_sub_return_relaxed(1LL, (v)) #define atomic64_dec_and_test(v) (atomic64_dec_return((v)) == 0) -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1LL, 0LL) #endif /* !CONFIG_GENERIC_ATOMIC64 */ #endif diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h index 264d20339f74..ad50412889c5 100644 --- a/arch/arm64/include/asm/atomic.h +++ b/arch/arm64/include/asm/atomic.h @@ -204,7 +204,5 @@ #define atomic64_add_unless(v, a, u) (___atomic_add_unless(v, a, u, 64) != u) #define atomic64_andnot atomic64_andnot -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) - #endif #endif diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h index 9d2ddde5f9d5..93d48b823220 100644 --- a/arch/ia64/include/asm/atomic.h +++ b/arch/ia64/include/asm/atomic.h @@ -246,8 +246,6 @@ static __inline__ long atomic64_add_unless(atomic64_t *v, long a, long u) return c != (u); } -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) - static __inline__ long atomic64_dec_if_positive(atomic64_t *v) { long c, old, dec; diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h index 02fc1553cf9b..502e691c6393 100644 --- a/arch/mips/include/asm/atomic.h +++ b/arch/mips/include/asm/atomic.h @@ -644,8 +644,6 @@ static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u) return c != (u); } -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) - #define atomic64_dec_return(v) atomic64_sub_return(1, (v)) #define atomic64_inc_return(v) atomic64_add_return(1, (v)) diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h index 7748abced766..3fd0243bf405 100644 --- a/arch/parisc/include/asm/atomic.h +++ b/arch/parisc/include/asm/atomic.h @@ -305,8 +305,6 @@ static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u) return c != (u); } -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) - /* * atomic64_dec_if_positive - decrement by 1 if old value positive * @v: pointer of type atomic_t diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h index 1483261080a1..e59620ee4f6b 100644 --- a/arch/powerpc/include/asm/atomic.h +++ b/arch/powerpc/include/asm/atomic.h @@ -582,6 +582,7 @@ static __inline__ int atomic64_inc_not_zero(atomic64_t *v) return t1 != 0; } +#define atomic64_inc_not_zero(v) atomic64_inc_not_zero((v)) #endif /* __powerpc64__ */ diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h index 0e27e050ba14..18259e90f57e 100644 --- a/arch/riscv/include/asm/atomic.h +++ b/arch/riscv/include/asm/atomic.h @@ -375,13 +375,6 @@ static __always_inline int atomic64_add_unless(atomic64_t *v, long a, long u) } #endif -#ifndef CONFIG_GENERIC_ATOMIC64 -static __always_inline long atomic64_inc_not_zero(atomic64_t *v) -{ - return atomic64_add_unless(v, 1, 0); -} -#endif - /* * atomic_{cmp,}xchg is required to have exactly the same ordering semantics as * {cmp,}xchg and the operations that return, so they need a full barrier. diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h index c2858cdd8c29..66dac30a4fe1 100644 --- a/arch/s390/include/asm/atomic.h +++ b/arch/s390/include/asm/atomic.h @@ -212,6 +212,5 @@ static inline long atomic64_dec_if_positive(atomic64_t *v) #define atomic64_dec(_v) atomic64_sub(1, _v) #define atomic64_dec_return(_v) atomic64_sub_return(1, _v) #define atomic64_dec_and_test(_v) (atomic64_sub_return(1, _v) == 0) -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) #endif /* __ARCH_S390_ATOMIC__ */ diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h index f416fd3d2708..07830a316464 100644 --- a/arch/sparc/include/asm/atomic_64.h +++ b/arch/sparc/include/asm/atomic_64.h @@ -123,8 +123,6 @@ static inline long atomic64_add_unless(atomic64_t *v, long a, long u) return c != (u); } -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) - long atomic64_dec_if_positive(atomic64_t *v); #endif /* !(__ARCH_SPARC64_ATOMIC__) */ diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h index 92212bf0484f..2a33cc17801b 100644 --- a/arch/x86/include/asm/atomic64_32.h +++ b/arch/x86/include/asm/atomic64_32.h @@ -295,7 +295,7 @@ static inline int arch_atomic64_add_unless(atomic64_t *v, long long a, return (int)a; } - +#define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero static inline int arch_atomic64_inc_not_zero(atomic64_t *v) { int r; diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h index 6106b59d3260..6f95023894b7 100644 --- a/arch/x86/include/asm/atomic64_64.h +++ b/arch/x86/include/asm/atomic64_64.h @@ -207,8 +207,6 @@ static inline bool arch_atomic64_add_unless(atomic64_t *v, long a, long u) return true; } -#define arch_atomic64_inc_not_zero(v) arch_atomic64_add_unless((v), 1, 0) - /* * arch_atomic64_dec_if_positive - decrement by 1 if old value positive * @v: pointer of type atomic_t diff --git a/include/asm-generic/atomic-instrumented.h b/include/asm-generic/atomic-instrumented.h index 497faa4a05e3..83bb88d791c4 100644 --- a/include/asm-generic/atomic-instrumented.h +++ b/include/asm-generic/atomic-instrumented.h @@ -205,11 +205,14 @@ static __always_inline s64 atomic64_dec_return(atomic64_t *v) return arch_atomic64_dec_return(v); } +#ifdef arch_atomic64_inc_not_zero +#define atomic64_inc_not_zero atomic64_inc_not_zero static __always_inline bool atomic64_inc_not_zero(atomic64_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic64_inc_not_zero(v); } +#endif static __always_inline s64 atomic64_dec_if_positive(atomic64_t *v) { diff --git a/include/asm-generic/atomic64.h b/include/asm-generic/atomic64.h index a951a721e1bb..5105275ac825 100644 --- a/include/asm-generic/atomic64.h +++ b/include/asm-generic/atomic64.h @@ -63,6 +63,5 @@ extern bool atomic64_add_unless(atomic64_t *v, long long a, long long u); #define atomic64_dec(v) atomic64_sub(1LL, (v)) #define atomic64_dec_return(v) atomic64_sub_return(1LL, (v)) #define atomic64_dec_and_test(v) (atomic64_dec_return((v)) == 0) -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1LL, 0LL) #endif /* _ASM_GENERIC_ATOMIC64_H */ diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 307a7f6d619a..ae3f30923d05 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -1019,6 +1019,17 @@ static inline int atomic_dec_if_positive(atomic_t *v) #define atomic64_try_cmpxchg_release atomic64_try_cmpxchg #endif /* atomic64_try_cmpxchg */ +/** + * atomic64_inc_not_zero - increment unless the number is zero + * @v: pointer of type atomic64_t + * + * Atomically increments @v by 1, if @v is non-zero. + * Returns true if the increment was done. + */ +#ifndef atomic64_inc_not_zero +#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) +#endif + #ifndef atomic64_andnot static inline void atomic64_andnot(long long i, atomic64_t *v) { -- cgit v1.2.3 From eccc2da8c03f316bba202e15af2be4615f461900 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Thu, 21 Jun 2018 13:13:09 +0100 Subject: atomics/treewide: Make atomic_fetch_add_unless() optional Several architectures these have a near-identical implementation based on atomic_read() and atomic_cmpxchg() which we can instead define in , so let's do so, using something close to the existing x86 implementation with try_cmpxchg(). Where an architecture provides its own atomic_fetch_add_unless(), it must define a preprocessor symbol for it. The instrumented atomics are updated accordingly. Note that arch/arc's existing atomic_fetch_add_unless() had redundant barriers, as these are already present in its atomic_cmpxchg() implementation. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Reviewed-by: Geert Uytterhoeven Reviewed-by: Will Deacon Acked-by: Geert Uytterhoeven Acked-by: Peter Zijlstra (Intel) Acked-by: Palmer Dabbelt Cc: Boqun Feng Cc: Linus Torvalds Cc: Thomas Gleixner Cc: Vineet Gupta Link: https://lore.kernel.org/lkml/20180621121321.4761-7-mark.rutland@arm.com Signed-off-by: Ingo Molnar --- arch/alpha/include/asm/atomic.h | 2 +- arch/arc/include/asm/atomic.h | 28 ---------------------------- arch/arm/include/asm/atomic.h | 11 +---------- arch/arm64/include/asm/atomic.h | 1 - arch/h8300/include/asm/atomic.h | 1 + arch/hexagon/include/asm/atomic.h | 1 + arch/ia64/include/asm/atomic.h | 16 ---------------- arch/m68k/include/asm/atomic.h | 15 --------------- arch/mips/include/asm/atomic.h | 24 ------------------------ arch/parisc/include/asm/atomic.h | 24 ------------------------ arch/powerpc/include/asm/atomic.h | 1 + arch/riscv/include/asm/atomic.h | 1 + arch/s390/include/asm/atomic.h | 15 --------------- arch/sh/include/asm/atomic.h | 25 ------------------------- arch/sparc/include/asm/atomic_32.h | 2 ++ arch/sparc/include/asm/atomic_64.h | 15 --------------- arch/x86/include/asm/atomic.h | 21 --------------------- arch/xtensa/include/asm/atomic.h | 24 ------------------------ include/asm-generic/atomic-instrumented.h | 4 +++- include/asm-generic/atomic.h | 11 ----------- include/linux/atomic.h | 23 +++++++++++++++++++++++ 21 files changed, 34 insertions(+), 231 deletions(-) (limited to 'include') diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h index eb0f25e4c5dd..4a800a3424a3 100644 --- a/arch/alpha/include/asm/atomic.h +++ b/arch/alpha/include/asm/atomic.h @@ -235,7 +235,7 @@ static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u) smp_mb(); return old; } - +#define atomic_fetch_add_unless atomic_fetch_add_unless /** * atomic64_add_unless - add unless the number is a given value diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h index 1406825b5e7d..60da80481c5d 100644 --- a/arch/arc/include/asm/atomic.h +++ b/arch/arc/include/asm/atomic.h @@ -308,34 +308,6 @@ ATOMIC_OPS(xor, ^=, CTOP_INST_AXOR_DI_R2_R2_R3) #undef ATOMIC_OP_RETURN #undef ATOMIC_OP -/** - * atomic_fetch_add_unless - add unless the number is a given value - * @v: pointer of type atomic_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as it was not @u. - * Returns the old value of @v - */ -#define atomic_fetch_add_unless(v, a, u) \ -({ \ - int c, old; \ - \ - /* \ - * Explicit full memory barrier needed before/after as \ - * LLOCK/SCOND thmeselves don't provide any such semantics \ - */ \ - smp_mb(); \ - \ - c = atomic_read(v); \ - while (c != (u) && (old = atomic_cmpxchg((v), c, c + (a))) != c)\ - c = old; \ - \ - smp_mb(); \ - \ - c; \ -}) - #define atomic_inc(v) atomic_add(1, v) #define atomic_dec(v) atomic_sub(1, v) diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h index 02f3894faa48..74460aa00fa0 100644 --- a/arch/arm/include/asm/atomic.h +++ b/arch/arm/include/asm/atomic.h @@ -156,6 +156,7 @@ static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) return oldval; } +#define atomic_fetch_add_unless atomic_fetch_add_unless #else /* ARM_ARCH_6 */ @@ -215,16 +216,6 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new) return ret; } -static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) -{ - int c, old; - - c = atomic_read(v); - while (c != u && (old = atomic_cmpxchg((v), c, c + a)) != c) - c = old; - return c; -} - #endif /* __LINUX_ARM_ARCH__ */ #define ATOMIC_OPS(op, c_op, asm_op) \ diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h index ad50412889c5..22c8c43d6689 100644 --- a/arch/arm64/include/asm/atomic.h +++ b/arch/arm64/include/asm/atomic.h @@ -125,7 +125,6 @@ #define atomic_dec_and_test(v) (atomic_dec_return(v) == 0) #define atomic_sub_and_test(i, v) (atomic_sub_return((i), (v)) == 0) #define atomic_add_negative(i, v) (atomic_add_return((i), (v)) < 0) -#define atomic_fetch_add_unless(v, a, u) ___atomic_add_unless(v, a, u,) #define atomic_andnot atomic_andnot /* diff --git a/arch/h8300/include/asm/atomic.h b/arch/h8300/include/asm/atomic.h index 5c856887fdf2..710364946308 100644 --- a/arch/h8300/include/asm/atomic.h +++ b/arch/h8300/include/asm/atomic.h @@ -106,5 +106,6 @@ static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) arch_local_irq_restore(flags); return ret; } +#define atomic_fetch_add_unless atomic_fetch_add_unless #endif /* __ARCH_H8300_ATOMIC __ */ diff --git a/arch/hexagon/include/asm/atomic.h b/arch/hexagon/include/asm/atomic.h index d2feeba93c44..86c67e9adbfa 100644 --- a/arch/hexagon/include/asm/atomic.h +++ b/arch/hexagon/include/asm/atomic.h @@ -196,6 +196,7 @@ static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) ); return __oldval; } +#define atomic_fetch_add_unless atomic_fetch_add_unless #define atomic_inc(v) atomic_add(1, (v)) #define atomic_dec(v) atomic_sub(1, (v)) diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h index 93d48b823220..cfe44086338e 100644 --- a/arch/ia64/include/asm/atomic.h +++ b/arch/ia64/include/asm/atomic.h @@ -215,22 +215,6 @@ ATOMIC64_FETCH_OP(xor, ^) (cmpxchg(&((v)->counter), old, new)) #define atomic64_xchg(v, new) (xchg(&((v)->counter), new)) -static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u) -{ - int c, old; - c = atomic_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - return c; -} - - static __inline__ long atomic64_add_unless(atomic64_t *v, long a, long u) { long c, old; diff --git a/arch/m68k/include/asm/atomic.h b/arch/m68k/include/asm/atomic.h index 8022d9ea1213..596882cda224 100644 --- a/arch/m68k/include/asm/atomic.h +++ b/arch/m68k/include/asm/atomic.h @@ -211,19 +211,4 @@ static inline int atomic_add_negative(int i, atomic_t *v) return c != 0; } -static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u) -{ - int c, old; - c = atomic_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - return c; -} - #endif /* __ARCH_M68K_ATOMIC __ */ diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h index 502e691c6393..794734e730d9 100644 --- a/arch/mips/include/asm/atomic.h +++ b/arch/mips/include/asm/atomic.h @@ -274,30 +274,6 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v) #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n))) #define atomic_xchg(v, new) (xchg(&((v)->counter), (new))) -/** - * atomic_fetch_add_unless - add unless the number is a given value - * @v: pointer of type atomic_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as it was not @u. - * Returns the old value of @v. - */ -static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u) -{ - int c, old; - c = atomic_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - return c; -} - #define atomic_dec_return(v) atomic_sub_return(1, (v)) #define atomic_inc_return(v) atomic_add_return(1, (v)) diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h index 3fd0243bf405..b2b6261d05e7 100644 --- a/arch/parisc/include/asm/atomic.h +++ b/arch/parisc/include/asm/atomic.h @@ -77,30 +77,6 @@ static __inline__ int atomic_read(const atomic_t *v) #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n))) #define atomic_xchg(v, new) (xchg(&((v)->counter), new)) -/** - * atomic_fetch_add_unless - add unless the number is a given value - * @v: pointer of type atomic_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as it was not @u. - * Returns the old value of @v. - */ -static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u) -{ - int c, old; - c = atomic_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - return c; -} - #define ATOMIC_OP(op, c_op) \ static __inline__ void atomic_##op(int i, atomic_t *v) \ { \ diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h index e59620ee4f6b..b5646c079c16 100644 --- a/arch/powerpc/include/asm/atomic.h +++ b/arch/powerpc/include/asm/atomic.h @@ -248,6 +248,7 @@ static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u) return t; } +#define atomic_fetch_add_unless atomic_fetch_add_unless /** * atomic_inc_not_zero - increment unless the number is zero diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h index 18259e90f57e..5f161daefcd2 100644 --- a/arch/riscv/include/asm/atomic.h +++ b/arch/riscv/include/asm/atomic.h @@ -349,6 +349,7 @@ static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) : "memory"); return prev; } +#define atomic_fetch_add_unless atomic_fetch_add_unless #ifndef CONFIG_GENERIC_ATOMIC64 static __always_inline long __atomic64_add_unless(atomic64_t *v, long a, long u) diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h index 66dac30a4fe1..26c6b713a7a3 100644 --- a/arch/s390/include/asm/atomic.h +++ b/arch/s390/include/asm/atomic.h @@ -90,21 +90,6 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new) return __atomic_cmpxchg(&v->counter, old, new); } -static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) -{ - int c, old; - c = atomic_read(v); - for (;;) { - if (unlikely(c == u)) - break; - old = atomic_cmpxchg(v, c, c + a); - if (likely(old == c)) - break; - c = old; - } - return c; -} - #define ATOMIC64_INIT(i) { (i) } static inline long atomic64_read(const atomic64_t *v) diff --git a/arch/sh/include/asm/atomic.h b/arch/sh/include/asm/atomic.h index ef45931ebac5..422fac764ca1 100644 --- a/arch/sh/include/asm/atomic.h +++ b/arch/sh/include/asm/atomic.h @@ -45,31 +45,6 @@ #define atomic_xchg(v, new) (xchg(&((v)->counter), new)) #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n))) -/** - * atomic_fetch_add_unless - add unless the number is a given value - * @v: pointer of type atomic_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as it was not @u. - * Returns the old value of @v. - */ -static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) -{ - int c, old; - c = atomic_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - - return c; -} - #endif /* CONFIG_CPU_J2 */ #endif /* __ASM_SH_ATOMIC_H */ diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h index a58f4b43bcc7..9d7a15acc0c5 100644 --- a/arch/sparc/include/asm/atomic_32.h +++ b/arch/sparc/include/asm/atomic_32.h @@ -30,6 +30,8 @@ int atomic_xchg(atomic_t *, int); int atomic_fetch_add_unless(atomic_t *, int, int); void atomic_set(atomic_t *, int); +#define atomic_fetch_add_unless atomic_fetch_add_unless + #define atomic_set_release(v, i) atomic_set((v), (i)) #define atomic_read(v) READ_ONCE((v)->counter) diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h index 07830a316464..e4f1c93db31f 100644 --- a/arch/sparc/include/asm/atomic_64.h +++ b/arch/sparc/include/asm/atomic_64.h @@ -89,21 +89,6 @@ static inline int atomic_xchg(atomic_t *v, int new) return xchg(&v->counter, new); } -static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) -{ - int c, old; - c = atomic_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - return c; -} - #define atomic64_cmpxchg(v, o, n) \ ((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n))) #define atomic64_xchg(v, new) (xchg(&((v)->counter), new)) diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h index 84ed0bd76aef..616327ac9d39 100644 --- a/arch/x86/include/asm/atomic.h +++ b/arch/x86/include/asm/atomic.h @@ -253,27 +253,6 @@ static inline int arch_atomic_fetch_xor(int i, atomic_t *v) return val; } -/** - * arch_atomic_fetch_add_unless - add unless the number is already a given value - * @v: pointer of type atomic_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as @v was not already @u. - * Returns the old value of @v. - */ -static __always_inline int arch_atomic_fetch_add_unless(atomic_t *v, int a, int u) -{ - int c = arch_atomic_read(v); - - do { - if (unlikely(c == u)) - break; - } while (!arch_atomic_try_cmpxchg(v, &c, c + a)); - - return c; -} - #ifdef CONFIG_X86_32 # include #else diff --git a/arch/xtensa/include/asm/atomic.h b/arch/xtensa/include/asm/atomic.h index 4188e56c06c9..f4c9f82c40c6 100644 --- a/arch/xtensa/include/asm/atomic.h +++ b/arch/xtensa/include/asm/atomic.h @@ -274,30 +274,6 @@ ATOMIC_OPS(xor) #define atomic_cmpxchg(v, o, n) ((int)cmpxchg(&((v)->counter), (o), (n))) #define atomic_xchg(v, new) (xchg(&((v)->counter), new)) -/** - * atomic_fetch_add_unless - add unless the number is a given value - * @v: pointer of type atomic_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as it was not @u. - * Returns the old value of @v. - */ -static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u) -{ - int c, old; - c = atomic_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - return c; -} - #endif /* __KERNEL__ */ #endif /* _XTENSA_ATOMIC_H */ diff --git a/include/asm-generic/atomic-instrumented.h b/include/asm-generic/atomic-instrumented.h index 83bb88d791c4..1f9b2a767d3c 100644 --- a/include/asm-generic/atomic-instrumented.h +++ b/include/asm-generic/atomic-instrumented.h @@ -84,12 +84,14 @@ static __always_inline bool atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 ne } #endif +#ifdef arch_atomic_fetch_add_unless +#define atomic_fetch_add_unless atomic_fetch_add_unless static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { kasan_check_write(v, sizeof(*v)); return arch_atomic_fetch_add_unless(v, a, u); } - +#endif static __always_inline bool atomic64_add_unless(atomic64_t *v, s64 a, s64 u) { diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h index 10051ed6d088..757e45821220 100644 --- a/include/asm-generic/atomic.h +++ b/include/asm-generic/atomic.h @@ -221,15 +221,4 @@ static inline void atomic_dec(atomic_t *v) #define atomic_xchg(ptr, v) (xchg(&(ptr)->counter, (v))) #define atomic_cmpxchg(v, old, new) (cmpxchg(&((v)->counter), (old), (new))) -#ifndef atomic_fetch_add_unless -static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) -{ - int c, old; - c = atomic_read(v); - while (c != u && (old = atomic_cmpxchg(v, c, c + a)) != c) - c = old; - return c; -} -#endif - #endif /* __ASM_GENERIC_ATOMIC_H */ diff --git a/include/linux/atomic.h b/include/linux/atomic.h index ae3f30923d05..b89ba36cab94 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -521,6 +521,29 @@ #endif #endif /* xchg_relaxed */ +/** + * atomic_fetch_add_unless - add unless the number is already a given value + * @v: pointer of type atomic_t + * @a: the amount to add to v... + * @u: ...unless v is equal to u. + * + * Atomically adds @a to @v, if @v was not already @u. + * Returns the original value of @v. + */ +#ifndef atomic_fetch_add_unless +static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) +{ + int c = atomic_read(v); + + do { + if (unlikely(c == u)) + break; + } while (!atomic_try_cmpxchg(v, &c, c + a)); + + return c; +} +#endif + /** * atomic_add_unless - add unless the number is already a given value * @v: pointer of type atomic_t -- cgit v1.2.3 From 0ae1d994020d75ac065fd42ac4cbf5ac6ce9b255 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Thu, 21 Jun 2018 13:13:10 +0100 Subject: atomics: Prepare for atomic64_fetch_add_unless() Currently all architectures must implement atomic_fetch_add_unless(), with common code providing atomic_add_unless(). Architectures must also implement atomic64_add_unless() directly, with no corresponding atomic64_fetch_add_unless(). This divergence is unfortunate, and means that the APIs for atomic_t, atomic64_t, and atomic_long_t differ. In preparation for unifying things, with architectures providing atomic64_fetch_add_unless, this patch adds a generic atomic64_add_unless() which will use atomic64_fetch_add_unless(). The instrumented atomics are updated to take this case into account. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Reviewed-by: Will Deacon Acked-by: Peter Zijlstra (Intel) Cc: Albert Ou Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Boqun Feng Cc: Ivan Kokshaysky Cc: Linus Torvalds Cc: Matt Turner Cc: Michael Ellerman Cc: Palmer Dabbelt Cc: Paul Mackerras Cc: Richard Henderson Cc: Russell King Cc: Thomas Gleixner Cc: Vineet Gupta Link: https://lore.kernel.org/lkml/20180621121321.4761-8-mark.rutland@arm.com Signed-off-by: Ingo Molnar --- include/asm-generic/atomic-instrumented.h | 9 +++++++++ include/linux/atomic.h | 16 ++++++++++++++++ 2 files changed, 25 insertions(+) (limited to 'include') diff --git a/include/asm-generic/atomic-instrumented.h b/include/asm-generic/atomic-instrumented.h index 1f9b2a767d3c..444bf2f9d54d 100644 --- a/include/asm-generic/atomic-instrumented.h +++ b/include/asm-generic/atomic-instrumented.h @@ -93,11 +93,20 @@ static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) } #endif +#ifdef arch_atomic64_fetch_add_unless +#define atomic64_fetch_add_unless atomic64_fetch_add_unless +static __always_inline s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) +{ + kasan_check_write(v, sizeof(*v)); + return arch_atomic64_fetch_add_unless(v, a, u); +} +#else static __always_inline bool atomic64_add_unless(atomic64_t *v, s64 a, s64 u) { kasan_check_write(v, sizeof(*v)); return arch_atomic64_add_unless(v, a, u); } +#endif static __always_inline void atomic_inc(atomic_t *v) { diff --git a/include/linux/atomic.h b/include/linux/atomic.h index b89ba36cab94..3c03de648007 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -1042,6 +1042,22 @@ static inline int atomic_dec_if_positive(atomic_t *v) #define atomic64_try_cmpxchg_release atomic64_try_cmpxchg #endif /* atomic64_try_cmpxchg */ +/** + * atomic64_add_unless - add unless the number is already a given value + * @v: pointer of type atomic_t + * @a: the amount to add to v... + * @u: ...unless v is equal to u. + * + * Atomically adds @a to @v, if @v was not already @u. + * Returns true if the addition was done. + */ +#ifdef atomic64_fetch_add_unless +static inline bool atomic64_add_unless(atomic64_t *v, long long a, long long u) +{ + return atomic64_fetch_add_unless(v, a, u) != u; +} +#endif + /** * atomic64_inc_not_zero - increment unless the number is zero * @v: pointer of type atomic64_t -- cgit v1.2.3 From 00b808ab79ead372daf1a0682d1ef271599c0b55 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Thu, 21 Jun 2018 13:13:11 +0100 Subject: atomics/generic: Define atomic64_fetch_add_unless() As a step towards unifying the atomic/atomic64/atomic_long APIs, this patch converts the generic implementation of atomic64_add_unless() into a generic implementation of atomic64_fetch_add_unless(). A wrapper in will build atomic_add_unless() atop of this, provided it is given a preprocessor definition. No functional change is intended as a result of this patch. Signed-off-by: Mark Rutland Reviewed-by: Will Deacon Acked-by: Peter Zijlstra (Intel) Cc: Arnd Bergmann Cc: Boqun Feng Cc: Linus Torvalds Cc: Thomas Gleixner Link: https://lore.kernel.org/lkml/20180621121321.4761-9-mark.rutland@arm.com Signed-off-by: Ingo Molnar --- include/asm-generic/atomic64.h | 3 ++- lib/atomic64.c | 14 +++++++------- 2 files changed, 9 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/asm-generic/atomic64.h b/include/asm-generic/atomic64.h index 5105275ac825..49460107b29a 100644 --- a/include/asm-generic/atomic64.h +++ b/include/asm-generic/atomic64.h @@ -53,7 +53,8 @@ ATOMIC64_OPS(xor) extern long long atomic64_dec_if_positive(atomic64_t *v); extern long long atomic64_cmpxchg(atomic64_t *v, long long o, long long n); extern long long atomic64_xchg(atomic64_t *v, long long new); -extern bool atomic64_add_unless(atomic64_t *v, long long a, long long u); +extern long long atomic64_fetch_add_unless(atomic64_t *v, long long a, long long u); +#define atomic64_fetch_add_unless atomic64_fetch_add_unless #define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0) #define atomic64_inc(v) atomic64_add(1LL, (v)) diff --git a/lib/atomic64.c b/lib/atomic64.c index 4230f4b8906c..1d91e31eceec 100644 --- a/lib/atomic64.c +++ b/lib/atomic64.c @@ -178,18 +178,18 @@ long long atomic64_xchg(atomic64_t *v, long long new) } EXPORT_SYMBOL(atomic64_xchg); -bool atomic64_add_unless(atomic64_t *v, long long a, long long u) +long long atomic64_fetch_add_unless(atomic64_t *v, long long a, long long u) { unsigned long flags; raw_spinlock_t *lock = lock_addr(v); - bool ret = false; + long long val; raw_spin_lock_irqsave(lock, flags); - if (v->counter != u) { + val = v->counter; + if (val != u) v->counter += a; - ret = true; - } raw_spin_unlock_irqrestore(lock, flags); - return ret; + + return val; } -EXPORT_SYMBOL(atomic64_add_unless); +EXPORT_SYMBOL(atomic64_fetch_add_unless); -- cgit v1.2.3 From 356701329fb391184618eda7b7fb68cb35271506 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Thu, 21 Jun 2018 13:13:17 +0100 Subject: atomics/treewide: Make atomic64_fetch_add_unless() optional Architectures with atomic64_fetch_add_unless() provide a preprocessor symbol if they do so, and all other architectures have trivial C implementations of atomic64_add_unless() which are near-identical. Let's unify the trivial definitions of atomic64_fetch_add_unless() in , so that we always have both atomic64_fetch_add_unless() and atomic64_add_unless() with less boilerplate code. This means that atomic64_add_unless() is always implemented in core code, and the instrumented atomics are updated accordingly. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Reviewed-by: Will Deacon Acked-by: Peter Zijlstra (Intel) Cc: Boqun Feng Cc: Linus Torvalds Cc: Thomas Gleixner Link: https://lore.kernel.org/lkml/20180621121321.4761-15-mark.rutland@arm.com Signed-off-by: Ingo Molnar --- arch/arm64/include/asm/atomic.h | 12 ------------ arch/ia64/include/asm/atomic.h | 15 --------------- arch/mips/include/asm/atomic.h | 24 ------------------------ arch/parisc/include/asm/atomic.h | 24 ------------------------ arch/s390/include/asm/atomic.h | 16 ---------------- arch/sparc/include/asm/atomic_64.h | 15 --------------- arch/x86/include/asm/atomic64_64.h | 19 ------------------- include/asm-generic/atomic-instrumented.h | 6 ------ include/linux/atomic.h | 26 ++++++++++++++++++++++++-- 9 files changed, 24 insertions(+), 133 deletions(-) (limited to 'include') diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h index 22c8c43d6689..82db0e4febd4 100644 --- a/arch/arm64/include/asm/atomic.h +++ b/arch/arm64/include/asm/atomic.h @@ -40,17 +40,6 @@ #include -#define ___atomic_add_unless(v, a, u, sfx) \ -({ \ - typeof((v)->counter) c, old; \ - \ - c = atomic##sfx##_read(v); \ - while (c != (u) && \ - (old = atomic##sfx##_cmpxchg((v), c, c + (a))) != c) \ - c = old; \ - c; \ - }) - #define ATOMIC_INIT(i) { (i) } #define atomic_read(v) READ_ONCE((v)->counter) @@ -200,7 +189,6 @@ #define atomic64_dec_and_test(v) (atomic64_dec_return(v) == 0) #define atomic64_sub_and_test(i, v) (atomic64_sub_return((i), (v)) == 0) #define atomic64_add_negative(i, v) (atomic64_add_return((i), (v)) < 0) -#define atomic64_add_unless(v, a, u) (___atomic_add_unless(v, a, u, 64) != u) #define atomic64_andnot atomic64_andnot #endif diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h index cfe44086338e..0f80a3eafaba 100644 --- a/arch/ia64/include/asm/atomic.h +++ b/arch/ia64/include/asm/atomic.h @@ -215,21 +215,6 @@ ATOMIC64_FETCH_OP(xor, ^) (cmpxchg(&((v)->counter), old, new)) #define atomic64_xchg(v, new) (xchg(&((v)->counter), new)) -static __inline__ long atomic64_add_unless(atomic64_t *v, long a, long u) -{ - long c, old; - c = atomic64_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic64_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - return c != (u); -} - static __inline__ long atomic64_dec_if_positive(atomic64_t *v) { long c, old, dec; diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h index 794734e730d9..d42b27df1548 100644 --- a/arch/mips/include/asm/atomic.h +++ b/arch/mips/include/asm/atomic.h @@ -596,30 +596,6 @@ static __inline__ long atomic64_sub_if_positive(long i, atomic64_t * v) ((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n))) #define atomic64_xchg(v, new) (xchg(&((v)->counter), (new))) -/** - * atomic64_add_unless - add unless the number is a given value - * @v: pointer of type atomic64_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as it was not @u. - * Returns true iff @v was not @u. - */ -static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u) -{ - long c, old; - c = atomic64_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic64_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - return c != (u); -} - #define atomic64_dec_return(v) atomic64_sub_return(1, (v)) #define atomic64_inc_return(v) atomic64_add_return(1, (v)) diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h index b2b6261d05e7..f53ba2d6ff67 100644 --- a/arch/parisc/include/asm/atomic.h +++ b/arch/parisc/include/asm/atomic.h @@ -257,30 +257,6 @@ atomic64_read(const atomic64_t *v) ((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n))) #define atomic64_xchg(v, new) (xchg(&((v)->counter), new)) -/** - * atomic64_add_unless - add unless the number is a given value - * @v: pointer of type atomic64_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as it was not @u. - * Returns the old value of @v. - */ -static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u) -{ - long c, old; - c = atomic64_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic64_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - return c != (u); -} - /* * atomic64_dec_if_positive - decrement by 1 if old value positive * @v: pointer of type atomic_t diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h index 26c6b713a7a3..eb9329741bad 100644 --- a/arch/s390/include/asm/atomic.h +++ b/arch/s390/include/asm/atomic.h @@ -153,22 +153,6 @@ ATOMIC64_OPS(xor) #undef ATOMIC64_OPS -static inline int atomic64_add_unless(atomic64_t *v, long i, long u) -{ - long c, old; - - c = atomic64_read(v); - for (;;) { - if (unlikely(c == u)) - break; - old = atomic64_cmpxchg(v, c, c + i); - if (likely(old == c)) - break; - c = old; - } - return c != u; -} - static inline long atomic64_dec_if_positive(atomic64_t *v) { long c, old, dec; diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h index e4f1c93db31f..458783e99997 100644 --- a/arch/sparc/include/asm/atomic_64.h +++ b/arch/sparc/include/asm/atomic_64.h @@ -93,21 +93,6 @@ static inline int atomic_xchg(atomic_t *v, int new) ((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n))) #define atomic64_xchg(v, new) (xchg(&((v)->counter), new)) -static inline long atomic64_add_unless(atomic64_t *v, long a, long u) -{ - long c, old; - c = atomic64_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic64_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - return c != (u); -} - long atomic64_dec_if_positive(atomic64_t *v); #endif /* !(__ARCH_SPARC64_ATOMIC__) */ diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h index 6f95023894b7..7e04b294e6eb 100644 --- a/arch/x86/include/asm/atomic64_64.h +++ b/arch/x86/include/asm/atomic64_64.h @@ -188,25 +188,6 @@ static inline long arch_atomic64_xchg(atomic64_t *v, long new) return xchg(&v->counter, new); } -/** - * arch_atomic64_add_unless - add unless the number is a given value - * @v: pointer of type atomic64_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as it was not @u. - * Returns the old value of @v. - */ -static inline bool arch_atomic64_add_unless(atomic64_t *v, long a, long u) -{ - s64 c = arch_atomic64_read(v); - do { - if (unlikely(c == u)) - return false; - } while (!arch_atomic64_try_cmpxchg(v, &c, c + a)); - return true; -} - /* * arch_atomic64_dec_if_positive - decrement by 1 if old value positive * @v: pointer of type atomic_t diff --git a/include/asm-generic/atomic-instrumented.h b/include/asm-generic/atomic-instrumented.h index 444bf2f9d54d..2b487f28ef35 100644 --- a/include/asm-generic/atomic-instrumented.h +++ b/include/asm-generic/atomic-instrumented.h @@ -100,12 +100,6 @@ static __always_inline s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u kasan_check_write(v, sizeof(*v)); return arch_atomic64_fetch_add_unless(v, a, u); } -#else -static __always_inline bool atomic64_add_unless(atomic64_t *v, s64 a, s64 u) -{ - kasan_check_write(v, sizeof(*v)); - return arch_atomic64_add_unless(v, a, u); -} #endif static __always_inline void atomic_inc(atomic_t *v) diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 3c03de648007..530562ac7909 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -1042,6 +1042,30 @@ static inline int atomic_dec_if_positive(atomic_t *v) #define atomic64_try_cmpxchg_release atomic64_try_cmpxchg #endif /* atomic64_try_cmpxchg */ +/** + * atomic64_fetch_add_unless - add unless the number is already a given value + * @v: pointer of type atomic64_t + * @a: the amount to add to v... + * @u: ...unless v is equal to u. + * + * Atomically adds @a to @v, if @v was not already @u. + * Returns the original value of @v. + */ +#ifndef atomic64_fetch_add_unless +static inline long long atomic64_fetch_add_unless(atomic64_t *v, long long a, + long long u) +{ + long long c = atomic64_read(v); + + do { + if (unlikely(c == u)) + break; + } while (!atomic64_try_cmpxchg(v, &c, c + a)); + + return c; +} +#endif + /** * atomic64_add_unless - add unless the number is already a given value * @v: pointer of type atomic_t @@ -1051,12 +1075,10 @@ static inline int atomic_dec_if_positive(atomic_t *v) * Atomically adds @a to @v, if @v was not already @u. * Returns true if the addition was done. */ -#ifdef atomic64_fetch_add_unless static inline bool atomic64_add_unless(atomic64_t *v, long long a, long long u) { return atomic64_fetch_add_unless(v, a, u) != u; } -#endif /** * atomic64_inc_not_zero - increment unless the number is zero -- cgit v1.2.3 From 18cc1814d4e7560412c9c8c6d28f9d6782c8b402 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Thu, 21 Jun 2018 13:13:18 +0100 Subject: atomics/treewide: Make test ops optional Some of the atomics return the result of a test applied after the atomic operation, and almost all architectures implement these as trivial wrappers around the underlying atomic. Specifically: * _inc_and_test(v) is (_inc_return(v) == 0) * _dec_and_test(v) is (_dec_return(v) == 0) * _sub_and_test(i, v) is (_sub_return(i, v) == 0) * _add_negative(i, v) is (_add_return(i, v) < 0) Rather than have these definitions duplicated in all architectures, with minor inconsistencies in formatting and documentation, let's make these operations optional, with default fallbacks as above. Implementations must now provide a preprocessor symbol. The instrumented atomics are updated accordingly. Both x86 and m68k have custom implementations, which are left as-is, given preprocessor symbols to avoid being overridden. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Reviewed-by: Will Deacon Acked-by: Geert Uytterhoeven Acked-by: Peter Zijlstra (Intel) Acked-by: Palmer Dabbelt Cc: Boqun Feng Cc: Linus Torvalds Cc: Thomas Gleixner Link: https://lore.kernel.org/lkml/20180621121321.4761-16-mark.rutland@arm.com Signed-off-by: Ingo Molnar --- arch/alpha/include/asm/atomic.h | 12 --- arch/arc/include/asm/atomic.h | 10 --- arch/arm/include/asm/atomic.h | 9 --- arch/arm64/include/asm/atomic.h | 8 -- arch/h8300/include/asm/atomic.h | 5 -- arch/hexagon/include/asm/atomic.h | 5 -- arch/ia64/include/asm/atomic.h | 23 ------ arch/m68k/include/asm/atomic.h | 4 + arch/mips/include/asm/atomic.h | 84 -------------------- arch/parisc/include/asm/atomic.h | 22 ------ arch/powerpc/include/asm/atomic.h | 30 -------- arch/riscv/include/asm/atomic.h | 46 ----------- arch/s390/include/asm/atomic.h | 8 -- arch/sh/include/asm/atomic.h | 4 - arch/sparc/include/asm/atomic_32.h | 15 ---- arch/sparc/include/asm/atomic_64.h | 20 ----- arch/x86/include/asm/atomic.h | 4 + arch/x86/include/asm/atomic64_32.h | 54 ------------- arch/x86/include/asm/atomic64_64.h | 4 + arch/xtensa/include/asm/atomic.h | 42 ---------- include/asm-generic/atomic-instrumented.h | 24 ++++++ include/asm-generic/atomic.h | 9 --- include/asm-generic/atomic64.h | 4 - include/linux/atomic.h | 124 ++++++++++++++++++++++++++++++ 24 files changed, 160 insertions(+), 410 deletions(-) (limited to 'include') diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h index cc486dbb3837..25f8693c5a42 100644 --- a/arch/alpha/include/asm/atomic.h +++ b/arch/alpha/include/asm/atomic.h @@ -297,24 +297,12 @@ static inline long atomic64_dec_if_positive(atomic64_t *v) return old - 1; } -#define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0) -#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0) - #define atomic_dec_return(v) atomic_sub_return(1,(v)) #define atomic64_dec_return(v) atomic64_sub_return(1,(v)) #define atomic_inc_return(v) atomic_add_return(1,(v)) #define atomic64_inc_return(v) atomic64_add_return(1,(v)) -#define atomic_sub_and_test(i,v) (atomic_sub_return((i), (v)) == 0) -#define atomic64_sub_and_test(i,v) (atomic64_sub_return((i), (v)) == 0) - -#define atomic_inc_and_test(v) (atomic_add_return(1, (v)) == 0) -#define atomic64_inc_and_test(v) (atomic64_add_return(1, (v)) == 0) - -#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0) -#define atomic64_dec_and_test(v) (atomic64_sub_return(1, (v)) == 0) - #define atomic_inc(v) atomic_add(1,(v)) #define atomic64_inc(v) atomic64_add(1,(v)) diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h index 4917ffa61579..4222e726f84c 100644 --- a/arch/arc/include/asm/atomic.h +++ b/arch/arc/include/asm/atomic.h @@ -311,14 +311,8 @@ ATOMIC_OPS(xor, ^=, CTOP_INST_AXOR_DI_R2_R2_R3) #define atomic_inc(v) atomic_add(1, v) #define atomic_dec(v) atomic_sub(1, v) -#define atomic_inc_and_test(v) (atomic_add_return(1, v) == 0) -#define atomic_dec_and_test(v) (atomic_sub_return(1, v) == 0) #define atomic_inc_return(v) atomic_add_return(1, (v)) #define atomic_dec_return(v) atomic_sub_return(1, (v)) -#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0) - -#define atomic_add_negative(i, v) (atomic_add_return(i, v) < 0) - #ifdef CONFIG_GENERIC_ATOMIC64 @@ -566,14 +560,10 @@ static inline long long atomic64_fetch_add_unless(atomic64_t *v, long long a, } #define atomic64_fetch_add_unless atomic64_fetch_add_unless -#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0) #define atomic64_inc(v) atomic64_add(1LL, (v)) #define atomic64_inc_return(v) atomic64_add_return(1LL, (v)) -#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0) -#define atomic64_sub_and_test(a, v) (atomic64_sub_return((a), (v)) == 0) #define atomic64_dec(v) atomic64_sub(1LL, (v)) #define atomic64_dec_return(v) atomic64_sub_return(1LL, (v)) -#define atomic64_dec_and_test(v) (atomic64_dec_return((v)) == 0) #endif /* !CONFIG_GENERIC_ATOMIC64 */ diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h index 852e1fee72b0..35fb7f504daa 100644 --- a/arch/arm/include/asm/atomic.h +++ b/arch/arm/include/asm/atomic.h @@ -248,13 +248,8 @@ ATOMIC_OPS(xor, ^=, eor) #define atomic_inc(v) atomic_add(1, v) #define atomic_dec(v) atomic_sub(1, v) -#define atomic_inc_and_test(v) (atomic_add_return(1, v) == 0) -#define atomic_dec_and_test(v) (atomic_sub_return(1, v) == 0) #define atomic_inc_return_relaxed(v) (atomic_add_return_relaxed(1, v)) #define atomic_dec_return_relaxed(v) (atomic_sub_return_relaxed(1, v)) -#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0) - -#define atomic_add_negative(i,v) (atomic_add_return(i, v) < 0) #ifndef CONFIG_GENERIC_ATOMIC64 typedef struct { @@ -517,14 +512,10 @@ static inline long long atomic64_fetch_add_unless(atomic64_t *v, long long a, } #define atomic64_fetch_add_unless atomic64_fetch_add_unless -#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0) #define atomic64_inc(v) atomic64_add(1LL, (v)) #define atomic64_inc_return_relaxed(v) atomic64_add_return_relaxed(1LL, (v)) -#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0) -#define atomic64_sub_and_test(a, v) (atomic64_sub_return((a), (v)) == 0) #define atomic64_dec(v) atomic64_sub(1LL, (v)) #define atomic64_dec_return_relaxed(v) atomic64_sub_return_relaxed(1LL, (v)) -#define atomic64_dec_and_test(v) (atomic64_dec_return((v)) == 0) #endif /* !CONFIG_GENERIC_ATOMIC64 */ #endif diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h index 82db0e4febd4..edbe53fa3106 100644 --- a/arch/arm64/include/asm/atomic.h +++ b/arch/arm64/include/asm/atomic.h @@ -110,10 +110,6 @@ #define atomic_inc(v) atomic_add(1, (v)) #define atomic_dec(v) atomic_sub(1, (v)) -#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0) -#define atomic_dec_and_test(v) (atomic_dec_return(v) == 0) -#define atomic_sub_and_test(i, v) (atomic_sub_return((i), (v)) == 0) -#define atomic_add_negative(i, v) (atomic_add_return((i), (v)) < 0) #define atomic_andnot atomic_andnot /* @@ -185,10 +181,6 @@ #define atomic64_inc(v) atomic64_add(1, (v)) #define atomic64_dec(v) atomic64_sub(1, (v)) -#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0) -#define atomic64_dec_and_test(v) (atomic64_dec_return(v) == 0) -#define atomic64_sub_and_test(i, v) (atomic64_sub_return((i), (v)) == 0) -#define atomic64_add_negative(i, v) (atomic64_add_return((i), (v)) < 0) #define atomic64_andnot atomic64_andnot #endif diff --git a/arch/h8300/include/asm/atomic.h b/arch/h8300/include/asm/atomic.h index 710364946308..8977b5157c8f 100644 --- a/arch/h8300/include/asm/atomic.h +++ b/arch/h8300/include/asm/atomic.h @@ -69,17 +69,12 @@ ATOMIC_OPS(sub, -=) #undef ATOMIC_OP_RETURN #undef ATOMIC_OP -#define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0) -#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0) - #define atomic_inc_return(v) atomic_add_return(1, v) #define atomic_dec_return(v) atomic_sub_return(1, v) #define atomic_inc(v) (void)atomic_inc_return(v) -#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0) #define atomic_dec(v) (void)atomic_dec_return(v) -#define atomic_dec_and_test(v) (atomic_dec_return(v) == 0) static inline int atomic_cmpxchg(atomic_t *v, int old, int new) { diff --git a/arch/hexagon/include/asm/atomic.h b/arch/hexagon/include/asm/atomic.h index 86c67e9adbfa..31638f511674 100644 --- a/arch/hexagon/include/asm/atomic.h +++ b/arch/hexagon/include/asm/atomic.h @@ -201,11 +201,6 @@ static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) #define atomic_inc(v) atomic_add(1, (v)) #define atomic_dec(v) atomic_sub(1, (v)) -#define atomic_inc_and_test(v) (atomic_add_return(1, (v)) == 0) -#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0) -#define atomic_sub_and_test(i, v) (atomic_sub_return(i, (v)) == 0) -#define atomic_add_negative(i, v) (atomic_add_return(i, (v)) < 0) - #define atomic_inc_return(v) (atomic_add_return(1, v)) #define atomic_dec_return(v) (atomic_sub_return(1, v)) diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h index 0f80a3eafaba..e4143c462e65 100644 --- a/arch/ia64/include/asm/atomic.h +++ b/arch/ia64/include/asm/atomic.h @@ -231,34 +231,11 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v) return dec; } -/* - * Atomically add I to V and return TRUE if the resulting value is - * negative. - */ -static __inline__ int -atomic_add_negative (int i, atomic_t *v) -{ - return atomic_add_return(i, v) < 0; -} - -static __inline__ long -atomic64_add_negative (__s64 i, atomic64_t *v) -{ - return atomic64_add_return(i, v) < 0; -} - #define atomic_dec_return(v) atomic_sub_return(1, (v)) #define atomic_inc_return(v) atomic_add_return(1, (v)) #define atomic64_dec_return(v) atomic64_sub_return(1, (v)) #define atomic64_inc_return(v) atomic64_add_return(1, (v)) -#define atomic_sub_and_test(i,v) (atomic_sub_return((i), (v)) == 0) -#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0) -#define atomic_inc_and_test(v) (atomic_add_return(1, (v)) == 0) -#define atomic64_sub_and_test(i,v) (atomic64_sub_return((i), (v)) == 0) -#define atomic64_dec_and_test(v) (atomic64_sub_return(1, (v)) == 0) -#define atomic64_inc_and_test(v) (atomic64_add_return(1, (v)) == 0) - #define atomic_add(i,v) (void)atomic_add_return((i), (v)) #define atomic_sub(i,v) (void)atomic_sub_return((i), (v)) #define atomic_inc(v) atomic_add(1, (v)) diff --git a/arch/m68k/include/asm/atomic.h b/arch/m68k/include/asm/atomic.h index 596882cda224..9df09c876fa2 100644 --- a/arch/m68k/include/asm/atomic.h +++ b/arch/m68k/include/asm/atomic.h @@ -138,6 +138,7 @@ static inline int atomic_dec_and_test(atomic_t *v) __asm__ __volatile__("subql #1,%1; seq %0" : "=d" (c), "+m" (*v)); return c != 0; } +#define atomic_dec_and_test atomic_dec_and_test static inline int atomic_dec_and_test_lt(atomic_t *v) { @@ -155,6 +156,7 @@ static inline int atomic_inc_and_test(atomic_t *v) __asm__ __volatile__("addql #1,%1; seq %0" : "=d" (c), "+m" (*v)); return c != 0; } +#define atomic_inc_and_test atomic_inc_and_test #ifdef CONFIG_RMW_INSNS @@ -201,6 +203,7 @@ static inline int atomic_sub_and_test(int i, atomic_t *v) : ASM_DI (i)); return c != 0; } +#define atomic_sub_and_test atomic_sub_and_test static inline int atomic_add_negative(int i, atomic_t *v) { @@ -210,5 +213,6 @@ static inline int atomic_add_negative(int i, atomic_t *v) : ASM_DI (i)); return c != 0; } +#define atomic_add_negative atomic_add_negative #endif /* __ARCH_M68K_ATOMIC __ */ diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h index d42b27df1548..fd3008ae164c 100644 --- a/arch/mips/include/asm/atomic.h +++ b/arch/mips/include/asm/atomic.h @@ -277,37 +277,6 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v) #define atomic_dec_return(v) atomic_sub_return(1, (v)) #define atomic_inc_return(v) atomic_add_return(1, (v)) -/* - * atomic_sub_and_test - subtract value from variable and test result - * @i: integer value to subtract - * @v: pointer of type atomic_t - * - * Atomically subtracts @i from @v and returns - * true if the result is zero, or false for all - * other cases. - */ -#define atomic_sub_and_test(i, v) (atomic_sub_return((i), (v)) == 0) - -/* - * atomic_inc_and_test - increment and test - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0) - -/* - * atomic_dec_and_test - decrement by 1 and test - * @v: pointer of type atomic_t - * - * Atomically decrements @v by 1 and - * returns true if the result is 0, or false for all other - * cases. - */ -#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0) - /* * atomic_dec_if_positive - decrement by 1 if old value positive * @v: pointer of type atomic_t @@ -330,17 +299,6 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v) */ #define atomic_dec(v) atomic_sub(1, (v)) -/* - * atomic_add_negative - add and test if negative - * @v: pointer of type atomic_t - * @i: integer value to add - * - * Atomically adds @i to @v and returns true - * if the result is negative, or false when - * result is greater than or equal to zero. - */ -#define atomic_add_negative(i, v) (atomic_add_return(i, (v)) < 0) - #ifdef CONFIG_64BIT #define ATOMIC64_INIT(i) { (i) } @@ -599,37 +557,6 @@ static __inline__ long atomic64_sub_if_positive(long i, atomic64_t * v) #define atomic64_dec_return(v) atomic64_sub_return(1, (v)) #define atomic64_inc_return(v) atomic64_add_return(1, (v)) -/* - * atomic64_sub_and_test - subtract value from variable and test result - * @i: integer value to subtract - * @v: pointer of type atomic64_t - * - * Atomically subtracts @i from @v and returns - * true if the result is zero, or false for all - * other cases. - */ -#define atomic64_sub_and_test(i, v) (atomic64_sub_return((i), (v)) == 0) - -/* - * atomic64_inc_and_test - increment and test - * @v: pointer of type atomic64_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0) - -/* - * atomic64_dec_and_test - decrement by 1 and test - * @v: pointer of type atomic64_t - * - * Atomically decrements @v by 1 and - * returns true if the result is 0, or false for all other - * cases. - */ -#define atomic64_dec_and_test(v) (atomic64_sub_return(1, (v)) == 0) - /* * atomic64_dec_if_positive - decrement by 1 if old value positive * @v: pointer of type atomic64_t @@ -652,17 +579,6 @@ static __inline__ long atomic64_sub_if_positive(long i, atomic64_t * v) */ #define atomic64_dec(v) atomic64_sub(1, (v)) -/* - * atomic64_add_negative - add and test if negative - * @v: pointer of type atomic64_t - * @i: integer value to add - * - * Atomically adds @i to @v and returns true - * if the result is negative, or false when - * result is greater than or equal to zero. - */ -#define atomic64_add_negative(i, v) (atomic64_add_return(i, (v)) < 0) - #endif /* CONFIG_64BIT */ #endif /* _ASM_ATOMIC_H */ diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h index f53ba2d6ff67..f85844ff6336 100644 --- a/arch/parisc/include/asm/atomic.h +++ b/arch/parisc/include/asm/atomic.h @@ -142,22 +142,6 @@ ATOMIC_OPS(xor, ^=) #define atomic_inc_return(v) (atomic_add_return( 1,(v))) #define atomic_dec_return(v) (atomic_add_return( -1,(v))) -#define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0) - -/* - * atomic_inc_and_test - increment and test - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0) - -#define atomic_dec_and_test(v) (atomic_dec_return(v) == 0) - -#define atomic_sub_and_test(i,v) (atomic_sub_return((i),(v)) == 0) - #define ATOMIC_INIT(i) { (i) } #ifdef CONFIG_64BIT @@ -246,12 +230,6 @@ atomic64_read(const atomic64_t *v) #define atomic64_inc_return(v) (atomic64_add_return( 1,(v))) #define atomic64_dec_return(v) (atomic64_add_return( -1,(v))) -#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0) - -#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0) -#define atomic64_dec_and_test(v) (atomic64_dec_return(v) == 0) -#define atomic64_sub_and_test(i,v) (atomic64_sub_return((i),(v)) == 0) - /* exported interface */ #define atomic64_cmpxchg(v, o, n) \ ((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n))) diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h index 233dbf31911c..5d76f05d2be3 100644 --- a/arch/powerpc/include/asm/atomic.h +++ b/arch/powerpc/include/asm/atomic.h @@ -129,8 +129,6 @@ ATOMIC_OPS(xor, xor) #undef ATOMIC_OP_RETURN_RELAXED #undef ATOMIC_OP -#define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0) - static __inline__ void atomic_inc(atomic_t *v) { int t; @@ -163,16 +161,6 @@ static __inline__ int atomic_inc_return_relaxed(atomic_t *v) return t; } -/* - * atomic_inc_and_test - increment and test - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0) - static __inline__ void atomic_dec(atomic_t *v) { int t; @@ -281,9 +269,6 @@ static __inline__ int atomic_inc_not_zero(atomic_t *v) } #define atomic_inc_not_zero(v) atomic_inc_not_zero((v)) -#define atomic_sub_and_test(a, v) (atomic_sub_return((a), (v)) == 0) -#define atomic_dec_and_test(v) (atomic_dec_return((v)) == 0) - /* * Atomically test *v and decrement if it is greater than 0. * The function returns the old value of *v minus 1, even if @@ -413,8 +398,6 @@ ATOMIC64_OPS(xor, xor) #undef ATOMIC64_OP_RETURN_RELAXED #undef ATOMIC64_OP -#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0) - static __inline__ void atomic64_inc(atomic64_t *v) { long t; @@ -445,16 +428,6 @@ static __inline__ long atomic64_inc_return_relaxed(atomic64_t *v) return t; } -/* - * atomic64_inc_and_test - increment and test - * @v: pointer of type atomic64_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0) - static __inline__ void atomic64_dec(atomic64_t *v) { long t; @@ -488,9 +461,6 @@ static __inline__ long atomic64_dec_return_relaxed(atomic64_t *v) #define atomic64_inc_return_relaxed atomic64_inc_return_relaxed #define atomic64_dec_return_relaxed atomic64_dec_return_relaxed -#define atomic64_sub_and_test(a, v) (atomic64_sub_return((a), (v)) == 0) -#define atomic64_dec_and_test(v) (atomic64_dec_return((v)) == 0) - /* * Atomically test *v and decrement if it is greater than 0. * The function returns the old value of *v minus 1. diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h index d959bbaaad41..68eef0a805ca 100644 --- a/arch/riscv/include/asm/atomic.h +++ b/arch/riscv/include/asm/atomic.h @@ -209,36 +209,6 @@ ATOMIC_OPS(xor, xor, i) #undef ATOMIC_FETCH_OP #undef ATOMIC_OP_RETURN -/* - * The extra atomic operations that are constructed from one of the core - * AMO-based operations above (aside from sub, which is easier to fit above). - * These are required to perform a full barrier, but they're OK this way - * because atomic_*_return is also required to perform a full barrier. - * - */ -#define ATOMIC_OP(op, func_op, comp_op, I, c_type, prefix) \ -static __always_inline \ -bool atomic##prefix##_##op(c_type i, atomic##prefix##_t *v) \ -{ \ - return atomic##prefix##_##func_op##_return(i, v) comp_op I; \ -} - -#ifdef CONFIG_GENERIC_ATOMIC64 -#define ATOMIC_OPS(op, func_op, comp_op, I) \ - ATOMIC_OP(op, func_op, comp_op, I, int, ) -#else -#define ATOMIC_OPS(op, func_op, comp_op, I) \ - ATOMIC_OP(op, func_op, comp_op, I, int, ) \ - ATOMIC_OP(op, func_op, comp_op, I, long, 64) -#endif - -ATOMIC_OPS(add_and_test, add, ==, 0) -ATOMIC_OPS(sub_and_test, sub, ==, 0) -ATOMIC_OPS(add_negative, add, <, 0) - -#undef ATOMIC_OP -#undef ATOMIC_OPS - #define ATOMIC_OP(op, func_op, I, c_type, prefix) \ static __always_inline \ void atomic##prefix##_##op(atomic##prefix##_t *v) \ @@ -315,22 +285,6 @@ ATOMIC_OPS(dec, add, +, -1) #undef ATOMIC_FETCH_OP #undef ATOMIC_OP_RETURN -#define ATOMIC_OP(op, func_op, comp_op, I, prefix) \ -static __always_inline \ -bool atomic##prefix##_##op(atomic##prefix##_t *v) \ -{ \ - return atomic##prefix##_##func_op##_return(v) comp_op I; \ -} - -ATOMIC_OP(inc_and_test, inc, ==, 0, ) -ATOMIC_OP(dec_and_test, dec, ==, 0, ) -#ifndef CONFIG_GENERIC_ATOMIC64 -ATOMIC_OP(inc_and_test, inc, ==, 0, 64) -ATOMIC_OP(dec_and_test, dec, ==, 0, 64) -#endif - -#undef ATOMIC_OP - /* This is required to provide a full barrier on success. */ static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h index eb9329741bad..7f5fbd595f01 100644 --- a/arch/s390/include/asm/atomic.h +++ b/arch/s390/include/asm/atomic.h @@ -55,17 +55,13 @@ static inline void atomic_add(int i, atomic_t *v) __atomic_add(i, &v->counter); } -#define atomic_add_negative(_i, _v) (atomic_add_return(_i, _v) < 0) #define atomic_inc(_v) atomic_add(1, _v) #define atomic_inc_return(_v) atomic_add_return(1, _v) -#define atomic_inc_and_test(_v) (atomic_add_return(1, _v) == 0) #define atomic_sub(_i, _v) atomic_add(-(int)(_i), _v) #define atomic_sub_return(_i, _v) atomic_add_return(-(int)(_i), _v) #define atomic_fetch_sub(_i, _v) atomic_fetch_add(-(int)(_i), _v) -#define atomic_sub_and_test(_i, _v) (atomic_sub_return(_i, _v) == 0) #define atomic_dec(_v) atomic_sub(1, _v) #define atomic_dec_return(_v) atomic_sub_return(1, _v) -#define atomic_dec_and_test(_v) (atomic_sub_return(1, _v) == 0) #define ATOMIC_OPS(op) \ static inline void atomic_##op(int i, atomic_t *v) \ @@ -170,16 +166,12 @@ static inline long atomic64_dec_if_positive(atomic64_t *v) return dec; } -#define atomic64_add_negative(_i, _v) (atomic64_add_return(_i, _v) < 0) #define atomic64_inc(_v) atomic64_add(1, _v) #define atomic64_inc_return(_v) atomic64_add_return(1, _v) -#define atomic64_inc_and_test(_v) (atomic64_add_return(1, _v) == 0) #define atomic64_sub_return(_i, _v) atomic64_add_return(-(long)(_i), _v) #define atomic64_fetch_sub(_i, _v) atomic64_fetch_add(-(long)(_i), _v) #define atomic64_sub(_i, _v) atomic64_add(-(long)(_i), _v) -#define atomic64_sub_and_test(_i, _v) (atomic64_sub_return(_i, _v) == 0) #define atomic64_dec(_v) atomic64_sub(1, _v) #define atomic64_dec_return(_v) atomic64_sub_return(1, _v) -#define atomic64_dec_and_test(_v) (atomic64_sub_return(1, _v) == 0) #endif /* __ARCH_S390_ATOMIC__ */ diff --git a/arch/sh/include/asm/atomic.h b/arch/sh/include/asm/atomic.h index 422fac764ca1..d438494fa112 100644 --- a/arch/sh/include/asm/atomic.h +++ b/arch/sh/include/asm/atomic.h @@ -32,12 +32,8 @@ #include #endif -#define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0) #define atomic_dec_return(v) atomic_sub_return(1, (v)) #define atomic_inc_return(v) atomic_add_return(1, (v)) -#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0) -#define atomic_sub_and_test(i,v) (atomic_sub_return((i), (v)) == 0) -#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0) #define atomic_inc(v) atomic_add(1, (v)) #define atomic_dec(v) atomic_sub(1, (v)) diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h index 9d7a15acc0c5..3a26573790c6 100644 --- a/arch/sparc/include/asm/atomic_32.h +++ b/arch/sparc/include/asm/atomic_32.h @@ -51,19 +51,4 @@ void atomic_set(atomic_t *, int); #define atomic_inc_return(v) (atomic_add_return( 1, (v))) #define atomic_dec_return(v) (atomic_add_return( -1, (v))) -#define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0) - -/* - * atomic_inc_and_test - increment and test - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0) - -#define atomic_dec_and_test(v) (atomic_dec_return(v) == 0) -#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0) - #endif /* !(__ARCH_SPARC_ATOMIC__) */ diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h index 458783e99997..634508282aea 100644 --- a/arch/sparc/include/asm/atomic_64.h +++ b/arch/sparc/include/asm/atomic_64.h @@ -56,32 +56,12 @@ ATOMIC_OPS(xor) #define atomic_inc_return(v) atomic_add_return(1, v) #define atomic64_inc_return(v) atomic64_add_return(1, v) -/* - * atomic_inc_and_test - increment and test - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0) -#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0) - -#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0) -#define atomic64_sub_and_test(i, v) (atomic64_sub_return(i, v) == 0) - -#define atomic_dec_and_test(v) (atomic_sub_return(1, v) == 0) -#define atomic64_dec_and_test(v) (atomic64_sub_return(1, v) == 0) - #define atomic_inc(v) atomic_add(1, v) #define atomic64_inc(v) atomic64_add(1, v) #define atomic_dec(v) atomic_sub(1, v) #define atomic64_dec(v) atomic64_sub(1, v) -#define atomic_add_negative(i, v) (atomic_add_return(i, v) < 0) -#define atomic64_add_negative(i, v) (atomic64_add_return(i, v) < 0) - #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n))) static inline int atomic_xchg(atomic_t *v, int new) diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h index 616327ac9d39..73bda4abe180 100644 --- a/arch/x86/include/asm/atomic.h +++ b/arch/x86/include/asm/atomic.h @@ -80,6 +80,7 @@ static __always_inline void arch_atomic_sub(int i, atomic_t *v) * true if the result is zero, or false for all * other cases. */ +#define arch_atomic_sub_and_test arch_atomic_sub_and_test static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, "er", i, "%0", e); @@ -117,6 +118,7 @@ static __always_inline void arch_atomic_dec(atomic_t *v) * returns true if the result is 0, or false for all other * cases. */ +#define arch_atomic_dec_and_test arch_atomic_dec_and_test static __always_inline bool arch_atomic_dec_and_test(atomic_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", e); @@ -130,6 +132,7 @@ static __always_inline bool arch_atomic_dec_and_test(atomic_t *v) * and returns true if the result is zero, or false for all * other cases. */ +#define arch_atomic_inc_and_test arch_atomic_inc_and_test static __always_inline bool arch_atomic_inc_and_test(atomic_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", e); @@ -144,6 +147,7 @@ static __always_inline bool arch_atomic_inc_and_test(atomic_t *v) * if the result is negative, or false when * result is greater than or equal to zero. */ +#define arch_atomic_add_negative arch_atomic_add_negative static __always_inline bool arch_atomic_add_negative(int i, atomic_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, "er", i, "%0", s); diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h index 2a33cc17801b..a26810d005e0 100644 --- a/arch/x86/include/asm/atomic64_32.h +++ b/arch/x86/include/asm/atomic64_32.h @@ -197,20 +197,6 @@ static inline long long arch_atomic64_sub(long long i, atomic64_t *v) return i; } -/** - * arch_atomic64_sub_and_test - subtract value from variable and test result - * @i: integer value to subtract - * @v: pointer to type atomic64_t - * - * Atomically subtracts @i from @v and returns - * true if the result is zero, or false for all - * other cases. - */ -static inline int arch_atomic64_sub_and_test(long long i, atomic64_t *v) -{ - return arch_atomic64_sub_return(i, v) == 0; -} - /** * arch_atomic64_inc - increment atomic64 variable * @v: pointer to type atomic64_t @@ -235,46 +221,6 @@ static inline void arch_atomic64_dec(atomic64_t *v) "S" (v) : "memory", "eax", "ecx", "edx"); } -/** - * arch_atomic64_dec_and_test - decrement and test - * @v: pointer to type atomic64_t - * - * Atomically decrements @v by 1 and - * returns true if the result is 0, or false for all other - * cases. - */ -static inline int arch_atomic64_dec_and_test(atomic64_t *v) -{ - return arch_atomic64_dec_return(v) == 0; -} - -/** - * atomic64_inc_and_test - increment and test - * @v: pointer to type atomic64_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -static inline int arch_atomic64_inc_and_test(atomic64_t *v) -{ - return arch_atomic64_inc_return(v) == 0; -} - -/** - * arch_atomic64_add_negative - add and test if negative - * @i: integer value to add - * @v: pointer to type atomic64_t - * - * Atomically adds @i to @v and returns true - * if the result is negative, or false when - * result is greater than or equal to zero. - */ -static inline int arch_atomic64_add_negative(long long i, atomic64_t *v) -{ - return arch_atomic64_add_return(i, v) < 0; -} - /** * arch_atomic64_add_unless - add unless the number is a given value * @v: pointer of type atomic64_t diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h index 7e04b294e6eb..6a65228a3db6 100644 --- a/arch/x86/include/asm/atomic64_64.h +++ b/arch/x86/include/asm/atomic64_64.h @@ -71,6 +71,7 @@ static inline void arch_atomic64_sub(long i, atomic64_t *v) * true if the result is zero, or false for all * other cases. */ +#define arch_atomic64_sub_and_test arch_atomic64_sub_and_test static inline bool arch_atomic64_sub_and_test(long i, atomic64_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, "er", i, "%0", e); @@ -110,6 +111,7 @@ static __always_inline void arch_atomic64_dec(atomic64_t *v) * returns true if the result is 0, or false for all other * cases. */ +#define arch_atomic64_dec_and_test arch_atomic64_dec_and_test static inline bool arch_atomic64_dec_and_test(atomic64_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, "%0", e); @@ -123,6 +125,7 @@ static inline bool arch_atomic64_dec_and_test(atomic64_t *v) * and returns true if the result is zero, or false for all * other cases. */ +#define arch_atomic64_inc_and_test arch_atomic64_inc_and_test static inline bool arch_atomic64_inc_and_test(atomic64_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, "%0", e); @@ -137,6 +140,7 @@ static inline bool arch_atomic64_inc_and_test(atomic64_t *v) * if the result is negative, or false when * result is greater than or equal to zero. */ +#define arch_atomic64_add_negative arch_atomic64_add_negative static inline bool arch_atomic64_add_negative(long i, atomic64_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, "er", i, "%0", s); diff --git a/arch/xtensa/include/asm/atomic.h b/arch/xtensa/include/asm/atomic.h index f4c9f82c40c6..332ae4eca737 100644 --- a/arch/xtensa/include/asm/atomic.h +++ b/arch/xtensa/include/asm/atomic.h @@ -197,17 +197,6 @@ ATOMIC_OPS(xor) #undef ATOMIC_OP_RETURN #undef ATOMIC_OP -/** - * atomic_sub_and_test - subtract value from variable and test result - * @i: integer value to subtract - * @v: pointer of type atomic_t - * - * Atomically subtracts @i from @v and returns - * true if the result is zero, or false for all - * other cases. - */ -#define atomic_sub_and_test(i,v) (atomic_sub_return((i),(v)) == 0) - /** * atomic_inc - increment atomic variable * @v: pointer of type atomic_t @@ -240,37 +229,6 @@ ATOMIC_OPS(xor) */ #define atomic_dec_return(v) atomic_sub_return(1,(v)) -/** - * atomic_dec_and_test - decrement and test - * @v: pointer of type atomic_t - * - * Atomically decrements @v by 1 and - * returns true if the result is 0, or false for all other - * cases. - */ -#define atomic_dec_and_test(v) (atomic_sub_return(1,(v)) == 0) - -/** - * atomic_inc_and_test - increment and test - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -#define atomic_inc_and_test(v) (atomic_add_return(1,(v)) == 0) - -/** - * atomic_add_negative - add and test if negative - * @v: pointer of type atomic_t - * @i: integer value to add - * - * Atomically adds @i to @v and returns true - * if the result is negative, or false when - * result is greater than or equal to zero. - */ -#define atomic_add_negative(i,v) (atomic_add_return((i),(v)) < 0) - #define atomic_cmpxchg(v, o, n) ((int)cmpxchg(&((v)->counter), (o), (n))) #define atomic_xchg(v, new) (xchg(&((v)->counter), new)) diff --git a/include/asm-generic/atomic-instrumented.h b/include/asm-generic/atomic-instrumented.h index 2b487f28ef35..6b64c200de73 100644 --- a/include/asm-generic/atomic-instrumented.h +++ b/include/asm-generic/atomic-instrumented.h @@ -225,29 +225,41 @@ static __always_inline s64 atomic64_dec_if_positive(atomic64_t *v) return arch_atomic64_dec_if_positive(v); } +#ifdef arch_atomic_dec_and_test +#define atomic_dec_and_test atomic_dec_and_test static __always_inline bool atomic_dec_and_test(atomic_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic_dec_and_test(v); } +#endif +#ifdef arch_atomic64_dec_and_test +#define atomic64_dec_and_test atomic64_dec_and_test static __always_inline bool atomic64_dec_and_test(atomic64_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic64_dec_and_test(v); } +#endif +#ifdef arch_atomic_inc_and_test +#define atomic_inc_and_test atomic_inc_and_test static __always_inline bool atomic_inc_and_test(atomic_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic_inc_and_test(v); } +#endif +#ifdef arch_atomic64_inc_and_test +#define atomic64_inc_and_test atomic64_inc_and_test static __always_inline bool atomic64_inc_and_test(atomic64_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic64_inc_and_test(v); } +#endif static __always_inline int atomic_add_return(int i, atomic_t *v) { @@ -333,29 +345,41 @@ static __always_inline s64 atomic64_fetch_xor(s64 i, atomic64_t *v) return arch_atomic64_fetch_xor(i, v); } +#ifdef arch_atomic_sub_and_test +#define atomic_sub_and_test atomic_sub_and_test static __always_inline bool atomic_sub_and_test(int i, atomic_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic_sub_and_test(i, v); } +#endif +#ifdef arch_atomic64_sub_and_test +#define atomic64_sub_and_test atomic64_sub_and_test static __always_inline bool atomic64_sub_and_test(s64 i, atomic64_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic64_sub_and_test(i, v); } +#endif +#ifdef arch_atomic_add_negative +#define atomic_add_negative atomic_add_negative static __always_inline bool atomic_add_negative(int i, atomic_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic_add_negative(i, v); } +#endif +#ifdef arch_atomic64_add_negative +#define atomic64_add_negative atomic64_add_negative static __always_inline bool atomic64_add_negative(s64 i, atomic64_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic64_add_negative(i, v); } +#endif static __always_inline unsigned long cmpxchg_size(volatile void *ptr, unsigned long old, unsigned long new, int size) diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h index 757e45821220..40cab858aaaa 100644 --- a/include/asm-generic/atomic.h +++ b/include/asm-generic/atomic.h @@ -186,11 +186,6 @@ ATOMIC_OP(xor, ^) #include -static inline int atomic_add_negative(int i, atomic_t *v) -{ - return atomic_add_return(i, v) < 0; -} - static inline void atomic_add(int i, atomic_t *v) { atomic_add_return(i, v); @@ -214,10 +209,6 @@ static inline void atomic_dec(atomic_t *v) #define atomic_dec_return(v) atomic_sub_return(1, (v)) #define atomic_inc_return(v) atomic_add_return(1, (v)) -#define atomic_sub_and_test(i, v) (atomic_sub_return((i), (v)) == 0) -#define atomic_dec_and_test(v) (atomic_dec_return(v) == 0) -#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0) - #define atomic_xchg(ptr, v) (xchg(&(ptr)->counter, (v))) #define atomic_cmpxchg(v, old, new) (cmpxchg(&((v)->counter), (old), (new))) diff --git a/include/asm-generic/atomic64.h b/include/asm-generic/atomic64.h index 49460107b29a..d3827ab97aa4 100644 --- a/include/asm-generic/atomic64.h +++ b/include/asm-generic/atomic64.h @@ -56,13 +56,9 @@ extern long long atomic64_xchg(atomic64_t *v, long long new); extern long long atomic64_fetch_add_unless(atomic64_t *v, long long a, long long u); #define atomic64_fetch_add_unless atomic64_fetch_add_unless -#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0) #define atomic64_inc(v) atomic64_add(1LL, (v)) #define atomic64_inc_return(v) atomic64_add_return(1LL, (v)) -#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0) -#define atomic64_sub_and_test(a, v) (atomic64_sub_return((a), (v)) == 0) #define atomic64_dec(v) atomic64_sub(1LL, (v)) #define atomic64_dec_return(v) atomic64_sub_return(1LL, (v)) -#define atomic64_dec_and_test(v) (atomic64_dec_return((v)) == 0) #endif /* _ASM_GENERIC_ATOMIC64_H */ diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 530562ac7909..3ee8da9023cd 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -569,6 +569,68 @@ static inline bool atomic_add_unless(atomic_t *v, int a, int u) #define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0) #endif +/** + * atomic_inc_and_test - increment and test + * @v: pointer of type atomic_t + * + * Atomically increments @v by 1 + * and returns true if the result is zero, or false for all + * other cases. + */ +#ifndef atomic_inc_and_test +static inline bool atomic_inc_and_test(atomic_t *v) +{ + return atomic_inc_return(v) == 0; +} +#endif + +/** + * atomic_dec_and_test - decrement and test + * @v: pointer of type atomic_t + * + * Atomically decrements @v by 1 and + * returns true if the result is 0, or false for all other + * cases. + */ +#ifndef atomic_dec_and_test +static inline bool atomic_dec_and_test(atomic_t *v) +{ + return atomic_dec_return(v) == 0; +} +#endif + +/** + * atomic_sub_and_test - subtract value from variable and test result + * @i: integer value to subtract + * @v: pointer of type atomic_t + * + * Atomically subtracts @i from @v and returns + * true if the result is zero, or false for all + * other cases. + */ +#ifndef atomic_sub_and_test +static inline bool atomic_sub_and_test(int i, atomic_t *v) +{ + return atomic_sub_return(i, v) == 0; +} +#endif + +/** + * atomic_add_negative - add and test if negative + * @i: integer value to add + * @v: pointer of type atomic_t + * + * Atomically adds @i to @v and returns true + * if the result is negative, or false when + * result is greater than or equal to zero. + */ +#ifndef atomic_add_negative +static inline bool atomic_add_negative(int i, atomic_t *v) +{ + return atomic_add_return(i, v) < 0; +} +#endif + #ifndef atomic_andnot static inline void atomic_andnot(int i, atomic_t *v) { @@ -1091,6 +1153,68 @@ static inline bool atomic64_add_unless(atomic64_t *v, long long a, long long u) #define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) #endif +/** + * atomic64_inc_and_test - increment and test + * @v: pointer of type atomic64_t + * + * Atomically increments @v by 1 + * and returns true if the result is zero, or false for all + * other cases. + */ +#ifndef atomic64_inc_and_test +static inline bool atomic64_inc_and_test(atomic64_t *v) +{ + return atomic64_inc_return(v) == 0; +} +#endif + +/** + * atomic64_dec_and_test - decrement and test + * @v: pointer of type atomic64_t + * + * Atomically decrements @v by 1 and + * returns true if the result is 0, or false for all other + * cases. + */ +#ifndef atomic64_dec_and_test +static inline bool atomic64_dec_and_test(atomic64_t *v) +{ + return atomic64_dec_return(v) == 0; +} +#endif + +/** + * atomic64_sub_and_test - subtract value from variable and test result + * @i: integer value to subtract + * @v: pointer of type atomic64_t + * + * Atomically subtracts @i from @v and returns + * true if the result is zero, or false for all + * other cases. + */ +#ifndef atomic64_sub_and_test +static inline bool atomic64_sub_and_test(long long i, atomic64_t *v) +{ + return atomic64_sub_return(i, v) == 0; +} +#endif + +/** + * atomic64_add_negative - add and test if negative + * @i: integer value to add + * @v: pointer of type atomic64_t + * + * Atomically adds @i to @v and returns true + * if the result is negative, or false when + * result is greater than or equal to zero. + */ +#ifndef atomic64_add_negative +static inline bool atomic64_add_negative(long long i, atomic64_t *v) +{ + return atomic64_add_return(i, v) < 0; +} +#endif + #ifndef atomic64_andnot static inline void atomic64_andnot(long long i, atomic64_t *v) { -- cgit v1.2.3 From 9837559d8eb01ce834e56fc9a567c1d94ebd3698 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Thu, 21 Jun 2018 13:13:19 +0100 Subject: atomics/treewide: Make unconditional inc/dec ops optional Many of the inc/dec ops are mandatory, but for most architectures inc/dec are simply trivial wrappers around their corresponding add/sub ops. Let's make all the inc/dec ops optional, so that we can get rid of these boilerplate wrappers. The instrumented atomics are updated accordingly. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Reviewed-by: Will Deacon Acked-by: Peter Zijlstra (Intel) Acked-by: Palmer Dabbelt Cc: Boqun Feng Cc: Linus Torvalds Cc: Thomas Gleixner Link: https://lore.kernel.org/lkml/20180621121321.4761-17-mark.rutland@arm.com Signed-off-by: Ingo Molnar --- arch/alpha/include/asm/atomic.h | 12 ----- arch/arc/include/asm/atomic.h | 11 ----- arch/arm/include/asm/atomic.h | 11 ----- arch/arm64/include/asm/atomic.h | 24 ---------- arch/h8300/include/asm/atomic.h | 7 --- arch/hexagon/include/asm/atomic.h | 6 --- arch/ia64/include/asm/atomic.h | 9 ---- arch/m68k/include/asm/atomic.h | 5 +- arch/mips/include/asm/atomic.h | 38 ---------------- arch/parisc/include/asm/atomic.h | 12 ----- arch/powerpc/include/asm/atomic.h | 4 ++ arch/riscv/include/asm/atomic.h | 76 ------------------------------- arch/s390/include/asm/atomic.h | 8 ---- arch/sh/include/asm/atomic.h | 6 --- arch/sparc/include/asm/atomic_32.h | 5 -- arch/sparc/include/asm/atomic_64.h | 12 ----- arch/x86/include/asm/atomic.h | 5 +- arch/x86/include/asm/atomic64_32.h | 4 ++ arch/x86/include/asm/atomic64_64.h | 5 +- arch/xtensa/include/asm/atomic.h | 32 ------------- include/asm-generic/atomic-instrumented.h | 24 ++++++++++ include/asm-generic/atomic.h | 13 ------ include/asm-generic/atomic64.h | 5 -- include/linux/atomic.h | 48 +++++++++++++++++++ 24 files changed, 86 insertions(+), 296 deletions(-) (limited to 'include') diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h index 25f8693c5a42..f6410cb68058 100644 --- a/arch/alpha/include/asm/atomic.h +++ b/arch/alpha/include/asm/atomic.h @@ -297,16 +297,4 @@ static inline long atomic64_dec_if_positive(atomic64_t *v) return old - 1; } -#define atomic_dec_return(v) atomic_sub_return(1,(v)) -#define atomic64_dec_return(v) atomic64_sub_return(1,(v)) - -#define atomic_inc_return(v) atomic_add_return(1,(v)) -#define atomic64_inc_return(v) atomic64_add_return(1,(v)) - -#define atomic_inc(v) atomic_add(1,(v)) -#define atomic64_inc(v) atomic64_add(1,(v)) - -#define atomic_dec(v) atomic_sub(1,(v)) -#define atomic64_dec(v) atomic64_sub(1,(v)) - #endif /* _ALPHA_ATOMIC_H */ diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h index 4222e726f84c..27b95a928c1e 100644 --- a/arch/arc/include/asm/atomic.h +++ b/arch/arc/include/asm/atomic.h @@ -308,12 +308,6 @@ ATOMIC_OPS(xor, ^=, CTOP_INST_AXOR_DI_R2_R2_R3) #undef ATOMIC_OP_RETURN #undef ATOMIC_OP -#define atomic_inc(v) atomic_add(1, v) -#define atomic_dec(v) atomic_sub(1, v) - -#define atomic_inc_return(v) atomic_add_return(1, (v)) -#define atomic_dec_return(v) atomic_sub_return(1, (v)) - #ifdef CONFIG_GENERIC_ATOMIC64 #include @@ -560,11 +554,6 @@ static inline long long atomic64_fetch_add_unless(atomic64_t *v, long long a, } #define atomic64_fetch_add_unless atomic64_fetch_add_unless -#define atomic64_inc(v) atomic64_add(1LL, (v)) -#define atomic64_inc_return(v) atomic64_add_return(1LL, (v)) -#define atomic64_dec(v) atomic64_sub(1LL, (v)) -#define atomic64_dec_return(v) atomic64_sub_return(1LL, (v)) - #endif /* !CONFIG_GENERIC_ATOMIC64 */ #endif /* !__ASSEMBLY__ */ diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h index 35fb7f504daa..5a58d061d3d2 100644 --- a/arch/arm/include/asm/atomic.h +++ b/arch/arm/include/asm/atomic.h @@ -245,12 +245,6 @@ ATOMIC_OPS(xor, ^=, eor) #define atomic_xchg(v, new) (xchg(&((v)->counter), new)) -#define atomic_inc(v) atomic_add(1, v) -#define atomic_dec(v) atomic_sub(1, v) - -#define atomic_inc_return_relaxed(v) (atomic_add_return_relaxed(1, v)) -#define atomic_dec_return_relaxed(v) (atomic_sub_return_relaxed(1, v)) - #ifndef CONFIG_GENERIC_ATOMIC64 typedef struct { long long counter; @@ -512,11 +506,6 @@ static inline long long atomic64_fetch_add_unless(atomic64_t *v, long long a, } #define atomic64_fetch_add_unless atomic64_fetch_add_unless -#define atomic64_inc(v) atomic64_add(1LL, (v)) -#define atomic64_inc_return_relaxed(v) atomic64_add_return_relaxed(1LL, (v)) -#define atomic64_dec(v) atomic64_sub(1LL, (v)) -#define atomic64_dec_return_relaxed(v) atomic64_sub_return_relaxed(1LL, (v)) - #endif /* !CONFIG_GENERIC_ATOMIC64 */ #endif #endif diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h index edbe53fa3106..078f785cd97f 100644 --- a/arch/arm64/include/asm/atomic.h +++ b/arch/arm64/include/asm/atomic.h @@ -50,21 +50,11 @@ #define atomic_add_return_release atomic_add_return_release #define atomic_add_return atomic_add_return -#define atomic_inc_return_relaxed(v) atomic_add_return_relaxed(1, (v)) -#define atomic_inc_return_acquire(v) atomic_add_return_acquire(1, (v)) -#define atomic_inc_return_release(v) atomic_add_return_release(1, (v)) -#define atomic_inc_return(v) atomic_add_return(1, (v)) - #define atomic_sub_return_relaxed atomic_sub_return_relaxed #define atomic_sub_return_acquire atomic_sub_return_acquire #define atomic_sub_return_release atomic_sub_return_release #define atomic_sub_return atomic_sub_return -#define atomic_dec_return_relaxed(v) atomic_sub_return_relaxed(1, (v)) -#define atomic_dec_return_acquire(v) atomic_sub_return_acquire(1, (v)) -#define atomic_dec_return_release(v) atomic_sub_return_release(1, (v)) -#define atomic_dec_return(v) atomic_sub_return(1, (v)) - #define atomic_fetch_add_relaxed atomic_fetch_add_relaxed #define atomic_fetch_add_acquire atomic_fetch_add_acquire #define atomic_fetch_add_release atomic_fetch_add_release @@ -108,8 +98,6 @@ cmpxchg_release(&((v)->counter), (old), (new)) #define atomic_cmpxchg(v, old, new) cmpxchg(&((v)->counter), (old), (new)) -#define atomic_inc(v) atomic_add(1, (v)) -#define atomic_dec(v) atomic_sub(1, (v)) #define atomic_andnot atomic_andnot /* @@ -124,21 +112,11 @@ #define atomic64_add_return_release atomic64_add_return_release #define atomic64_add_return atomic64_add_return -#define atomic64_inc_return_relaxed(v) atomic64_add_return_relaxed(1, (v)) -#define atomic64_inc_return_acquire(v) atomic64_add_return_acquire(1, (v)) -#define atomic64_inc_return_release(v) atomic64_add_return_release(1, (v)) -#define atomic64_inc_return(v) atomic64_add_return(1, (v)) - #define atomic64_sub_return_relaxed atomic64_sub_return_relaxed #define atomic64_sub_return_acquire atomic64_sub_return_acquire #define atomic64_sub_return_release atomic64_sub_return_release #define atomic64_sub_return atomic64_sub_return -#define atomic64_dec_return_relaxed(v) atomic64_sub_return_relaxed(1, (v)) -#define atomic64_dec_return_acquire(v) atomic64_sub_return_acquire(1, (v)) -#define atomic64_dec_return_release(v) atomic64_sub_return_release(1, (v)) -#define atomic64_dec_return(v) atomic64_sub_return(1, (v)) - #define atomic64_fetch_add_relaxed atomic64_fetch_add_relaxed #define atomic64_fetch_add_acquire atomic64_fetch_add_acquire #define atomic64_fetch_add_release atomic64_fetch_add_release @@ -179,8 +157,6 @@ #define atomic64_cmpxchg_release atomic_cmpxchg_release #define atomic64_cmpxchg atomic_cmpxchg -#define atomic64_inc(v) atomic64_add(1, (v)) -#define atomic64_dec(v) atomic64_sub(1, (v)) #define atomic64_andnot atomic64_andnot #endif diff --git a/arch/h8300/include/asm/atomic.h b/arch/h8300/include/asm/atomic.h index 8977b5157c8f..c6b6a06231b2 100644 --- a/arch/h8300/include/asm/atomic.h +++ b/arch/h8300/include/asm/atomic.h @@ -69,13 +69,6 @@ ATOMIC_OPS(sub, -=) #undef ATOMIC_OP_RETURN #undef ATOMIC_OP -#define atomic_inc_return(v) atomic_add_return(1, v) -#define atomic_dec_return(v) atomic_sub_return(1, v) - -#define atomic_inc(v) (void)atomic_inc_return(v) - -#define atomic_dec(v) (void)atomic_dec_return(v) - static inline int atomic_cmpxchg(atomic_t *v, int old, int new) { int ret; diff --git a/arch/hexagon/include/asm/atomic.h b/arch/hexagon/include/asm/atomic.h index 31638f511674..311b9894ccc8 100644 --- a/arch/hexagon/include/asm/atomic.h +++ b/arch/hexagon/include/asm/atomic.h @@ -198,10 +198,4 @@ static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) } #define atomic_fetch_add_unless atomic_fetch_add_unless -#define atomic_inc(v) atomic_add(1, (v)) -#define atomic_dec(v) atomic_sub(1, (v)) - -#define atomic_inc_return(v) (atomic_add_return(1, v)) -#define atomic_dec_return(v) (atomic_sub_return(1, v)) - #endif diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h index e4143c462e65..46a15a974bed 100644 --- a/arch/ia64/include/asm/atomic.h +++ b/arch/ia64/include/asm/atomic.h @@ -231,19 +231,10 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v) return dec; } -#define atomic_dec_return(v) atomic_sub_return(1, (v)) -#define atomic_inc_return(v) atomic_add_return(1, (v)) -#define atomic64_dec_return(v) atomic64_sub_return(1, (v)) -#define atomic64_inc_return(v) atomic64_add_return(1, (v)) - #define atomic_add(i,v) (void)atomic_add_return((i), (v)) #define atomic_sub(i,v) (void)atomic_sub_return((i), (v)) -#define atomic_inc(v) atomic_add(1, (v)) -#define atomic_dec(v) atomic_sub(1, (v)) #define atomic64_add(i,v) (void)atomic64_add_return((i), (v)) #define atomic64_sub(i,v) (void)atomic64_sub_return((i), (v)) -#define atomic64_inc(v) atomic64_add(1, (v)) -#define atomic64_dec(v) atomic64_sub(1, (v)) #endif /* _ASM_IA64_ATOMIC_H */ diff --git a/arch/m68k/include/asm/atomic.h b/arch/m68k/include/asm/atomic.h index 9df09c876fa2..47228b0d4163 100644 --- a/arch/m68k/include/asm/atomic.h +++ b/arch/m68k/include/asm/atomic.h @@ -126,11 +126,13 @@ static inline void atomic_inc(atomic_t *v) { __asm__ __volatile__("addql #1,%0" : "+m" (*v)); } +#define atomic_inc atomic_inc static inline void atomic_dec(atomic_t *v) { __asm__ __volatile__("subql #1,%0" : "+m" (*v)); } +#define atomic_dec atomic_dec static inline int atomic_dec_and_test(atomic_t *v) { @@ -192,9 +194,6 @@ static inline int atomic_xchg(atomic_t *v, int new) #endif /* !CONFIG_RMW_INSNS */ -#define atomic_dec_return(v) atomic_sub_return(1, (v)) -#define atomic_inc_return(v) atomic_add_return(1, (v)) - static inline int atomic_sub_and_test(int i, atomic_t *v) { char c; diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h index fd3008ae164c..79be687de4ab 100644 --- a/arch/mips/include/asm/atomic.h +++ b/arch/mips/include/asm/atomic.h @@ -274,31 +274,12 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v) #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n))) #define atomic_xchg(v, new) (xchg(&((v)->counter), (new))) -#define atomic_dec_return(v) atomic_sub_return(1, (v)) -#define atomic_inc_return(v) atomic_add_return(1, (v)) - /* * atomic_dec_if_positive - decrement by 1 if old value positive * @v: pointer of type atomic_t */ #define atomic_dec_if_positive(v) atomic_sub_if_positive(1, v) -/* - * atomic_inc - increment atomic variable - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1. - */ -#define atomic_inc(v) atomic_add(1, (v)) - -/* - * atomic_dec - decrement and test - * @v: pointer of type atomic_t - * - * Atomically decrements @v by 1. - */ -#define atomic_dec(v) atomic_sub(1, (v)) - #ifdef CONFIG_64BIT #define ATOMIC64_INIT(i) { (i) } @@ -554,31 +535,12 @@ static __inline__ long atomic64_sub_if_positive(long i, atomic64_t * v) ((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n))) #define atomic64_xchg(v, new) (xchg(&((v)->counter), (new))) -#define atomic64_dec_return(v) atomic64_sub_return(1, (v)) -#define atomic64_inc_return(v) atomic64_add_return(1, (v)) - /* * atomic64_dec_if_positive - decrement by 1 if old value positive * @v: pointer of type atomic64_t */ #define atomic64_dec_if_positive(v) atomic64_sub_if_positive(1, v) -/* - * atomic64_inc - increment atomic variable - * @v: pointer of type atomic64_t - * - * Atomically increments @v by 1. - */ -#define atomic64_inc(v) atomic64_add(1, (v)) - -/* - * atomic64_dec - decrement and test - * @v: pointer of type atomic64_t - * - * Atomically decrements @v by 1. - */ -#define atomic64_dec(v) atomic64_sub(1, (v)) - #endif /* CONFIG_64BIT */ #endif /* _ASM_ATOMIC_H */ diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h index f85844ff6336..10bc490327c1 100644 --- a/arch/parisc/include/asm/atomic.h +++ b/arch/parisc/include/asm/atomic.h @@ -136,12 +136,6 @@ ATOMIC_OPS(xor, ^=) #undef ATOMIC_OP_RETURN #undef ATOMIC_OP -#define atomic_inc(v) (atomic_add( 1,(v))) -#define atomic_dec(v) (atomic_add( -1,(v))) - -#define atomic_inc_return(v) (atomic_add_return( 1,(v))) -#define atomic_dec_return(v) (atomic_add_return( -1,(v))) - #define ATOMIC_INIT(i) { (i) } #ifdef CONFIG_64BIT @@ -224,12 +218,6 @@ atomic64_read(const atomic64_t *v) return READ_ONCE((v)->counter); } -#define atomic64_inc(v) (atomic64_add( 1,(v))) -#define atomic64_dec(v) (atomic64_add( -1,(v))) - -#define atomic64_inc_return(v) (atomic64_add_return( 1,(v))) -#define atomic64_dec_return(v) (atomic64_add_return( -1,(v))) - /* exported interface */ #define atomic64_cmpxchg(v, o, n) \ ((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n))) diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h index 5d76f05d2be3..ebaefdee4a57 100644 --- a/arch/powerpc/include/asm/atomic.h +++ b/arch/powerpc/include/asm/atomic.h @@ -143,6 +143,7 @@ static __inline__ void atomic_inc(atomic_t *v) : "r" (&v->counter) : "cc", "xer"); } +#define atomic_inc atomic_inc static __inline__ int atomic_inc_return_relaxed(atomic_t *v) { @@ -175,6 +176,7 @@ static __inline__ void atomic_dec(atomic_t *v) : "r" (&v->counter) : "cc", "xer"); } +#define atomic_dec atomic_dec static __inline__ int atomic_dec_return_relaxed(atomic_t *v) { @@ -411,6 +413,7 @@ static __inline__ void atomic64_inc(atomic64_t *v) : "r" (&v->counter) : "cc", "xer"); } +#define atomic64_inc atomic64_inc static __inline__ long atomic64_inc_return_relaxed(atomic64_t *v) { @@ -441,6 +444,7 @@ static __inline__ void atomic64_dec(atomic64_t *v) : "r" (&v->counter) : "cc", "xer"); } +#define atomic64_dec atomic64_dec static __inline__ long atomic64_dec_return_relaxed(atomic64_t *v) { diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h index 68eef0a805ca..512b89485790 100644 --- a/arch/riscv/include/asm/atomic.h +++ b/arch/riscv/include/asm/atomic.h @@ -209,82 +209,6 @@ ATOMIC_OPS(xor, xor, i) #undef ATOMIC_FETCH_OP #undef ATOMIC_OP_RETURN -#define ATOMIC_OP(op, func_op, I, c_type, prefix) \ -static __always_inline \ -void atomic##prefix##_##op(atomic##prefix##_t *v) \ -{ \ - atomic##prefix##_##func_op(I, v); \ -} - -#define ATOMIC_FETCH_OP(op, func_op, I, c_type, prefix) \ -static __always_inline \ -c_type atomic##prefix##_fetch_##op##_relaxed(atomic##prefix##_t *v) \ -{ \ - return atomic##prefix##_fetch_##func_op##_relaxed(I, v); \ -} \ -static __always_inline \ -c_type atomic##prefix##_fetch_##op(atomic##prefix##_t *v) \ -{ \ - return atomic##prefix##_fetch_##func_op(I, v); \ -} - -#define ATOMIC_OP_RETURN(op, asm_op, c_op, I, c_type, prefix) \ -static __always_inline \ -c_type atomic##prefix##_##op##_return_relaxed(atomic##prefix##_t *v) \ -{ \ - return atomic##prefix##_fetch_##op##_relaxed(v) c_op I; \ -} \ -static __always_inline \ -c_type atomic##prefix##_##op##_return(atomic##prefix##_t *v) \ -{ \ - return atomic##prefix##_fetch_##op(v) c_op I; \ -} - -#ifdef CONFIG_GENERIC_ATOMIC64 -#define ATOMIC_OPS(op, asm_op, c_op, I) \ - ATOMIC_OP( op, asm_op, I, int, ) \ - ATOMIC_FETCH_OP( op, asm_op, I, int, ) \ - ATOMIC_OP_RETURN(op, asm_op, c_op, I, int, ) -#else -#define ATOMIC_OPS(op, asm_op, c_op, I) \ - ATOMIC_OP( op, asm_op, I, int, ) \ - ATOMIC_FETCH_OP( op, asm_op, I, int, ) \ - ATOMIC_OP_RETURN(op, asm_op, c_op, I, int, ) \ - ATOMIC_OP( op, asm_op, I, long, 64) \ - ATOMIC_FETCH_OP( op, asm_op, I, long, 64) \ - ATOMIC_OP_RETURN(op, asm_op, c_op, I, long, 64) -#endif - -ATOMIC_OPS(inc, add, +, 1) -ATOMIC_OPS(dec, add, +, -1) - -#define atomic_inc_return_relaxed atomic_inc_return_relaxed -#define atomic_dec_return_relaxed atomic_dec_return_relaxed -#define atomic_inc_return atomic_inc_return -#define atomic_dec_return atomic_dec_return - -#define atomic_fetch_inc_relaxed atomic_fetch_inc_relaxed -#define atomic_fetch_dec_relaxed atomic_fetch_dec_relaxed -#define atomic_fetch_inc atomic_fetch_inc -#define atomic_fetch_dec atomic_fetch_dec - -#ifndef CONFIG_GENERIC_ATOMIC64 -#define atomic64_inc_return_relaxed atomic64_inc_return_relaxed -#define atomic64_dec_return_relaxed atomic64_dec_return_relaxed -#define atomic64_inc_return atomic64_inc_return -#define atomic64_dec_return atomic64_dec_return - -#define atomic64_fetch_inc_relaxed atomic64_fetch_inc_relaxed -#define atomic64_fetch_dec_relaxed atomic64_fetch_dec_relaxed -#define atomic64_fetch_inc atomic64_fetch_inc -#define atomic64_fetch_dec atomic64_fetch_dec -#endif - -#undef ATOMIC_OPS -#undef ATOMIC_OP -#undef ATOMIC_FETCH_OP -#undef ATOMIC_OP_RETURN - /* This is required to provide a full barrier on success. */ static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h index 7f5fbd595f01..376e64af951f 100644 --- a/arch/s390/include/asm/atomic.h +++ b/arch/s390/include/asm/atomic.h @@ -55,13 +55,9 @@ static inline void atomic_add(int i, atomic_t *v) __atomic_add(i, &v->counter); } -#define atomic_inc(_v) atomic_add(1, _v) -#define atomic_inc_return(_v) atomic_add_return(1, _v) #define atomic_sub(_i, _v) atomic_add(-(int)(_i), _v) #define atomic_sub_return(_i, _v) atomic_add_return(-(int)(_i), _v) #define atomic_fetch_sub(_i, _v) atomic_fetch_add(-(int)(_i), _v) -#define atomic_dec(_v) atomic_sub(1, _v) -#define atomic_dec_return(_v) atomic_sub_return(1, _v) #define ATOMIC_OPS(op) \ static inline void atomic_##op(int i, atomic_t *v) \ @@ -166,12 +162,8 @@ static inline long atomic64_dec_if_positive(atomic64_t *v) return dec; } -#define atomic64_inc(_v) atomic64_add(1, _v) -#define atomic64_inc_return(_v) atomic64_add_return(1, _v) #define atomic64_sub_return(_i, _v) atomic64_add_return(-(long)(_i), _v) #define atomic64_fetch_sub(_i, _v) atomic64_fetch_add(-(long)(_i), _v) #define atomic64_sub(_i, _v) atomic64_add(-(long)(_i), _v) -#define atomic64_dec(_v) atomic64_sub(1, _v) -#define atomic64_dec_return(_v) atomic64_sub_return(1, _v) #endif /* __ARCH_S390_ATOMIC__ */ diff --git a/arch/sh/include/asm/atomic.h b/arch/sh/include/asm/atomic.h index d438494fa112..f37b95a80232 100644 --- a/arch/sh/include/asm/atomic.h +++ b/arch/sh/include/asm/atomic.h @@ -32,12 +32,6 @@ #include #endif -#define atomic_dec_return(v) atomic_sub_return(1, (v)) -#define atomic_inc_return(v) atomic_add_return(1, (v)) - -#define atomic_inc(v) atomic_add(1, (v)) -#define atomic_dec(v) atomic_sub(1, (v)) - #define atomic_xchg(v, new) (xchg(&((v)->counter), new)) #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n))) diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h index 3a26573790c6..94c930f0bc62 100644 --- a/arch/sparc/include/asm/atomic_32.h +++ b/arch/sparc/include/asm/atomic_32.h @@ -38,8 +38,6 @@ void atomic_set(atomic_t *, int); #define atomic_add(i, v) ((void)atomic_add_return( (int)(i), (v))) #define atomic_sub(i, v) ((void)atomic_add_return(-(int)(i), (v))) -#define atomic_inc(v) ((void)atomic_add_return( 1, (v))) -#define atomic_dec(v) ((void)atomic_add_return( -1, (v))) #define atomic_and(i, v) ((void)atomic_fetch_and((i), (v))) #define atomic_or(i, v) ((void)atomic_fetch_or((i), (v))) @@ -48,7 +46,4 @@ void atomic_set(atomic_t *, int); #define atomic_sub_return(i, v) (atomic_add_return(-(int)(i), (v))) #define atomic_fetch_sub(i, v) (atomic_fetch_add (-(int)(i), (v))) -#define atomic_inc_return(v) (atomic_add_return( 1, (v))) -#define atomic_dec_return(v) (atomic_add_return( -1, (v))) - #endif /* !(__ARCH_SPARC_ATOMIC__) */ diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h index 634508282aea..304865c7cdbb 100644 --- a/arch/sparc/include/asm/atomic_64.h +++ b/arch/sparc/include/asm/atomic_64.h @@ -50,18 +50,6 @@ ATOMIC_OPS(xor) #undef ATOMIC_OP_RETURN #undef ATOMIC_OP -#define atomic_dec_return(v) atomic_sub_return(1, v) -#define atomic64_dec_return(v) atomic64_sub_return(1, v) - -#define atomic_inc_return(v) atomic_add_return(1, v) -#define atomic64_inc_return(v) atomic64_add_return(1, v) - -#define atomic_inc(v) atomic_add(1, v) -#define atomic64_inc(v) atomic64_add(1, v) - -#define atomic_dec(v) atomic_sub(1, v) -#define atomic64_dec(v) atomic64_sub(1, v) - #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n))) static inline int atomic_xchg(atomic_t *v, int new) diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h index 73bda4abe180..823fd2f320cf 100644 --- a/arch/x86/include/asm/atomic.h +++ b/arch/x86/include/asm/atomic.h @@ -92,6 +92,7 @@ static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v) * * Atomically increments @v by 1. */ +#define arch_atomic_inc arch_atomic_inc static __always_inline void arch_atomic_inc(atomic_t *v) { asm volatile(LOCK_PREFIX "incl %0" @@ -104,6 +105,7 @@ static __always_inline void arch_atomic_inc(atomic_t *v) * * Atomically decrements @v by 1. */ +#define arch_atomic_dec arch_atomic_dec static __always_inline void arch_atomic_dec(atomic_t *v) { asm volatile(LOCK_PREFIX "decl %0" @@ -177,9 +179,6 @@ static __always_inline int arch_atomic_sub_return(int i, atomic_t *v) return arch_atomic_add_return(-i, v); } -#define arch_atomic_inc_return(v) (arch_atomic_add_return(1, v)) -#define arch_atomic_dec_return(v) (arch_atomic_sub_return(1, v)) - static __always_inline int arch_atomic_fetch_add(int i, atomic_t *v) { return xadd(&v->counter, i); diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h index a26810d005e0..472c7af0ed48 100644 --- a/arch/x86/include/asm/atomic64_32.h +++ b/arch/x86/include/asm/atomic64_32.h @@ -158,6 +158,7 @@ static inline long long arch_atomic64_inc_return(atomic64_t *v) "S" (v) : "memory", "ecx"); return a; } +#define arch_atomic64_inc_return arch_atomic64_inc_return static inline long long arch_atomic64_dec_return(atomic64_t *v) { @@ -166,6 +167,7 @@ static inline long long arch_atomic64_dec_return(atomic64_t *v) "S" (v) : "memory", "ecx"); return a; } +#define arch_atomic64_dec_return arch_atomic64_dec_return /** * arch_atomic64_add - add integer to atomic64 variable @@ -203,6 +205,7 @@ static inline long long arch_atomic64_sub(long long i, atomic64_t *v) * * Atomically increments @v by 1. */ +#define arch_atomic64_inc arch_atomic64_inc static inline void arch_atomic64_inc(atomic64_t *v) { __alternative_atomic64(inc, inc_return, /* no output */, @@ -215,6 +218,7 @@ static inline void arch_atomic64_inc(atomic64_t *v) * * Atomically decrements @v by 1. */ +#define arch_atomic64_dec arch_atomic64_dec static inline void arch_atomic64_dec(atomic64_t *v) { __alternative_atomic64(dec, dec_return, /* no output */, diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h index 6a65228a3db6..1b282272a801 100644 --- a/arch/x86/include/asm/atomic64_64.h +++ b/arch/x86/include/asm/atomic64_64.h @@ -83,6 +83,7 @@ static inline bool arch_atomic64_sub_and_test(long i, atomic64_t *v) * * Atomically increments @v by 1. */ +#define arch_atomic64_inc arch_atomic64_inc static __always_inline void arch_atomic64_inc(atomic64_t *v) { asm volatile(LOCK_PREFIX "incq %0" @@ -96,6 +97,7 @@ static __always_inline void arch_atomic64_inc(atomic64_t *v) * * Atomically decrements @v by 1. */ +#define arch_atomic64_dec arch_atomic64_dec static __always_inline void arch_atomic64_dec(atomic64_t *v) { asm volatile(LOCK_PREFIX "decq %0" @@ -173,9 +175,6 @@ static inline long arch_atomic64_fetch_sub(long i, atomic64_t *v) return xadd(&v->counter, -i); } -#define arch_atomic64_inc_return(v) (arch_atomic64_add_return(1, (v))) -#define arch_atomic64_dec_return(v) (arch_atomic64_sub_return(1, (v))) - static inline long arch_atomic64_cmpxchg(atomic64_t *v, long old, long new) { return arch_cmpxchg(&v->counter, old, new); diff --git a/arch/xtensa/include/asm/atomic.h b/arch/xtensa/include/asm/atomic.h index 332ae4eca737..7de0149e1cf7 100644 --- a/arch/xtensa/include/asm/atomic.h +++ b/arch/xtensa/include/asm/atomic.h @@ -197,38 +197,6 @@ ATOMIC_OPS(xor) #undef ATOMIC_OP_RETURN #undef ATOMIC_OP -/** - * atomic_inc - increment atomic variable - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1. - */ -#define atomic_inc(v) atomic_add(1,(v)) - -/** - * atomic_inc - increment atomic variable - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1. - */ -#define atomic_inc_return(v) atomic_add_return(1,(v)) - -/** - * atomic_dec - decrement atomic variable - * @v: pointer of type atomic_t - * - * Atomically decrements @v by 1. - */ -#define atomic_dec(v) atomic_sub(1,(v)) - -/** - * atomic_dec_return - decrement atomic variable - * @v: pointer of type atomic_t - * - * Atomically decrements @v by 1. - */ -#define atomic_dec_return(v) atomic_sub_return(1,(v)) - #define atomic_cmpxchg(v, o, n) ((int)cmpxchg(&((v)->counter), (o), (n))) #define atomic_xchg(v, new) (xchg(&((v)->counter), new)) diff --git a/include/asm-generic/atomic-instrumented.h b/include/asm-generic/atomic-instrumented.h index 6b64c200de73..12f9634750d7 100644 --- a/include/asm-generic/atomic-instrumented.h +++ b/include/asm-generic/atomic-instrumented.h @@ -102,29 +102,41 @@ static __always_inline s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u } #endif +#ifdef arch_atomic_inc +#define atomic_inc atomic_inc static __always_inline void atomic_inc(atomic_t *v) { kasan_check_write(v, sizeof(*v)); arch_atomic_inc(v); } +#endif +#ifdef arch_atomic64_inc +#define atomic64_inc atomic64_inc static __always_inline void atomic64_inc(atomic64_t *v) { kasan_check_write(v, sizeof(*v)); arch_atomic64_inc(v); } +#endif +#ifdef arch_atomic_dec +#define atomic_dec atomic_dec static __always_inline void atomic_dec(atomic_t *v) { kasan_check_write(v, sizeof(*v)); arch_atomic_dec(v); } +#endif +#ifdef atch_atomic64_dec +#define atomic64_dec static __always_inline void atomic64_dec(atomic64_t *v) { kasan_check_write(v, sizeof(*v)); arch_atomic64_dec(v); } +#endif static __always_inline void atomic_add(int i, atomic_t *v) { @@ -186,29 +198,41 @@ static __always_inline void atomic64_xor(s64 i, atomic64_t *v) arch_atomic64_xor(i, v); } +#ifdef arch_atomic_inc_return +#define atomic_inc_return atomic_inc_return static __always_inline int atomic_inc_return(atomic_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic_inc_return(v); } +#endif +#ifdef arch_atomic64_in_return +#define atomic64_inc_return atomic64_inc_return static __always_inline s64 atomic64_inc_return(atomic64_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic64_inc_return(v); } +#endif +#ifdef arch_atomic_dec_return +#define atomic_dec_return atomic_dec_return static __always_inline int atomic_dec_return(atomic_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic_dec_return(v); } +#endif +#ifdef arch_atomic64_dec_return +#define atomic64_dec_return atomic64_dec_return static __always_inline s64 atomic64_dec_return(atomic64_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic64_dec_return(v); } +#endif #ifdef arch_atomic64_inc_not_zero #define atomic64_inc_not_zero atomic64_inc_not_zero diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h index 40cab858aaaa..13324aa828eb 100644 --- a/include/asm-generic/atomic.h +++ b/include/asm-generic/atomic.h @@ -196,19 +196,6 @@ static inline void atomic_sub(int i, atomic_t *v) atomic_sub_return(i, v); } -static inline void atomic_inc(atomic_t *v) -{ - atomic_add_return(1, v); -} - -static inline void atomic_dec(atomic_t *v) -{ - atomic_sub_return(1, v); -} - -#define atomic_dec_return(v) atomic_sub_return(1, (v)) -#define atomic_inc_return(v) atomic_add_return(1, (v)) - #define atomic_xchg(ptr, v) (xchg(&(ptr)->counter, (v))) #define atomic_cmpxchg(v, old, new) (cmpxchg(&((v)->counter), (old), (new))) diff --git a/include/asm-generic/atomic64.h b/include/asm-generic/atomic64.h index d3827ab97aa4..242b79ae0b57 100644 --- a/include/asm-generic/atomic64.h +++ b/include/asm-generic/atomic64.h @@ -56,9 +56,4 @@ extern long long atomic64_xchg(atomic64_t *v, long long new); extern long long atomic64_fetch_add_unless(atomic64_t *v, long long a, long long u); #define atomic64_fetch_add_unless atomic64_fetch_add_unless -#define atomic64_inc(v) atomic64_add(1LL, (v)) -#define atomic64_inc_return(v) atomic64_add_return(1LL, (v)) -#define atomic64_dec(v) atomic64_sub(1LL, (v)) -#define atomic64_dec_return(v) atomic64_sub_return(1LL, (v)) - #endif /* _ASM_GENERIC_ATOMIC64_H */ diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 3ee8da9023cd..24f345df7ba6 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -97,11 +97,23 @@ #endif #endif /* atomic_add_return_relaxed */ +#ifndef atomic_inc +#define atomic_inc(v) atomic_add(1, (v)) +#endif + /* atomic_inc_return_relaxed */ #ifndef atomic_inc_return_relaxed + +#ifndef atomic_inc_return +#define atomic_inc_return(v) atomic_add_return(1, (v)) +#define atomic_inc_return_relaxed(v) atomic_add_return_relaxed(1, (v)) +#define atomic_inc_return_acquire(v) atomic_add_return_acquire(1, (v)) +#define atomic_inc_return_release(v) atomic_add_return_release(1, (v)) +#else /* atomic_inc_return */ #define atomic_inc_return_relaxed atomic_inc_return #define atomic_inc_return_acquire atomic_inc_return #define atomic_inc_return_release atomic_inc_return +#endif /* atomic_inc_return */ #else /* atomic_inc_return_relaxed */ @@ -145,11 +157,23 @@ #endif #endif /* atomic_sub_return_relaxed */ +#ifndef atomic_dec +#define atomic_dec(v) atomic_sub(1, (v)) +#endif + /* atomic_dec_return_relaxed */ #ifndef atomic_dec_return_relaxed + +#ifndef atomic_dec_return +#define atomic_dec_return(v) atomic_sub_return(1, (v)) +#define atomic_dec_return_relaxed(v) atomic_sub_return_relaxed(1, (v)) +#define atomic_dec_return_acquire(v) atomic_sub_return_acquire(1, (v)) +#define atomic_dec_return_release(v) atomic_sub_return_release(1, (v)) +#else /* atomic_dec_return */ #define atomic_dec_return_relaxed atomic_dec_return #define atomic_dec_return_acquire atomic_dec_return #define atomic_dec_return_release atomic_dec_return +#endif /* atomic_dec_return */ #else /* atomic_dec_return_relaxed */ @@ -748,11 +772,23 @@ static inline int atomic_dec_if_positive(atomic_t *v) #endif #endif /* atomic64_add_return_relaxed */ +#ifndef atomic64_inc +#define atomic64_inc(v) atomic64_add(1, (v)) +#endif + /* atomic64_inc_return_relaxed */ #ifndef atomic64_inc_return_relaxed + +#ifndef atomic64_inc_return +#define atomic64_inc_return(v) atomic64_add_return(1, (v)) +#define atomic64_inc_return_relaxed(v) atomic64_add_return_relaxed(1, (v)) +#define atomic64_inc_return_acquire(v) atomic64_add_return_acquire(1, (v)) +#define atomic64_inc_return_release(v) atomic64_add_return_release(1, (v)) +#else /* atomic64_inc_return */ #define atomic64_inc_return_relaxed atomic64_inc_return #define atomic64_inc_return_acquire atomic64_inc_return #define atomic64_inc_return_release atomic64_inc_return +#endif /* atomic64_inc_return */ #else /* atomic64_inc_return_relaxed */ @@ -797,11 +833,23 @@ static inline int atomic_dec_if_positive(atomic_t *v) #endif #endif /* atomic64_sub_return_relaxed */ +#ifndef atomic64_dec +#define atomic64_dec(v) atomic64_sub(1, (v)) +#endif + /* atomic64_dec_return_relaxed */ #ifndef atomic64_dec_return_relaxed + +#ifndef atomic64_dec_return +#define atomic64_dec_return(v) atomic64_sub_return(1, (v)) +#define atomic64_dec_return_relaxed(v) atomic64_sub_return_relaxed(1, (v)) +#define atomic64_dec_return_acquire(v) atomic64_sub_return_acquire(1, (v)) +#define atomic64_dec_return_release(v) atomic64_sub_return_release(1, (v)) +#else /* atomic64_dec_return */ #define atomic64_dec_return_relaxed atomic64_dec_return #define atomic64_dec_return_acquire atomic64_dec_return #define atomic64_dec_return_release atomic64_dec_return +#endif /* atomic64_dec_return */ #else /* atomic64_dec_return_relaxed */ -- cgit v1.2.3 From b3a2a05f9111de0b79312e577608a27b0318c0a1 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Thu, 21 Jun 2018 13:13:20 +0100 Subject: atomics/treewide: Make conditional inc/dec ops optional The conditional inc/dec ops differ for atomic_t and atomic64_t: - atomic_inc_unless_positive() is optional for atomic_t, and doesn't exist for atomic64_t. - atomic_dec_unless_negative() is optional for atomic_t, and doesn't exist for atomic64_t. - atomic_dec_if_positive is optional for atomic_t, and is mandatory for atomic64_t. Let's make these consistently optional for both. At the same time, let's clean up the existing fallbacks to use atomic_try_cmpxchg(). The instrumented atomics are updated accordingly. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Reviewed-by: Will Deacon Acked-by: Peter Zijlstra (Intel) Cc: Boqun Feng Cc: Linus Torvalds Cc: Thomas Gleixner Link: https://lore.kernel.org/lkml/20180621121321.4761-18-mark.rutland@arm.com Signed-off-by: Ingo Molnar --- arch/alpha/include/asm/atomic.h | 1 + arch/arc/include/asm/atomic.h | 1 + arch/arm/include/asm/atomic.h | 1 + arch/arm64/include/asm/atomic.h | 2 + arch/ia64/include/asm/atomic.h | 16 ----- arch/parisc/include/asm/atomic.h | 23 -------- arch/powerpc/include/asm/atomic.h | 1 + arch/s390/include/asm/atomic.h | 17 ------ arch/sparc/include/asm/atomic_64.h | 1 + arch/x86/include/asm/atomic64_32.h | 1 + arch/x86/include/asm/atomic64_64.h | 18 ------ include/asm-generic/atomic-instrumented.h | 3 + include/asm-generic/atomic64.h | 1 + include/linux/atomic.h | 97 +++++++++++++++++++++++-------- 14 files changed, 85 insertions(+), 98 deletions(-) (limited to 'include') diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h index f6410cb68058..4a6a8f58c9c9 100644 --- a/arch/alpha/include/asm/atomic.h +++ b/arch/alpha/include/asm/atomic.h @@ -296,5 +296,6 @@ static inline long atomic64_dec_if_positive(atomic64_t *v) smp_mb(); return old - 1; } +#define atomic64_dec_if_positive atomic64_dec_if_positive #endif /* _ALPHA_ATOMIC_H */ diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h index 27b95a928c1e..8f64f3b79b8a 100644 --- a/arch/arc/include/asm/atomic.h +++ b/arch/arc/include/asm/atomic.h @@ -517,6 +517,7 @@ static inline long long atomic64_dec_if_positive(atomic64_t *v) return val; } +#define atomic64_dec_if_positive atomic64_dec_if_positive /** * atomic64_fetch_add_unless - add unless the number is a given value diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h index 5a58d061d3d2..884c241424fe 100644 --- a/arch/arm/include/asm/atomic.h +++ b/arch/arm/include/asm/atomic.h @@ -474,6 +474,7 @@ static inline long long atomic64_dec_if_positive(atomic64_t *v) return result; } +#define atomic64_dec_if_positive atomic64_dec_if_positive static inline long long atomic64_fetch_add_unless(atomic64_t *v, long long a, long long u) diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h index 078f785cd97f..9bca54dda75c 100644 --- a/arch/arm64/include/asm/atomic.h +++ b/arch/arm64/include/asm/atomic.h @@ -159,5 +159,7 @@ #define atomic64_andnot atomic64_andnot +#define atomic64_dec_if_positive atomic64_dec_if_positive + #endif #endif diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h index 46a15a974bed..206530d0751b 100644 --- a/arch/ia64/include/asm/atomic.h +++ b/arch/ia64/include/asm/atomic.h @@ -215,22 +215,6 @@ ATOMIC64_FETCH_OP(xor, ^) (cmpxchg(&((v)->counter), old, new)) #define atomic64_xchg(v, new) (xchg(&((v)->counter), new)) -static __inline__ long atomic64_dec_if_positive(atomic64_t *v) -{ - long c, old, dec; - c = atomic64_read(v); - for (;;) { - dec = c - 1; - if (unlikely(dec < 0)) - break; - old = atomic64_cmpxchg((v), c, dec); - if (likely(old == c)) - break; - c = old; - } - return dec; -} - #define atomic_add(i,v) (void)atomic_add_return((i), (v)) #define atomic_sub(i,v) (void)atomic_sub_return((i), (v)) diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h index 10bc490327c1..118953d41763 100644 --- a/arch/parisc/include/asm/atomic.h +++ b/arch/parisc/include/asm/atomic.h @@ -223,29 +223,6 @@ atomic64_read(const atomic64_t *v) ((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n))) #define atomic64_xchg(v, new) (xchg(&((v)->counter), new)) -/* - * atomic64_dec_if_positive - decrement by 1 if old value positive - * @v: pointer of type atomic_t - * - * The function returns the old value of *v minus 1, even if - * the atomic variable, v, was not decremented. - */ -static inline long atomic64_dec_if_positive(atomic64_t *v) -{ - long c, old, dec; - c = atomic64_read(v); - for (;;) { - dec = c - 1; - if (unlikely(dec < 0)) - break; - old = atomic64_cmpxchg((v), c, dec); - if (likely(old == c)) - break; - c = old; - } - return dec; -} - #endif /* !CONFIG_64BIT */ diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h index ebaefdee4a57..a0156cb43d1f 100644 --- a/arch/powerpc/include/asm/atomic.h +++ b/arch/powerpc/include/asm/atomic.h @@ -488,6 +488,7 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v) return t; } +#define atomic64_dec_if_positive atomic64_dec_if_positive #define atomic64_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n))) #define atomic64_cmpxchg_relaxed(v, o, n) \ diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h index 376e64af951f..fd20ab5d4cf7 100644 --- a/arch/s390/include/asm/atomic.h +++ b/arch/s390/include/asm/atomic.h @@ -145,23 +145,6 @@ ATOMIC64_OPS(xor) #undef ATOMIC64_OPS -static inline long atomic64_dec_if_positive(atomic64_t *v) -{ - long c, old, dec; - - c = atomic64_read(v); - for (;;) { - dec = c - 1; - if (unlikely(dec < 0)) - break; - old = atomic64_cmpxchg((v), c, dec); - if (likely(old == c)) - break; - c = old; - } - return dec; -} - #define atomic64_sub_return(_i, _v) atomic64_add_return(-(long)(_i), _v) #define atomic64_fetch_sub(_i, _v) atomic64_fetch_add(-(long)(_i), _v) #define atomic64_sub(_i, _v) atomic64_add(-(long)(_i), _v) diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h index 304865c7cdbb..6963482c81d8 100644 --- a/arch/sparc/include/asm/atomic_64.h +++ b/arch/sparc/include/asm/atomic_64.h @@ -62,5 +62,6 @@ static inline int atomic_xchg(atomic_t *v, int new) #define atomic64_xchg(v, new) (xchg(&((v)->counter), new)) long atomic64_dec_if_positive(atomic64_t *v); +#define atomic64_dec_if_positive atomic64_dec_if_positive #endif /* !(__ARCH_SPARC64_ATOMIC__) */ diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h index 472c7af0ed48..ef959f02d070 100644 --- a/arch/x86/include/asm/atomic64_32.h +++ b/arch/x86/include/asm/atomic64_32.h @@ -254,6 +254,7 @@ static inline int arch_atomic64_inc_not_zero(atomic64_t *v) return r; } +#define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive static inline long long arch_atomic64_dec_if_positive(atomic64_t *v) { long long r; diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h index 1b282272a801..849f1c566a11 100644 --- a/arch/x86/include/asm/atomic64_64.h +++ b/arch/x86/include/asm/atomic64_64.h @@ -191,24 +191,6 @@ static inline long arch_atomic64_xchg(atomic64_t *v, long new) return xchg(&v->counter, new); } -/* - * arch_atomic64_dec_if_positive - decrement by 1 if old value positive - * @v: pointer of type atomic_t - * - * The function returns the old value of *v minus 1, even if - * the atomic variable, v, was not decremented. - */ -static inline long arch_atomic64_dec_if_positive(atomic64_t *v) -{ - s64 dec, c = arch_atomic64_read(v); - do { - dec = c - 1; - if (unlikely(dec < 0)) - break; - } while (!arch_atomic64_try_cmpxchg(v, &c, dec)); - return dec; -} - static inline void arch_atomic64_and(long i, atomic64_t *v) { asm volatile(LOCK_PREFIX "andq %1,%0" diff --git a/include/asm-generic/atomic-instrumented.h b/include/asm-generic/atomic-instrumented.h index 12f9634750d7..3c64e95d5ed0 100644 --- a/include/asm-generic/atomic-instrumented.h +++ b/include/asm-generic/atomic-instrumented.h @@ -243,11 +243,14 @@ static __always_inline bool atomic64_inc_not_zero(atomic64_t *v) } #endif +#ifdef arch_atomic64_dec_if_positive +#define atomic64_dec_if_positive atomic64_dec_if_positive static __always_inline s64 atomic64_dec_if_positive(atomic64_t *v) { kasan_check_write(v, sizeof(*v)); return arch_atomic64_dec_if_positive(v); } +#endif #ifdef arch_atomic_dec_and_test #define atomic_dec_and_test atomic_dec_and_test diff --git a/include/asm-generic/atomic64.h b/include/asm-generic/atomic64.h index 242b79ae0b57..97b28b7f1f29 100644 --- a/include/asm-generic/atomic64.h +++ b/include/asm-generic/atomic64.h @@ -51,6 +51,7 @@ ATOMIC64_OPS(xor) #undef ATOMIC64_OP extern long long atomic64_dec_if_positive(atomic64_t *v); +#define atomic64_dec_if_positive atomic64_dec_if_positive extern long long atomic64_cmpxchg(atomic64_t *v, long long o, long long n); extern long long atomic64_xchg(atomic64_t *v, long long new); extern long long atomic64_fetch_add_unless(atomic64_t *v, long long a, long long u); diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 24f345df7ba6..93fe5b4041e1 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -683,28 +683,30 @@ static inline int atomic_fetch_andnot_release(int i, atomic_t *v) #endif #ifndef atomic_inc_unless_negative -static inline bool atomic_inc_unless_negative(atomic_t *p) +static inline bool atomic_inc_unless_negative(atomic_t *v) { - int v, v1; - for (v = 0; v >= 0; v = v1) { - v1 = atomic_cmpxchg(p, v, v + 1); - if (likely(v1 == v)) - return true; - } - return false; + int c = atomic_read(v); + + do { + if (unlikely(c < 0)) + return false; + } while (!atomic_try_cmpxchg(v, &c, c + 1)); + + return true; } #endif #ifndef atomic_dec_unless_positive -static inline bool atomic_dec_unless_positive(atomic_t *p) +static inline bool atomic_dec_unless_positive(atomic_t *v) { - int v, v1; - for (v = 0; v <= 0; v = v1) { - v1 = atomic_cmpxchg(p, v, v - 1); - if (likely(v1 == v)) - return true; - } - return false; + int c = atomic_read(v); + + do { + if (unlikely(c > 0)) + return false; + } while (!atomic_try_cmpxchg(v, &c, c - 1)); + + return true; } #endif @@ -718,17 +720,14 @@ static inline bool atomic_dec_unless_positive(atomic_t *p) #ifndef atomic_dec_if_positive static inline int atomic_dec_if_positive(atomic_t *v) { - int c, old, dec; - c = atomic_read(v); - for (;;) { + int dec, c = atomic_read(v); + + do { dec = c - 1; if (unlikely(dec < 0)) break; - old = atomic_cmpxchg((v), c, dec); - if (likely(old == c)) - break; - c = old; - } + } while (!atomic_try_cmpxchg(v, &c, dec)); + return dec; } #endif @@ -1290,6 +1289,56 @@ static inline long long atomic64_fetch_andnot_release(long long i, atomic64_t *v } #endif +#ifndef atomic64_inc_unless_negative +static inline bool atomic64_inc_unless_negative(atomic64_t *v) +{ + long long c = atomic64_read(v); + + do { + if (unlikely(c < 0)) + return false; + } while (!atomic64_try_cmpxchg(v, &c, c + 1)); + + return true; +} +#endif + +#ifndef atomic64_dec_unless_positive +static inline bool atomic64_dec_unless_positive(atomic64_t *v) +{ + long long c = atomic64_read(v); + + do { + if (unlikely(c > 0)) + return false; + } while (!atomic64_try_cmpxchg(v, &c, c - 1)); + + return true; +} +#endif + +/* + * atomic64_dec_if_positive - decrement by 1 if old value positive + * @v: pointer of type atomic64_t + * + * The function returns the old value of *v minus 1, even if + * the atomic64 variable, v, was not decremented. + */ +#ifndef atomic64_dec_if_positive +static inline long long atomic64_dec_if_positive(atomic64_t *v) +{ + long long dec, c = atomic64_read(v); + + do { + dec = c - 1; + if (unlikely(dec < 0)) + break; + } while (!atomic64_try_cmpxchg(v, &c, dec)); + + return dec; +} +#endif + #define atomic64_cond_read_relaxed(v, c) smp_cond_load_relaxed(&(v)->counter, (c)) #define atomic64_cond_read_acquire(v, c) smp_cond_load_acquire(&(v)->counter, (c)) -- cgit v1.2.3 From 7cc7eaad49c30ac165ecf84d95b26f7e0d53bd97 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Thu, 21 Jun 2018 13:13:21 +0100 Subject: atomics/treewide: Clean up '*_andnot()' ifdeffery The ifdeffery for atomic*_{fetch_,}andnot() is unlike that for all the other atomics. If atomic*_andnot() is not defined, the corresponding atomic*_fetch_andnot() is assumed to not be defined. Additionally, the fallbacks for the various ordering cases are written much later in atomic.h as static inlines. This isn't problematic today, but gets in the way of scripting the generation of atomics. To prepare for scripting, this patch: * Switches to separate ifdefs for atomic*_andnot() and atomic*_fetch_andnot(), updating implementations as appropriate. * Moves the fallbacks into the standards ifdefs, as macro expansions rather than static inlines. * Removes trivial andnot implementations from architectures, where these are superseded by core code. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Reviewed-by: Will Deacon Acked-by: Peter Zijlstra (Intel) Cc: Boqun Feng Cc: Linus Torvalds Cc: Thomas Gleixner Link: https://lore.kernel.org/lkml/20180621121321.4761-19-mark.rutland@arm.com Signed-off-by: Ingo Molnar --- arch/arc/include/asm/atomic.h | 8 ++-- arch/arm/include/asm/atomic.h | 2 + include/linux/atomic.h | 96 ++++++++++++++----------------------------- 3 files changed, 36 insertions(+), 70 deletions(-) (limited to 'include') diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h index 8f64f3b79b8a..4e0072730241 100644 --- a/arch/arc/include/asm/atomic.h +++ b/arch/arc/include/asm/atomic.h @@ -187,7 +187,8 @@ static inline int atomic_fetch_##op(int i, atomic_t *v) \ ATOMIC_OPS(add, +=, add) ATOMIC_OPS(sub, -=, sub) -#define atomic_andnot atomic_andnot +#define atomic_andnot atomic_andnot +#define atomic_fetch_andnot atomic_fetch_andnot #undef ATOMIC_OPS #define ATOMIC_OPS(op, c_op, asm_op) \ @@ -296,8 +297,6 @@ ATOMIC_OPS(add, +=, CTOP_INST_AADD_DI_R2_R2_R3) ATOMIC_FETCH_OP(op, c_op, asm_op) ATOMIC_OPS(and, &=, CTOP_INST_AAND_DI_R2_R2_R3) -#define atomic_andnot(mask, v) atomic_and(~(mask), (v)) -#define atomic_fetch_andnot(mask, v) atomic_fetch_and(~(mask), (v)) ATOMIC_OPS(or, |=, CTOP_INST_AOR_DI_R2_R2_R3) ATOMIC_OPS(xor, ^=, CTOP_INST_AXOR_DI_R2_R2_R3) @@ -430,7 +429,8 @@ static inline long long atomic64_fetch_##op(long long a, atomic64_t *v) \ ATOMIC64_OP_RETURN(op, op1, op2) \ ATOMIC64_FETCH_OP(op, op1, op2) -#define atomic64_andnot atomic64_andnot +#define atomic64_andnot atomic64_andnot +#define atomic64_fetch_andnot atomic64_fetch_andnot ATOMIC64_OPS(add, add.f, adc) ATOMIC64_OPS(sub, sub.f, sbc) diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h index 884c241424fe..f74756641410 100644 --- a/arch/arm/include/asm/atomic.h +++ b/arch/arm/include/asm/atomic.h @@ -216,6 +216,8 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new) return ret; } +#define atomic_fetch_andnot atomic_fetch_andnot + #endif /* __LINUX_ARM_ARCH__ */ #define ATOMIC_OPS(op, c_op, asm_op) \ diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 93fe5b4041e1..8e04f1f69bd9 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -354,12 +354,22 @@ #endif #endif /* atomic_fetch_and_relaxed */ -#ifdef atomic_andnot -/* atomic_fetch_andnot_relaxed */ +#ifndef atomic_andnot +#define atomic_andnot(i, v) atomic_and(~(int)(i), (v)) +#endif + #ifndef atomic_fetch_andnot_relaxed -#define atomic_fetch_andnot_relaxed atomic_fetch_andnot -#define atomic_fetch_andnot_acquire atomic_fetch_andnot -#define atomic_fetch_andnot_release atomic_fetch_andnot + +#ifndef atomic_fetch_andnot +#define atomic_fetch_andnot(i, v) atomic_fetch_and(~(int)(i), (v)) +#define atomic_fetch_andnot_relaxed(i, v) atomic_fetch_and_relaxed(~(int)(i), (v)) +#define atomic_fetch_andnot_acquire(i, v) atomic_fetch_and_acquire(~(int)(i), (v)) +#define atomic_fetch_andnot_release(i, v) atomic_fetch_and_release(~(int)(i), (v)) +#else /* atomic_fetch_andnot */ +#define atomic_fetch_andnot_relaxed atomic_fetch_andnot +#define atomic_fetch_andnot_acquire atomic_fetch_andnot +#define atomic_fetch_andnot_release atomic_fetch_andnot +#endif /* atomic_fetch_andnot */ #else /* atomic_fetch_andnot_relaxed */ @@ -378,7 +388,6 @@ __atomic_op_fence(atomic_fetch_andnot, __VA_ARGS__) #endif #endif /* atomic_fetch_andnot_relaxed */ -#endif /* atomic_andnot */ /* atomic_fetch_xor_relaxed */ #ifndef atomic_fetch_xor_relaxed @@ -655,33 +664,6 @@ static inline bool atomic_add_negative(int i, atomic_t *v) } #endif -#ifndef atomic_andnot -static inline void atomic_andnot(int i, atomic_t *v) -{ - atomic_and(~i, v); -} - -static inline int atomic_fetch_andnot(int i, atomic_t *v) -{ - return atomic_fetch_and(~i, v); -} - -static inline int atomic_fetch_andnot_relaxed(int i, atomic_t *v) -{ - return atomic_fetch_and_relaxed(~i, v); -} - -static inline int atomic_fetch_andnot_acquire(int i, atomic_t *v) -{ - return atomic_fetch_and_acquire(~i, v); -} - -static inline int atomic_fetch_andnot_release(int i, atomic_t *v) -{ - return atomic_fetch_and_release(~i, v); -} -#endif - #ifndef atomic_inc_unless_negative static inline bool atomic_inc_unless_negative(atomic_t *v) { @@ -1029,12 +1011,22 @@ static inline int atomic_dec_if_positive(atomic_t *v) #endif #endif /* atomic64_fetch_and_relaxed */ -#ifdef atomic64_andnot -/* atomic64_fetch_andnot_relaxed */ +#ifndef atomic64_andnot +#define atomic64_andnot(i, v) atomic64_and(~(long long)(i), (v)) +#endif + #ifndef atomic64_fetch_andnot_relaxed -#define atomic64_fetch_andnot_relaxed atomic64_fetch_andnot -#define atomic64_fetch_andnot_acquire atomic64_fetch_andnot -#define atomic64_fetch_andnot_release atomic64_fetch_andnot + +#ifndef atomic64_fetch_andnot +#define atomic64_fetch_andnot(i, v) atomic64_fetch_and(~(long long)(i), (v)) +#define atomic64_fetch_andnot_relaxed(i, v) atomic64_fetch_and_relaxed(~(long long)(i), (v)) +#define atomic64_fetch_andnot_acquire(i, v) atomic64_fetch_and_acquire(~(long long)(i), (v)) +#define atomic64_fetch_andnot_release(i, v) atomic64_fetch_and_release(~(long long)(i), (v)) +#else /* atomic64_fetch_andnot */ +#define atomic64_fetch_andnot_relaxed atomic64_fetch_andnot +#define atomic64_fetch_andnot_acquire atomic64_fetch_andnot +#define atomic64_fetch_andnot_release atomic64_fetch_andnot +#endif /* atomic64_fetch_andnot */ #else /* atomic64_fetch_andnot_relaxed */ @@ -1053,7 +1045,6 @@ static inline int atomic_dec_if_positive(atomic_t *v) __atomic_op_fence(atomic64_fetch_andnot, __VA_ARGS__) #endif #endif /* atomic64_fetch_andnot_relaxed */ -#endif /* atomic64_andnot */ /* atomic64_fetch_xor_relaxed */ #ifndef atomic64_fetch_xor_relaxed @@ -1262,33 +1253,6 @@ static inline bool atomic64_add_negative(long long i, atomic64_t *v) } #endif -#ifndef atomic64_andnot -static inline void atomic64_andnot(long long i, atomic64_t *v) -{ - atomic64_and(~i, v); -} - -static inline long long atomic64_fetch_andnot(long long i, atomic64_t *v) -{ - return atomic64_fetch_and(~i, v); -} - -static inline long long atomic64_fetch_andnot_relaxed(long long i, atomic64_t *v) -{ - return atomic64_fetch_and_relaxed(~i, v); -} - -static inline long long atomic64_fetch_andnot_acquire(long long i, atomic64_t *v) -{ - return atomic64_fetch_and_acquire(~i, v); -} - -static inline long long atomic64_fetch_andnot_release(long long i, atomic64_t *v) -{ - return atomic64_fetch_and_release(~i, v); -} -#endif - #ifndef atomic64_inc_unless_negative static inline bool atomic64_inc_unless_negative(atomic64_t *v) { -- cgit v1.2.3 From 8d4f4b82155cc6774d0fd8aaafb882566f7fd5fb Mon Sep 17 00:00:00 2001 From: Ville Syrjälä Date: Fri, 15 Jun 2018 20:39:39 +0300 Subject: drm: Document mode_config.max_width/height as the max fb dimensions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The meaning of the mode_config max_width/height fields has not been entirely clear. They are used both as the max framebuffer dimensions, and they are also used by drm_mode_getconnector() to filter out any mode whose hdisplay/vdisplay exceed those limits. Let's put it in writing that max_width/height only refrer to the max framebuffer dimensions, and should those be higher than the hardware limits for display timings the driver must validate the latter using some other means. We'll keep the max_width/height usage in drm_mode_getconnector() because setcrtc treats hdisplay/vdisplay also as the primary plane width, and having a plane bigger than the max fb size doesn't make much sense (if we ignore scaling that is). It all works out fine as long as the max fb dimensions are at least equal to the max timing limits. If the opposite were true we may want to rethink what drm_mode_getconnector() does. Maybe do the mode filtering only for non-atomic userspace? Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20180615173939.11353-1-ville.syrjala@linux.intel.com Reviewed-by: Manasi Navare --- include/drm/drm_mode_config.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/drm/drm_mode_config.h b/include/drm/drm_mode_config.h index f4a173c8d79c..a0b202e1d69a 100644 --- a/include/drm/drm_mode_config.h +++ b/include/drm/drm_mode_config.h @@ -329,10 +329,10 @@ struct drm_mode_config_funcs { /** * struct drm_mode_config - Mode configuration control structure - * @min_width: minimum pixel width on this device - * @min_height: minimum pixel height on this device - * @max_width: maximum pixel width on this device - * @max_height: maximum pixel height on this device + * @min_width: minimum fb pixel width on this device + * @min_height: minimum fb pixel height on this device + * @max_width: maximum fb pixel width on this device + * @max_height: maximum fb pixel height on this device * @funcs: core driver provided mode setting functions * @fb_base: base address of the framebuffer * @poll_enabled: track polling support for this device -- cgit v1.2.3 From 75a040ff14d9a99fc041f5e1d8f09541cab13ba4 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Sun, 1 Apr 2018 01:00:36 +0300 Subject: locking/refcounts: Include fewer headers in Debloat 's dependencies: - is not needed, but is. - is not needed, only a forward declaration of "struct mutex". - is not needed, is enough. Signed-off-by: Alexey Dobriyan Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Will Deacon Link: https://lkml.kernel.org/lkml/20180331220036.GA7676@avx2 Signed-off-by: Ingo Molnar --- arch/x86/include/asm/refcount.h | 1 + include/linux/refcount.h | 7 ++++--- lib/refcount.c | 2 ++ 3 files changed, 7 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/arch/x86/include/asm/refcount.h b/arch/x86/include/asm/refcount.h index 4cf11d88d3b3..19b90521954c 100644 --- a/arch/x86/include/asm/refcount.h +++ b/arch/x86/include/asm/refcount.h @@ -5,6 +5,7 @@ * PaX/grsecurity. */ #include +#include /* * This is the first portion of the refcount error handling, which lives in diff --git a/include/linux/refcount.h b/include/linux/refcount.h index 4193c41e383a..c36addd27dd5 100644 --- a/include/linux/refcount.h +++ b/include/linux/refcount.h @@ -3,9 +3,10 @@ #define _LINUX_REFCOUNT_H #include -#include -#include -#include +#include +#include + +struct mutex; /** * struct refcount_t - variant of atomic_t specialized for reference counts diff --git a/lib/refcount.c b/lib/refcount.c index 0eb48353abe3..4bd842f20749 100644 --- a/lib/refcount.c +++ b/lib/refcount.c @@ -35,7 +35,9 @@ * */ +#include #include +#include #include #ifdef CONFIG_REFCOUNT_FULL -- cgit v1.2.3 From 6aa13402c11035a428d8c621b334734971d5d39d Mon Sep 17 00:00:00 2001 From: Eric Anholt Date: Wed, 6 Jun 2018 12:04:29 -0700 Subject: drm/bridge: Move the struct drm_bridge member kerneldoc inline. This makes it more likely that the docs stay updated with the code. Signed-off-by: Eric Anholt Link: https://patchwork.freedesktop.org/patch/msgid/20180606190431.1833-1-eric@anholt.net Reviewed-by: Andrzej Hajda --- include/drm/drm_bridge.h | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/drm/drm_bridge.h b/include/drm/drm_bridge.h index 70131ab57e8f..bd850747ce54 100644 --- a/include/drm/drm_bridge.h +++ b/include/drm/drm_bridge.h @@ -270,27 +270,29 @@ struct drm_bridge_timings { /** * struct drm_bridge - central DRM bridge control structure - * @dev: DRM device this bridge belongs to - * @encoder: encoder to which this bridge is connected - * @next: the next bridge in the encoder chain - * @of_node: device node pointer to the bridge - * @list: to keep track of all added bridges - * @timings: the timing specification for the bridge, if any (may - * be NULL) - * @funcs: control functions - * @driver_private: pointer to the bridge driver's internal context */ struct drm_bridge { + /** @dev: DRM device this bridge belongs to */ struct drm_device *dev; + /** @encoder: encoder to which this bridge is connected */ struct drm_encoder *encoder; + /** @next: the next bridge in the encoder chain */ struct drm_bridge *next; #ifdef CONFIG_OF + /** @of_node: device node pointer to the bridge */ struct device_node *of_node; #endif + /** @list: to keep track of all added bridges */ struct list_head list; + /** + * @timings: + * + * the timing specification for the bridge, if any (may be NULL) + */ const struct drm_bridge_timings *timings; - + /** @funcs: control functions */ const struct drm_bridge_funcs *funcs; + /** @driver_private: pointer to the bridge driver's internal context */ void *driver_private; }; -- cgit v1.2.3 From 0eb71a9da5796851fa87ddc1a534066c0fe54055 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 18 Jun 2018 12:52:50 +1000 Subject: rhashtable: split rhashtable.h Due to the use of rhashtables in net namespaces, rhashtable.h is included in lots of the kernel, so a small changes can required a large recompilation. This makes development painful. This patch splits out rhashtable-types.h which just includes the major type declarations, and does not include (non-trivial) inline code. rhashtable.h is no longer included by anything in the include/ directory. Common include files only include rhashtable-types.h so a large recompilation is only triggered when that changes. Acked-by: Herbert Xu Signed-off-by: NeilBrown Signed-off-by: David S. Miller --- MAINTAINERS | 2 + drivers/net/ethernet/chelsio/cxgb4/cxgb4.h | 1 + include/linux/ipc.h | 2 +- include/linux/ipc_namespace.h | 2 +- include/linux/mroute_base.h | 2 +- include/linux/rhashtable-types.h | 139 +++++++++++++++++++++++++++++ include/linux/rhashtable.h | 127 +------------------------- include/net/inet_frag.h | 2 +- include/net/netfilter/nf_flow_table.h | 2 +- include/net/sctp/structs.h | 2 +- include/net/seg6.h | 2 +- include/net/seg6_hmac.h | 2 +- ipc/msg.c | 1 + ipc/sem.c | 1 + ipc/shm.c | 1 + ipc/util.c | 1 + lib/rhashtable.c | 1 + net/ipv4/inet_fragment.c | 1 + net/ipv4/ipmr.c | 1 + net/ipv4/ipmr_base.c | 1 + net/ipv6/ip6mr.c | 1 + net/ipv6/seg6.c | 1 + net/ipv6/seg6_hmac.c | 1 + net/netfilter/nf_tables_api.c | 1 + net/sctp/input.c | 1 + net/sctp/socket.c | 1 + 26 files changed, 166 insertions(+), 133 deletions(-) create mode 100644 include/linux/rhashtable-types.h (limited to 'include') diff --git a/MAINTAINERS b/MAINTAINERS index edf3cf5ea691..99e5cef8172e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -12162,7 +12162,9 @@ M: Herbert Xu L: netdev@vger.kernel.org S: Maintained F: lib/rhashtable.c +F: lib/test_rhashtable.c F: include/linux/rhashtable.h +F: include/linux/rhashtable-types.h RICOH R5C592 MEMORYSTICK DRIVER M: Maxim Levitsky diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index 0dbe2d9e22d6..1adb968b8354 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -46,6 +46,7 @@ #include #include #include +#include #include #include #include diff --git a/include/linux/ipc.h b/include/linux/ipc.h index 6cc2df7f7ac9..e1c9eea6015b 100644 --- a/include/linux/ipc.h +++ b/include/linux/ipc.h @@ -4,7 +4,7 @@ #include #include -#include +#include #include #include diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index b5630c8eb2f3..6cea726612b7 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -9,7 +9,7 @@ #include #include #include -#include +#include struct user_namespace; diff --git a/include/linux/mroute_base.h b/include/linux/mroute_base.h index d633f737b3c6..fd436cdd4725 100644 --- a/include/linux/mroute_base.h +++ b/include/linux/mroute_base.h @@ -2,7 +2,7 @@ #define __LINUX_MROUTE_BASE_H #include -#include +#include #include #include #include diff --git a/include/linux/rhashtable-types.h b/include/linux/rhashtable-types.h new file mode 100644 index 000000000000..9740063ff13b --- /dev/null +++ b/include/linux/rhashtable-types.h @@ -0,0 +1,139 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Resizable, Scalable, Concurrent Hash Table + * + * Simple structures that might be needed in include + * files. + */ + +#ifndef _LINUX_RHASHTABLE_TYPES_H +#define _LINUX_RHASHTABLE_TYPES_H + +#include +#include +#include +#include + +struct rhash_head { + struct rhash_head __rcu *next; +}; + +struct rhlist_head { + struct rhash_head rhead; + struct rhlist_head __rcu *next; +}; + +struct bucket_table; + +/** + * struct rhashtable_compare_arg - Key for the function rhashtable_compare + * @ht: Hash table + * @key: Key to compare against + */ +struct rhashtable_compare_arg { + struct rhashtable *ht; + const void *key; +}; + +typedef u32 (*rht_hashfn_t)(const void *data, u32 len, u32 seed); +typedef u32 (*rht_obj_hashfn_t)(const void *data, u32 len, u32 seed); +typedef int (*rht_obj_cmpfn_t)(struct rhashtable_compare_arg *arg, + const void *obj); + +/** + * struct rhashtable_params - Hash table construction parameters + * @nelem_hint: Hint on number of elements, should be 75% of desired size + * @key_len: Length of key + * @key_offset: Offset of key in struct to be hashed + * @head_offset: Offset of rhash_head in struct to be hashed + * @max_size: Maximum size while expanding + * @min_size: Minimum size while shrinking + * @locks_mul: Number of bucket locks to allocate per cpu (default: 32) + * @automatic_shrinking: Enable automatic shrinking of tables + * @nulls_base: Base value to generate nulls marker + * @hashfn: Hash function (default: jhash2 if !(key_len % 4), or jhash) + * @obj_hashfn: Function to hash object + * @obj_cmpfn: Function to compare key with object + */ +struct rhashtable_params { + u16 nelem_hint; + u16 key_len; + u16 key_offset; + u16 head_offset; + unsigned int max_size; + u16 min_size; + bool automatic_shrinking; + u8 locks_mul; + u32 nulls_base; + rht_hashfn_t hashfn; + rht_obj_hashfn_t obj_hashfn; + rht_obj_cmpfn_t obj_cmpfn; +}; + +/** + * struct rhashtable - Hash table handle + * @tbl: Bucket table + * @key_len: Key length for hashfn + * @max_elems: Maximum number of elements in table + * @p: Configuration parameters + * @rhlist: True if this is an rhltable + * @run_work: Deferred worker to expand/shrink asynchronously + * @mutex: Mutex to protect current/future table swapping + * @lock: Spin lock to protect walker list + * @nelems: Number of elements in table + */ +struct rhashtable { + struct bucket_table __rcu *tbl; + unsigned int key_len; + unsigned int max_elems; + struct rhashtable_params p; + bool rhlist; + struct work_struct run_work; + struct mutex mutex; + spinlock_t lock; + atomic_t nelems; +}; + +/** + * struct rhltable - Hash table with duplicate objects in a list + * @ht: Underlying rhtable + */ +struct rhltable { + struct rhashtable ht; +}; + +/** + * struct rhashtable_walker - Hash table walker + * @list: List entry on list of walkers + * @tbl: The table that we were walking over + */ +struct rhashtable_walker { + struct list_head list; + struct bucket_table *tbl; +}; + +/** + * struct rhashtable_iter - Hash table iterator + * @ht: Table to iterate through + * @p: Current pointer + * @list: Current hash list pointer + * @walker: Associated rhashtable walker + * @slot: Current slot + * @skip: Number of entries to skip in slot + */ +struct rhashtable_iter { + struct rhashtable *ht; + struct rhash_head *p; + struct rhlist_head *list; + struct rhashtable_walker walker; + unsigned int slot; + unsigned int skip; + bool end_of_table; +}; + +int rhashtable_init(struct rhashtable *ht, + const struct rhashtable_params *params); +int rhltable_init(struct rhltable *hlt, + const struct rhashtable_params *params); + +#endif /* _LINUX_RHASHTABLE_TYPES_H */ diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 4e1f535c2034..48754ab07cdf 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Resizable, Scalable, Concurrent Hash Table * @@ -17,16 +18,14 @@ #ifndef _LINUX_RHASHTABLE_H #define _LINUX_RHASHTABLE_H -#include -#include #include #include #include #include #include -#include #include +#include /* * The end of the chain is marked with a special nulls marks which has * the following format: @@ -64,15 +63,6 @@ */ #define RHT_ELASTICITY 16u -struct rhash_head { - struct rhash_head __rcu *next; -}; - -struct rhlist_head { - struct rhash_head rhead; - struct rhlist_head __rcu *next; -}; - /** * struct bucket_table - Table of hash buckets * @size: Number of hash buckets @@ -102,114 +92,6 @@ struct bucket_table { struct rhash_head __rcu *buckets[] ____cacheline_aligned_in_smp; }; -/** - * struct rhashtable_compare_arg - Key for the function rhashtable_compare - * @ht: Hash table - * @key: Key to compare against - */ -struct rhashtable_compare_arg { - struct rhashtable *ht; - const void *key; -}; - -typedef u32 (*rht_hashfn_t)(const void *data, u32 len, u32 seed); -typedef u32 (*rht_obj_hashfn_t)(const void *data, u32 len, u32 seed); -typedef int (*rht_obj_cmpfn_t)(struct rhashtable_compare_arg *arg, - const void *obj); - -struct rhashtable; - -/** - * struct rhashtable_params - Hash table construction parameters - * @nelem_hint: Hint on number of elements, should be 75% of desired size - * @key_len: Length of key - * @key_offset: Offset of key in struct to be hashed - * @head_offset: Offset of rhash_head in struct to be hashed - * @max_size: Maximum size while expanding - * @min_size: Minimum size while shrinking - * @locks_mul: Number of bucket locks to allocate per cpu (default: 32) - * @automatic_shrinking: Enable automatic shrinking of tables - * @nulls_base: Base value to generate nulls marker - * @hashfn: Hash function (default: jhash2 if !(key_len % 4), or jhash) - * @obj_hashfn: Function to hash object - * @obj_cmpfn: Function to compare key with object - */ -struct rhashtable_params { - u16 nelem_hint; - u16 key_len; - u16 key_offset; - u16 head_offset; - unsigned int max_size; - u16 min_size; - bool automatic_shrinking; - u8 locks_mul; - u32 nulls_base; - rht_hashfn_t hashfn; - rht_obj_hashfn_t obj_hashfn; - rht_obj_cmpfn_t obj_cmpfn; -}; - -/** - * struct rhashtable - Hash table handle - * @tbl: Bucket table - * @key_len: Key length for hashfn - * @max_elems: Maximum number of elements in table - * @p: Configuration parameters - * @rhlist: True if this is an rhltable - * @run_work: Deferred worker to expand/shrink asynchronously - * @mutex: Mutex to protect current/future table swapping - * @lock: Spin lock to protect walker list - * @nelems: Number of elements in table - */ -struct rhashtable { - struct bucket_table __rcu *tbl; - unsigned int key_len; - unsigned int max_elems; - struct rhashtable_params p; - bool rhlist; - struct work_struct run_work; - struct mutex mutex; - spinlock_t lock; - atomic_t nelems; -}; - -/** - * struct rhltable - Hash table with duplicate objects in a list - * @ht: Underlying rhtable - */ -struct rhltable { - struct rhashtable ht; -}; - -/** - * struct rhashtable_walker - Hash table walker - * @list: List entry on list of walkers - * @tbl: The table that we were walking over - */ -struct rhashtable_walker { - struct list_head list; - struct bucket_table *tbl; -}; - -/** - * struct rhashtable_iter - Hash table iterator - * @ht: Table to iterate through - * @p: Current pointer - * @list: Current hash list pointer - * @walker: Associated rhashtable walker - * @slot: Current slot - * @skip: Number of entries to skip in slot - */ -struct rhashtable_iter { - struct rhashtable *ht; - struct rhash_head *p; - struct rhlist_head *list; - struct rhashtable_walker walker; - unsigned int slot; - unsigned int skip; - bool end_of_table; -}; - static inline unsigned long rht_marker(const struct rhashtable *ht, u32 hash) { return NULLS_MARKER(ht->p.nulls_base + hash); @@ -376,11 +258,6 @@ static inline int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, } #endif /* CONFIG_PROVE_LOCKING */ -int rhashtable_init(struct rhashtable *ht, - const struct rhashtable_params *params); -int rhltable_init(struct rhltable *hlt, - const struct rhashtable_params *params); - void *rhashtable_insert_slow(struct rhashtable *ht, const void *key, struct rhash_head *obj); diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index ed07e3786d98..f4272a29dc44 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -2,7 +2,7 @@ #ifndef __NET_FRAG_H__ #define __NET_FRAG_H__ -#include +#include struct netns_frags { /* sysctls */ diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index ba9fa4592f2b..0e355f4a3d76 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -4,7 +4,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index dbe1b911a24d..e0f962d27386 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -48,7 +48,7 @@ #define __sctp_structs_h__ #include -#include +#include #include /* linux/in.h needs this!! */ #include /* We get struct sockaddr_in. */ #include /* We get struct in6_addr */ diff --git a/include/net/seg6.h b/include/net/seg6.h index e029e301faa5..2567941a2f32 100644 --- a/include/net/seg6.h +++ b/include/net/seg6.h @@ -18,7 +18,7 @@ #include #include #include -#include +#include static inline void update_csum_diff4(struct sk_buff *skb, __be32 from, __be32 to) diff --git a/include/net/seg6_hmac.h b/include/net/seg6_hmac.h index 69c3a106056b..7fda469e2758 100644 --- a/include/net/seg6_hmac.h +++ b/include/net/seg6_hmac.h @@ -22,7 +22,7 @@ #include #include #include -#include +#include #define SEG6_HMAC_MAX_DIGESTSIZE 160 #define SEG6_HMAC_RING_SIZE 256 diff --git a/ipc/msg.c b/ipc/msg.c index 3b6545302598..203281198079 100644 --- a/ipc/msg.c +++ b/ipc/msg.c @@ -38,6 +38,7 @@ #include #include #include +#include #include #include diff --git a/ipc/sem.c b/ipc/sem.c index 5af1943ad782..29c0347ef11d 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -86,6 +86,7 @@ #include #include #include +#include #include #include "util.h" diff --git a/ipc/shm.c b/ipc/shm.c index 051a3e1fb8df..d4daf78df6da 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -43,6 +43,7 @@ #include #include #include +#include #include diff --git a/ipc/util.c b/ipc/util.c index 4e81182fa0ac..fdffff41f65b 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -63,6 +63,7 @@ #include #include #include +#include #include diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 9427b5766134..c9fafea7dc6e 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -28,6 +28,7 @@ #include #include #include +#include #define HASH_DEFAULT_SIZE 64UL #define HASH_MIN_SIZE 4U diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index c9e35b81d093..316518f87294 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 9f79b9803a16..82f914122f1b 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -60,6 +60,7 @@ #include #include #include +#include #include #include #include diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c index cafb0506c8c9..1ad9aa62a97b 100644 --- a/net/ipv4/ipmr_base.c +++ b/net/ipv4/ipmr_base.c @@ -2,6 +2,7 @@ * Common logic shared by IPv4 [ipmr] and IPv6 [ip6mr] implementation */ +#include #include /* Sets everything common except 'dev', since that is done under locking */ diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 0d0f0053bb11..d0b7e0249c13 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -32,6 +32,7 @@ #include #include #include +#include #include #include #include diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index 0fdf2a55e746..8d0ba757a46c 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c index 33fb35cbfac1..b1791129a875 100644 --- a/net/ipv6/seg6_hmac.c +++ b/net/ipv6/seg6_hmac.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 896d4a36081d..3f211e1025c1 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include diff --git a/net/sctp/input.c b/net/sctp/input.c index ba8a6e6c36fa..9bbc5f92c941 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -56,6 +56,7 @@ #include #include #include +#include /* Forward declarations for internal helpers. */ static int sctp_rcv_ootb(struct sk_buff *); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index d20f7addee19..0e91e83eea5a 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -66,6 +66,7 @@ #include #include #include +#include #include #include -- cgit v1.2.3 From 9f9a707738aa7a8b9f78a641b83927ada256a626 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 18 Jun 2018 12:52:50 +1000 Subject: rhashtable: remove nulls_base and related code. This "feature" is unused, undocumented, and untested and so doesn't really belong. A patch is under development to properly implement support for detecting when a search gets diverted down a different chain, which the common purpose of nulls markers. This patch actually fixes a bug too. The table resizing allows a table to grow to 2^31 buckets, but the hash is truncated to 27 bits - any growth beyond 2^27 is wasteful an ineffective. This patch results in NULLS_MARKER(0) being used for all chains, and leaves the use of rht_is_a_null() to test for it. Acked-by: Herbert Xu Signed-off-by: NeilBrown Signed-off-by: David S. Miller --- include/linux/rhashtable-types.h | 2 -- include/linux/rhashtable.h | 33 +++------------------------------ lib/rhashtable.c | 8 -------- lib/test_rhashtable.c | 5 +---- net/core/xdp.c | 4 ++-- 5 files changed, 6 insertions(+), 46 deletions(-) (limited to 'include') diff --git a/include/linux/rhashtable-types.h b/include/linux/rhashtable-types.h index 9740063ff13b..763d613ce2c2 100644 --- a/include/linux/rhashtable-types.h +++ b/include/linux/rhashtable-types.h @@ -50,7 +50,6 @@ typedef int (*rht_obj_cmpfn_t)(struct rhashtable_compare_arg *arg, * @min_size: Minimum size while shrinking * @locks_mul: Number of bucket locks to allocate per cpu (default: 32) * @automatic_shrinking: Enable automatic shrinking of tables - * @nulls_base: Base value to generate nulls marker * @hashfn: Hash function (default: jhash2 if !(key_len % 4), or jhash) * @obj_hashfn: Function to hash object * @obj_cmpfn: Function to compare key with object @@ -64,7 +63,6 @@ struct rhashtable_params { u16 min_size; bool automatic_shrinking; u8 locks_mul; - u32 nulls_base; rht_hashfn_t hashfn; rht_obj_hashfn_t obj_hashfn; rht_obj_cmpfn_t obj_cmpfn; diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 48754ab07cdf..d9f719af7936 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -28,25 +28,8 @@ #include /* * The end of the chain is marked with a special nulls marks which has - * the following format: - * - * +-------+-----------------------------------------------------+-+ - * | Base | Hash |1| - * +-------+-----------------------------------------------------+-+ - * - * Base (4 bits) : Reserved to distinguish between multiple tables. - * Specified via &struct rhashtable_params.nulls_base. - * Hash (27 bits): Full hash (unmasked) of first element added to bucket - * 1 (1 bit) : Nulls marker (always set) - * - * The remaining bits of the next pointer remain unused for now. + * the least significant bit set. */ -#define RHT_BASE_BITS 4 -#define RHT_HASH_BITS 27 -#define RHT_BASE_SHIFT RHT_HASH_BITS - -/* Base bits plus 1 bit for nulls marker */ -#define RHT_HASH_RESERVED_SPACE (RHT_BASE_BITS + 1) /* Maximum chain length before rehash * @@ -92,24 +75,14 @@ struct bucket_table { struct rhash_head __rcu *buckets[] ____cacheline_aligned_in_smp; }; -static inline unsigned long rht_marker(const struct rhashtable *ht, u32 hash) -{ - return NULLS_MARKER(ht->p.nulls_base + hash); -} - #define INIT_RHT_NULLS_HEAD(ptr, ht, hash) \ - ((ptr) = (typeof(ptr)) rht_marker(ht, hash)) + ((ptr) = (typeof(ptr)) NULLS_MARKER(0)) static inline bool rht_is_a_nulls(const struct rhash_head *ptr) { return ((unsigned long) ptr & 1); } -static inline unsigned long rht_get_nulls_value(const struct rhash_head *ptr) -{ - return ((unsigned long) ptr) >> 1; -} - static inline void *rht_obj(const struct rhashtable *ht, const struct rhash_head *he) { @@ -119,7 +92,7 @@ static inline void *rht_obj(const struct rhashtable *ht, static inline unsigned int rht_bucket_index(const struct bucket_table *tbl, unsigned int hash) { - return (hash >> RHT_HASH_RESERVED_SPACE) & (tbl->size - 1); + return hash & (tbl->size - 1); } static inline unsigned int rht_key_get_hash(struct rhashtable *ht, diff --git a/lib/rhashtable.c b/lib/rhashtable.c index c9fafea7dc6e..688693c919be 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -995,7 +995,6 @@ static u32 rhashtable_jhash2(const void *key, u32 length, u32 seed) * .key_offset = offsetof(struct test_obj, key), * .key_len = sizeof(int), * .hashfn = jhash, - * .nulls_base = (1U << RHT_BASE_SHIFT), * }; * * Configuration Example 2: Variable length keys @@ -1029,9 +1028,6 @@ int rhashtable_init(struct rhashtable *ht, (params->obj_hashfn && !params->obj_cmpfn)) return -EINVAL; - if (params->nulls_base && params->nulls_base < (1U << RHT_BASE_SHIFT)) - return -EINVAL; - memset(ht, 0, sizeof(*ht)); mutex_init(&ht->mutex); spin_lock_init(&ht->lock); @@ -1096,10 +1092,6 @@ int rhltable_init(struct rhltable *hlt, const struct rhashtable_params *params) { int err; - /* No rhlist NULLs marking for now. */ - if (params->nulls_base) - return -EINVAL; - err = rhashtable_init(&hlt->ht, params); hlt->ht.rhlist = true; return err; diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c index 6ca59ffcacbe..82ac39ce5310 100644 --- a/lib/test_rhashtable.c +++ b/lib/test_rhashtable.c @@ -83,7 +83,7 @@ static u32 my_hashfn(const void *data, u32 len, u32 seed) { const struct test_obj_rhl *obj = data; - return (obj->value.id % 10) << RHT_HASH_RESERVED_SPACE; + return (obj->value.id % 10); } static int my_cmpfn(struct rhashtable_compare_arg *arg, const void *obj) @@ -99,7 +99,6 @@ static struct rhashtable_params test_rht_params = { .key_offset = offsetof(struct test_obj, value), .key_len = sizeof(struct test_obj_val), .hashfn = jhash, - .nulls_base = (3U << RHT_BASE_SHIFT), }; static struct rhashtable_params test_rht_params_dup = { @@ -296,8 +295,6 @@ static int __init test_rhltable(unsigned int entries) if (!obj_in_table) goto out_free; - /* nulls_base not supported in rhlist interface */ - test_rht_params.nulls_base = 0; err = rhltable_init(&rhlt, &test_rht_params); if (WARN_ON(err)) goto out_free; diff --git a/net/core/xdp.c b/net/core/xdp.c index 9d1f22072d5d..31c58719b5a9 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -45,8 +45,8 @@ static u32 xdp_mem_id_hashfn(const void *data, u32 len, u32 seed) BUILD_BUG_ON(FIELD_SIZEOF(struct xdp_mem_allocator, mem.id) != sizeof(u32)); - /* Use cyclic increasing ID as direct hash key, see rht_bucket_index */ - return key << RHT_HASH_RESERVED_SPACE; + /* Use cyclic increasing ID as direct hash key */ + return key; } static int xdp_mem_id_cmp(struct rhashtable_compare_arg *arg, -- cgit v1.2.3 From 9b4f64a227b6f462482a8cc68c7134dc6e26f1c1 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 18 Jun 2018 12:52:50 +1000 Subject: rhashtable: simplify INIT_RHT_NULLS_HEAD() The 'ht' and 'hash' arguments to INIT_RHT_NULLS_HEAD() are no longer used - so drop them. This allows us to also remove the nhash argument from nested_table_alloc(). Acked-by: Herbert Xu Signed-off-by: NeilBrown Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 2 +- lib/rhashtable.c | 15 ++++++--------- 2 files changed, 7 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index d9f719af7936..3f3a182bd0b4 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -75,7 +75,7 @@ struct bucket_table { struct rhash_head __rcu *buckets[] ____cacheline_aligned_in_smp; }; -#define INIT_RHT_NULLS_HEAD(ptr, ht, hash) \ +#define INIT_RHT_NULLS_HEAD(ptr) \ ((ptr) = (typeof(ptr)) NULLS_MARKER(0)) static inline bool rht_is_a_nulls(const struct rhash_head *ptr) diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 688693c919be..a81cd27d518c 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -116,8 +116,7 @@ static void bucket_table_free_rcu(struct rcu_head *head) static union nested_table *nested_table_alloc(struct rhashtable *ht, union nested_table __rcu **prev, - unsigned int shifted, - unsigned int nhash) + unsigned int shifted) { union nested_table *ntbl; int i; @@ -130,8 +129,7 @@ static union nested_table *nested_table_alloc(struct rhashtable *ht, if (ntbl && shifted) { for (i = 0; i < PAGE_SIZE / sizeof(ntbl[0].bucket); i++) - INIT_RHT_NULLS_HEAD(ntbl[i].bucket, ht, - (i << shifted) | nhash); + INIT_RHT_NULLS_HEAD(ntbl[i].bucket); } rcu_assign_pointer(*prev, ntbl); @@ -157,7 +155,7 @@ static struct bucket_table *nested_bucket_table_alloc(struct rhashtable *ht, return NULL; if (!nested_table_alloc(ht, (union nested_table __rcu **)tbl->buckets, - 0, 0)) { + 0)) { kfree(tbl); return NULL; } @@ -207,7 +205,7 @@ static struct bucket_table *bucket_table_alloc(struct rhashtable *ht, tbl->hash_rnd = get_random_u32(); for (i = 0; i < nbuckets; i++) - INIT_RHT_NULLS_HEAD(tbl->buckets[i], ht, i); + INIT_RHT_NULLS_HEAD(tbl->buckets[i]); return tbl; } @@ -1217,7 +1215,7 @@ struct rhash_head __rcu **rht_bucket_nested_insert(struct rhashtable *ht, nhash = index; shifted = tbl->nest; ntbl = nested_table_alloc(ht, &ntbl[index].table, - size <= (1 << shift) ? shifted : 0, nhash); + size <= (1 << shift) ? shifted : 0); while (ntbl && size > (1 << shift)) { index = hash & ((1 << shift) - 1); @@ -1226,8 +1224,7 @@ struct rhash_head __rcu **rht_bucket_nested_insert(struct rhashtable *ht, nhash |= index << shifted; shifted += shift; ntbl = nested_table_alloc(ht, &ntbl[index].table, - size <= (1 << shift) ? shifted : 0, - nhash); + size <= (1 << shift) ? shifted : 0); } if (!ntbl) -- cgit v1.2.3 From c0690016a73fe6bd456887bbbe6e10c7f0096554 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 18 Jun 2018 12:52:50 +1000 Subject: rhashtable: clean up dereference of ->future_tbl. Using rht_dereference_bucket() to dereference ->future_tbl looks like a type error, and could be confusing. Using rht_dereference_rcu() to test a pointer for NULL adds an unnecessary barrier - rcu_access_pointer() is preferred for NULL tests when no lock is held. This uses 3 different ways to access ->future_tbl. - if we know the mutex is held, use rht_dereference() - if we don't hold the mutex, and are only testing for NULL, use rcu_access_pointer() - otherwise (using RCU protection for true dereference), use rht_dereference_rcu(). Note that this includes a simplification of the call to rhashtable_last_table() - we don't do an extra dereference before the call any more. Acked-by: Herbert Xu Signed-off-by: NeilBrown Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 2 +- lib/rhashtable.c | 9 ++++----- 2 files changed, 5 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 3f3a182bd0b4..eb7111039247 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -595,7 +595,7 @@ static inline void *__rhashtable_insert_fast( lock = rht_bucket_lock(tbl, hash); spin_lock_bh(lock); - if (unlikely(rht_dereference_bucket(tbl->future_tbl, tbl, hash))) { + if (unlikely(rcu_access_pointer(tbl->future_tbl))) { slow_path: spin_unlock_bh(lock); rcu_read_unlock(); diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 52ec83212856..0e04947b7e0c 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -226,8 +226,7 @@ static struct bucket_table *rhashtable_last_table(struct rhashtable *ht, static int rhashtable_rehash_one(struct rhashtable *ht, unsigned int old_hash) { struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht); - struct bucket_table *new_tbl = rhashtable_last_table(ht, - rht_dereference_rcu(old_tbl->future_tbl, ht)); + struct bucket_table *new_tbl = rhashtable_last_table(ht, old_tbl); struct rhash_head __rcu **pprev = rht_bucket_var(old_tbl, old_hash); int err = -EAGAIN; struct rhash_head *head, *next, *entry; @@ -467,7 +466,7 @@ static int rhashtable_insert_rehash(struct rhashtable *ht, fail: /* Do not fail the insert if someone else did a rehash. */ - if (likely(rcu_dereference_raw(tbl->future_tbl))) + if (likely(rcu_access_pointer(tbl->future_tbl))) return 0; /* Schedule async rehash to retry allocation in process context. */ @@ -540,7 +539,7 @@ static struct bucket_table *rhashtable_insert_one(struct rhashtable *ht, if (PTR_ERR(data) != -EAGAIN && PTR_ERR(data) != -ENOENT) return ERR_CAST(data); - new_tbl = rcu_dereference(tbl->future_tbl); + new_tbl = rht_dereference_rcu(tbl->future_tbl, ht); if (new_tbl) return new_tbl; @@ -599,7 +598,7 @@ static void *rhashtable_try_insert(struct rhashtable *ht, const void *key, break; spin_unlock_bh(lock); - tbl = rcu_dereference(tbl->future_tbl); + tbl = rht_dereference_rcu(tbl->future_tbl, ht); } data = rhashtable_lookup_one(ht, tbl, hash, key, obj); -- cgit v1.2.3 From 3f6c65d6255a872846c44182c82c78d3dc6239f5 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Tue, 19 Jun 2018 21:42:50 -0700 Subject: tcp: ignore rcv_rtt sample with old ts ecr value When receiving multiple packets with the same ts ecr value, only try to compute rcv_rtt sample with the earliest received packet. This is because the rcv_rtt calculated by later received packets could possibly include long idle time or other types of delay. For example: (1) server sends last packet of reply with TS val V1 (2) client ACKs last packet of reply with TS ecr V1 (3) long idle time passes (4) client sends next request data packet with TS ecr V1 (again!) At this time, the rcv_rtt computed on server with TS ecr V1 will be inflated with the idle time and should get ignored. Signed-off-by: Wei Wang Signed-off-by: Neal Cardwell Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + net/ipv4/tcp.c | 1 + net/ipv4/tcp_input.c | 14 +++++++++++--- 3 files changed, 13 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 72705eaf4b84..3dbea6610304 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -350,6 +350,7 @@ struct tcp_sock { #endif /* Receiver side RTT estimation */ + u32 rcv_rtt_last_tsecr; struct { u32 rtt_us; u32 seq; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 141acd92e58a..47c45d5be9f9 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2563,6 +2563,7 @@ int tcp_disconnect(struct sock *sk, int flags) sk->sk_shutdown = 0; sock_reset_flag(sk, SOCK_DONE); tp->srtt_us = 0; + tp->rcv_rtt_last_tsecr = 0; tp->write_seq += tp->max_window + 2; if (tp->write_seq == 0) tp->write_seq = 1; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 355d3dffd021..76ca88f63b70 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -582,9 +582,12 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk, { struct tcp_sock *tp = tcp_sk(sk); - if (tp->rx_opt.rcv_tsecr && - (TCP_SKB_CB(skb)->end_seq - - TCP_SKB_CB(skb)->seq >= inet_csk(sk)->icsk_ack.rcv_mss)) { + if (tp->rx_opt.rcv_tsecr == tp->rcv_rtt_last_tsecr) + return; + tp->rcv_rtt_last_tsecr = tp->rx_opt.rcv_tsecr; + + if (TCP_SKB_CB(skb)->end_seq - + TCP_SKB_CB(skb)->seq >= inet_csk(sk)->icsk_ack.rcv_mss) { u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr; u32 delta_us; @@ -5475,6 +5478,11 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb) tcp_ack(sk, skb, 0); __kfree_skb(skb); tcp_data_snd_check(sk); + /* When receiving pure ack in fast path, update + * last ts ecr directly instead of calling + * tcp_rcv_rtt_measure_ts() + */ + tp->rcv_rtt_last_tsecr = tp->rx_opt.rcv_tsecr; return; } else { /* Header too small */ TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); -- cgit v1.2.3 From cadefe5f584abaac40dce72009e4de738cbff467 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 20 Jun 2018 16:07:35 -0400 Subject: tcp_bbr: fix bbr pacing rate for internal pacing This commit makes BBR use only the MSS (without any headers) to calculate pacing rates when internal TCP-layer pacing is used. This is necessary to achieve the correct pacing behavior in this case, since tcp_internal_pacing() uses only the payload length to calculate pacing delays. Signed-off-by: Kevin Yang Signed-off-by: Eric Dumazet Reviewed-by: Neal Cardwell Signed-off-by: David S. Miller --- include/net/tcp.h | 11 +++++++++++ net/ipv4/tcp_bbr.c | 6 +++++- net/ipv4/tcp_output.c | 14 -------------- 3 files changed, 16 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 0448e7c5d2b4..822ee49ed0f9 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1184,6 +1184,17 @@ static inline bool tcp_is_cwnd_limited(const struct sock *sk) return tp->is_cwnd_limited; } +/* BBR congestion control needs pacing. + * Same remark for SO_MAX_PACING_RATE. + * sch_fq packet scheduler is efficiently handling pacing, + * but is not always installed/used. + * Return true if TCP stack should pace packets itself. + */ +static inline bool tcp_needs_internal_pacing(const struct sock *sk) +{ + return smp_load_acquire(&sk->sk_pacing_status) == SK_PACING_NEEDED; +} + /* Something is really bad, we could not queue an additional packet, * because qdisc is full or receiver sent a 0 window. * We do not want to add fuel to the fire, or abort too early, diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 58e2f479ffb4..3b5f45b9e81e 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -205,7 +205,11 @@ static u32 bbr_bw(const struct sock *sk) */ static u64 bbr_rate_bytes_per_sec(struct sock *sk, u64 rate, int gain) { - rate *= tcp_mss_to_mtu(sk, tcp_sk(sk)->mss_cache); + unsigned int mss = tcp_sk(sk)->mss_cache; + + if (!tcp_needs_internal_pacing(sk)) + mss = tcp_mss_to_mtu(sk, mss); + rate *= mss; rate *= gain; rate >>= BBR_SCALE; rate *= USEC_PER_SEC; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 8e08b409c71e..f8f6129160dd 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -973,17 +973,6 @@ enum hrtimer_restart tcp_pace_kick(struct hrtimer *timer) return HRTIMER_NORESTART; } -/* BBR congestion control needs pacing. - * Same remark for SO_MAX_PACING_RATE. - * sch_fq packet scheduler is efficiently handling pacing, - * but is not always installed/used. - * Return true if TCP stack should pace packets itself. - */ -static bool tcp_needs_internal_pacing(const struct sock *sk) -{ - return smp_load_acquire(&sk->sk_pacing_status) == SK_PACING_NEEDED; -} - static void tcp_internal_pacing(struct sock *sk, const struct sk_buff *skb) { u64 len_ns; @@ -995,9 +984,6 @@ static void tcp_internal_pacing(struct sock *sk, const struct sk_buff *skb) if (!rate || rate == ~0U) return; - /* Should account for header sizes as sch_fq does, - * but lets make things simple. - */ len_ns = (u64)skb->len * NSEC_PER_SEC; do_div(len_ns, rate); hrtimer_start(&tcp_sk(sk)->pacing_timer, -- cgit v1.2.3 From 372401efd9eeee24701848874ecb9845524013ee Mon Sep 17 00:00:00 2001 From: Jerome Brunet Date: Tue, 22 May 2018 18:34:56 +0200 Subject: dt-bindings: clock: add meson axg audio clock controller bindings Export the clock ids dt-bindings usable by the consumers of the clock controller and add the documentation for the device tree bindings of the audio clock controller of the A113 based SoCs. Acked-by: Neil Armstrong Reviewed-by: Rob Herring Signed-off-by: Jerome Brunet --- .../bindings/clock/amlogic,axg-audio-clkc.txt | 56 +++++++++++++ include/dt-bindings/clock/axg-audio-clkc.h | 94 ++++++++++++++++++++++ 2 files changed, 150 insertions(+) create mode 100644 Documentation/devicetree/bindings/clock/amlogic,axg-audio-clkc.txt create mode 100644 include/dt-bindings/clock/axg-audio-clkc.h (limited to 'include') diff --git a/Documentation/devicetree/bindings/clock/amlogic,axg-audio-clkc.txt b/Documentation/devicetree/bindings/clock/amlogic,axg-audio-clkc.txt new file mode 100644 index 000000000000..61777ad24f61 --- /dev/null +++ b/Documentation/devicetree/bindings/clock/amlogic,axg-audio-clkc.txt @@ -0,0 +1,56 @@ +* Amlogic AXG Audio Clock Controllers + +The Amlogic AXG audio clock controller generates and supplies clock to the +other elements of the audio subsystem, such as fifos, i2s, spdif and pdm +devices. + +Required Properties: + +- compatible : should be "amlogic,axg-audio-clkc" for the A113X and A113D +- reg : physical base address of the clock controller and length of + memory mapped region. +- clocks : a list of phandle + clock-specifier pairs for the clocks listed + in clock-names. +- clock-names : must contain the following: + * "pclk" - Main peripheral bus clock + may contain the following: + * "mst_in[0-7]" - 8 input plls to generate clock signals + * "slv_sclk[0-9]" - 10 slave bit clocks provided by external + components. + * "slv_lrclk[0-9]" - 10 slave sample clocks provided by external + components. +- resets : phandle of the internal reset line +- #clock-cells : should be 1. + +Each clock is assigned an identifier and client nodes can use this identifier +to specify the clock which they consume. All available clocks are defined as +preprocessor macros in the dt-bindings/clock/axg-audio-clkc.h header and can be +used in device tree sources. + +Example: + +clkc_audio: clock-controller@0 { + compatible = "amlogic,axg-audio-clkc"; + reg = <0x0 0x0 0x0 0xb4>; + #clock-cells = <1>; + + clocks = <&clkc CLKID_AUDIO>, + <&clkc CLKID_MPLL0>, + <&clkc CLKID_MPLL1>, + <&clkc CLKID_MPLL2>, + <&clkc CLKID_MPLL3>, + <&clkc CLKID_HIFI_PLL>, + <&clkc CLKID_FCLK_DIV3>, + <&clkc CLKID_FCLK_DIV4>, + <&clkc CLKID_GP0_PLL>; + clock-names = "pclk", + "mst_in0", + "mst_in1", + "mst_in2", + "mst_in3", + "mst_in4", + "mst_in5", + "mst_in6", + "mst_in7"; + resets = <&reset RESET_AUDIO>; +}; diff --git a/include/dt-bindings/clock/axg-audio-clkc.h b/include/dt-bindings/clock/axg-audio-clkc.h new file mode 100644 index 000000000000..fd9c362099d9 --- /dev/null +++ b/include/dt-bindings/clock/axg-audio-clkc.h @@ -0,0 +1,94 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */ +/* + * Copyright (c) 2018 Baylibre SAS. + * Author: Jerome Brunet + */ + +#ifndef __AXG_AUDIO_CLKC_BINDINGS_H +#define __AXG_AUDIO_CLKC_BINDINGS_H + +#define AUD_CLKID_SLV_SCLK0 9 +#define AUD_CLKID_SLV_SCLK1 10 +#define AUD_CLKID_SLV_SCLK2 11 +#define AUD_CLKID_SLV_SCLK3 12 +#define AUD_CLKID_SLV_SCLK4 13 +#define AUD_CLKID_SLV_SCLK5 14 +#define AUD_CLKID_SLV_SCLK6 15 +#define AUD_CLKID_SLV_SCLK7 16 +#define AUD_CLKID_SLV_SCLK8 17 +#define AUD_CLKID_SLV_SCLK9 18 +#define AUD_CLKID_SLV_LRCLK0 19 +#define AUD_CLKID_SLV_LRCLK1 20 +#define AUD_CLKID_SLV_LRCLK2 21 +#define AUD_CLKID_SLV_LRCLK3 22 +#define AUD_CLKID_SLV_LRCLK4 23 +#define AUD_CLKID_SLV_LRCLK5 24 +#define AUD_CLKID_SLV_LRCLK6 25 +#define AUD_CLKID_SLV_LRCLK7 26 +#define AUD_CLKID_SLV_LRCLK8 27 +#define AUD_CLKID_SLV_LRCLK9 28 +#define AUD_CLKID_DDR_ARB 29 +#define AUD_CLKID_PDM 30 +#define AUD_CLKID_TDMIN_A 31 +#define AUD_CLKID_TDMIN_B 32 +#define AUD_CLKID_TDMIN_C 33 +#define AUD_CLKID_TDMIN_LB 34 +#define AUD_CLKID_TDMOUT_A 35 +#define AUD_CLKID_TDMOUT_B 36 +#define AUD_CLKID_TDMOUT_C 37 +#define AUD_CLKID_FRDDR_A 38 +#define AUD_CLKID_FRDDR_B 39 +#define AUD_CLKID_FRDDR_C 40 +#define AUD_CLKID_TODDR_A 41 +#define AUD_CLKID_TODDR_B 42 +#define AUD_CLKID_TODDR_C 43 +#define AUD_CLKID_LOOPBACK 44 +#define AUD_CLKID_SPDIFIN 45 +#define AUD_CLKID_SPDIFOUT 46 +#define AUD_CLKID_RESAMPLE 47 +#define AUD_CLKID_POWER_DETECT 48 +#define AUD_CLKID_MST_A_MCLK 49 +#define AUD_CLKID_MST_B_MCLK 50 +#define AUD_CLKID_MST_C_MCLK 51 +#define AUD_CLKID_MST_D_MCLK 52 +#define AUD_CLKID_MST_E_MCLK 53 +#define AUD_CLKID_MST_F_MCLK 54 +#define AUD_CLKID_SPDIFOUT_CLK 55 +#define AUD_CLKID_SPDIFIN_CLK 56 +#define AUD_CLKID_PDM_DCLK 57 +#define AUD_CLKID_PDM_SYSCLK 58 +#define AUD_CLKID_MST_A_SCLK 79 +#define AUD_CLKID_MST_B_SCLK 80 +#define AUD_CLKID_MST_C_SCLK 81 +#define AUD_CLKID_MST_D_SCLK 82 +#define AUD_CLKID_MST_E_SCLK 83 +#define AUD_CLKID_MST_F_SCLK 84 +#define AUD_CLKID_MST_A_LRCLK 86 +#define AUD_CLKID_MST_B_LRCLK 87 +#define AUD_CLKID_MST_C_LRCLK 88 +#define AUD_CLKID_MST_D_LRCLK 89 +#define AUD_CLKID_MST_E_LRCLK 90 +#define AUD_CLKID_MST_F_LRCLK 91 +#define AUD_CLKID_TDMIN_A_SCLK_SEL 116 +#define AUD_CLKID_TDMIN_B_SCLK_SEL 117 +#define AUD_CLKID_TDMIN_C_SCLK_SEL 118 +#define AUD_CLKID_TDMIN_LB_SCLK_SEL 119 +#define AUD_CLKID_TDMOUT_A_SCLK_SEL 120 +#define AUD_CLKID_TDMOUT_B_SCLK_SEL 121 +#define AUD_CLKID_TDMOUT_C_SCLK_SEL 122 +#define AUD_CLKID_TDMIN_A_SCLK 123 +#define AUD_CLKID_TDMIN_B_SCLK 124 +#define AUD_CLKID_TDMIN_C_SCLK 125 +#define AUD_CLKID_TDMIN_LB_SCLK 126 +#define AUD_CLKID_TDMOUT_A_SCLK 127 +#define AUD_CLKID_TDMOUT_B_SCLK 128 +#define AUD_CLKID_TDMOUT_C_SCLK 129 +#define AUD_CLKID_TDMIN_A_LRCLK 130 +#define AUD_CLKID_TDMIN_B_LRCLK 131 +#define AUD_CLKID_TDMIN_C_LRCLK 132 +#define AUD_CLKID_TDMIN_LB_LRCLK 133 +#define AUD_CLKID_TDMOUT_A_LRCLK 134 +#define AUD_CLKID_TDMOUT_B_LRCLK 135 +#define AUD_CLKID_TDMOUT_C_LRCLK 136 + +#endif /* __AXG_AUDIO_CLKC_BINDINGS_H */ -- cgit v1.2.3 From d467239f37c4e49158e0569a26c6a9c365ec5b61 Mon Sep 17 00:00:00 2001 From: Michel Pollet Date: Thu, 14 Jun 2018 11:56:30 +0100 Subject: dt-bindings: clock: Add the r9a06g032-sysctrl.h file This adds the constants necessary to use the renesas,r9a06g032-sysctrl node. Signed-off-by: Michel Pollet Reviewed-by: Rob Herring Signed-off-by: Geert Uytterhoeven --- include/dt-bindings/clock/r9a06g032-sysctrl.h | 148 ++++++++++++++++++++++++++ 1 file changed, 148 insertions(+) create mode 100644 include/dt-bindings/clock/r9a06g032-sysctrl.h (limited to 'include') diff --git a/include/dt-bindings/clock/r9a06g032-sysctrl.h b/include/dt-bindings/clock/r9a06g032-sysctrl.h new file mode 100644 index 000000000000..90c0f3dc1ba1 --- /dev/null +++ b/include/dt-bindings/clock/r9a06g032-sysctrl.h @@ -0,0 +1,148 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * R9A06G032 sysctrl IDs + * + * Copyright (C) 2018 Renesas Electronics Europe Limited + * + * Michel Pollet , + */ + +#ifndef __DT_BINDINGS_R9A06G032_SYSCTRL_H__ +#define __DT_BINDINGS_R9A06G032_SYSCTRL_H__ + +#define R9A06G032_CLK_PLL_USB 1 +#define R9A06G032_CLK_48 1 /* AKA CLK_PLL_USB */ +#define R9A06G032_MSEBIS_CLK 3 /* AKA CLKOUT_D16 */ +#define R9A06G032_MSEBIM_CLK 3 /* AKA CLKOUT_D16 */ +#define R9A06G032_CLK_DDRPHY_PLLCLK 5 /* AKA CLKOUT_D1OR2 */ +#define R9A06G032_CLK50 6 /* AKA CLKOUT_D20 */ +#define R9A06G032_CLK25 7 /* AKA CLKOUT_D40 */ +#define R9A06G032_CLK125 9 /* AKA CLKOUT_D8 */ +#define R9A06G032_CLK_P5_PG1 17 /* AKA DIV_P5_PG */ +#define R9A06G032_CLK_REF_SYNC 21 /* AKA DIV_REF_SYNC */ +#define R9A06G032_CLK_25_PG4 26 +#define R9A06G032_CLK_25_PG5 27 +#define R9A06G032_CLK_25_PG6 28 +#define R9A06G032_CLK_25_PG7 29 +#define R9A06G032_CLK_25_PG8 30 +#define R9A06G032_CLK_ADC 31 +#define R9A06G032_CLK_ECAT100 32 +#define R9A06G032_CLK_HSR100 33 +#define R9A06G032_CLK_I2C0 34 +#define R9A06G032_CLK_I2C1 35 +#define R9A06G032_CLK_MII_REF 36 +#define R9A06G032_CLK_NAND 37 +#define R9A06G032_CLK_NOUSBP2_PG6 38 +#define R9A06G032_CLK_P1_PG2 39 +#define R9A06G032_CLK_P1_PG3 40 +#define R9A06G032_CLK_P1_PG4 41 +#define R9A06G032_CLK_P4_PG3 42 +#define R9A06G032_CLK_P4_PG4 43 +#define R9A06G032_CLK_P6_PG1 44 +#define R9A06G032_CLK_P6_PG2 45 +#define R9A06G032_CLK_P6_PG3 46 +#define R9A06G032_CLK_P6_PG4 47 +#define R9A06G032_CLK_PCI_USB 48 +#define R9A06G032_CLK_QSPI0 49 +#define R9A06G032_CLK_QSPI1 50 +#define R9A06G032_CLK_RGMII_REF 51 +#define R9A06G032_CLK_RMII_REF 52 +#define R9A06G032_CLK_SDIO0 53 +#define R9A06G032_CLK_SDIO1 54 +#define R9A06G032_CLK_SERCOS100 55 +#define R9A06G032_CLK_SLCD 56 +#define R9A06G032_CLK_SPI0 57 +#define R9A06G032_CLK_SPI1 58 +#define R9A06G032_CLK_SPI2 59 +#define R9A06G032_CLK_SPI3 60 +#define R9A06G032_CLK_SPI4 61 +#define R9A06G032_CLK_SPI5 62 +#define R9A06G032_CLK_SWITCH 63 +#define R9A06G032_HCLK_ECAT125 65 +#define R9A06G032_HCLK_PINCONFIG 66 +#define R9A06G032_HCLK_SERCOS 67 +#define R9A06G032_HCLK_SGPIO2 68 +#define R9A06G032_HCLK_SGPIO3 69 +#define R9A06G032_HCLK_SGPIO4 70 +#define R9A06G032_HCLK_TIMER0 71 +#define R9A06G032_HCLK_TIMER1 72 +#define R9A06G032_HCLK_USBF 73 +#define R9A06G032_HCLK_USBH 74 +#define R9A06G032_HCLK_USBPM 75 +#define R9A06G032_CLK_48_PG_F 76 +#define R9A06G032_CLK_48_PG4 77 +#define R9A06G032_CLK_DDRPHY_PCLK 81 /* AKA CLK_REF_SYNC_D4 */ +#define R9A06G032_CLK_FW 81 /* AKA CLK_REF_SYNC_D4 */ +#define R9A06G032_CLK_CRYPTO 81 /* AKA CLK_REF_SYNC_D4 */ +#define R9A06G032_CLK_A7MP 84 /* AKA DIV_CA7 */ +#define R9A06G032_HCLK_CAN0 85 +#define R9A06G032_HCLK_CAN1 86 +#define R9A06G032_HCLK_DELTASIGMA 87 +#define R9A06G032_HCLK_PWMPTO 88 +#define R9A06G032_HCLK_RSV 89 +#define R9A06G032_HCLK_SGPIO0 90 +#define R9A06G032_HCLK_SGPIO1 91 +#define R9A06G032_RTOS_MDC 92 +#define R9A06G032_CLK_CM3 93 +#define R9A06G032_CLK_DDRC 94 +#define R9A06G032_CLK_ECAT25 95 +#define R9A06G032_CLK_HSR50 96 +#define R9A06G032_CLK_HW_RTOS 97 +#define R9A06G032_CLK_SERCOS50 98 +#define R9A06G032_HCLK_ADC 99 +#define R9A06G032_HCLK_CM3 100 +#define R9A06G032_HCLK_CRYPTO_EIP150 101 +#define R9A06G032_HCLK_CRYPTO_EIP93 102 +#define R9A06G032_HCLK_DDRC 103 +#define R9A06G032_HCLK_DMA0 104 +#define R9A06G032_HCLK_DMA1 105 +#define R9A06G032_HCLK_GMAC0 106 +#define R9A06G032_HCLK_GMAC1 107 +#define R9A06G032_HCLK_GPIO0 108 +#define R9A06G032_HCLK_GPIO1 109 +#define R9A06G032_HCLK_GPIO2 110 +#define R9A06G032_HCLK_HSR 111 +#define R9A06G032_HCLK_I2C0 112 +#define R9A06G032_HCLK_I2C1 113 +#define R9A06G032_HCLK_LCD 114 +#define R9A06G032_HCLK_MSEBI_M 115 +#define R9A06G032_HCLK_MSEBI_S 116 +#define R9A06G032_HCLK_NAND 117 +#define R9A06G032_HCLK_PG_I 118 +#define R9A06G032_HCLK_PG19 119 +#define R9A06G032_HCLK_PG20 120 +#define R9A06G032_HCLK_PG3 121 +#define R9A06G032_HCLK_PG4 122 +#define R9A06G032_HCLK_QSPI0 123 +#define R9A06G032_HCLK_QSPI1 124 +#define R9A06G032_HCLK_ROM 125 +#define R9A06G032_HCLK_RTC 126 +#define R9A06G032_HCLK_SDIO0 127 +#define R9A06G032_HCLK_SDIO1 128 +#define R9A06G032_HCLK_SEMAP 129 +#define R9A06G032_HCLK_SPI0 130 +#define R9A06G032_HCLK_SPI1 131 +#define R9A06G032_HCLK_SPI2 132 +#define R9A06G032_HCLK_SPI3 133 +#define R9A06G032_HCLK_SPI4 134 +#define R9A06G032_HCLK_SPI5 135 +#define R9A06G032_HCLK_SWITCH 136 +#define R9A06G032_HCLK_SWITCH_RG 137 +#define R9A06G032_HCLK_UART0 138 +#define R9A06G032_HCLK_UART1 139 +#define R9A06G032_HCLK_UART2 140 +#define R9A06G032_HCLK_UART3 141 +#define R9A06G032_HCLK_UART4 142 +#define R9A06G032_HCLK_UART5 143 +#define R9A06G032_HCLK_UART6 144 +#define R9A06G032_HCLK_UART7 145 +#define R9A06G032_CLK_UART0 146 +#define R9A06G032_CLK_UART1 147 +#define R9A06G032_CLK_UART2 148 +#define R9A06G032_CLK_UART3 149 +#define R9A06G032_CLK_UART4 150 +#define R9A06G032_CLK_UART5 151 +#define R9A06G032_CLK_UART6 152 +#define R9A06G032_CLK_UART7 153 + +#endif /* __DT_BINDINGS_R9A06G032_SYSCTRL_H__ */ -- cgit v1.2.3 From f4c277b817cc9489fffabffb4e15d2f3b686056c Mon Sep 17 00:00:00 2001 From: Jiada Wang Date: Wed, 20 Jun 2018 18:25:20 +0900 Subject: ASoC: soc-pcm: DPCM cares BE channel constraint Current DPCM is caring only FE channel configuration. Sometimes it will be trouble if user selects channel which isn't supported by BE. This patch adds new .dpcm_merged_chan on struct snd_soc_dai_link. DPCM will use FE / BE merged channel if struct snd_soc_dai_link has it. Signed-off-by: Jiada Wang Signed-off-by: Mark Brown --- include/sound/soc.h | 2 ++ sound/soc/soc-pcm.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 48 insertions(+) (limited to 'include') diff --git a/include/sound/soc.h b/include/sound/soc.h index 1378dcd2128a..f7579f82cc00 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -957,6 +957,8 @@ struct snd_soc_dai_link { /* DPCM used FE & BE merged format */ unsigned int dpcm_merged_format:1; + /* DPCM used FE & BE merged channel */ + unsigned int dpcm_merged_chan:1; /* pmdown_time is ignored at stop */ unsigned int ignore_pmdown_time:1; diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index 45b52f7b9690..19ebfc958b9d 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -1715,6 +1715,46 @@ static u64 dpcm_runtime_base_format(struct snd_pcm_substream *substream) return formats; } +static void dpcm_runtime_base_chan(struct snd_pcm_substream *substream, + unsigned int *channels_min, + unsigned int *channels_max) +{ + struct snd_soc_pcm_runtime *fe = substream->private_data; + struct snd_soc_dpcm *dpcm; + int stream = substream->stream; + + if (!fe->dai_link->dpcm_merged_chan) + return; + + *channels_min = 0; + *channels_max = UINT_MAX; + + /* + * It returns merged BE codec channel; + * if FE want to use it (= dpcm_merged_chan) + */ + + list_for_each_entry(dpcm, &fe->dpcm[stream].be_clients, list_be) { + struct snd_soc_pcm_runtime *be = dpcm->be; + struct snd_soc_dai_driver *codec_dai_drv; + struct snd_soc_pcm_stream *codec_stream; + int i; + + for (i = 0; i < be->num_codecs; i++) { + codec_dai_drv = be->codec_dais[i]->driver; + if (stream == SNDRV_PCM_STREAM_PLAYBACK) + codec_stream = &codec_dai_drv->playback; + else + codec_stream = &codec_dai_drv->capture; + + *channels_min = max(*channels_min, + codec_stream->channels_min); + *channels_max = min(*channels_max, + codec_stream->channels_max); + } + } +} + static void dpcm_set_fe_runtime(struct snd_pcm_substream *substream) { struct snd_pcm_runtime *runtime = substream->runtime; @@ -1722,11 +1762,17 @@ static void dpcm_set_fe_runtime(struct snd_pcm_substream *substream) struct snd_soc_dai *cpu_dai = rtd->cpu_dai; struct snd_soc_dai_driver *cpu_dai_drv = cpu_dai->driver; u64 format = dpcm_runtime_base_format(substream); + unsigned int channels_min = 0, channels_max = UINT_MAX; if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) dpcm_init_runtime_hw(runtime, &cpu_dai_drv->playback, format); else dpcm_init_runtime_hw(runtime, &cpu_dai_drv->capture, format); + + dpcm_runtime_base_chan(substream, &channels_min, &channels_max); + + runtime->hw.channels_min = max(channels_min, runtime->hw.channels_min); + runtime->hw.channels_max = min(channels_max, runtime->hw.channels_max); } static int dpcm_fe_dai_do_trigger(struct snd_pcm_substream *substream, int cmd); -- cgit v1.2.3 From 30c217ef6411d24b8c8b0478b89335dc2dabe6e8 Mon Sep 17 00:00:00 2001 From: Antoine Tenart Date: Tue, 29 May 2018 14:13:45 +0200 Subject: crypto: sha512_generic - add a sha512 0-length pre-computed hash This patch adds the sha512 pre-computed 0-length hash so that device drivers can use it when an hardware engine does not support computing a hash from a 0 length input. Signed-off-by: Antoine Tenart Signed-off-by: Herbert Xu --- crypto/sha512_generic.c | 12 ++++++++++++ include/crypto/sha.h | 2 ++ 2 files changed, 14 insertions(+) (limited to 'include') diff --git a/crypto/sha512_generic.c b/crypto/sha512_generic.c index eba965d18bfc..439723d9273e 100644 --- a/crypto/sha512_generic.c +++ b/crypto/sha512_generic.c @@ -23,6 +23,18 @@ #include #include +const u8 sha512_zero_message_hash[SHA512_DIGEST_SIZE] = { + 0xcf, 0x83, 0xe1, 0x35, 0x7e, 0xef, 0xb8, 0xbd, + 0xf1, 0x54, 0x28, 0x50, 0xd6, 0x6d, 0x80, 0x07, + 0xd6, 0x20, 0xe4, 0x05, 0x0b, 0x57, 0x15, 0xdc, + 0x83, 0xf4, 0xa9, 0x21, 0xd3, 0x6c, 0xe9, 0xce, + 0x47, 0xd0, 0xd1, 0x3c, 0x5d, 0x85, 0xf2, 0xb0, + 0xff, 0x83, 0x18, 0xd2, 0x87, 0x7e, 0xec, 0x2f, + 0x63, 0xb9, 0x31, 0xbd, 0x47, 0x41, 0x7a, 0x81, + 0xa5, 0x38, 0x32, 0x7a, 0xf9, 0x27, 0xda, 0x3e +}; +EXPORT_SYMBOL_GPL(sha512_zero_message_hash); + static inline u64 Ch(u64 x, u64 y, u64 z) { return z ^ (x & (y ^ z)); diff --git a/include/crypto/sha.h b/include/crypto/sha.h index 0555b571dd34..799f071b93df 100644 --- a/include/crypto/sha.h +++ b/include/crypto/sha.h @@ -71,6 +71,8 @@ extern const u8 sha224_zero_message_hash[SHA224_DIGEST_SIZE]; extern const u8 sha256_zero_message_hash[SHA256_DIGEST_SIZE]; +extern const u8 sha512_zero_message_hash[SHA512_DIGEST_SIZE]; + struct sha1_state { u32 state[SHA1_DIGEST_SIZE / 4]; u64 count; -- cgit v1.2.3 From 26f7120b86a964a886ececb9eb8e6dd50276dbb2 Mon Sep 17 00:00:00 2001 From: Antoine Tenart Date: Tue, 29 May 2018 14:13:49 +0200 Subject: crypto: sha512_generic - add a sha384 0-length pre-computed hash This patch adds the sha384 pre-computed 0-length hash so that device drivers can use it when an hardware engine does not support computing a hash from a 0 length input. Signed-off-by: Antoine Tenart Signed-off-by: Herbert Xu --- crypto/sha512_generic.c | 10 ++++++++++ include/crypto/sha.h | 2 ++ 2 files changed, 12 insertions(+) (limited to 'include') diff --git a/crypto/sha512_generic.c b/crypto/sha512_generic.c index 439723d9273e..0b805d03b5e5 100644 --- a/crypto/sha512_generic.c +++ b/crypto/sha512_generic.c @@ -23,6 +23,16 @@ #include #include +const u8 sha384_zero_message_hash[SHA384_DIGEST_SIZE] = { + 0x38, 0xb0, 0x60, 0xa7, 0x51, 0xac, 0x96, 0x38, + 0x4c, 0xd9, 0x32, 0x7e, 0xb1, 0xb1, 0xe3, 0x6a, + 0x21, 0xfd, 0xb7, 0x11, 0x14, 0xbe, 0x07, 0x43, + 0x4c, 0x0c, 0xc7, 0xbf, 0x63, 0xf6, 0xe1, 0xda, + 0x27, 0x4e, 0xde, 0xbf, 0xe7, 0x6f, 0x65, 0xfb, + 0xd5, 0x1a, 0xd2, 0xf1, 0x48, 0x98, 0xb9, 0x5b +}; +EXPORT_SYMBOL_GPL(sha384_zero_message_hash); + const u8 sha512_zero_message_hash[SHA512_DIGEST_SIZE] = { 0xcf, 0x83, 0xe1, 0x35, 0x7e, 0xef, 0xb8, 0xbd, 0xf1, 0x54, 0x28, 0x50, 0xd6, 0x6d, 0x80, 0x07, diff --git a/include/crypto/sha.h b/include/crypto/sha.h index 799f071b93df..8a46202b1857 100644 --- a/include/crypto/sha.h +++ b/include/crypto/sha.h @@ -71,6 +71,8 @@ extern const u8 sha224_zero_message_hash[SHA224_DIGEST_SIZE]; extern const u8 sha256_zero_message_hash[SHA256_DIGEST_SIZE]; +extern const u8 sha384_zero_message_hash[SHA384_DIGEST_SIZE]; + extern const u8 sha512_zero_message_hash[SHA512_DIGEST_SIZE]; struct sha1_state { -- cgit v1.2.3 From 46d8f405e16cdc47962edbe7771246c8d5b8c795 Mon Sep 17 00:00:00 2001 From: Eric Anholt Date: Thu, 21 Jun 2018 12:54:28 -0700 Subject: drm: Consider drivers setting DRIVER_ATOMIC as atomic. Drivers such as vc4 don't initialize mode_config.funcs until later in initialization, but we know they're atomic since they've got the flag set. This avoids oopsing on dereferencing funcs in the new atomic methods sanity checks. I moved the atomic check function down below the core flag check, to avoid needing a prototype. Signed-off-by: Eric Anholt Fixes: ba1f665f161c ("drm: Add checks for atomic_[duplicate/destroy]_state with atomic drivers") Link: https://patchwork.freedesktop.org/patch/msgid/20180621195428.17447-1-eric@anholt.net Reviewed-by: Daniel Vetter --- include/drm/drmP.h | 23 ++++++++++++----------- 1 file changed, 12 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/drm/drmP.h b/include/drm/drmP.h index f5099c12c6a6..c5dfbdb7271d 100644 --- a/include/drm/drmP.h +++ b/include/drm/drmP.h @@ -97,6 +97,16 @@ struct pci_controller; #define DRM_IF_VERSION(maj, min) (maj << 16 | min) +#define DRM_SWITCH_POWER_ON 0 +#define DRM_SWITCH_POWER_OFF 1 +#define DRM_SWITCH_POWER_CHANGING 2 +#define DRM_SWITCH_POWER_DYNAMIC_OFF 3 + +static inline bool drm_core_check_feature(struct drm_device *dev, int feature) +{ + return dev->driver->driver_features & feature; +} + /** * drm_drv_uses_atomic_modeset - check if the driver implements * atomic_commit() @@ -107,17 +117,8 @@ struct pci_controller; */ static inline bool drm_drv_uses_atomic_modeset(struct drm_device *dev) { - return dev->mode_config.funcs->atomic_commit != NULL; -} - -#define DRM_SWITCH_POWER_ON 0 -#define DRM_SWITCH_POWER_OFF 1 -#define DRM_SWITCH_POWER_CHANGING 2 -#define DRM_SWITCH_POWER_DYNAMIC_OFF 3 - -static inline bool drm_core_check_feature(struct drm_device *dev, int feature) -{ - return dev->driver->driver_features & feature; + return drm_core_check_feature(dev, DRIVER_ATOMIC) || + dev->mode_config.funcs->atomic_commit != NULL; } /* returns true if currently okay to sleep */ -- cgit v1.2.3 From 5424ea27390f1f8903e5de0eaa0c5b561e8e877a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 22 Jun 2018 16:27:47 -0700 Subject: netns: get more entropy from net_hash_mix() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit struct net are effectively allocated from order-1 pages on x86, with one object per slab, meaning that the 13 low order bits of their addresses are zero. Once shifted by L1_CACHE_SHIFT, this leaves 7 zero-bits, meaning that net_hash_mix() does not help spreading objects on various hash tables. For example, TCP listen table has 32 buckets, meaning that all netns use the same bucket for port 80 or port 443. Signed-off-by: Eric Dumazet Reported-by: Maciej Żenczykowski Signed-off-by: David S. Miller --- include/net/netns/hash.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/netns/hash.h b/include/net/netns/hash.h index 24c78183a4c2..16a842456189 100644 --- a/include/net/netns/hash.h +++ b/include/net/netns/hash.h @@ -9,12 +9,7 @@ struct net; static inline u32 net_hash_mix(const struct net *net) { #ifdef CONFIG_NET_NS - /* - * shift this right to eliminate bits, that are - * always zeroed - */ - - return (u32)(((unsigned long)net) >> L1_CACHE_SHIFT); + return (u32)(((unsigned long)net) >> ilog2(sizeof(*net))); #else return 0; #endif -- cgit v1.2.3 From 9b42c1f179a614e11893ae4619f0304a38f481ae Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Tue, 12 Jun 2018 12:44:26 +0200 Subject: xfrm: Extend the output_mark to support input direction and masking. We already support setting an output mark at the xfrm_state, unfortunately this does not support the input direction and masking the marks that will be applied to the skb. This change adds support applying a masked value in both directions. The existing XFRMA_OUTPUT_MARK number is reused for this purpose and as it is now bi-directional, it is renamed to XFRMA_SET_MARK. An additional XFRMA_SET_MARK_MASK attribute is added for setting the mask. If the attribute mask not provided, it is set to 0xffffffff, keeping the XFRMA_OUTPUT_MARK existing 'full mask' semantics. Co-developed-by: Tobias Brunner Co-developed-by: Eyal Birger Co-developed-by: Lorenzo Colitti Signed-off-by: Steffen Klassert Signed-off-by: Tobias Brunner Signed-off-by: Eyal Birger Signed-off-by: Lorenzo Colitti --- include/net/xfrm.h | 9 ++++++++- include/uapi/linux/xfrm.h | 4 +++- net/xfrm/xfrm_device.c | 3 ++- net/xfrm/xfrm_input.c | 2 ++ net/xfrm/xfrm_output.c | 3 +-- net/xfrm/xfrm_policy.c | 5 +++-- net/xfrm/xfrm_user.c | 48 +++++++++++++++++++++++++++++++++++++---------- 7 files changed, 57 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 557122846e0e..3dc83ba26f62 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -166,7 +166,7 @@ struct xfrm_state { int header_len; int trailer_len; u32 extra_flags; - u32 output_mark; + struct xfrm_mark smark; } props; struct xfrm_lifetime_cfg lft; @@ -2012,6 +2012,13 @@ static inline int xfrm_mark_put(struct sk_buff *skb, const struct xfrm_mark *m) return ret; } +static inline __u32 xfrm_smark_get(__u32 mark, struct xfrm_state *x) +{ + struct xfrm_mark *m = &x->props.smark; + + return (m->v & m->m) | (mark & ~m->m); +} + static inline int xfrm_tunnel_check(struct sk_buff *skb, struct xfrm_state *x, unsigned int family) { diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h index e3af2859188b..5a6ed7ce5a29 100644 --- a/include/uapi/linux/xfrm.h +++ b/include/uapi/linux/xfrm.h @@ -305,9 +305,11 @@ enum xfrm_attr_type_t { XFRMA_ADDRESS_FILTER, /* struct xfrm_address_filter */ XFRMA_PAD, XFRMA_OFFLOAD_DEV, /* struct xfrm_state_offload */ - XFRMA_OUTPUT_MARK, /* __u32 */ + XFRMA_SET_MARK, /* __u32 */ + XFRMA_SET_MARK_MASK, /* __u32 */ __XFRMA_MAX +#define XFRMA_OUTPUT_MARK XFRMA_SET_MARK /* Compatibility */ #define XFRMA_MAX (__XFRMA_MAX - 1) }; diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 175941e15a6e..16c1230d20fa 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -162,7 +162,8 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, } dst = __xfrm_dst_lookup(net, 0, 0, saddr, daddr, - x->props.family, x->props.output_mark); + x->props.family, + xfrm_smark_get(0, x)); if (IS_ERR(dst)) return 0; diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 352abca2605f..074810436242 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -339,6 +339,8 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) goto drop; } + skb->mark = xfrm_smark_get(skb->mark, x); + skb->sp->xvec[skb->sp->len++] = x; lock: diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 89b178a78dc7..45ba07ab3e4f 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -66,8 +66,7 @@ static int xfrm_output_one(struct sk_buff *skb, int err) goto error_nolock; } - if (x->props.output_mark) - skb->mark = x->props.output_mark; + skb->mark = xfrm_smark_get(skb->mark, x); err = x->outer_mode->output(x, skb); if (err) { diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 5f48251c1319..7637637717ec 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1607,10 +1607,11 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, dst_copy_metrics(dst1, dst); if (xfrm[i]->props.mode != XFRM_MODE_TRANSPORT) { + __u32 mark = xfrm_smark_get(fl->flowi_mark, xfrm[i]); + family = xfrm[i]->props.family; dst = xfrm_dst_lookup(xfrm[i], tos, fl->flowi_oif, - &saddr, &daddr, family, - xfrm[i]->props.output_mark); + &saddr, &daddr, family, mark); err = PTR_ERR(dst); if (IS_ERR(dst)) goto put_states; diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 080035f056d9..9602cc9e05ab 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -527,6 +527,19 @@ static void xfrm_update_ae_params(struct xfrm_state *x, struct nlattr **attrs, x->replay_maxdiff = nla_get_u32(rt); } +static void xfrm_smark_init(struct nlattr **attrs, struct xfrm_mark *m) +{ + if (attrs[XFRMA_SET_MARK]) { + m->v = nla_get_u32(attrs[XFRMA_SET_MARK]); + if (attrs[XFRMA_SET_MARK_MASK]) + m->m = nla_get_u32(attrs[XFRMA_SET_MARK_MASK]); + else + m->m = 0xffffffff; + } else { + m->v = m->m = 0; + } +} + static struct xfrm_state *xfrm_state_construct(struct net *net, struct xfrm_usersa_info *p, struct nlattr **attrs, @@ -579,8 +592,7 @@ static struct xfrm_state *xfrm_state_construct(struct net *net, xfrm_mark_get(attrs, &x->mark); - if (attrs[XFRMA_OUTPUT_MARK]) - x->props.output_mark = nla_get_u32(attrs[XFRMA_OUTPUT_MARK]); + xfrm_smark_init(attrs, &x->props.smark); err = __xfrm_init_state(x, false, attrs[XFRMA_OFFLOAD_DEV]); if (err) @@ -824,6 +836,18 @@ static int copy_to_user_auth(struct xfrm_algo_auth *auth, struct sk_buff *skb) return 0; } +static int xfrm_smark_put(struct sk_buff *skb, struct xfrm_mark *m) +{ + int ret = 0; + + if (m->v | m->m) { + ret = nla_put_u32(skb, XFRMA_SET_MARK, m->v); + if (!ret) + ret = nla_put_u32(skb, XFRMA_SET_MARK_MASK, m->m); + } + return ret; +} + /* Don't change this without updating xfrm_sa_len! */ static int copy_to_user_state_extra(struct xfrm_state *x, struct xfrm_usersa_info *p, @@ -887,6 +911,11 @@ static int copy_to_user_state_extra(struct xfrm_state *x, ret = xfrm_mark_put(skb, &x->mark); if (ret) goto out; + + ret = xfrm_smark_put(skb, &x->props.smark); + if (ret) + goto out; + if (x->replay_esn) ret = nla_put(skb, XFRMA_REPLAY_ESN_VAL, xfrm_replay_state_esn_len(x->replay_esn), @@ -900,11 +929,7 @@ static int copy_to_user_state_extra(struct xfrm_state *x, ret = copy_user_offload(&x->xso, skb); if (ret) goto out; - if (x->props.output_mark) { - ret = nla_put_u32(skb, XFRMA_OUTPUT_MARK, x->props.output_mark); - if (ret) - goto out; - } + if (x->security) ret = copy_sec_ctx(x->security, skb); out: @@ -2493,7 +2518,8 @@ static const struct nla_policy xfrma_policy[XFRMA_MAX+1] = { [XFRMA_PROTO] = { .type = NLA_U8 }, [XFRMA_ADDRESS_FILTER] = { .len = sizeof(struct xfrm_address_filter) }, [XFRMA_OFFLOAD_DEV] = { .len = sizeof(struct xfrm_user_offload) }, - [XFRMA_OUTPUT_MARK] = { .type = NLA_U32 }, + [XFRMA_SET_MARK] = { .type = NLA_U32 }, + [XFRMA_SET_MARK_MASK] = { .type = NLA_U32 }, }; static const struct nla_policy xfrma_spd_policy[XFRMA_SPD_MAX+1] = { @@ -2719,8 +2745,10 @@ static inline unsigned int xfrm_sa_len(struct xfrm_state *x) l += nla_total_size(sizeof(x->props.extra_flags)); if (x->xso.dev) l += nla_total_size(sizeof(x->xso)); - if (x->props.output_mark) - l += nla_total_size(sizeof(x->props.output_mark)); + if (x->props.smark.v | x->props.smark.m) { + l += nla_total_size(sizeof(x->props.smark.v)); + l += nla_total_size(sizeof(x->props.smark.m)); + } /* Must count x->lastused as it may become non-zero behind our back. */ l += nla_total_size_64bit(sizeof(u64)); -- cgit v1.2.3 From d159ce7957eec306eacda672e5909e26675ca8ef Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Tue, 12 Jun 2018 14:06:57 +0200 Subject: flow: Extend flow informations with xfrm interface id. Add a new flowi_xfrm structure with informations needed to do a xfrm lookup. At the moment it keeps the informations about the new xfrm interface id needed to lookup xfrm interfaces that are introduced with a followup patch. We need this new lookup key as other possible keys, like the ifindex is already part of the xfrm selector and used as a key to enforce the output device after the transformation in the policy/state lookup. Signed-off-by: Steffen Klassert Acked-by: Shannon Nelson Acked-by: Benedict Wong Tested-by: Benedict Wong Tested-by: Antony Antony Reviewed-by: Eyal Birger --- include/net/flow.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/net/flow.h b/include/net/flow.h index 8ce21793094e..187c9bef672f 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -26,6 +26,10 @@ struct flowi_tunnel { __be64 tun_id; }; +struct flowi_xfrm { + __u32 if_id; +}; + struct flowi_common { int flowic_oif; int flowic_iif; @@ -39,6 +43,7 @@ struct flowi_common { #define FLOWI_FLAG_SKIP_NH_OIF 0x04 __u32 flowic_secid; struct flowi_tunnel flowic_tun_key; + struct flowi_xfrm xfrm; kuid_t flowic_uid; }; @@ -78,6 +83,7 @@ struct flowi4 { #define flowi4_secid __fl_common.flowic_secid #define flowi4_tun_key __fl_common.flowic_tun_key #define flowi4_uid __fl_common.flowic_uid +#define flowi4_xfrm __fl_common.xfrm /* (saddr,daddr) must be grouped, same order as in IP header */ __be32 saddr; @@ -109,6 +115,7 @@ static inline void flowi4_init_output(struct flowi4 *fl4, int oif, fl4->flowi4_flags = flags; fl4->flowi4_secid = 0; fl4->flowi4_tun_key.tun_id = 0; + fl4->flowi4_xfrm.if_id = 0; fl4->flowi4_uid = uid; fl4->daddr = daddr; fl4->saddr = saddr; @@ -138,6 +145,7 @@ struct flowi6 { #define flowi6_secid __fl_common.flowic_secid #define flowi6_tun_key __fl_common.flowic_tun_key #define flowi6_uid __fl_common.flowic_uid +#define flowi6_xfrm __fl_common.xfrm struct in6_addr daddr; struct in6_addr saddr; /* Note: flowi6_tos is encoded in flowlabel, too. */ @@ -185,6 +193,7 @@ struct flowi { #define flowi_secid u.__fl_common.flowic_secid #define flowi_tun_key u.__fl_common.flowic_tun_key #define flowi_uid u.__fl_common.flowic_uid +#define flowi_xfrm u.__fl_common.xfrm } __attribute__((__aligned__(BITS_PER_LONG/8))); static inline struct flowi *flowi4_to_flowi(struct flowi4 *fl4) -- cgit v1.2.3 From 7e6526404adedf079279aa7aa11722deaca8fe2e Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Tue, 12 Jun 2018 14:07:07 +0200 Subject: xfrm: Add a new lookup key to match xfrm interfaces. This patch adds the xfrm interface id as a lookup key for xfrm states and policies. With this we can assign states and policies to virtual xfrm interfaces. Signed-off-by: Steffen Klassert Acked-by: Shannon Nelson Acked-by: Benedict Wong Tested-by: Benedict Wong Tested-by: Antony Antony Reviewed-by: Eyal Birger --- include/net/xfrm.h | 21 +++++++++++++----- include/uapi/linux/xfrm.h | 1 + net/core/pktgen.c | 2 +- net/key/af_key.c | 6 +++--- net/xfrm/xfrm_policy.c | 18 +++++++++++----- net/xfrm/xfrm_state.c | 19 ++++++++++++----- net/xfrm/xfrm_user.c | 54 +++++++++++++++++++++++++++++++++++++++++------ 7 files changed, 96 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 3dc83ba26f62..e8bada4d2a45 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -147,6 +147,7 @@ struct xfrm_state { struct xfrm_id id; struct xfrm_selector sel; struct xfrm_mark mark; + u32 if_id; u32 tfcpad; u32 genid; @@ -574,6 +575,7 @@ struct xfrm_policy { atomic_t genid; u32 priority; u32 index; + u32 if_id; struct xfrm_mark mark; struct xfrm_selector selector; struct xfrm_lifetime_cfg lft; @@ -1533,7 +1535,7 @@ struct xfrm_state *xfrm_state_find(const xfrm_address_t *daddr, struct xfrm_tmpl *tmpl, struct xfrm_policy *pol, int *err, unsigned short family); -struct xfrm_state *xfrm_stateonly_find(struct net *net, u32 mark, +struct xfrm_state *xfrm_stateonly_find(struct net *net, u32 mark, u32 if_id, xfrm_address_t *daddr, xfrm_address_t *saddr, unsigned short family, @@ -1690,20 +1692,20 @@ int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk, void *); void xfrm_policy_walk_done(struct xfrm_policy_walk *walk, struct net *net); int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl); -struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, +struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id, u8 type, int dir, struct xfrm_selector *sel, struct xfrm_sec_ctx *ctx, int delete, int *err); -struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8, int dir, - u32 id, int delete, int *err); +struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u32 if_id, u8, + int dir, u32 id, int delete, int *err); int xfrm_policy_flush(struct net *net, u8 type, bool task_valid); void xfrm_policy_hash_rebuild(struct net *net); u32 xfrm_get_acqseq(void); int verify_spi_info(u8 proto, u32 min, u32 max); int xfrm_alloc_spi(struct xfrm_state *x, u32 minspi, u32 maxspi); struct xfrm_state *xfrm_find_acq(struct net *net, const struct xfrm_mark *mark, - u8 mode, u32 reqid, u8 proto, + u8 mode, u32 reqid, u32 if_id, u8 proto, const xfrm_address_t *daddr, const xfrm_address_t *saddr, int create, unsigned short family); @@ -2019,6 +2021,15 @@ static inline __u32 xfrm_smark_get(__u32 mark, struct xfrm_state *x) return (m->v & m->m) | (mark & ~m->m); } +static inline int xfrm_if_id_put(struct sk_buff *skb, __u32 if_id) +{ + int ret = 0; + + if (if_id) + ret = nla_put_u32(skb, XFRMA_IF_ID, if_id); + return ret; +} + static inline int xfrm_tunnel_check(struct sk_buff *skb, struct xfrm_state *x, unsigned int family) { diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h index 5a6ed7ce5a29..5f3b9fec7b5f 100644 --- a/include/uapi/linux/xfrm.h +++ b/include/uapi/linux/xfrm.h @@ -307,6 +307,7 @@ enum xfrm_attr_type_t { XFRMA_OFFLOAD_DEV, /* struct xfrm_state_offload */ XFRMA_SET_MARK, /* __u32 */ XFRMA_SET_MARK_MASK, /* __u32 */ + XFRMA_IF_ID, /* __u32 */ __XFRMA_MAX #define XFRMA_OUTPUT_MARK XFRMA_SET_MARK /* Compatibility */ diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 49368e21d228..6d37dbf0aa64 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -2255,7 +2255,7 @@ static void get_ipsec_sa(struct pktgen_dev *pkt_dev, int flow) x = xfrm_state_lookup_byspi(pn->net, htonl(pkt_dev->spi), AF_INET); } else { /* slow path: we dont already have xfrm_state */ - x = xfrm_stateonly_find(pn->net, DUMMY_MARK, + x = xfrm_stateonly_find(pn->net, DUMMY_MARK, 0, (xfrm_address_t *)&pkt_dev->cur_daddr, (xfrm_address_t *)&pkt_dev->cur_saddr, AF_INET, diff --git a/net/key/af_key.c b/net/key/af_key.c index 8bdc1cbe490a..398ebcd614a0 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1383,7 +1383,7 @@ static int pfkey_getspi(struct sock *sk, struct sk_buff *skb, const struct sadb_ } if (!x) - x = xfrm_find_acq(net, &dummy_mark, mode, reqid, proto, xdaddr, xsaddr, 1, family); + x = xfrm_find_acq(net, &dummy_mark, mode, reqid, 0, proto, xdaddr, xsaddr, 1, family); if (x == NULL) return -ENOENT; @@ -2414,7 +2414,7 @@ static int pfkey_spddelete(struct sock *sk, struct sk_buff *skb, const struct sa return err; } - xp = xfrm_policy_bysel_ctx(net, DUMMY_MARK, XFRM_POLICY_TYPE_MAIN, + xp = xfrm_policy_bysel_ctx(net, DUMMY_MARK, 0, XFRM_POLICY_TYPE_MAIN, pol->sadb_x_policy_dir - 1, &sel, pol_ctx, 1, &err); security_xfrm_policy_free(pol_ctx); @@ -2663,7 +2663,7 @@ static int pfkey_spdget(struct sock *sk, struct sk_buff *skb, const struct sadb_ return -EINVAL; delete = (hdr->sadb_msg_type == SADB_X_SPDDELETE2); - xp = xfrm_policy_byid(net, DUMMY_MARK, XFRM_POLICY_TYPE_MAIN, + xp = xfrm_policy_byid(net, DUMMY_MARK, 0, XFRM_POLICY_TYPE_MAIN, dir, pol->sadb_x_policy_id, delete, &err); if (xp == NULL) return -ENOENT; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 7637637717ec..fc0c69312b2c 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -747,6 +747,7 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) newpos = NULL; hlist_for_each_entry(pol, chain, bydst) { if (pol->type == policy->type && + pol->if_id == policy->if_id && !selector_cmp(&pol->selector, &policy->selector) && xfrm_policy_mark_match(policy, pol) && xfrm_sec_ctx_match(pol->security, policy->security) && @@ -798,8 +799,9 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) } EXPORT_SYMBOL(xfrm_policy_insert); -struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u8 type, - int dir, struct xfrm_selector *sel, +struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id, + u8 type, int dir, + struct xfrm_selector *sel, struct xfrm_sec_ctx *ctx, int delete, int *err) { @@ -812,6 +814,7 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u8 type, ret = NULL; hlist_for_each_entry(pol, chain, bydst) { if (pol->type == type && + pol->if_id == if_id && (mark & pol->mark.m) == pol->mark.v && !selector_cmp(sel, &pol->selector) && xfrm_sec_ctx_match(ctx, pol->security)) { @@ -837,8 +840,9 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u8 type, } EXPORT_SYMBOL(xfrm_policy_bysel_ctx); -struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8 type, - int dir, u32 id, int delete, int *err) +struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u32 if_id, + u8 type, int dir, u32 id, int delete, + int *err) { struct xfrm_policy *pol, *ret; struct hlist_head *chain; @@ -853,6 +857,7 @@ struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8 type, ret = NULL; hlist_for_each_entry(pol, chain, byidx) { if (pol->type == type && pol->index == id && + pol->if_id == if_id && (mark & pol->mark.m) == pol->mark.v) { xfrm_pol_hold(pol); if (delete) { @@ -1063,6 +1068,7 @@ static int xfrm_policy_match(const struct xfrm_policy *pol, bool match; if (pol->family != family || + pol->if_id != fl->flowi_xfrm.if_id || (fl->flowi_mark & pol->mark.m) != pol->mark.v || pol->type != type) return ret; @@ -1177,7 +1183,8 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir, match = xfrm_selector_match(&pol->selector, fl, family); if (match) { - if ((sk->sk_mark & pol->mark.m) != pol->mark.v) { + if ((sk->sk_mark & pol->mark.m) != pol->mark.v || + pol->if_id != fl->flowi_xfrm.if_id) { pol = NULL; goto out; } @@ -1305,6 +1312,7 @@ static struct xfrm_policy *clone_policy(const struct xfrm_policy *old, int dir) newp->lft = old->lft; newp->curlft = old->curlft; newp->mark = old->mark; + newp->if_id = old->if_id; newp->action = old->action; newp->flags = old->flags; newp->xfrm_nr = old->xfrm_nr; diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 8308281f3253..3803b6813fc5 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -941,6 +941,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, int error = 0; struct xfrm_state *best = NULL; u32 mark = pol->mark.v & pol->mark.m; + u32 if_id = fl->flowi_xfrm.if_id; unsigned short encap_family = tmpl->encap_family; unsigned int sequence; struct km_event c; @@ -955,6 +956,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, if (x->props.family == encap_family && x->props.reqid == tmpl->reqid && (mark & x->mark.m) == x->mark.v && + x->if_id == if_id && !(x->props.flags & XFRM_STATE_WILDRECV) && xfrm_state_addr_check(x, daddr, saddr, encap_family) && tmpl->mode == x->props.mode && @@ -971,6 +973,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, if (x->props.family == encap_family && x->props.reqid == tmpl->reqid && (mark & x->mark.m) == x->mark.v && + x->if_id == if_id && !(x->props.flags & XFRM_STATE_WILDRECV) && xfrm_addr_equal(&x->id.daddr, daddr, encap_family) && tmpl->mode == x->props.mode && @@ -1010,6 +1013,7 @@ found: * to current session. */ xfrm_init_tempstate(x, fl, tmpl, daddr, saddr, family); memcpy(&x->mark, &pol->mark, sizeof(x->mark)); + x->if_id = if_id; error = security_xfrm_state_alloc_acquire(x, pol->security, fl->flowi_secid); if (error) { @@ -1067,7 +1071,7 @@ out: } struct xfrm_state * -xfrm_stateonly_find(struct net *net, u32 mark, +xfrm_stateonly_find(struct net *net, u32 mark, u32 if_id, xfrm_address_t *daddr, xfrm_address_t *saddr, unsigned short family, u8 mode, u8 proto, u32 reqid) { @@ -1080,6 +1084,7 @@ xfrm_stateonly_find(struct net *net, u32 mark, if (x->props.family == family && x->props.reqid == reqid && (mark & x->mark.m) == x->mark.v && + x->if_id == if_id && !(x->props.flags & XFRM_STATE_WILDRECV) && xfrm_state_addr_check(x, daddr, saddr, family) && mode == x->props.mode && @@ -1160,11 +1165,13 @@ static void __xfrm_state_bump_genids(struct xfrm_state *xnew) struct xfrm_state *x; unsigned int h; u32 mark = xnew->mark.v & xnew->mark.m; + u32 if_id = xnew->if_id; h = xfrm_dst_hash(net, &xnew->id.daddr, &xnew->props.saddr, reqid, family); hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) { if (x->props.family == family && x->props.reqid == reqid && + x->if_id == if_id && (mark & x->mark.m) == x->mark.v && xfrm_addr_equal(&x->id.daddr, &xnew->id.daddr, family) && xfrm_addr_equal(&x->props.saddr, &xnew->props.saddr, family)) @@ -1187,7 +1194,7 @@ EXPORT_SYMBOL(xfrm_state_insert); static struct xfrm_state *__find_acq_core(struct net *net, const struct xfrm_mark *m, unsigned short family, u8 mode, - u32 reqid, u8 proto, + u32 reqid, u32 if_id, u8 proto, const xfrm_address_t *daddr, const xfrm_address_t *saddr, int create) @@ -1242,6 +1249,7 @@ static struct xfrm_state *__find_acq_core(struct net *net, x->props.family = family; x->props.mode = mode; x->props.reqid = reqid; + x->if_id = if_id; x->mark.v = m->v; x->mark.m = m->m; x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires; @@ -1296,7 +1304,7 @@ int xfrm_state_add(struct xfrm_state *x) if (use_spi && !x1) x1 = __find_acq_core(net, &x->mark, family, x->props.mode, - x->props.reqid, x->id.proto, + x->props.reqid, x->if_id, x->id.proto, &x->id.daddr, &x->props.saddr, 0); __xfrm_state_bump_genids(x); @@ -1395,6 +1403,7 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, x->props.flags = orig->props.flags; x->props.extra_flags = orig->props.extra_flags; + x->if_id = orig->if_id; x->tfcpad = orig->tfcpad; x->replay_maxdiff = orig->replay_maxdiff; x->replay_maxage = orig->replay_maxage; @@ -1619,13 +1628,13 @@ EXPORT_SYMBOL(xfrm_state_lookup_byaddr); struct xfrm_state * xfrm_find_acq(struct net *net, const struct xfrm_mark *mark, u8 mode, u32 reqid, - u8 proto, const xfrm_address_t *daddr, + u32 if_id, u8 proto, const xfrm_address_t *daddr, const xfrm_address_t *saddr, int create, unsigned short family) { struct xfrm_state *x; spin_lock_bh(&net->xfrm.xfrm_state_lock); - x = __find_acq_core(net, mark, family, mode, reqid, proto, daddr, saddr, create); + x = __find_acq_core(net, mark, family, mode, reqid, if_id, proto, daddr, saddr, create); spin_unlock_bh(&net->xfrm.xfrm_state_lock); return x; diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 9602cc9e05ab..79245e1c3487 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -594,6 +594,9 @@ static struct xfrm_state *xfrm_state_construct(struct net *net, xfrm_smark_init(attrs, &x->props.smark); + if (attrs[XFRMA_IF_ID]) + x->if_id = nla_get_u32(attrs[XFRMA_IF_ID]); + err = __xfrm_init_state(x, false, attrs[XFRMA_OFFLOAD_DEV]); if (err) goto error; @@ -929,7 +932,11 @@ static int copy_to_user_state_extra(struct xfrm_state *x, ret = copy_user_offload(&x->xso, skb); if (ret) goto out; - + if (x->if_id) { + ret = nla_put_u32(skb, XFRMA_IF_ID, x->if_id); + if (ret) + goto out; + } if (x->security) ret = copy_sec_ctx(x->security, skb); out: @@ -1278,6 +1285,7 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh, int err; u32 mark; struct xfrm_mark m; + u32 if_id = 0; p = nlmsg_data(nlh); err = verify_spi_info(p->info.id.proto, p->min, p->max); @@ -1290,6 +1298,10 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh, x = NULL; mark = xfrm_mark_get(attrs, &m); + + if (attrs[XFRMA_IF_ID]) + if_id = nla_get_u32(attrs[XFRMA_IF_ID]); + if (p->info.seq) { x = xfrm_find_acq_byseq(net, mark, p->info.seq); if (x && !xfrm_addr_equal(&x->id.daddr, daddr, family)) { @@ -1300,7 +1312,7 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh, if (!x) x = xfrm_find_acq(net, &m, p->info.mode, p->info.reqid, - p->info.id.proto, daddr, + if_id, p->info.id.proto, daddr, &p->info.saddr, 1, family); err = -ENOENT; @@ -1588,6 +1600,9 @@ static struct xfrm_policy *xfrm_policy_construct(struct net *net, struct xfrm_us xfrm_mark_get(attrs, &xp->mark); + if (attrs[XFRMA_IF_ID]) + xp->if_id = nla_get_u32(attrs[XFRMA_IF_ID]); + return xp; error: *errp = err; @@ -1733,6 +1748,8 @@ static int dump_one_policy(struct xfrm_policy *xp, int dir, int count, void *ptr err = copy_to_user_policy_type(xp->type, skb); if (!err) err = xfrm_mark_put(skb, &xp->mark); + if (!err) + err = xfrm_if_id_put(skb, xp->if_id); if (err) { nlmsg_cancel(skb, nlh); return err; @@ -1814,6 +1831,7 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, int delete; struct xfrm_mark m; u32 mark = xfrm_mark_get(attrs, &m); + u32 if_id = 0; p = nlmsg_data(nlh); delete = nlh->nlmsg_type == XFRM_MSG_DELPOLICY; @@ -1826,8 +1844,11 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, if (err) return err; + if (attrs[XFRMA_IF_ID]) + if_id = nla_get_u32(attrs[XFRMA_IF_ID]); + if (p->index) - xp = xfrm_policy_byid(net, mark, type, p->dir, p->index, delete, &err); + xp = xfrm_policy_byid(net, mark, if_id, type, p->dir, p->index, delete, &err); else { struct nlattr *rt = attrs[XFRMA_SEC_CTX]; struct xfrm_sec_ctx *ctx; @@ -1844,7 +1865,7 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, if (err) return err; } - xp = xfrm_policy_bysel_ctx(net, mark, type, p->dir, &p->sel, + xp = xfrm_policy_bysel_ctx(net, mark, if_id, type, p->dir, &p->sel, ctx, delete, &err); security_xfrm_policy_free(ctx); } @@ -1967,6 +1988,10 @@ static int build_aevent(struct sk_buff *skb, struct xfrm_state *x, const struct if (err) goto out_cancel; + err = xfrm_if_id_put(skb, x->if_id); + if (err) + goto out_cancel; + nlmsg_end(skb, nlh); return 0; @@ -2109,6 +2134,7 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, int err = -ENOENT; struct xfrm_mark m; u32 mark = xfrm_mark_get(attrs, &m); + u32 if_id = 0; err = copy_from_user_policy_type(&type, attrs); if (err) @@ -2118,8 +2144,11 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, if (err) return err; + if (attrs[XFRMA_IF_ID]) + if_id = nla_get_u32(attrs[XFRMA_IF_ID]); + if (p->index) - xp = xfrm_policy_byid(net, mark, type, p->dir, p->index, 0, &err); + xp = xfrm_policy_byid(net, mark, if_id, type, p->dir, p->index, 0, &err); else { struct nlattr *rt = attrs[XFRMA_SEC_CTX]; struct xfrm_sec_ctx *ctx; @@ -2136,7 +2165,7 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, if (err) return err; } - xp = xfrm_policy_bysel_ctx(net, mark, type, p->dir, + xp = xfrm_policy_bysel_ctx(net, mark, if_id, type, p->dir, &p->sel, ctx, 0, &err); security_xfrm_policy_free(ctx); } @@ -2520,6 +2549,7 @@ static const struct nla_policy xfrma_policy[XFRMA_MAX+1] = { [XFRMA_OFFLOAD_DEV] = { .len = sizeof(struct xfrm_user_offload) }, [XFRMA_SET_MARK] = { .type = NLA_U32 }, [XFRMA_SET_MARK_MASK] = { .type = NLA_U32 }, + [XFRMA_IF_ID] = { .type = NLA_U32 }, }; static const struct nla_policy xfrma_spd_policy[XFRMA_SPD_MAX+1] = { @@ -2651,6 +2681,10 @@ static int build_expire(struct sk_buff *skb, struct xfrm_state *x, const struct if (err) return err; + err = xfrm_if_id_put(skb, x->if_id); + if (err) + return err; + nlmsg_end(skb, nlh); return 0; } @@ -2749,6 +2783,8 @@ static inline unsigned int xfrm_sa_len(struct xfrm_state *x) l += nla_total_size(sizeof(x->props.smark.v)); l += nla_total_size(sizeof(x->props.smark.m)); } + if (x->if_id) + l += nla_total_size(sizeof(x->if_id)); /* Must count x->lastused as it may become non-zero behind our back. */ l += nla_total_size_64bit(sizeof(u64)); @@ -2878,6 +2914,8 @@ static int build_acquire(struct sk_buff *skb, struct xfrm_state *x, err = copy_to_user_policy_type(xp->type, skb); if (!err) err = xfrm_mark_put(skb, &xp->mark); + if (!err) + err = xfrm_if_id_put(skb, xp->if_id); if (err) { nlmsg_cancel(skb, nlh); return err; @@ -2994,6 +3032,8 @@ static int build_polexpire(struct sk_buff *skb, struct xfrm_policy *xp, err = copy_to_user_policy_type(xp->type, skb); if (!err) err = xfrm_mark_put(skb, &xp->mark); + if (!err) + err = xfrm_if_id_put(skb, xp->if_id); if (err) { nlmsg_cancel(skb, nlh); return err; @@ -3075,6 +3115,8 @@ static int xfrm_notify_policy(struct xfrm_policy *xp, int dir, const struct km_e err = copy_to_user_policy_type(xp->type, skb); if (!err) err = xfrm_mark_put(skb, &xp->mark); + if (!err) + err = xfrm_if_id_put(skb, xp->if_id); if (err) goto out_free_skb; -- cgit v1.2.3 From f203b76d78092faf248db3f851840fbecf80b40e Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Tue, 12 Jun 2018 14:07:12 +0200 Subject: xfrm: Add virtual xfrm interfaces This patch adds support for virtual xfrm interfaces. Packets that are routed through such an interface are guaranteed to be IPsec transformed or dropped. It is a generic virtual interface that ensures IPsec transformation, no need to know what happens behind the interface. This means that we can tunnel IPv4 and IPv6 through the same interface and support all xfrm modes (tunnel, transport and beet) on it. Co-developed-by: Lorenzo Colitti Co-developed-by: Benedict Wong Signed-off-by: Lorenzo Colitti Signed-off-by: Benedict Wong Signed-off-by: Steffen Klassert Acked-by: Shannon Nelson Tested-by: Benedict Wong Tested-by: Antony Antony Reviewed-by: Eyal Birger --- include/net/xfrm.h | 24 ++ include/uapi/linux/if_link.h | 10 + net/xfrm/Kconfig | 8 + net/xfrm/Makefile | 1 + net/xfrm/xfrm_input.c | 3 + net/xfrm/xfrm_interface.c | 972 +++++++++++++++++++++++++++++++++++++++++++ net/xfrm/xfrm_policy.c | 43 ++ 7 files changed, 1061 insertions(+) create mode 100644 net/xfrm/xfrm_interface.c (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index e8bada4d2a45..3fa578a6a819 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -23,6 +23,7 @@ #include #include #include +#include #include @@ -293,6 +294,13 @@ struct xfrm_replay { int (*overflow)(struct xfrm_state *x, struct sk_buff *skb); }; +struct xfrm_if_cb { + struct xfrm_if *(*decode_session)(struct sk_buff *skb); +}; + +void xfrm_if_register_cb(const struct xfrm_if_cb *ifcb); +void xfrm_if_unregister_cb(void); + struct net_device; struct xfrm_type; struct xfrm_dst; @@ -1039,6 +1047,22 @@ static inline void xfrm_dst_destroy(struct xfrm_dst *xdst) void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev); +struct xfrm_if_parms { + char name[IFNAMSIZ]; /* name of XFRM device */ + int link; /* ifindex of underlying L2 interface */ + u32 if_id; /* interface identifyer */ +}; + +struct xfrm_if { + struct xfrm_if __rcu *next; /* next interface in list */ + struct net_device *dev; /* virtual device associated with interface */ + struct net_device *phydev; /* physical device */ + struct net *net; /* netns for packet i/o */ + struct xfrm_if_parms p; /* interface parms */ + + struct gro_cells gro_cells; +}; + struct xfrm_offload { /* Output sequence number for replay protection on offloading. */ struct { diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index cf01b6824244..bff0af507b32 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -459,6 +459,16 @@ enum { #define IFLA_MACSEC_MAX (__IFLA_MACSEC_MAX - 1) +/* XFRM section */ +enum { + IFLA_XFRM_UNSPEC, + IFLA_XFRM_LINK, + IFLA_XFRM_IF_ID, + __IFLA_XFRM_MAX +}; + +#define IFLA_XFRM_MAX (__IFLA_XFRM_MAX - 1) + enum macsec_validation_type { MACSEC_VALIDATE_DISABLED = 0, MACSEC_VALIDATE_CHECK = 1, diff --git a/net/xfrm/Kconfig b/net/xfrm/Kconfig index 286ed25c1a69..53381888a7b3 100644 --- a/net/xfrm/Kconfig +++ b/net/xfrm/Kconfig @@ -25,6 +25,14 @@ config XFRM_USER If unsure, say Y. +config XFRM_INTERFACE + tristate "Transformation virtual interface" + depends on XFRM && IPV6 + ---help--- + This provides a virtual interface to route IPsec traffic. + + If unsure, say N. + config XFRM_SUB_POLICY bool "Transformation sub policy support" depends on XFRM diff --git a/net/xfrm/Makefile b/net/xfrm/Makefile index 0bd2465a8c5a..fbc4552d17b8 100644 --- a/net/xfrm/Makefile +++ b/net/xfrm/Makefile @@ -10,3 +10,4 @@ obj-$(CONFIG_XFRM_STATISTICS) += xfrm_proc.o obj-$(CONFIG_XFRM_ALGO) += xfrm_algo.o obj-$(CONFIG_XFRM_USER) += xfrm_user.o obj-$(CONFIG_XFRM_IPCOMP) += xfrm_ipcomp.o +obj-$(CONFIG_XFRM_INTERFACE) += xfrm_interface.o diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 074810436242..b89c9c7f8c5c 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -320,6 +320,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) seq = 0; if (!spi && (err = xfrm_parse_spi(skb, nexthdr, &spi, &seq)) != 0) { + secpath_reset(skb); XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR); goto drop; } @@ -328,12 +329,14 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) XFRM_SPI_SKB_CB(skb)->daddroff); do { if (skb->sp->len == XFRM_MAX_DEPTH) { + secpath_reset(skb); XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR); goto drop; } x = xfrm_state_lookup(net, mark, daddr, spi, nexthdr, family); if (x == NULL) { + secpath_reset(skb); XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOSTATES); xfrm_audit_state_notfound(skb, family, spi, seq); goto drop; diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c new file mode 100644 index 000000000000..31cb1c7e3881 --- /dev/null +++ b/net/xfrm/xfrm_interface.c @@ -0,0 +1,972 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * XFRM virtual interface + * + * Copyright (C) 2018 secunet Security Networks AG + * + * Author: + * Steffen Klassert + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static int xfrmi_dev_init(struct net_device *dev); +static void xfrmi_dev_setup(struct net_device *dev); +static struct rtnl_link_ops xfrmi_link_ops __read_mostly; +static unsigned int xfrmi_net_id __read_mostly; + +struct xfrmi_net { + /* lists for storing interfaces in use */ + struct xfrm_if __rcu *xfrmi[1]; +}; + +#define for_each_xfrmi_rcu(start, xi) \ + for (xi = rcu_dereference(start); xi; xi = rcu_dereference(xi->next)) + +static struct xfrm_if *xfrmi_lookup(struct net *net, struct xfrm_state *x) +{ + struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id); + struct xfrm_if *xi; + + for_each_xfrmi_rcu(xfrmn->xfrmi[0], xi) { + if (x->if_id == xi->p.if_id && + (xi->dev->flags & IFF_UP)) + return xi; + } + + return NULL; +} + +static struct xfrm_if *xfrmi_decode_session(struct sk_buff *skb) +{ + struct xfrmi_net *xfrmn; + int ifindex; + struct xfrm_if *xi; + + if (!skb->dev) + return NULL; + + xfrmn = net_generic(dev_net(skb->dev), xfrmi_net_id); + ifindex = skb->dev->ifindex; + + for_each_xfrmi_rcu(xfrmn->xfrmi[0], xi) { + if (ifindex == xi->dev->ifindex && + (xi->dev->flags & IFF_UP)) + return xi; + } + + return NULL; +} + +static void xfrmi_link(struct xfrmi_net *xfrmn, struct xfrm_if *xi) +{ + struct xfrm_if __rcu **xip = &xfrmn->xfrmi[0]; + + rcu_assign_pointer(xi->next , rtnl_dereference(*xip)); + rcu_assign_pointer(*xip, xi); +} + +static void xfrmi_unlink(struct xfrmi_net *xfrmn, struct xfrm_if *xi) +{ + struct xfrm_if __rcu **xip; + struct xfrm_if *iter; + + for (xip = &xfrmn->xfrmi[0]; + (iter = rtnl_dereference(*xip)) != NULL; + xip = &iter->next) { + if (xi == iter) { + rcu_assign_pointer(*xip, xi->next); + break; + } + } +} + +static void xfrmi_dev_free(struct net_device *dev) +{ + free_percpu(dev->tstats); +} + +static int xfrmi_create2(struct net_device *dev) +{ + struct xfrm_if *xi = netdev_priv(dev); + struct net *net = dev_net(dev); + struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id); + int err; + + dev->rtnl_link_ops = &xfrmi_link_ops; + err = register_netdevice(dev); + if (err < 0) + goto out; + + strcpy(xi->p.name, dev->name); + + dev_hold(dev); + xfrmi_link(xfrmn, xi); + + return 0; + +out: + return err; +} + +static struct xfrm_if *xfrmi_create(struct net *net, struct xfrm_if_parms *p) +{ + struct net_device *dev; + struct xfrm_if *xi; + char name[IFNAMSIZ]; + int err; + + if (p->name[0]) + strlcpy(name, p->name, IFNAMSIZ); + else + goto failed; + + dev = alloc_netdev(sizeof(*xi), name, NET_NAME_UNKNOWN, xfrmi_dev_setup); + if (!dev) + goto failed; + + dev_net_set(dev, net); + + xi = netdev_priv(dev); + xi->p = *p; + xi->net = net; + xi->dev = dev; + xi->phydev = dev_get_by_index(net, p->link); + if (!xi->phydev) + goto failed_free; + + err = xfrmi_create2(dev); + if (err < 0) + goto failed_dev_put; + + return xi; + +failed_dev_put: + dev_put(xi->phydev); +failed_free: + free_netdev(dev); +failed: + return NULL; +} + +static struct xfrm_if *xfrmi_locate(struct net *net, struct xfrm_if_parms *p, + int create) +{ + struct xfrm_if __rcu **xip; + struct xfrm_if *xi; + struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id); + + for (xip = &xfrmn->xfrmi[0]; + (xi = rtnl_dereference(*xip)) != NULL; + xip = &xi->next) { + if (xi->p.if_id == p->if_id) { + if (create) + return NULL; + + return xi; + } + } + if (!create) + return NULL; + return xfrmi_create(net, p); +} + +static void xfrmi_dev_uninit(struct net_device *dev) +{ + struct xfrm_if *xi = netdev_priv(dev); + struct xfrmi_net *xfrmn = net_generic(xi->net, xfrmi_net_id); + + xfrmi_unlink(xfrmn, xi); + dev_put(xi->phydev); + dev_put(dev); +} + +static void xfrmi_scrub_packet(struct sk_buff *skb, bool xnet) +{ + skb->tstamp = 0; + skb->pkt_type = PACKET_HOST; + skb->skb_iif = 0; + skb->ignore_df = 0; + skb_dst_drop(skb); + nf_reset(skb); + nf_reset_trace(skb); + + if (!xnet) + return; + + ipvs_reset(skb); + secpath_reset(skb); + skb_orphan(skb); + skb->mark = 0; +} + +static int xfrmi_rcv_cb(struct sk_buff *skb, int err) +{ + struct pcpu_sw_netstats *tstats; + struct xfrm_mode *inner_mode; + struct net_device *dev; + struct xfrm_state *x; + struct xfrm_if *xi; + bool xnet; + + if (err && !skb->sp) + return 0; + + x = xfrm_input_state(skb); + + xi = xfrmi_lookup(xs_net(x), x); + if (!xi) + return 1; + + dev = xi->dev; + skb->dev = dev; + + if (err) { + dev->stats.rx_errors++; + dev->stats.rx_dropped++; + + return 0; + } + + xnet = !net_eq(xi->net, dev_net(skb->dev)); + + if (xnet) { + inner_mode = x->inner_mode; + + if (x->sel.family == AF_UNSPEC) { + inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol); + if (inner_mode == NULL) { + XFRM_INC_STATS(dev_net(skb->dev), + LINUX_MIB_XFRMINSTATEMODEERROR); + return -EINVAL; + } + } + + if (!xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, + inner_mode->afinfo->family)) + return -EPERM; + } + + xfrmi_scrub_packet(skb, xnet); + + tstats = this_cpu_ptr(dev->tstats); + + u64_stats_update_begin(&tstats->syncp); + tstats->rx_packets++; + tstats->rx_bytes += skb->len; + u64_stats_update_end(&tstats->syncp); + + return 0; +} + +static int +xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) +{ + struct xfrm_if *xi = netdev_priv(dev); + struct net_device_stats *stats = &xi->dev->stats; + struct dst_entry *dst = skb_dst(skb); + unsigned int length = skb->len; + struct net_device *tdev; + struct xfrm_state *x; + int err = -1; + int mtu; + + if (!dst) + goto tx_err_link_failure; + + fl->flowi_xfrm.if_id = xi->p.if_id; + + dst_hold(dst); + dst = xfrm_lookup(xi->net, dst, fl, NULL, 0); + if (IS_ERR(dst)) { + err = PTR_ERR(dst); + dst = NULL; + goto tx_err_link_failure; + } + + x = dst->xfrm; + if (!x) + goto tx_err_link_failure; + + if (x->if_id != xi->p.if_id) + goto tx_err_link_failure; + + tdev = dst->dev; + + if (tdev == dev) { + stats->collisions++; + net_warn_ratelimited("%s: Local routing loop detected!\n", + xi->p.name); + goto tx_err_dst_release; + } + + mtu = dst_mtu(dst); + if (!skb->ignore_df && skb->len > mtu) { + skb_dst_update_pmtu(skb, mtu); + + if (skb->protocol == htons(ETH_P_IPV6)) { + if (mtu < IPV6_MIN_MTU) + mtu = IPV6_MIN_MTU; + + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + } else { + icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, + htonl(mtu)); + } + + dst_release(dst); + return -EMSGSIZE; + } + + xfrmi_scrub_packet(skb, !net_eq(xi->net, dev_net(dev))); + skb_dst_set(skb, dst); + skb->dev = tdev; + + err = dst_output(xi->net, skb->sk, skb); + if (net_xmit_eval(err) == 0) { + struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); + + u64_stats_update_begin(&tstats->syncp); + tstats->tx_bytes += length; + tstats->tx_packets++; + u64_stats_update_end(&tstats->syncp); + } else { + stats->tx_errors++; + stats->tx_aborted_errors++; + } + + return 0; +tx_err_link_failure: + stats->tx_carrier_errors++; + dst_link_failure(skb); +tx_err_dst_release: + dst_release(dst); + return err; +} + +static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct xfrm_if *xi = netdev_priv(dev); + struct net_device_stats *stats = &xi->dev->stats; + struct flowi fl; + int ret; + + memset(&fl, 0, sizeof(fl)); + + switch (skb->protocol) { + case htons(ETH_P_IPV6): + xfrm_decode_session(skb, &fl, AF_INET6); + memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); + break; + case htons(ETH_P_IP): + xfrm_decode_session(skb, &fl, AF_INET); + memset(IPCB(skb), 0, sizeof(*IPCB(skb))); + break; + default: + goto tx_err; + } + + fl.flowi_oif = xi->phydev->ifindex; + + ret = xfrmi_xmit2(skb, dev, &fl); + if (ret < 0) + goto tx_err; + + return NETDEV_TX_OK; + +tx_err: + stats->tx_errors++; + stats->tx_dropped++; + kfree_skb(skb); + return NETDEV_TX_OK; +} + +static int xfrmi4_err(struct sk_buff *skb, u32 info) +{ + const struct iphdr *iph = (const struct iphdr *)skb->data; + struct net *net = dev_net(skb->dev); + int protocol = iph->protocol; + struct ip_comp_hdr *ipch; + struct ip_esp_hdr *esph; + struct ip_auth_hdr *ah ; + struct xfrm_state *x; + struct xfrm_if *xi; + __be32 spi; + + switch (protocol) { + case IPPROTO_ESP: + esph = (struct ip_esp_hdr *)(skb->data+(iph->ihl<<2)); + spi = esph->spi; + break; + case IPPROTO_AH: + ah = (struct ip_auth_hdr *)(skb->data+(iph->ihl<<2)); + spi = ah->spi; + break; + case IPPROTO_COMP: + ipch = (struct ip_comp_hdr *)(skb->data+(iph->ihl<<2)); + spi = htonl(ntohs(ipch->cpi)); + break; + default: + return 0; + } + + switch (icmp_hdr(skb)->type) { + case ICMP_DEST_UNREACH: + if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) + return 0; + case ICMP_REDIRECT: + break; + default: + return 0; + } + + x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, + spi, protocol, AF_INET); + if (!x) + return 0; + + xi = xfrmi_lookup(net, x); + if (!xi) { + xfrm_state_put(x); + return -1; + } + + if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) + ipv4_update_pmtu(skb, net, info, 0, 0, protocol, 0); + else + ipv4_redirect(skb, net, 0, 0, protocol, 0); + xfrm_state_put(x); + + return 0; +} + +static int xfrmi6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info) +{ + const struct ipv6hdr *iph = (const struct ipv6hdr *)skb->data; + struct net *net = dev_net(skb->dev); + int protocol = iph->nexthdr; + struct ip_comp_hdr *ipch; + struct ip_esp_hdr *esph; + struct ip_auth_hdr *ah; + struct xfrm_state *x; + struct xfrm_if *xi; + __be32 spi; + + switch (protocol) { + case IPPROTO_ESP: + esph = (struct ip_esp_hdr *)(skb->data + offset); + spi = esph->spi; + break; + case IPPROTO_AH: + ah = (struct ip_auth_hdr *)(skb->data + offset); + spi = ah->spi; + break; + case IPPROTO_COMP: + ipch = (struct ip_comp_hdr *)(skb->data + offset); + spi = htonl(ntohs(ipch->cpi)); + break; + default: + return 0; + } + + if (type != ICMPV6_PKT_TOOBIG && + type != NDISC_REDIRECT) + return 0; + + x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, + spi, protocol, AF_INET6); + if (!x) + return 0; + + xi = xfrmi_lookup(net, x); + if (!xi) { + xfrm_state_put(x); + return -1; + } + + if (type == NDISC_REDIRECT) + ip6_redirect(skb, net, skb->dev->ifindex, 0, + sock_net_uid(net, NULL)); + else + ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL)); + xfrm_state_put(x); + + return 0; +} + +static int xfrmi_change(struct xfrm_if *xi, const struct xfrm_if_parms *p) +{ + if (xi->p.link != p->link) + return -EINVAL; + + xi->p.if_id = p->if_id; + + return 0; +} + +static int xfrmi_update(struct xfrm_if *xi, struct xfrm_if_parms *p) +{ + struct net *net = dev_net(xi->dev); + struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id); + int err; + + xfrmi_unlink(xfrmn, xi); + synchronize_net(); + err = xfrmi_change(xi, p); + xfrmi_link(xfrmn, xi); + netdev_state_change(xi->dev); + return err; +} + +static void xfrmi_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *s) +{ + int cpu; + + if (!dev->tstats) + return; + + for_each_possible_cpu(cpu) { + struct pcpu_sw_netstats *stats; + struct pcpu_sw_netstats tmp; + int start; + + stats = per_cpu_ptr(dev->tstats, cpu); + do { + start = u64_stats_fetch_begin_irq(&stats->syncp); + tmp.rx_packets = stats->rx_packets; + tmp.rx_bytes = stats->rx_bytes; + tmp.tx_packets = stats->tx_packets; + tmp.tx_bytes = stats->tx_bytes; + } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); + + s->rx_packets += tmp.rx_packets; + s->rx_bytes += tmp.rx_bytes; + s->tx_packets += tmp.tx_packets; + s->tx_bytes += tmp.tx_bytes; + } + + s->rx_dropped = dev->stats.rx_dropped; + s->tx_dropped = dev->stats.tx_dropped; +} + +static int xfrmi_get_iflink(const struct net_device *dev) +{ + struct xfrm_if *xi = netdev_priv(dev); + + return xi->phydev->ifindex; +} + + +static const struct net_device_ops xfrmi_netdev_ops = { + .ndo_init = xfrmi_dev_init, + .ndo_uninit = xfrmi_dev_uninit, + .ndo_start_xmit = xfrmi_xmit, + .ndo_get_stats64 = xfrmi_get_stats64, + .ndo_get_iflink = xfrmi_get_iflink, +}; + +static void xfrmi_dev_setup(struct net_device *dev) +{ + dev->netdev_ops = &xfrmi_netdev_ops; + dev->type = ARPHRD_NONE; + dev->hard_header_len = ETH_HLEN; + dev->min_header_len = ETH_HLEN; + dev->mtu = ETH_DATA_LEN; + dev->min_mtu = ETH_MIN_MTU; + dev->max_mtu = ETH_DATA_LEN; + dev->addr_len = ETH_ALEN; + dev->flags = IFF_NOARP; + dev->needs_free_netdev = true; + dev->priv_destructor = xfrmi_dev_free; + netif_keep_dst(dev); +} + +static int xfrmi_dev_init(struct net_device *dev) +{ + struct xfrm_if *xi = netdev_priv(dev); + struct net_device *phydev = xi->phydev; + int err; + + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); + if (!dev->tstats) + return -ENOMEM; + + err = gro_cells_init(&xi->gro_cells, dev); + if (err) { + free_percpu(dev->tstats); + return err; + } + + dev->features |= NETIF_F_LLTX; + + dev->needed_headroom = phydev->needed_headroom; + dev->needed_tailroom = phydev->needed_tailroom; + + if (is_zero_ether_addr(dev->dev_addr)) + eth_hw_addr_inherit(dev, phydev); + if (is_zero_ether_addr(dev->broadcast)) + memcpy(dev->broadcast, phydev->broadcast, dev->addr_len); + + return 0; +} + +static int xfrmi_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + return 0; +} + +static void xfrmi_netlink_parms(struct nlattr *data[], + struct xfrm_if_parms *parms) +{ + memset(parms, 0, sizeof(*parms)); + + if (!data) + return; + + if (data[IFLA_XFRM_LINK]) + parms->link = nla_get_u32(data[IFLA_XFRM_LINK]); + + if (data[IFLA_XFRM_IF_ID]) + parms->if_id = nla_get_u32(data[IFLA_XFRM_IF_ID]); +} + +static int xfrmi_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct net *net = dev_net(dev); + struct xfrm_if_parms *p; + struct xfrm_if *xi; + + xi = netdev_priv(dev); + p = &xi->p; + + xfrmi_netlink_parms(data, p); + + if (!tb[IFLA_IFNAME]) + return -EINVAL; + + nla_strlcpy(p->name, tb[IFLA_IFNAME], IFNAMSIZ); + + if (!xfrmi_locate(net, p, 1)) + return -EEXIST; + + return 0; +} + +static void xfrmi_dellink(struct net_device *dev, struct list_head *head) +{ + unregister_netdevice_queue(dev, head); +} + +static int xfrmi_changelink(struct net_device *dev, struct nlattr *tb[], + struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct xfrm_if *xi = netdev_priv(dev); + struct net *net = dev_net(dev); + + xfrmi_netlink_parms(data, &xi->p); + + xi = xfrmi_locate(net, &xi->p, 0); + + if (xi) { + if (xi->dev != dev) + return -EEXIST; + } else + xi = netdev_priv(dev); + + return xfrmi_update(xi, &xi->p); +} + +static size_t xfrmi_get_size(const struct net_device *dev) +{ + return + /* IFLA_XFRM_LINK */ + nla_total_size(4) + + /* IFLA_XFRM_IF_ID */ + nla_total_size(4) + + 0; +} + +static int xfrmi_fill_info(struct sk_buff *skb, const struct net_device *dev) +{ + struct xfrm_if *xi = netdev_priv(dev); + struct xfrm_if_parms *parm = &xi->p; + + if (nla_put_u32(skb, IFLA_XFRM_LINK, parm->link) || + nla_put_u32(skb, IFLA_XFRM_IF_ID, parm->if_id)) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +struct net *xfrmi_get_link_net(const struct net_device *dev) +{ + struct xfrm_if *xi = netdev_priv(dev); + + return dev_net(xi->phydev); +} + +static const struct nla_policy xfrmi_policy[IFLA_XFRM_MAX + 1] = { + [IFLA_XFRM_LINK] = { .type = NLA_U32 }, + [IFLA_XFRM_IF_ID] = { .type = NLA_U32 }, +}; + +static struct rtnl_link_ops xfrmi_link_ops __read_mostly = { + .kind = "xfrm", + .maxtype = IFLA_XFRM_MAX, + .policy = xfrmi_policy, + .priv_size = sizeof(struct xfrm_if), + .setup = xfrmi_dev_setup, + .validate = xfrmi_validate, + .newlink = xfrmi_newlink, + .dellink = xfrmi_dellink, + .changelink = xfrmi_changelink, + .get_size = xfrmi_get_size, + .fill_info = xfrmi_fill_info, + .get_link_net = xfrmi_get_link_net, +}; + +static void __net_exit xfrmi_destroy_interfaces(struct xfrmi_net *xfrmn) +{ + struct xfrm_if *xi; + LIST_HEAD(list); + + xi = rtnl_dereference(xfrmn->xfrmi[0]); + if (!xi) + return; + + unregister_netdevice_queue(xi->dev, &list); + unregister_netdevice_many(&list); +} + +static int __net_init xfrmi_init_net(struct net *net) +{ + return 0; +} + +static void __net_exit xfrmi_exit_net(struct net *net) +{ + struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id); + + rtnl_lock(); + xfrmi_destroy_interfaces(xfrmn); + rtnl_unlock(); +} + +static struct pernet_operations xfrmi_net_ops = { + .init = xfrmi_init_net, + .exit = xfrmi_exit_net, + .id = &xfrmi_net_id, + .size = sizeof(struct xfrmi_net), +}; + +static struct xfrm6_protocol xfrmi_esp6_protocol __read_mostly = { + .handler = xfrm6_rcv, + .cb_handler = xfrmi_rcv_cb, + .err_handler = xfrmi6_err, + .priority = 10, +}; + +static struct xfrm6_protocol xfrmi_ah6_protocol __read_mostly = { + .handler = xfrm6_rcv, + .cb_handler = xfrmi_rcv_cb, + .err_handler = xfrmi6_err, + .priority = 10, +}; + +static struct xfrm6_protocol xfrmi_ipcomp6_protocol __read_mostly = { + .handler = xfrm6_rcv, + .cb_handler = xfrmi_rcv_cb, + .err_handler = xfrmi6_err, + .priority = 10, +}; + +static struct xfrm4_protocol xfrmi_esp4_protocol __read_mostly = { + .handler = xfrm4_rcv, + .input_handler = xfrm_input, + .cb_handler = xfrmi_rcv_cb, + .err_handler = xfrmi4_err, + .priority = 10, +}; + +static struct xfrm4_protocol xfrmi_ah4_protocol __read_mostly = { + .handler = xfrm4_rcv, + .input_handler = xfrm_input, + .cb_handler = xfrmi_rcv_cb, + .err_handler = xfrmi4_err, + .priority = 10, +}; + +static struct xfrm4_protocol xfrmi_ipcomp4_protocol __read_mostly = { + .handler = xfrm4_rcv, + .input_handler = xfrm_input, + .cb_handler = xfrmi_rcv_cb, + .err_handler = xfrmi4_err, + .priority = 10, +}; + +static int __init xfrmi4_init(void) +{ + int err; + + err = xfrm4_protocol_register(&xfrmi_esp4_protocol, IPPROTO_ESP); + if (err < 0) + goto xfrm_proto_esp_failed; + err = xfrm4_protocol_register(&xfrmi_ah4_protocol, IPPROTO_AH); + if (err < 0) + goto xfrm_proto_ah_failed; + err = xfrm4_protocol_register(&xfrmi_ipcomp4_protocol, IPPROTO_COMP); + if (err < 0) + goto xfrm_proto_comp_failed; + + return 0; + +xfrm_proto_comp_failed: + xfrm4_protocol_deregister(&xfrmi_ah4_protocol, IPPROTO_AH); +xfrm_proto_ah_failed: + xfrm4_protocol_deregister(&xfrmi_esp4_protocol, IPPROTO_ESP); +xfrm_proto_esp_failed: + return err; +} + +static void xfrmi4_fini(void) +{ + xfrm4_protocol_deregister(&xfrmi_ipcomp4_protocol, IPPROTO_COMP); + xfrm4_protocol_deregister(&xfrmi_ah4_protocol, IPPROTO_AH); + xfrm4_protocol_deregister(&xfrmi_esp4_protocol, IPPROTO_ESP); +} + +static int __init xfrmi6_init(void) +{ + int err; + + err = xfrm6_protocol_register(&xfrmi_esp6_protocol, IPPROTO_ESP); + if (err < 0) + goto xfrm_proto_esp_failed; + err = xfrm6_protocol_register(&xfrmi_ah6_protocol, IPPROTO_AH); + if (err < 0) + goto xfrm_proto_ah_failed; + err = xfrm6_protocol_register(&xfrmi_ipcomp6_protocol, IPPROTO_COMP); + if (err < 0) + goto xfrm_proto_comp_failed; + + return 0; + +xfrm_proto_comp_failed: + xfrm6_protocol_deregister(&xfrmi_ah6_protocol, IPPROTO_AH); +xfrm_proto_ah_failed: + xfrm6_protocol_deregister(&xfrmi_esp6_protocol, IPPROTO_ESP); +xfrm_proto_esp_failed: + return err; +} + +static void xfrmi6_fini(void) +{ + xfrm6_protocol_deregister(&xfrmi_ipcomp6_protocol, IPPROTO_COMP); + xfrm6_protocol_deregister(&xfrmi_ah6_protocol, IPPROTO_AH); + xfrm6_protocol_deregister(&xfrmi_esp6_protocol, IPPROTO_ESP); +} + +static const struct xfrm_if_cb xfrm_if_cb = { + .decode_session = xfrmi_decode_session, +}; + +static int __init xfrmi_init(void) +{ + const char *msg; + int err; + + pr_info("IPsec XFRM device driver\n"); + + msg = "tunnel device"; + err = register_pernet_device(&xfrmi_net_ops); + if (err < 0) + goto pernet_dev_failed; + + msg = "xfrm4 protocols"; + err = xfrmi4_init(); + if (err < 0) + goto xfrmi4_failed; + + msg = "xfrm6 protocols"; + err = xfrmi6_init(); + if (err < 0) + goto xfrmi6_failed; + + + msg = "netlink interface"; + err = rtnl_link_register(&xfrmi_link_ops); + if (err < 0) + goto rtnl_link_failed; + + xfrm_if_register_cb(&xfrm_if_cb); + + return err; + +rtnl_link_failed: + xfrmi6_fini(); +xfrmi6_failed: + xfrmi4_fini(); +xfrmi4_failed: + unregister_pernet_device(&xfrmi_net_ops); +pernet_dev_failed: + pr_err("xfrmi init: failed to register %s\n", msg); + return err; +} + +static void __exit xfrmi_fini(void) +{ + xfrm_if_unregister_cb(); + rtnl_link_unregister(&xfrmi_link_ops); + xfrmi4_fini(); + xfrmi6_fini(); + unregister_pernet_device(&xfrmi_net_ops); +} + +module_init(xfrmi_init); +module_exit(xfrmi_fini); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_RTNL_LINK("xfrm"); +MODULE_ALIAS_NETDEV("xfrm0"); +MODULE_AUTHOR("Steffen Klassert"); +MODULE_DESCRIPTION("XFRM virtual interface"); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index fc0c69312b2c..d960ea6657b5 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -47,6 +47,9 @@ struct xfrm_flo { static DEFINE_PER_CPU(struct xfrm_dst *, xfrm_last_dst); static struct work_struct *xfrm_pcpu_work __read_mostly; +static DEFINE_SPINLOCK(xfrm_if_cb_lock); +static struct xfrm_if_cb const __rcu *xfrm_if_cb __read_mostly; + static DEFINE_SPINLOCK(xfrm_policy_afinfo_lock); static struct xfrm_policy_afinfo const __rcu *xfrm_policy_afinfo[AF_INET6 + 1] __read_mostly; @@ -119,6 +122,12 @@ static const struct xfrm_policy_afinfo *xfrm_policy_get_afinfo(unsigned short fa return afinfo; } +/* Called with rcu_read_lock(). */ +static const struct xfrm_if_cb *xfrm_if_get_cb(void) +{ + return rcu_dereference(xfrm_if_cb); +} + struct dst_entry *__xfrm_dst_lookup(struct net *net, int tos, int oif, const xfrm_address_t *saddr, const xfrm_address_t *daddr, @@ -2083,6 +2092,11 @@ xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir, if (IS_ERR(xdst)) { err = PTR_ERR(xdst); + if (err == -EREMOTE) { + xfrm_pols_put(pols, num_pols); + return NULL; + } + if (err != -EAGAIN) goto error; goto make_dummy_bundle; @@ -2176,6 +2190,9 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, if (IS_ERR(xdst)) { xfrm_pols_put(pols, num_pols); err = PTR_ERR(xdst); + if (err == -EREMOTE) + goto nopol; + goto dropdst; } else if (xdst == NULL) { num_xfrms = 0; @@ -2368,12 +2385,20 @@ int __xfrm_decode_session(struct sk_buff *skb, struct flowi *fl, unsigned int family, int reverse) { const struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family); + const struct xfrm_if_cb *ifcb = xfrm_if_get_cb(); + struct xfrm_if *xi; int err; if (unlikely(afinfo == NULL)) return -EAFNOSUPPORT; afinfo->decode_session(skb, fl, reverse); + if (ifcb) { + xi = ifcb->decode_session(skb); + if (xi) + fl->flowi_xfrm.if_id = xi->p.if_id; + } + err = security_xfrm_decode_session(skb, &fl->flowi_secid); rcu_read_unlock(); return err; @@ -2828,6 +2853,21 @@ void xfrm_policy_unregister_afinfo(const struct xfrm_policy_afinfo *afinfo) } EXPORT_SYMBOL(xfrm_policy_unregister_afinfo); +void xfrm_if_register_cb(const struct xfrm_if_cb *ifcb) +{ + spin_lock(&xfrm_if_cb_lock); + rcu_assign_pointer(xfrm_if_cb, ifcb); + spin_unlock(&xfrm_if_cb_lock); +} +EXPORT_SYMBOL(xfrm_if_register_cb); + +void xfrm_if_unregister_cb(void) +{ + RCU_INIT_POINTER(xfrm_if_cb, NULL); + synchronize_rcu(); +} +EXPORT_SYMBOL(xfrm_if_unregister_cb); + #ifdef CONFIG_XFRM_STATISTICS static int __net_init xfrm_statistics_init(struct net *net) { @@ -3008,6 +3048,9 @@ void __init xfrm_init(void) xfrm_dev_init(); seqcount_init(&xfrm_policy_hash_generation); xfrm_input_init(); + + RCU_INIT_POINTER(xfrm_if_cb, NULL); + synchronize_rcu(); } #ifdef CONFIG_AUDITSYSCALL -- cgit v1.2.3 From 63a67a926e214dac94e29147c0f3d11499f655a1 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 23 Jun 2018 17:16:44 -0400 Subject: kill dentry_update_name_case() the last user is gone Spotted-by: Richard Weinberger Signed-off-by: Al Viro --- fs/dcache.c | 27 --------------------------- include/linux/dcache.h | 2 -- 2 files changed, 29 deletions(-) (limited to 'include') diff --git a/fs/dcache.c b/fs/dcache.c index 0e8e5de3c48a..d9323af88ed0 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -2676,33 +2676,6 @@ struct dentry *d_exact_alias(struct dentry *entry, struct inode *inode) } EXPORT_SYMBOL(d_exact_alias); -/** - * dentry_update_name_case - update case insensitive dentry with a new name - * @dentry: dentry to be updated - * @name: new name - * - * Update a case insensitive dentry with new case of name. - * - * dentry must have been returned by d_lookup with name @name. Old and new - * name lengths must match (ie. no d_compare which allows mismatched name - * lengths). - * - * Parent inode i_mutex must be held over d_lookup and into this call (to - * keep renames and concurrent inserts, and readdir(2) away). - */ -void dentry_update_name_case(struct dentry *dentry, const struct qstr *name) -{ - BUG_ON(!inode_is_locked(dentry->d_parent->d_inode)); - BUG_ON(dentry->d_name.len != name->len); /* d_lookup gives this */ - - spin_lock(&dentry->d_lock); - write_seqcount_begin(&dentry->d_seq); - memcpy((unsigned char *)dentry->d_name.name, name->name, name->len); - write_seqcount_end(&dentry->d_seq); - spin_unlock(&dentry->d_lock); -} -EXPORT_SYMBOL(dentry_update_name_case); - static void swap_names(struct dentry *dentry, struct dentry *target) { if (unlikely(dname_external(target))) { diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 66c6e17e61e5..cee70bf207fc 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -271,8 +271,6 @@ extern void d_rehash(struct dentry *); extern void d_add(struct dentry *, struct inode *); -extern void dentry_update_name_case(struct dentry *, const struct qstr *); - /* used for rename() and baskets */ extern void d_move(struct dentry *, struct dentry *); extern void d_exchange(struct dentry *, struct dentry *); -- cgit v1.2.3 From d0dd63a8aee1ef89f2e48e554b796b9f9e4fcadb Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Sat, 16 Jun 2018 22:11:42 -0700 Subject: time: Introduce struct __kernel_itimerspec struct itimerspec is not y2038-safe. Introduce a new struct __kernel_itimerspec based on the kernel internal y2038-safe struct itimerspec64. The definition of struct __kernel_itimerspec includes two struct __kernel_timespec. Since struct __kernel_timespec has the same representation in native and compat modes, so does struct __kernel_itimerspec. This helps have a common entry point for syscalls using struct __kernel_itimerspec. New y2038-safe syscalls will use this new type. Since most of the new syscalls are just an update to the native syscalls with the type update, place the new definition under CONFIG_64BIT_TIME. This helps architectures that do not support the above config to keep using the old definition of struct itimerspec. Also change the get/put_itimerspec64 to use struct__kernel_itimerspec. This will help 32 bit architectures to use the new syscalls when architectures select CONFIG_64BIT_TIME. Signed-off-by: Deepa Dinamani Signed-off-by: Thomas Gleixner Cc: arnd@arndb.de Cc: viro@zeniv.linux.org.uk Cc: linux-fsdevel@vger.kernel.org Cc: linux-api@vger.kernel.org Cc: y2038@lists.linaro.org Link: https://lkml.kernel.org/r/20180617051144.29756-2-deepa.kernel@gmail.com --- include/linux/time.h | 4 ++-- include/linux/time64.h | 1 + include/uapi/linux/time.h | 7 +++++++ kernel/time/time.c | 4 ++-- 4 files changed, 12 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/time.h b/include/linux/time.h index aed74463592d..27d83fd2ae61 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -14,9 +14,9 @@ int get_timespec64(struct timespec64 *ts, int put_timespec64(const struct timespec64 *ts, struct __kernel_timespec __user *uts); int get_itimerspec64(struct itimerspec64 *it, - const struct itimerspec __user *uit); + const struct __kernel_itimerspec __user *uit); int put_itimerspec64(const struct itimerspec64 *it, - struct itimerspec __user *uit); + struct __kernel_itimerspec __user *uit); extern time64_t mktime64(const unsigned int year, const unsigned int mon, const unsigned int day, const unsigned int hour, diff --git a/include/linux/time64.h b/include/linux/time64.h index 0a7b2f79cec7..05634afba0db 100644 --- a/include/linux/time64.h +++ b/include/linux/time64.h @@ -12,6 +12,7 @@ typedef __u64 timeu64_t; */ #ifndef CONFIG_64BIT_TIME #define __kernel_timespec timespec +#define __kernel_itimerspec itimerspec #endif #include diff --git a/include/uapi/linux/time.h b/include/uapi/linux/time.h index fcf936656493..6b56a2208be7 100644 --- a/include/uapi/linux/time.h +++ b/include/uapi/linux/time.h @@ -49,6 +49,13 @@ struct __kernel_timespec { }; #endif +#ifndef __kernel_itimerspec +struct __kernel_itimerspec { + struct __kernel_timespec it_interval; /* timer period */ + struct __kernel_timespec it_value; /* timer expiration */ +}; +#endif + /* * legacy timeval structure, only embedded in structures that * traditionally used 'timeval' to pass time intervals (not absolute diff --git a/kernel/time/time.c b/kernel/time/time.c index b1225db61eb2..c0195225fdce 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -927,7 +927,7 @@ int compat_put_timespec64(const struct timespec64 *ts, void __user *uts) EXPORT_SYMBOL_GPL(compat_put_timespec64); int get_itimerspec64(struct itimerspec64 *it, - const struct itimerspec __user *uit) + const struct __kernel_itimerspec __user *uit) { int ret; @@ -942,7 +942,7 @@ int get_itimerspec64(struct itimerspec64 *it, EXPORT_SYMBOL_GPL(get_itimerspec64); int put_itimerspec64(const struct itimerspec64 *it, - struct itimerspec __user *uit) + struct __kernel_itimerspec __user *uit) { int ret; -- cgit v1.2.3 From afef05cf238cfcecdc5ea9b06f31027b13ce6214 Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Sat, 16 Jun 2018 22:11:43 -0700 Subject: time: Enable get/put_compat_itimerspec64 always This will aid in enabling the compat syscalls on 32-bit architectures later on. Also move compat_itimerspec and related defines to compat_time.h. The compat_time.h file will eventually be deleted. Signed-off-by: Deepa Dinamani Signed-off-by: Thomas Gleixner Cc: arnd@arndb.de Cc: viro@zeniv.linux.org.uk Cc: linux-fsdevel@vger.kernel.org Cc: linux-api@vger.kernel.org Cc: y2038@lists.linaro.org Link: https://lkml.kernel.org/r/20180617051144.29756-3-deepa.kernel@gmail.com --- include/linux/compat.h | 9 --------- include/linux/compat_time.h | 9 +++++++++ kernel/compat.c | 29 ----------------------------- kernel/time/time.c | 21 +++++++++++++++++++++ 4 files changed, 30 insertions(+), 38 deletions(-) (limited to 'include') diff --git a/include/linux/compat.h b/include/linux/compat.h index b1a5562b3215..18a13f2df14b 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -109,11 +109,6 @@ typedef compat_ulong_t compat_aio_context_t; struct compat_sel_arg_struct; struct rusage; -struct compat_itimerspec { - struct compat_timespec it_interval; - struct compat_timespec it_value; -}; - struct compat_utimbuf { compat_time_t actime; compat_time_t modtime; @@ -294,10 +289,6 @@ extern int compat_get_timespec(struct timespec *, const void __user *); extern int compat_put_timespec(const struct timespec *, void __user *); extern int compat_get_timeval(struct timeval *, const void __user *); extern int compat_put_timeval(const struct timeval *, void __user *); -extern int get_compat_itimerspec64(struct itimerspec64 *its, - const struct compat_itimerspec __user *uits); -extern int put_compat_itimerspec64(const struct itimerspec64 *its, - struct compat_itimerspec __user *uits); struct compat_iovec { compat_uptr_t iov_base; diff --git a/include/linux/compat_time.h b/include/linux/compat_time.h index 31f2774f1994..e70bfd1d2c3f 100644 --- a/include/linux/compat_time.h +++ b/include/linux/compat_time.h @@ -17,7 +17,16 @@ struct compat_timeval { s32 tv_usec; }; +struct compat_itimerspec { + struct compat_timespec it_interval; + struct compat_timespec it_value; +}; + extern int compat_get_timespec64(struct timespec64 *, const void __user *); extern int compat_put_timespec64(const struct timespec64 *, void __user *); +extern int get_compat_itimerspec64(struct itimerspec64 *its, + const struct compat_itimerspec __user *uits); +extern int put_compat_itimerspec64(const struct itimerspec64 *its, + struct compat_itimerspec __user *uits); #endif /* _LINUX_COMPAT_TIME_H */ diff --git a/kernel/compat.c b/kernel/compat.c index 702aa846ddac..8e40efc2928a 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -324,35 +324,6 @@ COMPAT_SYSCALL_DEFINE3(sched_getaffinity, compat_pid_t, pid, unsigned int, len, return ret; } -/* Todo: Delete these extern declarations when get/put_compat_itimerspec64() - * are moved to kernel/time/time.c . - */ -extern int __compat_get_timespec64(struct timespec64 *ts64, - const struct compat_timespec __user *cts); -extern int __compat_put_timespec64(const struct timespec64 *ts64, - struct compat_timespec __user *cts); - -int get_compat_itimerspec64(struct itimerspec64 *its, - const struct compat_itimerspec __user *uits) -{ - - if (__compat_get_timespec64(&its->it_interval, &uits->it_interval) || - __compat_get_timespec64(&its->it_value, &uits->it_value)) - return -EFAULT; - return 0; -} -EXPORT_SYMBOL_GPL(get_compat_itimerspec64); - -int put_compat_itimerspec64(const struct itimerspec64 *its, - struct compat_itimerspec __user *uits) -{ - if (__compat_put_timespec64(&its->it_interval, &uits->it_interval) || - __compat_put_timespec64(&its->it_value, &uits->it_value)) - return -EFAULT; - return 0; -} -EXPORT_SYMBOL_GPL(put_compat_itimerspec64); - /* * We currently only need the following fields from the sigevent * structure: sigev_value, sigev_signo, sig_notify and (sometimes diff --git a/kernel/time/time.c b/kernel/time/time.c index c0195225fdce..72caf051901c 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -955,3 +955,24 @@ int put_itimerspec64(const struct itimerspec64 *it, return ret; } EXPORT_SYMBOL_GPL(put_itimerspec64); + +int get_compat_itimerspec64(struct itimerspec64 *its, + const struct compat_itimerspec __user *uits) +{ + + if (__compat_get_timespec64(&its->it_interval, &uits->it_interval) || + __compat_get_timespec64(&its->it_value, &uits->it_value)) + return -EFAULT; + return 0; +} +EXPORT_SYMBOL_GPL(get_compat_itimerspec64); + +int put_compat_itimerspec64(const struct itimerspec64 *its, + struct compat_itimerspec __user *uits) +{ + if (__compat_put_timespec64(&its->it_interval, &uits->it_interval) || + __compat_put_timespec64(&its->it_value, &uits->it_value)) + return -EFAULT; + return 0; +} +EXPORT_SYMBOL_GPL(put_compat_itimerspec64); -- cgit v1.2.3 From 6ff84735070276d72af716e21c3214ee20d60e70 Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Sat, 16 Jun 2018 22:11:44 -0700 Subject: time: Change types to new y2038 safe __kernel_itimerspec timer_set/gettime and timerfd_set/get apis use struct itimerspec at the user interface layer. struct itimerspec is not y2038-safe. Change these interfaces to use y2038-safe struct __kernel_itimerspec instead. This will help define new syscalls when 32bit architectures select CONFIG_64BIT_TIME. Signed-off-by: Deepa Dinamani Signed-off-by: Thomas Gleixner Cc: arnd@arndb.de Cc: viro@zeniv.linux.org.uk Cc: linux-fsdevel@vger.kernel.org Cc: linux-api@vger.kernel.org Cc: y2038@lists.linaro.org Link: https://lkml.kernel.org/r/20180617051144.29756-4-deepa.kernel@gmail.com --- fs/timerfd.c | 8 ++++---- include/linux/syscalls.h | 10 +++++----- kernel/time/posix-timers.c | 12 +++++++----- 3 files changed, 16 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/fs/timerfd.c b/fs/timerfd.c index d84a2bee4f82..8bb926253f88 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -533,8 +533,8 @@ static int do_timerfd_gettime(int ufd, struct itimerspec64 *t) } SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags, - const struct itimerspec __user *, utmr, - struct itimerspec __user *, otmr) + const struct __kernel_itimerspec __user *, utmr, + struct __kernel_itimerspec __user *, otmr) { struct itimerspec64 new, old; int ret; @@ -550,7 +550,7 @@ SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags, return ret; } -SYSCALL_DEFINE2(timerfd_gettime, int, ufd, struct itimerspec __user *, otmr) +SYSCALL_DEFINE2(timerfd_gettime, int, ufd, struct __kernel_itimerspec __user *, otmr) { struct itimerspec64 kotmr; int ret = do_timerfd_gettime(ufd, &kotmr); @@ -559,7 +559,7 @@ SYSCALL_DEFINE2(timerfd_gettime, int, ufd, struct itimerspec __user *, otmr) return put_itimerspec64(&kotmr, otmr) ? -EFAULT : 0; } -#ifdef CONFIG_COMPAT +#ifdef CONFIG_COMPAT_32BIT_TIME COMPAT_SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags, const struct compat_itimerspec __user *, utmr, struct compat_itimerspec __user *, otmr) diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 73810808cdf2..38b9ec152024 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -501,9 +501,9 @@ asmlinkage long sys_sync_file_range(int fd, loff_t offset, loff_t nbytes, /* fs/timerfd.c */ asmlinkage long sys_timerfd_create(int clockid, int flags); asmlinkage long sys_timerfd_settime(int ufd, int flags, - const struct itimerspec __user *utmr, - struct itimerspec __user *otmr); -asmlinkage long sys_timerfd_gettime(int ufd, struct itimerspec __user *otmr); + const struct __kernel_itimerspec __user *utmr, + struct __kernel_itimerspec __user *otmr); +asmlinkage long sys_timerfd_gettime(int ufd, struct __kernel_itimerspec __user *otmr); /* fs/utimes.c */ asmlinkage long sys_utimensat(int dfd, const char __user *filename, @@ -568,10 +568,10 @@ asmlinkage long sys_timer_create(clockid_t which_clock, struct sigevent __user *timer_event_spec, timer_t __user * created_timer_id); asmlinkage long sys_timer_gettime(timer_t timer_id, - struct itimerspec __user *setting); + struct __kernel_itimerspec __user *setting); asmlinkage long sys_timer_getoverrun(timer_t timer_id); asmlinkage long sys_timer_settime(timer_t timer_id, int flags, - const struct itimerspec __user *new_setting, + const struct __kernel_itimerspec __user *new_setting, struct itimerspec __user *old_setting); asmlinkage long sys_timer_delete(timer_t timer_id); asmlinkage long sys_clock_settime(clockid_t which_clock, diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index fcf90a10c43a..80d59333c76e 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -743,7 +743,7 @@ static int do_timer_gettime(timer_t timer_id, struct itimerspec64 *setting) /* Get the time remaining on a POSIX.1b interval timer. */ SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id, - struct itimerspec __user *, setting) + struct __kernel_itimerspec __user *, setting) { struct itimerspec64 cur_setting; @@ -755,7 +755,8 @@ SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id, return ret; } -#ifdef CONFIG_COMPAT +#ifdef CONFIG_COMPAT_32BIT_TIME + COMPAT_SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id, struct compat_itimerspec __user *, setting) { @@ -768,6 +769,7 @@ COMPAT_SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id, } return ret; } + #endif /* @@ -906,8 +908,8 @@ retry: /* Set a POSIX.1b interval timer */ SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags, - const struct itimerspec __user *, new_setting, - struct itimerspec __user *, old_setting) + const struct __kernel_itimerspec __user *, new_setting, + struct __kernel_itimerspec __user *, old_setting) { struct itimerspec64 new_spec, old_spec; struct itimerspec64 *rtn = old_setting ? &old_spec : NULL; @@ -927,7 +929,7 @@ SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags, return error; } -#ifdef CONFIG_COMPAT +#ifdef CONFIG_COMPAT_32BIT_TIME COMPAT_SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags, struct compat_itimerspec __user *, new, struct compat_itimerspec __user *, old) -- cgit v1.2.3 From faef87723ace12e5f685437c1e68cbecb69a7a89 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 15 Jun 2018 13:08:51 +0200 Subject: dma-noncoherent: add a arch_sync_dma_for_cpu_all hook The MIPS bmips platform needs a global flush when transferring ownership back to the CPU. Add a hook for that to the dma-noncoherent implementation. Signed-off-by: Christoph Hellwig Patchwork: https://patchwork.linux-mips.org/patch/19549/ Signed-off-by: Paul Burton Cc: Florian Fainelli Cc: David Daney Cc: Kevin Cernekee Cc: Jiaxun Yang Cc: Tom Bogendoerfer Cc: Huacai Chen Cc: iommu@lists.linux-foundation.org Cc: linux-mips@linux-mips.org --- include/linux/dma-noncoherent.h | 8 ++++++++ kernel/dma/noncoherent.c | 8 ++++++-- 2 files changed, 14 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h index 10b2654d549b..a0aa00cc909d 100644 --- a/include/linux/dma-noncoherent.h +++ b/include/linux/dma-noncoherent.h @@ -44,4 +44,12 @@ static inline void arch_sync_dma_for_cpu(struct device *dev, } #endif /* ARCH_HAS_SYNC_DMA_FOR_CPU */ +#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL +void arch_sync_dma_for_cpu_all(struct device *dev); +#else +static inline void arch_sync_dma_for_cpu_all(struct device *dev) +{ +} +#endif /* CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL */ + #endif /* _LINUX_DMA_NONCOHERENT_H */ diff --git a/kernel/dma/noncoherent.c b/kernel/dma/noncoherent.c index 79e9a757387f..031fe235d958 100644 --- a/kernel/dma/noncoherent.c +++ b/kernel/dma/noncoherent.c @@ -49,11 +49,13 @@ static int dma_noncoherent_map_sg(struct device *dev, struct scatterlist *sgl, return nents; } -#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU +#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ + defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) static void dma_noncoherent_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir) { arch_sync_dma_for_cpu(dev, dma_to_phys(dev, addr), size, dir); + arch_sync_dma_for_cpu_all(dev); } static void dma_noncoherent_sync_sg_for_cpu(struct device *dev, @@ -64,6 +66,7 @@ static void dma_noncoherent_sync_sg_for_cpu(struct device *dev, for_each_sg(sgl, sg, nents, i) arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir); + arch_sync_dma_for_cpu_all(dev); } static void dma_noncoherent_unmap_page(struct device *dev, dma_addr_t addr, @@ -89,7 +92,8 @@ const struct dma_map_ops dma_noncoherent_ops = { .sync_sg_for_device = dma_noncoherent_sync_sg_for_device, .map_page = dma_noncoherent_map_page, .map_sg = dma_noncoherent_map_sg, -#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU +#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ + defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) .sync_single_for_cpu = dma_noncoherent_sync_single_for_cpu, .sync_sg_for_cpu = dma_noncoherent_sync_sg_for_cpu, .unmap_page = dma_noncoherent_unmap_page, -- cgit v1.2.3 From e4db5b61c572475bbbcf63e3c8a2606bfccf2c9d Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 25 Jun 2018 17:26:02 +0200 Subject: xfrm: policy: remove pcpu policy cache Kristian Evensen says: In a project I am involved in, we are running ipsec (Strongswan) on different mt7621-based routers. Each router is configured as an initiator and has around ~30 tunnels to different responders (running on misc. devices). Before the flow cache was removed (kernel 4.9), we got a combined throughput of around 70Mbit/s for all tunnels on one router. However, we recently switched to kernel 4.14 (4.14.48), and the total throughput is somewhere around 57Mbit/s (best-case). I.e., a drop of around 20%. Reverting the flow cache removal restores, as expected, performance levels to that of kernel 4.9. When pcpu xdst exists, it has to be validated first before it can be used. A negative hit thus increases cost vs. no-cache. As number of tunnels increases, hit rate decreases so this pcpu caching isn't a viable strategy. Furthermore, the xdst cache also needs to run with BH off, so when removing this the bh disable/enable pairs can be removed too. Kristian tested a 4.14.y backport of this change and reported increased performance: In our tests, the throughput reduction has been reduced from around -20% to -5%. We also see that the overall throughput is independent of the number of tunnels, while before the throughput was reduced as the number of tunnels increased. Reported-by: Kristian Evensen Signed-off-by: Florian Westphal Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 1 - net/xfrm/xfrm_device.c | 10 ---- net/xfrm/xfrm_policy.c | 139 +------------------------------------------------ net/xfrm/xfrm_state.c | 5 +- 4 files changed, 3 insertions(+), 152 deletions(-) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 3fa578a6a819..a5378613a49c 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -332,7 +332,6 @@ int xfrm_policy_register_afinfo(const struct xfrm_policy_afinfo *afinfo, int fam void xfrm_policy_unregister_afinfo(const struct xfrm_policy_afinfo *afinfo); void km_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c); -void xfrm_policy_cache_flush(void); void km_state_notify(struct xfrm_state *x, const struct km_event *c); struct xfrm_tmpl; diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 16c1230d20fa..11d56a44e9e8 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -307,12 +307,6 @@ static int xfrm_dev_register(struct net_device *dev) return xfrm_api_check(dev); } -static int xfrm_dev_unregister(struct net_device *dev) -{ - xfrm_policy_cache_flush(); - return NOTIFY_DONE; -} - static int xfrm_dev_feat_change(struct net_device *dev) { return xfrm_api_check(dev); @@ -323,7 +317,6 @@ static int xfrm_dev_down(struct net_device *dev) if (dev->features & NETIF_F_HW_ESP) xfrm_dev_state_flush(dev_net(dev), dev, true); - xfrm_policy_cache_flush(); return NOTIFY_DONE; } @@ -335,9 +328,6 @@ static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void case NETDEV_REGISTER: return xfrm_dev_register(dev); - case NETDEV_UNREGISTER: - return xfrm_dev_unregister(dev); - case NETDEV_FEAT_CHANGE: return xfrm_dev_feat_change(dev); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index d960ea6657b5..ef75891450e7 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -45,8 +45,6 @@ struct xfrm_flo { u8 flags; }; -static DEFINE_PER_CPU(struct xfrm_dst *, xfrm_last_dst); -static struct work_struct *xfrm_pcpu_work __read_mostly; static DEFINE_SPINLOCK(xfrm_if_cb_lock); static struct xfrm_if_cb const __rcu *xfrm_if_cb __read_mostly; @@ -1732,108 +1730,6 @@ static int xfrm_expand_policies(const struct flowi *fl, u16 family, } -static void xfrm_last_dst_update(struct xfrm_dst *xdst, struct xfrm_dst *old) -{ - this_cpu_write(xfrm_last_dst, xdst); - if (old) - dst_release(&old->u.dst); -} - -static void __xfrm_pcpu_work_fn(void) -{ - struct xfrm_dst *old; - - old = this_cpu_read(xfrm_last_dst); - if (old && !xfrm_bundle_ok(old)) - xfrm_last_dst_update(NULL, old); -} - -static void xfrm_pcpu_work_fn(struct work_struct *work) -{ - local_bh_disable(); - rcu_read_lock(); - __xfrm_pcpu_work_fn(); - rcu_read_unlock(); - local_bh_enable(); -} - -void xfrm_policy_cache_flush(void) -{ - struct xfrm_dst *old; - bool found = false; - int cpu; - - might_sleep(); - - local_bh_disable(); - rcu_read_lock(); - for_each_possible_cpu(cpu) { - old = per_cpu(xfrm_last_dst, cpu); - if (old && !xfrm_bundle_ok(old)) { - if (smp_processor_id() == cpu) { - __xfrm_pcpu_work_fn(); - continue; - } - found = true; - break; - } - } - - rcu_read_unlock(); - local_bh_enable(); - - if (!found) - return; - - get_online_cpus(); - - for_each_possible_cpu(cpu) { - bool bundle_release; - - rcu_read_lock(); - old = per_cpu(xfrm_last_dst, cpu); - bundle_release = old && !xfrm_bundle_ok(old); - rcu_read_unlock(); - - if (!bundle_release) - continue; - - if (cpu_online(cpu)) { - schedule_work_on(cpu, &xfrm_pcpu_work[cpu]); - continue; - } - - rcu_read_lock(); - old = per_cpu(xfrm_last_dst, cpu); - if (old && !xfrm_bundle_ok(old)) { - per_cpu(xfrm_last_dst, cpu) = NULL; - dst_release(&old->u.dst); - } - rcu_read_unlock(); - } - - put_online_cpus(); -} - -static bool xfrm_xdst_can_reuse(struct xfrm_dst *xdst, - struct xfrm_state * const xfrm[], - int num) -{ - const struct dst_entry *dst = &xdst->u.dst; - int i; - - if (xdst->num_xfrms != num) - return false; - - for (i = 0; i < num; i++) { - if (!dst || dst->xfrm != xfrm[i]) - return false; - dst = xfrm_dst_child(dst); - } - - return xfrm_bundle_ok(xdst); -} - static struct xfrm_dst * xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols, const struct flowi *fl, u16 family, @@ -1842,7 +1738,7 @@ xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols, struct net *net = xp_net(pols[0]); struct xfrm_state *xfrm[XFRM_MAX_DEPTH]; struct xfrm_dst *bundle[XFRM_MAX_DEPTH]; - struct xfrm_dst *xdst, *old; + struct xfrm_dst *xdst; struct dst_entry *dst; int err; @@ -1854,22 +1750,6 @@ xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols, return ERR_PTR(err); } - xdst = this_cpu_read(xfrm_last_dst); - if (xdst && - xdst->u.dst.dev == dst_orig->dev && - xdst->num_pols == num_pols && - memcmp(xdst->pols, pols, - sizeof(struct xfrm_policy *) * num_pols) == 0 && - xfrm_xdst_can_reuse(xdst, xfrm, err)) { - dst_hold(&xdst->u.dst); - xfrm_pols_put(pols, num_pols); - while (err > 0) - xfrm_state_put(xfrm[--err]); - return xdst; - } - - old = xdst; - dst = xfrm_bundle_create(pols[0], xfrm, bundle, err, fl, dst_orig); if (IS_ERR(dst)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTBUNDLEGENERROR); @@ -1882,9 +1762,6 @@ xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols, memcpy(xdst->pols, pols, sizeof(struct xfrm_policy *) * num_pols); xdst->policy_genid = atomic_read(&pols[0]->genid); - atomic_set(&xdst->u.dst.__refcnt, 2); - xfrm_last_dst_update(xdst, old); - return xdst; } @@ -2085,11 +1962,8 @@ xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir, if (num_xfrms <= 0) goto make_dummy_bundle; - local_bh_disable(); xdst = xfrm_resolve_and_create_bundle(pols, num_pols, fl, family, xflo->dst_orig); - local_bh_enable(); - if (IS_ERR(xdst)) { err = PTR_ERR(xdst); if (err == -EREMOTE) { @@ -2181,11 +2055,9 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, goto no_transform; } - local_bh_disable(); xdst = xfrm_resolve_and_create_bundle( pols, num_pols, fl, family, dst_orig); - local_bh_enable(); if (IS_ERR(xdst)) { xfrm_pols_put(pols, num_pols); @@ -3035,15 +2907,6 @@ static struct pernet_operations __net_initdata xfrm_net_ops = { void __init xfrm_init(void) { - int i; - - xfrm_pcpu_work = kmalloc_array(NR_CPUS, sizeof(*xfrm_pcpu_work), - GFP_KERNEL); - BUG_ON(!xfrm_pcpu_work); - - for (i = 0; i < NR_CPUS; i++) - INIT_WORK(&xfrm_pcpu_work[i], xfrm_pcpu_work_fn); - register_pernet_subsys(&xfrm_net_ops); xfrm_dev_init(); seqcount_init(&xfrm_policy_hash_generation); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 3803b6813fc5..e04a510ec992 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -735,10 +735,9 @@ restart: } out: spin_unlock_bh(&net->xfrm.xfrm_state_lock); - if (cnt) { + if (cnt) err = 0; - xfrm_policy_cache_flush(); - } + return err; } EXPORT_SYMBOL(xfrm_state_flush); -- cgit v1.2.3 From fd55a281adf6c9b9723d369203fdd92e5ea62a09 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 27 Apr 2018 10:06:03 -0700 Subject: srcu: Introduce srcu_read_{un,}lock_notrace() Joel Fernandes is using SRCU to protect from-idle tracepoints, which requires notrace variants of srcu_read_lock() and srcu_read_unlock() in order to avoid problems with tracepoints in lockdep. This commit therefore adds srcu_read_lock_notrace() and srcu_read_unlock_notrace(). [1] http://lkml.kernel.org/r/20180427042656.190746-1-joelaf@google.com Reported-by: Joel Fernandes Intermittently-reported-by: Steven Rostedt Signed-off-by: Paul E. McKenney --- include/linux/srcu.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include') diff --git a/include/linux/srcu.h b/include/linux/srcu.h index 91494d7e8e41..3e72a291c401 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -195,6 +195,16 @@ static inline int srcu_read_lock(struct srcu_struct *sp) __acquires(sp) return retval; } +/* Used by tracing, cannot be traced and cannot invoke lockdep. */ +static inline notrace int +srcu_read_lock_notrace(struct srcu_struct *sp) __acquires(sp) +{ + int retval; + + retval = __srcu_read_lock(sp); + return retval; +} + /** * srcu_read_unlock - unregister a old reader from an SRCU-protected structure. * @sp: srcu_struct in which to unregister the old reader. @@ -209,6 +219,13 @@ static inline void srcu_read_unlock(struct srcu_struct *sp, int idx) __srcu_read_unlock(sp, idx); } +/* Used by tracing, cannot be traced and cannot call lockdep. */ +static inline notrace void +srcu_read_unlock_notrace(struct srcu_struct *sp, int idx) __releases(sp) +{ + __srcu_read_unlock(sp, idx); +} + /** * smp_mb__after_srcu_read_unlock - ensure full ordering after srcu_read_unlock * -- cgit v1.2.3 From 90127d605f403d814f4986436871210bf8ceb335 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 9 May 2018 10:29:18 -0700 Subject: torture: Make online/offline messages appear only for verbose=2 Some bugs reproduce quickly only at high CPU-hotplug rates, so the rcutorture TREE03 scenario now has only 200 milliseconds spacing between CPU-hotplug operations. At this rate, the torture-test pair of console messages per operation becomes a bit voluminous. This commit therefore converts the torture-test set of "verbose" kernel-boot arguments from bool to int, and prints the extra console messages only when verbose=2. The default is still verbose=1. Signed-off-by: Paul E. McKenney --- include/linux/torture.h | 2 +- kernel/locking/locktorture.c | 2 +- kernel/rcu/rcuperf.c | 2 +- kernel/rcu/rcutorture.c | 2 +- kernel/torture.c | 12 ++++++------ 5 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/torture.h b/include/linux/torture.h index 66272862070b..a55e80817dae 100644 --- a/include/linux/torture.h +++ b/include/linux/torture.h @@ -79,7 +79,7 @@ void stutter_wait(const char *title); int torture_stutter_init(int s); /* Initialization and cleanup. */ -bool torture_init_begin(char *ttype, bool v); +bool torture_init_begin(char *ttype, int v); void torture_init_end(void); bool torture_cleanup_begin(void); void torture_cleanup_end(void); diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c index 8402b3349dca..4a2e13870a9b 100644 --- a/kernel/locking/locktorture.c +++ b/kernel/locking/locktorture.c @@ -57,7 +57,7 @@ torture_param(int, shutdown_secs, 0, "Shutdown time (j), <= zero to disable."); torture_param(int, stat_interval, 60, "Number of seconds between stats printk()s"); torture_param(int, stutter, 5, "Number of jiffies to run/halt test, 0=disable"); -torture_param(bool, verbose, true, +torture_param(int, verbose, 1, "Enable verbose debugging printk()s"); static char *torture_type = "spin_lock"; diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c index e232846516b3..fb8094848906 100644 --- a/kernel/rcu/rcuperf.c +++ b/kernel/rcu/rcuperf.c @@ -88,7 +88,7 @@ torture_param(int, nreaders, -1, "Number of RCU reader threads"); torture_param(int, nwriters, -1, "Number of RCU updater threads"); torture_param(bool, shutdown, !IS_ENABLED(MODULE), "Shutdown at end of performance tests."); -torture_param(bool, verbose, true, "Enable verbose debugging printk()s"); +torture_param(int, verbose, 1, "Enable verbose debugging printk()s"); torture_param(int, writer_holdoff, 0, "Holdoff (us) between GPs, zero to disable"); static char *perf_type = "rcu"; diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index 42fcb7f05fac..a5540bd831c4 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -101,7 +101,7 @@ torture_param(int, test_boost_interval, 7, "Interval between boost tests, seconds."); torture_param(bool, test_no_idle_hz, true, "Test support for tickless idle CPUs"); -torture_param(bool, verbose, true, +torture_param(int, verbose, 1, "Enable verbose debugging printk()s"); static char *torture_type = "rcu"; diff --git a/kernel/torture.c b/kernel/torture.c index 3de1efbecd6a..840fd33c1cda 100644 --- a/kernel/torture.c +++ b/kernel/torture.c @@ -53,7 +53,7 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Paul E. McKenney "); static char *torture_type; -static bool verbose; +static int verbose; /* Mediate rmmod and system shutdown. Concurrent rmmod & shutdown illegal! */ #define FULLSTOP_DONTSTOP 0 /* Normal operation. */ @@ -98,7 +98,7 @@ bool torture_offline(int cpu, long *n_offl_attempts, long *n_offl_successes, if (!cpu_online(cpu) || !cpu_is_hotpluggable(cpu)) return false; - if (verbose) + if (verbose > 1) pr_alert("%s" TORTURE_FLAG "torture_onoff task: offlining %d\n", torture_type, cpu); @@ -111,7 +111,7 @@ bool torture_offline(int cpu, long *n_offl_attempts, long *n_offl_successes, "torture_onoff task: offline %d failed: errno %d\n", torture_type, cpu, ret); } else { - if (verbose) + if (verbose > 1) pr_alert("%s" TORTURE_FLAG "torture_onoff task: offlined %d\n", torture_type, cpu); @@ -147,7 +147,7 @@ bool torture_online(int cpu, long *n_onl_attempts, long *n_onl_successes, if (cpu_online(cpu) || !cpu_is_hotpluggable(cpu)) return false; - if (verbose) + if (verbose > 1) pr_alert("%s" TORTURE_FLAG "torture_onoff task: onlining %d\n", torture_type, cpu); @@ -160,7 +160,7 @@ bool torture_online(int cpu, long *n_onl_attempts, long *n_onl_successes, "torture_onoff task: online %d failed: errno %d\n", torture_type, cpu, ret); } else { - if (verbose) + if (verbose > 1) pr_alert("%s" TORTURE_FLAG "torture_onoff task: onlined %d\n", torture_type, cpu); @@ -647,7 +647,7 @@ static void torture_stutter_cleanup(void) * The runnable parameter points to a flag that controls whether or not * the test is currently runnable. If there is no such flag, pass in NULL. */ -bool torture_init_begin(char *ttype, bool v) +bool torture_init_begin(char *ttype, int v) { mutex_lock(&fullstop_mutex); if (torture_type != NULL) { -- cgit v1.2.3 From d4546c2509b1e9cd082e3682dcec98472e37ee5a Mon Sep 17 00:00:00 2001 From: David Miller Date: Sun, 24 Jun 2018 14:13:49 +0900 Subject: net: Convert GRO SKB handling to list_head. Manage pending per-NAPI GRO packets via list_head. Return an SKB pointer from the GRO receive handlers. When GRO receive handlers return non-NULL, it means that this SKB needs to be completed at this time and removed from the NAPI queue. Several operations are greatly simplified by this transformation, especially timing out the oldest SKB in the list when gro_count exceeds MAX_GRO_SKBS, and napi_gro_flush() which walks the queue in reverse order. Signed-off-by: David S. Miller --- drivers/net/geneve.c | 11 ++++---- drivers/net/vxlan.c | 11 ++++---- include/linux/etherdevice.h | 3 +- include/linux/netdevice.h | 32 ++++++++++----------- include/linux/skbuff.h | 3 +- include/linux/udp.h | 4 +-- include/net/inet_common.h | 2 +- include/net/tcp.h | 2 +- include/net/udp.h | 4 +-- include/net/udp_tunnel.h | 6 ++-- net/8021q/vlan.c | 13 +++++---- net/core/dev.c | 68 +++++++++++++++++++-------------------------- net/core/skbuff.c | 4 +-- net/ethernet/eth.c | 12 ++++---- net/ipv4/af_inet.c | 12 ++++---- net/ipv4/esp4_offload.c | 4 +-- net/ipv4/fou.c | 20 ++++++------- net/ipv4/gre_offload.c | 8 +++--- net/ipv4/tcp_offload.c | 14 +++++----- net/ipv4/udp_offload.c | 13 +++++---- net/ipv6/esp6_offload.c | 4 +-- net/ipv6/ip6_offload.c | 16 +++++------ net/ipv6/tcpv6_offload.c | 4 +-- net/ipv6/udp_offload.c | 4 +-- 24 files changed, 133 insertions(+), 141 deletions(-) (limited to 'include') diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 750eaa53bf0c..3e94375b9b01 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -418,11 +418,12 @@ static int geneve_hlen(struct genevehdr *gh) return sizeof(*gh) + gh->opt_len * 4; } -static struct sk_buff **geneve_gro_receive(struct sock *sk, - struct sk_buff **head, - struct sk_buff *skb) +static struct sk_buff *geneve_gro_receive(struct sock *sk, + struct list_head *head, + struct sk_buff *skb) { - struct sk_buff *p, **pp = NULL; + struct sk_buff *pp = NULL; + struct sk_buff *p; struct genevehdr *gh, *gh2; unsigned int hlen, gh_len, off_gnv; const struct packet_offload *ptype; @@ -449,7 +450,7 @@ static struct sk_buff **geneve_gro_receive(struct sock *sk, goto out; } - for (p = *head; p; p = p->next) { + list_for_each_entry(p, head, list) { if (!NAPI_GRO_CB(p)->same_flow) continue; diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index aee0e60471f1..cc14e0cd5647 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -568,11 +568,12 @@ static struct vxlanhdr *vxlan_gro_remcsum(struct sk_buff *skb, return vh; } -static struct sk_buff **vxlan_gro_receive(struct sock *sk, - struct sk_buff **head, - struct sk_buff *skb) +static struct sk_buff *vxlan_gro_receive(struct sock *sk, + struct list_head *head, + struct sk_buff *skb) { - struct sk_buff *p, **pp = NULL; + struct sk_buff *pp = NULL; + struct sk_buff *p; struct vxlanhdr *vh, *vh2; unsigned int hlen, off_vx; int flush = 1; @@ -607,7 +608,7 @@ static struct sk_buff **vxlan_gro_receive(struct sock *sk, skb_gro_pull(skb, sizeof(struct vxlanhdr)); /* pull vxlan header */ - for (p = *head; p; p = p->next) { + list_for_each_entry(p, head, list) { if (!NAPI_GRO_CB(p)->same_flow) continue; diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 79563840c295..572e11bb8696 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -59,8 +59,7 @@ struct net_device *devm_alloc_etherdev_mqs(struct device *dev, int sizeof_priv, unsigned int rxqs); #define devm_alloc_etherdev(dev, sizeof_priv) devm_alloc_etherdev_mqs(dev, sizeof_priv, 1, 1) -struct sk_buff **eth_gro_receive(struct sk_buff **head, - struct sk_buff *skb); +struct sk_buff *eth_gro_receive(struct list_head *head, struct sk_buff *skb); int eth_gro_complete(struct sk_buff *skb, int nhoff); /* Reserved Ethernet Addresses per IEEE 802.1Q */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3ec9850c7936..f176d9873910 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -322,7 +322,7 @@ struct napi_struct { int poll_owner; #endif struct net_device *dev; - struct sk_buff *gro_list; + struct list_head gro_list; struct sk_buff *skb; struct hrtimer timer; struct list_head dev_list; @@ -2255,10 +2255,10 @@ static inline int gro_recursion_inc_test(struct sk_buff *skb) return ++NAPI_GRO_CB(skb)->recursion_counter == GRO_RECURSION_LIMIT; } -typedef struct sk_buff **(*gro_receive_t)(struct sk_buff **, struct sk_buff *); -static inline struct sk_buff **call_gro_receive(gro_receive_t cb, - struct sk_buff **head, - struct sk_buff *skb) +typedef struct sk_buff *(*gro_receive_t)(struct list_head *, struct sk_buff *); +static inline struct sk_buff *call_gro_receive(gro_receive_t cb, + struct list_head *head, + struct sk_buff *skb) { if (unlikely(gro_recursion_inc_test(skb))) { NAPI_GRO_CB(skb)->flush |= 1; @@ -2268,12 +2268,12 @@ static inline struct sk_buff **call_gro_receive(gro_receive_t cb, return cb(head, skb); } -typedef struct sk_buff **(*gro_receive_sk_t)(struct sock *, struct sk_buff **, - struct sk_buff *); -static inline struct sk_buff **call_gro_receive_sk(gro_receive_sk_t cb, - struct sock *sk, - struct sk_buff **head, - struct sk_buff *skb) +typedef struct sk_buff *(*gro_receive_sk_t)(struct sock *, struct list_head *, + struct sk_buff *); +static inline struct sk_buff *call_gro_receive_sk(gro_receive_sk_t cb, + struct sock *sk, + struct list_head *head, + struct sk_buff *skb) { if (unlikely(gro_recursion_inc_test(skb))) { NAPI_GRO_CB(skb)->flush |= 1; @@ -2299,8 +2299,8 @@ struct packet_type { struct offload_callbacks { struct sk_buff *(*gso_segment)(struct sk_buff *skb, netdev_features_t features); - struct sk_buff **(*gro_receive)(struct sk_buff **head, - struct sk_buff *skb); + struct sk_buff *(*gro_receive)(struct list_head *head, + struct sk_buff *skb); int (*gro_complete)(struct sk_buff *skb, int nhoff); }; @@ -2568,7 +2568,7 @@ struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex); struct net_device *dev_get_by_napi_id(unsigned int napi_id); int netdev_get_name(struct net *net, char *name, int ifindex); int dev_restart(struct net_device *dev); -int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb); +int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb); static inline unsigned int skb_gro_offset(const struct sk_buff *skb) { @@ -2784,13 +2784,13 @@ static inline void skb_gro_remcsum_cleanup(struct sk_buff *skb, } #ifdef CONFIG_XFRM_OFFLOAD -static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp, int flush) +static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff *pp, int flush) { if (PTR_ERR(pp) != -EINPROGRESS) NAPI_GRO_CB(skb)->flush |= flush; } #else -static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp, int flush) +static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff *pp, int flush) { NAPI_GRO_CB(skb)->flush |= flush; } diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index c86885954994..7ccc601b55d9 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -677,7 +677,8 @@ struct sk_buff { int ip_defrag_offset; }; }; - struct rb_node rbnode; /* used in netem & tcp stack */ + struct rb_node rbnode; /* used in netem & tcp stack */ + struct list_head list; }; struct sock *sk; diff --git a/include/linux/udp.h b/include/linux/udp.h index ca840345571b..320d49d85484 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -74,8 +74,8 @@ struct udp_sock { void (*encap_destroy)(struct sock *sk); /* GRO functions for UDP socket */ - struct sk_buff ** (*gro_receive)(struct sock *sk, - struct sk_buff **head, + struct sk_buff * (*gro_receive)(struct sock *sk, + struct list_head *head, struct sk_buff *skb); int (*gro_complete)(struct sock *sk, struct sk_buff *skb, diff --git a/include/net/inet_common.h b/include/net/inet_common.h index 384b90c62c0b..3ca969cbd161 100644 --- a/include/net/inet_common.h +++ b/include/net/inet_common.h @@ -43,7 +43,7 @@ int inet_ctl_sock_create(struct sock **sk, unsigned short family, int inet_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len); -struct sk_buff **inet_gro_receive(struct sk_buff **head, struct sk_buff *skb); +struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb); int inet_gro_complete(struct sk_buff *skb, int nhoff); struct sk_buff *inet_gso_segment(struct sk_buff *skb, netdev_features_t features); diff --git a/include/net/tcp.h b/include/net/tcp.h index 822ee49ed0f9..402a88b0e8a8 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1788,7 +1788,7 @@ void tcp_v4_destroy_sock(struct sock *sk); struct sk_buff *tcp_gso_segment(struct sk_buff *skb, netdev_features_t features); -struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb); +struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb); int tcp_gro_complete(struct sk_buff *skb); void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr); diff --git a/include/net/udp.h b/include/net/udp.h index b1ea8b0f5e6a..5723c6128ae4 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -170,8 +170,8 @@ static inline void udp_csum_pull_header(struct sk_buff *skb) typedef struct sock *(*udp_lookup_t)(struct sk_buff *skb, __be16 sport, __be16 dport); -struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb, - struct udphdr *uh, udp_lookup_t lookup); +struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, + struct udphdr *uh, udp_lookup_t lookup); int udp_gro_complete(struct sk_buff *skb, int nhoff, udp_lookup_t lookup); struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index b95a6927c718..fe680ab6b15a 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -65,9 +65,9 @@ static inline int udp_sock_create(struct net *net, typedef int (*udp_tunnel_encap_rcv_t)(struct sock *sk, struct sk_buff *skb); typedef void (*udp_tunnel_encap_destroy_t)(struct sock *sk); -typedef struct sk_buff **(*udp_tunnel_gro_receive_t)(struct sock *sk, - struct sk_buff **head, - struct sk_buff *skb); +typedef struct sk_buff *(*udp_tunnel_gro_receive_t)(struct sock *sk, + struct list_head *head, + struct sk_buff *skb); typedef int (*udp_tunnel_gro_complete_t)(struct sock *sk, struct sk_buff *skb, int nhoff); diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 73a65789271b..99141986efa0 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -647,13 +647,14 @@ out: return err; } -static struct sk_buff **vlan_gro_receive(struct sk_buff **head, - struct sk_buff *skb) +static struct sk_buff *vlan_gro_receive(struct list_head *head, + struct sk_buff *skb) { - struct sk_buff *p, **pp = NULL; - struct vlan_hdr *vhdr; - unsigned int hlen, off_vlan; const struct packet_offload *ptype; + unsigned int hlen, off_vlan; + struct sk_buff *pp = NULL; + struct vlan_hdr *vhdr; + struct sk_buff *p; __be16 type; int flush = 1; @@ -675,7 +676,7 @@ static struct sk_buff **vlan_gro_receive(struct sk_buff **head, flush = 0; - for (p = *head; p; p = p->next) { + list_for_each_entry(p, head, list) { struct vlan_hdr *vhdr2; if (!NAPI_GRO_CB(p)->same_flow) diff --git a/net/core/dev.c b/net/core/dev.c index a5aa1c7444e6..aa61b9344b46 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4881,36 +4881,25 @@ out: */ void napi_gro_flush(struct napi_struct *napi, bool flush_old) { - struct sk_buff *skb, *prev = NULL; - - /* scan list and build reverse chain */ - for (skb = napi->gro_list; skb != NULL; skb = skb->next) { - skb->prev = prev; - prev = skb; - } - - for (skb = prev; skb; skb = prev) { - skb->next = NULL; + struct sk_buff *skb, *p; + list_for_each_entry_safe_reverse(skb, p, &napi->gro_list, list) { if (flush_old && NAPI_GRO_CB(skb)->age == jiffies) return; - - prev = skb->prev; + list_del_init(&skb->list); napi_gro_complete(skb); napi->gro_count--; } - - napi->gro_list = NULL; } EXPORT_SYMBOL(napi_gro_flush); static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb) { - struct sk_buff *p; unsigned int maclen = skb->dev->hard_header_len; u32 hash = skb_get_hash_raw(skb); + struct sk_buff *p; - for (p = napi->gro_list; p; p = p->next) { + list_for_each_entry(p, &napi->gro_list, list) { unsigned long diffs; NAPI_GRO_CB(p)->flush = 0; @@ -4977,12 +4966,12 @@ static void gro_pull_from_frag0(struct sk_buff *skb, int grow) static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { - struct sk_buff **pp = NULL; + struct list_head *head = &offload_base; struct packet_offload *ptype; __be16 type = skb->protocol; - struct list_head *head = &offload_base; - int same_flow; + struct sk_buff *pp = NULL; enum gro_result ret; + int same_flow; int grow; if (netif_elide_gro(skb->dev)) @@ -5039,11 +5028,8 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff ret = NAPI_GRO_CB(skb)->free ? GRO_MERGED_FREE : GRO_MERGED; if (pp) { - struct sk_buff *nskb = *pp; - - *pp = nskb->next; - nskb->next = NULL; - napi_gro_complete(nskb); + list_del_init(&pp->list); + napi_gro_complete(pp); napi->gro_count--; } @@ -5054,15 +5040,10 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff goto normal; if (unlikely(napi->gro_count >= MAX_GRO_SKBS)) { - struct sk_buff *nskb = napi->gro_list; + struct sk_buff *nskb; - /* locate the end of the list to select the 'oldest' flow */ - while (nskb->next) { - pp = &nskb->next; - nskb = *pp; - } - *pp = NULL; - nskb->next = NULL; + nskb = list_last_entry(&napi->gro_list, struct sk_buff, list); + list_del(&nskb->list); napi_gro_complete(nskb); } else { napi->gro_count++; @@ -5071,8 +5052,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff NAPI_GRO_CB(skb)->age = jiffies; NAPI_GRO_CB(skb)->last = skb; skb_shinfo(skb)->gso_size = skb_gro_len(skb); - skb->next = napi->gro_list; - napi->gro_list = skb; + list_add(&skb->list, &napi->gro_list); ret = GRO_HELD; pull: @@ -5478,7 +5458,7 @@ bool napi_complete_done(struct napi_struct *n, int work_done) NAPIF_STATE_IN_BUSY_POLL))) return false; - if (n->gro_list) { + if (!list_empty(&n->gro_list)) { unsigned long timeout = 0; if (work_done) @@ -5687,7 +5667,7 @@ static enum hrtimer_restart napi_watchdog(struct hrtimer *timer) /* Note : we use a relaxed variant of napi_schedule_prep() not setting * NAPI_STATE_MISSED, since we do not react to a device IRQ. */ - if (napi->gro_list && !napi_disable_pending(napi) && + if (!list_empty(&napi->gro_list) && !napi_disable_pending(napi) && !test_and_set_bit(NAPI_STATE_SCHED, &napi->state)) __napi_schedule_irqoff(napi); @@ -5701,7 +5681,7 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi, hrtimer_init(&napi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED); napi->timer.function = napi_watchdog; napi->gro_count = 0; - napi->gro_list = NULL; + INIT_LIST_HEAD(&napi->gro_list); napi->skb = NULL; napi->poll = poll; if (weight > NAPI_POLL_WEIGHT) @@ -5734,6 +5714,14 @@ void napi_disable(struct napi_struct *n) } EXPORT_SYMBOL(napi_disable); +static void gro_list_free(struct list_head *head) +{ + struct sk_buff *skb, *p; + + list_for_each_entry_safe(skb, p, head, list) + kfree_skb(skb); +} + /* Must be called in process context */ void netif_napi_del(struct napi_struct *napi) { @@ -5743,8 +5731,8 @@ void netif_napi_del(struct napi_struct *napi) list_del_init(&napi->dev_list); napi_free_frags(napi); - kfree_skb_list(napi->gro_list); - napi->gro_list = NULL; + gro_list_free(&napi->gro_list); + INIT_LIST_HEAD(&napi->gro_list); napi->gro_count = 0; } EXPORT_SYMBOL(netif_napi_del); @@ -5787,7 +5775,7 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll) goto out_unlock; } - if (n->gro_list) { + if (!list_empty(&n->gro_list)) { /* flush too old packets * If HZ < 1000, flush all packets. */ diff --git a/net/core/skbuff.c b/net/core/skbuff.c index c642304f178c..b1f274f22d85 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3815,14 +3815,14 @@ err: } EXPORT_SYMBOL_GPL(skb_segment); -int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) +int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb) { struct skb_shared_info *pinfo, *skbinfo = skb_shinfo(skb); unsigned int offset = skb_gro_offset(skb); unsigned int headlen = skb_headlen(skb); unsigned int len = skb_gro_len(skb); - struct sk_buff *lp, *p = *head; unsigned int delta_truesize; + struct sk_buff *lp; if (unlikely(p->len + len >= 65536)) return -E2BIG; diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index ee28440f57c5..fd8faa0dfa61 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -427,13 +427,13 @@ ssize_t sysfs_format_mac(char *buf, const unsigned char *addr, int len) } EXPORT_SYMBOL(sysfs_format_mac); -struct sk_buff **eth_gro_receive(struct sk_buff **head, - struct sk_buff *skb) +struct sk_buff *eth_gro_receive(struct list_head *head, struct sk_buff *skb) { - struct sk_buff *p, **pp = NULL; - struct ethhdr *eh, *eh2; - unsigned int hlen, off_eth; const struct packet_offload *ptype; + unsigned int hlen, off_eth; + struct sk_buff *pp = NULL; + struct ethhdr *eh, *eh2; + struct sk_buff *p; __be16 type; int flush = 1; @@ -448,7 +448,7 @@ struct sk_buff **eth_gro_receive(struct sk_buff **head, flush = 0; - for (p = *head; p; p = p->next) { + list_for_each_entry(p, head, list) { if (!NAPI_GRO_CB(p)->same_flow) continue; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 15e125558c76..06b218a2870f 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1384,12 +1384,12 @@ out: } EXPORT_SYMBOL(inet_gso_segment); -struct sk_buff **inet_gro_receive(struct sk_buff **head, struct sk_buff *skb) +struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb) { const struct net_offload *ops; - struct sk_buff **pp = NULL; - struct sk_buff *p; + struct sk_buff *pp = NULL; const struct iphdr *iph; + struct sk_buff *p; unsigned int hlen; unsigned int off; unsigned int id; @@ -1425,7 +1425,7 @@ struct sk_buff **inet_gro_receive(struct sk_buff **head, struct sk_buff *skb) flush = (u16)((ntohl(*(__be32 *)iph) ^ skb_gro_len(skb)) | (id & ~IP_DF)); id >>= 16; - for (p = *head; p; p = p->next) { + list_for_each_entry(p, head, list) { struct iphdr *iph2; u16 flush_id; @@ -1505,8 +1505,8 @@ out: } EXPORT_SYMBOL(inet_gro_receive); -static struct sk_buff **ipip_gro_receive(struct sk_buff **head, - struct sk_buff *skb) +static struct sk_buff *ipip_gro_receive(struct list_head *head, + struct sk_buff *skb) { if (NAPI_GRO_CB(skb)->encap_mark) { NAPI_GRO_CB(skb)->flush = 1; diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index 7cf755ef9efb..bbeecd13e534 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -28,8 +28,8 @@ #include #include -static struct sk_buff **esp4_gro_receive(struct sk_buff **head, - struct sk_buff *skb) +static struct sk_buff *esp4_gro_receive(struct list_head *head, + struct sk_buff *skb) { int offset = skb_gro_offset(skb); struct xfrm_offload *xo; diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index 1540db65241a..efdc9e1f741e 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -224,14 +224,14 @@ drop: return 0; } -static struct sk_buff **fou_gro_receive(struct sock *sk, - struct sk_buff **head, - struct sk_buff *skb) +static struct sk_buff *fou_gro_receive(struct sock *sk, + struct list_head *head, + struct sk_buff *skb) { - const struct net_offload *ops; - struct sk_buff **pp = NULL; u8 proto = fou_from_sock(sk)->protocol; const struct net_offload **offloads; + const struct net_offload *ops; + struct sk_buff *pp = NULL; /* We can clear the encap_mark for FOU as we are essentially doing * one of two possible things. We are either adding an L4 tunnel @@ -305,13 +305,13 @@ static struct guehdr *gue_gro_remcsum(struct sk_buff *skb, unsigned int off, return guehdr; } -static struct sk_buff **gue_gro_receive(struct sock *sk, - struct sk_buff **head, - struct sk_buff *skb) +static struct sk_buff *gue_gro_receive(struct sock *sk, + struct list_head *head, + struct sk_buff *skb) { const struct net_offload **offloads; const struct net_offload *ops; - struct sk_buff **pp = NULL; + struct sk_buff *pp = NULL; struct sk_buff *p; struct guehdr *guehdr; size_t len, optlen, hdrlen, off; @@ -397,7 +397,7 @@ static struct sk_buff **gue_gro_receive(struct sock *sk, skb_gro_pull(skb, hdrlen); - for (p = *head; p; p = p->next) { + list_for_each_entry(p, head, list) { const struct guehdr *guehdr2; if (!NAPI_GRO_CB(p)->same_flow) diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index 1859c473b21a..b9673c21be45 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -108,10 +108,10 @@ out: return segs; } -static struct sk_buff **gre_gro_receive(struct sk_buff **head, - struct sk_buff *skb) +static struct sk_buff *gre_gro_receive(struct list_head *head, + struct sk_buff *skb) { - struct sk_buff **pp = NULL; + struct sk_buff *pp = NULL; struct sk_buff *p; const struct gre_base_hdr *greh; unsigned int hlen, grehlen; @@ -182,7 +182,7 @@ static struct sk_buff **gre_gro_receive(struct sk_buff **head, null_compute_pseudo); } - for (p = *head; p; p = p->next) { + list_for_each_entry(p, head, list) { const struct gre_base_hdr *greh2; if (!NAPI_GRO_CB(p)->same_flow) diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 8cc7c3487330..f5aee641f825 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -180,9 +180,9 @@ out: return segs; } -struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb) +struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb) { - struct sk_buff **pp = NULL; + struct sk_buff *pp = NULL; struct sk_buff *p; struct tcphdr *th; struct tcphdr *th2; @@ -220,7 +220,7 @@ struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb) len = skb_gro_len(skb); flags = tcp_flag_word(th); - for (; (p = *head); head = &p->next) { + list_for_each_entry(p, head, list) { if (!NAPI_GRO_CB(p)->same_flow) continue; @@ -233,7 +233,7 @@ struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb) goto found; } - + p = NULL; goto out_check_final; found: @@ -263,7 +263,7 @@ found: flush |= (len - 1) >= mss; flush |= (ntohl(th2->seq) + skb_gro_len(p)) ^ ntohl(th->seq); - if (flush || skb_gro_receive(head, skb)) { + if (flush || skb_gro_receive(p, skb)) { mss = 1; goto out_check_final; } @@ -277,7 +277,7 @@ out_check_final: TCP_FLAG_FIN)); if (p && (!NAPI_GRO_CB(skb)->same_flow || flush)) - pp = head; + pp = p; out: NAPI_GRO_CB(skb)->flush |= (flush != 0); @@ -302,7 +302,7 @@ int tcp_gro_complete(struct sk_buff *skb) } EXPORT_SYMBOL(tcp_gro_complete); -static struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *skb) +static struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb) { /* Don't bother verifying checksum if we're going to flush anyway. */ if (!NAPI_GRO_CB(skb)->flush && diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 92dc9e5a7ff3..ac46c1c55c99 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -343,10 +343,11 @@ out: return segs; } -struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb, - struct udphdr *uh, udp_lookup_t lookup) +struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, + struct udphdr *uh, udp_lookup_t lookup) { - struct sk_buff *p, **pp = NULL; + struct sk_buff *pp = NULL; + struct sk_buff *p; struct udphdr *uh2; unsigned int off = skb_gro_offset(skb); int flush = 1; @@ -371,7 +372,7 @@ struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb, unflush: flush = 0; - for (p = *head; p; p = p->next) { + list_for_each_entry(p, head, list) { if (!NAPI_GRO_CB(p)->same_flow) continue; @@ -399,8 +400,8 @@ out: } EXPORT_SYMBOL(udp_gro_receive); -static struct sk_buff **udp4_gro_receive(struct sk_buff **head, - struct sk_buff *skb) +static struct sk_buff *udp4_gro_receive(struct list_head *head, + struct sk_buff *skb) { struct udphdr *uh = udp_gro_udphdr(skb); diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index 27f59b61f70f..ddfa533a84e5 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -49,8 +49,8 @@ static __u16 esp6_nexthdr_esp_offset(struct ipv6hdr *ipv6_hdr, int nhlen) return 0; } -static struct sk_buff **esp6_gro_receive(struct sk_buff **head, - struct sk_buff *skb) +static struct sk_buff *esp6_gro_receive(struct list_head *head, + struct sk_buff *skb) { int offset = skb_gro_offset(skb); struct xfrm_offload *xo; diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 5b3f2f89ef41..37ff4805b20c 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -163,11 +163,11 @@ static int ipv6_exthdrs_len(struct ipv6hdr *iph, return len; } -static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, - struct sk_buff *skb) +static struct sk_buff *ipv6_gro_receive(struct list_head *head, + struct sk_buff *skb) { const struct net_offload *ops; - struct sk_buff **pp = NULL; + struct sk_buff *pp = NULL; struct sk_buff *p; struct ipv6hdr *iph; unsigned int nlen; @@ -214,7 +214,7 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, flush--; nlen = skb_network_header_len(skb); - for (p = *head; p; p = p->next) { + list_for_each_entry(p, head, list) { const struct ipv6hdr *iph2; __be32 first_word; /* */ @@ -263,8 +263,8 @@ out: return pp; } -static struct sk_buff **sit_ip6ip6_gro_receive(struct sk_buff **head, - struct sk_buff *skb) +static struct sk_buff *sit_ip6ip6_gro_receive(struct list_head *head, + struct sk_buff *skb) { /* Common GRO receive for SIT and IP6IP6 */ @@ -278,8 +278,8 @@ static struct sk_buff **sit_ip6ip6_gro_receive(struct sk_buff **head, return ipv6_gro_receive(head, skb); } -static struct sk_buff **ip4ip6_gro_receive(struct sk_buff **head, - struct sk_buff *skb) +static struct sk_buff *ip4ip6_gro_receive(struct list_head *head, + struct sk_buff *skb) { /* Common GRO receive for SIT and IP6IP6 */ diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c index 278e49cd67d4..e72947c99454 100644 --- a/net/ipv6/tcpv6_offload.c +++ b/net/ipv6/tcpv6_offload.c @@ -15,8 +15,8 @@ #include #include "ip6_offload.h" -static struct sk_buff **tcp6_gro_receive(struct sk_buff **head, - struct sk_buff *skb) +static struct sk_buff *tcp6_gro_receive(struct list_head *head, + struct sk_buff *skb) { /* Don't bother verifying checksum if we're going to flush anyway. */ if (!NAPI_GRO_CB(skb)->flush && diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index 03a2ff3fe1e6..95dee9ca8d22 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -114,8 +114,8 @@ out: return segs; } -static struct sk_buff **udp6_gro_receive(struct sk_buff **head, - struct sk_buff *skb) +static struct sk_buff *udp6_gro_receive(struct list_head *head, + struct sk_buff *skb) { struct udphdr *uh = udp_gro_udphdr(skb); -- cgit v1.2.3 From 07d78363dcffd9cb1bf6f06a6cac0e0847f3c1de Mon Sep 17 00:00:00 2001 From: David Miller Date: Sun, 24 Jun 2018 14:14:02 +0900 Subject: net: Convert NAPI gro list into a small hash table. Improve the performance of GRO receive by splitting flows into multiple hash chains. Suggested-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +- net/core/dev.c | 105 ++++++++++++++++++++++++++++++++++------------ 2 files changed, 81 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f176d9873910..c6b377a15869 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -305,6 +305,7 @@ int __init netdev_boot_setup(char *str); /* * Structure for NAPI scheduling similar to tasklet but with weighting */ +#define GRO_HASH_BUCKETS 8 struct napi_struct { /* The poll_list must only be managed by the entity which * changes the state of the NAPI_STATE_SCHED bit. This means @@ -322,7 +323,7 @@ struct napi_struct { int poll_owner; #endif struct net_device *dev; - struct list_head gro_list; + struct list_head gro_hash[GRO_HASH_BUCKETS]; struct sk_buff *skb; struct hrtimer timer; struct list_head dev_list; diff --git a/net/core/dev.c b/net/core/dev.c index aa61b9344b46..dffed642e686 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4875,15 +4875,12 @@ out: return netif_receive_skb_internal(skb); } -/* napi->gro_list contains packets ordered by age. - * youngest packets at the head of it. - * Complete skbs in reverse order to reduce latencies. - */ -void napi_gro_flush(struct napi_struct *napi, bool flush_old) +static void __napi_gro_flush_chain(struct napi_struct *napi, struct list_head *head, + bool flush_old) { struct sk_buff *skb, *p; - list_for_each_entry_safe_reverse(skb, p, &napi->gro_list, list) { + list_for_each_entry_safe_reverse(skb, p, head, list) { if (flush_old && NAPI_GRO_CB(skb)->age == jiffies) return; list_del_init(&skb->list); @@ -4891,15 +4888,33 @@ void napi_gro_flush(struct napi_struct *napi, bool flush_old) napi->gro_count--; } } + +/* napi->gro_hash contains packets ordered by age. + * youngest packets at the head of it. + * Complete skbs in reverse order to reduce latencies. + */ +void napi_gro_flush(struct napi_struct *napi, bool flush_old) +{ + int i; + + for (i = 0; i < GRO_HASH_BUCKETS; i++) { + struct list_head *head = &napi->gro_hash[i]; + + __napi_gro_flush_chain(napi, head, flush_old); + } +} EXPORT_SYMBOL(napi_gro_flush); -static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb) +static struct list_head *gro_list_prepare(struct napi_struct *napi, + struct sk_buff *skb) { unsigned int maclen = skb->dev->hard_header_len; u32 hash = skb_get_hash_raw(skb); + struct list_head *head; struct sk_buff *p; - list_for_each_entry(p, &napi->gro_list, list) { + head = &napi->gro_hash[hash & (GRO_HASH_BUCKETS - 1)]; + list_for_each_entry(p, head, list) { unsigned long diffs; NAPI_GRO_CB(p)->flush = 0; @@ -4922,6 +4937,8 @@ static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb) maclen); NAPI_GRO_CB(p)->same_flow = !diffs; } + + return head; } static void skb_gro_reset_offset(struct sk_buff *skb) @@ -4964,11 +4981,45 @@ static void gro_pull_from_frag0(struct sk_buff *skb, int grow) } } +static void gro_flush_oldest(struct napi_struct *napi) +{ + struct sk_buff *oldest = NULL; + unsigned long age = jiffies; + int i; + + for (i = 0; i < GRO_HASH_BUCKETS; i++) { + struct list_head *head = &napi->gro_hash[i]; + struct sk_buff *skb; + + if (list_empty(head)) + continue; + + skb = list_last_entry(head, struct sk_buff, list); + if (!oldest || time_before(NAPI_GRO_CB(skb)->age, age)) { + oldest = skb; + age = NAPI_GRO_CB(skb)->age; + } + } + + /* We are called with napi->gro_count >= MAX_GRO_SKBS, so this is + * impossible. + */ + if (WARN_ON_ONCE(!oldest)) + return; + + /* Do not adjust napi->gro_count, caller is adding a new SKB to + * the chain. + */ + list_del(&oldest->list); + napi_gro_complete(oldest); +} + static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { struct list_head *head = &offload_base; struct packet_offload *ptype; __be16 type = skb->protocol; + struct list_head *gro_head; struct sk_buff *pp = NULL; enum gro_result ret; int same_flow; @@ -4977,7 +5028,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff if (netif_elide_gro(skb->dev)) goto normal; - gro_list_prepare(napi, skb); + gro_head = gro_list_prepare(napi, skb); rcu_read_lock(); list_for_each_entry_rcu(ptype, head, list) { @@ -5011,7 +5062,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff NAPI_GRO_CB(skb)->csum_valid = 0; } - pp = ptype->callbacks.gro_receive(&napi->gro_list, skb); + pp = ptype->callbacks.gro_receive(gro_head, skb); break; } rcu_read_unlock(); @@ -5040,11 +5091,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff goto normal; if (unlikely(napi->gro_count >= MAX_GRO_SKBS)) { - struct sk_buff *nskb; - - nskb = list_last_entry(&napi->gro_list, struct sk_buff, list); - list_del(&nskb->list); - napi_gro_complete(nskb); + gro_flush_oldest(napi); } else { napi->gro_count++; } @@ -5052,7 +5099,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff NAPI_GRO_CB(skb)->age = jiffies; NAPI_GRO_CB(skb)->last = skb; skb_shinfo(skb)->gso_size = skb_gro_len(skb); - list_add(&skb->list, &napi->gro_list); + list_add(&skb->list, gro_head); ret = GRO_HELD; pull: @@ -5458,7 +5505,7 @@ bool napi_complete_done(struct napi_struct *n, int work_done) NAPIF_STATE_IN_BUSY_POLL))) return false; - if (!list_empty(&n->gro_list)) { + if (n->gro_count) { unsigned long timeout = 0; if (work_done) @@ -5667,7 +5714,7 @@ static enum hrtimer_restart napi_watchdog(struct hrtimer *timer) /* Note : we use a relaxed variant of napi_schedule_prep() not setting * NAPI_STATE_MISSED, since we do not react to a device IRQ. */ - if (!list_empty(&napi->gro_list) && !napi_disable_pending(napi) && + if (napi->gro_count && !napi_disable_pending(napi) && !test_and_set_bit(NAPI_STATE_SCHED, &napi->state)) __napi_schedule_irqoff(napi); @@ -5677,11 +5724,14 @@ static enum hrtimer_restart napi_watchdog(struct hrtimer *timer) void netif_napi_add(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), int weight) { + int i; + INIT_LIST_HEAD(&napi->poll_list); hrtimer_init(&napi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED); napi->timer.function = napi_watchdog; napi->gro_count = 0; - INIT_LIST_HEAD(&napi->gro_list); + for (i = 0; i < GRO_HASH_BUCKETS; i++) + INIT_LIST_HEAD(&napi->gro_hash[i]); napi->skb = NULL; napi->poll = poll; if (weight > NAPI_POLL_WEIGHT) @@ -5714,12 +5764,16 @@ void napi_disable(struct napi_struct *n) } EXPORT_SYMBOL(napi_disable); -static void gro_list_free(struct list_head *head) +static void flush_gro_hash(struct napi_struct *napi) { - struct sk_buff *skb, *p; + int i; - list_for_each_entry_safe(skb, p, head, list) - kfree_skb(skb); + for (i = 0; i < GRO_HASH_BUCKETS; i++) { + struct sk_buff *skb, *n; + + list_for_each_entry_safe(skb, n, &napi->gro_hash[i], list) + kfree_skb(skb); + } } /* Must be called in process context */ @@ -5731,8 +5785,7 @@ void netif_napi_del(struct napi_struct *napi) list_del_init(&napi->dev_list); napi_free_frags(napi); - gro_list_free(&napi->gro_list); - INIT_LIST_HEAD(&napi->gro_list); + flush_gro_hash(napi); napi->gro_count = 0; } EXPORT_SYMBOL(netif_napi_del); @@ -5775,7 +5828,7 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll) goto out_unlock; } - if (!list_empty(&n->gro_list)) { + if (n->gro_count) { /* flush too old packets * If HZ < 1000, flush all packets. */ -- cgit v1.2.3 From fb223502ec0889444965f602f57b1f45f9e9845e Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Sun, 24 Jun 2018 10:02:54 -0400 Subject: tcp: add SNMP counter for zero-window drops It will be helpful if we could display the drops due to zero window or no enough window space. So a new SNMP MIB entry is added to track this behavior. This entry is named LINUX_MIB_TCPZEROWINDOWDROP and published in /proc/net/netstat in TcpExt line as TCPZeroWindowDrop. Signed-off-by: Yafang Shao Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/uapi/linux/snmp.h | 1 + net/ipv4/proc.c | 1 + net/ipv4/tcp_input.c | 8 ++++++-- 3 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index 750d89120335..97517f36a5f9 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -279,6 +279,7 @@ enum LINUX_MIB_TCPDELIVERED, /* TCPDelivered */ LINUX_MIB_TCPDELIVEREDCE, /* TCPDeliveredCE */ LINUX_MIB_TCPACKCOMPRESSED, /* TCPAckCompressed */ + LINUX_MIB_TCPZEROWINDOWDROP, /* TCPZeroWindowDrop */ __LINUX_MIB_MAX }; diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 77350c1256ce..225ef3433fe5 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -287,6 +287,7 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPDelivered", LINUX_MIB_TCPDELIVERED), SNMP_MIB_ITEM("TCPDeliveredCE", LINUX_MIB_TCPDELIVEREDCE), SNMP_MIB_ITEM("TCPAckCompressed", LINUX_MIB_TCPACKCOMPRESSED), + SNMP_MIB_ITEM("TCPZeroWindowDrop", LINUX_MIB_TCPZEROWINDOWDROP), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 76ca88f63b70..9c5b3415413f 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4668,8 +4668,10 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) * Out of sequence packets to the out_of_order_queue. */ if (TCP_SKB_CB(skb)->seq == tp->rcv_nxt) { - if (tcp_receive_window(tp) == 0) + if (tcp_receive_window(tp) == 0) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPZEROWINDOWDROP); goto out_of_window; + } /* Ok. In sequence. In window. */ queue_and_out: @@ -4735,8 +4737,10 @@ drop: /* If window is closed, drop tail of packet. But after * remembering D-SACK for its head made in previous line. */ - if (!tcp_receive_window(tp)) + if (!tcp_receive_window(tp)) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPZEROWINDOWDROP); goto out_of_window; + } goto queue_and_out; } -- cgit v1.2.3 From a8f62d0c6fe533e07cd1acce7588278f9d6e7720 Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Mon, 25 Jun 2018 20:37:08 +0800 Subject: ptp: support DPAA FMan 1588 timer in ptp_qoriq This patch is to support DPAA (Data Path Acceleration Architecture) 1588 timer by adding "fsl,fman-ptp-timer" compatible, sharing interrupt with FMan, adding FSL_DPAA_ETH dependency, and fixing up register offset. Signed-off-by: Yangbo Lu Acked-by: Richard Cochran Acked-by: Madalin Bucur Signed-off-by: David S. Miller --- drivers/ptp/Kconfig | 2 +- drivers/ptp/ptp_qoriq.c | 104 +++++++++++++++++++++++++++--------------- include/linux/fsl/ptp_qoriq.h | 38 ++++++++++++--- 3 files changed, 98 insertions(+), 46 deletions(-) (limited to 'include') diff --git a/drivers/ptp/Kconfig b/drivers/ptp/Kconfig index 474c988d2e95..d137c480db46 100644 --- a/drivers/ptp/Kconfig +++ b/drivers/ptp/Kconfig @@ -43,7 +43,7 @@ config PTP_1588_CLOCK_DTE config PTP_1588_CLOCK_QORIQ tristate "Freescale QorIQ 1588 timer as PTP clock" - depends on GIANFAR + depends on GIANFAR || FSL_DPAA_ETH depends on PTP_1588_CLOCK default y help diff --git a/drivers/ptp/ptp_qoriq.c b/drivers/ptp/ptp_qoriq.c index e8652c148c52..a14c317b5a38 100644 --- a/drivers/ptp/ptp_qoriq.c +++ b/drivers/ptp/ptp_qoriq.c @@ -39,11 +39,12 @@ /* Caller must hold qoriq_ptp->lock. */ static u64 tmr_cnt_read(struct qoriq_ptp *qoriq_ptp) { + struct qoriq_ptp_registers *regs = &qoriq_ptp->regs; u64 ns; u32 lo, hi; - lo = qoriq_read(&qoriq_ptp->regs->tmr_cnt_l); - hi = qoriq_read(&qoriq_ptp->regs->tmr_cnt_h); + lo = qoriq_read(®s->ctrl_regs->tmr_cnt_l); + hi = qoriq_read(®s->ctrl_regs->tmr_cnt_h); ns = ((u64) hi) << 32; ns |= lo; return ns; @@ -52,16 +53,18 @@ static u64 tmr_cnt_read(struct qoriq_ptp *qoriq_ptp) /* Caller must hold qoriq_ptp->lock. */ static void tmr_cnt_write(struct qoriq_ptp *qoriq_ptp, u64 ns) { + struct qoriq_ptp_registers *regs = &qoriq_ptp->regs; u32 hi = ns >> 32; u32 lo = ns & 0xffffffff; - qoriq_write(&qoriq_ptp->regs->tmr_cnt_l, lo); - qoriq_write(&qoriq_ptp->regs->tmr_cnt_h, hi); + qoriq_write(®s->ctrl_regs->tmr_cnt_l, lo); + qoriq_write(®s->ctrl_regs->tmr_cnt_h, hi); } /* Caller must hold qoriq_ptp->lock. */ static void set_alarm(struct qoriq_ptp *qoriq_ptp) { + struct qoriq_ptp_registers *regs = &qoriq_ptp->regs; u64 ns; u32 lo, hi; @@ -70,16 +73,18 @@ static void set_alarm(struct qoriq_ptp *qoriq_ptp) ns -= qoriq_ptp->tclk_period; hi = ns >> 32; lo = ns & 0xffffffff; - qoriq_write(&qoriq_ptp->regs->tmr_alarm1_l, lo); - qoriq_write(&qoriq_ptp->regs->tmr_alarm1_h, hi); + qoriq_write(®s->alarm_regs->tmr_alarm1_l, lo); + qoriq_write(®s->alarm_regs->tmr_alarm1_h, hi); } /* Caller must hold qoriq_ptp->lock. */ static void set_fipers(struct qoriq_ptp *qoriq_ptp) { + struct qoriq_ptp_registers *regs = &qoriq_ptp->regs; + set_alarm(qoriq_ptp); - qoriq_write(&qoriq_ptp->regs->tmr_fiper1, qoriq_ptp->tmr_fiper1); - qoriq_write(&qoriq_ptp->regs->tmr_fiper2, qoriq_ptp->tmr_fiper2); + qoriq_write(®s->fiper_regs->tmr_fiper1, qoriq_ptp->tmr_fiper1); + qoriq_write(®s->fiper_regs->tmr_fiper2, qoriq_ptp->tmr_fiper2); } /* @@ -89,16 +94,17 @@ static void set_fipers(struct qoriq_ptp *qoriq_ptp) static irqreturn_t isr(int irq, void *priv) { struct qoriq_ptp *qoriq_ptp = priv; + struct qoriq_ptp_registers *regs = &qoriq_ptp->regs; struct ptp_clock_event event; u64 ns; u32 ack = 0, lo, hi, mask, val; - val = qoriq_read(&qoriq_ptp->regs->tmr_tevent); + val = qoriq_read(®s->ctrl_regs->tmr_tevent); if (val & ETS1) { ack |= ETS1; - hi = qoriq_read(&qoriq_ptp->regs->tmr_etts1_h); - lo = qoriq_read(&qoriq_ptp->regs->tmr_etts1_l); + hi = qoriq_read(®s->etts_regs->tmr_etts1_h); + lo = qoriq_read(®s->etts_regs->tmr_etts1_l); event.type = PTP_CLOCK_EXTTS; event.index = 0; event.timestamp = ((u64) hi) << 32; @@ -108,8 +114,8 @@ static irqreturn_t isr(int irq, void *priv) if (val & ETS2) { ack |= ETS2; - hi = qoriq_read(&qoriq_ptp->regs->tmr_etts2_h); - lo = qoriq_read(&qoriq_ptp->regs->tmr_etts2_l); + hi = qoriq_read(®s->etts_regs->tmr_etts2_h); + lo = qoriq_read(®s->etts_regs->tmr_etts2_l); event.type = PTP_CLOCK_EXTTS; event.index = 1; event.timestamp = ((u64) hi) << 32; @@ -130,16 +136,16 @@ static irqreturn_t isr(int irq, void *priv) hi = ns >> 32; lo = ns & 0xffffffff; spin_lock(&qoriq_ptp->lock); - qoriq_write(&qoriq_ptp->regs->tmr_alarm2_l, lo); - qoriq_write(&qoriq_ptp->regs->tmr_alarm2_h, hi); + qoriq_write(®s->alarm_regs->tmr_alarm2_l, lo); + qoriq_write(®s->alarm_regs->tmr_alarm2_h, hi); spin_unlock(&qoriq_ptp->lock); qoriq_ptp->alarm_value = ns; } else { - qoriq_write(&qoriq_ptp->regs->tmr_tevent, ALM2); + qoriq_write(®s->ctrl_regs->tmr_tevent, ALM2); spin_lock(&qoriq_ptp->lock); - mask = qoriq_read(&qoriq_ptp->regs->tmr_temask); + mask = qoriq_read(®s->ctrl_regs->tmr_temask); mask &= ~ALM2EN; - qoriq_write(&qoriq_ptp->regs->tmr_temask, mask); + qoriq_write(®s->ctrl_regs->tmr_temask, mask); spin_unlock(&qoriq_ptp->lock); qoriq_ptp->alarm_value = 0; qoriq_ptp->alarm_interval = 0; @@ -153,7 +159,7 @@ static irqreturn_t isr(int irq, void *priv) } if (ack) { - qoriq_write(&qoriq_ptp->regs->tmr_tevent, ack); + qoriq_write(®s->ctrl_regs->tmr_tevent, ack); return IRQ_HANDLED; } else return IRQ_NONE; @@ -169,6 +175,7 @@ static int ptp_qoriq_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) u32 tmr_add; int neg_adj = 0; struct qoriq_ptp *qoriq_ptp = container_of(ptp, struct qoriq_ptp, caps); + struct qoriq_ptp_registers *regs = &qoriq_ptp->regs; if (scaled_ppm < 0) { neg_adj = 1; @@ -186,7 +193,7 @@ static int ptp_qoriq_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) tmr_add = neg_adj ? tmr_add - diff : tmr_add + diff; - qoriq_write(&qoriq_ptp->regs->tmr_add, tmr_add); + qoriq_write(®s->ctrl_regs->tmr_add, tmr_add); return 0; } @@ -250,6 +257,7 @@ static int ptp_qoriq_enable(struct ptp_clock_info *ptp, struct ptp_clock_request *rq, int on) { struct qoriq_ptp *qoriq_ptp = container_of(ptp, struct qoriq_ptp, caps); + struct qoriq_ptp_registers *regs = &qoriq_ptp->regs; unsigned long flags; u32 bit, mask; @@ -266,23 +274,23 @@ static int ptp_qoriq_enable(struct ptp_clock_info *ptp, return -EINVAL; } spin_lock_irqsave(&qoriq_ptp->lock, flags); - mask = qoriq_read(&qoriq_ptp->regs->tmr_temask); + mask = qoriq_read(®s->ctrl_regs->tmr_temask); if (on) mask |= bit; else mask &= ~bit; - qoriq_write(&qoriq_ptp->regs->tmr_temask, mask); + qoriq_write(®s->ctrl_regs->tmr_temask, mask); spin_unlock_irqrestore(&qoriq_ptp->lock, flags); return 0; case PTP_CLK_REQ_PPS: spin_lock_irqsave(&qoriq_ptp->lock, flags); - mask = qoriq_read(&qoriq_ptp->regs->tmr_temask); + mask = qoriq_read(®s->ctrl_regs->tmr_temask); if (on) mask |= PP1EN; else mask &= ~PP1EN; - qoriq_write(&qoriq_ptp->regs->tmr_temask, mask); + qoriq_write(®s->ctrl_regs->tmr_temask, mask); spin_unlock_irqrestore(&qoriq_ptp->lock, flags); return 0; @@ -313,10 +321,12 @@ static int qoriq_ptp_probe(struct platform_device *dev) { struct device_node *node = dev->dev.of_node; struct qoriq_ptp *qoriq_ptp; + struct qoriq_ptp_registers *regs; struct timespec64 now; int err = -ENOMEM; u32 tmr_ctrl; unsigned long flags; + void __iomem *base; qoriq_ptp = kzalloc(sizeof(*qoriq_ptp), GFP_KERNEL); if (!qoriq_ptp) @@ -351,7 +361,7 @@ static int qoriq_ptp_probe(struct platform_device *dev) pr_err("irq not in device tree\n"); goto no_node; } - if (request_irq(qoriq_ptp->irq, isr, 0, DRIVER, qoriq_ptp)) { + if (request_irq(qoriq_ptp->irq, isr, IRQF_SHARED, DRIVER, qoriq_ptp)) { pr_err("request_irq failed\n"); goto no_node; } @@ -368,12 +378,27 @@ static int qoriq_ptp_probe(struct platform_device *dev) spin_lock_init(&qoriq_ptp->lock); - qoriq_ptp->regs = ioremap(qoriq_ptp->rsrc->start, - resource_size(qoriq_ptp->rsrc)); - if (!qoriq_ptp->regs) { + base = ioremap(qoriq_ptp->rsrc->start, + resource_size(qoriq_ptp->rsrc)); + if (!base) { pr_err("ioremap ptp registers failed\n"); goto no_ioremap; } + + qoriq_ptp->base = base; + + if (of_device_is_compatible(node, "fsl,fman-ptp-timer")) { + qoriq_ptp->regs.ctrl_regs = base + FMAN_CTRL_REGS_OFFSET; + qoriq_ptp->regs.alarm_regs = base + FMAN_ALARM_REGS_OFFSET; + qoriq_ptp->regs.fiper_regs = base + FMAN_FIPER_REGS_OFFSET; + qoriq_ptp->regs.etts_regs = base + FMAN_ETTS_REGS_OFFSET; + } else { + qoriq_ptp->regs.ctrl_regs = base + CTRL_REGS_OFFSET; + qoriq_ptp->regs.alarm_regs = base + ALARM_REGS_OFFSET; + qoriq_ptp->regs.fiper_regs = base + FIPER_REGS_OFFSET; + qoriq_ptp->regs.etts_regs = base + ETTS_REGS_OFFSET; + } + ktime_get_real_ts64(&now); ptp_qoriq_settime(&qoriq_ptp->caps, &now); @@ -383,13 +408,14 @@ static int qoriq_ptp_probe(struct platform_device *dev) spin_lock_irqsave(&qoriq_ptp->lock, flags); - qoriq_write(&qoriq_ptp->regs->tmr_ctrl, tmr_ctrl); - qoriq_write(&qoriq_ptp->regs->tmr_add, qoriq_ptp->tmr_add); - qoriq_write(&qoriq_ptp->regs->tmr_prsc, qoriq_ptp->tmr_prsc); - qoriq_write(&qoriq_ptp->regs->tmr_fiper1, qoriq_ptp->tmr_fiper1); - qoriq_write(&qoriq_ptp->regs->tmr_fiper2, qoriq_ptp->tmr_fiper2); + regs = &qoriq_ptp->regs; + qoriq_write(®s->ctrl_regs->tmr_ctrl, tmr_ctrl); + qoriq_write(®s->ctrl_regs->tmr_add, qoriq_ptp->tmr_add); + qoriq_write(®s->ctrl_regs->tmr_prsc, qoriq_ptp->tmr_prsc); + qoriq_write(®s->fiper_regs->tmr_fiper1, qoriq_ptp->tmr_fiper1); + qoriq_write(®s->fiper_regs->tmr_fiper2, qoriq_ptp->tmr_fiper2); set_alarm(qoriq_ptp); - qoriq_write(&qoriq_ptp->regs->tmr_ctrl, tmr_ctrl|FIPERST|RTPE|TE|FRD); + qoriq_write(®s->ctrl_regs->tmr_ctrl, tmr_ctrl|FIPERST|RTPE|TE|FRD); spin_unlock_irqrestore(&qoriq_ptp->lock, flags); @@ -405,7 +431,7 @@ static int qoriq_ptp_probe(struct platform_device *dev) return 0; no_clock: - iounmap(qoriq_ptp->regs); + iounmap(qoriq_ptp->base); no_ioremap: release_resource(qoriq_ptp->rsrc); no_resource: @@ -419,12 +445,13 @@ no_memory: static int qoriq_ptp_remove(struct platform_device *dev) { struct qoriq_ptp *qoriq_ptp = platform_get_drvdata(dev); + struct qoriq_ptp_registers *regs = &qoriq_ptp->regs; - qoriq_write(&qoriq_ptp->regs->tmr_temask, 0); - qoriq_write(&qoriq_ptp->regs->tmr_ctrl, 0); + qoriq_write(®s->ctrl_regs->tmr_temask, 0); + qoriq_write(®s->ctrl_regs->tmr_ctrl, 0); ptp_clock_unregister(qoriq_ptp->clock); - iounmap(qoriq_ptp->regs); + iounmap(qoriq_ptp->base); release_resource(qoriq_ptp->rsrc); free_irq(qoriq_ptp->irq, qoriq_ptp); kfree(qoriq_ptp); @@ -434,6 +461,7 @@ static int qoriq_ptp_remove(struct platform_device *dev) static const struct of_device_id match_table[] = { { .compatible = "fsl,etsec-ptp" }, + { .compatible = "fsl,fman-ptp-timer" }, {}, }; MODULE_DEVICE_TABLE(of, match_table); diff --git a/include/linux/fsl/ptp_qoriq.h b/include/linux/fsl/ptp_qoriq.h index b462d9ea8007..dc3dac40f069 100644 --- a/include/linux/fsl/ptp_qoriq.h +++ b/include/linux/fsl/ptp_qoriq.h @@ -11,9 +11,8 @@ /* * qoriq ptp registers - * Generated by regen.tcl on Thu May 13 01:38:57 PM CEST 2010 */ -struct qoriq_ptp_registers { +struct ctrl_regs { u32 tmr_ctrl; /* Timer control register */ u32 tmr_tevent; /* Timestamp event register */ u32 tmr_temask; /* Timer event mask register */ @@ -28,22 +27,47 @@ struct qoriq_ptp_registers { u8 res1[4]; u32 tmroff_h; /* Timer offset high */ u32 tmroff_l; /* Timer offset low */ - u8 res2[8]; +}; + +struct alarm_regs { u32 tmr_alarm1_h; /* Timer alarm 1 high register */ u32 tmr_alarm1_l; /* Timer alarm 1 high register */ u32 tmr_alarm2_h; /* Timer alarm 2 high register */ u32 tmr_alarm2_l; /* Timer alarm 2 high register */ - u8 res3[48]; +}; + +struct fiper_regs { u32 tmr_fiper1; /* Timer fixed period interval */ u32 tmr_fiper2; /* Timer fixed period interval */ u32 tmr_fiper3; /* Timer fixed period interval */ - u8 res4[20]; +}; + +struct etts_regs { u32 tmr_etts1_h; /* Timestamp of general purpose external trigger */ u32 tmr_etts1_l; /* Timestamp of general purpose external trigger */ u32 tmr_etts2_h; /* Timestamp of general purpose external trigger */ u32 tmr_etts2_l; /* Timestamp of general purpose external trigger */ }; +struct qoriq_ptp_registers { + struct ctrl_regs __iomem *ctrl_regs; + struct alarm_regs __iomem *alarm_regs; + struct fiper_regs __iomem *fiper_regs; + struct etts_regs __iomem *etts_regs; +}; + +/* Offset definitions for the four register groups */ +#define CTRL_REGS_OFFSET 0x0 +#define ALARM_REGS_OFFSET 0x40 +#define FIPER_REGS_OFFSET 0x80 +#define ETTS_REGS_OFFSET 0xa0 + +#define FMAN_CTRL_REGS_OFFSET 0x80 +#define FMAN_ALARM_REGS_OFFSET 0xb8 +#define FMAN_FIPER_REGS_OFFSET 0xd0 +#define FMAN_ETTS_REGS_OFFSET 0xe0 + + /* Bit definitions for the TMR_CTRL register */ #define ALM1P (1<<31) /* Alarm1 output polarity */ #define ALM2P (1<<30) /* Alarm2 output polarity */ @@ -105,10 +129,10 @@ struct qoriq_ptp_registers { #define DRIVER "ptp_qoriq" #define DEFAULT_CKSEL 1 #define N_EXT_TS 2 -#define REG_SIZE sizeof(struct qoriq_ptp_registers) struct qoriq_ptp { - struct qoriq_ptp_registers __iomem *regs; + void __iomem *base; + struct qoriq_ptp_registers regs; spinlock_t lock; /* protects regs */ struct ptp_clock *clock; struct ptp_clock_info caps; -- cgit v1.2.3 From 60513bd82c825b659c05957e4f8106ba06f0797f Mon Sep 17 00:00:00 2001 From: John Hurley Date: Mon, 25 Jun 2018 14:30:04 -0700 Subject: net: sched: pass extack pointer to block binds and cb registration Pass the extact struct from a tc qdisc add to the block bind function and, in turn, to the setup_tc ndo of binding device via the tc_block_offload struct. Pass this back to any block callback registrations to allow netlink logging of fails in the bind process. Signed-off-by: John Hurley Signed-off-by: Jakub Kicinski Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 +- drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c | 2 +- drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 2 +- drivers/net/ethernet/intel/i40e/i40e_main.c | 2 +- drivers/net/ethernet/intel/i40evf/i40evf_main.c | 2 +- drivers/net/ethernet/intel/igb/igb_main.c | 2 +- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 2 +- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 10 +++++---- drivers/net/ethernet/netronome/nfp/bpf/main.c | 2 +- .../net/ethernet/netronome/nfp/flower/offload.c | 2 +- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 2 +- drivers/net/netdevsim/netdev.c | 2 +- include/net/pkt_cls.h | 11 ++++++---- net/dsa/slave.c | 2 +- net/sched/cls_api.c | 25 ++++++++++++++-------- 17 files changed, 43 insertions(+), 31 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 176fc9f4d7de..b5fc6414a951 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -7984,7 +7984,7 @@ static int bnxt_setup_tc_block(struct net_device *dev, switch (f->command) { case TC_BLOCK_BIND: return tcf_block_cb_register(f->block, bnxt_setup_tc_block_cb, - bp, bp); + bp, bp, f->extack); case TC_BLOCK_UNBIND: tcf_block_cb_unregister(f->block, bnxt_setup_tc_block_cb, bp); return 0; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c index 05d405905906..0745f2dfc80c 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c @@ -173,7 +173,7 @@ static int bnxt_vf_rep_setup_tc_block(struct net_device *dev, case TC_BLOCK_BIND: return tcf_block_cb_register(f->block, bnxt_vf_rep_setup_tc_block_cb, - vf_rep, vf_rep); + vf_rep, vf_rep, f->extack); case TC_BLOCK_UNBIND: tcf_block_cb_unregister(f->block, bnxt_vf_rep_setup_tc_block_cb, vf_rep); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index bc03c175a3cd..96bc177d54de 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -3016,7 +3016,7 @@ static int cxgb_setup_tc_block(struct net_device *dev, switch (f->command) { case TC_BLOCK_BIND: return tcf_block_cb_register(f->block, cxgb_setup_tc_block_cb, - pi, dev); + pi, dev, f->extack); case TC_BLOCK_UNBIND: tcf_block_cb_unregister(f->block, cxgb_setup_tc_block_cb, pi); return 0; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 7ad2b1b0b125..426b0ccb1fc6 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -7554,7 +7554,7 @@ static int i40e_setup_tc_block(struct net_device *dev, switch (f->command) { case TC_BLOCK_BIND: return tcf_block_cb_register(f->block, i40e_setup_tc_block_cb, - np, np); + np, np, f->extack); case TC_BLOCK_UNBIND: tcf_block_cb_unregister(f->block, i40e_setup_tc_block_cb, np); return 0; diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c index dc56a8667495..5906c1c1d19d 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c @@ -2926,7 +2926,7 @@ static int i40evf_setup_tc_block(struct net_device *dev, switch (f->command) { case TC_BLOCK_BIND: return tcf_block_cb_register(f->block, i40evf_setup_tc_block_cb, - adapter, adapter); + adapter, adapter, f->extack); case TC_BLOCK_UNBIND: tcf_block_cb_unregister(f->block, i40evf_setup_tc_block_cb, adapter); diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 6a78d8272eb2..f1e3397bd405 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -2728,7 +2728,7 @@ static int igb_setup_tc_block(struct igb_adapter *adapter, switch (f->command) { case TC_BLOCK_BIND: return tcf_block_cb_register(f->block, igb_setup_tc_block_cb, - adapter, adapter); + adapter, adapter, f->extack); case TC_BLOCK_UNBIND: tcf_block_cb_unregister(f->block, igb_setup_tc_block_cb, adapter); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 3e87dbbc9024..d29bd8fc3ff3 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -9325,7 +9325,7 @@ static int ixgbe_setup_tc_block(struct net_device *dev, switch (f->command) { case TC_BLOCK_BIND: return tcf_block_cb_register(f->block, ixgbe_setup_tc_block_cb, - adapter, adapter); + adapter, adapter, f->extack); case TC_BLOCK_UNBIND: tcf_block_cb_unregister(f->block, ixgbe_setup_tc_block_cb, adapter); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 56c1b6f5593e..134f20a182b5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3371,7 +3371,7 @@ static int mlx5e_setup_tc_block(struct net_device *dev, switch (f->command) { case TC_BLOCK_BIND: return tcf_block_cb_register(f->block, mlx5e_setup_tc_block_cb, - priv, priv); + priv, priv, f->extack); case TC_BLOCK_UNBIND: tcf_block_cb_unregister(f->block, mlx5e_setup_tc_block_cb, priv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 57987f6546e8..3f2fe95e01d9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -797,7 +797,7 @@ static int mlx5e_rep_setup_tc_block(struct net_device *dev, switch (f->command) { case TC_BLOCK_BIND: return tcf_block_cb_register(f->block, mlx5e_rep_setup_tc_cb, - priv, priv); + priv, priv, f->extack); case TC_BLOCK_UNBIND: tcf_block_cb_unregister(f->block, mlx5e_rep_setup_tc_cb, priv); return 0; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 968b88af2ef5..d2bc335dda11 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -1503,7 +1503,8 @@ static int mlxsw_sp_setup_tc_block_cb_flower(enum tc_setup_type type, static int mlxsw_sp_setup_tc_block_flower_bind(struct mlxsw_sp_port *mlxsw_sp_port, - struct tcf_block *block, bool ingress) + struct tcf_block *block, bool ingress, + struct netlink_ext_ack *extack) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; struct mlxsw_sp_acl_block *acl_block; @@ -1518,7 +1519,7 @@ mlxsw_sp_setup_tc_block_flower_bind(struct mlxsw_sp_port *mlxsw_sp_port, return -ENOMEM; block_cb = __tcf_block_cb_register(block, mlxsw_sp_setup_tc_block_cb_flower, - mlxsw_sp, acl_block); + mlxsw_sp, acl_block, extack); if (IS_ERR(block_cb)) { err = PTR_ERR(block_cb); goto err_cb_register; @@ -1596,11 +1597,12 @@ static int mlxsw_sp_setup_tc_block(struct mlxsw_sp_port *mlxsw_sp_port, switch (f->command) { case TC_BLOCK_BIND: err = tcf_block_cb_register(f->block, cb, mlxsw_sp_port, - mlxsw_sp_port); + mlxsw_sp_port, f->extack); if (err) return err; err = mlxsw_sp_setup_tc_block_flower_bind(mlxsw_sp_port, - f->block, ingress); + f->block, ingress, + f->extack); if (err) { tcf_block_cb_unregister(f->block, cb, mlxsw_sp_port); return err; diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c index fcdfb8e7fdea..bf46f7bff912 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c @@ -206,7 +206,7 @@ static int nfp_bpf_setup_tc_block(struct net_device *netdev, case TC_BLOCK_BIND: return tcf_block_cb_register(f->block, nfp_bpf_setup_tc_block_cb, - nn, nn); + nn, nn, f->extack); case TC_BLOCK_UNBIND: tcf_block_cb_unregister(f->block, nfp_bpf_setup_tc_block_cb, diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index c0e74aa4cb5e..a427dab4bf49 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -627,7 +627,7 @@ static int nfp_flower_setup_tc_block(struct net_device *netdev, case TC_BLOCK_BIND: return tcf_block_cb_register(f->block, nfp_flower_setup_tc_block_cb, - repr, repr); + repr, repr, f->extack); case TC_BLOCK_UNBIND: tcf_block_cb_unregister(f->block, nfp_flower_setup_tc_block_cb, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index cba46b62a1cd..2354e30caa78 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3776,7 +3776,7 @@ static int stmmac_setup_tc_block(struct stmmac_priv *priv, switch (f->command) { case TC_BLOCK_BIND: return tcf_block_cb_register(f->block, stmmac_setup_tc_block_cb, - priv, priv); + priv, priv, f->extack); case TC_BLOCK_UNBIND: tcf_block_cb_unregister(f->block, stmmac_setup_tc_block_cb, priv); return 0; diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c index ec68f38213d9..c9dacc6fcd59 100644 --- a/drivers/net/netdevsim/netdev.c +++ b/drivers/net/netdevsim/netdev.c @@ -260,7 +260,7 @@ nsim_setup_tc_block(struct net_device *dev, struct tc_block_offload *f) switch (f->command) { case TC_BLOCK_BIND: return tcf_block_cb_register(f->block, nsim_setup_tc_block_cb, - ns, ns); + ns, ns, f->extack); case TC_BLOCK_UNBIND: tcf_block_cb_unregister(f->block, nsim_setup_tc_block_cb, ns); return 0; diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index a3c1a2c47cd4..a2c6d35ba057 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -73,10 +73,11 @@ void tcf_block_cb_incref(struct tcf_block_cb *block_cb); unsigned int tcf_block_cb_decref(struct tcf_block_cb *block_cb); struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block, tc_setup_cb_t *cb, void *cb_ident, - void *cb_priv); + void *cb_priv, + struct netlink_ext_ack *extack); int tcf_block_cb_register(struct tcf_block *block, tc_setup_cb_t *cb, void *cb_ident, - void *cb_priv); + void *cb_priv, struct netlink_ext_ack *extack); void __tcf_block_cb_unregister(struct tcf_block_cb *block_cb); void tcf_block_cb_unregister(struct tcf_block *block, tc_setup_cb_t *cb, void *cb_ident); @@ -161,7 +162,8 @@ unsigned int tcf_block_cb_decref(struct tcf_block_cb *block_cb) static inline struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block, tc_setup_cb_t *cb, void *cb_ident, - void *cb_priv) + void *cb_priv, + struct netlink_ext_ack *extack) { return NULL; } @@ -169,7 +171,7 @@ struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block, static inline int tcf_block_cb_register(struct tcf_block *block, tc_setup_cb_t *cb, void *cb_ident, - void *cb_priv) + void *cb_priv, struct netlink_ext_ack *extack) { return 0; } @@ -596,6 +598,7 @@ struct tc_block_offload { enum tc_block_command command; enum tcf_block_binder_type binder_type; struct tcf_block *block; + struct netlink_ext_ack *extack; }; struct tc_cls_common_offload { diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 1e3b6a6d8a40..71536c435132 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -900,7 +900,7 @@ static int dsa_slave_setup_tc_block(struct net_device *dev, switch (f->command) { case TC_BLOCK_BIND: - return tcf_block_cb_register(f->block, cb, dev, dev); + return tcf_block_cb_register(f->block, cb, dev, dev, f->extack); case TC_BLOCK_UNBIND: tcf_block_cb_unregister(f->block, cb, dev); return 0; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index cdc3c87c53e6..8c9fb4b827a1 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -277,18 +277,21 @@ static bool tcf_block_offload_in_use(struct tcf_block *block) static int tcf_block_offload_cmd(struct tcf_block *block, struct net_device *dev, struct tcf_block_ext_info *ei, - enum tc_block_command command) + enum tc_block_command command, + struct netlink_ext_ack *extack) { struct tc_block_offload bo = {}; bo.command = command; bo.binder_type = ei->binder_type; bo.block = block; + bo.extack = extack; return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo); } static int tcf_block_offload_bind(struct tcf_block *block, struct Qdisc *q, - struct tcf_block_ext_info *ei) + struct tcf_block_ext_info *ei, + struct netlink_ext_ack *extack) { struct net_device *dev = q->dev_queue->dev; int err; @@ -299,10 +302,12 @@ static int tcf_block_offload_bind(struct tcf_block *block, struct Qdisc *q, /* If tc offload feature is disabled and the block we try to bind * to already has some offloaded filters, forbid to bind. */ - if (!tc_can_offload(dev) && tcf_block_offload_in_use(block)) + if (!tc_can_offload(dev) && tcf_block_offload_in_use(block)) { + NL_SET_ERR_MSG(extack, "Bind to offloaded block failed as dev has offload disabled"); return -EOPNOTSUPP; + } - err = tcf_block_offload_cmd(block, dev, ei, TC_BLOCK_BIND); + err = tcf_block_offload_cmd(block, dev, ei, TC_BLOCK_BIND, extack); if (err == -EOPNOTSUPP) goto no_offload_dev_inc; return err; @@ -322,7 +327,7 @@ static void tcf_block_offload_unbind(struct tcf_block *block, struct Qdisc *q, if (!dev->netdev_ops->ndo_setup_tc) goto no_offload_dev_dec; - err = tcf_block_offload_cmd(block, dev, ei, TC_BLOCK_UNBIND); + err = tcf_block_offload_cmd(block, dev, ei, TC_BLOCK_UNBIND, NULL); if (err == -EOPNOTSUPP) goto no_offload_dev_dec; return; @@ -612,7 +617,7 @@ int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q, if (err) goto err_chain_head_change_cb_add; - err = tcf_block_offload_bind(block, q, ei); + err = tcf_block_offload_bind(block, q, ei, extack); if (err) goto err_block_offload_bind; @@ -748,7 +753,8 @@ EXPORT_SYMBOL(tcf_block_cb_decref); struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block, tc_setup_cb_t *cb, void *cb_ident, - void *cb_priv) + void *cb_priv, + struct netlink_ext_ack *extack) { struct tcf_block_cb *block_cb; @@ -772,11 +778,12 @@ EXPORT_SYMBOL(__tcf_block_cb_register); int tcf_block_cb_register(struct tcf_block *block, tc_setup_cb_t *cb, void *cb_ident, - void *cb_priv) + void *cb_priv, struct netlink_ext_ack *extack) { struct tcf_block_cb *block_cb; - block_cb = __tcf_block_cb_register(block, cb, cb_ident, cb_priv); + block_cb = __tcf_block_cb_register(block, cb, cb_ident, cb_priv, + extack); return IS_ERR(block_cb) ? PTR_ERR(block_cb) : 0; } EXPORT_SYMBOL(tcf_block_cb_register); -- cgit v1.2.3 From e56185c78b500ac4d08768278ad8a25d5b756942 Mon Sep 17 00:00:00 2001 From: John Hurley Date: Mon, 25 Jun 2018 14:30:05 -0700 Subject: net: sched: add tcf_proto_op to offload a rule Create a new tcf_proto_op called 'reoffload' that generates a new offload message for each node in a tcf_proto. Pointers to the tcf_proto and whether the offload request is to add or delete the node are included. Also included is a callback function to send the offload message to and the option of priv data to go with the cb. Signed-off-by: John Hurley Signed-off-by: Jakub Kicinski Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/act_api.h | 3 --- include/net/sch_generic.h | 6 ++++++ 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/act_api.h b/include/net/act_api.h index 9e59ebfded62..5ff11adbe2a6 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -190,9 +190,6 @@ static inline void tcf_action_stats_update(struct tc_action *a, u64 bytes, #endif } -typedef int tc_setup_cb_t(enum tc_setup_type type, - void *type_data, void *cb_priv); - #ifdef CONFIG_NET_CLS_ACT int tc_setup_cb_egdev_register(const struct net_device *dev, tc_setup_cb_t *cb, void *cb_priv); diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 6488daa32f82..18adc9142b18 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -20,6 +20,9 @@ struct qdisc_walker; struct tcf_walker; struct module; +typedef int tc_setup_cb_t(enum tc_setup_type type, + void *type_data, void *cb_priv); + struct qdisc_rate_table { struct tc_ratespec rate; u32 data[256]; @@ -256,6 +259,9 @@ struct tcf_proto_ops { bool *last, struct netlink_ext_ack *); void (*walk)(struct tcf_proto*, struct tcf_walker *arg); + int (*reoffload)(struct tcf_proto *tp, bool add, + tc_setup_cb_t *cb, void *cb_priv, + struct netlink_ext_ack *extack); void (*bind_class)(void *, u32, unsigned long); /* rtnetlink specific */ -- cgit v1.2.3 From 31533cba4327aefeafe8a7d57de0c737a3b2faa6 Mon Sep 17 00:00:00 2001 From: John Hurley Date: Mon, 25 Jun 2018 14:30:06 -0700 Subject: net: sched: cls_flower: implement offload tcf_proto_op Add the reoffload tcf_proto_op in flower to generate an offload message for each filter in the given tcf_proto. Call the specified callback with this new offload message. The function only returns an error if the callback rejects adding a 'hardware only' rule. A filter contains a flag to indicate if it is in hardware or not. To ensure the reoffload function properly maintains this flag, keep a reference counter for the number of instances of the filter that are in hardware. Only update the flag when this counter changes from or to 0. Add a generic helper function to implement this behaviour. Signed-off-by: John Hurley Signed-off-by: Jakub Kicinski Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/sch_generic.h | 15 +++++++++++++++ net/sched/cls_flower.c | 44 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 59 insertions(+) (limited to 'include') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 18adc9142b18..7432100027b7 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -336,6 +336,21 @@ static inline void tcf_block_offload_dec(struct tcf_block *block, u32 *flags) block->offloadcnt--; } +static inline void +tc_cls_offload_cnt_update(struct tcf_block *block, unsigned int *cnt, + u32 *flags, bool add) +{ + if (add) { + if (!*cnt) + tcf_block_offload_inc(block, flags); + (*cnt)++; + } else { + (*cnt)--; + if (!*cnt) + tcf_block_offload_dec(block, flags); + } +} + static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz) { struct qdisc_skb_cb *qcb; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 9e8b26a80fb3..352876bb901b 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -87,6 +87,7 @@ struct cls_fl_filter { struct list_head list; u32 handle; u32 flags; + unsigned int in_hw_count; struct rcu_work rwork; struct net_device *hw_dev; }; @@ -289,6 +290,7 @@ static int fl_hw_replace_filter(struct tcf_proto *tp, fl_hw_destroy_filter(tp, f, NULL); return err; } else if (err > 0) { + f->in_hw_count = err; tcf_block_offload_inc(block, &f->flags); } @@ -1087,6 +1089,47 @@ skip: } } +static int fl_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb, + void *cb_priv, struct netlink_ext_ack *extack) +{ + struct cls_fl_head *head = rtnl_dereference(tp->root); + struct tc_cls_flower_offload cls_flower = {}; + struct tcf_block *block = tp->chain->block; + struct fl_flow_mask *mask; + struct cls_fl_filter *f; + int err; + + list_for_each_entry(mask, &head->masks, list) { + list_for_each_entry(f, &mask->filters, list) { + if (tc_skip_hw(f->flags)) + continue; + + tc_cls_common_offload_init(&cls_flower.common, tp, + f->flags, extack); + cls_flower.command = add ? + TC_CLSFLOWER_REPLACE : TC_CLSFLOWER_DESTROY; + cls_flower.cookie = (unsigned long)f; + cls_flower.dissector = &mask->dissector; + cls_flower.mask = &f->mkey; + cls_flower.key = &f->key; + cls_flower.exts = &f->exts; + cls_flower.classid = f->res.classid; + + err = cb(TC_SETUP_CLSFLOWER, &cls_flower, cb_priv); + if (err) { + if (add && tc_skip_sw(f->flags)) + return err; + continue; + } + + tc_cls_offload_cnt_update(block, &f->in_hw_count, + &f->flags, add); + } + } + + return 0; +} + static int fl_dump_key_val(struct sk_buff *skb, void *val, int val_type, void *mask, int mask_type, int len) @@ -1438,6 +1481,7 @@ static struct tcf_proto_ops cls_fl_ops __read_mostly = { .change = fl_change, .delete = fl_delete, .walk = fl_walk, + .reoffload = fl_reoffload, .dump = fl_dump, .bind_class = fl_bind_class, .owner = THIS_MODULE, -- cgit v1.2.3 From 326367427cc09d38e4c1d145131ee2e228ac94c5 Mon Sep 17 00:00:00 2001 From: John Hurley Date: Mon, 25 Jun 2018 14:30:10 -0700 Subject: net: sched: call reoffload op on block callback reg Call the reoffload tcf_proto_op on all tcf_proto nodes in all chains of a block when a callback tries to register to a block that already has offloaded rules. If all existing rules cannot be offloaded then the registration is rejected. This replaces the previous policy of rejecting such callback registration outright. On unregistration of a callback, the rules are flushed for that given cb. The implementation of block sharing in the NFP driver, for example, duplicates shared rules to all devs bound to a block. This meant that rules could still exist in hw even after a device is unbound from a block (assuming the block still remains active). Signed-off-by: John Hurley Signed-off-by: Jakub Kicinski Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 4 +- include/net/pkt_cls.h | 6 ++- net/sched/cls_api.c | 54 ++++++++++++++++++++++---- 3 files changed, 52 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index d2bc335dda11..52437363766a 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -1542,7 +1542,7 @@ mlxsw_sp_setup_tc_block_flower_bind(struct mlxsw_sp_port *mlxsw_sp_port, err_block_bind: if (!tcf_block_cb_decref(block_cb)) { - __tcf_block_cb_unregister(block_cb); + __tcf_block_cb_unregister(block, block_cb); err_cb_register: mlxsw_sp_acl_block_destroy(acl_block); } @@ -1572,7 +1572,7 @@ mlxsw_sp_setup_tc_block_flower_unbind(struct mlxsw_sp_port *mlxsw_sp_port, err = mlxsw_sp_acl_block_unbind(mlxsw_sp, acl_block, mlxsw_sp_port, ingress); if (!err && !tcf_block_cb_decref(block_cb)) { - __tcf_block_cb_unregister(block_cb); + __tcf_block_cb_unregister(block, block_cb); mlxsw_sp_acl_block_destroy(acl_block); } } diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index a2c6d35ba057..4070b8eb6d14 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -78,7 +78,8 @@ struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block, int tcf_block_cb_register(struct tcf_block *block, tc_setup_cb_t *cb, void *cb_ident, void *cb_priv, struct netlink_ext_ack *extack); -void __tcf_block_cb_unregister(struct tcf_block_cb *block_cb); +void __tcf_block_cb_unregister(struct tcf_block *block, + struct tcf_block_cb *block_cb); void tcf_block_cb_unregister(struct tcf_block *block, tc_setup_cb_t *cb, void *cb_ident); @@ -177,7 +178,8 @@ int tcf_block_cb_register(struct tcf_block *block, } static inline -void __tcf_block_cb_unregister(struct tcf_block_cb *block_cb) +void __tcf_block_cb_unregister(struct tcf_block *block, + struct tcf_block_cb *block_cb) { } diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 8c9fb4b827a1..bbf8dda96b0e 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -751,19 +751,53 @@ unsigned int tcf_block_cb_decref(struct tcf_block_cb *block_cb) } EXPORT_SYMBOL(tcf_block_cb_decref); +static int +tcf_block_playback_offloads(struct tcf_block *block, tc_setup_cb_t *cb, + void *cb_priv, bool add, bool offload_in_use, + struct netlink_ext_ack *extack) +{ + struct tcf_chain *chain; + struct tcf_proto *tp; + int err; + + list_for_each_entry(chain, &block->chain_list, list) { + for (tp = rtnl_dereference(chain->filter_chain); tp; + tp = rtnl_dereference(tp->next)) { + if (tp->ops->reoffload) { + err = tp->ops->reoffload(tp, add, cb, cb_priv, + extack); + if (err && add) + goto err_playback_remove; + } else if (add && offload_in_use) { + err = -EOPNOTSUPP; + NL_SET_ERR_MSG(extack, "Filter HW offload failed - classifier without re-offloading support"); + goto err_playback_remove; + } + } + } + + return 0; + +err_playback_remove: + tcf_block_playback_offloads(block, cb, cb_priv, false, offload_in_use, + extack); + return err; +} + struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block, tc_setup_cb_t *cb, void *cb_ident, void *cb_priv, struct netlink_ext_ack *extack) { struct tcf_block_cb *block_cb; + int err; - /* At this point, playback of previous block cb calls is not supported, - * so forbid to register to block which already has some offloaded - * filters present. - */ - if (tcf_block_offload_in_use(block)) - return ERR_PTR(-EOPNOTSUPP); + /* Replay any already present rules */ + err = tcf_block_playback_offloads(block, cb, cb_priv, true, + tcf_block_offload_in_use(block), + extack); + if (err) + return ERR_PTR(err); block_cb = kzalloc(sizeof(*block_cb), GFP_KERNEL); if (!block_cb) @@ -788,8 +822,12 @@ int tcf_block_cb_register(struct tcf_block *block, } EXPORT_SYMBOL(tcf_block_cb_register); -void __tcf_block_cb_unregister(struct tcf_block_cb *block_cb) +void __tcf_block_cb_unregister(struct tcf_block *block, + struct tcf_block_cb *block_cb) { + tcf_block_playback_offloads(block, block_cb->cb, block_cb->cb_priv, + false, tcf_block_offload_in_use(block), + NULL); list_del(&block_cb->list); kfree(block_cb); } @@ -803,7 +841,7 @@ void tcf_block_cb_unregister(struct tcf_block *block, block_cb = tcf_block_cb_lookup(block, cb, cb_ident); if (!block_cb) return; - __tcf_block_cb_unregister(block_cb); + __tcf_block_cb_unregister(block, block_cb); } EXPORT_SYMBOL(tcf_block_cb_unregister); -- cgit v1.2.3 From e2607484370ea1b3595a3c51485e66e0cbd17341 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Fri, 22 Jun 2018 16:40:23 -0500 Subject: scsi: target: remove target_find_device target_find_device is no longer used, so remove it. Signed-off-by: Mike Christie Tested-by: Xiubo Li Signed-off-by: Martin K. Petersen --- drivers/target/target_core_device.c | 24 ------------------------ include/target/target_core_backend.h | 2 -- 2 files changed, 26 deletions(-) (limited to 'include') diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index e27db4d45a9d..a9ad6ecb1812 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -879,30 +879,6 @@ sector_t target_to_linux_sector(struct se_device *dev, sector_t lb) } EXPORT_SYMBOL(target_to_linux_sector); -/** - * target_find_device - find a se_device by its dev_index - * @id: dev_index - * @do_depend: true if caller needs target_depend_item to be done - * - * If do_depend is true, the caller must do a target_undepend_item - * when finished using the device. - * - * If do_depend is false, the caller must be called in a configfs - * callback or during removal. - */ -struct se_device *target_find_device(int id, bool do_depend) -{ - struct se_device *dev; - - mutex_lock(&device_mutex); - dev = idr_find(&devices_idr, id); - if (dev && do_depend && target_depend_item(&dev->dev_group.cg_item)) - dev = NULL; - mutex_unlock(&device_mutex); - return dev; -} -EXPORT_SYMBOL(target_find_device); - struct devices_idr_iter { int (*fn)(struct se_device *dev, void *data); void *data; diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h index 34a15d59ed88..c3ac47255218 100644 --- a/include/target/target_core_backend.h +++ b/include/target/target_core_backend.h @@ -106,8 +106,6 @@ bool target_lun_is_rdonly(struct se_cmd *); sense_reason_t passthrough_parse_cdb(struct se_cmd *cmd, sense_reason_t (*exec_cmd)(struct se_cmd *cmd)); -struct se_device *target_find_device(int id, bool do_depend); - bool target_sense_desc_format(struct se_device *dev); sector_t target_to_linux_sector(struct se_device *dev, sector_t lb); bool target_configure_unmap_from_queue(struct se_dev_attrib *attrib, -- cgit v1.2.3 From c84b023a4c1461498abf0eda54f60e2fd64a1ca2 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Sun, 24 Jun 2018 22:03:26 +0800 Subject: scsi: read host_busy via scsi_host_busy() No functional change. Just introduce scsi_host_busy() and replace the direct read of scsi_host->host_busy with this new API. Cc: Omar Sandoval , Cc: "Martin K. Petersen" , Cc: James Bottomley , Cc: Christoph Hellwig , Cc: Don Brace Cc: Kashyap Desai Cc: Mike Snitzer Cc: Hannes Reinecke Cc: Laurence Oberman Cc: Bart Van Assche Signed-off-by: Ming Lei Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- drivers/scsi/advansys.c | 8 ++++---- drivers/scsi/hosts.c | 10 ++++++++++ drivers/scsi/libsas/sas_scsi_host.c | 4 ++-- drivers/scsi/megaraid/megaraid_sas_base.c | 2 +- drivers/scsi/mpt3sas/mpt3sas_base.c | 4 ++-- drivers/scsi/qlogicpti.c | 2 +- drivers/scsi/scsi.c | 2 +- drivers/scsi/scsi_error.c | 6 +++--- drivers/scsi/scsi_sysfs.c | 2 +- include/scsi/scsi_host.h | 1 + 10 files changed, 26 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/drivers/scsi/advansys.c b/drivers/scsi/advansys.c index c9a52905070e..713f69033f20 100644 --- a/drivers/scsi/advansys.c +++ b/drivers/scsi/advansys.c @@ -2416,8 +2416,8 @@ static void asc_prt_scsi_host(struct Scsi_Host *s) struct asc_board *boardp = shost_priv(s); printk("Scsi_Host at addr 0x%p, device %s\n", s, dev_name(boardp->dev)); - printk(" host_busy %u, host_no %d,\n", - atomic_read(&s->host_busy), s->host_no); + printk(" host_busy %d, host_no %d,\n", + scsi_host_busy(s), s->host_no); printk(" base 0x%lx, io_port 0x%lx, irq %d,\n", (ulong)s->base, (ulong)s->io_port, boardp->irq); @@ -3182,8 +3182,8 @@ static void asc_prt_driver_conf(struct seq_file *m, struct Scsi_Host *shost) shost->host_no); seq_printf(m, - " host_busy %u, max_id %u, max_lun %llu, max_channel %u\n", - atomic_read(&shost->host_busy), shost->max_id, + " host_busy %d, max_id %u, max_lun %llu, max_channel %u\n", + scsi_host_busy(shost), shost->max_id, shost->max_lun, shost->max_channel); seq_printf(m, diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c index 3771e59a9fae..ea4b0bb0c1cd 100644 --- a/drivers/scsi/hosts.c +++ b/drivers/scsi/hosts.c @@ -563,6 +563,16 @@ struct Scsi_Host *scsi_host_get(struct Scsi_Host *shost) } EXPORT_SYMBOL(scsi_host_get); +/** + * scsi_host_busy - Return the host busy counter + * @shost: Pointer to Scsi_Host to inc. + **/ +int scsi_host_busy(struct Scsi_Host *shost) +{ + return atomic_read(&shost->host_busy); +} +EXPORT_SYMBOL(scsi_host_busy); + /** * scsi_host_put - dec a Scsi_Host ref count * @shost: Pointer to Scsi_Host to dec. diff --git a/drivers/scsi/libsas/sas_scsi_host.c b/drivers/scsi/libsas/sas_scsi_host.c index ceab5e5c41c2..33229348dcb6 100644 --- a/drivers/scsi/libsas/sas_scsi_host.c +++ b/drivers/scsi/libsas/sas_scsi_host.c @@ -759,7 +759,7 @@ retry: spin_unlock_irq(shost->host_lock); SAS_DPRINTK("Enter %s busy: %d failed: %d\n", - __func__, atomic_read(&shost->host_busy), shost->host_failed); + __func__, scsi_host_busy(shost), shost->host_failed); /* * Deal with commands that still have SAS tasks (i.e. they didn't * complete via the normal sas_task completion mechanism), @@ -801,7 +801,7 @@ out: goto retry; SAS_DPRINTK("--- Exit %s: busy: %d failed: %d tries: %d\n", - __func__, atomic_read(&shost->host_busy), + __func__, scsi_host_busy(shost), shost->host_failed, tries); } diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index e6ba02793610..9aa9590c5373 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -2834,7 +2834,7 @@ static int megasas_reset_bus_host(struct scsi_cmnd *scmd) "SCSI command pointer: (%p)\t SCSI host state: %d\t" " SCSI host busy: %d\t FW outstanding: %d\n", scmd, scmd->device->host->shost_state, - atomic_read((atomic_t *)&scmd->device->host->host_busy), + scsi_host_busy(scmd->device->host), atomic_read(&instance->fw_outstanding)); /* diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 2053970fc9f8..dc41bd3de08a 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -3250,7 +3250,7 @@ _base_recovery_check(struct MPT3SAS_ADAPTER *ioc) * See _wait_for_commands_to_complete() call with regards to this code. */ if (ioc->shost_recovery && ioc->pending_io_count) { - ioc->pending_io_count = atomic_read(&ioc->shost->host_busy); + ioc->pending_io_count = scsi_host_busy(ioc->shost); if (ioc->pending_io_count == 0) wake_up(&ioc->reset_wq); } @@ -6857,7 +6857,7 @@ mpt3sas_wait_for_commands_to_complete(struct MPT3SAS_ADAPTER *ioc) return; /* pending command count */ - ioc->pending_io_count = atomic_read(&ioc->shost->host_busy); + ioc->pending_io_count = scsi_host_busy(ioc->shost); if (!ioc->pending_io_count) return; diff --git a/drivers/scsi/qlogicpti.c b/drivers/scsi/qlogicpti.c index 8578e566ab41..9d09228eee28 100644 --- a/drivers/scsi/qlogicpti.c +++ b/drivers/scsi/qlogicpti.c @@ -959,7 +959,7 @@ static inline void update_can_queue(struct Scsi_Host *host, u_int in_ptr, u_int /* Temporary workaround until bug is found and fixed (one bug has been found already, but fixing it makes things even worse) -jj */ int num_free = QLOGICPTI_REQ_QUEUE_LEN - REQ_QUEUE_DEPTH(in_ptr, out_ptr) - 64; - host->can_queue = atomic_read(&host->host_busy) + num_free; + host->can_queue = scsi_host_busy(host) + num_free; host->sg_tablesize = QLOGICPTI_MAX_SG(num_free); } diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c index 70ef3c39061d..fc1356d101b0 100644 --- a/drivers/scsi/scsi.c +++ b/drivers/scsi/scsi.c @@ -167,7 +167,7 @@ void scsi_log_completion(struct scsi_cmnd *cmd, int disposition) if (level > 3) scmd_printk(KERN_INFO, cmd, "scsi host busy %d failed %d\n", - atomic_read(&cmd->device->host->host_busy), + scsi_host_busy(cmd->device->host), cmd->device->host->host_failed); } } diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 8932ae81a15a..6a014fd15fe9 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -66,7 +66,7 @@ void scsi_eh_wakeup(struct Scsi_Host *shost) { lockdep_assert_held(shost->host_lock); - if (atomic_read(&shost->host_busy) == shost->host_failed) { + if (scsi_host_busy(shost) == shost->host_failed) { trace_scsi_eh_wakeup(shost); wake_up_process(shost->ehandler); SCSI_LOG_ERROR_RECOVERY(5, shost_printk(KERN_INFO, shost, @@ -2155,7 +2155,7 @@ int scsi_error_handler(void *data) break; if ((shost->host_failed == 0 && shost->host_eh_scheduled == 0) || - shost->host_failed != atomic_read(&shost->host_busy)) { + shost->host_failed != scsi_host_busy(shost)) { SCSI_LOG_ERROR_RECOVERY(1, shost_printk(KERN_INFO, shost, "scsi_eh_%d: sleeping\n", @@ -2170,7 +2170,7 @@ int scsi_error_handler(void *data) "scsi_eh_%d: waking up %d/%d/%d\n", shost->host_no, shost->host_eh_scheduled, shost->host_failed, - atomic_read(&shost->host_busy))); + scsi_host_busy(shost))); /* * We have a host that is failing for some reason. Figure out diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index 7943b762c12d..de122354d09a 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -382,7 +382,7 @@ static ssize_t show_host_busy(struct device *dev, struct device_attribute *attr, char *buf) { struct Scsi_Host *shost = class_to_shost(dev); - return snprintf(buf, 20, "%d\n", atomic_read(&shost->host_busy)); + return snprintf(buf, 20, "%d\n", scsi_host_busy(shost)); } static DEVICE_ATTR(host_busy, S_IRUGO, show_host_busy, NULL); diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h index 53b485fe9b67..5ea06d310a25 100644 --- a/include/scsi/scsi_host.h +++ b/include/scsi/scsi_host.h @@ -758,6 +758,7 @@ extern void scsi_scan_host(struct Scsi_Host *); extern void scsi_rescan_device(struct device *); extern void scsi_remove_host(struct Scsi_Host *); extern struct Scsi_Host *scsi_host_get(struct Scsi_Host *); +extern int scsi_host_busy(struct Scsi_Host *shost); extern void scsi_host_put(struct Scsi_Host *t); extern struct Scsi_Host *scsi_host_lookup(unsigned short); extern const char *scsi_host_state_name(enum scsi_host_state); -- cgit v1.2.3 From b03799b0cb35dbc39e89602b1203863e2a6e06bf Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Mon, 25 Jun 2018 16:49:06 -0500 Subject: PCI: shpchp: Separate existence of SHPC and permission to use it The shpchp driver registers for all PCI bridge devices. Its probe method should fail if either (1) the bridge doesn't have an SHPC or (2) the OS isn't allowed to use it (the platform firmware may be operating the SHPC itself). Separate these two tests into: - A new shpc_capable() that looks for the SHPC hardware and is applicable on all systems (ACPI and non-ACPI), and - A simplified acpi_get_hp_hw_control_from_firmware() that we call only when we already know an SHPC exists and there may be ACPI methods to either request permission to use it (_OSC) or transfer control to the OS (OSHP). acpi_get_hp_hw_control_from_firmware() is implemented when CONFIG_ACPI=y, but does nothing if the current platform doesn't support ACPI. Signed-off-by: Bjorn Helgaas Reviewed-by: Mika Westerberg --- drivers/pci/hotplug/acpi_pcihp.c | 36 +++++++++++++++++++----------------- drivers/pci/hotplug/shpchp_core.c | 21 +++++++++++++++++++++ drivers/pci/pci-acpi.c | 19 +------------------ include/linux/pci.h | 1 + 4 files changed, 42 insertions(+), 35 deletions(-) (limited to 'include') diff --git a/drivers/pci/hotplug/acpi_pcihp.c b/drivers/pci/hotplug/acpi_pcihp.c index 5bd6c1573295..6b7c1ed58e7e 100644 --- a/drivers/pci/hotplug/acpi_pcihp.c +++ b/drivers/pci/hotplug/acpi_pcihp.c @@ -73,20 +73,6 @@ int acpi_get_hp_hw_control_from_firmware(struct pci_dev *pdev) acpi_handle chandle, handle; struct acpi_buffer string = { ACPI_ALLOCATE_BUFFER, NULL }; - /* - * Per PCI firmware specification, we should run the ACPI _OSC - * method to get control of hotplug hardware before using it. If - * an _OSC is missing, we look for an OSHP to do the same thing. - * To handle different BIOS behavior, we look for _OSC on a root - * bridge preferentially (according to PCI fw spec). Later for - * OSHP within the scope of the hotplug controller and its parents, - * up to the host bridge under which this controller exists. - */ - if (shpchp_is_native(pdev)) - return 0; - - /* If _OSC exists, we should not evaluate OSHP */ - /* * If there's no ACPI host bridge (i.e., ACPI support is compiled * into the kernel but the hardware platform doesn't support ACPI), @@ -97,9 +83,25 @@ int acpi_get_hp_hw_control_from_firmware(struct pci_dev *pdev) if (!root) return 0; - if (root->osc_support_set) - goto no_control; + /* + * If _OSC exists, it determines whether we're allowed to manage + * the SHPC. We executed it while enumerating the host bridge. + */ + if (root->osc_support_set) { + if (host->native_shpc_hotplug) + return 0; + return -ENODEV; + } + /* + * In the absence of _OSC, we're always allowed to manage the SHPC. + * However, if an OSHP method is present, we must execute it so the + * firmware can transfer control to the OS, e.g., direct interrupts + * to the OS instead of to the firmware. + * + * N.B. The PCI Firmware Spec (r3.2, sec 4.8) does not endorse + * searching up the ACPI hierarchy, so the loops below are suspect. + */ handle = ACPI_HANDLE(&pdev->dev); if (!handle) { /* @@ -128,7 +130,7 @@ int acpi_get_hp_hw_control_from_firmware(struct pci_dev *pdev) if (ACPI_FAILURE(status)) break; } -no_control: + pci_info(pdev, "Cannot get control of SHPC hotplug\n"); kfree(string.pointer); return -ENODEV; diff --git a/drivers/pci/hotplug/shpchp_core.c b/drivers/pci/hotplug/shpchp_core.c index e91be287f292..8e3c6ce12f31 100644 --- a/drivers/pci/hotplug/shpchp_core.c +++ b/drivers/pci/hotplug/shpchp_core.c @@ -270,11 +270,30 @@ static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value) return 0; } +static bool shpc_capable(struct pci_dev *bridge) +{ + /* + * It is assumed that AMD GOLAM chips support SHPC but they do not + * have SHPC capability. + */ + if (bridge->vendor == PCI_VENDOR_ID_AMD && + bridge->device == PCI_DEVICE_ID_AMD_GOLAM_7450) + return true; + + if (pci_find_capability(bridge, PCI_CAP_ID_SHPC)) + return true; + + return false; +} + static int shpc_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { int rc; struct controller *ctrl; + if (!shpc_capable(pdev)) + return -ENODEV; + if (acpi_get_hp_hw_control_from_firmware(pdev)) return -ENODEV; @@ -303,6 +322,7 @@ static int shpc_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (rc) goto err_cleanup_slots; + pdev->shpc_managed = 1; return 0; err_cleanup_slots: @@ -319,6 +339,7 @@ static void shpc_remove(struct pci_dev *dev) { struct controller *ctrl = pci_get_drvdata(dev); + dev->shpc_managed = 0; shpchp_remove_ctrl_files(ctrl); ctrl->hpc_ops->release_ctlr(ctrl); kfree(ctrl); diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c index 65113b6eed14..5100fd2d5a75 100644 --- a/drivers/pci/pci-acpi.c +++ b/drivers/pci/pci-acpi.c @@ -403,24 +403,7 @@ bool pciehp_is_native(struct pci_dev *bridge) */ bool shpchp_is_native(struct pci_dev *bridge) { - const struct pci_host_bridge *host; - - if (!IS_ENABLED(CONFIG_HOTPLUG_PCI_SHPC)) - return false; - - /* - * It is assumed that AMD GOLAM chips support SHPC but they do not - * have SHPC capability. - */ - if (bridge->vendor == PCI_VENDOR_ID_AMD && - bridge->device == PCI_DEVICE_ID_AMD_GOLAM_7450) - return true; - - if (!pci_find_capability(bridge, PCI_CAP_ID_SHPC)) - return false; - - host = pci_find_host_bridge(bridge->bus); - return host->native_shpc_hotplug; + return bridge->shpc_managed; } /** diff --git a/include/linux/pci.h b/include/linux/pci.h index 340029b2fb38..f776a1cce120 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -388,6 +388,7 @@ struct pci_dev { unsigned int is_virtfn:1; unsigned int reset_fn:1; unsigned int is_hotplug_bridge:1; + unsigned int shpc_managed:1; /* SHPC owned by shpchp */ unsigned int is_thunderbolt:1; /* Thunderbolt controller */ unsigned int __aer_firmware_first_valid:1; unsigned int __aer_firmware_first:1; -- cgit v1.2.3 From 22eceb8bf3e8f1f9b2f566062d06b25807725d7f Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Tue, 19 Jun 2018 13:57:26 +0200 Subject: printk: Make CONSOLE_LOGLEVEL_QUIET configurable The goal of passing the "quiet" option to the kernel is for the kernel to be quiet unless something really is wrong. Sofar passing quiet has been (mostly) equivalent to passing loglevel=4 on the kernel commandline. Which means to show any messages with a level of KERN_ERR or higher severity on the console. In practice this often does not result in a quiet boot though, since there are many false-positive or otherwise harmless error messages printed, defeating the purpose of the quiet option. Esp. the ACPICA code is really bad wrt this, but there are plenty of others too. This commit makes CONSOLE_LOGLEVEL_QUIET configurable. This for example will allow distros which want quiet to really mean quiet to set CONSOLE_LOGLEVEL_QUIET so that only messages with a higher severity then KERN_ERR (CRIT, ALERT, EMERG) get printed, avoiding an endless game of whack-a-mole silencing harmless error messages. Link: http://lkml.kernel.org/r/20180619115726.3098-1-hdegoede@redhat.com To: Petr Mladek To: Sergey Senozhatsky Cc: Hans de Goede Cc: Steven Rostedt Cc: linux-kernel@vger.kernel.org Signed-off-by: Hans de Goede Acked-by: Steven Rostedt (VMware) Reviewed-by: Sergey Senozhatsky Signed-off-by: Petr Mladek --- include/linux/printk.h | 6 +++--- lib/Kconfig.debug | 11 +++++++++++ 2 files changed, 14 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/printk.h b/include/linux/printk.h index 6d7e800affd8..18602bb3eca8 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -50,15 +50,15 @@ static inline const char *printk_skip_headers(const char *buffer) /* We show everything that is MORE important than this.. */ #define CONSOLE_LOGLEVEL_SILENT 0 /* Mum's the word */ #define CONSOLE_LOGLEVEL_MIN 1 /* Minimum loglevel we let people use */ -#define CONSOLE_LOGLEVEL_QUIET 4 /* Shhh ..., when booted with "quiet" */ #define CONSOLE_LOGLEVEL_DEBUG 10 /* issue debug messages */ #define CONSOLE_LOGLEVEL_MOTORMOUTH 15 /* You can't shut this one up */ /* - * Default used to be hard-coded at 7, we're now allowing it to be set from - * kernel config. + * Default used to be hard-coded at 7, quiet used to be hardcoded at 4, + * we're now allowing both to be set from kernel config. */ #define CONSOLE_LOGLEVEL_DEFAULT CONFIG_CONSOLE_LOGLEVEL_DEFAULT +#define CONSOLE_LOGLEVEL_QUIET CONFIG_CONSOLE_LOGLEVEL_QUIET extern int console_printk[]; diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 76555479ae36..a7ef03009e9e 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -30,6 +30,17 @@ config CONSOLE_LOGLEVEL_DEFAULT usage in the kernel. That is controlled by the MESSAGE_LOGLEVEL_DEFAULT option. +config CONSOLE_LOGLEVEL_QUIET + int "quiet console loglevel (1-15)" + range 1 15 + default "4" + help + loglevel to use when "quiet" is passed on the kernel commandline. + + When "quiet" is passed on the kernel commandline this loglevel + will be used as the loglevel. IOW passing "quiet" will be the + equivalent of passing "loglevel=" + config MESSAGE_LOGLEVEL_DEFAULT int "Default message log level (1-7)" range 1 7 -- cgit v1.2.3 From e7d4a95da86e0b048702765bbdcdc968aaf312e7 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 20 Jun 2018 08:58:28 +0200 Subject: bitfield: fix *_encode_bits() There's a bug in *_encode_bits() in using ~field_multiplier() for the check whether or not the constant value fits into the field, this is wrong and clearly ~field_mask() was intended. This was triggering for me for both constant and non-constant values. Additionally, make this case actually into an compile error. Declaring the extern function that will never exist with just a warning is pointless as then later we'll just get a link error. While at it, also fix the indentation in those lines I'm touching. Finally, as suggested by Andy Shevchenko, add some tests and for that introduce also u8 helpers. The tests don't compile without the fix, showing that it's necessary. Fixes: 00b0c9b82663 ("Add primitives for manipulating bitfields both in host- and fixed-endian.") Reviewed-by: Andy Shevchenko Signed-off-by: Johannes Berg Signed-off-by: Kalle Valo --- include/linux/bitfield.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/bitfield.h b/include/linux/bitfield.h index cf2588d81148..147a7bb341dd 100644 --- a/include/linux/bitfield.h +++ b/include/linux/bitfield.h @@ -104,7 +104,7 @@ (typeof(_mask))(((_reg) & (_mask)) >> __bf_shf(_mask)); \ }) -extern void __compiletime_warning("value doesn't fit into mask") +extern void __compiletime_error("value doesn't fit into mask") __field_overflow(void); extern void __compiletime_error("bad bitfield mask") __bad_mask(void); @@ -121,8 +121,8 @@ static __always_inline u64 field_mask(u64 field) #define ____MAKE_OP(type,base,to,from) \ static __always_inline __##type type##_encode_bits(base v, base field) \ { \ - if (__builtin_constant_p(v) && (v & ~field_multiplier(field))) \ - __field_overflow(); \ + if (__builtin_constant_p(v) && (v & ~field_mask(field))) \ + __field_overflow(); \ return to((v & field_mask(field)) * field_multiplier(field)); \ } \ static __always_inline __##type type##_replace_bits(__##type old, \ -- cgit v1.2.3 From 37a3862e1238262e9866d5d66e5f5f9069cee3a1 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 20 Jun 2018 08:58:29 +0200 Subject: bitfield: add u8 helpers There's no reason why we shouldn't pack/unpack bits into/from u8 values/registers/etc., so add u8 helpers. Use the ____MAKE_OP() macro directly to avoid having nonsense le8_encode_bits() and similar functions. Reviewed-by: Andy Shevchenko Signed-off-by: Johannes Berg Signed-off-by: Kalle Valo --- include/linux/bitfield.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/bitfield.h b/include/linux/bitfield.h index 147a7bb341dd..65a6981eef7b 100644 --- a/include/linux/bitfield.h +++ b/include/linux/bitfield.h @@ -143,6 +143,7 @@ static __always_inline base type##_get_bits(__##type v, base field) \ ____MAKE_OP(le##size,u##size,cpu_to_le##size,le##size##_to_cpu) \ ____MAKE_OP(be##size,u##size,cpu_to_be##size,be##size##_to_cpu) \ ____MAKE_OP(u##size,u##size,,) +____MAKE_OP(u8,u8,,) __MAKE_OP(16) __MAKE_OP(32) __MAKE_OP(64) -- cgit v1.2.3 From d18e85349f6a65baa69b8ee397efb93e4ca31909 Mon Sep 17 00:00:00 2001 From: Jernej Skrabec Date: Mon, 25 Jun 2018 14:02:43 +0200 Subject: clk: sunxi-ng: r40: Export video PLLs Video PLLs need to be referenced in R40 DT as possible HDMI PHY parent. Export them. Reviewed-by: Rob Herring Reviewed-by: Chen-Yu Tsai Signed-off-by: Jernej Skrabec Signed-off-by: Maxime Ripard --- drivers/clk/sunxi-ng/ccu-sun8i-r40.h | 8 ++++++-- include/dt-bindings/clock/sun8i-r40-ccu.h | 4 ++++ 2 files changed, 10 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-r40.h b/drivers/clk/sunxi-ng/ccu-sun8i-r40.h index 0db8e1e97af8..db2a1243f9ff 100644 --- a/drivers/clk/sunxi-ng/ccu-sun8i-r40.h +++ b/drivers/clk/sunxi-ng/ccu-sun8i-r40.h @@ -25,7 +25,9 @@ #define CLK_PLL_AUDIO_2X 4 #define CLK_PLL_AUDIO_4X 5 #define CLK_PLL_AUDIO_8X 6 -#define CLK_PLL_VIDEO0 7 + +/* PLL_VIDEO0 is exported */ + #define CLK_PLL_VIDEO0_2X 8 #define CLK_PLL_VE 9 #define CLK_PLL_DDR0 10 @@ -34,7 +36,9 @@ #define CLK_PLL_PERIPH0_2X 13 #define CLK_PLL_PERIPH1 14 #define CLK_PLL_PERIPH1_2X 15 -#define CLK_PLL_VIDEO1 16 + +/* PLL_VIDEO1 is exported */ + #define CLK_PLL_VIDEO1_2X 17 #define CLK_PLL_SATA 18 #define CLK_PLL_SATA_OUT 19 diff --git a/include/dt-bindings/clock/sun8i-r40-ccu.h b/include/dt-bindings/clock/sun8i-r40-ccu.h index 4fa5f69fc297..f9e15a235626 100644 --- a/include/dt-bindings/clock/sun8i-r40-ccu.h +++ b/include/dt-bindings/clock/sun8i-r40-ccu.h @@ -43,6 +43,10 @@ #ifndef _DT_BINDINGS_CLK_SUN8I_R40_H_ #define _DT_BINDINGS_CLK_SUN8I_R40_H_ +#define CLK_PLL_VIDEO0 7 + +#define CLK_PLL_VIDEO1 16 + #define CLK_CPU 24 #define CLK_BUS_MIPI_DSI 29 -- cgit v1.2.3 From 59a9c39544cd1e5952c2a33028d71aa8180648f8 Mon Sep 17 00:00:00 2001 From: Jernej Skrabec Date: Mon, 25 Jun 2018 14:02:44 +0200 Subject: dt-bindings: display: sunxi-drm: Add TCON TOP description TCON TOP main purpose is to configure whole display pipeline. It determines relationships between mixers and TCONs, selects source TCON for HDMI, muxes LCD and TV encoder GPIO output, selects TV encoder clock source and contains additional TV TCON and DSI gates. Reviewed-by: Rob Herring Signed-off-by: Jernej Skrabec Signed-off-by: Maxime Ripard Link: https://patchwork.freedesktop.org/patch/msgid/20180625120304.7543-5-jernej.skrabec@siol.net --- .../bindings/display/sunxi/sun4i-drm.txt | 56 ++++++++++++++++++++++ include/dt-bindings/clock/sun8i-tcon-top.h | 11 +++++ 2 files changed, 67 insertions(+) create mode 100644 include/dt-bindings/clock/sun8i-tcon-top.h (limited to 'include') diff --git a/Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt b/Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt index 3346c1e2a7a0..fe31b1510717 100644 --- a/Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt +++ b/Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt @@ -187,6 +187,62 @@ And on the A23, A31, A31s and A33, you need one more clock line: - 'lvds-alt': An alternative clock source, separate from the TCON channel 0 clock, that can be used to drive the LVDS clock +TCON TOP +-------- + +TCON TOPs main purpose is to configure whole display pipeline. It determines +relationships between mixers and TCONs, selects source TCON for HDMI, muxes +LCD and TV encoder GPIO output, selects TV encoder clock source and contains +additional TV TCON and DSI gates. + +It allows display pipeline to be configured in very different ways: + + / LCD0/LVDS0 + / [0] TCON-LCD0 + | \ MIPI DSI + mixer0 | + \ / [1] TCON-LCD1 - LCD1/LVDS1 + TCON-TOP + / \ [2] TCON-TV0 [0] - TVE0/RGB + mixer1 | \ + | TCON-TOP - HDMI + | / + \ [3] TCON-TV1 [1] - TVE1/RGB + +Note that both TCON TOP references same physical unit. Both mixers can be +connected to any TCON. + +Required properties: + - compatible: value must be one of: + * allwinner,sun8i-r40-tcon-top + - reg: base address and size of the memory-mapped region. + - clocks: phandle to the clocks feeding the TCON TOP + * bus: TCON TOP interface clock + * tcon-tv0: TCON TV0 clock + * tve0: TVE0 clock + * tcon-tv1: TCON TV1 clock + * tve1: TVE0 clock + * dsi: MIPI DSI clock + - clock-names: clock name mentioned above + - resets: phandle to the reset line driving the TCON TOP + - #clock-cells : must contain 1 + - clock-output-names: Names of clocks created for TCON TV0 channel clock, + TCON TV1 channel clock and DSI channel clock, in that order. + +- ports: A ports node with endpoint definitions as defined in + Documentation/devicetree/bindings/media/video-interfaces.txt. 6 ports should + be defined: + * port 0 is input for mixer0 mux + * port 1 is output for mixer0 mux + * port 2 is input for mixer1 mux + * port 3 is output for mixer1 mux + * port 4 is input for HDMI mux + * port 5 is output for HDMI mux + All output endpoints for mixer muxes and input endpoints for HDMI mux should + have reg property with the id of the target TCON, as shown in above graph + (0-3 for mixer muxes and 0-1 for HDMI mux). All ports should have only one + endpoint connected to remote endpoint. + DRC --- diff --git a/include/dt-bindings/clock/sun8i-tcon-top.h b/include/dt-bindings/clock/sun8i-tcon-top.h new file mode 100644 index 000000000000..25164d767835 --- /dev/null +++ b/include/dt-bindings/clock/sun8i-tcon-top.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: (GPL-2.0+ OR MIT) */ +/* Copyright (C) 2018 Jernej Skrabec */ + +#ifndef _DT_BINDINGS_CLOCK_SUN8I_TCON_TOP_H_ +#define _DT_BINDINGS_CLOCK_SUN8I_TCON_TOP_H_ + +#define CLK_TCON_TOP_TV0 0 +#define CLK_TCON_TOP_TV1 1 +#define CLK_TCON_TOP_DSI 2 + +#endif /* _DT_BINDINGS_CLOCK_SUN8I_TCON_TOP_H_ */ -- cgit v1.2.3 From 8b5f7a62464a24cb83d6290c01d6cf9c8871774a Mon Sep 17 00:00:00 2001 From: Jernej Skrabec Date: Mon, 25 Jun 2018 14:03:01 +0200 Subject: drm: of: Export and rename drm_crtc_port_mask() Function is useful when drm_of_find_possible_crtcs() can't be used and custom parsing is needed. This can happen for example when there is a node with multiple muxes between crtc and encoder. Reviewed-by: Sean Paul Signed-off-by: Jernej Skrabec [maxime: change the function to have a consistent prefix] Signed-off-by: Maxime Ripard Link: https://patchwork.freedesktop.org/patch/msgid/20180625120304.7543-22-jernej.skrabec@siol.net --- drivers/gpu/drm/drm_of.c | 9 +++++---- include/drm/drm_of.h | 8 ++++++++ 2 files changed, 13 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_of.c b/drivers/gpu/drm/drm_of.c index 1fe122461298..3b8c7a6a5720 100644 --- a/drivers/gpu/drm/drm_of.c +++ b/drivers/gpu/drm/drm_of.c @@ -15,15 +15,15 @@ static void drm_release_of(struct device *dev, void *data) } /** - * drm_crtc_port_mask - find the mask of a registered CRTC by port OF node + * drm_of_crtc_port_mask - find the mask of a registered CRTC by port OF node * @dev: DRM device * @port: port OF node * * Given a port OF node, return the possible mask of the corresponding * CRTC within a device's list of CRTCs. Returns zero if not found. */ -static uint32_t drm_crtc_port_mask(struct drm_device *dev, - struct device_node *port) +uint32_t drm_of_crtc_port_mask(struct drm_device *dev, + struct device_node *port) { unsigned int index = 0; struct drm_crtc *tmp; @@ -37,6 +37,7 @@ static uint32_t drm_crtc_port_mask(struct drm_device *dev, return 0; } +EXPORT_SYMBOL(drm_of_crtc_port_mask); /** * drm_of_find_possible_crtcs - find the possible CRTCs for an encoder port @@ -62,7 +63,7 @@ uint32_t drm_of_find_possible_crtcs(struct drm_device *dev, return 0; } - possible_crtcs |= drm_crtc_port_mask(dev, remote_port); + possible_crtcs |= drm_of_crtc_port_mask(dev, remote_port); of_node_put(remote_port); } diff --git a/include/drm/drm_of.h b/include/drm/drm_of.h index b93c239afb60..ead34ab5ca4e 100644 --- a/include/drm/drm_of.h +++ b/include/drm/drm_of.h @@ -17,6 +17,8 @@ struct drm_bridge; struct device_node; #ifdef CONFIG_OF +uint32_t drm_of_crtc_port_mask(struct drm_device *dev, + struct device_node *port); uint32_t drm_of_find_possible_crtcs(struct drm_device *dev, struct device_node *port); void drm_of_component_match_add(struct device *master, @@ -34,6 +36,12 @@ int drm_of_find_panel_or_bridge(const struct device_node *np, struct drm_panel **panel, struct drm_bridge **bridge); #else +static inline uint32_t drm_of_crtc_port_mask(struct drm_device *dev, + struct device_node *port) +{ + return 0; +} + static inline uint32_t drm_of_find_possible_crtcs(struct drm_device *dev, struct device_node *port) { -- cgit v1.2.3 From feb20faec73ba0b30f949d54c4153cf0ad3807c8 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 27 Jun 2018 09:03:51 +0200 Subject: ALSA: hda - Move in_pm accessors to HDA core The in_pm atomic in hdac_device is an important field used as a flag as well as a refcount for PM. The existing snd_hdac_power_up/down helpers already refer to it in the HD-audio core code, while the code to actually setting the value (atomic_inc() / _dec()) is open-coded in HDA legacy side, which is hard to find. This patch adds the helper functions to set/reset the in_pm counter to HDA core and use them in HDA legacy side, for making it clearer who / where the PM is managed. There is no functional changes, just code refactoring. Reviewed-by: Chris Wilson Signed-off-by: Takashi Iwai --- include/sound/hdaudio.h | 27 +++++++++++++++++++++++++++ sound/pci/hda/hda_codec.c | 21 ++++++--------------- sound/pci/hda/patch_hdmi.c | 2 +- 3 files changed, 34 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/sound/hdaudio.h b/include/sound/hdaudio.h index c052afc27547..294a5a21937b 100644 --- a/include/sound/hdaudio.h +++ b/include/sound/hdaudio.h @@ -8,6 +8,7 @@ #include #include +#include #include #include #include @@ -171,12 +172,38 @@ int snd_hdac_power_down(struct hdac_device *codec); int snd_hdac_power_up_pm(struct hdac_device *codec); int snd_hdac_power_down_pm(struct hdac_device *codec); int snd_hdac_keep_power_up(struct hdac_device *codec); + +/* call this at entering into suspend/resume callbacks in codec driver */ +static inline void snd_hdac_enter_pm(struct hdac_device *codec) +{ + atomic_inc(&codec->in_pm); +} + +/* call this at leaving from suspend/resume callbacks in codec driver */ +static inline void snd_hdac_leave_pm(struct hdac_device *codec) +{ + atomic_dec(&codec->in_pm); +} + +static inline bool snd_hdac_is_in_pm(struct hdac_device *codec) +{ + return atomic_read(&codec->in_pm); +} + +static inline bool snd_hdac_is_power_on(struct hdac_device *codec) +{ + return !pm_runtime_suspended(&codec->dev); +} #else static inline int snd_hdac_power_up(struct hdac_device *codec) { return 0; } static inline int snd_hdac_power_down(struct hdac_device *codec) { return 0; } static inline int snd_hdac_power_up_pm(struct hdac_device *codec) { return 0; } static inline int snd_hdac_power_down_pm(struct hdac_device *codec) { return 0; } static inline int snd_hdac_keep_power_up(struct hdac_device *codec) { return 0; } +static inline void snd_hdac_enter_pm(struct hdac_device *codec) {} +static inline void snd_hdac_leave_pm(struct hdac_device *codec) {} +static inline bool snd_hdac_is_in_pm(struct hdac_device *codec) { return 0; } +static inline bool snd_hdac_is_power_on(struct hdac_device *codec) { return 1; } #endif /* diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c index f42af88bd2de..decd46b51087 100644 --- a/sound/pci/hda/hda_codec.c +++ b/sound/pci/hda/hda_codec.c @@ -37,15 +37,8 @@ #include "hda_jack.h" #include -#ifdef CONFIG_PM -#define codec_in_pm(codec) atomic_read(&(codec)->core.in_pm) -#define hda_codec_is_power_on(codec) \ - (!pm_runtime_suspended(hda_codec_dev(codec))) -#else -#define codec_in_pm(codec) 0 -#define hda_codec_is_power_on(codec) 1 -#endif - +#define codec_in_pm(codec) snd_hdac_is_in_pm(&codec->core) +#define hda_codec_is_power_on(codec) snd_hdac_is_power_on(&codec->core) #define codec_has_epss(codec) \ ((codec)->core.power_caps & AC_PWRST_EPSS) #define codec_has_clkstop(codec) \ @@ -2846,14 +2839,13 @@ static unsigned int hda_call_codec_suspend(struct hda_codec *codec) { unsigned int state; - atomic_inc(&codec->core.in_pm); - + snd_hdac_enter_pm(&codec->core); if (codec->patch_ops.suspend) codec->patch_ops.suspend(codec); hda_cleanup_all_streams(codec); state = hda_set_power_state(codec, AC_PWRST_D3); update_power_acct(codec, true); - atomic_dec(&codec->core.in_pm); + snd_hdac_leave_pm(&codec->core); return state; } @@ -2862,8 +2854,7 @@ static unsigned int hda_call_codec_suspend(struct hda_codec *codec) */ static void hda_call_codec_resume(struct hda_codec *codec) { - atomic_inc(&codec->core.in_pm); - + snd_hdac_enter_pm(&codec->core); if (codec->core.regmap) regcache_mark_dirty(codec->core.regmap); @@ -2886,7 +2877,7 @@ static void hda_call_codec_resume(struct hda_codec *codec) hda_jackpoll_work(&codec->jackpoll_work.work); else snd_hda_jack_report_sync(codec); - atomic_dec(&codec->core.in_pm); + snd_hdac_leave_pm(&codec->core); } static int hda_codec_runtime_suspend(struct device *dev) diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 8840daf9c6a3..ed2318f79e3c 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -2489,7 +2489,7 @@ static void intel_pin_eld_notify(void *audio_ptr, int port, int pipe) if (snd_power_get_state(codec->card) != SNDRV_CTL_POWER_D0) return; /* ditto during suspend/resume process itself */ - if (atomic_read(&(codec)->core.in_pm)) + if (snd_hdac_is_in_pm(&codec->core)) return; snd_hdac_i915_set_bclk(&codec->bus->core); -- cgit v1.2.3 From 3787a39852b0d6a9e67336f8fb5815c13ab78bb6 Mon Sep 17 00:00:00 2001 From: Rakesh Ughreja Date: Fri, 1 Jun 2018 22:53:49 -0500 Subject: ALSA: hdac: Remove usage of struct hdac_ext_device and use hdac_device instead This patch removes the hdac_ext_device structure. The legacy and enhanced HDaudio capabilities can be handled in a backward-compatible way without separate definitions. Follow-up patches in this series handle the bus and driver definitions. Signed-off-by: Rakesh Ughreja Signed-off-by: Pierre-Louis Bossart Signed-off-by: Takashi Iwai --- include/sound/hdaudio_ext.h | 36 +--- sound/hda/ext/hdac_ext_bus.c | 25 ++- sound/soc/codecs/hdac_hdmi.c | 396 +++++++++++++++++++++---------------------- 3 files changed, 204 insertions(+), 253 deletions(-) (limited to 'include') diff --git a/include/sound/hdaudio_ext.h b/include/sound/hdaudio_ext.h index 9c14e21dda85..c1a5ad0e6e39 100644 --- a/include/sound/hdaudio_ext.h +++ b/include/sound/hdaudio_ext.h @@ -181,48 +181,20 @@ struct hda_dai_map { u32 maxbps; }; -#define HDA_MAX_NIDS 16 - -/** - * struct hdac_ext_device - HDAC Ext device - * - * @hdac: hdac core device - * @nid_list - the dai map which matches the dai-name with the nid - * @map_cur_idx - the idx in use in dai_map - * @ops - the hda codec ops common to all codec drivers - * @pvt_data - private data, for asoc contains asoc codec object - */ -struct hdac_ext_device { - struct hdac_device hdev; - struct hdac_ext_bus *ebus; - - /* soc-dai to nid map */ - struct hda_dai_map nid_list[HDA_MAX_NIDS]; - unsigned int map_cur_idx; - - /* codec ops */ - struct hdac_ext_codec_ops ops; - - struct snd_card *card; - void *scodec; - void *private_data; -}; - struct hdac_ext_dma_params { u32 format; u8 stream_tag; }; -#define to_ehdac_device(dev) (container_of((dev), \ - struct hdac_ext_device, hdev)) + /* * HD-audio codec base driver */ struct hdac_ext_driver { struct hdac_driver hdac; - int (*probe)(struct hdac_ext_device *dev); - int (*remove)(struct hdac_ext_device *dev); - void (*shutdown)(struct hdac_ext_device *dev); + int (*probe)(struct hdac_device *dev); + int (*remove)(struct hdac_device *dev); + void (*shutdown)(struct hdac_device *dev); }; int snd_hda_ext_driver_register(struct hdac_ext_driver *drv); diff --git a/sound/hda/ext/hdac_ext_bus.c b/sound/hda/ext/hdac_ext_bus.c index 0daf31383084..0e4823fdd411 100644 --- a/sound/hda/ext/hdac_ext_bus.c +++ b/sound/hda/ext/hdac_ext_bus.c @@ -137,17 +137,16 @@ static void default_release(struct device *dev) */ int snd_hdac_ext_bus_device_init(struct hdac_ext_bus *ebus, int addr) { - struct hdac_ext_device *edev; struct hdac_device *hdev = NULL; struct hdac_bus *bus = ebus_to_hbus(ebus); char name[15]; int ret; - edev = kzalloc(sizeof(*edev), GFP_KERNEL); - if (!edev) + hdev = kzalloc(sizeof(*hdev), GFP_KERNEL); + if (!hdev) return -ENOMEM; - hdev = &edev->hdev; - edev->ebus = ebus; + + hdev->bus = bus; snprintf(name, sizeof(name), "ehdaudio%dD%d", ebus->idx, addr); @@ -176,10 +175,8 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_device_init); */ void snd_hdac_ext_bus_device_exit(struct hdac_device *hdev) { - struct hdac_ext_device *edev = to_ehdac_device(hdev); - snd_hdac_device_exit(hdev); - kfree(edev); + kfree(hdev); } EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_device_exit); @@ -212,27 +209,25 @@ static inline struct hdac_ext_driver *get_edrv(struct device *dev) return edrv; } -static inline struct hdac_ext_device *get_edev(struct device *dev) +static inline struct hdac_device *get_hdev(struct device *dev) { struct hdac_device *hdev = dev_to_hdac_dev(dev); - struct hdac_ext_device *edev = to_ehdac_device(hdev); - - return edev; + return hdev; } static int hda_ext_drv_probe(struct device *dev) { - return (get_edrv(dev))->probe(get_edev(dev)); + return (get_edrv(dev))->probe(get_hdev(dev)); } static int hdac_ext_drv_remove(struct device *dev) { - return (get_edrv(dev))->remove(get_edev(dev)); + return (get_edrv(dev))->remove(get_hdev(dev)); } static void hdac_ext_drv_shutdown(struct device *dev) { - return (get_edrv(dev))->shutdown(get_edev(dev)); + return (get_edrv(dev))->shutdown(get_hdev(dev)); } /** diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c index 84f7a7a36e4b..f1e235817a65 100644 --- a/sound/soc/codecs/hdac_hdmi.c +++ b/sound/soc/codecs/hdac_hdmi.c @@ -85,7 +85,7 @@ struct hdac_hdmi_pin { bool mst_capable; struct hdac_hdmi_port *ports; int num_ports; - struct hdac_ext_device *edev; + struct hdac_device *hdev; }; struct hdac_hdmi_port { @@ -126,6 +126,9 @@ struct hdac_hdmi_drv_data { }; struct hdac_hdmi_priv { + struct hdac_device *hdev; + struct snd_soc_component *component; + struct snd_card *card; struct hdac_hdmi_dai_port_map dai_map[HDA_MAX_CVTS]; struct list_head pin_list; struct list_head cvt_list; @@ -139,7 +142,7 @@ struct hdac_hdmi_priv { struct snd_soc_dai_driver *dai_drv; }; -#define hdev_to_hdmi_priv(_hdev) ((to_ehdac_device(_hdev))->private_data) +#define hdev_to_hdmi_priv(_hdev) dev_get_drvdata(&(_hdev)->dev) static struct hdac_hdmi_pcm * hdac_hdmi_get_pcm_from_cvt(struct hdac_hdmi_priv *hdmi, @@ -158,7 +161,7 @@ hdac_hdmi_get_pcm_from_cvt(struct hdac_hdmi_priv *hdmi, static void hdac_hdmi_jack_report(struct hdac_hdmi_pcm *pcm, struct hdac_hdmi_port *port, bool is_connect) { - struct hdac_ext_device *edev = port->pin->edev; + struct hdac_device *hdev = port->pin->hdev; if (is_connect) snd_soc_dapm_enable_pin(port->dapm, port->jack_pin); @@ -172,7 +175,7 @@ static void hdac_hdmi_jack_report(struct hdac_hdmi_pcm *pcm, * ports. */ if (pcm->jack_event == 0) { - dev_dbg(&edev->hdev.dev, + dev_dbg(&hdev->dev, "jack report for pcm=%d\n", pcm->pcm_id); snd_soc_jack_report(pcm->jack, SND_JACK_AVOUT, @@ -198,19 +201,18 @@ static void hdac_hdmi_jack_report(struct hdac_hdmi_pcm *pcm, /* * Get the no devices that can be connected to a port on the Pin widget. */ -static int hdac_hdmi_get_port_len(struct hdac_ext_device *edev, hda_nid_t nid) +static int hdac_hdmi_get_port_len(struct hdac_device *hdev, hda_nid_t nid) { unsigned int caps; unsigned int type, param; - caps = get_wcaps(&edev->hdev, nid); + caps = get_wcaps(hdev, nid); type = get_wcaps_type(caps); if (!(caps & AC_WCAP_DIGITAL) || (type != AC_WID_PIN)) return 0; - param = snd_hdac_read_parm_uncached(&edev->hdev, nid, - AC_PAR_DEVLIST_LEN); + param = snd_hdac_read_parm_uncached(hdev, nid, AC_PAR_DEVLIST_LEN); if (param == -1) return param; @@ -222,10 +224,10 @@ static int hdac_hdmi_get_port_len(struct hdac_ext_device *edev, hda_nid_t nid) * id selected on the pin. Return 0 means the first port entry * is selected or MST is not supported. */ -static int hdac_hdmi_port_select_get(struct hdac_ext_device *edev, +static int hdac_hdmi_port_select_get(struct hdac_device *hdev, struct hdac_hdmi_port *port) { - return snd_hdac_codec_read(&edev->hdev, port->pin->nid, + return snd_hdac_codec_read(hdev, port->pin->nid, 0, AC_VERB_GET_DEVICE_SEL, 0); } @@ -233,7 +235,7 @@ static int hdac_hdmi_port_select_get(struct hdac_ext_device *edev, * Sets the selected port entry for the configuring Pin widget verb. * returns error if port set is not equal to port get otherwise success */ -static int hdac_hdmi_port_select_set(struct hdac_ext_device *edev, +static int hdac_hdmi_port_select_set(struct hdac_device *hdev, struct hdac_hdmi_port *port) { int num_ports; @@ -242,8 +244,7 @@ static int hdac_hdmi_port_select_set(struct hdac_ext_device *edev, return 0; /* AC_PAR_DEVLIST_LEN is 0 based. */ - num_ports = hdac_hdmi_get_port_len(edev, port->pin->nid); - + num_ports = hdac_hdmi_get_port_len(hdev, port->pin->nid); if (num_ports < 0) return -EIO; /* @@ -253,13 +254,13 @@ static int hdac_hdmi_port_select_set(struct hdac_ext_device *edev, if (num_ports + 1 < port->id) return 0; - snd_hdac_codec_write(&edev->hdev, port->pin->nid, 0, + snd_hdac_codec_write(hdev, port->pin->nid, 0, AC_VERB_SET_DEVICE_SEL, port->id); - if (port->id != hdac_hdmi_port_select_get(edev, port)) + if (port->id != hdac_hdmi_port_select_get(hdev, port)) return -EIO; - dev_dbg(&edev->hdev.dev, "Selected the port=%d\n", port->id); + dev_dbg(&hdev->dev, "Selected the port=%d\n", port->id); return 0; } @@ -277,13 +278,6 @@ static struct hdac_hdmi_pcm *get_hdmi_pcm_from_id(struct hdac_hdmi_priv *hdmi, return NULL; } -static inline struct hdac_ext_device *to_hda_ext_device(struct device *dev) -{ - struct hdac_device *hdev = dev_to_hdac_dev(dev); - - return to_ehdac_device(hdev); -} - static unsigned int sad_format(const u8 *sad) { return ((sad[0] >> 0x3) & 0x1f); @@ -324,15 +318,13 @@ format_constraint: } static void -hdac_hdmi_set_dip_index(struct hdac_ext_device *edev, hda_nid_t pin_nid, +hdac_hdmi_set_dip_index(struct hdac_device *hdev, hda_nid_t pin_nid, int packet_index, int byte_index) { int val; val = (packet_index << 5) | (byte_index & 0x1f); - - snd_hdac_codec_write(&edev->hdev, pin_nid, 0, - AC_VERB_SET_HDMI_DIP_INDEX, val); + snd_hdac_codec_write(hdev, pin_nid, 0, AC_VERB_SET_HDMI_DIP_INDEX, val); } struct dp_audio_infoframe { @@ -347,14 +339,14 @@ struct dp_audio_infoframe { u8 LFEPBL01_LSV36_DM_INH7; }; -static int hdac_hdmi_setup_audio_infoframe(struct hdac_ext_device *edev, +static int hdac_hdmi_setup_audio_infoframe(struct hdac_device *hdev, struct hdac_hdmi_pcm *pcm, struct hdac_hdmi_port *port) { uint8_t buffer[HDMI_INFOFRAME_HEADER_SIZE + HDMI_AUDIO_INFOFRAME_SIZE]; struct hdmi_audio_infoframe frame; struct hdac_hdmi_pin *pin = port->pin; struct dp_audio_infoframe dp_ai; - struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev); + struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev); struct hdac_hdmi_cvt *cvt = pcm->cvt; u8 *dip; int ret; @@ -363,11 +355,11 @@ static int hdac_hdmi_setup_audio_infoframe(struct hdac_ext_device *edev, u8 conn_type; int channels, ca; - ca = snd_hdac_channel_allocation(&edev->hdev, port->eld.info.spk_alloc, + ca = snd_hdac_channel_allocation(hdev, port->eld.info.spk_alloc, pcm->channels, pcm->chmap_set, true, pcm->chmap); channels = snd_hdac_get_active_channels(ca); - hdmi->chmap.ops.set_channel_count(&edev->hdev, cvt->nid, channels); + hdmi->chmap.ops.set_channel_count(hdev, cvt->nid, channels); snd_hdac_setup_channel_mapping(&hdmi->chmap, pin->nid, false, ca, pcm->channels, pcm->chmap, pcm->chmap_set); @@ -400,32 +392,31 @@ static int hdac_hdmi_setup_audio_infoframe(struct hdac_ext_device *edev, break; default: - dev_err(&edev->hdev.dev, "Invalid connection type: %d\n", - conn_type); + dev_err(&hdev->dev, "Invalid connection type: %d\n", conn_type); return -EIO; } /* stop infoframe transmission */ - hdac_hdmi_set_dip_index(edev, pin->nid, 0x0, 0x0); - snd_hdac_codec_write(&edev->hdev, pin->nid, 0, + hdac_hdmi_set_dip_index(hdev, pin->nid, 0x0, 0x0); + snd_hdac_codec_write(hdev, pin->nid, 0, AC_VERB_SET_HDMI_DIP_XMIT, AC_DIPXMIT_DISABLE); /* Fill infoframe. Index auto-incremented */ - hdac_hdmi_set_dip_index(edev, pin->nid, 0x0, 0x0); + hdac_hdmi_set_dip_index(hdev, pin->nid, 0x0, 0x0); if (conn_type == DRM_ELD_CONN_TYPE_HDMI) { for (i = 0; i < sizeof(buffer); i++) - snd_hdac_codec_write(&edev->hdev, pin->nid, 0, + snd_hdac_codec_write(hdev, pin->nid, 0, AC_VERB_SET_HDMI_DIP_DATA, buffer[i]); } else { for (i = 0; i < sizeof(dp_ai); i++) - snd_hdac_codec_write(&edev->hdev, pin->nid, 0, + snd_hdac_codec_write(hdev, pin->nid, 0, AC_VERB_SET_HDMI_DIP_DATA, dip[i]); } /* Start infoframe */ - hdac_hdmi_set_dip_index(edev, pin->nid, 0x0, 0x0); - snd_hdac_codec_write(&edev->hdev, pin->nid, 0, + hdac_hdmi_set_dip_index(hdev, pin->nid, 0x0, 0x0); + snd_hdac_codec_write(hdev, pin->nid, 0, AC_VERB_SET_HDMI_DIP_XMIT, AC_DIPXMIT_BEST); return 0; @@ -435,12 +426,12 @@ static int hdac_hdmi_set_tdm_slot(struct snd_soc_dai *dai, unsigned int tx_mask, unsigned int rx_mask, int slots, int slot_width) { - struct hdac_ext_device *edev = snd_soc_dai_get_drvdata(dai); - struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev); + struct hdac_hdmi_priv *hdmi = snd_soc_dai_get_drvdata(dai); + struct hdac_device *hdev = hdmi->hdev; struct hdac_hdmi_dai_port_map *dai_map; struct hdac_hdmi_pcm *pcm; - dev_dbg(&edev->hdev.dev, "%s: strm_tag: %d\n", __func__, tx_mask); + dev_dbg(&hdev->dev, "%s: strm_tag: %d\n", __func__, tx_mask); dai_map = &hdmi->dai_map[dai->id]; @@ -455,8 +446,8 @@ static int hdac_hdmi_set_tdm_slot(struct snd_soc_dai *dai, static int hdac_hdmi_set_hw_params(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *hparams, struct snd_soc_dai *dai) { - struct hdac_ext_device *edev = snd_soc_dai_get_drvdata(dai); - struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev); + struct hdac_hdmi_priv *hdmi = snd_soc_dai_get_drvdata(dai); + struct hdac_device *hdev = hdmi->hdev; struct hdac_hdmi_dai_port_map *dai_map; struct hdac_hdmi_port *port; struct hdac_hdmi_pcm *pcm; @@ -469,7 +460,7 @@ static int hdac_hdmi_set_hw_params(struct snd_pcm_substream *substream, return -ENODEV; if ((!port->eld.monitor_present) || (!port->eld.eld_valid)) { - dev_err(&edev->hdev.dev, + dev_err(&hdev->dev, "device is not configured for this pin:port%d:%d\n", port->pin->nid, port->id); return -ENODEV; @@ -489,28 +480,28 @@ static int hdac_hdmi_set_hw_params(struct snd_pcm_substream *substream, return 0; } -static int hdac_hdmi_query_port_connlist(struct hdac_ext_device *edev, +static int hdac_hdmi_query_port_connlist(struct hdac_device *hdev, struct hdac_hdmi_pin *pin, struct hdac_hdmi_port *port) { - if (!(get_wcaps(&edev->hdev, pin->nid) & AC_WCAP_CONN_LIST)) { - dev_warn(&edev->hdev.dev, + if (!(get_wcaps(hdev, pin->nid) & AC_WCAP_CONN_LIST)) { + dev_warn(&hdev->dev, "HDMI: pin %d wcaps %#x does not support connection list\n", - pin->nid, get_wcaps(&edev->hdev, pin->nid)); + pin->nid, get_wcaps(hdev, pin->nid)); return -EINVAL; } - if (hdac_hdmi_port_select_set(edev, port) < 0) + if (hdac_hdmi_port_select_set(hdev, port) < 0) return -EIO; - port->num_mux_nids = snd_hdac_get_connections(&edev->hdev, pin->nid, + port->num_mux_nids = snd_hdac_get_connections(hdev, pin->nid, port->mux_nids, HDA_MAX_CONNECTIONS); if (port->num_mux_nids == 0) - dev_warn(&edev->hdev.dev, + dev_warn(&hdev->dev, "No connections found for pin:port %d:%d\n", pin->nid, port->id); - dev_dbg(&edev->hdev.dev, "num_mux_nids %d for pin:port %d:%d\n", + dev_dbg(&hdev->dev, "num_mux_nids %d for pin:port %d:%d\n", port->num_mux_nids, pin->nid, port->id); return port->num_mux_nids; @@ -526,7 +517,7 @@ static int hdac_hdmi_query_port_connlist(struct hdac_ext_device *edev, * connected. */ static struct hdac_hdmi_port *hdac_hdmi_get_port_from_cvt( - struct hdac_ext_device *edev, + struct hdac_device *hdev, struct hdac_hdmi_priv *hdmi, struct hdac_hdmi_cvt *cvt) { @@ -541,7 +532,7 @@ static struct hdac_hdmi_port *hdac_hdmi_get_port_from_cvt( list_for_each_entry(port, &pcm->port_list, head) { mutex_lock(&pcm->lock); - ret = hdac_hdmi_query_port_connlist(edev, + ret = hdac_hdmi_query_port_connlist(hdev, port->pin, port); mutex_unlock(&pcm->lock); if (ret < 0) @@ -568,8 +559,8 @@ static struct hdac_hdmi_port *hdac_hdmi_get_port_from_cvt( static int hdac_hdmi_pcm_open(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { - struct hdac_ext_device *edev = snd_soc_dai_get_drvdata(dai); - struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev); + struct hdac_hdmi_priv *hdmi = snd_soc_dai_get_drvdata(dai); + struct hdac_device *hdev = hdmi->hdev; struct hdac_hdmi_dai_port_map *dai_map; struct hdac_hdmi_cvt *cvt; struct hdac_hdmi_port *port; @@ -578,7 +569,7 @@ static int hdac_hdmi_pcm_open(struct snd_pcm_substream *substream, dai_map = &hdmi->dai_map[dai->id]; cvt = dai_map->cvt; - port = hdac_hdmi_get_port_from_cvt(edev, hdmi, cvt); + port = hdac_hdmi_get_port_from_cvt(hdev, hdmi, cvt); /* * To make PA and other userland happy. @@ -589,7 +580,7 @@ static int hdac_hdmi_pcm_open(struct snd_pcm_substream *substream, if ((!port->eld.monitor_present) || (!port->eld.eld_valid)) { - dev_warn(&edev->hdev.dev, + dev_warn(&hdev->dev, "Failed: present?:%d ELD valid?:%d pin:port: %d:%d\n", port->eld.monitor_present, port->eld.eld_valid, port->pin->nid, port->id); @@ -611,8 +602,7 @@ static int hdac_hdmi_pcm_open(struct snd_pcm_substream *substream, static void hdac_hdmi_pcm_close(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { - struct hdac_ext_device *edev = snd_soc_dai_get_drvdata(dai); - struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev); + struct hdac_hdmi_priv *hdmi = snd_soc_dai_get_drvdata(dai); struct hdac_hdmi_dai_port_map *dai_map; struct hdac_hdmi_pcm *pcm; @@ -695,10 +685,10 @@ static void hdac_hdmi_fill_route(struct snd_soc_dapm_route *route, route->connected = handler; } -static struct hdac_hdmi_pcm *hdac_hdmi_get_pcm(struct hdac_ext_device *edev, +static struct hdac_hdmi_pcm *hdac_hdmi_get_pcm(struct hdac_device *hdev, struct hdac_hdmi_port *port) { - struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev); + struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev); struct hdac_hdmi_pcm *pcm = NULL; struct hdac_hdmi_port *p; @@ -715,33 +705,32 @@ static struct hdac_hdmi_pcm *hdac_hdmi_get_pcm(struct hdac_ext_device *edev, return NULL; } -static void hdac_hdmi_set_power_state(struct hdac_ext_device *edev, +static void hdac_hdmi_set_power_state(struct hdac_device *hdev, hda_nid_t nid, unsigned int pwr_state) { int count; unsigned int state; - if (get_wcaps(&edev->hdev, nid) & AC_WCAP_POWER) { - if (!snd_hdac_check_power_state(&edev->hdev, nid, pwr_state)) { + if (get_wcaps(hdev, nid) & AC_WCAP_POWER) { + if (!snd_hdac_check_power_state(hdev, nid, pwr_state)) { for (count = 0; count < 10; count++) { - snd_hdac_codec_read(&edev->hdev, nid, 0, + snd_hdac_codec_read(hdev, nid, 0, AC_VERB_SET_POWER_STATE, pwr_state); - state = snd_hdac_sync_power_state(&edev->hdev, + state = snd_hdac_sync_power_state(hdev, nid, pwr_state); if (!(state & AC_PWRST_ERROR)) break; } } - } } -static void hdac_hdmi_set_amp(struct hdac_ext_device *edev, +static void hdac_hdmi_set_amp(struct hdac_device *hdev, hda_nid_t nid, int val) { - if (get_wcaps(&edev->hdev, nid) & AC_WCAP_OUT_AMP) - snd_hdac_codec_write(&edev->hdev, nid, 0, + if (get_wcaps(hdev, nid) & AC_WCAP_OUT_AMP) + snd_hdac_codec_write(hdev, nid, 0, AC_VERB_SET_AMP_GAIN_MUTE, val); } @@ -750,40 +739,40 @@ static int hdac_hdmi_pin_output_widget_event(struct snd_soc_dapm_widget *w, struct snd_kcontrol *kc, int event) { struct hdac_hdmi_port *port = w->priv; - struct hdac_ext_device *edev = to_hda_ext_device(w->dapm->dev); + struct hdac_device *hdev = dev_to_hdac_dev(w->dapm->dev); struct hdac_hdmi_pcm *pcm; - dev_dbg(&edev->hdev.dev, "%s: widget: %s event: %x\n", + dev_dbg(&hdev->dev, "%s: widget: %s event: %x\n", __func__, w->name, event); - pcm = hdac_hdmi_get_pcm(edev, port); + pcm = hdac_hdmi_get_pcm(hdev, port); if (!pcm) return -EIO; /* set the device if pin is mst_capable */ - if (hdac_hdmi_port_select_set(edev, port) < 0) + if (hdac_hdmi_port_select_set(hdev, port) < 0) return -EIO; switch (event) { case SND_SOC_DAPM_PRE_PMU: - hdac_hdmi_set_power_state(edev, port->pin->nid, AC_PWRST_D0); + hdac_hdmi_set_power_state(hdev, port->pin->nid, AC_PWRST_D0); /* Enable out path for this pin widget */ - snd_hdac_codec_write(&edev->hdev, port->pin->nid, 0, + snd_hdac_codec_write(hdev, port->pin->nid, 0, AC_VERB_SET_PIN_WIDGET_CONTROL, PIN_OUT); - hdac_hdmi_set_amp(edev, port->pin->nid, AMP_OUT_UNMUTE); + hdac_hdmi_set_amp(hdev, port->pin->nid, AMP_OUT_UNMUTE); - return hdac_hdmi_setup_audio_infoframe(edev, pcm, port); + return hdac_hdmi_setup_audio_infoframe(hdev, pcm, port); case SND_SOC_DAPM_POST_PMD: - hdac_hdmi_set_amp(edev, port->pin->nid, AMP_OUT_MUTE); + hdac_hdmi_set_amp(hdev, port->pin->nid, AMP_OUT_MUTE); /* Disable out path for this pin widget */ - snd_hdac_codec_write(&edev->hdev, port->pin->nid, 0, + snd_hdac_codec_write(hdev, port->pin->nid, 0, AC_VERB_SET_PIN_WIDGET_CONTROL, 0); - hdac_hdmi_set_power_state(edev, port->pin->nid, AC_PWRST_D3); + hdac_hdmi_set_power_state(hdev, port->pin->nid, AC_PWRST_D3); break; } @@ -795,11 +784,11 @@ static int hdac_hdmi_cvt_output_widget_event(struct snd_soc_dapm_widget *w, struct snd_kcontrol *kc, int event) { struct hdac_hdmi_cvt *cvt = w->priv; - struct hdac_ext_device *edev = to_hda_ext_device(w->dapm->dev); - struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev); + struct hdac_device *hdev = dev_to_hdac_dev(w->dapm->dev); + struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev); struct hdac_hdmi_pcm *pcm; - dev_dbg(&edev->hdev.dev, "%s: widget: %s event: %x\n", + dev_dbg(&hdev->dev, "%s: widget: %s event: %x\n", __func__, w->name, event); pcm = hdac_hdmi_get_pcm_from_cvt(hdmi, cvt); @@ -808,29 +797,29 @@ static int hdac_hdmi_cvt_output_widget_event(struct snd_soc_dapm_widget *w, switch (event) { case SND_SOC_DAPM_PRE_PMU: - hdac_hdmi_set_power_state(edev, cvt->nid, AC_PWRST_D0); + hdac_hdmi_set_power_state(hdev, cvt->nid, AC_PWRST_D0); /* Enable transmission */ - snd_hdac_codec_write(&edev->hdev, cvt->nid, 0, + snd_hdac_codec_write(hdev, cvt->nid, 0, AC_VERB_SET_DIGI_CONVERT_1, 1); /* Category Code (CC) to zero */ - snd_hdac_codec_write(&edev->hdev, cvt->nid, 0, + snd_hdac_codec_write(hdev, cvt->nid, 0, AC_VERB_SET_DIGI_CONVERT_2, 0); - snd_hdac_codec_write(&edev->hdev, cvt->nid, 0, + snd_hdac_codec_write(hdev, cvt->nid, 0, AC_VERB_SET_CHANNEL_STREAMID, pcm->stream_tag); - snd_hdac_codec_write(&edev->hdev, cvt->nid, 0, + snd_hdac_codec_write(hdev, cvt->nid, 0, AC_VERB_SET_STREAM_FORMAT, pcm->format); break; case SND_SOC_DAPM_POST_PMD: - snd_hdac_codec_write(&edev->hdev, cvt->nid, 0, + snd_hdac_codec_write(hdev, cvt->nid, 0, AC_VERB_SET_CHANNEL_STREAMID, 0); - snd_hdac_codec_write(&edev->hdev, cvt->nid, 0, + snd_hdac_codec_write(hdev, cvt->nid, 0, AC_VERB_SET_STREAM_FORMAT, 0); - hdac_hdmi_set_power_state(edev, cvt->nid, AC_PWRST_D3); + hdac_hdmi_set_power_state(hdev, cvt->nid, AC_PWRST_D3); break; } @@ -842,10 +831,10 @@ static int hdac_hdmi_pin_mux_widget_event(struct snd_soc_dapm_widget *w, struct snd_kcontrol *kc, int event) { struct hdac_hdmi_port *port = w->priv; - struct hdac_ext_device *edev = to_hda_ext_device(w->dapm->dev); + struct hdac_device *hdev = dev_to_hdac_dev(w->dapm->dev); int mux_idx; - dev_dbg(&edev->hdev.dev, "%s: widget: %s event: %x\n", + dev_dbg(&hdev->dev, "%s: widget: %s event: %x\n", __func__, w->name, event); if (!kc) @@ -854,11 +843,11 @@ static int hdac_hdmi_pin_mux_widget_event(struct snd_soc_dapm_widget *w, mux_idx = dapm_kcontrol_get_value(kc); /* set the device if pin is mst_capable */ - if (hdac_hdmi_port_select_set(edev, port) < 0) + if (hdac_hdmi_port_select_set(hdev, port) < 0) return -EIO; if (mux_idx > 0) { - snd_hdac_codec_write(&edev->hdev, port->pin->nid, 0, + snd_hdac_codec_write(hdev, port->pin->nid, 0, AC_VERB_SET_CONNECT_SEL, (mux_idx - 1)); } @@ -877,8 +866,8 @@ static int hdac_hdmi_set_pin_port_mux(struct snd_kcontrol *kcontrol, struct snd_soc_dapm_widget *w = snd_soc_dapm_kcontrol_widget(kcontrol); struct snd_soc_dapm_context *dapm = w->dapm; struct hdac_hdmi_port *port = w->priv; - struct hdac_ext_device *edev = to_hda_ext_device(dapm->dev); - struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev); + struct hdac_device *hdev = dev_to_hdac_dev(dapm->dev); + struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev); struct hdac_hdmi_pcm *pcm = NULL; const char *cvt_name = e->texts[ucontrol->value.enumerated.item[0]]; @@ -931,12 +920,12 @@ static int hdac_hdmi_set_pin_port_mux(struct snd_kcontrol *kcontrol, * care of selecting the right one and leaving all other inputs selected to * "NONE" */ -static int hdac_hdmi_create_pin_port_muxs(struct hdac_ext_device *edev, +static int hdac_hdmi_create_pin_port_muxs(struct hdac_device *hdev, struct hdac_hdmi_port *port, struct snd_soc_dapm_widget *widget, const char *widget_name) { - struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev); + struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev); struct hdac_hdmi_pin *pin = port->pin; struct snd_kcontrol_new *kc; struct hdac_hdmi_cvt *cvt; @@ -948,17 +937,17 @@ static int hdac_hdmi_create_pin_port_muxs(struct hdac_ext_device *edev, int i = 0; int num_items = hdmi->num_cvt + 1; - kc = devm_kzalloc(&edev->hdev.dev, sizeof(*kc), GFP_KERNEL); + kc = devm_kzalloc(&hdev->dev, sizeof(*kc), GFP_KERNEL); if (!kc) return -ENOMEM; - se = devm_kzalloc(&edev->hdev.dev, sizeof(*se), GFP_KERNEL); + se = devm_kzalloc(&hdev->dev, sizeof(*se), GFP_KERNEL); if (!se) return -ENOMEM; snprintf(kc_name, NAME_SIZE, "Pin %d port %d Input", pin->nid, port->id); - kc->name = devm_kstrdup(&edev->hdev.dev, kc_name, GFP_KERNEL); + kc->name = devm_kstrdup(&hdev->dev, kc_name, GFP_KERNEL); if (!kc->name) return -ENOMEM; @@ -976,35 +965,35 @@ static int hdac_hdmi_create_pin_port_muxs(struct hdac_ext_device *edev, se->mask = roundup_pow_of_two(se->items) - 1; sprintf(mux_items, "NONE"); - items[i] = devm_kstrdup(&edev->hdev.dev, mux_items, GFP_KERNEL); + items[i] = devm_kstrdup(&hdev->dev, mux_items, GFP_KERNEL); if (!items[i]) return -ENOMEM; list_for_each_entry(cvt, &hdmi->cvt_list, head) { i++; sprintf(mux_items, "cvt %d", cvt->nid); - items[i] = devm_kstrdup(&edev->hdev.dev, mux_items, GFP_KERNEL); + items[i] = devm_kstrdup(&hdev->dev, mux_items, GFP_KERNEL); if (!items[i]) return -ENOMEM; } - se->texts = devm_kmemdup(&edev->hdev.dev, items, + se->texts = devm_kmemdup(&hdev->dev, items, (num_items * sizeof(char *)), GFP_KERNEL); if (!se->texts) return -ENOMEM; - return hdac_hdmi_fill_widget_info(&edev->hdev.dev, widget, + return hdac_hdmi_fill_widget_info(&hdev->dev, widget, snd_soc_dapm_mux, port, widget_name, NULL, kc, 1, hdac_hdmi_pin_mux_widget_event, SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_REG); } /* Add cvt <- input <- mux route map */ -static void hdac_hdmi_add_pinmux_cvt_route(struct hdac_ext_device *edev, +static void hdac_hdmi_add_pinmux_cvt_route(struct hdac_device *hdev, struct snd_soc_dapm_widget *widgets, struct snd_soc_dapm_route *route, int rindex) { - struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev); + struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev); const struct snd_kcontrol_new *kc; struct soc_enum *se; int mux_index = hdmi->num_cvt + hdmi->num_ports; @@ -1046,8 +1035,8 @@ static int create_fill_widget_route_map(struct snd_soc_dapm_context *dapm) { struct snd_soc_dapm_widget *widgets; struct snd_soc_dapm_route *route; - struct hdac_ext_device *edev = to_hda_ext_device(dapm->dev); - struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev); + struct hdac_device *hdev = dev_to_hdac_dev(dapm->dev); + struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev); struct snd_soc_dai_driver *dai_drv = hdmi->dai_drv; char widget_name[NAME_SIZE]; struct hdac_hdmi_cvt *cvt; @@ -1099,7 +1088,7 @@ static int create_fill_widget_route_map(struct snd_soc_dapm_context *dapm) for (j = 0; j < pin->num_ports; j++) { sprintf(widget_name, "Pin%d-Port%d Mux", pin->nid, pin->ports[j].id); - ret = hdac_hdmi_create_pin_port_muxs(edev, + ret = hdac_hdmi_create_pin_port_muxs(hdev, &pin->ports[j], &widgets[i], widget_name); if (ret < 0) @@ -1134,7 +1123,7 @@ static int create_fill_widget_route_map(struct snd_soc_dapm_context *dapm) } } - hdac_hdmi_add_pinmux_cvt_route(edev, widgets, route, i); + hdac_hdmi_add_pinmux_cvt_route(hdev, widgets, route, i); snd_soc_dapm_new_controls(dapm, widgets, ((2 * hdmi->num_ports) + hdmi->num_cvt)); @@ -1146,9 +1135,9 @@ static int create_fill_widget_route_map(struct snd_soc_dapm_context *dapm) } -static int hdac_hdmi_init_dai_map(struct hdac_ext_device *edev) +static int hdac_hdmi_init_dai_map(struct hdac_device *hdev) { - struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev); + struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev); struct hdac_hdmi_dai_port_map *dai_map; struct hdac_hdmi_cvt *cvt; int dai_id = 0; @@ -1164,7 +1153,7 @@ static int hdac_hdmi_init_dai_map(struct hdac_ext_device *edev) dai_id++; if (dai_id == HDA_MAX_CVTS) { - dev_warn(&edev->hdev.dev, + dev_warn(&hdev->dev, "Max dais supported: %d\n", dai_id); break; } @@ -1173,9 +1162,9 @@ static int hdac_hdmi_init_dai_map(struct hdac_ext_device *edev) return 0; } -static int hdac_hdmi_add_cvt(struct hdac_ext_device *edev, hda_nid_t nid) +static int hdac_hdmi_add_cvt(struct hdac_device *hdev, hda_nid_t nid) { - struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev); + struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev); struct hdac_hdmi_cvt *cvt; char name[NAME_SIZE]; @@ -1190,10 +1179,10 @@ static int hdac_hdmi_add_cvt(struct hdac_ext_device *edev, hda_nid_t nid) list_add_tail(&cvt->head, &hdmi->cvt_list); hdmi->num_cvt++; - return hdac_hdmi_query_cvt_params(&edev->hdev, cvt); + return hdac_hdmi_query_cvt_params(hdev, cvt); } -static int hdac_hdmi_parse_eld(struct hdac_ext_device *edev, +static int hdac_hdmi_parse_eld(struct hdac_device *hdev, struct hdac_hdmi_port *port) { unsigned int ver, mnl; @@ -1202,7 +1191,7 @@ static int hdac_hdmi_parse_eld(struct hdac_ext_device *edev, >> DRM_ELD_VER_SHIFT; if (ver != ELD_VER_CEA_861D && ver != ELD_VER_PARTIAL) { - dev_err(&edev->hdev.dev, "HDMI: Unknown ELD version %d\n", ver); + dev_err(&hdev->dev, "HDMI: Unknown ELD version %d\n", ver); return -EINVAL; } @@ -1210,7 +1199,7 @@ static int hdac_hdmi_parse_eld(struct hdac_ext_device *edev, DRM_ELD_MNL_MASK) >> DRM_ELD_MNL_SHIFT; if (mnl > ELD_MAX_MNL) { - dev_err(&edev->hdev.dev, "HDMI: MNL Invalid %d\n", mnl); + dev_err(&hdev->dev, "HDMI: MNL Invalid %d\n", mnl); return -EINVAL; } @@ -1222,8 +1211,8 @@ static int hdac_hdmi_parse_eld(struct hdac_ext_device *edev, static void hdac_hdmi_present_sense(struct hdac_hdmi_pin *pin, struct hdac_hdmi_port *port) { - struct hdac_ext_device *edev = pin->edev; - struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev); + struct hdac_device *hdev = pin->hdev; + struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev); struct hdac_hdmi_pcm *pcm; int size = 0; int port_id = -1; @@ -1241,14 +1230,14 @@ static void hdac_hdmi_present_sense(struct hdac_hdmi_pin *pin, if (pin->mst_capable) port_id = port->id; - size = snd_hdac_acomp_get_eld(&edev->hdev, pin->nid, port_id, + size = snd_hdac_acomp_get_eld(hdev, pin->nid, port_id, &port->eld.monitor_present, port->eld.eld_buffer, ELD_MAX_SIZE); if (size > 0) { size = min(size, ELD_MAX_SIZE); - if (hdac_hdmi_parse_eld(edev, port) < 0) + if (hdac_hdmi_parse_eld(hdev, port) < 0) size = -EINVAL; } @@ -1260,11 +1249,11 @@ static void hdac_hdmi_present_sense(struct hdac_hdmi_pin *pin, port->eld.eld_size = 0; } - pcm = hdac_hdmi_get_pcm(edev, port); + pcm = hdac_hdmi_get_pcm(hdev, port); if (!port->eld.monitor_present || !port->eld.eld_valid) { - dev_err(&edev->hdev.dev, "%s: disconnect for pin:port %d:%d\n", + dev_err(&hdev->dev, "%s: disconnect for pin:port %d:%d\n", __func__, pin->nid, port->id); /* @@ -1316,9 +1305,9 @@ static int hdac_hdmi_add_ports(struct hdac_hdmi_priv *hdmi, return 0; } -static int hdac_hdmi_add_pin(struct hdac_ext_device *edev, hda_nid_t nid) +static int hdac_hdmi_add_pin(struct hdac_device *hdev, hda_nid_t nid) { - struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev); + struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev); struct hdac_hdmi_pin *pin; int ret; @@ -1328,7 +1317,7 @@ static int hdac_hdmi_add_pin(struct hdac_ext_device *edev, hda_nid_t nid) pin->nid = nid; pin->mst_capable = false; - pin->edev = edev; + pin->hdev = hdev; ret = hdac_hdmi_add_ports(hdmi, pin); if (ret < 0) return ret; @@ -1459,15 +1448,14 @@ static int hdac_hdmi_create_dais(struct hdac_device *hdev, * Parse all nodes and store the cvt/pin nids in array * Add one time initialization for pin and cvt widgets */ -static int hdac_hdmi_parse_and_map_nid(struct hdac_ext_device *edev, +static int hdac_hdmi_parse_and_map_nid(struct hdac_device *hdev, struct snd_soc_dai_driver **dais, int *num_dais) { hda_nid_t nid; int i, num_nodes; struct hdac_hdmi_cvt *temp_cvt, *cvt_next; struct hdac_hdmi_pin *temp_pin, *pin_next; - struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev); - struct hdac_device *hdev = &edev->hdev; + struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev); int ret; hdac_hdmi_skl_enable_all_pins(hdev); @@ -1492,13 +1480,13 @@ static int hdac_hdmi_parse_and_map_nid(struct hdac_ext_device *edev, switch (type) { case AC_WID_AUD_OUT: - ret = hdac_hdmi_add_cvt(edev, nid); + ret = hdac_hdmi_add_cvt(hdev, nid); if (ret < 0) goto free_widgets; break; case AC_WID_PIN: - ret = hdac_hdmi_add_pin(edev, nid); + ret = hdac_hdmi_add_pin(hdev, nid); if (ret < 0) goto free_widgets; break; @@ -1518,7 +1506,7 @@ static int hdac_hdmi_parse_and_map_nid(struct hdac_ext_device *edev, } *num_dais = hdmi->num_cvt; - ret = hdac_hdmi_init_dai_map(edev); + ret = hdac_hdmi_init_dai_map(hdev); if (ret < 0) goto free_widgets; @@ -1544,17 +1532,17 @@ free_widgets: static void hdac_hdmi_eld_notify_cb(void *aptr, int port, int pipe) { - struct hdac_ext_device *edev = aptr; - struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev); + struct hdac_device *hdev = aptr; + struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev); struct hdac_hdmi_pin *pin = NULL; struct hdac_hdmi_port *hport = NULL; - struct snd_soc_component *component = edev->scodec; + struct snd_soc_component *component = hdmi->component; int i; /* Don't know how this mapping is derived */ hda_nid_t pin_nid = port + 0x04; - dev_dbg(&edev->hdev.dev, "%s: for pin:%d port=%d\n", __func__, + dev_dbg(&hdev->dev, "%s: for pin:%d port=%d\n", __func__, pin_nid, pipe); /* @@ -1567,7 +1555,7 @@ static void hdac_hdmi_eld_notify_cb(void *aptr, int port, int pipe) SNDRV_CTL_POWER_D0) return; - if (atomic_read(&edev->hdev.in_pm)) + if (atomic_read(&hdev->in_pm)) return; list_for_each_entry(pin, &hdmi->pin_list, head) { @@ -1614,15 +1602,15 @@ static struct snd_pcm *hdac_hdmi_get_pcm_from_id(struct snd_soc_card *card, /* create jack pin kcontrols */ static int create_fill_jack_kcontrols(struct snd_soc_card *card, - struct hdac_ext_device *edev) + struct hdac_device *hdev) { struct hdac_hdmi_pin *pin; struct snd_kcontrol_new *kc; char kc_name[NAME_SIZE], xname[NAME_SIZE]; char *name; int i = 0, j; - struct snd_soc_component *component = edev->scodec; - struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev); + struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev); + struct snd_soc_component *component = hdmi->component; kc = devm_kcalloc(component->dev, hdmi->num_ports, sizeof(*kc), GFP_KERNEL); @@ -1659,8 +1647,8 @@ static int create_fill_jack_kcontrols(struct snd_soc_card *card, int hdac_hdmi_jack_port_init(struct snd_soc_component *component, struct snd_soc_dapm_context *dapm) { - struct hdac_ext_device *edev = snd_soc_component_get_drvdata(component); - struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev); + struct hdac_hdmi_priv *hdmi = snd_soc_component_get_drvdata(component); + struct hdac_device *hdev = hdmi->hdev; struct hdac_hdmi_pin *pin; struct snd_soc_dapm_widget *widgets; struct snd_soc_dapm_route *route; @@ -1715,7 +1703,7 @@ int hdac_hdmi_jack_port_init(struct snd_soc_component *component, return ret; /* Add Jack Pin switch Kcontrol */ - ret = create_fill_jack_kcontrols(dapm->card, edev); + ret = create_fill_jack_kcontrols(dapm->card, hdev); if (ret < 0) return ret; @@ -1735,8 +1723,8 @@ int hdac_hdmi_jack_init(struct snd_soc_dai *dai, int device, struct snd_soc_jack *jack) { struct snd_soc_component *component = dai->component; - struct hdac_ext_device *edev = snd_soc_component_get_drvdata(component); - struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev); + struct hdac_hdmi_priv *hdmi = snd_soc_component_get_drvdata(component); + struct hdac_device *hdev = hdmi->hdev; struct hdac_hdmi_pcm *pcm; struct snd_pcm *snd_pcm; int err; @@ -1758,7 +1746,7 @@ int hdac_hdmi_jack_init(struct snd_soc_dai *dai, int device, if (snd_pcm) { err = snd_hdac_add_chmap_ctls(snd_pcm, device, &hdmi->chmap); if (err < 0) { - dev_err(&edev->hdev.dev, + dev_err(&hdev->dev, "chmap control add failed with err: %d for pcm: %d\n", err, device); kfree(pcm); @@ -1772,7 +1760,7 @@ int hdac_hdmi_jack_init(struct snd_soc_dai *dai, int device, } EXPORT_SYMBOL_GPL(hdac_hdmi_jack_init); -static void hdac_hdmi_present_sense_all_pins(struct hdac_ext_device *edev, +static void hdac_hdmi_present_sense_all_pins(struct hdac_device *hdev, struct hdac_hdmi_priv *hdmi, bool detect_pin_caps) { int i; @@ -1781,7 +1769,7 @@ static void hdac_hdmi_present_sense_all_pins(struct hdac_ext_device *edev, list_for_each_entry(pin, &hdmi->pin_list, head) { if (detect_pin_caps) { - if (hdac_hdmi_get_port_len(edev, pin->nid) == 0) + if (hdac_hdmi_get_port_len(hdev, pin->nid) == 0) pin->mst_capable = false; else pin->mst_capable = true; @@ -1798,68 +1786,68 @@ static void hdac_hdmi_present_sense_all_pins(struct hdac_ext_device *edev, static int hdmi_codec_probe(struct snd_soc_component *component) { - struct hdac_ext_device *edev = snd_soc_component_get_drvdata(component); - struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev); + struct hdac_hdmi_priv *hdmi = snd_soc_component_get_drvdata(component); + struct hdac_device *hdev = hdmi->hdev; struct snd_soc_dapm_context *dapm = snd_soc_component_get_dapm(component); struct hdac_ext_link *hlink = NULL; int ret; - edev->scodec = component; + hdmi->component = component; /* * hold the ref while we probe, also no need to drop the ref on * exit, we call pm_runtime_suspend() so that will do for us */ - hlink = snd_hdac_ext_bus_get_link(edev->ebus, dev_name(&edev->hdev.dev)); + hlink = snd_hdac_ext_bus_get_link(hbus_to_ebus(hdev->bus), + dev_name(&hdev->dev)); if (!hlink) { - dev_err(&edev->hdev.dev, "hdac link not found\n"); + dev_err(&hdev->dev, "hdac link not found\n"); return -EIO; } - snd_hdac_ext_bus_link_get(edev->ebus, hlink); + snd_hdac_ext_bus_link_get(hbus_to_ebus(hdev->bus), hlink); ret = create_fill_widget_route_map(dapm); if (ret < 0) return ret; - aops.audio_ptr = edev; + aops.audio_ptr = hdev; ret = snd_hdac_i915_register_notifier(&aops); if (ret < 0) { - dev_err(&edev->hdev.dev, "notifier register failed: err: %d\n", - ret); + dev_err(&hdev->dev, "notifier register failed: err: %d\n", ret); return ret; } - hdac_hdmi_present_sense_all_pins(edev, hdmi, true); + hdac_hdmi_present_sense_all_pins(hdev, hdmi, true); /* Imp: Store the card pointer in hda_codec */ - edev->card = dapm->card->snd_card; + hdmi->card = dapm->card->snd_card; /* * hdac_device core already sets the state to active and calls * get_noresume. So enable runtime and set the device to suspend. */ - pm_runtime_enable(&edev->hdev.dev); - pm_runtime_put(&edev->hdev.dev); - pm_runtime_suspend(&edev->hdev.dev); + pm_runtime_enable(&hdev->dev); + pm_runtime_put(&hdev->dev); + pm_runtime_suspend(&hdev->dev); return 0; } static void hdmi_codec_remove(struct snd_soc_component *component) { - struct hdac_ext_device *edev = snd_soc_component_get_drvdata(component); + struct hdac_hdmi_priv *hdmi = snd_soc_component_get_drvdata(component); + struct hdac_device *hdev = hdmi->hdev; - pm_runtime_disable(&edev->hdev.dev); + pm_runtime_disable(&hdev->dev); } #ifdef CONFIG_PM static int hdmi_codec_prepare(struct device *dev) { - struct hdac_ext_device *edev = to_hda_ext_device(dev); - struct hdac_device *hdev = &edev->hdev; + struct hdac_device *hdev = dev_to_hdac_dev(dev); - pm_runtime_get_sync(&edev->hdev.dev); + pm_runtime_get_sync(&hdev->dev); /* * Power down afg. @@ -1876,16 +1864,15 @@ static int hdmi_codec_prepare(struct device *dev) static void hdmi_codec_complete(struct device *dev) { - struct hdac_ext_device *edev = to_hda_ext_device(dev); - struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev); - struct hdac_device *hdev = &edev->hdev; + struct hdac_device *hdev = dev_to_hdac_dev(dev); + struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev); /* Power up afg */ snd_hdac_codec_read(hdev, hdev->afg, 0, AC_VERB_SET_POWER_STATE, AC_PWRST_D0); - hdac_hdmi_skl_enable_all_pins(&edev->hdev); - hdac_hdmi_skl_enable_dp12(&edev->hdev); + hdac_hdmi_skl_enable_all_pins(hdev); + hdac_hdmi_skl_enable_dp12(hdev); /* * As the ELD notify callback request is not entertained while the @@ -1893,9 +1880,9 @@ static void hdmi_codec_complete(struct device *dev) * all pins here. pin capablity change is not support, so use the * already set pin caps. */ - hdac_hdmi_present_sense_all_pins(edev, hdmi, false); + hdac_hdmi_present_sense_all_pins(hdev, hdmi, false); - pm_runtime_put_sync(&edev->hdev.dev); + pm_runtime_put_sync(&hdev->dev); } #else #define hdmi_codec_prepare NULL @@ -1922,7 +1909,6 @@ static void hdac_hdmi_get_chmap(struct hdac_device *hdev, int pcm_idx, static void hdac_hdmi_set_chmap(struct hdac_device *hdev, int pcm_idx, unsigned char *chmap, int prepared) { - struct hdac_ext_device *edev = to_ehdac_device(hdev); struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev); struct hdac_hdmi_pcm *pcm = get_hdmi_pcm_from_id(hdmi, pcm_idx); struct hdac_hdmi_port *port; @@ -1938,7 +1924,7 @@ static void hdac_hdmi_set_chmap(struct hdac_device *hdev, int pcm_idx, memcpy(pcm->chmap, chmap, ARRAY_SIZE(pcm->chmap)); list_for_each_entry(port, &pcm->port_list, head) if (prepared) - hdac_hdmi_setup_audio_infoframe(edev, pcm, port); + hdac_hdmi_setup_audio_infoframe(hdev, pcm, port); mutex_unlock(&pcm->lock); } @@ -1987,10 +1973,9 @@ static struct hdac_hdmi_drv_data intel_drv_data = { .vendor_nid = INTEL_VENDOR_NID, }; -static int hdac_hdmi_dev_probe(struct hdac_ext_device *edev) +static int hdac_hdmi_dev_probe(struct hdac_device *hdev) { - struct hdac_device *hdev = &edev->hdev; - struct hdac_hdmi_priv *hdmi_priv; + struct hdac_hdmi_priv *hdmi_priv = NULL; struct snd_soc_dai_driver *hdmi_dais = NULL; struct hdac_ext_link *hlink = NULL; int num_dais = 0; @@ -1999,24 +1984,25 @@ static int hdac_hdmi_dev_probe(struct hdac_ext_device *edev) const struct hda_device_id *hdac_id = hdac_get_device_id(hdev, hdrv); /* hold the ref while we probe */ - hlink = snd_hdac_ext_bus_get_link(edev->ebus, dev_name(&edev->hdev.dev)); + hlink = snd_hdac_ext_bus_get_link(hbus_to_ebus(hdev->bus), + dev_name(&hdev->dev)); if (!hlink) { - dev_err(&edev->hdev.dev, "hdac link not found\n"); + dev_err(&hdev->dev, "hdac link not found\n"); return -EIO; } - snd_hdac_ext_bus_link_get(edev->ebus, hlink); + snd_hdac_ext_bus_link_get(hbus_to_ebus(hdev->bus), hlink); hdmi_priv = devm_kzalloc(&hdev->dev, sizeof(*hdmi_priv), GFP_KERNEL); if (hdmi_priv == NULL) return -ENOMEM; - edev->private_data = hdmi_priv; snd_hdac_register_chmap_ops(hdev, &hdmi_priv->chmap); hdmi_priv->chmap.ops.get_chmap = hdac_hdmi_get_chmap; hdmi_priv->chmap.ops.set_chmap = hdac_hdmi_set_chmap; hdmi_priv->chmap.ops.is_pcm_attached = is_hdac_hdmi_pcm_attached; hdmi_priv->chmap.ops.get_spk_alloc = hdac_hdmi_get_spk_alloc; + hdmi_priv->hdev = hdev; if (!hdac_id) return -ENODEV; @@ -2027,7 +2013,7 @@ static int hdac_hdmi_dev_probe(struct hdac_ext_device *edev) else hdmi_priv->drv_data = &intel_drv_data; - dev_set_drvdata(&hdev->dev, edev); + dev_set_drvdata(&hdev->dev, hdmi_priv); INIT_LIST_HEAD(&hdmi_priv->pin_list); INIT_LIST_HEAD(&hdmi_priv->cvt_list); @@ -2038,15 +2024,15 @@ static int hdac_hdmi_dev_probe(struct hdac_ext_device *edev) * Turned off in the runtime_suspend during the first explicit * pm_runtime_suspend call. */ - ret = snd_hdac_display_power(edev->hdev.bus, true); + ret = snd_hdac_display_power(hdev->bus, true); if (ret < 0) { - dev_err(&edev->hdev.dev, + dev_err(&hdev->dev, "Cannot turn on display power on i915 err: %d\n", ret); return ret; } - ret = hdac_hdmi_parse_and_map_nid(edev, &hdmi_dais, &num_dais); + ret = hdac_hdmi_parse_and_map_nid(hdev, &hdmi_dais, &num_dais); if (ret < 0) { dev_err(&hdev->dev, "Failed in parse and map nid with err: %d\n", ret); @@ -2058,14 +2044,14 @@ static int hdac_hdmi_dev_probe(struct hdac_ext_device *edev) ret = devm_snd_soc_register_component(&hdev->dev, &hdmi_hda_codec, hdmi_dais, num_dais); - snd_hdac_ext_bus_link_put(edev->ebus, hlink); + snd_hdac_ext_bus_link_put(hbus_to_ebus(hdev->bus), hlink); return ret; } -static int hdac_hdmi_dev_remove(struct hdac_ext_device *edev) +static int hdac_hdmi_dev_remove(struct hdac_device *hdev) { - struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev); + struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev); struct hdac_hdmi_pin *pin, *pin_next; struct hdac_hdmi_cvt *cvt, *cvt_next; struct hdac_hdmi_pcm *pcm, *pcm_next; @@ -2105,8 +2091,7 @@ static int hdac_hdmi_dev_remove(struct hdac_ext_device *edev) #ifdef CONFIG_PM static int hdac_hdmi_runtime_suspend(struct device *dev) { - struct hdac_ext_device *edev = to_hda_ext_device(dev); - struct hdac_device *hdev = &edev->hdev; + struct hdac_device *hdev = dev_to_hdac_dev(dev); struct hdac_bus *bus = hdev->bus; struct hdac_ext_bus *ebus = hbus_to_ebus(bus); struct hdac_ext_link *hlink = NULL; @@ -2129,7 +2114,7 @@ static int hdac_hdmi_runtime_suspend(struct device *dev) AC_PWRST_D3); err = snd_hdac_display_power(bus, false); if (err < 0) { - dev_err(bus->dev, "Cannot turn on display power on i915\n"); + dev_err(dev, "Cannot turn on display power on i915\n"); return err; } @@ -2146,8 +2131,7 @@ static int hdac_hdmi_runtime_suspend(struct device *dev) static int hdac_hdmi_runtime_resume(struct device *dev) { - struct hdac_ext_device *edev = to_hda_ext_device(dev); - struct hdac_device *hdev = &edev->hdev; + struct hdac_device *hdev = dev_to_hdac_dev(dev); struct hdac_bus *bus = hdev->bus; struct hdac_ext_bus *ebus = hbus_to_ebus(bus); struct hdac_ext_link *hlink = NULL; @@ -2169,12 +2153,12 @@ static int hdac_hdmi_runtime_resume(struct device *dev) err = snd_hdac_display_power(bus, true); if (err < 0) { - dev_err(bus->dev, "Cannot turn on display power on i915\n"); + dev_err(dev, "Cannot turn on display power on i915\n"); return err; } - hdac_hdmi_skl_enable_all_pins(&edev->hdev); - hdac_hdmi_skl_enable_dp12(&edev->hdev); + hdac_hdmi_skl_enable_all_pins(hdev); + hdac_hdmi_skl_enable_dp12(hdev); /* Power up afg */ snd_hdac_codec_read(hdev, hdev->afg, 0, AC_VERB_SET_POWER_STATE, -- cgit v1.2.3 From 76f56fae1cf9040325a58d1375291baf71dfaf03 Mon Sep 17 00:00:00 2001 From: Rakesh Ughreja Date: Fri, 1 Jun 2018 22:53:50 -0500 Subject: ALSA: hdac: Remove usage of struct hdac_ext_bus and use hdac_bus instead This patch removes the hdac_ext_bus structure. The legacy and enhanced HDaudio capabilities can be handled in a backward-compatible way without separate definitions. Follow-up patches in this series handle the driver definition. Signed-off-by: Rakesh Ughreja Signed-off-by: Pierre-Louis Bossart Signed-off-by: Takashi Iwai --- include/sound/hdaudio.h | 15 +++ include/sound/hdaudio_ext.h | 74 +++++-------- sound/hda/ext/hdac_ext_bus.c | 27 +++-- sound/hda/ext/hdac_ext_controller.c | 55 +++++----- sound/hda/ext/hdac_ext_stream.c | 104 ++++++++----------- sound/soc/codecs/hdac_hdmi.c | 22 ++-- sound/soc/intel/skylake/skl-messages.c | 50 ++++----- sound/soc/intel/skylake/skl-nhlt.c | 8 +- sound/soc/intel/skylake/skl-pcm.c | 112 ++++++++++---------- sound/soc/intel/skylake/skl-topology.c | 20 ++-- sound/soc/intel/skylake/skl-topology.h | 6 +- sound/soc/intel/skylake/skl.c | 184 +++++++++++++++------------------ sound/soc/intel/skylake/skl.h | 7 +- 13 files changed, 308 insertions(+), 376 deletions(-) (limited to 'include') diff --git a/include/sound/hdaudio.h b/include/sound/hdaudio.h index c052afc27547..9735b51aef08 100644 --- a/include/sound/hdaudio.h +++ b/include/sound/hdaudio.h @@ -250,6 +250,11 @@ struct hdac_rb { * @mlcap: MultiLink capabilities pointer * @gtscap: gts capabilities pointer * @drsmcap: dma resume capabilities pointer + * @num_streams: streams supported + * @idx: HDA link index + * @hlink_list: link list of HDA links + * @lock: lock for link mgmt + * @cmd_dma_state: state of cmd DMAs: CORB and RIRB */ struct hdac_bus { struct device *dev; @@ -317,6 +322,16 @@ struct hdac_bus { /* i915 component interface */ struct i915_audio_component *audio_component; int i915_power_refcount; + + /* parameters required for enhanced capabilities */ + int num_streams; + int idx; + + struct list_head hlink_list; + + struct mutex lock; + bool cmd_dma_state; + }; int snd_hdac_bus_init(struct hdac_bus *bus, struct device *dev, diff --git a/include/sound/hdaudio_ext.h b/include/sound/hdaudio_ext.h index c1a5ad0e6e39..e5b0cd1ade19 100644 --- a/include/sound/hdaudio_ext.h +++ b/include/sound/hdaudio_ext.h @@ -4,38 +4,14 @@ #include -/** - * hdac_ext_bus: HDAC extended bus for extended HDA caps - * - * @bus: hdac bus - * @num_streams: streams supported - * @hlink_list: link list of HDA links - * @lock: lock for link mgmt - * @cmd_dma_state: state of cmd DMAs: CORB and RIRB - */ -struct hdac_ext_bus { - struct hdac_bus bus; - int num_streams; - int idx; - - struct list_head hlink_list; - - struct mutex lock; - bool cmd_dma_state; -}; - -int snd_hdac_ext_bus_init(struct hdac_ext_bus *sbus, struct device *dev, +int snd_hdac_ext_bus_init(struct hdac_bus *bus, struct device *dev, const struct hdac_bus_ops *ops, const struct hdac_io_ops *io_ops); -void snd_hdac_ext_bus_exit(struct hdac_ext_bus *sbus); -int snd_hdac_ext_bus_device_init(struct hdac_ext_bus *sbus, int addr); +void snd_hdac_ext_bus_exit(struct hdac_bus *bus); +int snd_hdac_ext_bus_device_init(struct hdac_bus *bus, int addr); void snd_hdac_ext_bus_device_exit(struct hdac_device *hdev); -void snd_hdac_ext_bus_device_remove(struct hdac_ext_bus *ebus); - -#define ebus_to_hbus(ebus) (&(ebus)->bus) -#define hbus_to_ebus(_bus) \ - container_of(_bus, struct hdac_ext_bus, bus) +void snd_hdac_ext_bus_device_remove(struct hdac_bus *bus); #define HDA_CODEC_REV_EXT_ENTRY(_vid, _rev, _name, drv_data) \ { .vendor_id = (_vid), .rev_id = (_rev), .name = (_name), \ @@ -44,14 +20,14 @@ void snd_hdac_ext_bus_device_remove(struct hdac_ext_bus *ebus); #define HDA_CODEC_EXT_ENTRY(_vid, _revid, _name, _drv_data) \ HDA_CODEC_REV_EXT_ENTRY(_vid, _revid, _name, _drv_data) -void snd_hdac_ext_bus_ppcap_enable(struct hdac_ext_bus *chip, bool enable); -void snd_hdac_ext_bus_ppcap_int_enable(struct hdac_ext_bus *chip, bool enable); +void snd_hdac_ext_bus_ppcap_enable(struct hdac_bus *chip, bool enable); +void snd_hdac_ext_bus_ppcap_int_enable(struct hdac_bus *chip, bool enable); -void snd_hdac_ext_stream_spbcap_enable(struct hdac_ext_bus *chip, +void snd_hdac_ext_stream_spbcap_enable(struct hdac_bus *chip, bool enable, int index); -int snd_hdac_ext_bus_get_ml_capabilities(struct hdac_ext_bus *bus); -struct hdac_ext_link *snd_hdac_ext_bus_get_link(struct hdac_ext_bus *bus, +int snd_hdac_ext_bus_get_ml_capabilities(struct hdac_bus *bus); +struct hdac_ext_link *snd_hdac_ext_bus_get_link(struct hdac_bus *bus, const char *codec_name); enum hdac_ext_stream_type { @@ -100,28 +76,28 @@ struct hdac_ext_stream { #define stream_to_hdac_ext_stream(s) \ container_of(s, struct hdac_ext_stream, hstream) -void snd_hdac_ext_stream_init(struct hdac_ext_bus *bus, +void snd_hdac_ext_stream_init(struct hdac_bus *bus, struct hdac_ext_stream *stream, int idx, int direction, int tag); -int snd_hdac_ext_stream_init_all(struct hdac_ext_bus *ebus, int start_idx, +int snd_hdac_ext_stream_init_all(struct hdac_bus *bus, int start_idx, int num_stream, int dir); -void snd_hdac_stream_free_all(struct hdac_ext_bus *ebus); -void snd_hdac_link_free_all(struct hdac_ext_bus *ebus); -struct hdac_ext_stream *snd_hdac_ext_stream_assign(struct hdac_ext_bus *bus, +void snd_hdac_stream_free_all(struct hdac_bus *bus); +void snd_hdac_link_free_all(struct hdac_bus *bus); +struct hdac_ext_stream *snd_hdac_ext_stream_assign(struct hdac_bus *bus, struct snd_pcm_substream *substream, int type); void snd_hdac_ext_stream_release(struct hdac_ext_stream *azx_dev, int type); -void snd_hdac_ext_stream_decouple(struct hdac_ext_bus *bus, +void snd_hdac_ext_stream_decouple(struct hdac_bus *bus, struct hdac_ext_stream *azx_dev, bool decouple); -void snd_hdac_ext_stop_streams(struct hdac_ext_bus *sbus); +void snd_hdac_ext_stop_streams(struct hdac_bus *bus); -int snd_hdac_ext_stream_set_spib(struct hdac_ext_bus *ebus, +int snd_hdac_ext_stream_set_spib(struct hdac_bus *bus, struct hdac_ext_stream *stream, u32 value); -int snd_hdac_ext_stream_get_spbmaxfifo(struct hdac_ext_bus *ebus, +int snd_hdac_ext_stream_get_spbmaxfifo(struct hdac_bus *bus, struct hdac_ext_stream *stream); -void snd_hdac_ext_stream_drsm_enable(struct hdac_ext_bus *ebus, +void snd_hdac_ext_stream_drsm_enable(struct hdac_bus *bus, bool enable, int index); -int snd_hdac_ext_stream_set_dpibr(struct hdac_ext_bus *ebus, +int snd_hdac_ext_stream_set_dpibr(struct hdac_bus *bus, struct hdac_ext_stream *stream, u32 value); int snd_hdac_ext_stream_set_lpib(struct hdac_ext_stream *stream, u32 value); @@ -144,17 +120,15 @@ struct hdac_ext_link { int snd_hdac_ext_bus_link_power_up(struct hdac_ext_link *link); int snd_hdac_ext_bus_link_power_down(struct hdac_ext_link *link); -int snd_hdac_ext_bus_link_power_up_all(struct hdac_ext_bus *ebus); -int snd_hdac_ext_bus_link_power_down_all(struct hdac_ext_bus *ebus); +int snd_hdac_ext_bus_link_power_up_all(struct hdac_bus *bus); +int snd_hdac_ext_bus_link_power_down_all(struct hdac_bus *bus); void snd_hdac_ext_link_set_stream_id(struct hdac_ext_link *link, int stream); void snd_hdac_ext_link_clear_stream_id(struct hdac_ext_link *link, int stream); -int snd_hdac_ext_bus_link_get(struct hdac_ext_bus *ebus, - struct hdac_ext_link *link); -int snd_hdac_ext_bus_link_put(struct hdac_ext_bus *ebus, - struct hdac_ext_link *link); +int snd_hdac_ext_bus_link_get(struct hdac_bus *bus, struct hdac_ext_link *link); +int snd_hdac_ext_bus_link_put(struct hdac_bus *bus, struct hdac_ext_link *link); /* update register macro */ #define snd_hdac_updatel(addr, reg, mask, val) \ diff --git a/sound/hda/ext/hdac_ext_bus.c b/sound/hda/ext/hdac_ext_bus.c index 0e4823fdd411..77547ede9ae8 100644 --- a/sound/hda/ext/hdac_ext_bus.c +++ b/sound/hda/ext/hdac_ext_bus.c @@ -87,7 +87,7 @@ static const struct hdac_io_ops hdac_ext_default_io = { * * Returns 0 if successful, or a negative error code. */ -int snd_hdac_ext_bus_init(struct hdac_ext_bus *ebus, struct device *dev, +int snd_hdac_ext_bus_init(struct hdac_bus *bus, struct device *dev, const struct hdac_bus_ops *ops, const struct hdac_io_ops *io_ops) { @@ -98,15 +98,15 @@ int snd_hdac_ext_bus_init(struct hdac_ext_bus *ebus, struct device *dev, if (io_ops == NULL) io_ops = &hdac_ext_default_io; - ret = snd_hdac_bus_init(&ebus->bus, dev, ops, io_ops); + ret = snd_hdac_bus_init(bus, dev, ops, io_ops); if (ret < 0) return ret; - INIT_LIST_HEAD(&ebus->hlink_list); - ebus->idx = idx++; + INIT_LIST_HEAD(&bus->hlink_list); + bus->idx = idx++; - mutex_init(&ebus->lock); - ebus->cmd_dma_state = true; + mutex_init(&bus->lock); + bus->cmd_dma_state = true; return 0; } @@ -116,10 +116,10 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_init); * snd_hdac_ext_bus_exit - clean up a HD-audio extended bus * @ebus: the pointer to extended bus object */ -void snd_hdac_ext_bus_exit(struct hdac_ext_bus *ebus) +void snd_hdac_ext_bus_exit(struct hdac_bus *bus) { - snd_hdac_bus_exit(&ebus->bus); - WARN_ON(!list_empty(&ebus->hlink_list)); + snd_hdac_bus_exit(bus); + WARN_ON(!list_empty(&bus->hlink_list)); } EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_exit); @@ -135,10 +135,9 @@ static void default_release(struct device *dev) * * Returns zero for success or a negative error code. */ -int snd_hdac_ext_bus_device_init(struct hdac_ext_bus *ebus, int addr) +int snd_hdac_ext_bus_device_init(struct hdac_bus *bus, int addr) { struct hdac_device *hdev = NULL; - struct hdac_bus *bus = ebus_to_hbus(ebus); char name[15]; int ret; @@ -148,7 +147,7 @@ int snd_hdac_ext_bus_device_init(struct hdac_ext_bus *ebus, int addr) hdev->bus = bus; - snprintf(name, sizeof(name), "ehdaudio%dD%d", ebus->idx, addr); + snprintf(name, sizeof(name), "ehdaudio%dD%d", bus->idx, addr); ret = snd_hdac_device_init(hdev, bus, name, addr); if (ret < 0) { @@ -185,14 +184,14 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_device_exit); * * @ebus: HD-audio extended bus */ -void snd_hdac_ext_bus_device_remove(struct hdac_ext_bus *ebus) +void snd_hdac_ext_bus_device_remove(struct hdac_bus *bus) { struct hdac_device *codec, *__codec; /* * we need to remove all the codec devices objects created in the * snd_hdac_ext_bus_device_init */ - list_for_each_entry_safe(codec, __codec, &ebus->bus.codec_list, list) { + list_for_each_entry_safe(codec, __codec, &bus->codec_list, list) { snd_hdac_device_unregister(codec); put_device(&codec->dev); } diff --git a/sound/hda/ext/hdac_ext_controller.c b/sound/hda/ext/hdac_ext_controller.c index 84f3b8168716..72774119dd11 100644 --- a/sound/hda/ext/hdac_ext_controller.c +++ b/sound/hda/ext/hdac_ext_controller.c @@ -39,9 +39,8 @@ * @ebus: HD-audio extended core bus * @enable: flag to turn on/off the capability */ -void snd_hdac_ext_bus_ppcap_enable(struct hdac_ext_bus *ebus, bool enable) +void snd_hdac_ext_bus_ppcap_enable(struct hdac_bus *bus, bool enable) { - struct hdac_bus *bus = &ebus->bus; if (!bus->ppcap) { dev_err(bus->dev, "Address of PP capability is NULL"); @@ -60,9 +59,8 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_ppcap_enable); * @ebus: HD-audio extended core bus * @enable: flag to enable/disable interrupt */ -void snd_hdac_ext_bus_ppcap_int_enable(struct hdac_ext_bus *ebus, bool enable) +void snd_hdac_ext_bus_ppcap_int_enable(struct hdac_bus *bus, bool enable) { - struct hdac_bus *bus = &ebus->bus; if (!bus->ppcap) { dev_err(bus->dev, "Address of PP capability is NULL\n"); @@ -89,12 +87,11 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_ppcap_int_enable); * in hlink_list of extended hdac bus * Note: this will be freed on bus exit by driver */ -int snd_hdac_ext_bus_get_ml_capabilities(struct hdac_ext_bus *ebus) +int snd_hdac_ext_bus_get_ml_capabilities(struct hdac_bus *bus) { int idx; u32 link_count; struct hdac_ext_link *hlink; - struct hdac_bus *bus = &ebus->bus; link_count = readl(bus->mlcap + AZX_REG_ML_MLCD) + 1; @@ -114,7 +111,7 @@ int snd_hdac_ext_bus_get_ml_capabilities(struct hdac_ext_bus *ebus) /* since link in On, update the ref */ hlink->ref_count = 1; - list_add_tail(&hlink->list, &ebus->hlink_list); + list_add_tail(&hlink->list, &bus->hlink_list); } return 0; @@ -127,12 +124,12 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_get_ml_capabilities); * @ebus: HD-audio ext core bus */ -void snd_hdac_link_free_all(struct hdac_ext_bus *ebus) +void snd_hdac_link_free_all(struct hdac_bus *bus) { struct hdac_ext_link *l; - while (!list_empty(&ebus->hlink_list)) { - l = list_first_entry(&ebus->hlink_list, struct hdac_ext_link, list); + while (!list_empty(&bus->hlink_list)) { + l = list_first_entry(&bus->hlink_list, struct hdac_ext_link, list); list_del(&l->list); kfree(l); } @@ -144,7 +141,7 @@ EXPORT_SYMBOL_GPL(snd_hdac_link_free_all); * @ebus: HD-audio extended core bus * @codec_name: codec name */ -struct hdac_ext_link *snd_hdac_ext_bus_get_link(struct hdac_ext_bus *ebus, +struct hdac_ext_link *snd_hdac_ext_bus_get_link(struct hdac_bus *bus, const char *codec_name) { int i; @@ -153,10 +150,10 @@ struct hdac_ext_link *snd_hdac_ext_bus_get_link(struct hdac_ext_bus *ebus, if (sscanf(codec_name, "ehdaudio%dD%d", &bus_idx, &addr) != 2) return NULL; - if (ebus->idx != bus_idx) + if (bus->idx != bus_idx) return NULL; - list_for_each_entry(hlink, &ebus->hlink_list, list) { + list_for_each_entry(hlink, &bus->hlink_list, list) { for (i = 0; i < HDA_MAX_CODECS; i++) { if (hlink->lsdiid & (0x1 << addr)) return hlink; @@ -219,12 +216,12 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_link_power_down); * snd_hdac_ext_bus_link_power_up_all -power up all hda link * @ebus: HD-audio extended bus */ -int snd_hdac_ext_bus_link_power_up_all(struct hdac_ext_bus *ebus) +int snd_hdac_ext_bus_link_power_up_all(struct hdac_bus *bus) { struct hdac_ext_link *hlink = NULL; int ret; - list_for_each_entry(hlink, &ebus->hlink_list, list) { + list_for_each_entry(hlink, &bus->hlink_list, list) { snd_hdac_updatel(hlink->ml_addr, AZX_REG_ML_LCTL, 0, AZX_MLCTL_SPA); ret = check_hdac_link_power_active(hlink, true); @@ -240,12 +237,12 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_link_power_up_all); * snd_hdac_ext_bus_link_power_down_all -power down all hda link * @ebus: HD-audio extended bus */ -int snd_hdac_ext_bus_link_power_down_all(struct hdac_ext_bus *ebus) +int snd_hdac_ext_bus_link_power_down_all(struct hdac_bus *bus) { struct hdac_ext_link *hlink = NULL; int ret; - list_for_each_entry(hlink, &ebus->hlink_list, list) { + list_for_each_entry(hlink, &bus->hlink_list, list) { snd_hdac_updatel(hlink->ml_addr, AZX_REG_ML_LCTL, AZX_MLCTL_SPA, 0); ret = check_hdac_link_power_active(hlink, false); if (ret < 0) @@ -256,39 +253,39 @@ int snd_hdac_ext_bus_link_power_down_all(struct hdac_ext_bus *ebus) } EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_link_power_down_all); -int snd_hdac_ext_bus_link_get(struct hdac_ext_bus *ebus, +int snd_hdac_ext_bus_link_get(struct hdac_bus *bus, struct hdac_ext_link *link) { int ret = 0; - mutex_lock(&ebus->lock); + mutex_lock(&bus->lock); /* * if we move from 0 to 1, count will be 1 so power up this link * as well, also check the dma status and trigger that */ if (++link->ref_count == 1) { - if (!ebus->cmd_dma_state) { - snd_hdac_bus_init_cmd_io(&ebus->bus); - ebus->cmd_dma_state = true; + if (!bus->cmd_dma_state) { + snd_hdac_bus_init_cmd_io(bus); + bus->cmd_dma_state = true; } ret = snd_hdac_ext_bus_link_power_up(link); } - mutex_unlock(&ebus->lock); + mutex_unlock(&bus->lock); return ret; } EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_link_get); -int snd_hdac_ext_bus_link_put(struct hdac_ext_bus *ebus, +int snd_hdac_ext_bus_link_put(struct hdac_bus *bus, struct hdac_ext_link *link) { int ret = 0; struct hdac_ext_link *hlink; bool link_up = false; - mutex_lock(&ebus->lock); + mutex_lock(&bus->lock); /* * if we move from 1 to 0, count will be 0 @@ -301,7 +298,7 @@ int snd_hdac_ext_bus_link_put(struct hdac_ext_bus *ebus, * now check if all links are off, if so turn off * cmd dma as well */ - list_for_each_entry(hlink, &ebus->hlink_list, list) { + list_for_each_entry(hlink, &bus->hlink_list, list) { if (hlink->ref_count) { link_up = true; break; @@ -309,12 +306,12 @@ int snd_hdac_ext_bus_link_put(struct hdac_ext_bus *ebus, } if (!link_up) { - snd_hdac_bus_stop_cmd_io(&ebus->bus); - ebus->cmd_dma_state = false; + snd_hdac_bus_stop_cmd_io(bus); + bus->cmd_dma_state = false; } } - mutex_unlock(&ebus->lock); + mutex_unlock(&bus->lock); return ret; } EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_link_put); diff --git a/sound/hda/ext/hdac_ext_stream.c b/sound/hda/ext/hdac_ext_stream.c index c96d7a7a36af..1bd27576db98 100644 --- a/sound/hda/ext/hdac_ext_stream.c +++ b/sound/hda/ext/hdac_ext_stream.c @@ -25,7 +25,7 @@ /** * snd_hdac_ext_stream_init - initialize each stream (aka device) - * @ebus: HD-audio ext core bus + * @bus: HD-audio core bus * @stream: HD-audio ext core stream object to initialize * @idx: stream index number * @direction: stream direction (SNDRV_PCM_STREAM_PLAYBACK or SNDRV_PCM_STREAM_CAPTURE) @@ -34,18 +34,16 @@ * initialize the stream, if ppcap is enabled then init those and then * invoke hdac stream initialization routine */ -void snd_hdac_ext_stream_init(struct hdac_ext_bus *ebus, +void snd_hdac_ext_stream_init(struct hdac_bus *bus, struct hdac_ext_stream *stream, int idx, int direction, int tag) { - struct hdac_bus *bus = &ebus->bus; - if (bus->ppcap) { stream->pphc_addr = bus->ppcap + AZX_PPHC_BASE + AZX_PPHC_INTERVAL * idx; stream->pplc_addr = bus->ppcap + AZX_PPLC_BASE + - AZX_PPLC_MULTI * ebus->num_streams + + AZX_PPLC_MULTI * bus->num_streams + AZX_PPLC_INTERVAL * idx; } @@ -71,12 +69,12 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_stream_init); /** * snd_hdac_ext_stream_init_all - create and initialize the stream objects * for an extended hda bus - * @ebus: HD-audio ext core bus + * @bus: HD-audio core bus * @start_idx: start index for streams * @num_stream: number of streams to initialize * @dir: direction of streams */ -int snd_hdac_ext_stream_init_all(struct hdac_ext_bus *ebus, int start_idx, +int snd_hdac_ext_stream_init_all(struct hdac_bus *bus, int start_idx, int num_stream, int dir) { int stream_tag = 0; @@ -88,7 +86,7 @@ int snd_hdac_ext_stream_init_all(struct hdac_ext_bus *ebus, int start_idx, if (!stream) return -ENOMEM; tag = ++stream_tag; - snd_hdac_ext_stream_init(ebus, stream, idx, dir, tag); + snd_hdac_ext_stream_init(bus, stream, idx, dir, tag); idx++; } @@ -100,17 +98,16 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_stream_init_all); /** * snd_hdac_stream_free_all - free hdac extended stream objects * - * @ebus: HD-audio ext core bus + * @bus: HD-audio core bus */ -void snd_hdac_stream_free_all(struct hdac_ext_bus *ebus) +void snd_hdac_stream_free_all(struct hdac_bus *bus) { struct hdac_stream *s, *_s; struct hdac_ext_stream *stream; - struct hdac_bus *bus = ebus_to_hbus(ebus); list_for_each_entry_safe(s, _s, &bus->stream_list, list) { stream = stream_to_hdac_ext_stream(s); - snd_hdac_ext_stream_decouple(ebus, stream, false); + snd_hdac_ext_stream_decouple(bus, stream, false); list_del(&s->list); kfree(stream); } @@ -119,15 +116,14 @@ EXPORT_SYMBOL_GPL(snd_hdac_stream_free_all); /** * snd_hdac_ext_stream_decouple - decouple the hdac stream - * @ebus: HD-audio ext core bus + * @bus: HD-audio core bus * @stream: HD-audio ext core stream object to initialize * @decouple: flag to decouple */ -void snd_hdac_ext_stream_decouple(struct hdac_ext_bus *ebus, +void snd_hdac_ext_stream_decouple(struct hdac_bus *bus, struct hdac_ext_stream *stream, bool decouple) { struct hdac_stream *hstream = &stream->hstream; - struct hdac_bus *bus = &ebus->bus; u32 val; int mask = AZX_PPCTL_PROCEN(hstream->index); @@ -251,19 +247,18 @@ void snd_hdac_ext_link_clear_stream_id(struct hdac_ext_link *link, EXPORT_SYMBOL_GPL(snd_hdac_ext_link_clear_stream_id); static struct hdac_ext_stream * -hdac_ext_link_stream_assign(struct hdac_ext_bus *ebus, +hdac_ext_link_stream_assign(struct hdac_bus *bus, struct snd_pcm_substream *substream) { struct hdac_ext_stream *res = NULL; struct hdac_stream *stream = NULL; - struct hdac_bus *hbus = &ebus->bus; - if (!hbus->ppcap) { - dev_err(hbus->dev, "stream type not supported\n"); + if (!bus->ppcap) { + dev_err(bus->dev, "stream type not supported\n"); return NULL; } - list_for_each_entry(stream, &hbus->stream_list, list) { + list_for_each_entry(stream, &bus->stream_list, list) { struct hdac_ext_stream *hstream = container_of(stream, struct hdac_ext_stream, hstream); @@ -277,34 +272,33 @@ hdac_ext_link_stream_assign(struct hdac_ext_bus *ebus, } if (!hstream->link_locked) { - snd_hdac_ext_stream_decouple(ebus, hstream, true); + snd_hdac_ext_stream_decouple(bus, hstream, true); res = hstream; break; } } if (res) { - spin_lock_irq(&hbus->reg_lock); + spin_lock_irq(&bus->reg_lock); res->link_locked = 1; res->link_substream = substream; - spin_unlock_irq(&hbus->reg_lock); + spin_unlock_irq(&bus->reg_lock); } return res; } static struct hdac_ext_stream * -hdac_ext_host_stream_assign(struct hdac_ext_bus *ebus, +hdac_ext_host_stream_assign(struct hdac_bus *bus, struct snd_pcm_substream *substream) { struct hdac_ext_stream *res = NULL; struct hdac_stream *stream = NULL; - struct hdac_bus *hbus = &ebus->bus; - if (!hbus->ppcap) { - dev_err(hbus->dev, "stream type not supported\n"); + if (!bus->ppcap) { + dev_err(bus->dev, "stream type not supported\n"); return NULL; } - list_for_each_entry(stream, &hbus->stream_list, list) { + list_for_each_entry(stream, &bus->stream_list, list) { struct hdac_ext_stream *hstream = container_of(stream, struct hdac_ext_stream, hstream); @@ -313,17 +307,17 @@ hdac_ext_host_stream_assign(struct hdac_ext_bus *ebus, if (!stream->opened) { if (!hstream->decoupled) - snd_hdac_ext_stream_decouple(ebus, hstream, true); + snd_hdac_ext_stream_decouple(bus, hstream, true); res = hstream; break; } } if (res) { - spin_lock_irq(&hbus->reg_lock); + spin_lock_irq(&bus->reg_lock); res->hstream.opened = 1; res->hstream.running = 0; res->hstream.substream = substream; - spin_unlock_irq(&hbus->reg_lock); + spin_unlock_irq(&bus->reg_lock); } return res; @@ -331,7 +325,7 @@ hdac_ext_host_stream_assign(struct hdac_ext_bus *ebus, /** * snd_hdac_ext_stream_assign - assign a stream for the PCM - * @ebus: HD-audio ext core bus + * @bus: HD-audio core bus * @substream: PCM substream to assign * @type: type of stream (coupled, host or link stream) * @@ -346,27 +340,26 @@ hdac_ext_host_stream_assign(struct hdac_ext_bus *ebus, * the same stream object when it's used beforehand. when a stream is * decoupled, it becomes a host stream and link stream. */ -struct hdac_ext_stream *snd_hdac_ext_stream_assign(struct hdac_ext_bus *ebus, +struct hdac_ext_stream *snd_hdac_ext_stream_assign(struct hdac_bus *bus, struct snd_pcm_substream *substream, int type) { struct hdac_ext_stream *hstream = NULL; struct hdac_stream *stream = NULL; - struct hdac_bus *hbus = &ebus->bus; switch (type) { case HDAC_EXT_STREAM_TYPE_COUPLED: - stream = snd_hdac_stream_assign(hbus, substream); + stream = snd_hdac_stream_assign(bus, substream); if (stream) hstream = container_of(stream, struct hdac_ext_stream, hstream); return hstream; case HDAC_EXT_STREAM_TYPE_HOST: - return hdac_ext_host_stream_assign(ebus, substream); + return hdac_ext_host_stream_assign(bus, substream); case HDAC_EXT_STREAM_TYPE_LINK: - return hdac_ext_link_stream_assign(ebus, substream); + return hdac_ext_link_stream_assign(bus, substream); default: return NULL; @@ -384,7 +377,6 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_stream_assign); void snd_hdac_ext_stream_release(struct hdac_ext_stream *stream, int type) { struct hdac_bus *bus = stream->hstream.bus; - struct hdac_ext_bus *ebus = hbus_to_ebus(bus); switch (type) { case HDAC_EXT_STREAM_TYPE_COUPLED: @@ -393,13 +385,13 @@ void snd_hdac_ext_stream_release(struct hdac_ext_stream *stream, int type) case HDAC_EXT_STREAM_TYPE_HOST: if (stream->decoupled && !stream->link_locked) - snd_hdac_ext_stream_decouple(ebus, stream, false); + snd_hdac_ext_stream_decouple(bus, stream, false); snd_hdac_stream_release(&stream->hstream); break; case HDAC_EXT_STREAM_TYPE_LINK: if (stream->decoupled && !stream->hstream.opened) - snd_hdac_ext_stream_decouple(ebus, stream, false); + snd_hdac_ext_stream_decouple(bus, stream, false); spin_lock_irq(&bus->reg_lock); stream->link_locked = 0; stream->link_substream = NULL; @@ -415,16 +407,15 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_stream_release); /** * snd_hdac_ext_stream_spbcap_enable - enable SPIB for a stream - * @ebus: HD-audio ext core bus + * @bus: HD-audio core bus * @enable: flag to enable/disable SPIB * @index: stream index for which SPIB need to be enabled */ -void snd_hdac_ext_stream_spbcap_enable(struct hdac_ext_bus *ebus, +void snd_hdac_ext_stream_spbcap_enable(struct hdac_bus *bus, bool enable, int index) { u32 mask = 0; u32 register_mask = 0; - struct hdac_bus *bus = &ebus->bus; if (!bus->spbcap) { dev_err(bus->dev, "Address of SPB capability is NULL\n"); @@ -446,14 +437,13 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_stream_spbcap_enable); /** * snd_hdac_ext_stream_set_spib - sets the spib value of a stream - * @ebus: HD-audio ext core bus + * @bus: HD-audio core bus * @stream: hdac_ext_stream * @value: spib value to set */ -int snd_hdac_ext_stream_set_spib(struct hdac_ext_bus *ebus, +int snd_hdac_ext_stream_set_spib(struct hdac_bus *bus, struct hdac_ext_stream *stream, u32 value) { - struct hdac_bus *bus = &ebus->bus; if (!bus->spbcap) { dev_err(bus->dev, "Address of SPB capability is NULL\n"); @@ -468,15 +458,14 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_stream_set_spib); /** * snd_hdac_ext_stream_get_spbmaxfifo - gets the spib value of a stream - * @ebus: HD-audio ext core bus + * @bus: HD-audio core bus * @stream: hdac_ext_stream * * Return maxfifo for the stream */ -int snd_hdac_ext_stream_get_spbmaxfifo(struct hdac_ext_bus *ebus, +int snd_hdac_ext_stream_get_spbmaxfifo(struct hdac_bus *bus, struct hdac_ext_stream *stream) { - struct hdac_bus *bus = &ebus->bus; if (!bus->spbcap) { dev_err(bus->dev, "Address of SPB capability is NULL\n"); @@ -490,11 +479,10 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_stream_get_spbmaxfifo); /** * snd_hdac_ext_stop_streams - stop all stream if running - * @ebus: HD-audio ext core bus + * @bus: HD-audio core bus */ -void snd_hdac_ext_stop_streams(struct hdac_ext_bus *ebus) +void snd_hdac_ext_stop_streams(struct hdac_bus *bus) { - struct hdac_bus *bus = ebus_to_hbus(ebus); struct hdac_stream *stream; if (bus->chip_init) { @@ -507,16 +495,15 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_stop_streams); /** * snd_hdac_ext_stream_drsm_enable - enable DMA resume for a stream - * @ebus: HD-audio ext core bus + * @bus: HD-audio core bus * @enable: flag to enable/disable DRSM * @index: stream index for which DRSM need to be enabled */ -void snd_hdac_ext_stream_drsm_enable(struct hdac_ext_bus *ebus, +void snd_hdac_ext_stream_drsm_enable(struct hdac_bus *bus, bool enable, int index) { u32 mask = 0; u32 register_mask = 0; - struct hdac_bus *bus = &ebus->bus; if (!bus->drsmcap) { dev_err(bus->dev, "Address of DRSM capability is NULL\n"); @@ -538,14 +525,13 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_stream_drsm_enable); /** * snd_hdac_ext_stream_set_dpibr - sets the dpibr value of a stream - * @ebus: HD-audio ext core bus + * @bus: HD-audio core bus * @stream: hdac_ext_stream * @value: dpib value to set */ -int snd_hdac_ext_stream_set_dpibr(struct hdac_ext_bus *ebus, +int snd_hdac_ext_stream_set_dpibr(struct hdac_bus *bus, struct hdac_ext_stream *stream, u32 value) { - struct hdac_bus *bus = &ebus->bus; if (!bus->drsmcap) { dev_err(bus->dev, "Address of DRSM capability is NULL\n"); @@ -560,7 +546,7 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_stream_set_dpibr); /** * snd_hdac_ext_stream_set_lpib - sets the lpib value of a stream - * @ebus: HD-audio ext core bus + * @bus: HD-audio core bus * @stream: hdac_ext_stream * @value: lpib value to set */ diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c index f1e235817a65..c3ccc8d9c91d 100644 --- a/sound/soc/codecs/hdac_hdmi.c +++ b/sound/soc/codecs/hdac_hdmi.c @@ -1799,14 +1799,13 @@ static int hdmi_codec_probe(struct snd_soc_component *component) * hold the ref while we probe, also no need to drop the ref on * exit, we call pm_runtime_suspend() so that will do for us */ - hlink = snd_hdac_ext_bus_get_link(hbus_to_ebus(hdev->bus), - dev_name(&hdev->dev)); + hlink = snd_hdac_ext_bus_get_link(hdev->bus, dev_name(&hdev->dev)); if (!hlink) { dev_err(&hdev->dev, "hdac link not found\n"); return -EIO; } - snd_hdac_ext_bus_link_get(hbus_to_ebus(hdev->bus), hlink); + snd_hdac_ext_bus_link_get(hdev->bus, hlink); ret = create_fill_widget_route_map(dapm); if (ret < 0) @@ -1984,14 +1983,13 @@ static int hdac_hdmi_dev_probe(struct hdac_device *hdev) const struct hda_device_id *hdac_id = hdac_get_device_id(hdev, hdrv); /* hold the ref while we probe */ - hlink = snd_hdac_ext_bus_get_link(hbus_to_ebus(hdev->bus), - dev_name(&hdev->dev)); + hlink = snd_hdac_ext_bus_get_link(hdev->bus, dev_name(&hdev->dev)); if (!hlink) { dev_err(&hdev->dev, "hdac link not found\n"); return -EIO; } - snd_hdac_ext_bus_link_get(hbus_to_ebus(hdev->bus), hlink); + snd_hdac_ext_bus_link_get(hdev->bus, hlink); hdmi_priv = devm_kzalloc(&hdev->dev, sizeof(*hdmi_priv), GFP_KERNEL); if (hdmi_priv == NULL) @@ -2044,7 +2042,7 @@ static int hdac_hdmi_dev_probe(struct hdac_device *hdev) ret = devm_snd_soc_register_component(&hdev->dev, &hdmi_hda_codec, hdmi_dais, num_dais); - snd_hdac_ext_bus_link_put(hbus_to_ebus(hdev->bus), hlink); + snd_hdac_ext_bus_link_put(hdev->bus, hlink); return ret; } @@ -2093,7 +2091,6 @@ static int hdac_hdmi_runtime_suspend(struct device *dev) { struct hdac_device *hdev = dev_to_hdac_dev(dev); struct hdac_bus *bus = hdev->bus; - struct hdac_ext_bus *ebus = hbus_to_ebus(bus); struct hdac_ext_link *hlink = NULL; int err; @@ -2118,13 +2115,13 @@ static int hdac_hdmi_runtime_suspend(struct device *dev) return err; } - hlink = snd_hdac_ext_bus_get_link(ebus, dev_name(dev)); + hlink = snd_hdac_ext_bus_get_link(bus, dev_name(dev)); if (!hlink) { dev_err(dev, "hdac link not found\n"); return -EIO; } - snd_hdac_ext_bus_link_put(ebus, hlink); + snd_hdac_ext_bus_link_put(bus, hlink); return 0; } @@ -2133,7 +2130,6 @@ static int hdac_hdmi_runtime_resume(struct device *dev) { struct hdac_device *hdev = dev_to_hdac_dev(dev); struct hdac_bus *bus = hdev->bus; - struct hdac_ext_bus *ebus = hbus_to_ebus(bus); struct hdac_ext_link *hlink = NULL; int err; @@ -2143,13 +2139,13 @@ static int hdac_hdmi_runtime_resume(struct device *dev) if (!bus) return 0; - hlink = snd_hdac_ext_bus_get_link(ebus, dev_name(dev)); + hlink = snd_hdac_ext_bus_get_link(bus, dev_name(dev)); if (!hlink) { dev_err(dev, "hdac link not found\n"); return -EIO; } - snd_hdac_ext_bus_link_get(ebus, hlink); + snd_hdac_ext_bus_link_get(bus, hlink); err = snd_hdac_display_power(bus, true); if (err < 0) { diff --git a/sound/soc/intel/skylake/skl-messages.c b/sound/soc/intel/skylake/skl-messages.c index d5f9c30eba32..8bfb8b0fa3d5 100644 --- a/sound/soc/intel/skylake/skl-messages.c +++ b/sound/soc/intel/skylake/skl-messages.c @@ -33,8 +33,7 @@ static int skl_alloc_dma_buf(struct device *dev, struct snd_dma_buffer *dmab, size_t size) { - struct hdac_ext_bus *ebus = dev_get_drvdata(dev); - struct hdac_bus *bus = ebus_to_hbus(ebus); + struct hdac_bus *bus = dev_get_drvdata(dev); if (!bus) return -ENODEV; @@ -44,8 +43,7 @@ static int skl_alloc_dma_buf(struct device *dev, static int skl_free_dma_buf(struct device *dev, struct snd_dma_buffer *dmab) { - struct hdac_ext_bus *ebus = dev_get_drvdata(dev); - struct hdac_bus *bus = ebus_to_hbus(ebus); + struct hdac_bus *bus = dev_get_drvdata(dev); if (!bus) return -ENODEV; @@ -89,8 +87,7 @@ void skl_dsp_enable_notification(struct skl_sst *ctx, bool enable) static int skl_dsp_setup_spib(struct device *dev, unsigned int size, int stream_tag, int enable) { - struct hdac_ext_bus *ebus = dev_get_drvdata(dev); - struct hdac_bus *bus = ebus_to_hbus(ebus); + struct hdac_bus *bus = dev_get_drvdata(dev); struct hdac_stream *stream = snd_hdac_get_stream(bus, SNDRV_PCM_STREAM_PLAYBACK, stream_tag); struct hdac_ext_stream *estream; @@ -100,10 +97,10 @@ static int skl_dsp_setup_spib(struct device *dev, unsigned int size, estream = stream_to_hdac_ext_stream(stream); /* enable/disable SPIB for this hdac stream */ - snd_hdac_ext_stream_spbcap_enable(ebus, enable, stream->index); + snd_hdac_ext_stream_spbcap_enable(bus, enable, stream->index); /* set the spib value */ - snd_hdac_ext_stream_set_spib(ebus, estream, size); + snd_hdac_ext_stream_set_spib(bus, estream, size); return 0; } @@ -111,8 +108,7 @@ static int skl_dsp_setup_spib(struct device *dev, unsigned int size, static int skl_dsp_prepare(struct device *dev, unsigned int format, unsigned int size, struct snd_dma_buffer *dmab) { - struct hdac_ext_bus *ebus = dev_get_drvdata(dev); - struct hdac_bus *bus = ebus_to_hbus(ebus); + struct hdac_bus *bus = dev_get_drvdata(dev); struct hdac_ext_stream *estream; struct hdac_stream *stream; struct snd_pcm_substream substream; @@ -124,7 +120,7 @@ static int skl_dsp_prepare(struct device *dev, unsigned int format, memset(&substream, 0, sizeof(substream)); substream.stream = SNDRV_PCM_STREAM_PLAYBACK; - estream = snd_hdac_ext_stream_assign(ebus, &substream, + estream = snd_hdac_ext_stream_assign(bus, &substream, HDAC_EXT_STREAM_TYPE_HOST); if (!estream) return -ENODEV; @@ -143,9 +139,8 @@ static int skl_dsp_prepare(struct device *dev, unsigned int format, static int skl_dsp_trigger(struct device *dev, bool start, int stream_tag) { - struct hdac_ext_bus *ebus = dev_get_drvdata(dev); + struct hdac_bus *bus = dev_get_drvdata(dev); struct hdac_stream *stream; - struct hdac_bus *bus = ebus_to_hbus(ebus); if (!bus) return -ENODEV; @@ -163,10 +158,9 @@ static int skl_dsp_trigger(struct device *dev, bool start, int stream_tag) static int skl_dsp_cleanup(struct device *dev, struct snd_dma_buffer *dmab, int stream_tag) { - struct hdac_ext_bus *ebus = dev_get_drvdata(dev); + struct hdac_bus *bus = dev_get_drvdata(dev); struct hdac_stream *stream; struct hdac_ext_stream *estream; - struct hdac_bus *bus = ebus_to_hbus(ebus); if (!bus) return -ENODEV; @@ -270,8 +264,7 @@ const struct skl_dsp_ops *skl_get_dsp_ops(int pci_id) int skl_init_dsp(struct skl *skl) { void __iomem *mmio_base; - struct hdac_ext_bus *ebus = &skl->ebus; - struct hdac_bus *bus = ebus_to_hbus(ebus); + struct hdac_bus *bus = skl_to_bus(skl); struct skl_dsp_loader_ops loader_ops; int irq = bus->irq; const struct skl_dsp_ops *ops; @@ -279,8 +272,8 @@ int skl_init_dsp(struct skl *skl) int ret; /* enable ppcap interrupt */ - snd_hdac_ext_bus_ppcap_enable(&skl->ebus, true); - snd_hdac_ext_bus_ppcap_int_enable(&skl->ebus, true); + snd_hdac_ext_bus_ppcap_enable(bus, true); + snd_hdac_ext_bus_ppcap_int_enable(bus, true); /* read the BAR of the ADSP MMIO */ mmio_base = pci_ioremap_bar(skl->pci, 4); @@ -335,12 +328,11 @@ unmap_mmio: int skl_free_dsp(struct skl *skl) { - struct hdac_ext_bus *ebus = &skl->ebus; - struct hdac_bus *bus = ebus_to_hbus(ebus); + struct hdac_bus *bus = skl_to_bus(skl); struct skl_sst *ctx = skl->skl_sst; /* disable ppcap interrupt */ - snd_hdac_ext_bus_ppcap_int_enable(&skl->ebus, false); + snd_hdac_ext_bus_ppcap_int_enable(bus, false); ctx->dsp_ops->cleanup(bus->dev, ctx); @@ -383,10 +375,11 @@ int skl_suspend_late_dsp(struct skl *skl) int skl_suspend_dsp(struct skl *skl) { struct skl_sst *ctx = skl->skl_sst; + struct hdac_bus *bus = skl_to_bus(skl); int ret; /* if ppcap is not supported return 0 */ - if (!skl->ebus.bus.ppcap) + if (!bus->ppcap) return 0; ret = skl_dsp_sleep(ctx->dsp); @@ -394,8 +387,8 @@ int skl_suspend_dsp(struct skl *skl) return ret; /* disable ppcap interrupt */ - snd_hdac_ext_bus_ppcap_int_enable(&skl->ebus, false); - snd_hdac_ext_bus_ppcap_enable(&skl->ebus, false); + snd_hdac_ext_bus_ppcap_int_enable(bus, false); + snd_hdac_ext_bus_ppcap_enable(bus, false); return 0; } @@ -403,15 +396,16 @@ int skl_suspend_dsp(struct skl *skl) int skl_resume_dsp(struct skl *skl) { struct skl_sst *ctx = skl->skl_sst; + struct hdac_bus *bus = skl_to_bus(skl); int ret; /* if ppcap is not supported return 0 */ - if (!skl->ebus.bus.ppcap) + if (!bus->ppcap) return 0; /* enable ppcap interrupt */ - snd_hdac_ext_bus_ppcap_enable(&skl->ebus, true); - snd_hdac_ext_bus_ppcap_int_enable(&skl->ebus, true); + snd_hdac_ext_bus_ppcap_enable(bus, true); + snd_hdac_ext_bus_ppcap_int_enable(bus, true); /* check if DSP 1st boot is done */ if (skl->skl_sst->is_first_boot == true) diff --git a/sound/soc/intel/skylake/skl-nhlt.c b/sound/soc/intel/skylake/skl-nhlt.c index b9b140275be0..01a050cf8775 100644 --- a/sound/soc/intel/skylake/skl-nhlt.c +++ b/sound/soc/intel/skylake/skl-nhlt.c @@ -141,7 +141,7 @@ struct nhlt_specific_cfg { struct nhlt_fmt *fmt; struct nhlt_endpoint *epnt; - struct hdac_bus *bus = ebus_to_hbus(&skl->ebus); + struct hdac_bus *bus = skl_to_bus(skl); struct device *dev = bus->dev; struct nhlt_specific_cfg *sp_config; struct nhlt_acpi_table *nhlt = skl->nhlt; @@ -228,7 +228,7 @@ static void skl_nhlt_trim_space(char *trim) int skl_nhlt_update_topology_bin(struct skl *skl) { struct nhlt_acpi_table *nhlt = (struct nhlt_acpi_table *)skl->nhlt; - struct hdac_bus *bus = ebus_to_hbus(&skl->ebus); + struct hdac_bus *bus = skl_to_bus(skl); struct device *dev = bus->dev; dev_dbg(dev, "oem_id %.6s, oem_table_id %8s oem_revision %d\n", @@ -248,8 +248,8 @@ static ssize_t skl_nhlt_platform_id_show(struct device *dev, struct device_attribute *attr, char *buf) { struct pci_dev *pci = to_pci_dev(dev); - struct hdac_ext_bus *ebus = pci_get_drvdata(pci); - struct skl *skl = ebus_to_skl(ebus); + struct hdac_bus *bus = pci_get_drvdata(pci); + struct skl *skl = bus_to_skl(bus); struct nhlt_acpi_table *nhlt = (struct nhlt_acpi_table *)skl->nhlt; char platform_id[32]; diff --git a/sound/soc/intel/skylake/skl-pcm.c b/sound/soc/intel/skylake/skl-pcm.c index afa86b9e4dcf..d7fc3b2d3e68 100644 --- a/sound/soc/intel/skylake/skl-pcm.c +++ b/sound/soc/intel/skylake/skl-pcm.c @@ -67,16 +67,15 @@ struct hdac_ext_stream *get_hdac_ext_stream(struct snd_pcm_substream *substream) return substream->runtime->private_data; } -static struct hdac_ext_bus *get_bus_ctx(struct snd_pcm_substream *substream) +static struct hdac_bus *get_bus_ctx(struct snd_pcm_substream *substream) { struct hdac_ext_stream *stream = get_hdac_ext_stream(substream); struct hdac_stream *hstream = hdac_stream(stream); struct hdac_bus *bus = hstream->bus; - - return hbus_to_ebus(bus); + return bus; } -static int skl_substream_alloc_pages(struct hdac_ext_bus *ebus, +static int skl_substream_alloc_pages(struct hdac_bus *bus, struct snd_pcm_substream *substream, size_t size) { @@ -95,7 +94,7 @@ static int skl_substream_free_pages(struct hdac_bus *bus, return snd_pcm_lib_free_pages(substream); } -static void skl_set_pcm_constrains(struct hdac_ext_bus *ebus, +static void skl_set_pcm_constrains(struct hdac_bus *bus, struct snd_pcm_runtime *runtime) { snd_pcm_hw_constraint_integer(runtime, SNDRV_PCM_HW_PARAM_PERIODS); @@ -105,9 +104,9 @@ static void skl_set_pcm_constrains(struct hdac_ext_bus *ebus, 20, 178000000); } -static enum hdac_ext_stream_type skl_get_host_stream_type(struct hdac_ext_bus *ebus) +static enum hdac_ext_stream_type skl_get_host_stream_type(struct hdac_bus *bus) { - if ((ebus_to_hbus(ebus))->ppcap) + if (bus->ppcap) return HDAC_EXT_STREAM_TYPE_HOST; else return HDAC_EXT_STREAM_TYPE_COUPLED; @@ -123,9 +122,9 @@ static enum hdac_ext_stream_type skl_get_host_stream_type(struct hdac_ext_bus *e static void skl_set_suspend_active(struct snd_pcm_substream *substream, struct snd_soc_dai *dai, bool enable) { - struct hdac_ext_bus *ebus = dev_get_drvdata(dai->dev); + struct hdac_bus *bus = dev_get_drvdata(dai->dev); struct snd_soc_dapm_widget *w; - struct skl *skl = ebus_to_skl(ebus); + struct skl *skl = bus_to_skl(bus); if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) w = dai->playback_widget; @@ -140,8 +139,7 @@ static void skl_set_suspend_active(struct snd_pcm_substream *substream, int skl_pcm_host_dma_prepare(struct device *dev, struct skl_pipe_params *params) { - struct hdac_ext_bus *ebus = dev_get_drvdata(dev); - struct hdac_bus *bus = ebus_to_hbus(ebus); + struct hdac_bus *bus = dev_get_drvdata(dev); unsigned int format_val; struct hdac_stream *hstream; struct hdac_ext_stream *stream; @@ -153,7 +151,7 @@ int skl_pcm_host_dma_prepare(struct device *dev, struct skl_pipe_params *params) return -EINVAL; stream = stream_to_hdac_ext_stream(hstream); - snd_hdac_ext_stream_decouple(ebus, stream, true); + snd_hdac_ext_stream_decouple(bus, stream, true); format_val = snd_hdac_calc_stream_format(params->s_freq, params->ch, params->format, params->host_bps, 0); @@ -177,8 +175,7 @@ int skl_pcm_host_dma_prepare(struct device *dev, struct skl_pipe_params *params) int skl_pcm_link_dma_prepare(struct device *dev, struct skl_pipe_params *params) { - struct hdac_ext_bus *ebus = dev_get_drvdata(dev); - struct hdac_bus *bus = ebus_to_hbus(ebus); + struct hdac_bus *bus = dev_get_drvdata(dev); unsigned int format_val; struct hdac_stream *hstream; struct hdac_ext_stream *stream; @@ -190,7 +187,7 @@ int skl_pcm_link_dma_prepare(struct device *dev, struct skl_pipe_params *params) return -EINVAL; stream = stream_to_hdac_ext_stream(hstream); - snd_hdac_ext_stream_decouple(ebus, stream, true); + snd_hdac_ext_stream_decouple(bus, stream, true); format_val = snd_hdac_calc_stream_format(params->s_freq, params->ch, params->format, params->link_bps, 0); @@ -201,7 +198,7 @@ int skl_pcm_link_dma_prepare(struct device *dev, struct skl_pipe_params *params) snd_hdac_ext_link_stream_setup(stream, format_val); - list_for_each_entry(link, &ebus->hlink_list, list) { + list_for_each_entry(link, &bus->hlink_list, list) { if (link->index == params->link_index) snd_hdac_ext_link_set_stream_id(link, hstream->stream_tag); @@ -215,7 +212,7 @@ int skl_pcm_link_dma_prepare(struct device *dev, struct skl_pipe_params *params) static int skl_pcm_open(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { - struct hdac_ext_bus *ebus = dev_get_drvdata(dai->dev); + struct hdac_bus *bus = dev_get_drvdata(dai->dev); struct hdac_ext_stream *stream; struct snd_pcm_runtime *runtime = substream->runtime; struct skl_dma_params *dma_params; @@ -224,12 +221,12 @@ static int skl_pcm_open(struct snd_pcm_substream *substream, dev_dbg(dai->dev, "%s: %s\n", __func__, dai->name); - stream = snd_hdac_ext_stream_assign(ebus, substream, - skl_get_host_stream_type(ebus)); + stream = snd_hdac_ext_stream_assign(bus, substream, + skl_get_host_stream_type(bus)); if (stream == NULL) return -EBUSY; - skl_set_pcm_constrains(ebus, runtime); + skl_set_pcm_constrains(bus, runtime); /* * disable WALLCLOCK timestamps for capture streams @@ -301,7 +298,7 @@ static int skl_pcm_hw_params(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params, struct snd_soc_dai *dai) { - struct hdac_ext_bus *ebus = dev_get_drvdata(dai->dev); + struct hdac_bus *bus = dev_get_drvdata(dai->dev); struct hdac_ext_stream *stream = get_hdac_ext_stream(substream); struct snd_pcm_runtime *runtime = substream->runtime; struct skl_pipe_params p_params = {0}; @@ -309,7 +306,7 @@ static int skl_pcm_hw_params(struct snd_pcm_substream *substream, int ret, dma_id; dev_dbg(dai->dev, "%s: %s\n", __func__, dai->name); - ret = skl_substream_alloc_pages(ebus, substream, + ret = skl_substream_alloc_pages(bus, substream, params_buffer_bytes(params)); if (ret < 0) return ret; @@ -343,14 +340,14 @@ static void skl_pcm_close(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { struct hdac_ext_stream *stream = get_hdac_ext_stream(substream); - struct hdac_ext_bus *ebus = dev_get_drvdata(dai->dev); + struct hdac_bus *bus = dev_get_drvdata(dai->dev); struct skl_dma_params *dma_params = NULL; - struct skl *skl = ebus_to_skl(ebus); + struct skl *skl = bus_to_skl(bus); struct skl_module_cfg *mconfig; dev_dbg(dai->dev, "%s: %s\n", __func__, dai->name); - snd_hdac_ext_stream_release(stream, skl_get_host_stream_type(ebus)); + snd_hdac_ext_stream_release(stream, skl_get_host_stream_type(bus)); dma_params = snd_soc_dai_get_dma_data(dai, substream); /* @@ -380,7 +377,7 @@ static void skl_pcm_close(struct snd_pcm_substream *substream, static int skl_pcm_hw_free(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { - struct hdac_ext_bus *ebus = dev_get_drvdata(dai->dev); + struct hdac_bus *bus = dev_get_drvdata(dai->dev); struct hdac_ext_stream *stream = get_hdac_ext_stream(substream); struct skl *skl = get_skl_ctx(dai->dev); struct skl_module_cfg *mconfig; @@ -400,7 +397,7 @@ static int skl_pcm_hw_free(struct snd_pcm_substream *substream, snd_hdac_stream_cleanup(hdac_stream(stream)); hdac_stream(stream)->prepared = 0; - return skl_substream_free_pages(ebus_to_hbus(ebus), substream); + return skl_substream_free_pages(bus, substream); } static int skl_be_hw_params(struct snd_pcm_substream *substream, @@ -420,8 +417,7 @@ static int skl_be_hw_params(struct snd_pcm_substream *substream, static int skl_decoupled_trigger(struct snd_pcm_substream *substream, int cmd) { - struct hdac_ext_bus *ebus = get_bus_ctx(substream); - struct hdac_bus *bus = ebus_to_hbus(ebus); + struct hdac_bus *bus = get_bus_ctx(substream); struct hdac_ext_stream *stream; int start; unsigned long cookie; @@ -470,7 +466,7 @@ static int skl_pcm_trigger(struct snd_pcm_substream *substream, int cmd, struct skl *skl = get_skl_ctx(dai->dev); struct skl_sst *ctx = skl->skl_sst; struct skl_module_cfg *mconfig; - struct hdac_ext_bus *ebus = get_bus_ctx(substream); + struct hdac_bus *bus = get_bus_ctx(substream); struct hdac_ext_stream *stream = get_hdac_ext_stream(substream); struct snd_soc_dapm_widget *w; int ret; @@ -492,9 +488,9 @@ static int skl_pcm_trigger(struct snd_pcm_substream *substream, int cmd, * dpib & lpib position to resume before starting the * DMA */ - snd_hdac_ext_stream_drsm_enable(ebus, true, + snd_hdac_ext_stream_drsm_enable(bus, true, hdac_stream(stream)->index); - snd_hdac_ext_stream_set_dpibr(ebus, stream, + snd_hdac_ext_stream_set_dpibr(bus, stream, stream->lpib); snd_hdac_ext_stream_set_lpib(stream, stream->lpib); } @@ -528,14 +524,14 @@ static int skl_pcm_trigger(struct snd_pcm_substream *substream, int cmd, ret = skl_decoupled_trigger(substream, cmd); if ((cmd == SNDRV_PCM_TRIGGER_SUSPEND) && !w->ignore_suspend) { /* save the dpib and lpib positions */ - stream->dpib = readl(ebus->bus.remap_addr + + stream->dpib = readl(bus->remap_addr + AZX_REG_VS_SDXDPIB_XBASE + (AZX_REG_VS_SDXDPIB_XINTERVAL * hdac_stream(stream)->index)); stream->lpib = snd_hdac_stream_get_pos_lpib( hdac_stream(stream)); - snd_hdac_ext_stream_decouple(ebus, stream, false); + snd_hdac_ext_stream_decouple(bus, stream, false); } break; @@ -546,11 +542,12 @@ static int skl_pcm_trigger(struct snd_pcm_substream *substream, int cmd, return 0; } + static int skl_link_hw_params(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params, struct snd_soc_dai *dai) { - struct hdac_ext_bus *ebus = dev_get_drvdata(dai->dev); + struct hdac_bus *bus = dev_get_drvdata(dai->dev); struct hdac_ext_stream *link_dev; struct snd_soc_pcm_runtime *rtd = snd_pcm_substream_chip(substream); struct snd_soc_dai *codec_dai = rtd->codec_dai; @@ -558,14 +555,14 @@ static int skl_link_hw_params(struct snd_pcm_substream *substream, struct hdac_ext_link *link; int stream_tag; - link_dev = snd_hdac_ext_stream_assign(ebus, substream, + link_dev = snd_hdac_ext_stream_assign(bus, substream, HDAC_EXT_STREAM_TYPE_LINK); if (!link_dev) return -EBUSY; snd_soc_dai_set_dma_data(dai, substream, (void *)link_dev); - link = snd_hdac_ext_bus_get_link(ebus, codec_dai->component->name); + link = snd_hdac_ext_bus_get_link(bus, codec_dai->component->name); if (!link) return -EINVAL; @@ -610,7 +607,7 @@ static int skl_link_pcm_trigger(struct snd_pcm_substream *substream, { struct hdac_ext_stream *link_dev = snd_soc_dai_get_dma_data(dai, substream); - struct hdac_ext_bus *ebus = get_bus_ctx(substream); + struct hdac_bus *bus = get_bus_ctx(substream); struct hdac_ext_stream *stream = get_hdac_ext_stream(substream); dev_dbg(dai->dev, "In %s cmd=%d\n", __func__, cmd); @@ -626,7 +623,7 @@ static int skl_link_pcm_trigger(struct snd_pcm_substream *substream, case SNDRV_PCM_TRIGGER_STOP: snd_hdac_ext_link_stream_clear(link_dev); if (cmd == SNDRV_PCM_TRIGGER_SUSPEND) - snd_hdac_ext_stream_decouple(ebus, stream, false); + snd_hdac_ext_stream_decouple(bus, stream, false); break; default: @@ -638,7 +635,7 @@ static int skl_link_pcm_trigger(struct snd_pcm_substream *substream, static int skl_link_hw_free(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { - struct hdac_ext_bus *ebus = dev_get_drvdata(dai->dev); + struct hdac_bus *bus = dev_get_drvdata(dai->dev); struct snd_soc_pcm_runtime *rtd = snd_pcm_substream_chip(substream); struct hdac_ext_stream *link_dev = snd_soc_dai_get_dma_data(dai, substream); @@ -648,7 +645,7 @@ static int skl_link_hw_free(struct snd_pcm_substream *substream, link_dev->link_prepared = 0; - link = snd_hdac_ext_bus_get_link(ebus, rtd->codec_dai->component->name); + link = snd_hdac_ext_bus_get_link(bus, rtd->codec_dai->component->name); if (!link) return -EINVAL; @@ -1041,8 +1038,7 @@ static int skl_platform_open(struct snd_pcm_substream *substream) static int skl_coupled_trigger(struct snd_pcm_substream *substream, int cmd) { - struct hdac_ext_bus *ebus = get_bus_ctx(substream); - struct hdac_bus *bus = ebus_to_hbus(ebus); + struct hdac_bus *bus = get_bus_ctx(substream); struct hdac_ext_stream *stream; struct snd_pcm_substream *s; bool start; @@ -1115,9 +1111,9 @@ static int skl_coupled_trigger(struct snd_pcm_substream *substream, static int skl_platform_pcm_trigger(struct snd_pcm_substream *substream, int cmd) { - struct hdac_ext_bus *ebus = get_bus_ctx(substream); + struct hdac_bus *bus = get_bus_ctx(substream); - if (!(ebus_to_hbus(ebus))->ppcap) + if (!bus->ppcap) return skl_coupled_trigger(substream, cmd); return 0; @@ -1127,7 +1123,7 @@ static snd_pcm_uframes_t skl_platform_pcm_pointer (struct snd_pcm_substream *substream) { struct hdac_ext_stream *hstream = get_hdac_ext_stream(substream); - struct hdac_ext_bus *ebus = get_bus_ctx(substream); + struct hdac_bus *bus = get_bus_ctx(substream); unsigned int pos; /* @@ -1152,12 +1148,12 @@ static snd_pcm_uframes_t skl_platform_pcm_pointer */ if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { - pos = readl(ebus->bus.remap_addr + AZX_REG_VS_SDXDPIB_XBASE + + pos = readl(bus->remap_addr + AZX_REG_VS_SDXDPIB_XBASE + (AZX_REG_VS_SDXDPIB_XINTERVAL * hdac_stream(hstream)->index)); } else { udelay(20); - readl(ebus->bus.remap_addr + + readl(bus->remap_addr + AZX_REG_VS_SDXDPIB_XBASE + (AZX_REG_VS_SDXDPIB_XINTERVAL * hdac_stream(hstream)->index)); @@ -1242,11 +1238,11 @@ static void skl_pcm_free(struct snd_pcm *pcm) static int skl_pcm_new(struct snd_soc_pcm_runtime *rtd) { struct snd_soc_dai *dai = rtd->cpu_dai; - struct hdac_ext_bus *ebus = dev_get_drvdata(dai->dev); + struct hdac_bus *bus = dev_get_drvdata(dai->dev); struct snd_pcm *pcm = rtd->pcm; unsigned int size; int retval = 0; - struct skl *skl = ebus_to_skl(ebus); + struct skl *skl = bus_to_skl(bus); if (dai->driver->playback.channels_min || dai->driver->capture.channels_min) { @@ -1356,19 +1352,19 @@ static int skl_populate_modules(struct skl *skl) static int skl_platform_soc_probe(struct snd_soc_component *component) { - struct hdac_ext_bus *ebus = dev_get_drvdata(component->dev); - struct skl *skl = ebus_to_skl(ebus); + struct hdac_bus *bus = dev_get_drvdata(component->dev); + struct skl *skl = bus_to_skl(bus); const struct skl_dsp_ops *ops; int ret; pm_runtime_get_sync(component->dev); - if ((ebus_to_hbus(ebus))->ppcap) { + if (bus->ppcap) { skl->component = component; /* init debugfs */ skl->debugfs = skl_debugfs_init(skl); - ret = skl_tplg_init(component, ebus); + ret = skl_tplg_init(component, bus); if (ret < 0) { dev_err(component->dev, "Failed to init topology!\n"); return ret; @@ -1425,10 +1421,10 @@ static const struct snd_soc_component_driver skl_component = { int skl_platform_register(struct device *dev) { int ret; - struct hdac_ext_bus *ebus = dev_get_drvdata(dev); - struct skl *skl = ebus_to_skl(ebus); struct snd_soc_dai_driver *dais; int num_dais = ARRAY_SIZE(skl_platform_dai); + struct hdac_bus *bus = dev_get_drvdata(dev); + struct skl *skl = bus_to_skl(bus); INIT_LIST_HEAD(&skl->ppl_list); INIT_LIST_HEAD(&skl->bind_list); @@ -1464,8 +1460,8 @@ err: int skl_platform_unregister(struct device *dev) { - struct hdac_ext_bus *ebus = dev_get_drvdata(dev); - struct skl *skl = ebus_to_skl(ebus); + struct hdac_bus *bus = dev_get_drvdata(dev); + struct skl *skl = bus_to_skl(bus); struct skl_module_deferred_bind *modules, *tmp; if (!list_empty(&skl->bind_list)) { diff --git a/sound/soc/intel/skylake/skl-topology.c b/sound/soc/intel/skylake/skl-topology.c index fcdc716754b6..abfdb67c05cc 100644 --- a/sound/soc/intel/skylake/skl-topology.c +++ b/sound/soc/intel/skylake/skl-topology.c @@ -934,7 +934,7 @@ static int skl_tplg_find_moduleid_from_uuid(struct skl *skl, struct soc_bytes_ext *sb = (void *) k->private_value; struct skl_algo_data *bc = (struct skl_algo_data *)sb->dobj.private; struct skl_kpb_params *uuid_params, *params; - struct hdac_bus *bus = ebus_to_hbus(skl_to_ebus(skl)); + struct hdac_bus *bus = skl_to_bus(skl); int i, size, module_id; if (bc->set_params == SKL_PARAM_BIND && bc->max) { @@ -3029,9 +3029,8 @@ static int skl_tplg_widget_load(struct snd_soc_component *cmpnt, struct snd_soc_tplg_dapm_widget *tplg_w) { int ret; - struct hdac_ext_bus *ebus = snd_soc_component_get_drvdata(cmpnt); - struct skl *skl = ebus_to_skl(ebus); - struct hdac_bus *bus = ebus_to_hbus(ebus); + struct hdac_bus *bus = snd_soc_component_get_drvdata(cmpnt); + struct skl *skl = bus_to_skl(bus); struct skl_module_cfg *mconfig; if (!tplg_w->priv.size) @@ -3137,8 +3136,7 @@ static int skl_tplg_control_load(struct snd_soc_component *cmpnt, struct soc_bytes_ext *sb; struct snd_soc_tplg_bytes_control *tplg_bc; struct snd_soc_tplg_enum_control *tplg_ec; - struct hdac_ext_bus *ebus = snd_soc_component_get_drvdata(cmpnt); - struct hdac_bus *bus = ebus_to_hbus(ebus); + struct hdac_bus *bus = snd_soc_component_get_drvdata(cmpnt); struct soc_enum *se; switch (hdr->ops.info) { @@ -3622,9 +3620,8 @@ static int skl_tplg_get_manifest_data(struct snd_soc_tplg_manifest *manifest, static int skl_manifest_load(struct snd_soc_component *cmpnt, struct snd_soc_tplg_manifest *manifest) { - struct hdac_ext_bus *ebus = snd_soc_component_get_drvdata(cmpnt); - struct hdac_bus *bus = ebus_to_hbus(ebus); - struct skl *skl = ebus_to_skl(ebus); + struct hdac_bus *bus = snd_soc_component_get_drvdata(cmpnt); + struct skl *skl = bus_to_skl(bus); /* proceed only if we have private data defined */ if (manifest->priv.size == 0) @@ -3713,12 +3710,11 @@ static void skl_tplg_set_pipe_type(struct skl *skl, struct skl_pipe *pipe) /* * SKL topology init routine */ -int skl_tplg_init(struct snd_soc_component *component, struct hdac_ext_bus *ebus) +int skl_tplg_init(struct snd_soc_component *component, struct hdac_bus *bus) { int ret; const struct firmware *fw; - struct hdac_bus *bus = ebus_to_hbus(ebus); - struct skl *skl = ebus_to_skl(ebus); + struct skl *skl = bus_to_skl(bus); struct skl_pipeline *ppl; ret = request_firmware(&fw, skl->tplg_name, bus->dev); diff --git a/sound/soc/intel/skylake/skl-topology.h b/sound/soc/intel/skylake/skl-topology.h index 6d7e0569695f..daeb6d2bb7fc 100644 --- a/sound/soc/intel/skylake/skl-topology.h +++ b/sound/soc/intel/skylake/skl-topology.h @@ -458,9 +458,9 @@ enum skl_channel { static inline struct skl *get_skl_ctx(struct device *dev) { - struct hdac_ext_bus *ebus = dev_get_drvdata(dev); + struct hdac_bus *bus = dev_get_drvdata(dev); - return ebus_to_skl(ebus); + return bus_to_skl(bus); } int skl_tplg_be_update_params(struct snd_soc_dai *dai, @@ -470,7 +470,7 @@ int skl_dsp_set_dma_control(struct skl_sst *ctx, u32 *caps, void skl_tplg_set_be_dmic_config(struct snd_soc_dai *dai, struct skl_pipe_params *params, int stream); int skl_tplg_init(struct snd_soc_component *component, - struct hdac_ext_bus *ebus); + struct hdac_bus *ebus); struct skl_module_cfg *skl_tplg_fe_get_cpr_module( struct snd_soc_dai *dai, int stream); int skl_tplg_update_pipe_params(struct device *dev, diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c index f0d9793f872a..9c5a701d68ac 100644 --- a/sound/soc/intel/skylake/skl.c +++ b/sound/soc/intel/skylake/skl.c @@ -54,7 +54,7 @@ static void skl_update_pci_byte(struct pci_dev *pci, unsigned int reg, static void skl_init_pci(struct skl *skl) { - struct hdac_ext_bus *ebus = &skl->ebus; + struct hdac_bus *bus = skl_to_bus(skl); /* * Clear bits 0-2 of PCI register TCSEL (at offset 0x44) @@ -63,7 +63,7 @@ static void skl_init_pci(struct skl *skl) * codecs. * The PCI register TCSEL is defined in the Intel manuals. */ - dev_dbg(ebus_to_hbus(ebus)->dev, "Clearing TCSEL\n"); + dev_dbg(bus->dev, "Clearing TCSEL\n"); skl_update_pci_byte(skl->pci, AZX_PCIREG_TCSEL, 0x07, 0); } @@ -103,8 +103,7 @@ static void skl_enable_miscbdcge(struct device *dev, bool enable) static void skl_clock_power_gating(struct device *dev, bool enable) { struct pci_dev *pci = to_pci_dev(dev); - struct hdac_ext_bus *ebus = pci_get_drvdata(pci); - struct hdac_bus *bus = ebus_to_hbus(ebus); + struct hdac_bus *bus = pci_get_drvdata(pci); u32 val; /* Update PDCGE bit of CGCTL register */ @@ -127,7 +126,6 @@ static void skl_clock_power_gating(struct device *dev, bool enable) */ static int skl_init_chip(struct hdac_bus *bus, bool full_reset) { - struct hdac_ext_bus *ebus = hbus_to_ebus(bus); struct hdac_ext_link *hlink; int ret; @@ -135,7 +133,7 @@ static int skl_init_chip(struct hdac_bus *bus, bool full_reset) ret = snd_hdac_bus_init_chip(bus, full_reset); /* Reset stream-to-link mapping */ - list_for_each_entry(hlink, &ebus->hlink_list, list) + list_for_each_entry(hlink, &bus->hlink_list, list) bus->io_ops->reg_writel(0, hlink->ml_addr + AZX_REG_ML_LOSIDV); skl_enable_miscbdcge(bus->dev, true); @@ -146,8 +144,7 @@ static int skl_init_chip(struct hdac_bus *bus, bool full_reset) void skl_update_d0i3c(struct device *dev, bool enable) { struct pci_dev *pci = to_pci_dev(dev); - struct hdac_ext_bus *ebus = pci_get_drvdata(pci); - struct hdac_bus *bus = ebus_to_hbus(ebus); + struct hdac_bus *bus = pci_get_drvdata(pci); u8 reg; int timeout = 50; @@ -197,8 +194,7 @@ static void skl_stream_update(struct hdac_bus *bus, struct hdac_stream *hstr) static irqreturn_t skl_interrupt(int irq, void *dev_id) { - struct hdac_ext_bus *ebus = dev_id; - struct hdac_bus *bus = ebus_to_hbus(ebus); + struct hdac_bus *bus = dev_id; u32 status; if (!pm_runtime_active(bus->dev)) @@ -227,8 +223,7 @@ static irqreturn_t skl_interrupt(int irq, void *dev_id) static irqreturn_t skl_threaded_handler(int irq, void *dev_id) { - struct hdac_ext_bus *ebus = dev_id; - struct hdac_bus *bus = ebus_to_hbus(ebus); + struct hdac_bus *bus = dev_id; u32 status; status = snd_hdac_chip_readl(bus, INTSTS); @@ -238,16 +233,15 @@ static irqreturn_t skl_threaded_handler(int irq, void *dev_id) return IRQ_HANDLED; } -static int skl_acquire_irq(struct hdac_ext_bus *ebus, int do_disconnect) +static int skl_acquire_irq(struct hdac_bus *bus, int do_disconnect) { - struct skl *skl = ebus_to_skl(ebus); - struct hdac_bus *bus = ebus_to_hbus(ebus); + struct skl *skl = bus_to_skl(bus); int ret; ret = request_threaded_irq(skl->pci->irq, skl_interrupt, skl_threaded_handler, IRQF_SHARED, - KBUILD_MODNAME, ebus); + KBUILD_MODNAME, bus); if (ret) { dev_err(bus->dev, "unable to grab IRQ %d, disabling device\n", @@ -264,21 +258,20 @@ static int skl_acquire_irq(struct hdac_ext_bus *ebus, int do_disconnect) static int skl_suspend_late(struct device *dev) { struct pci_dev *pci = to_pci_dev(dev); - struct hdac_ext_bus *ebus = pci_get_drvdata(pci); - struct skl *skl = ebus_to_skl(ebus); + struct hdac_bus *bus = pci_get_drvdata(pci); + struct skl *skl = bus_to_skl(bus); return skl_suspend_late_dsp(skl); } #ifdef CONFIG_PM -static int _skl_suspend(struct hdac_ext_bus *ebus) +static int _skl_suspend(struct hdac_bus *bus) { - struct skl *skl = ebus_to_skl(ebus); - struct hdac_bus *bus = ebus_to_hbus(ebus); + struct skl *skl = bus_to_skl(bus); struct pci_dev *pci = to_pci_dev(bus->dev); int ret; - snd_hdac_ext_bus_link_power_down_all(ebus); + snd_hdac_ext_bus_link_power_down_all(bus); ret = skl_suspend_dsp(skl); if (ret < 0) @@ -295,10 +288,9 @@ static int _skl_suspend(struct hdac_ext_bus *ebus) return 0; } -static int _skl_resume(struct hdac_ext_bus *ebus) +static int _skl_resume(struct hdac_bus *bus) { - struct skl *skl = ebus_to_skl(ebus); - struct hdac_bus *bus = ebus_to_hbus(ebus); + struct skl *skl = bus_to_skl(bus); skl_init_pci(skl); skl_init_chip(bus, true); @@ -314,9 +306,8 @@ static int _skl_resume(struct hdac_ext_bus *ebus) static int skl_suspend(struct device *dev) { struct pci_dev *pci = to_pci_dev(dev); - struct hdac_ext_bus *ebus = pci_get_drvdata(pci); - struct skl *skl = ebus_to_skl(ebus); - struct hdac_bus *bus = ebus_to_hbus(ebus); + struct hdac_bus *bus = pci_get_drvdata(pci); + struct skl *skl = bus_to_skl(bus); int ret = 0; /* @@ -325,15 +316,15 @@ static int skl_suspend(struct device *dev) */ if (skl->supend_active) { /* turn off the links and stop the CORB/RIRB DMA if it is On */ - snd_hdac_ext_bus_link_power_down_all(ebus); + snd_hdac_ext_bus_link_power_down_all(bus); - if (ebus->cmd_dma_state) - snd_hdac_bus_stop_cmd_io(&ebus->bus); + if (bus->cmd_dma_state) + snd_hdac_bus_stop_cmd_io(bus); enable_irq_wake(bus->irq); pci_save_state(pci); } else { - ret = _skl_suspend(ebus); + ret = _skl_suspend(bus); if (ret < 0) return ret; skl->skl_sst->fw_loaded = false; @@ -352,9 +343,8 @@ static int skl_suspend(struct device *dev) static int skl_resume(struct device *dev) { struct pci_dev *pci = to_pci_dev(dev); - struct hdac_ext_bus *ebus = pci_get_drvdata(pci); - struct skl *skl = ebus_to_skl(ebus); - struct hdac_bus *bus = ebus_to_hbus(ebus); + struct hdac_bus *bus = pci_get_drvdata(pci); + struct skl *skl = bus_to_skl(bus); struct hdac_ext_link *hlink = NULL; int ret; @@ -374,32 +364,32 @@ static int skl_resume(struct device *dev) */ if (skl->supend_active) { pci_restore_state(pci); - snd_hdac_ext_bus_link_power_up_all(ebus); + snd_hdac_ext_bus_link_power_up_all(bus); disable_irq_wake(bus->irq); /* * turn On the links which are On before active suspend * and start the CORB/RIRB DMA if On before * active suspend. */ - list_for_each_entry(hlink, &ebus->hlink_list, list) { + list_for_each_entry(hlink, &bus->hlink_list, list) { if (hlink->ref_count) snd_hdac_ext_bus_link_power_up(hlink); } - if (ebus->cmd_dma_state) - snd_hdac_bus_init_cmd_io(&ebus->bus); ret = 0; + if (bus->cmd_dma_state) + snd_hdac_bus_init_cmd_io(bus); } else { - ret = _skl_resume(ebus); + ret = _skl_resume(bus); /* turn off the links which are off before suspend */ - list_for_each_entry(hlink, &ebus->hlink_list, list) { + list_for_each_entry(hlink, &bus->hlink_list, list) { if (!hlink->ref_count) snd_hdac_ext_bus_link_power_down(hlink); } - if (!ebus->cmd_dma_state) - snd_hdac_bus_stop_cmd_io(&ebus->bus); + if (!bus->cmd_dma_state) + snd_hdac_bus_stop_cmd_io(bus); } return ret; @@ -410,23 +400,21 @@ static int skl_resume(struct device *dev) static int skl_runtime_suspend(struct device *dev) { struct pci_dev *pci = to_pci_dev(dev); - struct hdac_ext_bus *ebus = pci_get_drvdata(pci); - struct hdac_bus *bus = ebus_to_hbus(ebus); + struct hdac_bus *bus = pci_get_drvdata(pci); dev_dbg(bus->dev, "in %s\n", __func__); - return _skl_suspend(ebus); + return _skl_suspend(bus); } static int skl_runtime_resume(struct device *dev) { struct pci_dev *pci = to_pci_dev(dev); - struct hdac_ext_bus *ebus = pci_get_drvdata(pci); - struct hdac_bus *bus = ebus_to_hbus(ebus); + struct hdac_bus *bus = pci_get_drvdata(pci); dev_dbg(bus->dev, "in %s\n", __func__); - return _skl_resume(ebus); + return _skl_resume(bus); } #endif /* CONFIG_PM */ @@ -439,20 +427,19 @@ static const struct dev_pm_ops skl_pm = { /* * destructor */ -static int skl_free(struct hdac_ext_bus *ebus) +static int skl_free(struct hdac_bus *bus) { - struct skl *skl = ebus_to_skl(ebus); - struct hdac_bus *bus = ebus_to_hbus(ebus); + struct skl *skl = bus_to_skl(bus); skl->init_done = 0; /* to be sure */ - snd_hdac_ext_stop_streams(ebus); + snd_hdac_ext_stop_streams(bus); if (bus->irq >= 0) - free_irq(bus->irq, (void *)ebus); + free_irq(bus->irq, (void *)bus); snd_hdac_bus_free_stream_pages(bus); - snd_hdac_stream_free_all(ebus); - snd_hdac_link_free_all(ebus); + snd_hdac_stream_free_all(bus); + snd_hdac_link_free_all(bus); if (bus->remap_addr) iounmap(bus->remap_addr); @@ -460,11 +447,11 @@ static int skl_free(struct hdac_ext_bus *ebus) pci_release_regions(skl->pci); pci_disable_device(skl->pci); - snd_hdac_ext_bus_exit(ebus); + snd_hdac_ext_bus_exit(bus); cancel_work_sync(&skl->probe_work); if (IS_ENABLED(CONFIG_SND_SOC_HDAC_HDMI)) - snd_hdac_i915_exit(&ebus->bus); + snd_hdac_i915_exit(bus); return 0; } @@ -488,8 +475,8 @@ static struct skl_ssp_clk skl_ssp_clks[] = { static int skl_find_machine(struct skl *skl, void *driver_data) { + struct hdac_bus *bus = skl_to_bus(skl); struct snd_soc_acpi_mach *mach = driver_data; - struct hdac_bus *bus = ebus_to_hbus(&skl->ebus); struct skl_machine_pdata *pdata; mach = snd_soc_acpi_find_machine(mach); @@ -510,7 +497,7 @@ static int skl_find_machine(struct skl *skl, void *driver_data) static int skl_machine_device_register(struct skl *skl) { - struct hdac_bus *bus = ebus_to_hbus(&skl->ebus); + struct hdac_bus *bus = skl_to_bus(skl); struct snd_soc_acpi_mach *mach = skl->mach; struct platform_device *pdev; int ret; @@ -544,7 +531,7 @@ static void skl_machine_device_unregister(struct skl *skl) static int skl_dmic_device_register(struct skl *skl) { - struct hdac_bus *bus = ebus_to_hbus(&skl->ebus); + struct hdac_bus *bus = skl_to_bus(skl); struct platform_device *pdev; int ret; @@ -643,9 +630,8 @@ static void skl_clock_device_unregister(struct skl *skl) /* * Probe the given codec address */ -static int probe_codec(struct hdac_ext_bus *ebus, int addr) +static int probe_codec(struct hdac_bus *bus, int addr) { - struct hdac_bus *bus = ebus_to_hbus(ebus); unsigned int cmd = (addr << 28) | (AC_NODE_ROOT << 20) | (AC_VERB_PARAMETERS << 8) | AC_PAR_VENDOR_ID; unsigned int res = -1; @@ -658,13 +644,12 @@ static int probe_codec(struct hdac_ext_bus *ebus, int addr) return -EIO; dev_dbg(bus->dev, "codec #%d probed OK\n", addr); - return snd_hdac_ext_bus_device_init(ebus, addr); + return snd_hdac_ext_bus_device_init(bus, addr); } /* Codec initialization */ -static void skl_codec_create(struct hdac_ext_bus *ebus) +static void skl_codec_create(struct hdac_bus *bus) { - struct hdac_bus *bus = ebus_to_hbus(ebus); int c, max_slots; max_slots = HDA_MAX_CODECS; @@ -672,7 +657,7 @@ static void skl_codec_create(struct hdac_ext_bus *ebus) /* First try to probe all given codec slots */ for (c = 0; c < max_slots; c++) { if ((bus->codec_mask & (1 << c))) { - if (probe_codec(ebus, c) < 0) { + if (probe_codec(bus, c) < 0) { /* * Some BIOSen give you wrong codec addresses * that don't exist @@ -722,8 +707,7 @@ static int skl_i915_init(struct hdac_bus *bus) static void skl_probe_work(struct work_struct *work) { struct skl *skl = container_of(work, struct skl, probe_work); - struct hdac_ext_bus *ebus = &skl->ebus; - struct hdac_bus *bus = ebus_to_hbus(ebus); + struct hdac_bus *bus = skl_to_bus(skl); struct hdac_ext_link *hlink = NULL; int err; @@ -744,7 +728,7 @@ static void skl_probe_work(struct work_struct *work) dev_info(bus->dev, "no hda codecs found!\n"); /* create codec instances */ - skl_codec_create(ebus); + skl_codec_create(bus); /* register platform dai and controls */ err = skl_platform_register(bus->dev); @@ -773,8 +757,8 @@ static void skl_probe_work(struct work_struct *work) /* * we are done probing so decrement link counts */ - list_for_each_entry(hlink, &ebus->hlink_list, list) - snd_hdac_ext_bus_link_put(ebus, hlink); + list_for_each_entry(hlink, &bus->hlink_list, list) + snd_hdac_ext_bus_link_put(bus, hlink); /* configure PM */ pm_runtime_put_noidle(bus->dev); @@ -796,7 +780,7 @@ static int skl_create(struct pci_dev *pci, struct skl **rskl) { struct skl *skl; - struct hdac_ext_bus *ebus; + struct hdac_bus *bus; int err; @@ -811,23 +795,22 @@ static int skl_create(struct pci_dev *pci, pci_disable_device(pci); return -ENOMEM; } - ebus = &skl->ebus; - snd_hdac_ext_bus_init(ebus, &pci->dev, &bus_core_ops, io_ops); - ebus->bus.use_posbuf = 1; + + bus = skl_to_bus(skl); + snd_hdac_ext_bus_init(bus, &pci->dev, &bus_core_ops, io_ops); + bus->use_posbuf = 1; skl->pci = pci; INIT_WORK(&skl->probe_work, skl_probe_work); - - ebus->bus.bdl_pos_adj = 0; + bus->bdl_pos_adj = 0; *rskl = skl; return 0; } -static int skl_first_init(struct hdac_ext_bus *ebus) +static int skl_first_init(struct hdac_bus *bus) { - struct skl *skl = ebus_to_skl(ebus); - struct hdac_bus *bus = ebus_to_hbus(ebus); + struct skl *skl = bus_to_skl(bus); struct pci_dev *pci = skl->pci; int err; unsigned short gcap; @@ -848,7 +831,7 @@ static int skl_first_init(struct hdac_ext_bus *ebus) snd_hdac_bus_parse_capabilities(bus); - if (skl_acquire_irq(ebus, 0) < 0) + if (skl_acquire_irq(bus, 0) < 0) return -EBUSY; pci_set_master(pci); @@ -872,14 +855,14 @@ static int skl_first_init(struct hdac_ext_bus *ebus) if (!pb_streams && !cp_streams) return -EIO; - ebus->num_streams = cp_streams + pb_streams; + bus->num_streams = cp_streams + pb_streams; /* initialize streams */ snd_hdac_ext_stream_init_all - (ebus, 0, cp_streams, SNDRV_PCM_STREAM_CAPTURE); + (bus, 0, cp_streams, SNDRV_PCM_STREAM_CAPTURE); start_idx = cp_streams; snd_hdac_ext_stream_init_all - (ebus, start_idx, pb_streams, SNDRV_PCM_STREAM_PLAYBACK); + (bus, start_idx, pb_streams, SNDRV_PCM_STREAM_PLAYBACK); err = snd_hdac_bus_alloc_stream_pages(bus); if (err < 0) @@ -895,7 +878,6 @@ static int skl_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) { struct skl *skl; - struct hdac_ext_bus *ebus = NULL; struct hdac_bus *bus = NULL; int err; @@ -904,10 +886,9 @@ static int skl_probe(struct pci_dev *pci, if (err < 0) return err; - ebus = &skl->ebus; - bus = ebus_to_hbus(ebus); + bus = skl_to_bus(skl); - err = skl_first_init(ebus); + err = skl_first_init(bus); if (err < 0) goto out_free; @@ -928,7 +909,7 @@ static int skl_probe(struct pci_dev *pci, skl_nhlt_update_topology_bin(skl); - pci_set_drvdata(skl->pci, ebus); + pci_set_drvdata(skl->pci, bus); skl_dmic_data.dmic_num = skl_get_dmic_geo(skl); @@ -952,7 +933,7 @@ static int skl_probe(struct pci_dev *pci, skl->skl_sst->clock_power_gating = skl_clock_power_gating; } if (bus->mlcap) - snd_hdac_ext_bus_get_ml_capabilities(ebus); + snd_hdac_ext_bus_get_ml_capabilities(bus); snd_hdac_bus_stop_chip(bus); @@ -972,31 +953,30 @@ out_clk_free: out_nhlt_free: skl_nhlt_free(skl->nhlt); out_free: - skl_free(ebus); + skl_free(bus); return err; } static void skl_shutdown(struct pci_dev *pci) { - struct hdac_ext_bus *ebus = pci_get_drvdata(pci); - struct hdac_bus *bus = ebus_to_hbus(ebus); + struct hdac_bus *bus = pci_get_drvdata(pci); struct hdac_stream *s; struct hdac_ext_stream *stream; struct skl *skl; - if (ebus == NULL) + if (!bus) return; - skl = ebus_to_skl(ebus); + skl = bus_to_skl(bus); if (!skl->init_done) return; - snd_hdac_ext_stop_streams(ebus); + snd_hdac_ext_stop_streams(bus); list_for_each_entry(s, &bus->stream_list, list) { stream = stream_to_hdac_ext_stream(s); - snd_hdac_ext_stream_decouple(ebus, stream, false); + snd_hdac_ext_stream_decouple(bus, stream, false); } snd_hdac_bus_stop_chip(bus); @@ -1004,15 +984,15 @@ static void skl_shutdown(struct pci_dev *pci) static void skl_remove(struct pci_dev *pci) { - struct hdac_ext_bus *ebus = pci_get_drvdata(pci); - struct skl *skl = ebus_to_skl(ebus); + struct hdac_bus *bus = pci_get_drvdata(pci); + struct skl *skl = bus_to_skl(bus); release_firmware(skl->tplg); pm_runtime_get_noresume(&pci->dev); /* codec removal, invoke bus_device_remove */ - snd_hdac_ext_bus_device_remove(ebus); + snd_hdac_ext_bus_device_remove(bus); skl->debugfs = NULL; skl_platform_unregister(&pci->dev); @@ -1022,7 +1002,7 @@ static void skl_remove(struct pci_dev *pci) skl_clock_device_unregister(skl); skl_nhlt_remove_sysfs(skl); skl_nhlt_free(skl->nhlt); - skl_free(ebus); + skl_free(bus); dev_set_drvdata(&pci->dev, NULL); } diff --git a/sound/soc/intel/skylake/skl.h b/sound/soc/intel/skylake/skl.h index 0d5375cbcf6e..78aa8bdcb619 100644 --- a/sound/soc/intel/skylake/skl.h +++ b/sound/soc/intel/skylake/skl.h @@ -71,7 +71,7 @@ struct skl_fw_config { }; struct skl { - struct hdac_ext_bus ebus; + struct hdac_bus hbus; struct pci_dev *pci; unsigned int init_done:1; /* delayed init status */ @@ -105,9 +105,8 @@ struct skl { struct snd_soc_acpi_mach *mach; }; -#define skl_to_ebus(s) (&(s)->ebus) -#define ebus_to_skl(sbus) \ - container_of(sbus, struct skl, sbus) +#define skl_to_bus(s) (&(s)->hbus) +#define bus_to_skl(bus) container_of(bus, struct skl, hbus) /* to pass dai dma data */ struct skl_dma_params { -- cgit v1.2.3 From e1df9317cbb192582ed7aa88c5f294c2336a3c75 Mon Sep 17 00:00:00 2001 From: Rakesh Ughreja Date: Fri, 1 Jun 2018 22:53:51 -0500 Subject: ALSA: hdac: Remove usage of struct hdac_ext_driver, use hdac_driver instead This patch removes the hdac_ext_driver structure. The legacy and enhanced HDaudio capabilities can be handled in a backward-compatible way without separate definitions. Signed-off-by: Rakesh Ughreja Signed-off-by: Takashi Iwai --- include/sound/hdaudio.h | 5 +++++ include/sound/hdaudio_ext.h | 17 ++--------------- sound/hda/ext/hdac_ext_bus.c | 30 ++++++++++++++---------------- sound/soc/codecs/hdac_hdmi.c | 12 +++++------- 4 files changed, 26 insertions(+), 38 deletions(-) (limited to 'include') diff --git a/include/sound/hdaudio.h b/include/sound/hdaudio.h index 9735b51aef08..59ffe63cf194 100644 --- a/include/sound/hdaudio.h +++ b/include/sound/hdaudio.h @@ -188,6 +188,11 @@ struct hdac_driver { const struct hda_device_id *id_table; int (*match)(struct hdac_device *dev, struct hdac_driver *drv); void (*unsol_event)(struct hdac_device *dev, unsigned int event); + + /* fields used by ext bus APIs */ + int (*probe)(struct hdac_device *dev); + int (*remove)(struct hdac_device *dev); + void (*shutdown)(struct hdac_device *dev); }; #define drv_to_hdac_driver(_drv) container_of(_drv, struct hdac_driver, driver) diff --git a/include/sound/hdaudio_ext.h b/include/sound/hdaudio_ext.h index e5b0cd1ade19..3c302477750b 100644 --- a/include/sound/hdaudio_ext.h +++ b/include/sound/hdaudio_ext.h @@ -160,20 +160,7 @@ struct hdac_ext_dma_params { u8 stream_tag; }; -/* - * HD-audio codec base driver - */ -struct hdac_ext_driver { - struct hdac_driver hdac; - - int (*probe)(struct hdac_device *dev); - int (*remove)(struct hdac_device *dev); - void (*shutdown)(struct hdac_device *dev); -}; - -int snd_hda_ext_driver_register(struct hdac_ext_driver *drv); -void snd_hda_ext_driver_unregister(struct hdac_ext_driver *drv); - -#define to_ehdac_driver(_drv) container_of(_drv, struct hdac_ext_driver, hdac) +int snd_hda_ext_driver_register(struct hdac_driver *drv); +void snd_hda_ext_driver_unregister(struct hdac_driver *drv); #endif /* __SOUND_HDAUDIO_EXT_H */ diff --git a/sound/hda/ext/hdac_ext_bus.c b/sound/hda/ext/hdac_ext_bus.c index 77547ede9ae8..52f07766fff3 100644 --- a/sound/hda/ext/hdac_ext_bus.c +++ b/sound/hda/ext/hdac_ext_bus.c @@ -200,12 +200,10 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_device_remove); #define dev_to_hdac(dev) (container_of((dev), \ struct hdac_device, dev)) -static inline struct hdac_ext_driver *get_edrv(struct device *dev) +static inline struct hdac_driver *get_hdrv(struct device *dev) { struct hdac_driver *hdrv = drv_to_hdac_driver(dev->driver); - struct hdac_ext_driver *edrv = to_ehdac_driver(hdrv); - - return edrv; + return hdrv; } static inline struct hdac_device *get_hdev(struct device *dev) @@ -216,17 +214,17 @@ static inline struct hdac_device *get_hdev(struct device *dev) static int hda_ext_drv_probe(struct device *dev) { - return (get_edrv(dev))->probe(get_hdev(dev)); + return (get_hdrv(dev))->probe(get_hdev(dev)); } static int hdac_ext_drv_remove(struct device *dev) { - return (get_edrv(dev))->remove(get_hdev(dev)); + return (get_hdrv(dev))->remove(get_hdev(dev)); } static void hdac_ext_drv_shutdown(struct device *dev) { - return (get_edrv(dev))->shutdown(get_hdev(dev)); + return (get_hdrv(dev))->shutdown(get_hdev(dev)); } /** @@ -234,20 +232,20 @@ static void hdac_ext_drv_shutdown(struct device *dev) * * @drv: ext hda driver structure */ -int snd_hda_ext_driver_register(struct hdac_ext_driver *drv) +int snd_hda_ext_driver_register(struct hdac_driver *drv) { - drv->hdac.type = HDA_DEV_ASOC; - drv->hdac.driver.bus = &snd_hda_bus_type; + drv->type = HDA_DEV_ASOC; + drv->driver.bus = &snd_hda_bus_type; /* we use default match */ if (drv->probe) - drv->hdac.driver.probe = hda_ext_drv_probe; + drv->driver.probe = hda_ext_drv_probe; if (drv->remove) - drv->hdac.driver.remove = hdac_ext_drv_remove; + drv->driver.remove = hdac_ext_drv_remove; if (drv->shutdown) - drv->hdac.driver.shutdown = hdac_ext_drv_shutdown; + drv->driver.shutdown = hdac_ext_drv_shutdown; - return driver_register(&drv->hdac.driver); + return driver_register(&drv->driver); } EXPORT_SYMBOL_GPL(snd_hda_ext_driver_register); @@ -256,8 +254,8 @@ EXPORT_SYMBOL_GPL(snd_hda_ext_driver_register); * * @drv: ext hda driver structure */ -void snd_hda_ext_driver_unregister(struct hdac_ext_driver *drv) +void snd_hda_ext_driver_unregister(struct hdac_driver *drv) { - driver_unregister(&drv->hdac.driver); + driver_unregister(&drv->driver); } EXPORT_SYMBOL_GPL(snd_hda_ext_driver_unregister); diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c index c3ccc8d9c91d..3e3a2a9ef310 100644 --- a/sound/soc/codecs/hdac_hdmi.c +++ b/sound/soc/codecs/hdac_hdmi.c @@ -2186,14 +2186,12 @@ static const struct hda_device_id hdmi_list[] = { MODULE_DEVICE_TABLE(hdaudio, hdmi_list); -static struct hdac_ext_driver hdmi_driver = { - . hdac = { - .driver = { - .name = "HDMI HDA Codec", - .pm = &hdac_hdmi_pm, - }, - .id_table = hdmi_list, +static struct hdac_driver hdmi_driver = { + .driver = { + .name = "HDMI HDA Codec", + .pm = &hdac_hdmi_pm, }, + .id_table = hdmi_list, .probe = hdac_hdmi_dev_probe, .remove = hdac_hdmi_dev_remove, }; -- cgit v1.2.3 From 6298542fa33b6ba0e3effbace5b99b70b93ed9ae Mon Sep 17 00:00:00 2001 From: Rakesh Ughreja Date: Fri, 1 Jun 2018 22:53:57 -0500 Subject: ALSA: hdac: remove memory allocation from snd_hdac_ext_bus_device_init Remove memory allocation within snd_hdac_ext_bus_device_init, to make its behaviour identical to snd_hdac_bus_device_init. So that caller can allocate the parent data structure containing hdac_device. This API change helps in reusing the legacy HDA codec drivers with ASoC platform drivers. Signed-off-by: Rakesh Ughreja Signed-off-by: Pierre-Louis Bossart Signed-off-by: Takashi Iwai --- include/sound/hdaudio_ext.h | 3 ++- sound/hda/ext/hdac_ext_bus.c | 8 ++------ sound/soc/intel/skylake/skl.c | 8 +++++++- 3 files changed, 11 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/sound/hdaudio_ext.h b/include/sound/hdaudio_ext.h index 3c302477750b..c188b801239f 100644 --- a/include/sound/hdaudio_ext.h +++ b/include/sound/hdaudio_ext.h @@ -9,7 +9,8 @@ int snd_hdac_ext_bus_init(struct hdac_bus *bus, struct device *dev, const struct hdac_io_ops *io_ops); void snd_hdac_ext_bus_exit(struct hdac_bus *bus); -int snd_hdac_ext_bus_device_init(struct hdac_bus *bus, int addr); +int snd_hdac_ext_bus_device_init(struct hdac_bus *bus, int addr, + struct hdac_device *hdev); void snd_hdac_ext_bus_device_exit(struct hdac_device *hdev); void snd_hdac_ext_bus_device_remove(struct hdac_bus *bus); diff --git a/sound/hda/ext/hdac_ext_bus.c b/sound/hda/ext/hdac_ext_bus.c index 52f07766fff3..1eb58244688e 100644 --- a/sound/hda/ext/hdac_ext_bus.c +++ b/sound/hda/ext/hdac_ext_bus.c @@ -135,16 +135,12 @@ static void default_release(struct device *dev) * * Returns zero for success or a negative error code. */ -int snd_hdac_ext_bus_device_init(struct hdac_bus *bus, int addr) +int snd_hdac_ext_bus_device_init(struct hdac_bus *bus, int addr, + struct hdac_device *hdev) { - struct hdac_device *hdev = NULL; char name[15]; int ret; - hdev = kzalloc(sizeof(*hdev), GFP_KERNEL); - if (!hdev) - return -ENOMEM; - hdev->bus = bus; snprintf(name, sizeof(name), "ehdaudio%dD%d", bus->idx, addr); diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c index 9c5a701d68ac..3a7f5eb4902b 100644 --- a/sound/soc/intel/skylake/skl.c +++ b/sound/soc/intel/skylake/skl.c @@ -635,6 +635,8 @@ static int probe_codec(struct hdac_bus *bus, int addr) unsigned int cmd = (addr << 28) | (AC_NODE_ROOT << 20) | (AC_VERB_PARAMETERS << 8) | AC_PAR_VENDOR_ID; unsigned int res = -1; + struct skl *skl = bus_to_skl(bus); + struct hdac_device *hdev; mutex_lock(&bus->cmd_mutex); snd_hdac_bus_send_cmd(bus, cmd); @@ -644,7 +646,11 @@ static int probe_codec(struct hdac_bus *bus, int addr) return -EIO; dev_dbg(bus->dev, "codec #%d probed OK\n", addr); - return snd_hdac_ext_bus_device_init(bus, addr); + hdev = devm_kzalloc(&skl->pci->dev, sizeof(*hdev), GFP_KERNEL); + if (!hdev) + return -ENOMEM; + + return snd_hdac_ext_bus_device_init(bus, addr, hdev); } /* Codec initialization */ -- cgit v1.2.3 From cb04ba33187ca571142b67c2fb60d0a8c24994c8 Mon Sep 17 00:00:00 2001 From: Rakesh Ughreja Date: Fri, 1 Jun 2018 22:53:58 -0500 Subject: ALSA: hdac: add extended ops in the hdac_bus Add extended ops in the hdac_bus to allow calling the ASoC HDAC library ops to reuse the legacy HDA codec drivers with ASoC framework. Extended ops are used by the legacy codec drivers to call into hdac_hda library, in the subsequent patches.. Signed-off-by: Rakesh Ughreja Signed-off-by: Pierre-Louis Bossart Signed-off-by: Takashi Iwai --- include/sound/hdaudio.h | 9 +++++++++ include/sound/hdaudio_ext.h | 3 ++- sound/hda/ext/hdac_ext_bus.c | 4 +++- sound/soc/intel/skylake/skl.c | 2 +- 4 files changed, 15 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/sound/hdaudio.h b/include/sound/hdaudio.h index 59ffe63cf194..f1baaa88e766 100644 --- a/include/sound/hdaudio.h +++ b/include/sound/hdaudio.h @@ -213,6 +213,14 @@ struct hdac_bus_ops { int (*link_power)(struct hdac_bus *bus, bool enable); }; +/* + * ops used for ASoC HDA codec drivers + */ +struct hdac_ext_bus_ops { + int (*hdev_attach)(struct hdac_device *hdev); + int (*hdev_detach)(struct hdac_device *hdev); +}; + /* * Lowlevel I/O operators */ @@ -265,6 +273,7 @@ struct hdac_bus { struct device *dev; const struct hdac_bus_ops *ops; const struct hdac_io_ops *io_ops; + const struct hdac_ext_bus_ops *ext_ops; /* h/w resources */ unsigned long addr; diff --git a/include/sound/hdaudio_ext.h b/include/sound/hdaudio_ext.h index c188b801239f..f34aced69ca8 100644 --- a/include/sound/hdaudio_ext.h +++ b/include/sound/hdaudio_ext.h @@ -6,7 +6,8 @@ int snd_hdac_ext_bus_init(struct hdac_bus *bus, struct device *dev, const struct hdac_bus_ops *ops, - const struct hdac_io_ops *io_ops); + const struct hdac_io_ops *io_ops, + const struct hdac_ext_bus_ops *ext_ops); void snd_hdac_ext_bus_exit(struct hdac_bus *bus); int snd_hdac_ext_bus_device_init(struct hdac_bus *bus, int addr, diff --git a/sound/hda/ext/hdac_ext_bus.c b/sound/hda/ext/hdac_ext_bus.c index 1eb58244688e..9c37d9af3023 100644 --- a/sound/hda/ext/hdac_ext_bus.c +++ b/sound/hda/ext/hdac_ext_bus.c @@ -89,7 +89,8 @@ static const struct hdac_io_ops hdac_ext_default_io = { */ int snd_hdac_ext_bus_init(struct hdac_bus *bus, struct device *dev, const struct hdac_bus_ops *ops, - const struct hdac_io_ops *io_ops) + const struct hdac_io_ops *io_ops, + const struct hdac_ext_bus_ops *ext_ops) { int ret; static int idx; @@ -102,6 +103,7 @@ int snd_hdac_ext_bus_init(struct hdac_bus *bus, struct device *dev, if (ret < 0) return ret; + bus->ext_ops = ext_ops; INIT_LIST_HEAD(&bus->hlink_list); bus->idx = idx++; diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c index 3a7f5eb4902b..00e051467a40 100644 --- a/sound/soc/intel/skylake/skl.c +++ b/sound/soc/intel/skylake/skl.c @@ -803,7 +803,7 @@ static int skl_create(struct pci_dev *pci, } bus = skl_to_bus(skl); - snd_hdac_ext_bus_init(bus, &pci->dev, &bus_core_ops, io_ops); + snd_hdac_ext_bus_init(bus, &pci->dev, &bus_core_ops, io_ops, NULL); bus->use_posbuf = 1; skl->pci = pci; INIT_WORK(&skl->probe_work, skl_probe_work); -- cgit v1.2.3 From 653d500ccaadd76ccade9f07469cdc66759315b6 Mon Sep 17 00:00:00 2001 From: Pavel Machek Date: Sun, 6 May 2018 04:06:07 -0400 Subject: media: i2c: lm3560: add support for lm3559 chip Add support for LM3559, as found in Motorola Droid 4 phone, for example. SW interface seems to be identical. Signed-off-by: Pavel Machek Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/media/i2c/lm3560.c | 3 ++- include/media/i2c/lm3560.h | 1 + 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/media/i2c/lm3560.c b/drivers/media/i2c/lm3560.c index b600e03aa94b..49c6644cbba7 100644 --- a/drivers/media/i2c/lm3560.c +++ b/drivers/media/i2c/lm3560.c @@ -1,6 +1,6 @@ /* * drivers/media/i2c/lm3560.c - * General device driver for TI lm3560, FLASH LED Driver + * General device driver for TI lm3559, lm3560, FLASH LED Driver * * Copyright (C) 2013 Texas Instruments * @@ -465,6 +465,7 @@ static int lm3560_remove(struct i2c_client *client) } static const struct i2c_device_id lm3560_id_table[] = { + {LM3559_NAME, 0}, {LM3560_NAME, 0}, {} }; diff --git a/include/media/i2c/lm3560.h b/include/media/i2c/lm3560.h index a5bd310c9e1e..0e2b1c751a5d 100644 --- a/include/media/i2c/lm3560.h +++ b/include/media/i2c/lm3560.h @@ -22,6 +22,7 @@ #include +#define LM3559_NAME "lm3559" #define LM3560_NAME "lm3560" #define LM3560_I2C_ADDR (0x53) -- cgit v1.2.3 From aa2f88712718d045855acc6686dbce6a7286d010 Mon Sep 17 00:00:00 2001 From: Niklas Söderlund Date: Thu, 17 May 2018 10:30:15 -0400 Subject: media: v4l2-ioctl: create helper to fill in v4l2_standard for ENUMSTD MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Prepare for adding a new IOCTL VIDIOC_SUBDEV_ENUMSTD which would enumerate the standards for a subdevice by breaking out the code which could be shared between the video and subdevice versions of this IOCTL. Signed-off-by: Niklas Söderlund Signed-off-by: Hans Verkuil [hans.verkuil@cisco.com: fixed 'sdandard' typos in v4l2-ioctl.h] Signed-off-by: Mauro Carvalho Chehab --- drivers/media/v4l2-core/v4l2-ioctl.c | 66 ++++++++++++++++++++---------------- include/media/v4l2-ioctl.h | 15 ++++++-- 2 files changed, 50 insertions(+), 31 deletions(-) (limited to 'include') diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index dd210067151f..eeed14468a17 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -125,6 +125,42 @@ int v4l2_video_std_construct(struct v4l2_standard *vs, } EXPORT_SYMBOL(v4l2_video_std_construct); +/* Fill in the fields of a v4l2_standard structure according to the + * 'id' and 'vs->index' parameters. Returns negative on error. */ +int v4l_video_std_enumstd(struct v4l2_standard *vs, v4l2_std_id id) +{ + v4l2_std_id curr_id = 0; + unsigned int index = vs->index, i, j = 0; + const char *descr = ""; + + /* Return -ENODATA if the id for the current input + or output is 0, meaning that it doesn't support this API. */ + if (id == 0) + return -ENODATA; + + /* Return norm array in a canonical way */ + for (i = 0; i <= index && id; i++) { + /* last std value in the standards array is 0, so this + while always ends there since (id & 0) == 0. */ + while ((id & standards[j].std) != standards[j].std) + j++; + curr_id = standards[j].std; + descr = standards[j].descr; + j++; + if (curr_id == 0) + break; + if (curr_id != V4L2_STD_PAL && + curr_id != V4L2_STD_SECAM && + curr_id != V4L2_STD_NTSC) + id &= ~curr_id; + } + if (i <= index) + return -EINVAL; + + v4l2_video_std_construct(vs, curr_id, descr); + return 0; +} + /* ----------------------------------------------------------------- */ /* some arrays for pretty-printing debug messages of enum types */ @@ -1753,36 +1789,8 @@ static int v4l_enumstd(const struct v4l2_ioctl_ops *ops, { struct video_device *vfd = video_devdata(file); struct v4l2_standard *p = arg; - v4l2_std_id id = vfd->tvnorms, curr_id = 0; - unsigned int index = p->index, i, j = 0; - const char *descr = ""; - - /* Return -ENODATA if the tvnorms for the current input - or output is 0, meaning that it doesn't support this API. */ - if (id == 0) - return -ENODATA; - /* Return norm array in a canonical way */ - for (i = 0; i <= index && id; i++) { - /* last std value in the standards array is 0, so this - while always ends there since (id & 0) == 0. */ - while ((id & standards[j].std) != standards[j].std) - j++; - curr_id = standards[j].std; - descr = standards[j].descr; - j++; - if (curr_id == 0) - break; - if (curr_id != V4L2_STD_PAL && - curr_id != V4L2_STD_SECAM && - curr_id != V4L2_STD_NTSC) - id &= ~curr_id; - } - if (i <= index) - return -EINVAL; - - v4l2_video_std_construct(p, curr_id, descr); - return 0; + return v4l_video_std_enumstd(p, vfd->tvnorms); } static int v4l_s_std(const struct v4l2_ioctl_ops *ops, diff --git a/include/media/v4l2-ioctl.h b/include/media/v4l2-ioctl.h index a8dbf5b54b5c..5848d92c30da 100644 --- a/include/media/v4l2-ioctl.h +++ b/include/media/v4l2-ioctl.h @@ -621,7 +621,7 @@ const char *v4l2_norm_to_name(v4l2_std_id id); * v4l2_video_std_frame_period - Ancillary routine that fills a * struct &v4l2_fract pointer with the default framerate fraction. * - * @id: analog TV sdandard ID. + * @id: analog TV standard ID. * @frameperiod: struct &v4l2_fract pointer to be filled * */ @@ -632,7 +632,7 @@ void v4l2_video_std_frame_period(int id, struct v4l2_fract *frameperiod); * a &v4l2_standard structure according to the @id parameter. * * @vs: struct &v4l2_standard pointer to be filled - * @id: analog TV sdandard ID. + * @id: analog TV standard ID. * @name: name of the standard to be used * * .. note:: @@ -642,6 +642,17 @@ void v4l2_video_std_frame_period(int id, struct v4l2_fract *frameperiod); int v4l2_video_std_construct(struct v4l2_standard *vs, int id, const char *name); +/** + * v4l_video_std_enumstd - Ancillary routine that fills in the fields of + * a &v4l2_standard structure according to the @id and @vs->index + * parameters. + * + * @vs: struct &v4l2_standard pointer to be filled. + * @id: analog TV standard ID. + * + */ +int v4l_video_std_enumstd(struct v4l2_standard *vs, v4l2_std_id id); + /** * v4l_printk_ioctl - Ancillary routine that prints the ioctl in a * human-readable format. -- cgit v1.2.3 From d7e913cc58c5f6db5159c72e8f8d1f2be9e2fe2f Mon Sep 17 00:00:00 2001 From: Ezequiel Garcia Date: Thu, 14 Jun 2018 11:34:03 -0400 Subject: media: mem2mem: Remove unused v4l2_m2m_ops .lock/.unlock Commit f1a81afc98e3 ("[media] m2m: fix bad unlock balance") removed the last use of v4l2_m2m_ops.lock and v4l2_m2m_ops.unlock hooks. They are not actually used anymore. Remove them. Signed-off-by: Ezequiel Garcia Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/media/platform/coda/coda-common.c | 26 ++++------------------ drivers/media/platform/m2m-deinterlace.c | 20 ++--------------- drivers/media/platform/mtk-vcodec/mtk_vcodec_dec.c | 18 --------------- drivers/media/platform/mtk-vcodec/mtk_vcodec_enc.c | 16 ------------- drivers/media/platform/mx2_emmaprp.c | 16 ------------- drivers/media/platform/sti/delta/delta-v4l2.c | 18 --------------- drivers/media/platform/ti-vpe/vpe.c | 19 ---------------- include/media/v4l2-mem2mem.h | 6 ----- 8 files changed, 6 insertions(+), 133 deletions(-) (limited to 'include') diff --git a/drivers/media/platform/coda/coda-common.c b/drivers/media/platform/coda/coda-common.c index c7631e117dd3..b86d704ae10c 100644 --- a/drivers/media/platform/coda/coda-common.c +++ b/drivers/media/platform/coda/coda-common.c @@ -1297,28 +1297,10 @@ static void coda_job_abort(void *priv) "Aborting task\n"); } -static void coda_lock(void *m2m_priv) -{ - struct coda_ctx *ctx = m2m_priv; - struct coda_dev *pcdev = ctx->dev; - - mutex_lock(&pcdev->dev_mutex); -} - -static void coda_unlock(void *m2m_priv) -{ - struct coda_ctx *ctx = m2m_priv; - struct coda_dev *pcdev = ctx->dev; - - mutex_unlock(&pcdev->dev_mutex); -} - static const struct v4l2_m2m_ops coda_m2m_ops = { .device_run = coda_device_run, .job_ready = coda_job_ready, .job_abort = coda_job_abort, - .lock = coda_lock, - .unlock = coda_unlock, }; static void set_default_params(struct coda_ctx *ctx) @@ -2092,9 +2074,9 @@ static int coda_open(struct file *file) INIT_LIST_HEAD(&ctx->buffer_meta_list); spin_lock_init(&ctx->buffer_meta_lock); - coda_lock(ctx); + mutex_lock(&dev->dev_mutex); list_add(&ctx->list, &dev->instances); - coda_unlock(ctx); + mutex_unlock(&dev->dev_mutex); v4l2_dbg(1, coda_debug, &dev->v4l2_dev, "Created instance %d (%p)\n", ctx->idx, ctx); @@ -2142,9 +2124,9 @@ static int coda_release(struct file *file) flush_work(&ctx->seq_end_work); } - coda_lock(ctx); + mutex_lock(&dev->dev_mutex); list_del(&ctx->list); - coda_unlock(ctx); + mutex_unlock(&dev->dev_mutex); if (ctx->dev->devtype->product == CODA_DX6) coda_free_aux_buf(dev, &ctx->workbuf); diff --git a/drivers/media/platform/m2m-deinterlace.c b/drivers/media/platform/m2m-deinterlace.c index 3008892eb8dd..a566ec566cec 100644 --- a/drivers/media/platform/m2m-deinterlace.c +++ b/drivers/media/platform/m2m-deinterlace.c @@ -181,20 +181,6 @@ static void deinterlace_job_abort(void *priv) v4l2_m2m_job_finish(pcdev->m2m_dev, ctx->m2m_ctx); } -static void deinterlace_lock(void *priv) -{ - struct deinterlace_ctx *ctx = priv; - struct deinterlace_dev *pcdev = ctx->dev; - mutex_lock(&pcdev->dev_mutex); -} - -static void deinterlace_unlock(void *priv) -{ - struct deinterlace_ctx *ctx = priv; - struct deinterlace_dev *pcdev = ctx->dev; - mutex_unlock(&pcdev->dev_mutex); -} - static void dma_callback(void *data) { struct deinterlace_ctx *curr_ctx = data; @@ -956,9 +942,9 @@ static __poll_t deinterlace_poll(struct file *file, struct deinterlace_ctx *ctx = file->private_data; __poll_t ret; - deinterlace_lock(ctx); + mutex_lock(&ctx->dev->dev_mutex); ret = v4l2_m2m_poll(file, ctx->m2m_ctx, wait); - deinterlace_unlock(ctx); + mutex_unlock(&ctx->dev->dev_mutex); return ret; } @@ -992,8 +978,6 @@ static const struct v4l2_m2m_ops m2m_ops = { .device_run = deinterlace_device_run, .job_ready = deinterlace_job_ready, .job_abort = deinterlace_job_abort, - .lock = deinterlace_lock, - .unlock = deinterlace_unlock, }; static int deinterlace_probe(struct platform_device *pdev) diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec.c b/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec.c index 86f0a7134365..5523edadb86c 100644 --- a/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec.c +++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec.c @@ -1411,28 +1411,10 @@ int mtk_vcodec_dec_ctrls_setup(struct mtk_vcodec_ctx *ctx) return 0; } -static void m2mops_vdec_lock(void *m2m_priv) -{ - struct mtk_vcodec_ctx *ctx = m2m_priv; - - mtk_v4l2_debug(3, "[%d]", ctx->id); - mutex_lock(&ctx->dev->dev_mutex); -} - -static void m2mops_vdec_unlock(void *m2m_priv) -{ - struct mtk_vcodec_ctx *ctx = m2m_priv; - - mtk_v4l2_debug(3, "[%d]", ctx->id); - mutex_unlock(&ctx->dev->dev_mutex); -} - const struct v4l2_m2m_ops mtk_vdec_m2m_ops = { .device_run = m2mops_vdec_device_run, .job_ready = m2mops_vdec_job_ready, .job_abort = m2mops_vdec_job_abort, - .lock = m2mops_vdec_lock, - .unlock = m2mops_vdec_unlock, }; static const struct vb2_ops mtk_vdec_vb2_ops = { diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc.c b/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc.c index 1b1a28abbf1f..6ad408514a99 100644 --- a/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc.c +++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc.c @@ -1181,26 +1181,10 @@ static void m2mops_venc_job_abort(void *priv) ctx->state = MTK_STATE_ABORT; } -static void m2mops_venc_lock(void *m2m_priv) -{ - struct mtk_vcodec_ctx *ctx = m2m_priv; - - mutex_lock(&ctx->dev->dev_mutex); -} - -static void m2mops_venc_unlock(void *m2m_priv) -{ - struct mtk_vcodec_ctx *ctx = m2m_priv; - - mutex_unlock(&ctx->dev->dev_mutex); -} - const struct v4l2_m2m_ops mtk_venc_m2m_ops = { .device_run = m2mops_venc_device_run, .job_ready = m2mops_venc_job_ready, .job_abort = m2mops_venc_job_abort, - .lock = m2mops_venc_lock, - .unlock = m2mops_venc_unlock, }; void mtk_vcodec_enc_set_default_params(struct mtk_vcodec_ctx *ctx) diff --git a/drivers/media/platform/mx2_emmaprp.c b/drivers/media/platform/mx2_emmaprp.c index 2e64729134b2..83b9db895a64 100644 --- a/drivers/media/platform/mx2_emmaprp.c +++ b/drivers/media/platform/mx2_emmaprp.c @@ -250,20 +250,6 @@ static void emmaprp_job_abort(void *priv) v4l2_m2m_job_finish(pcdev->m2m_dev, ctx->m2m_ctx); } -static void emmaprp_lock(void *priv) -{ - struct emmaprp_ctx *ctx = priv; - struct emmaprp_dev *pcdev = ctx->dev; - mutex_lock(&pcdev->dev_mutex); -} - -static void emmaprp_unlock(void *priv) -{ - struct emmaprp_ctx *ctx = priv; - struct emmaprp_dev *pcdev = ctx->dev; - mutex_unlock(&pcdev->dev_mutex); -} - static inline void emmaprp_dump_regs(struct emmaprp_dev *pcdev) { dprintk(pcdev, @@ -885,8 +871,6 @@ static const struct video_device emmaprp_videodev = { static const struct v4l2_m2m_ops m2m_ops = { .device_run = emmaprp_device_run, .job_abort = emmaprp_job_abort, - .lock = emmaprp_lock, - .unlock = emmaprp_unlock, }; static int emmaprp_probe(struct platform_device *pdev) diff --git a/drivers/media/platform/sti/delta/delta-v4l2.c b/drivers/media/platform/sti/delta/delta-v4l2.c index 232d508c5b66..0b42acd4e3a6 100644 --- a/drivers/media/platform/sti/delta/delta-v4l2.c +++ b/drivers/media/platform/sti/delta/delta-v4l2.c @@ -339,22 +339,6 @@ static void register_decoders(struct delta_dev *delta) } } -static void delta_lock(void *priv) -{ - struct delta_ctx *ctx = priv; - struct delta_dev *delta = ctx->dev; - - mutex_lock(&delta->lock); -} - -static void delta_unlock(void *priv) -{ - struct delta_ctx *ctx = priv; - struct delta_dev *delta = ctx->dev; - - mutex_unlock(&delta->lock); -} - static int delta_open_decoder(struct delta_ctx *ctx, u32 streamformat, u32 pixelformat, const struct delta_dec **pdec) { @@ -1099,8 +1083,6 @@ static const struct v4l2_m2m_ops delta_m2m_ops = { .device_run = delta_device_run, .job_ready = delta_job_ready, .job_abort = delta_job_abort, - .lock = delta_lock, - .unlock = delta_unlock, }; /* diff --git a/drivers/media/platform/ti-vpe/vpe.c b/drivers/media/platform/ti-vpe/vpe.c index de968295ca7d..d70871d0ad2d 100644 --- a/drivers/media/platform/ti-vpe/vpe.c +++ b/drivers/media/platform/ti-vpe/vpe.c @@ -953,23 +953,6 @@ static void job_abort(void *priv) ctx->aborting = 1; } -/* - * Lock access to the device - */ -static void vpe_lock(void *priv) -{ - struct vpe_ctx *ctx = priv; - struct vpe_dev *dev = ctx->dev; - mutex_lock(&dev->dev_mutex); -} - -static void vpe_unlock(void *priv) -{ - struct vpe_ctx *ctx = priv; - struct vpe_dev *dev = ctx->dev; - mutex_unlock(&dev->dev_mutex); -} - static void vpe_dump_regs(struct vpe_dev *dev) { #define DUMPREG(r) vpe_dbg(dev, "%-35s %08x\n", #r, read_reg(dev, VPE_##r)) @@ -2434,8 +2417,6 @@ static const struct v4l2_m2m_ops m2m_ops = { .device_run = device_run, .job_ready = job_ready, .job_abort = job_abort, - .lock = vpe_lock, - .unlock = vpe_unlock, }; static int vpe_runtime_get(struct platform_device *pdev) diff --git a/include/media/v4l2-mem2mem.h b/include/media/v4l2-mem2mem.h index 3d07ba3a8262..8f4b208cfee7 100644 --- a/include/media/v4l2-mem2mem.h +++ b/include/media/v4l2-mem2mem.h @@ -40,17 +40,11 @@ * v4l2_m2m_job_finish() (as if the transaction ended normally). * This function does not have to (and will usually not) wait * until the device enters a state when it can be stopped. - * @lock: optional. Define a driver's own lock callback, instead of using - * &v4l2_m2m_ctx->q_lock. - * @unlock: optional. Define a driver's own unlock callback, instead of - * using &v4l2_m2m_ctx->q_lock. */ struct v4l2_m2m_ops { void (*device_run)(void *priv); int (*job_ready)(void *priv); void (*job_abort)(void *priv); - void (*lock)(void *priv); - void (*unlock)(void *priv); }; struct v4l2_m2m_dev; -- cgit v1.2.3 From e1a98c163eb276b5b5e1bece560ed7f0b9eb3b49 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Fri, 15 Jun 2018 09:19:46 -0400 Subject: media: media.h: remove __NEED_MEDIA_LEGACY_API The __NEED_MEDIA_LEGACY_API define is 1) ugly and 2) dangerous since it is all too easy for drivers to define it to get hold of legacy defines. Instead just define what we need in media-device.c which is the only place where we need the legacy define (MEDIA_ENT_T_DEVNODE_UNKNOWN). Signed-off-by: Hans Verkuil Acked-by: Mauro Carvalho Chehab Signed-off-by: Mauro Carvalho Chehab --- drivers/media/media-device.c | 13 ++++++++++--- include/uapi/linux/media.h | 2 +- 2 files changed, 11 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/media/media-device.c b/drivers/media/media-device.c index ae59c3177555..47bb2254fbfd 100644 --- a/drivers/media/media-device.c +++ b/drivers/media/media-device.c @@ -16,9 +16,6 @@ * GNU General Public License for more details. */ -/* We need to access legacy defines from linux/media.h */ -#define __NEED_MEDIA_LEGACY_API - #include #include #include @@ -35,6 +32,16 @@ #ifdef CONFIG_MEDIA_CONTROLLER +/* + * Legacy defines from linux/media.h. This is the only place we need this + * so we just define it here. The media.h header doesn't expose it to the + * kernel to prevent it from being used by drivers, but here (and only here!) + * we need it to handle the legacy behavior. + */ +#define MEDIA_ENT_SUBTYPE_MASK 0x0000ffff +#define MEDIA_ENT_T_DEVNODE_UNKNOWN (MEDIA_ENT_F_OLD_BASE | \ + MEDIA_ENT_SUBTYPE_MASK) + /* ----------------------------------------------------------------------------- * Userspace API */ diff --git a/include/uapi/linux/media.h b/include/uapi/linux/media.h index c7e9a5cba24e..86c7dcc9cba3 100644 --- a/include/uapi/linux/media.h +++ b/include/uapi/linux/media.h @@ -348,7 +348,7 @@ struct media_v2_topology { #define MEDIA_IOC_SETUP_LINK _IOWR('|', 0x03, struct media_link_desc) #define MEDIA_IOC_G_TOPOLOGY _IOWR('|', 0x04, struct media_v2_topology) -#if !defined(__KERNEL__) || defined(__NEED_MEDIA_LEGACY_API) +#ifndef __KERNEL__ /* * Legacy symbols used to avoid userspace compilation breakages. -- cgit v1.2.3 From 0a9fe5c375b57fab6d18ed0a6a7f935eefb09db3 Mon Sep 17 00:00:00 2001 From: Yousuk Seung Date: Wed, 27 Jun 2018 10:32:19 -0700 Subject: netem: slotting with non-uniform distribution Extend slotting with support for non-uniform distributions. This is similar to netem's non-uniform distribution delay feature. Commit f043efeae2f1 ("netem: support delivering packets in delayed time slots") added the slotting feature to approximate the behaviors of media with packet aggregation but only supported a uniform distribution for delays between transmission attempts. Tests with TCP BBR with emulated wifi links with non-uniform distributions produced more useful results. Syntax: slot dist DISTRIBUTION DELAY JITTER [packets MAX_PACKETS] \ [bytes MAX_BYTES] The syntax and use of the distribution table is the same as in the non-uniform distribution delay feature. A file DISTRIBUTION must be present in TC_LIB_DIR (e.g. /usr/lib/tc) containing numbers scaled by NETEM_DIST_SCALE. A random value x is selected from the table and it takes DELAY + ( x * JITTER ) as delay. Correlation between values is not supported. Examples: Normal distribution delay with mean = 800us and stdev = 100us. > tc qdisc add dev eth0 root netem slot dist normal 800us 100us Optionally set the max slot size in bytes and/or packets. > tc qdisc add dev eth0 root netem slot dist normal 800us 100us \ bytes 64k packets 42 Signed-off-by: Yousuk Seung Acked-by: Eric Dumazet Acked-by: Neal Cardwell Signed-off-by: David S. Miller --- include/uapi/linux/pkt_sched.h | 3 ++ net/sched/sch_netem.c | 73 ++++++++++++++++++++++++++++-------------- 2 files changed, 52 insertions(+), 24 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index 37b5096ae97b..bad3c03bcf43 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -539,6 +539,7 @@ enum { TCA_NETEM_LATENCY64, TCA_NETEM_JITTER64, TCA_NETEM_SLOT, + TCA_NETEM_SLOT_DIST, __TCA_NETEM_MAX, }; @@ -581,6 +582,8 @@ struct tc_netem_slot { __s64 max_delay; __s32 max_packets; __s32 max_bytes; + __s64 dist_delay; /* nsec */ + __s64 dist_jitter; /* nsec */ }; enum { diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 7d6801fc5340..ad18a2052416 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -68,6 +68,11 @@ Fabio Ludovici */ +struct disttable { + u32 size; + s16 table[0]; +}; + struct netem_sched_data { /* internal t(ime)fifo qdisc uses t_root and sch->limit */ struct rb_root t_root; @@ -99,10 +104,7 @@ struct netem_sched_data { u32 rho; } delay_cor, loss_cor, dup_cor, reorder_cor, corrupt_cor; - struct disttable { - u32 size; - s16 table[0]; - } *delay_dist; + struct disttable *delay_dist; enum { CLG_RANDOM, @@ -142,6 +144,7 @@ struct netem_sched_data { s32 bytes_left; } slot; + struct disttable *slot_dist; }; /* Time stamp put into socket buffer control block @@ -180,7 +183,7 @@ static u32 get_crandom(struct crndstate *state) u64 value, rho; unsigned long answer; - if (state->rho == 0) /* no correlation */ + if (!state || state->rho == 0) /* no correlation */ return prandom_u32(); value = prandom_u32(); @@ -601,10 +604,19 @@ finish_segs: static void get_slot_next(struct netem_sched_data *q, u64 now) { - q->slot.slot_next = now + q->slot_config.min_delay + - (prandom_u32() * - (q->slot_config.max_delay - - q->slot_config.min_delay) >> 32); + s64 next_delay; + + if (!q->slot_dist) + next_delay = q->slot_config.min_delay + + (prandom_u32() * + (q->slot_config.max_delay - + q->slot_config.min_delay) >> 32); + else + next_delay = tabledist(q->slot_config.dist_delay, + (s32)(q->slot_config.dist_jitter), + NULL, q->slot_dist); + + q->slot.slot_next = now + next_delay; q->slot.packets_left = q->slot_config.max_packets; q->slot.bytes_left = q->slot_config.max_bytes; } @@ -721,9 +733,9 @@ static void dist_free(struct disttable *d) * signed 16 bit values. */ -static int get_dist_table(struct Qdisc *sch, const struct nlattr *attr) +static int get_dist_table(struct Qdisc *sch, struct disttable **tbl, + const struct nlattr *attr) { - struct netem_sched_data *q = qdisc_priv(sch); size_t n = nla_len(attr)/sizeof(__s16); const __s16 *data = nla_data(attr); spinlock_t *root_lock; @@ -744,7 +756,7 @@ static int get_dist_table(struct Qdisc *sch, const struct nlattr *attr) root_lock = qdisc_root_sleeping_lock(sch); spin_lock_bh(root_lock); - swap(q->delay_dist, d); + swap(*tbl, d); spin_unlock_bh(root_lock); dist_free(d); @@ -762,7 +774,8 @@ static void get_slot(struct netem_sched_data *q, const struct nlattr *attr) q->slot_config.max_bytes = INT_MAX; q->slot.packets_left = q->slot_config.max_packets; q->slot.bytes_left = q->slot_config.max_bytes; - if (q->slot_config.min_delay | q->slot_config.max_delay) + if (q->slot_config.min_delay | q->slot_config.max_delay | + q->slot_config.dist_jitter) q->slot.slot_next = ktime_get_ns(); else q->slot.slot_next = 0; @@ -926,16 +939,17 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, } if (tb[TCA_NETEM_DELAY_DIST]) { - ret = get_dist_table(sch, tb[TCA_NETEM_DELAY_DIST]); - if (ret) { - /* recover clg and loss_model, in case of - * q->clg and q->loss_model were modified - * in get_loss_clg() - */ - q->clg = old_clg; - q->loss_model = old_loss_model; - return ret; - } + ret = get_dist_table(sch, &q->delay_dist, + tb[TCA_NETEM_DELAY_DIST]); + if (ret) + goto get_table_failure; + } + + if (tb[TCA_NETEM_SLOT_DIST]) { + ret = get_dist_table(sch, &q->slot_dist, + tb[TCA_NETEM_SLOT_DIST]); + if (ret) + goto get_table_failure; } sch->limit = qopt->limit; @@ -983,6 +997,15 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, get_slot(q, tb[TCA_NETEM_SLOT]); return ret; + +get_table_failure: + /* recover clg and loss_model, in case of + * q->clg and q->loss_model were modified + * in get_loss_clg() + */ + q->clg = old_clg; + q->loss_model = old_loss_model; + return ret; } static int netem_init(struct Qdisc *sch, struct nlattr *opt, @@ -1011,6 +1034,7 @@ static void netem_destroy(struct Qdisc *sch) if (q->qdisc) qdisc_destroy(q->qdisc); dist_free(q->delay_dist); + dist_free(q->slot_dist); } static int dump_loss_model(const struct netem_sched_data *q, @@ -1127,7 +1151,8 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb) if (dump_loss_model(q, skb) != 0) goto nla_put_failure; - if (q->slot_config.min_delay | q->slot_config.max_delay) { + if (q->slot_config.min_delay | q->slot_config.max_delay | + q->slot_config.dist_jitter) { slot = q->slot_config; if (slot.max_packets == INT_MAX) slot.max_packets = 0; -- cgit v1.2.3 From d020d4559de9baf47cafa2669f29ea59d11a914c Mon Sep 17 00:00:00 2001 From: Roman Mashak Date: Wed, 27 Jun 2018 13:33:31 -0400 Subject: net sched actions: fix coding style in pedit headers Fix coding style issues in tc pedit headers detected by the checkpatch script. Reviewed-by: Simon Horman Signed-off-by: Roman Mashak Signed-off-by: David S. Miller --- include/net/tc_act/tc_pedit.h | 1 + include/uapi/linux/tc_act/tc_pedit.h | 9 +++++++-- 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/tc_act/tc_pedit.h b/include/net/tc_act/tc_pedit.h index 227a6f1d02f4..fac3ad4a86de 100644 --- a/include/net/tc_act/tc_pedit.h +++ b/include/net/tc_act/tc_pedit.h @@ -17,6 +17,7 @@ struct tcf_pedit { struct tc_pedit_key *tcfp_keys; struct tcf_pedit_key_ex *tcfp_keys_ex; }; + #define to_pedit(a) ((struct tcf_pedit *)a) static inline bool is_tcf_pedit(const struct tc_action *a) diff --git a/include/uapi/linux/tc_act/tc_pedit.h b/include/uapi/linux/tc_act/tc_pedit.h index 162d1094c41c..24ec792dacc1 100644 --- a/include/uapi/linux/tc_act/tc_pedit.h +++ b/include/uapi/linux/tc_act/tc_pedit.h @@ -17,13 +17,15 @@ enum { TCA_PEDIT_KEY_EX, __TCA_PEDIT_MAX }; + #define TCA_PEDIT_MAX (__TCA_PEDIT_MAX - 1) - + enum { TCA_PEDIT_KEY_EX_HTYPE = 1, TCA_PEDIT_KEY_EX_CMD = 2, __TCA_PEDIT_KEY_EX_MAX }; + #define TCA_PEDIT_KEY_EX_MAX (__TCA_PEDIT_KEY_EX_MAX - 1) /* TCA_PEDIT_KEY_EX_HDR_TYPE_NETWROK is a special case for legacy users. It @@ -38,6 +40,7 @@ enum pedit_header_type { TCA_PEDIT_KEY_EX_HDR_TYPE_UDP = 5, __PEDIT_HDR_TYPE_MAX, }; + #define TCA_PEDIT_HDR_TYPE_MAX (__PEDIT_HDR_TYPE_MAX - 1) enum pedit_cmd { @@ -45,6 +48,7 @@ enum pedit_cmd { TCA_PEDIT_KEY_EX_CMD_ADD = 1, __PEDIT_CMD_MAX, }; + #define TCA_PEDIT_CMD_MAX (__PEDIT_CMD_MAX - 1) struct tc_pedit_key { @@ -55,13 +59,14 @@ struct tc_pedit_key { __u32 offmask; __u32 shift; }; - + struct tc_pedit_sel { tc_gen; unsigned char nkeys; unsigned char flags; struct tc_pedit_key keys[0]; }; + #define tc_pedit tc_pedit_sel #endif -- cgit v1.2.3 From 83d83bebf40132e2d55ec58af666713cc76f9764 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Thu, 28 Jun 2018 15:20:30 +0200 Subject: console/fbcon: Add support for deferred console takeover Currently fbcon claims fbdevs as soon as they are registered and takes over the console as soon as the first fbdev gets registered. This behavior is undesirable in cases where a smooth graphical bootup is desired, in such cases we typically want the contents of the framebuffer (typically a vendor logo) to stay in place as is. The current solution for this problem (on embedded systems) is to not enable fbcon. This commit adds a new FRAMEBUFFER_CONSOLE_DEFERRED_TAKEOVER config option, which when enabled defers fbcon taking over the console from the dummy console until the first text is displayed on the console. Together with the "quiet" kernel commandline option, this allows fbcon to still be used together with a smooth graphical bootup, having it take over the console as soon as e.g. an error message is logged. Note the choice to detect the first console output in the dummycon driver, rather then handling this entirely inside the fbcon code, was made after 2 failed attempts to handle this entirely inside the fbcon code. The fbcon code is woven quite tightly into the console code, making this to only feasible option. Reviewed-by: Daniel Vetter Signed-off-by: Hans de Goede Signed-off-by: Bartlomiej Zolnierkiewicz --- Documentation/fb/fbcon.txt | 7 ++++ drivers/video/console/Kconfig | 11 ++++++ drivers/video/console/dummycon.c | 67 ++++++++++++++++++++++++++++++++----- drivers/video/fbdev/core/fbcon.c | 72 ++++++++++++++++++++++++++++++++++++++++ include/linux/console.h | 5 +++ 5 files changed, 154 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/Documentation/fb/fbcon.txt b/Documentation/fb/fbcon.txt index 79c22d096bbc..d4d642e1ce9c 100644 --- a/Documentation/fb/fbcon.txt +++ b/Documentation/fb/fbcon.txt @@ -155,6 +155,13 @@ C. Boot options used by text. By default, this area will be black. The 'color' value is an integer number that depends on the framebuffer driver being used. +6. fbcon=nodefer + + If the kernel is compiled with deferred fbcon takeover support, normally + the framebuffer contents, left in place by the firmware/bootloader, will + be preserved until there actually is some text is output to the console. + This option causes fbcon to bind immediately to the fbdev device. + C. Attaching, Detaching and Unloading Before going on how to attach, detach and unload the framebuffer console, an diff --git a/drivers/video/console/Kconfig b/drivers/video/console/Kconfig index 4110ba7d7ca9..e91edef98633 100644 --- a/drivers/video/console/Kconfig +++ b/drivers/video/console/Kconfig @@ -150,6 +150,17 @@ config FRAMEBUFFER_CONSOLE_ROTATION such that other users of the framebuffer will remain normally oriented. +config FRAMEBUFFER_CONSOLE_DEFERRED_TAKEOVER + bool "Framebuffer Console Deferred Takeover" + depends on FRAMEBUFFER_CONSOLE=y && DUMMY_CONSOLE=y + help + If enabled this defers the framebuffer console taking over the + console from the dummy console until the first text is displayed on + the console. This is useful in combination with the "quiet" kernel + commandline option to keep the framebuffer contents initially put up + by the firmware in place, rather then replacing the contents with a + black screen as soon as fbcon loads. + config STI_CONSOLE bool "STI text console" depends on PARISC && HAS_IOMEM diff --git a/drivers/video/console/dummycon.c b/drivers/video/console/dummycon.c index f2eafe2ed980..45ad925ad5f8 100644 --- a/drivers/video/console/dummycon.c +++ b/drivers/video/console/dummycon.c @@ -26,6 +26,65 @@ #define DUMMY_ROWS CONFIG_DUMMY_CONSOLE_ROWS #endif +#ifdef CONFIG_FRAMEBUFFER_CONSOLE_DEFERRED_TAKEOVER +/* These are both protected by the console_lock */ +static RAW_NOTIFIER_HEAD(dummycon_output_nh); +static bool dummycon_putc_called; + +void dummycon_register_output_notifier(struct notifier_block *nb) +{ + raw_notifier_chain_register(&dummycon_output_nh, nb); + + if (dummycon_putc_called) + nb->notifier_call(nb, 0, NULL); +} + +void dummycon_unregister_output_notifier(struct notifier_block *nb) +{ + raw_notifier_chain_unregister(&dummycon_output_nh, nb); +} + +static void dummycon_putc(struct vc_data *vc, int c, int ypos, int xpos) +{ + dummycon_putc_called = true; + raw_notifier_call_chain(&dummycon_output_nh, 0, NULL); +} + +static void dummycon_putcs(struct vc_data *vc, const unsigned short *s, + int count, int ypos, int xpos) +{ + int i; + + if (!dummycon_putc_called) { + /* Ignore erases */ + for (i = 0 ; i < count; i++) { + if (s[i] != vc->vc_video_erase_char) + break; + } + if (i == count) + return; + + dummycon_putc_called = true; + } + + raw_notifier_call_chain(&dummycon_output_nh, 0, NULL); +} + +static int dummycon_blank(struct vc_data *vc, int blank, int mode_switch) +{ + /* Redraw, so that we get putc(s) for output done while blanked */ + return 1; +} +#else +static void dummycon_putc(struct vc_data *vc, int c, int ypos, int xpos) { } +static void dummycon_putcs(struct vc_data *vc, const unsigned short *s, + int count, int ypos, int xpos) { } +static int dummycon_blank(struct vc_data *vc, int blank, int mode_switch) +{ + return 0; +} +#endif + static const char *dummycon_startup(void) { return "dummy device"; @@ -44,9 +103,6 @@ static void dummycon_init(struct vc_data *vc, int init) static void dummycon_deinit(struct vc_data *vc) { } static void dummycon_clear(struct vc_data *vc, int sy, int sx, int height, int width) { } -static void dummycon_putc(struct vc_data *vc, int c, int ypos, int xpos) { } -static void dummycon_putcs(struct vc_data *vc, const unsigned short *s, - int count, int ypos, int xpos) { } static void dummycon_cursor(struct vc_data *vc, int mode) { } static bool dummycon_scroll(struct vc_data *vc, unsigned int top, @@ -61,11 +117,6 @@ static int dummycon_switch(struct vc_data *vc) return 0; } -static int dummycon_blank(struct vc_data *vc, int blank, int mode_switch) -{ - return 0; -} - static int dummycon_font_set(struct vc_data *vc, struct console_font *font, unsigned int flags) { diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index cd8d52a967aa..5fb156bdcf4e 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -129,6 +129,12 @@ static inline void fbcon_map_override(void) } #endif /* CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY */ +#ifdef CONFIG_FRAMEBUFFER_CONSOLE_DEFERRED_TAKEOVER +static bool deferred_takeover = true; +#else +#define deferred_takeover false +#endif + /* font data */ static char fontname[40]; @@ -499,6 +505,12 @@ static int __init fb_console_setup(char *this_opt) margin_color = simple_strtoul(options, &options, 0); continue; } +#ifdef CONFIG_FRAMEBUFFER_CONSOLE_DEFERRED_TAKEOVER + if (!strcmp(options, "nodefer")) { + deferred_takeover = false; + continue; + } +#endif } return 1; } @@ -3100,6 +3112,9 @@ static int fbcon_fb_unregistered(struct fb_info *info) WARN_CONSOLE_UNLOCKED(); + if (deferred_takeover) + return 0; + idx = info->node; for (i = first_fb_vc; i <= last_fb_vc; i++) { if (con2fb_map[i] == idx) @@ -3140,6 +3155,13 @@ static void fbcon_remap_all(int idx) WARN_CONSOLE_UNLOCKED(); + if (deferred_takeover) { + for (i = first_fb_vc; i <= last_fb_vc; i++) + con2fb_map_boot[i] = idx; + fbcon_map_override(); + return; + } + for (i = first_fb_vc; i <= last_fb_vc; i++) set_con2fb_map(i, idx, 0); @@ -3191,6 +3213,11 @@ static int fbcon_fb_registered(struct fb_info *info) idx = info->node; fbcon_select_primary(info); + if (deferred_takeover) { + pr_info("fbcon: Deferring console take-over\n"); + return 0; + } + if (info_idx == -1) { for (i = first_fb_vc; i <= last_fb_vc; i++) { if (con2fb_map_boot[i] == idx) { @@ -3566,8 +3593,46 @@ static int fbcon_init_device(void) return 0; } +#ifdef CONFIG_FRAMEBUFFER_CONSOLE_DEFERRED_TAKEOVER +static struct notifier_block fbcon_output_nb; + +static int fbcon_output_notifier(struct notifier_block *nb, + unsigned long action, void *data) +{ + int i; + + WARN_CONSOLE_UNLOCKED(); + + pr_info("fbcon: Taking over console\n"); + + dummycon_unregister_output_notifier(&fbcon_output_nb); + deferred_takeover = false; + logo_shown = FBCON_LOGO_DONTSHOW; + + for (i = 0; i < FB_MAX; i++) { + if (registered_fb[i]) + fbcon_fb_registered(registered_fb[i]); + } + + return NOTIFY_OK; +} + +static void fbcon_register_output_notifier(void) +{ + fbcon_output_nb.notifier_call = fbcon_output_notifier; + dummycon_register_output_notifier(&fbcon_output_nb); +} +#else +static inline void fbcon_register_output_notifier(void) {} +#endif + static void fbcon_start(void) { + if (deferred_takeover) { + fbcon_register_output_notifier(); + return; + } + if (num_registered_fb) { int i; @@ -3594,6 +3659,13 @@ static void fbcon_exit(void) if (fbcon_has_exited) return; +#ifdef CONFIG_FRAMEBUFFER_CONSOLE_DEFERRED_TAKEOVER + if (deferred_takeover) { + dummycon_unregister_output_notifier(&fbcon_output_nb); + deferred_takeover = false; + } +#endif + kfree((void *)softback_buf); softback_buf = 0UL; diff --git a/include/linux/console.h b/include/linux/console.h index dfd6b0e97855..f59f3dbca65c 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -21,6 +21,7 @@ struct console_font_op; struct console_font; struct module; struct tty_struct; +struct notifier_block; /* * this is what the terminal answers to a ESC-Z or csi0c query. @@ -220,4 +221,8 @@ static inline bool vgacon_text_force(void) { return false; } extern void console_init(void); +/* For deferred console takeover */ +void dummycon_register_output_notifier(struct notifier_block *nb); +void dummycon_unregister_output_notifier(struct notifier_block *nb); + #endif /* _LINUX_CONSOLE_H */ -- cgit v1.2.3 From f564650106a6e85702660fefd59fdff0877ab46a Mon Sep 17 00:00:00 2001 From: Flavio Leitner Date: Wed, 27 Jun 2018 10:34:25 -0300 Subject: netfilter: check if the socket netns is correct. Netfilter assumes that if the socket is present in the skb, then it can be used because that reference is cleaned up while the skb is crossing netns. We want to change that to preserve the socket reference in a future patch, so this is a preparation updating netfilter to check if the socket netns matches before use it. Signed-off-by: Flavio Leitner Acked-by: Florian Westphal Signed-off-by: David S. Miller --- include/net/netfilter/nf_log.h | 3 ++- net/ipv4/netfilter/nf_log_ipv4.c | 8 ++++---- net/ipv6/netfilter/nf_log_ipv6.c | 8 ++++---- net/netfilter/nf_conntrack_broadcast.c | 2 +- net/netfilter/nf_log_common.c | 5 +++-- net/netfilter/nf_nat_core.c | 6 +++++- net/netfilter/nft_meta.c | 9 ++++++--- net/netfilter/nft_socket.c | 5 ++++- net/netfilter/xt_cgroup.c | 6 ++++-- net/netfilter/xt_owner.c | 2 +- net/netfilter/xt_recent.c | 3 ++- net/netfilter/xt_socket.c | 8 ++++++++ 12 files changed, 44 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_log.h b/include/net/netfilter/nf_log.h index e811ac07ea94..0d3920896d50 100644 --- a/include/net/netfilter/nf_log.h +++ b/include/net/netfilter/nf_log.h @@ -106,7 +106,8 @@ int nf_log_dump_udp_header(struct nf_log_buf *m, const struct sk_buff *skb, int nf_log_dump_tcp_header(struct nf_log_buf *m, const struct sk_buff *skb, u8 proto, int fragment, unsigned int offset, unsigned int logflags); -void nf_log_dump_sk_uid_gid(struct nf_log_buf *m, struct sock *sk); +void nf_log_dump_sk_uid_gid(struct net *net, struct nf_log_buf *m, + struct sock *sk); void nf_log_dump_packet_common(struct nf_log_buf *m, u_int8_t pf, unsigned int hooknum, const struct sk_buff *skb, const struct net_device *in, diff --git a/net/ipv4/netfilter/nf_log_ipv4.c b/net/ipv4/netfilter/nf_log_ipv4.c index 4388de0e5380..1e6f28c97d3a 100644 --- a/net/ipv4/netfilter/nf_log_ipv4.c +++ b/net/ipv4/netfilter/nf_log_ipv4.c @@ -35,7 +35,7 @@ static const struct nf_loginfo default_loginfo = { }; /* One level of recursion won't kill us */ -static void dump_ipv4_packet(struct nf_log_buf *m, +static void dump_ipv4_packet(struct net *net, struct nf_log_buf *m, const struct nf_loginfo *info, const struct sk_buff *skb, unsigned int iphoff) { @@ -183,7 +183,7 @@ static void dump_ipv4_packet(struct nf_log_buf *m, /* Max length: 3+maxlen */ if (!iphoff) { /* Only recurse once. */ nf_log_buf_add(m, "["); - dump_ipv4_packet(m, info, skb, + dump_ipv4_packet(net, m, info, skb, iphoff + ih->ihl*4+sizeof(_icmph)); nf_log_buf_add(m, "] "); } @@ -251,7 +251,7 @@ static void dump_ipv4_packet(struct nf_log_buf *m, /* Max length: 15 "UID=4294967295 " */ if ((logflags & NF_LOG_UID) && !iphoff) - nf_log_dump_sk_uid_gid(m, skb->sk); + nf_log_dump_sk_uid_gid(net, m, skb->sk); /* Max length: 16 "MARK=0xFFFFFFFF " */ if (!iphoff && skb->mark) @@ -333,7 +333,7 @@ static void nf_log_ip_packet(struct net *net, u_int8_t pf, if (in != NULL) dump_ipv4_mac_header(m, loginfo, skb); - dump_ipv4_packet(m, loginfo, skb, 0); + dump_ipv4_packet(net, m, loginfo, skb, 0); nf_log_buf_close(m); } diff --git a/net/ipv6/netfilter/nf_log_ipv6.c b/net/ipv6/netfilter/nf_log_ipv6.c index b397a8fe88b9..c6bf580d0f33 100644 --- a/net/ipv6/netfilter/nf_log_ipv6.c +++ b/net/ipv6/netfilter/nf_log_ipv6.c @@ -36,7 +36,7 @@ static const struct nf_loginfo default_loginfo = { }; /* One level of recursion won't kill us */ -static void dump_ipv6_packet(struct nf_log_buf *m, +static void dump_ipv6_packet(struct net *net, struct nf_log_buf *m, const struct nf_loginfo *info, const struct sk_buff *skb, unsigned int ip6hoff, int recurse) @@ -258,7 +258,7 @@ static void dump_ipv6_packet(struct nf_log_buf *m, /* Max length: 3+maxlen */ if (recurse) { nf_log_buf_add(m, "["); - dump_ipv6_packet(m, info, skb, + dump_ipv6_packet(net, m, info, skb, ptr + sizeof(_icmp6h), 0); nf_log_buf_add(m, "] "); } @@ -278,7 +278,7 @@ static void dump_ipv6_packet(struct nf_log_buf *m, /* Max length: 15 "UID=4294967295 " */ if ((logflags & NF_LOG_UID) && recurse) - nf_log_dump_sk_uid_gid(m, skb->sk); + nf_log_dump_sk_uid_gid(net, m, skb->sk); /* Max length: 16 "MARK=0xFFFFFFFF " */ if (recurse && skb->mark) @@ -365,7 +365,7 @@ static void nf_log_ip6_packet(struct net *net, u_int8_t pf, if (in != NULL) dump_ipv6_mac_header(m, loginfo, skb); - dump_ipv6_packet(m, loginfo, skb, skb_network_offset(skb), 1); + dump_ipv6_packet(net, m, loginfo, skb, skb_network_offset(skb), 1); nf_log_buf_close(m); } diff --git a/net/netfilter/nf_conntrack_broadcast.c b/net/netfilter/nf_conntrack_broadcast.c index a1086bdec242..5423b197d98a 100644 --- a/net/netfilter/nf_conntrack_broadcast.c +++ b/net/netfilter/nf_conntrack_broadcast.c @@ -32,7 +32,7 @@ int nf_conntrack_broadcast_help(struct sk_buff *skb, __be32 mask = 0; /* we're only interested in locally generated packets */ - if (skb->sk == NULL) + if (skb->sk == NULL || !net_eq(nf_ct_net(ct), sock_net(skb->sk))) goto out; if (rt == NULL || !(rt->rt_flags & RTCF_BROADCAST)) goto out; diff --git a/net/netfilter/nf_log_common.c b/net/netfilter/nf_log_common.c index dc61399e30be..a8c5c846aec1 100644 --- a/net/netfilter/nf_log_common.c +++ b/net/netfilter/nf_log_common.c @@ -132,9 +132,10 @@ int nf_log_dump_tcp_header(struct nf_log_buf *m, const struct sk_buff *skb, } EXPORT_SYMBOL_GPL(nf_log_dump_tcp_header); -void nf_log_dump_sk_uid_gid(struct nf_log_buf *m, struct sock *sk) +void nf_log_dump_sk_uid_gid(struct net *net, struct nf_log_buf *m, + struct sock *sk) { - if (!sk || !sk_fullsock(sk)) + if (!sk || !sk_fullsock(sk) || !net_eq(net, sock_net(sk))) return; read_lock_bh(&sk->sk_callback_lock); diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 46f9df99d276..86df2a1666fd 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -108,6 +108,7 @@ int nf_xfrm_me_harder(struct net *net, struct sk_buff *skb, unsigned int family) struct flowi fl; unsigned int hh_len; struct dst_entry *dst; + struct sock *sk = skb->sk; int err; err = xfrm_decode_session(skb, &fl, family); @@ -119,7 +120,10 @@ int nf_xfrm_me_harder(struct net *net, struct sk_buff *skb, unsigned int family) dst = ((struct xfrm_dst *)dst)->route; dst_hold(dst); - dst = xfrm_lookup(net, dst, &fl, skb->sk, 0); + if (sk && !net_eq(net, sock_net(sk))) + sk = NULL; + + dst = xfrm_lookup(net, dst, &fl, sk, 0); if (IS_ERR(dst)) return PTR_ERR(dst); diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index 1105a23bda5e..2b94dcc43456 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -107,7 +107,8 @@ static void nft_meta_get_eval(const struct nft_expr *expr, break; case NFT_META_SKUID: sk = skb_to_full_sk(skb); - if (!sk || !sk_fullsock(sk)) + if (!sk || !sk_fullsock(sk) || + !net_eq(nft_net(pkt), sock_net(sk))) goto err; read_lock_bh(&sk->sk_callback_lock); @@ -123,7 +124,8 @@ static void nft_meta_get_eval(const struct nft_expr *expr, break; case NFT_META_SKGID: sk = skb_to_full_sk(skb); - if (!sk || !sk_fullsock(sk)) + if (!sk || !sk_fullsock(sk) || + !net_eq(nft_net(pkt), sock_net(sk))) goto err; read_lock_bh(&sk->sk_callback_lock); @@ -214,7 +216,8 @@ static void nft_meta_get_eval(const struct nft_expr *expr, #ifdef CONFIG_CGROUP_NET_CLASSID case NFT_META_CGROUP: sk = skb_to_full_sk(skb); - if (!sk || !sk_fullsock(sk)) + if (!sk || !sk_fullsock(sk) || + !net_eq(nft_net(pkt), sock_net(sk))) goto err; *dest = sock_cgroup_classid(&sk->sk_cgrp_data); break; diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c index 74e1b3bd6954..998c2b546f6d 100644 --- a/net/netfilter/nft_socket.c +++ b/net/netfilter/nft_socket.c @@ -23,6 +23,9 @@ static void nft_socket_eval(const struct nft_expr *expr, struct sock *sk = skb->sk; u32 *dest = ®s->data[priv->dreg]; + if (sk && !net_eq(nft_net(pkt), sock_net(sk))) + sk = NULL; + if (!sk) switch(nft_pf(pkt)) { case NFPROTO_IPV4: @@ -39,7 +42,7 @@ static void nft_socket_eval(const struct nft_expr *expr, return; } - if(!sk) { + if (!sk) { nft_reg_store8(dest, 0); return; } diff --git a/net/netfilter/xt_cgroup.c b/net/netfilter/xt_cgroup.c index 7df2dece57d3..5d92e1781980 100644 --- a/net/netfilter/xt_cgroup.c +++ b/net/netfilter/xt_cgroup.c @@ -72,8 +72,9 @@ static bool cgroup_mt_v0(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_cgroup_info_v0 *info = par->matchinfo; + struct sock *sk = skb->sk; - if (skb->sk == NULL || !sk_fullsock(skb->sk)) + if (!sk || !sk_fullsock(sk) || !net_eq(xt_net(par), sock_net(sk))) return false; return (info->id == sock_cgroup_classid(&skb->sk->sk_cgrp_data)) ^ @@ -85,8 +86,9 @@ static bool cgroup_mt_v1(const struct sk_buff *skb, struct xt_action_param *par) const struct xt_cgroup_info_v1 *info = par->matchinfo; struct sock_cgroup_data *skcd = &skb->sk->sk_cgrp_data; struct cgroup *ancestor = info->priv; + struct sock *sk = skb->sk; - if (!skb->sk || !sk_fullsock(skb->sk)) + if (!sk || !sk_fullsock(sk) || !net_eq(xt_net(par), sock_net(sk))) return false; if (ancestor) diff --git a/net/netfilter/xt_owner.c b/net/netfilter/xt_owner.c index 3d705c688a27..46686fb73784 100644 --- a/net/netfilter/xt_owner.c +++ b/net/netfilter/xt_owner.c @@ -67,7 +67,7 @@ owner_mt(const struct sk_buff *skb, struct xt_action_param *par) struct sock *sk = skb_to_full_sk(skb); struct net *net = xt_net(par); - if (sk == NULL || sk->sk_socket == NULL) + if (!sk || !sk->sk_socket || !net_eq(net, sock_net(sk))) return (info->match ^ info->invert) == 0; else if (info->match & info->invert & XT_OWNER_SOCKET) /* diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c index 07085c22b19c..f44de4bc2100 100644 --- a/net/netfilter/xt_recent.c +++ b/net/netfilter/xt_recent.c @@ -265,7 +265,8 @@ recent_mt(const struct sk_buff *skb, struct xt_action_param *par) } /* use TTL as seen before forwarding */ - if (xt_out(par) != NULL && skb->sk == NULL) + if (xt_out(par) != NULL && + (!skb->sk || !net_eq(net, sock_net(skb->sk)))) ttl++; spin_lock_bh(&recent_lock); diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index 5c0779c4fa3c..0472f3472842 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -56,8 +56,12 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, struct sk_buff *pskb = (struct sk_buff *)skb; struct sock *sk = skb->sk; + if (!net_eq(xt_net(par), sock_net(sk))) + sk = NULL; + if (!sk) sk = nf_sk_lookup_slow_v4(xt_net(par), skb, xt_in(par)); + if (sk) { bool wildcard; bool transparent = true; @@ -113,8 +117,12 @@ socket_mt6_v1_v2_v3(const struct sk_buff *skb, struct xt_action_param *par) struct sk_buff *pskb = (struct sk_buff *)skb; struct sock *sk = skb->sk; + if (!net_eq(xt_net(par), sock_net(sk))) + sk = NULL; + if (!sk) sk = nf_sk_lookup_slow_v6(xt_net(par), skb, xt_in(par)); + if (sk) { bool wildcard; bool transparent = true; -- cgit v1.2.3 From 2bbc46e811f0d40ed92ff9c104fce6618049f726 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Thu, 21 Jun 2018 05:41:21 -0400 Subject: media: v4l-common: Make v4l2_find_nearest_size more sparse-friendly This sparse warning is emitted by using v4l2_find_nearest_size in some cases. Fix it in the framework. >> drivers/media/i2c/ov5640.c:1394:14: sparse: incorrect type in assignment +(different base types) @@ expected struct ov5640_mode_info const *mode @@ +got ststruct ov5640_mode_info const *mode @@ drivers/media/i2c/ov5640.c:1394:14: expected struct ov5640_mode_info const +*mode drivers/media/i2c/ov5640.c:1394:14: got struct ov5640_mode_info const ( *< +noident> )[9] Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-common.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/media/v4l2-common.h b/include/media/v4l2-common.h index 160bca96d524..cdc87ec61e54 100644 --- a/include/media/v4l2-common.h +++ b/include/media/v4l2-common.h @@ -338,7 +338,7 @@ void v4l_bound_align_image(unsigned int *width, unsigned int wmin, ({ \ BUILD_BUG_ON(sizeof((array)->width_field) != sizeof(u32) || \ sizeof((array)->height_field) != sizeof(u32)); \ - (typeof(&(*(array))))__v4l2_find_nearest_size( \ + (typeof(&(array)[0]))__v4l2_find_nearest_size( \ (array), array_size, sizeof(*(array)), \ offsetof(typeof(*(array)), width_field), \ offsetof(typeof(*(array)), height_field), \ -- cgit v1.2.3 From 4b09791ba059cc5a5ec7d69049f5d05da65b6418 Mon Sep 17 00:00:00 2001 From: Ondrej Mosnáček Date: Tue, 26 Jun 2018 13:04:42 +0200 Subject: cred: conditionally declare groups-related functions The groups-related functions declared in include/linux/cred.h are defined in kernel/groups.c, which is compiled only when CONFIG_MULTIUSER=y. Move all these function declarations under #ifdef CONFIG_MULTIUSER to help avoid accidental usage in contexts where CONFIG_MULTIUSER might be disabled. This patch also adds a fallback for groups_search(). Currently this function is only called from kernel/groups.c itself and security/keys/permissions.c, where the call is (by coincidence) optimized away in case CONFIG_MULTIUSER=n. However, the audit subsystem (which does not depend on CONFIG_MULTIUSER) calls this function in -next, so the fallback will be needed to avoid compilation errors or ugly workarounds. See also: https://lkml.org/lkml/2018/6/20/670 https://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/audit.git/commit/?h=next&id=af85d1772e31fed34165a1b3decef340cf4080c0 Reported-by: Randy Dunlap Tested-by: Randy Dunlap Signed-off-by: Ondrej Mosnacek Signed-off-by: Paul Moore --- include/linux/cred.h | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/cred.h b/include/linux/cred.h index 631286535d0f..7eed6101c791 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -65,6 +65,12 @@ extern void groups_free(struct group_info *); extern int in_group_p(kgid_t); extern int in_egroup_p(kgid_t); +extern int groups_search(const struct group_info *, kgid_t); + +extern int set_current_groups(struct group_info *); +extern void set_groups(struct cred *, struct group_info *); +extern bool may_setgroups(void); +extern void groups_sort(struct group_info *); #else static inline void groups_free(struct group_info *group_info) { @@ -78,12 +84,11 @@ static inline int in_egroup_p(kgid_t grp) { return 1; } +static inline int groups_search(const struct group_info *group_info, kgid_t grp) +{ + return 1; +} #endif -extern int set_current_groups(struct group_info *); -extern void set_groups(struct cred *, struct group_info *); -extern int groups_search(const struct group_info *, kgid_t); -extern bool may_setgroups(void); -extern void groups_sort(struct group_info *); /* * The security context of a task -- cgit v1.2.3 From b6e71bdebb12cb79f931db358066a33f5f526b6a Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Wed, 27 Jun 2018 14:39:02 -0700 Subject: ila: Flush netlink command to clear xlat table Add ILA_CMD_FLUSH netlink command to clear the ILA translation table. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/uapi/linux/ila.h | 1 + net/ipv6/ila/ila.h | 1 + net/ipv6/ila/ila_main.c | 6 +++++ net/ipv6/ila/ila_xlat.c | 62 ++++++++++++++++++++++++++++++++++++++++++++++-- 4 files changed, 68 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/ila.h b/include/uapi/linux/ila.h index 483b77af4eb8..db45d3e49a12 100644 --- a/include/uapi/linux/ila.h +++ b/include/uapi/linux/ila.h @@ -30,6 +30,7 @@ enum { ILA_CMD_ADD, ILA_CMD_DEL, ILA_CMD_GET, + ILA_CMD_FLUSH, __ILA_CMD_MAX, }; diff --git a/net/ipv6/ila/ila.h b/net/ipv6/ila/ila.h index faba7824ea56..1f747bcbec29 100644 --- a/net/ipv6/ila/ila.h +++ b/net/ipv6/ila/ila.h @@ -123,6 +123,7 @@ void ila_xlat_exit_net(struct net *net); int ila_xlat_nl_cmd_add_mapping(struct sk_buff *skb, struct genl_info *info); int ila_xlat_nl_cmd_del_mapping(struct sk_buff *skb, struct genl_info *info); int ila_xlat_nl_cmd_get_mapping(struct sk_buff *skb, struct genl_info *info); +int ila_xlat_nl_cmd_flush(struct sk_buff *skb, struct genl_info *info); int ila_xlat_nl_dump_start(struct netlink_callback *cb); int ila_xlat_nl_dump_done(struct netlink_callback *cb); int ila_xlat_nl_dump(struct sk_buff *skb, struct netlink_callback *cb); diff --git a/net/ipv6/ila/ila_main.c b/net/ipv6/ila/ila_main.c index f6ac6b14577e..18fac76b9520 100644 --- a/net/ipv6/ila/ila_main.c +++ b/net/ipv6/ila/ila_main.c @@ -26,6 +26,12 @@ static const struct genl_ops ila_nl_ops[] = { .policy = ila_nl_policy, .flags = GENL_ADMIN_PERM, }, + { + .cmd = ILA_CMD_FLUSH, + .doit = ila_xlat_nl_cmd_flush, + .policy = ila_nl_policy, + .flags = GENL_ADMIN_PERM, + }, { .cmd = ILA_CMD_GET, .doit = ila_xlat_nl_cmd_get_mapping, diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c index d05de891dfb6..51a15ce50a64 100644 --- a/net/ipv6/ila/ila_xlat.c +++ b/net/ipv6/ila/ila_xlat.c @@ -164,9 +164,9 @@ static inline void ila_release(struct ila_map *ila) kfree_rcu(ila, rcu); } -static void ila_free_cb(void *ptr, void *arg) +static void ila_free_node(struct ila_map *ila) { - struct ila_map *ila = (struct ila_map *)ptr, *next; + struct ila_map *next; /* Assume rcu_readlock held */ while (ila) { @@ -176,6 +176,11 @@ static void ila_free_cb(void *ptr, void *arg) } } +static void ila_free_cb(void *ptr, void *arg) +{ + ila_free_node((struct ila_map *)ptr); +} + static int ila_xlat_addr(struct sk_buff *skb, bool sir2ila); static unsigned int @@ -365,6 +370,59 @@ int ila_xlat_nl_cmd_del_mapping(struct sk_buff *skb, struct genl_info *info) return 0; } +static inline spinlock_t *lock_from_ila_map(struct ila_net *ilan, + struct ila_map *ila) +{ + return ila_get_lock(ilan, ila->xp.ip.locator_match); +} + +int ila_xlat_nl_cmd_flush(struct sk_buff *skb, struct genl_info *info) +{ + struct net *net = genl_info_net(info); + struct ila_net *ilan = net_generic(net, ila_net_id); + struct rhashtable_iter iter; + struct ila_map *ila; + spinlock_t *lock; + int ret; + + ret = rhashtable_walk_init(&ilan->xlat.rhash_table, &iter, GFP_KERNEL); + if (ret) + goto done; + + rhashtable_walk_start(&iter); + + for (;;) { + ila = rhashtable_walk_next(&iter); + + if (IS_ERR(ila)) { + if (PTR_ERR(ila) == -EAGAIN) + continue; + ret = PTR_ERR(ila); + goto done; + } else if (!ila) { + break; + } + + lock = lock_from_ila_map(ilan, ila); + + spin_lock(lock); + + ret = rhashtable_remove_fast(&ilan->xlat.rhash_table, + &ila->node, rht_params); + if (!ret) + ila_free_node(ila); + + spin_unlock(lock); + + if (ret) + break; + } + +done: + rhashtable_walk_stop(&iter); + return ret; +} + static int ila_fill_info(struct ila_map *ila, struct sk_buff *msg) { if (nla_put_u64_64bit(msg, ILA_ATTR_LOCATOR, -- cgit v1.2.3 From a7160670b5e2d6b59e0f7a5b7e5bcef3b532c24c Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Wed, 27 Jun 2018 21:33:54 +0200 Subject: ASoC: pxa: clean up function names in pxa2xx-lib Clean up the namespace a bit and drop the __ prefix of all functions exported by pxa2xx-lib. This improves the readability of the code. Signed-off-by: Daniel Mack Signed-off-by: Mark Brown --- include/sound/pxa2xx-lib.h | 10 +++++----- sound/arm/pxa2xx-ac97.c | 10 +++++----- sound/arm/pxa2xx-pcm-lib.c | 22 +++++++++++----------- sound/soc/pxa/pxa2xx-pcm.c | 21 +++++++-------------- 4 files changed, 28 insertions(+), 35 deletions(-) (limited to 'include') diff --git a/include/sound/pxa2xx-lib.h b/include/sound/pxa2xx-lib.h index 63f75450d3db..b43de38de8b2 100644 --- a/include/sound/pxa2xx-lib.h +++ b/include/sound/pxa2xx-lib.h @@ -10,14 +10,14 @@ struct snd_pcm_substream; struct snd_pcm_hw_params; struct snd_pcm; -extern int __pxa2xx_pcm_hw_params(struct snd_pcm_substream *substream, +extern int pxa2xx_pcm_hw_params(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params); -extern int __pxa2xx_pcm_hw_free(struct snd_pcm_substream *substream); +extern int pxa2xx_pcm_hw_free(struct snd_pcm_substream *substream); extern int pxa2xx_pcm_trigger(struct snd_pcm_substream *substream, int cmd); extern snd_pcm_uframes_t pxa2xx_pcm_pointer(struct snd_pcm_substream *substream); -extern int __pxa2xx_pcm_prepare(struct snd_pcm_substream *substream); -extern int __pxa2xx_pcm_open(struct snd_pcm_substream *substream); -extern int __pxa2xx_pcm_close(struct snd_pcm_substream *substream); +extern int pxa2xx_pcm_prepare(struct snd_pcm_substream *substream); +extern int pxa2xx_pcm_open(struct snd_pcm_substream *substream); +extern int pxa2xx_pcm_close(struct snd_pcm_substream *substream); extern int pxa2xx_pcm_mmap(struct snd_pcm_substream *substream, struct vm_area_struct *vma); extern int pxa2xx_pcm_preallocate_dma_buffer(struct snd_pcm *pcm, int stream); diff --git a/sound/arm/pxa2xx-ac97.c b/sound/arm/pxa2xx-ac97.c index 7d8d7b7199dc..0d624337857b 100644 --- a/sound/arm/pxa2xx-ac97.c +++ b/sound/arm/pxa2xx-ac97.c @@ -70,7 +70,7 @@ static int pxa2xx_ac97_pcm_open(struct snd_pcm_substream *substream) pxa2xx_audio_ops_t *platform_ops; int ret, i; - ret = __pxa2xx_pcm_open(substream); + ret = pxa2xx_pcm_open(substream); if (ret) return ret; @@ -86,7 +86,7 @@ static int pxa2xx_ac97_pcm_open(struct snd_pcm_substream *substream) if (platform_ops && platform_ops->startup) { ret = platform_ops->startup(substream, platform_ops->priv); if (ret < 0) - __pxa2xx_pcm_close(substream); + pxa2xx_pcm_close(substream); } return ret; @@ -110,7 +110,7 @@ static int pxa2xx_ac97_pcm_prepare(struct snd_pcm_substream *substream) AC97_PCM_FRONT_DAC_RATE : AC97_PCM_LR_ADC_RATE; int ret; - ret = __pxa2xx_pcm_prepare(substream); + ret = pxa2xx_pcm_prepare(substream); if (ret < 0) return ret; @@ -178,8 +178,8 @@ static const struct snd_pcm_ops pxa2xx_pcm_ops = { .open = pxa2xx_ac97_pcm_open, .close = pxa2xx_ac97_pcm_close, .ioctl = snd_pcm_lib_ioctl, - .hw_params = __pxa2xx_pcm_hw_params, - .hw_free = __pxa2xx_pcm_hw_free, + .hw_params = pxa2xx_pcm_hw_params, + .hw_free = pxa2xx_pcm_hw_free, .prepare = pxa2xx_ac97_pcm_prepare, .trigger = pxa2xx_pcm_trigger, .pointer = pxa2xx_pcm_pointer, diff --git a/sound/arm/pxa2xx-pcm-lib.c b/sound/arm/pxa2xx-pcm-lib.c index b927fa5ddbc0..dc56dbebf441 100644 --- a/sound/arm/pxa2xx-pcm-lib.c +++ b/sound/arm/pxa2xx-pcm-lib.c @@ -33,8 +33,8 @@ static const struct snd_pcm_hardware pxa2xx_pcm_hardware = { .fifo_size = 32, }; -int __pxa2xx_pcm_hw_params(struct snd_pcm_substream *substream, - struct snd_pcm_hw_params *params) +int pxa2xx_pcm_hw_params(struct snd_pcm_substream *substream, + struct snd_pcm_hw_params *params) { struct dma_chan *chan = snd_dmaengine_pcm_get_chan(substream); struct snd_soc_pcm_runtime *rtd = substream->private_data; @@ -62,14 +62,14 @@ int __pxa2xx_pcm_hw_params(struct snd_pcm_substream *substream, return 0; } -EXPORT_SYMBOL(__pxa2xx_pcm_hw_params); +EXPORT_SYMBOL(pxa2xx_pcm_hw_params); -int __pxa2xx_pcm_hw_free(struct snd_pcm_substream *substream) +int pxa2xx_pcm_hw_free(struct snd_pcm_substream *substream) { snd_pcm_set_runtime_buffer(substream, NULL); return 0; } -EXPORT_SYMBOL(__pxa2xx_pcm_hw_free); +EXPORT_SYMBOL(pxa2xx_pcm_hw_free); int pxa2xx_pcm_trigger(struct snd_pcm_substream *substream, int cmd) { @@ -84,13 +84,13 @@ pxa2xx_pcm_pointer(struct snd_pcm_substream *substream) } EXPORT_SYMBOL(pxa2xx_pcm_pointer); -int __pxa2xx_pcm_prepare(struct snd_pcm_substream *substream) +int pxa2xx_pcm_prepare(struct snd_pcm_substream *substream) { return 0; } -EXPORT_SYMBOL(__pxa2xx_pcm_prepare); +EXPORT_SYMBOL(pxa2xx_pcm_prepare); -int __pxa2xx_pcm_open(struct snd_pcm_substream *substream) +int pxa2xx_pcm_open(struct snd_pcm_substream *substream) { struct snd_soc_pcm_runtime *rtd = substream->private_data; struct snd_pcm_runtime *runtime = substream->runtime; @@ -127,13 +127,13 @@ int __pxa2xx_pcm_open(struct snd_pcm_substream *substream) substream, dma_request_slave_channel(rtd->cpu_dai->dev, dma_params->chan_name)); } -EXPORT_SYMBOL(__pxa2xx_pcm_open); +EXPORT_SYMBOL(pxa2xx_pcm_open); -int __pxa2xx_pcm_close(struct snd_pcm_substream *substream) +int pxa2xx_pcm_close(struct snd_pcm_substream *substream) { return snd_dmaengine_pcm_close_release_chan(substream); } -EXPORT_SYMBOL(__pxa2xx_pcm_close); +EXPORT_SYMBOL(pxa2xx_pcm_close); int pxa2xx_pcm_mmap(struct snd_pcm_substream *substream, struct vm_area_struct *vma) diff --git a/sound/soc/pxa/pxa2xx-pcm.c b/sound/soc/pxa/pxa2xx-pcm.c index 445e691126e5..da252d1f732e 100644 --- a/sound/soc/pxa/pxa2xx-pcm.c +++ b/sound/soc/pxa/pxa2xx-pcm.c @@ -20,8 +20,8 @@ #include #include -static int pxa2xx_pcm_hw_params(struct snd_pcm_substream *substream, - struct snd_pcm_hw_params *params) +static int __pxa2xx_pcm_hw_params(struct snd_pcm_substream *substream, + struct snd_pcm_hw_params *params) { struct snd_soc_pcm_runtime *rtd = substream->private_data; struct snd_dmaengine_dai_dma_data *dma; @@ -33,23 +33,16 @@ static int pxa2xx_pcm_hw_params(struct snd_pcm_substream *substream, if (!dma) return 0; - return __pxa2xx_pcm_hw_params(substream, params); -} - -static int pxa2xx_pcm_hw_free(struct snd_pcm_substream *substream) -{ - __pxa2xx_pcm_hw_free(substream); - - return 0; + return pxa2xx_pcm_hw_params(substream, params); } static const struct snd_pcm_ops pxa2xx_pcm_ops = { - .open = __pxa2xx_pcm_open, - .close = __pxa2xx_pcm_close, + .open = pxa2xx_pcm_open, + .close = pxa2xx_pcm_close, .ioctl = snd_pcm_lib_ioctl, - .hw_params = pxa2xx_pcm_hw_params, + .hw_params = __pxa2xx_pcm_hw_params, .hw_free = pxa2xx_pcm_hw_free, - .prepare = __pxa2xx_pcm_prepare, + .prepare = pxa2xx_pcm_prepare, .trigger = pxa2xx_pcm_trigger, .pointer = pxa2xx_pcm_pointer, .mmap = pxa2xx_pcm_mmap, -- cgit v1.2.3 From 7afd1b0b2ef9a8120951188a955010ef92bdf885 Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Wed, 27 Jun 2018 21:33:55 +0200 Subject: ASoC: pxa: move some functions to pxa2xx-lib To get rid of some intermediate platform layers, move pxa2xx_soc_pcm_new() and pxa2xx_pcm_ops in pxa2xx-lib. Signed-off-by: Daniel Mack Signed-off-by: Mark Brown --- include/sound/pxa2xx-lib.h | 3 +++ sound/arm/pxa2xx-ac97.c | 6 ++--- sound/arm/pxa2xx-pcm-lib.c | 41 ++++++++++++++++++++++++++++++++++ sound/soc/pxa/pxa2xx-pcm.c | 55 ---------------------------------------------- 4 files changed, 47 insertions(+), 58 deletions(-) (limited to 'include') diff --git a/include/sound/pxa2xx-lib.h b/include/sound/pxa2xx-lib.h index b43de38de8b2..6758fc12fa84 100644 --- a/include/sound/pxa2xx-lib.h +++ b/include/sound/pxa2xx-lib.h @@ -8,6 +8,7 @@ /* PCM */ struct snd_pcm_substream; struct snd_pcm_hw_params; +struct snd_soc_pcm_runtime; struct snd_pcm; extern int pxa2xx_pcm_hw_params(struct snd_pcm_substream *substream, @@ -22,6 +23,8 @@ extern int pxa2xx_pcm_mmap(struct snd_pcm_substream *substream, struct vm_area_struct *vma); extern int pxa2xx_pcm_preallocate_dma_buffer(struct snd_pcm *pcm, int stream); extern void pxa2xx_pcm_free_dma_buffers(struct snd_pcm *pcm); +extern int pxa2xx_soc_pcm_new(struct snd_soc_pcm_runtime *rtd); +extern const struct snd_pcm_ops pxa2xx_pcm_ops; /* AC97 */ diff --git a/sound/arm/pxa2xx-ac97.c b/sound/arm/pxa2xx-ac97.c index 0d624337857b..1f72672262d0 100644 --- a/sound/arm/pxa2xx-ac97.c +++ b/sound/arm/pxa2xx-ac97.c @@ -174,7 +174,7 @@ static int pxa2xx_ac97_resume(struct device *dev) static SIMPLE_DEV_PM_OPS(pxa2xx_ac97_pm_ops, pxa2xx_ac97_suspend, pxa2xx_ac97_resume); #endif -static const struct snd_pcm_ops pxa2xx_pcm_ops = { +static const struct snd_pcm_ops pxa2xx_ac97_pcm_ops = { .open = pxa2xx_ac97_pcm_open, .close = pxa2xx_ac97_pcm_close, .ioctl = snd_pcm_lib_ioctl, @@ -203,13 +203,13 @@ static int pxa2xx_ac97_pcm_new(struct snd_card *card) goto out; stream = SNDRV_PCM_STREAM_PLAYBACK; - snd_pcm_set_ops(pcm, stream, &pxa2xx_pcm_ops); + snd_pcm_set_ops(pcm, stream, &pxa2xx_ac97_pcm_ops); ret = pxa2xx_pcm_preallocate_dma_buffer(pcm, stream); if (ret) goto out; stream = SNDRV_PCM_STREAM_CAPTURE; - snd_pcm_set_ops(pcm, stream, &pxa2xx_pcm_ops); + snd_pcm_set_ops(pcm, stream, &pxa2xx_ac97_pcm_ops); ret = pxa2xx_pcm_preallocate_dma_buffer(pcm, stream); if (ret) goto out; diff --git a/sound/arm/pxa2xx-pcm-lib.c b/sound/arm/pxa2xx-pcm-lib.c index dc56dbebf441..add23d9b4ef6 100644 --- a/sound/arm/pxa2xx-pcm-lib.c +++ b/sound/arm/pxa2xx-pcm-lib.c @@ -179,6 +179,47 @@ void pxa2xx_pcm_free_dma_buffers(struct snd_pcm *pcm) } EXPORT_SYMBOL(pxa2xx_pcm_free_dma_buffers); +int pxa2xx_soc_pcm_new(struct snd_soc_pcm_runtime *rtd) +{ + struct snd_card *card = rtd->card->snd_card; + struct snd_pcm *pcm = rtd->pcm; + int ret; + + ret = dma_coerce_mask_and_coherent(card->dev, DMA_BIT_MASK(32)); + if (ret) + return ret; + + if (pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream) { + ret = pxa2xx_pcm_preallocate_dma_buffer(pcm, + SNDRV_PCM_STREAM_PLAYBACK); + if (ret) + goto out; + } + + if (pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream) { + ret = pxa2xx_pcm_preallocate_dma_buffer(pcm, + SNDRV_PCM_STREAM_CAPTURE); + if (ret) + goto out; + } + out: + return ret; +} +EXPORT_SYMBOL(pxa2xx_soc_pcm_new); + +const struct snd_pcm_ops pxa2xx_pcm_ops = { + .open = pxa2xx_pcm_open, + .close = pxa2xx_pcm_close, + .ioctl = snd_pcm_lib_ioctl, + .hw_params = pxa2xx_pcm_hw_params, + .hw_free = pxa2xx_pcm_hw_free, + .prepare = pxa2xx_pcm_prepare, + .trigger = pxa2xx_pcm_trigger, + .pointer = pxa2xx_pcm_pointer, + .mmap = pxa2xx_pcm_mmap, +}; +EXPORT_SYMBOL(pxa2xx_pcm_ops); + MODULE_AUTHOR("Nicolas Pitre"); MODULE_DESCRIPTION("Intel PXA2xx sound library"); MODULE_LICENSE("GPL"); diff --git a/sound/soc/pxa/pxa2xx-pcm.c b/sound/soc/pxa/pxa2xx-pcm.c index da252d1f732e..a1df4ec76cbd 100644 --- a/sound/soc/pxa/pxa2xx-pcm.c +++ b/sound/soc/pxa/pxa2xx-pcm.c @@ -20,61 +20,6 @@ #include #include -static int __pxa2xx_pcm_hw_params(struct snd_pcm_substream *substream, - struct snd_pcm_hw_params *params) -{ - struct snd_soc_pcm_runtime *rtd = substream->private_data; - struct snd_dmaengine_dai_dma_data *dma; - - dma = snd_soc_dai_get_dma_data(rtd->cpu_dai, substream); - - /* return if this is a bufferless transfer e.g. - * codec <--> BT codec or GSM modem -- lg FIXME */ - if (!dma) - return 0; - - return pxa2xx_pcm_hw_params(substream, params); -} - -static const struct snd_pcm_ops pxa2xx_pcm_ops = { - .open = pxa2xx_pcm_open, - .close = pxa2xx_pcm_close, - .ioctl = snd_pcm_lib_ioctl, - .hw_params = __pxa2xx_pcm_hw_params, - .hw_free = pxa2xx_pcm_hw_free, - .prepare = pxa2xx_pcm_prepare, - .trigger = pxa2xx_pcm_trigger, - .pointer = pxa2xx_pcm_pointer, - .mmap = pxa2xx_pcm_mmap, -}; - -static int pxa2xx_soc_pcm_new(struct snd_soc_pcm_runtime *rtd) -{ - struct snd_card *card = rtd->card->snd_card; - struct snd_pcm *pcm = rtd->pcm; - int ret; - - ret = dma_coerce_mask_and_coherent(card->dev, DMA_BIT_MASK(32)); - if (ret) - return ret; - - if (pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream) { - ret = pxa2xx_pcm_preallocate_dma_buffer(pcm, - SNDRV_PCM_STREAM_PLAYBACK); - if (ret) - goto out; - } - - if (pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream) { - ret = pxa2xx_pcm_preallocate_dma_buffer(pcm, - SNDRV_PCM_STREAM_CAPTURE); - if (ret) - goto out; - } - out: - return ret; -} - static const struct snd_soc_component_driver pxa2xx_soc_platform = { .ops = &pxa2xx_pcm_ops, .pcm_new = pxa2xx_soc_pcm_new, -- cgit v1.2.3 From b0e9a2fe3ff971950833bc0ffc383babd9443bc4 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Thu, 28 Jun 2018 15:31:00 +0800 Subject: sctp: add support for SCTP_REUSE_PORT sockopt This feature is actually already supported by sk->sk_reuse which can be set by socket level opt SO_REUSEADDR. But it's not working exactly as RFC6458 demands in section 8.1.27, like: - This option only supports one-to-one style SCTP sockets - This socket option must not be used after calling bind() or sctp_bindx(). Besides, SCTP_REUSE_PORT sockopt should be provided for user's programs. Otherwise, the programs with SCTP_REUSE_PORT from other systems will not work in linux. To separate it from the socket level version, this patch adds 'reuse' in sctp_sock and it works pretty much as sk->sk_reuse, but with some extra setup limitations that are needed when it is being enabled. "It should be noted that the behavior of the socket-level socket option to reuse ports and/or addresses for SCTP sockets is unspecified", so it leaves SO_REUSEADDR as is for the compatibility. Note that the name SCTP_REUSE_PORT is somewhat confusing, as its functionality is nearly identical to SO_REUSEADDR, but with some extra restrictions. Here it uses 'reuse' in sctp_sock instead of 'reuseport'. As for sk->sk_reuseport support for SCTP, it will be added in another patch. Thanks to Neil to make this clear. v1->v2: - add sctp_sk->reuse to separate it from the socket level version. v2->v3: - improve changelog according to Marcelo's suggestion. Acked-by: Neil Horman Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 1 + include/uapi/linux/sctp.h | 1 + net/sctp/socket.c | 62 ++++++++++++++++++++++++++++++++++++++++------ 3 files changed, 57 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index e0f962d27386..701a51736fa5 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -220,6 +220,7 @@ struct sctp_sock { __u32 adaptation_ind; __u32 pd_point; __u16 nodelay:1, + reuse:1, disable_fragments:1, v4mapped:1, frag_interleave:1, diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index b64d583bf053..c02986a284db 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -100,6 +100,7 @@ typedef __s32 sctp_assoc_t; #define SCTP_RECVNXTINFO 33 #define SCTP_DEFAULT_SNDINFO 34 #define SCTP_AUTH_DEACTIVATE_KEY 35 +#define SCTP_REUSE_PORT 36 /* Internal Socket Options. Some of the sctp library functions are * implemented using these socket options. diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 0e91e83eea5a..bf11f9cacb63 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4170,6 +4170,28 @@ out: return retval; } +static int sctp_setsockopt_reuse_port(struct sock *sk, char __user *optval, + unsigned int optlen) +{ + int val; + + if (!sctp_style(sk, TCP)) + return -EOPNOTSUPP; + + if (sctp_sk(sk)->ep->base.bind_addr.port) + return -EFAULT; + + if (optlen < sizeof(int)) + return -EINVAL; + + if (get_user(val, (int __user *)optval)) + return -EFAULT; + + sctp_sk(sk)->reuse = !!val; + + return 0; +} + /* API 6.2 setsockopt(), getsockopt() * * Applications use setsockopt() and getsockopt() to set or retrieve @@ -4364,6 +4386,9 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname, retval = sctp_setsockopt_interleaving_supported(sk, optval, optlen); break; + case SCTP_REUSE_PORT: + retval = sctp_setsockopt_reuse_port(sk, optval, optlen); + break; default: retval = -ENOPROTOOPT; break; @@ -7197,6 +7222,26 @@ out: return retval; } +static int sctp_getsockopt_reuse_port(struct sock *sk, int len, + char __user *optval, + int __user *optlen) +{ + int val; + + if (len < sizeof(int)) + return -EINVAL; + + len = sizeof(int); + val = sctp_sk(sk)->reuse; + if (put_user(len, optlen)) + return -EFAULT; + + if (copy_to_user(optval, &val, len)) + return -EFAULT; + + return 0; +} + static int sctp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { @@ -7392,6 +7437,9 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname, retval = sctp_getsockopt_interleaving_supported(sk, len, optval, optlen); break; + case SCTP_REUSE_PORT: + retval = sctp_getsockopt_reuse_port(sk, len, optval, optlen); + break; default: retval = -ENOPROTOOPT; break; @@ -7429,6 +7477,7 @@ static struct sctp_bind_bucket *sctp_bucket_create( static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr) { + bool reuse = (sk->sk_reuse || sctp_sk(sk)->reuse); struct sctp_bind_hashbucket *head; /* hash list */ struct sctp_bind_bucket *pp; unsigned short snum; @@ -7501,13 +7550,11 @@ pp_found: * used by other socket (pp->owner not empty); that other * socket is going to be sk2. */ - int reuse = sk->sk_reuse; struct sock *sk2; pr_debug("%s: found a possible match\n", __func__); - if (pp->fastreuse && sk->sk_reuse && - sk->sk_state != SCTP_SS_LISTENING) + if (pp->fastreuse && reuse && sk->sk_state != SCTP_SS_LISTENING) goto success; /* Run through the list of sockets bound to the port @@ -7525,7 +7572,7 @@ pp_found: ep2 = sctp_sk(sk2)->ep; if (sk == sk2 || - (reuse && sk2->sk_reuse && + (reuse && (sk2->sk_reuse || sctp_sk(sk2)->reuse) && sk2->sk_state != SCTP_SS_LISTENING)) continue; @@ -7549,12 +7596,12 @@ pp_not_found: * SO_REUSEADDR on this socket -sk-). */ if (hlist_empty(&pp->owner)) { - if (sk->sk_reuse && sk->sk_state != SCTP_SS_LISTENING) + if (reuse && sk->sk_state != SCTP_SS_LISTENING) pp->fastreuse = 1; else pp->fastreuse = 0; } else if (pp->fastreuse && - (!sk->sk_reuse || sk->sk_state == SCTP_SS_LISTENING)) + (!reuse || sk->sk_state == SCTP_SS_LISTENING)) pp->fastreuse = 0; /* We are set, so fill up all the data in the hash table @@ -7685,7 +7732,7 @@ int sctp_inet_listen(struct socket *sock, int backlog) err = 0; sctp_unhash_endpoint(ep); sk->sk_state = SCTP_SS_CLOSED; - if (sk->sk_reuse) + if (sk->sk_reuse || sctp_sk(sk)->reuse) sctp_sk(sk)->bind_hash->fastreuse = 1; goto out; } @@ -8550,6 +8597,7 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk, newsk->sk_no_check_tx = sk->sk_no_check_tx; newsk->sk_no_check_rx = sk->sk_no_check_rx; newsk->sk_reuse = sk->sk_reuse; + sctp_sk(newsk)->reuse = sp->reuse; newsk->sk_shutdown = sk->sk_shutdown; newsk->sk_destruct = sctp_destruct_sock; -- cgit v1.2.3 From 256c87c17c53e60882a43dcf3e98f3bf859eaf6f Mon Sep 17 00:00:00 2001 From: Pieter Jansen van Vuuren Date: Tue, 26 Jun 2018 21:39:36 -0700 Subject: net: check tunnel option type in tunnel flags Check the tunnel option type stored in tunnel flags when creating options for tunnels. Thereby ensuring we do not set geneve, vxlan or erspan tunnel options on interfaces that are not associated with them. Make sure all users of the infrastructure set correct flags, for the BPF helper we have to set all bits to keep backward compatibility. Signed-off-by: Pieter Jansen van Vuuren Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- drivers/net/geneve.c | 6 ++++-- drivers/net/vxlan.c | 3 ++- include/net/ip_tunnels.h | 8 ++++++-- net/core/filter.c | 2 +- net/ipv4/ip_gre.c | 2 ++ net/ipv6/ip6_gre.c | 2 ++ net/openvswitch/flow_netlink.c | 7 ++++++- 7 files changed, 23 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 3e94375b9b01..471edd76ff55 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -236,7 +236,8 @@ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs, } /* Update tunnel dst according to Geneve options. */ ip_tunnel_info_opts_set(&tun_dst->u.tun_info, - gnvh->options, gnvh->opt_len * 4); + gnvh->options, gnvh->opt_len * 4, + TUNNEL_GENEVE_OPT); } else { /* Drop packets w/ critical options, * since we don't support any... @@ -675,7 +676,8 @@ static void geneve_build_header(struct genevehdr *geneveh, geneveh->proto_type = htons(ETH_P_TEB); geneveh->rsvd2 = 0; - ip_tunnel_info_opts_get(geneveh->options, info); + if (info->key.tun_flags & TUNNEL_GENEVE_OPT) + ip_tunnel_info_opts_get(geneveh->options, info); } static int geneve_build_skb(struct dst_entry *dst, struct sk_buff *skb, diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index cc14e0cd5647..7eb30d7c8bd7 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2122,7 +2122,8 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, vni = tunnel_id_to_key32(info->key.tun_id); ifindex = 0; dst_cache = &info->dst_cache; - if (info->options_len) + if (info->options_len && + info->key.tun_flags & TUNNEL_VXLAN_OPT) md = ip_tunnel_info_opts(info); ttl = info->key.ttl; tos = info->key.tos; diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 90ff430f5e9d..b0d022ff6ea1 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -466,10 +466,12 @@ static inline void ip_tunnel_info_opts_get(void *to, } static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info, - const void *from, int len) + const void *from, int len, + __be16 flags) { memcpy(ip_tunnel_info_opts(info), from, len); info->options_len = len; + info->key.tun_flags |= flags; } static inline struct ip_tunnel_info *lwt_tun_info(struct lwtunnel_state *lwtstate) @@ -511,9 +513,11 @@ static inline void ip_tunnel_info_opts_get(void *to, } static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info, - const void *from, int len) + const void *from, int len, + __be16 flags) { info->options_len = 0; + info->key.tun_flags |= flags; } #endif /* CONFIG_INET */ diff --git a/net/core/filter.c b/net/core/filter.c index e7f12e9f598c..dade922678f6 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3582,7 +3582,7 @@ BPF_CALL_3(bpf_skb_set_tunnel_opt, struct sk_buff *, skb, if (unlikely(size > IP_TUNNEL_OPTS_MAX)) return -ENOMEM; - ip_tunnel_info_opts_set(info, from, size); + ip_tunnel_info_opts_set(info, from, size, TUNNEL_OPTIONS_PRESENT); return 0; } diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 2d8efeecf619..c8ca5d8f0f75 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -587,6 +587,8 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev, goto err_free_skb; key = &tun_info->key; + if (!(tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT)) + goto err_free_rt; md = ip_tunnel_info_opts(tun_info); if (!md) goto err_free_rt; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index c8cf2fdbb13b..367177786e34 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -990,6 +990,8 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL); dsfield = key->tos; + if (!(tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT)) + goto tx_err; md = ip_tunnel_info_opts(tun_info); if (!md) goto tx_err; diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 492ab0c36f7c..391c4073a6dc 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -2516,7 +2516,9 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, struct ovs_tunnel_info *ovs_tun; struct nlattr *a; int err = 0, start, opts_type; + __be16 dst_opt_type; + dst_opt_type = 0; ovs_match_init(&match, &key, true, NULL); opts_type = ip_tun_from_nlattr(nla_data(attr), &match, false, log); if (opts_type < 0) @@ -2528,10 +2530,13 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, err = validate_geneve_opts(&key); if (err < 0) return err; + dst_opt_type = TUNNEL_GENEVE_OPT; break; case OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS: + dst_opt_type = TUNNEL_VXLAN_OPT; break; case OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS: + dst_opt_type = TUNNEL_ERSPAN_OPT; break; } } @@ -2574,7 +2579,7 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, */ ip_tunnel_info_opts_set(tun_info, TUN_METADATA_OPTS(&key, key.tun_opts_len), - key.tun_opts_len); + key.tun_opts_len, dst_opt_type); add_nested_action_end(*sfa, start); return err; -- cgit v1.2.3 From 0ed5269f9e41f495c8e9020c85f5e1644c1afc57 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Tue, 26 Jun 2018 21:39:37 -0700 Subject: net/sched: add tunnel option support to act_tunnel_key Allow setting tunnel options using the act_tunnel_key action. Options are expressed as class:type:data and multiple options may be listed using a comma delimiter. # ip link add name geneve0 type geneve dstport 0 external # tc qdisc add dev eth0 ingress # tc filter add dev eth0 protocol ip parent ffff: \ flower indev eth0 \ ip_proto udp \ action tunnel_key \ set src_ip 10.0.99.192 \ dst_ip 10.0.99.193 \ dst_port 6081 \ id 11 \ geneve_opts 0102:80:00800022,0102:80:00800022 \ action mirred egress redirect dev geneve0 Signed-off-by: Simon Horman Signed-off-by: Pieter Jansen van Vuuren Reviewed-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/uapi/linux/tc_act/tc_tunnel_key.h | 26 ++++ net/sched/act_tunnel_key.c | 214 +++++++++++++++++++++++++++++- 2 files changed, 236 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/tc_act/tc_tunnel_key.h b/include/uapi/linux/tc_act/tc_tunnel_key.h index 72bbefe5d1d1..e284fec8c467 100644 --- a/include/uapi/linux/tc_act/tc_tunnel_key.h +++ b/include/uapi/linux/tc_act/tc_tunnel_key.h @@ -36,9 +36,35 @@ enum { TCA_TUNNEL_KEY_PAD, TCA_TUNNEL_KEY_ENC_DST_PORT, /* be16 */ TCA_TUNNEL_KEY_NO_CSUM, /* u8 */ + TCA_TUNNEL_KEY_ENC_OPTS, /* Nested TCA_TUNNEL_KEY_ENC_OPTS_ + * attributes + */ __TCA_TUNNEL_KEY_MAX, }; #define TCA_TUNNEL_KEY_MAX (__TCA_TUNNEL_KEY_MAX - 1) +enum { + TCA_TUNNEL_KEY_ENC_OPTS_UNSPEC, + TCA_TUNNEL_KEY_ENC_OPTS_GENEVE, /* Nested + * TCA_TUNNEL_KEY_ENC_OPTS_ + * attributes + */ + __TCA_TUNNEL_KEY_ENC_OPTS_MAX, +}; + +#define TCA_TUNNEL_KEY_ENC_OPTS_MAX (__TCA_TUNNEL_KEY_ENC_OPTS_MAX - 1) + +enum { + TCA_TUNNEL_KEY_ENC_OPT_GENEVE_UNSPEC, + TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS, /* be16 */ + TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE, /* u8 */ + TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA, /* 4 to 128 bytes */ + + __TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX, +}; + +#define TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX \ + (__TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX - 1) + #endif diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 20e98ed8d498..ea203e386a92 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -57,6 +58,135 @@ static int tunnel_key_act(struct sk_buff *skb, const struct tc_action *a, return action; } +static const struct nla_policy +enc_opts_policy[TCA_TUNNEL_KEY_ENC_OPTS_MAX + 1] = { + [TCA_TUNNEL_KEY_ENC_OPTS_GENEVE] = { .type = NLA_NESTED }, +}; + +static const struct nla_policy +geneve_opt_policy[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX + 1] = { + [TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS] = { .type = NLA_U16 }, + [TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE] = { .type = NLA_U8 }, + [TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA] = { .type = NLA_BINARY, + .len = 128 }, +}; + +static int +tunnel_key_copy_geneve_opt(const struct nlattr *nla, void *dst, int dst_len, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX + 1]; + int err, data_len, opt_len; + u8 *data; + + err = nla_parse_nested(tb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX, + nla, geneve_opt_policy, extack); + if (err < 0) + return err; + + if (!tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS] || + !tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE] || + !tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA]) { + NL_SET_ERR_MSG(extack, "Missing tunnel key geneve option class, type or data"); + return -EINVAL; + } + + data = nla_data(tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA]); + data_len = nla_len(tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA]); + if (data_len < 4) { + NL_SET_ERR_MSG(extack, "Tunnel key geneve option data is less than 4 bytes long"); + return -ERANGE; + } + if (data_len % 4) { + NL_SET_ERR_MSG(extack, "Tunnel key geneve option data is not a multiple of 4 bytes long"); + return -ERANGE; + } + + opt_len = sizeof(struct geneve_opt) + data_len; + if (dst) { + struct geneve_opt *opt = dst; + + WARN_ON(dst_len < opt_len); + + opt->opt_class = + nla_get_be16(tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS]); + opt->type = nla_get_u8(tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE]); + opt->length = data_len / 4; /* length is in units of 4 bytes */ + opt->r1 = 0; + opt->r2 = 0; + opt->r3 = 0; + + memcpy(opt + 1, data, data_len); + } + + return opt_len; +} + +static int tunnel_key_copy_opts(const struct nlattr *nla, u8 *dst, + int dst_len, struct netlink_ext_ack *extack) +{ + int err, rem, opt_len, len = nla_len(nla), opts_len = 0; + const struct nlattr *attr, *head = nla_data(nla); + + err = nla_validate(head, len, TCA_TUNNEL_KEY_ENC_OPTS_MAX, + enc_opts_policy, extack); + if (err) + return err; + + nla_for_each_attr(attr, head, len, rem) { + switch (nla_type(attr)) { + case TCA_TUNNEL_KEY_ENC_OPTS_GENEVE: + opt_len = tunnel_key_copy_geneve_opt(attr, dst, + dst_len, extack); + if (opt_len < 0) + return opt_len; + opts_len += opt_len; + if (dst) { + dst_len -= opt_len; + dst += opt_len; + } + break; + } + } + + if (!opts_len) { + NL_SET_ERR_MSG(extack, "Empty list of tunnel options"); + return -EINVAL; + } + + if (rem > 0) { + NL_SET_ERR_MSG(extack, "Trailing data after parsing tunnel key options attributes"); + return -EINVAL; + } + + return opts_len; +} + +static int tunnel_key_get_opts_len(struct nlattr *nla, + struct netlink_ext_ack *extack) +{ + return tunnel_key_copy_opts(nla, NULL, 0, extack); +} + +static int tunnel_key_opts_set(struct nlattr *nla, struct ip_tunnel_info *info, + int opts_len, struct netlink_ext_ack *extack) +{ + info->options_len = opts_len; + switch (nla_type(nla_data(nla))) { + case TCA_TUNNEL_KEY_ENC_OPTS_GENEVE: +#if IS_ENABLED(CONFIG_INET) + info->key.tun_flags |= TUNNEL_GENEVE_OPT; + return tunnel_key_copy_opts(nla, ip_tunnel_info_opts(info), + opts_len, extack); +#else + return -EAFNOSUPPORT; +#endif + default: + NL_SET_ERR_MSG(extack, "Cannot set tunnel options for unknown tunnel type"); + return -EINVAL; + } +} + static const struct nla_policy tunnel_key_policy[TCA_TUNNEL_KEY_MAX + 1] = { [TCA_TUNNEL_KEY_PARMS] = { .len = sizeof(struct tc_tunnel_key) }, [TCA_TUNNEL_KEY_ENC_IPV4_SRC] = { .type = NLA_U32 }, @@ -66,6 +196,7 @@ static const struct nla_policy tunnel_key_policy[TCA_TUNNEL_KEY_MAX + 1] = { [TCA_TUNNEL_KEY_ENC_KEY_ID] = { .type = NLA_U32 }, [TCA_TUNNEL_KEY_ENC_DST_PORT] = {.type = NLA_U16}, [TCA_TUNNEL_KEY_NO_CSUM] = { .type = NLA_U8 }, + [TCA_TUNNEL_KEY_ENC_OPTS] = { .type = NLA_NESTED }, }; static int tunnel_key_init(struct net *net, struct nlattr *nla, @@ -81,6 +212,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, struct tcf_tunnel_key *t; bool exists = false; __be16 dst_port = 0; + int opts_len = 0; __be64 key_id; __be16 flags; int ret = 0; @@ -128,6 +260,15 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, if (tb[TCA_TUNNEL_KEY_ENC_DST_PORT]) dst_port = nla_get_be16(tb[TCA_TUNNEL_KEY_ENC_DST_PORT]); + if (tb[TCA_TUNNEL_KEY_ENC_OPTS]) { + opts_len = tunnel_key_get_opts_len(tb[TCA_TUNNEL_KEY_ENC_OPTS], + extack); + if (opts_len < 0) { + ret = opts_len; + goto err_out; + } + } + if (tb[TCA_TUNNEL_KEY_ENC_IPV4_SRC] && tb[TCA_TUNNEL_KEY_ENC_IPV4_DST]) { __be32 saddr; @@ -138,7 +279,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, metadata = __ip_tun_set_dst(saddr, daddr, 0, 0, dst_port, flags, - key_id, 0); + key_id, opts_len); } else if (tb[TCA_TUNNEL_KEY_ENC_IPV6_SRC] && tb[TCA_TUNNEL_KEY_ENC_IPV6_DST]) { struct in6_addr saddr; @@ -162,6 +303,14 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, goto err_out; } + if (opts_len) { + ret = tunnel_key_opts_set(tb[TCA_TUNNEL_KEY_ENC_OPTS], + &metadata->u.tun_info, + opts_len, extack); + if (ret < 0) + goto err_out; + } + metadata->u.tun_info.mode |= IP_TUNNEL_INFO_TX; break; default: @@ -234,6 +383,61 @@ static void tunnel_key_release(struct tc_action *a) } } +static int tunnel_key_geneve_opts_dump(struct sk_buff *skb, + const struct ip_tunnel_info *info) +{ + int len = info->options_len; + u8 *src = (u8 *)(info + 1); + struct nlattr *start; + + start = nla_nest_start(skb, TCA_TUNNEL_KEY_ENC_OPTS_GENEVE); + if (!start) + return -EMSGSIZE; + + while (len > 0) { + struct geneve_opt *opt = (struct geneve_opt *)src; + + if (nla_put_be16(skb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS, + opt->opt_class) || + nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE, + opt->type) || + nla_put(skb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA, + opt->length * 4, opt + 1)) + return -EMSGSIZE; + + len -= sizeof(struct geneve_opt) + opt->length * 4; + src += sizeof(struct geneve_opt) + opt->length * 4; + } + + nla_nest_end(skb, start); + return 0; +} + +static int tunnel_key_opts_dump(struct sk_buff *skb, + const struct ip_tunnel_info *info) +{ + struct nlattr *start; + int err; + + if (!info->options_len) + return 0; + + start = nla_nest_start(skb, TCA_TUNNEL_KEY_ENC_OPTS); + if (!start) + return -EMSGSIZE; + + if (info->key.tun_flags & TUNNEL_GENEVE_OPT) { + err = tunnel_key_geneve_opts_dump(skb, info); + if (err) + return err; + } else { + return -EINVAL; + } + + nla_nest_end(skb, start); + return 0; +} + static int tunnel_key_dump_addresses(struct sk_buff *skb, const struct ip_tunnel_info *info) { @@ -284,8 +488,9 @@ static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a, goto nla_put_failure; if (params->tcft_action == TCA_TUNNEL_KEY_ACT_SET) { - struct ip_tunnel_key *key = - ¶ms->tcft_enc_metadata->u.tun_info.key; + struct ip_tunnel_info *info = + ¶ms->tcft_enc_metadata->u.tun_info; + struct ip_tunnel_key *key = &info->key; __be32 key_id = tunnel_id_to_key32(key->tun_id); if (nla_put_be32(skb, TCA_TUNNEL_KEY_ENC_KEY_ID, key_id) || @@ -293,7 +498,8 @@ static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a, ¶ms->tcft_enc_metadata->u.tun_info) || nla_put_be16(skb, TCA_TUNNEL_KEY_ENC_DST_PORT, key->tp_dst) || nla_put_u8(skb, TCA_TUNNEL_KEY_NO_CSUM, - !(key->tun_flags & TUNNEL_CSUM))) + !(key->tun_flags & TUNNEL_CSUM)) || + tunnel_key_opts_dump(skb, info)) goto nla_put_failure; } -- cgit v1.2.3 From debef195bd5c79210d60f1d6dec38bde3dae2b88 Mon Sep 17 00:00:00 2001 From: Anson Huang Date: Sun, 3 Jun 2018 09:44:04 +0800 Subject: clk: imx6ul: add GPIO clock gates i.MX6UL has GPIO clock gates in CCM CCGR, add them into clock tree for clock management. Signed-off-by: Anson Huang Reviewed-by: Fabio Estevam Acked-by: Rob Herring Signed-off-by: Stephen Boyd --- drivers/clk/imx/clk-imx6ul.c | 5 +++++ include/dt-bindings/clock/imx6ul-clock.h | 8 +++++++- 2 files changed, 12 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/clk/imx/clk-imx6ul.c b/drivers/clk/imx/clk-imx6ul.c index ba563ba50b40..3ea2d97562fd 100644 --- a/drivers/clk/imx/clk-imx6ul.c +++ b/drivers/clk/imx/clk-imx6ul.c @@ -360,6 +360,7 @@ static void __init imx6ul_clocks_init(struct device_node *ccm_node) clks[IMX6UL_CLK_UART2_SERIAL] = imx_clk_gate2("uart2_serial", "uart_podf", base + 0x68, 28); if (clk_on_imx6ull()) clks[IMX6UL_CLK_AIPSTZ3] = imx_clk_gate2("aips_tz3", "ahb", base + 0x80, 18); + clks[IMX6UL_CLK_GPIO2] = imx_clk_gate2("gpio2", "ipg", base + 0x68, 30); /* CCGR1 */ clks[IMX6UL_CLK_ECSPI1] = imx_clk_gate2("ecspi1", "ecspi_podf", base + 0x6c, 0); @@ -376,6 +377,8 @@ static void __init imx6ul_clocks_init(struct device_node *ccm_node) clks[IMX6UL_CLK_GPT1_SERIAL] = imx_clk_gate2("gpt1_serial", "perclk", base + 0x6c, 22); clks[IMX6UL_CLK_UART4_IPG] = imx_clk_gate2("uart4_ipg", "ipg", base + 0x6c, 24); clks[IMX6UL_CLK_UART4_SERIAL] = imx_clk_gate2("uart4_serial", "uart_podf", base + 0x6c, 24); + clks[IMX6UL_CLK_GPIO1] = imx_clk_gate2("gpio1", "ipg", base + 0x6c, 26); + clks[IMX6UL_CLK_GPIO5] = imx_clk_gate2("gpio5", "ipg", base + 0x6c, 30); /* CCGR2 */ if (clk_on_imx6ull()) { @@ -389,6 +392,7 @@ static void __init imx6ul_clocks_init(struct device_node *ccm_node) clks[IMX6UL_CLK_I2C3] = imx_clk_gate2("i2c3", "perclk", base + 0x70, 10); clks[IMX6UL_CLK_OCOTP] = imx_clk_gate2("ocotp", "ipg", base + 0x70, 12); clks[IMX6UL_CLK_IOMUXC] = imx_clk_gate2("iomuxc", "lcdif_podf", base + 0x70, 14); + clks[IMX6UL_CLK_GPIO3] = imx_clk_gate2("gpio3", "ipg", base + 0x70, 26); clks[IMX6UL_CLK_LCDIF_APB] = imx_clk_gate2("lcdif_apb", "axi", base + 0x70, 28); clks[IMX6UL_CLK_PXP] = imx_clk_gate2("pxp", "axi", base + 0x70, 30); @@ -405,6 +409,7 @@ static void __init imx6ul_clocks_init(struct device_node *ccm_node) clks[IMX6UL_CLK_UART6_IPG] = imx_clk_gate2("uart6_ipg", "ipg", base + 0x74, 6); clks[IMX6UL_CLK_UART6_SERIAL] = imx_clk_gate2("uart6_serial", "uart_podf", base + 0x74, 6); clks[IMX6UL_CLK_LCDIF_PIX] = imx_clk_gate2("lcdif_pix", "lcdif_podf", base + 0x74, 10); + clks[IMX6UL_CLK_GPIO4] = imx_clk_gate2("gpio4", "ipg", base + 0x74, 12); clks[IMX6UL_CLK_QSPI] = imx_clk_gate2("qspi1", "qspi1_podf", base + 0x74, 14); clks[IMX6UL_CLK_WDOG1] = imx_clk_gate2("wdog1", "ipg", base + 0x74, 16); clks[IMX6UL_CLK_MMDC_P0_FAST] = imx_clk_gate("mmdc_p0_fast", "mmdc_podf", base + 0x74, 20); diff --git a/include/dt-bindings/clock/imx6ul-clock.h b/include/dt-bindings/clock/imx6ul-clock.h index 0aa1d9c3e0b9..f8e0476a3a0e 100644 --- a/include/dt-bindings/clock/imx6ul-clock.h +++ b/include/dt-bindings/clock/imx6ul-clock.h @@ -254,6 +254,12 @@ #define IMX6UL_CLK_CKO2_PODF 241 #define IMX6UL_CLK_CKO2 242 #define IMX6UL_CLK_CKO 243 -#define IMX6UL_CLK_END 244 +#define IMX6UL_CLK_GPIO1 244 +#define IMX6UL_CLK_GPIO2 245 +#define IMX6UL_CLK_GPIO3 246 +#define IMX6UL_CLK_GPIO4 247 +#define IMX6UL_CLK_GPIO5 248 + +#define IMX6UL_CLK_END 249 #endif /* __DT_BINDINGS_CLOCK_IMX6UL_H */ -- cgit v1.2.3 From 14d9deeb273c2bf4ec256589adabd8df65395d36 Mon Sep 17 00:00:00 2001 From: Eric Anholt Date: Wed, 20 Jun 2018 17:17:03 -0700 Subject: drm/v3d: Define the fourcc modifier for the Broadcom UIF format. This will be used by Mesa, and potentially other drivers in the future, to describe tiled buffers. Signed-off-by: Eric Anholt Link: https://patchwork.freedesktop.org/patch/msgid/20180621001703.13522-1-eric@anholt.net Acked-by: Daniel Vetter --- include/uapi/drm/drm_fourcc.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include') diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h index 64bf67abff7e..d5e52350a3aa 100644 --- a/include/uapi/drm/drm_fourcc.h +++ b/include/uapi/drm/drm_fourcc.h @@ -464,6 +464,27 @@ extern "C" { #define DRM_FORMAT_MOD_BROADCOM_SAND256 \ DRM_FORMAT_MOD_BROADCOM_SAND256_COL_HEIGHT(0) +/* Broadcom UIF format + * + * This is the common format for the current Broadcom multimedia + * blocks, including V3D 3.x and newer, newer video codecs, and + * displays. + * + * The image consists of utiles (64b blocks), UIF blocks (2x2 utiles), + * and macroblocks (4x4 UIF blocks). Those 4x4 UIF block groups are + * stored in columns, with padding between the columns to ensure that + * moving from one column to the next doesn't hit the same SDRAM page + * bank. + * + * To calculate the padding, it is assumed that each hardware block + * and the software driving it knows the platform's SDRAM page size, + * number of banks, and XOR address, and that it's identical between + * all blocks using the format. This tiling modifier will use XOR as + * necessary to reduce the padding. If a hardware block can't do XOR, + * the assumption is that a no-XOR tiling modifier will be created. + */ +#define DRM_FORMAT_MOD_BROADCOM_UIF fourcc_mod_code(BROADCOM, 6) + #if defined(__cplusplus) } #endif -- cgit v1.2.3 From b1277a226d8c519b8c33e23fe68b4e1658f15963 Mon Sep 17 00:00:00 2001 From: Christian König Date: Fri, 29 Jun 2018 19:55:03 -0500 Subject: PCI: Cleanup PCI_REBAR_CTRL_BAR_SHIFT handling MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Cleanup PCI_REBAR_CTRL_BAR_SHIFT handling. That was hard coded instead of properly defined in the header for some reason. Signed-off-by: Christian König Signed-off-by: Bjorn Helgaas --- drivers/pci/pci.c | 6 +++--- include/uapi/linux/pci_regs.h | 3 ++- 2 files changed, 5 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 44ccfb31363e..1b20c4392f09 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1193,7 +1193,7 @@ static void pci_restore_rebar_state(struct pci_dev *pdev) res = pdev->resource + bar_idx; size = order_base_2((resource_size(res) >> 20) | 1) - 1; ctrl &= ~PCI_REBAR_CTRL_BAR_SIZE; - ctrl |= size << 8; + ctrl |= size << PCI_REBAR_CTRL_BAR_SHIFT; pci_write_config_dword(pdev, pos + PCI_REBAR_CTRL, ctrl); } } @@ -3098,7 +3098,7 @@ int pci_rebar_get_current_size(struct pci_dev *pdev, int bar) return pos; pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl); - return (ctrl & PCI_REBAR_CTRL_BAR_SIZE) >> 8; + return (ctrl & PCI_REBAR_CTRL_BAR_SIZE) >> PCI_REBAR_CTRL_BAR_SHIFT; } /** @@ -3121,7 +3121,7 @@ int pci_rebar_set_size(struct pci_dev *pdev, int bar, int size) pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl); ctrl &= ~PCI_REBAR_CTRL_BAR_SIZE; - ctrl |= size << 8; + ctrl |= size << PCI_REBAR_CTRL_BAR_SHIFT; pci_write_config_dword(pdev, pos + PCI_REBAR_CTRL, ctrl); return 0; } diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index 4da87e2ef8a8..82e6b361204e 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -960,8 +960,9 @@ #define PCI_REBAR_CTRL 8 /* control register */ #define PCI_REBAR_CTRL_BAR_IDX 0x00000007 /* BAR index */ #define PCI_REBAR_CTRL_NBAR_MASK 0x000000E0 /* # of resizable BARs */ -#define PCI_REBAR_CTRL_NBAR_SHIFT 5 /* shift for # of BARs */ +#define PCI_REBAR_CTRL_NBAR_SHIFT 5 /* shift for # of BARs */ #define PCI_REBAR_CTRL_BAR_SIZE 0x00001F00 /* BAR size */ +#define PCI_REBAR_CTRL_BAR_SHIFT 8 /* shift for BAR size */ /* Dynamic Power Allocation */ #define PCI_DPA_CAP 4 /* capability register */ -- cgit v1.2.3 From cfdfc14e7fb8ae77290e9d5afaeecc0a234a3846 Mon Sep 17 00:00:00 2001 From: Doug Meyer Date: Wed, 23 May 2018 13:18:05 -0700 Subject: switchtec: Use generic PCI Vendor ID and Class Code Move the Microsemi Switchtec PCI Vendor ID (same as PCI_VENDOR_ID_PMC_Sierra) to pci_ids.h. Also, replace Microsemi class constants with the standard PCI definitions. Signed-off-by: Doug Meyer [bhelgaas: restore SPDX (I assume it was removed by mistake), remove device ID definitions] Signed-off-by: Bjorn Helgaas Reviewed-by: Logan Gunthorpe --- drivers/ntb/hw/mscc/ntb_hw_switchtec.c | 3 ++- drivers/pci/switch/switchtec.c | 14 +++++++------- include/linux/pci_ids.h | 1 + include/linux/switchtec.h | 4 ---- 4 files changed, 10 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/drivers/ntb/hw/mscc/ntb_hw_switchtec.c b/drivers/ntb/hw/mscc/ntb_hw_switchtec.c index f624ae27eabe..5ee5f40b4dfc 100644 --- a/drivers/ntb/hw/mscc/ntb_hw_switchtec.c +++ b/drivers/ntb/hw/mscc/ntb_hw_switchtec.c @@ -19,6 +19,7 @@ #include #include #include +#include MODULE_DESCRIPTION("Microsemi Switchtec(tm) NTB Driver"); MODULE_VERSION("0.1"); @@ -1487,7 +1488,7 @@ static int switchtec_ntb_add(struct device *dev, stdev->sndev = NULL; - if (stdev->pdev->class != MICROSEMI_NTB_CLASSCODE) + if (stdev->pdev->class != (PCI_CLASS_BRIDGE_OTHER << 8)) return -ENODEV; sndev = kzalloc_node(sizeof(*sndev), GFP_KERNEL, dev_to_node(dev)); diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c index 47cd0c037433..9940cc70f38b 100644 --- a/drivers/pci/switch/switchtec.c +++ b/drivers/pci/switch/switchtec.c @@ -641,7 +641,7 @@ static int ioctl_event_summary(struct switchtec_dev *stdev, for (i = 0; i < SWITCHTEC_MAX_PFF_CSR; i++) { reg = ioread16(&stdev->mmio_pff_csr[i].vendor_id); - if (reg != MICROSEMI_VENDOR_ID) + if (reg != PCI_VENDOR_ID_MICROSEMI) break; reg = ioread32(&stdev->mmio_pff_csr[i].pff_event_summary); @@ -1203,7 +1203,7 @@ static void init_pff(struct switchtec_dev *stdev) for (i = 0; i < SWITCHTEC_MAX_PFF_CSR; i++) { reg = ioread16(&stdev->mmio_pff_csr[i].vendor_id); - if (reg != MICROSEMI_VENDOR_ID) + if (reg != PCI_VENDOR_ID_MICROSEMI) break; } @@ -1267,7 +1267,7 @@ static int switchtec_pci_probe(struct pci_dev *pdev, struct switchtec_dev *stdev; int rc; - if (pdev->class == MICROSEMI_NTB_CLASSCODE) + if (pdev->class == (PCI_CLASS_BRIDGE_OTHER << 8)) request_module_nowait("ntb_hw_switchtec"); stdev = stdev_create(pdev); @@ -1321,19 +1321,19 @@ static void switchtec_pci_remove(struct pci_dev *pdev) #define SWITCHTEC_PCI_DEVICE(device_id) \ { \ - .vendor = MICROSEMI_VENDOR_ID, \ + .vendor = PCI_VENDOR_ID_MICROSEMI, \ .device = device_id, \ .subvendor = PCI_ANY_ID, \ .subdevice = PCI_ANY_ID, \ - .class = MICROSEMI_MGMT_CLASSCODE, \ + .class = (PCI_CLASS_MEMORY_OTHER << 8), \ .class_mask = 0xFFFFFFFF, \ }, \ { \ - .vendor = MICROSEMI_VENDOR_ID, \ + .vendor = PCI_VENDOR_ID_MICROSEMI, \ .device = device_id, \ .subvendor = PCI_ANY_ID, \ .subdevice = PCI_ANY_ID, \ - .class = MICROSEMI_NTB_CLASSCODE, \ + .class = (PCI_CLASS_BRIDGE_OTHER << 8), \ .class_mask = 0xFFFFFFFF, \ } diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 29502238e510..80aec5b9a6c1 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1668,6 +1668,7 @@ #define PCI_DEVICE_ID_COMPEX_ENET100VG4 0x0112 #define PCI_VENDOR_ID_PMC_Sierra 0x11f8 +#define PCI_VENDOR_ID_MICROSEMI 0x11f8 #define PCI_VENDOR_ID_RP 0x11fe #define PCI_DEVICE_ID_RP32INTF 0x0001 diff --git a/include/linux/switchtec.h b/include/linux/switchtec.h index ec93e93371fa..ab400af6f0ce 100644 --- a/include/linux/switchtec.h +++ b/include/linux/switchtec.h @@ -19,10 +19,6 @@ #include #include -#define MICROSEMI_VENDOR_ID 0x11f8 -#define MICROSEMI_NTB_CLASSCODE 0x068000 -#define MICROSEMI_MGMT_CLASSCODE 0x058000 - #define SWITCHTEC_MRPC_PAYLOAD_SIZE 1024 #define SWITCHTEC_MAX_PFF_CSR 48 -- cgit v1.2.3 From 783e84961b1d7a75045383586b8c49e02b7704cd Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Fri, 29 Jun 2018 21:17:26 -0500 Subject: PCI: Make pci_get_rom_size() static pci_get_rom_size() is called only from pci_map_rom(), so it can be static. Make it static and remove the declaration from include/linux/pci.h. Signed-off-by: Bjorn Helgaas --- drivers/pci/rom.c | 3 ++- include/linux/pci.h | 1 - 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/pci/rom.c b/drivers/pci/rom.c index 3a33f5ce314a..137bf0cee897 100644 --- a/drivers/pci/rom.c +++ b/drivers/pci/rom.c @@ -80,7 +80,8 @@ EXPORT_SYMBOL_GPL(pci_disable_rom); * The PCI window size could be much larger than the * actual image size. */ -size_t pci_get_rom_size(struct pci_dev *pdev, void __iomem *rom, size_t size) +static size_t pci_get_rom_size(struct pci_dev *pdev, void __iomem *rom, + size_t size) { void __iomem *image; int last_image; diff --git a/include/linux/pci.h b/include/linux/pci.h index 340029b2fb38..f40d3e05ccd1 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1122,7 +1122,6 @@ int pci_enable_rom(struct pci_dev *pdev); void pci_disable_rom(struct pci_dev *pdev); void __iomem __must_check *pci_map_rom(struct pci_dev *pdev, size_t *size); void pci_unmap_rom(struct pci_dev *pdev, void __iomem *rom); -size_t pci_get_rom_size(struct pci_dev *pdev, void __iomem *rom, size_t size); void __iomem __must_check *pci_platform_rom(struct pci_dev *pdev, size_t *size); /* Power management related routines */ -- cgit v1.2.3 From ea5d0c32498e1a08ff5f3dbeafa4d74895851b0d Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Thu, 28 Jun 2018 00:22:56 -0400 Subject: tcp: add new SNMP counter for drops when try to queue in rcv queue When sk_rmem_alloc is larger than the receive buffer and we can't schedule more memory for it, the skb will be dropped. In above situation, if this skb is put into the ofo queue, LINUX_MIB_TCPOFODROP is incremented to track it. While if this skb is put into the receive queue, there's no record. So a new SNMP counter is introduced to track this behavior. LINUX_MIB_TCPRCVQDROP: Number of packets meant to be queued in rcv queue but dropped because socket rcvbuf limit hit. Signed-off-by: Yafang Shao Signed-off-by: David S. Miller --- include/uapi/linux/snmp.h | 1 + net/ipv4/proc.c | 1 + net/ipv4/tcp_input.c | 8 ++++++-- 3 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index 97517f36a5f9..e5ebc83827ab 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -280,6 +280,7 @@ enum LINUX_MIB_TCPDELIVEREDCE, /* TCPDeliveredCE */ LINUX_MIB_TCPACKCOMPRESSED, /* TCPAckCompressed */ LINUX_MIB_TCPZEROWINDOWDROP, /* TCPZeroWindowDrop */ + LINUX_MIB_TCPRCVQDROP, /* TCPRcvQDrop */ __LINUX_MIB_MAX }; diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 225ef3433fe5..b46e4cf9a55a 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -288,6 +288,7 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPDeliveredCE", LINUX_MIB_TCPDELIVEREDCE), SNMP_MIB_ITEM("TCPAckCompressed", LINUX_MIB_TCPACKCOMPRESSED), SNMP_MIB_ITEM("TCPZeroWindowDrop", LINUX_MIB_TCPZEROWINDOWDROP), + SNMP_MIB_ITEM("TCPRcvQDrop", LINUX_MIB_TCPRCVQDROP), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 9c5b3415413f..eecd359595fc 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4611,8 +4611,10 @@ int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size) skb->data_len = data_len; skb->len = size; - if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) + if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVQDROP); goto err_free; + } err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, size); if (err) @@ -4677,8 +4679,10 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) queue_and_out: if (skb_queue_len(&sk->sk_receive_queue) == 0) sk_forced_mem_schedule(sk, skb->truesize); - else if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) + else if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVQDROP); goto drop; + } eaten = tcp_queue_rcv(sk, skb, 0, &fragstolen); tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq); -- cgit v1.2.3 From 0afff91c6f5ecef27715ea71e34dc2baacba1060 Mon Sep 17 00:00:00 2001 From: Ursula Braun Date: Thu, 28 Jun 2018 19:05:05 +0200 Subject: net/smc: add pnetid support s390 hardware supports the definition of a so-call Physical NETwork IDentifier (short PNETID) per network device port. These PNETIDS can be used to identify network devices that are attached to the same physical network (broadcast domain). On s390 try to use the PNETID of the ethernet device port used for initial connecting, and derive the IB device port used for SMC RDMA traffic. On platforms without PNETID support fall back to the existing solution of a configured pnet table. Signed-off-by: Ursula Braun Signed-off-by: David S. Miller --- include/net/smc.h | 2 + net/smc/smc_ib.c | 6 ++- net/smc/smc_ib.h | 3 ++ net/smc/smc_pnet.c | 109 +++++++++++++++++++++++++++++++++++++++++++---------- net/smc/smc_pnet.h | 14 +++++++ 5 files changed, 114 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/net/smc.h b/include/net/smc.h index 8381d163fefa..2173932fab9d 100644 --- a/include/net/smc.h +++ b/include/net/smc.h @@ -11,6 +11,8 @@ #ifndef _SMC_H #define _SMC_H +#define SMC_MAX_PNETID_LEN 16 /* Max. length of PNET id */ + struct smc_hashinfo { rwlock_t lock; struct hlist_head ht; diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index f8b159ced032..36de2fd76170 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -504,8 +504,12 @@ static void smc_ib_add_dev(struct ib_device *ibdev) port_cnt = smcibdev->ibdev->phys_port_cnt; for (i = 0; i < min_t(size_t, port_cnt, SMC_MAX_PORTS); - i++) + i++) { set_bit(i, &smcibdev->port_event_mask); + /* determine pnetids of the port */ + smc_pnetid_by_dev_port(ibdev->dev.parent, i, + smcibdev->pnetid[i]); + } schedule_work(&smcibdev->port_event_work); } diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h index 2c480b352928..7c1223c91229 100644 --- a/net/smc/smc_ib.h +++ b/net/smc/smc_ib.h @@ -15,6 +15,7 @@ #include #include #include +#include #define SMC_MAX_PORTS 2 /* Max # of ports */ #define SMC_GID_SIZE sizeof(union ib_gid) @@ -40,6 +41,8 @@ struct smc_ib_device { /* ib-device infos for smc */ char mac[SMC_MAX_PORTS][ETH_ALEN]; /* mac address per port*/ union ib_gid gid[SMC_MAX_PORTS]; /* gid per port */ + u8 pnetid[SMC_MAX_PORTS][SMC_MAX_PNETID_LEN]; + /* pnetid per port */ u8 initialized : 1; /* ib dev CQ, evthdl done */ struct work_struct port_event_work; unsigned long port_event_mask; diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index a82a5cad0282..cdc6e23b6ce1 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -23,12 +23,10 @@ #include "smc_pnet.h" #include "smc_ib.h" -#define SMC_MAX_PNET_ID_LEN 16 /* Max. length of PNET id */ - static struct nla_policy smc_pnet_policy[SMC_PNETID_MAX + 1] = { [SMC_PNETID_NAME] = { .type = NLA_NUL_STRING, - .len = SMC_MAX_PNET_ID_LEN - 1 + .len = SMC_MAX_PNETID_LEN - 1 }, [SMC_PNETID_ETHNAME] = { .type = NLA_NUL_STRING, @@ -65,7 +63,7 @@ static struct smc_pnettable { */ struct smc_pnetentry { struct list_head list; - char pnet_name[SMC_MAX_PNET_ID_LEN + 1]; + char pnet_name[SMC_MAX_PNETID_LEN + 1]; struct net_device *ndev; struct smc_ib_device *smcibdev; u8 ib_port; @@ -209,7 +207,7 @@ static bool smc_pnetid_valid(const char *pnet_name, char *pnetid) return false; while (--end >= bf && isspace(*end)) ; - if (end - bf >= SMC_MAX_PNET_ID_LEN) + if (end - bf >= SMC_MAX_PNETID_LEN) return false; while (bf <= end) { if (!isalnum(*bf)) @@ -512,26 +510,70 @@ void smc_pnet_exit(void) genl_unregister_family(&smc_pnet_nl_family); } -/* PNET table analysis for a given sock: - * determine ib_device and port belonging to used internal TCP socket - * ethernet interface. +/* Determine one base device for stacked net devices. + * If the lower device level contains more than one devices + * (for instance with bonding slaves), just the first device + * is used to reach a base device. */ -void smc_pnet_find_roce_resource(struct sock *sk, - struct smc_ib_device **smcibdev, u8 *ibport) +static struct net_device *pnet_find_base_ndev(struct net_device *ndev) { - struct dst_entry *dst = sk_dst_get(sk); - struct smc_pnetentry *pnetelem; + int i, nest_lvl; - *smcibdev = NULL; - *ibport = 0; + rtnl_lock(); + nest_lvl = dev_get_nest_level(ndev); + for (i = 0; i < nest_lvl; i++) { + struct list_head *lower = &ndev->adj_list.lower; + + if (list_empty(lower)) + break; + lower = lower->next; + ndev = netdev_lower_get_next(ndev, &lower); + } + rtnl_unlock(); + return ndev; +} + +/* Determine the corresponding IB device port based on the hardware PNETID. + * Searching stops at the first matching active IB device port. + */ +static void smc_pnet_find_roce_by_pnetid(struct net_device *ndev, + struct smc_ib_device **smcibdev, + u8 *ibport) +{ + u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; + struct smc_ib_device *ibdev; + int i; + + ndev = pnet_find_base_ndev(ndev); + if (smc_pnetid_by_dev_port(ndev->dev.parent, ndev->dev_port, + ndev_pnetid)) + return; /* pnetid could not be determined */ + + spin_lock(&smc_ib_devices.lock); + list_for_each_entry(ibdev, &smc_ib_devices.list, list) { + for (i = 1; i <= SMC_MAX_PORTS; i++) { + if (!memcmp(ibdev->pnetid[i - 1], ndev_pnetid, + SMC_MAX_PNETID_LEN) && + smc_ib_port_active(ibdev, i)) { + *smcibdev = ibdev; + *ibport = i; + break; + } + } + } + spin_unlock(&smc_ib_devices.lock); +} + +/* Lookup of coupled ib_device via SMC pnet table */ +static void smc_pnet_find_roce_by_table(struct net_device *netdev, + struct smc_ib_device **smcibdev, + u8 *ibport) +{ + struct smc_pnetentry *pnetelem; - if (!dst) - return; - if (!dst->dev) - goto out_rel; read_lock(&smc_pnettable.lock); list_for_each_entry(pnetelem, &smc_pnettable.pnetlist, list) { - if (dst->dev == pnetelem->ndev) { + if (netdev == pnetelem->ndev) { if (smc_ib_port_active(pnetelem->smcibdev, pnetelem->ib_port)) { *smcibdev = pnetelem->smcibdev; @@ -541,6 +583,35 @@ void smc_pnet_find_roce_resource(struct sock *sk, } } read_unlock(&smc_pnettable.lock); +} + +/* PNET table analysis for a given sock: + * determine ib_device and port belonging to used internal TCP socket + * ethernet interface. + */ +void smc_pnet_find_roce_resource(struct sock *sk, + struct smc_ib_device **smcibdev, u8 *ibport) +{ + struct dst_entry *dst = sk_dst_get(sk); + + *smcibdev = NULL; + *ibport = 0; + + if (!dst) + goto out; + if (!dst->dev) + goto out_rel; + + /* if possible, lookup via hardware-defined pnetid */ + smc_pnet_find_roce_by_pnetid(dst->dev, smcibdev, ibport); + if (*smcibdev) + goto out_rel; + + /* lookup via SMC PNET table */ + smc_pnet_find_roce_by_table(dst->dev, smcibdev, ibport); + out_rel: dst_release(dst); +out: + return; } diff --git a/net/smc/smc_pnet.h b/net/smc/smc_pnet.h index 5a29519db976..ad4455cde9e7 100644 --- a/net/smc/smc_pnet.h +++ b/net/smc/smc_pnet.h @@ -12,8 +12,22 @@ #ifndef _SMC_PNET_H #define _SMC_PNET_H +#if IS_ENABLED(CONFIG_HAVE_PNETID) +#include +#endif + struct smc_ib_device; +static inline int smc_pnetid_by_dev_port(struct device *dev, + unsigned short port, u8 *pnetid) +{ +#if IS_ENABLED(CONFIG_HAVE_PNETID) + return pnet_id_by_dev_port(dev, port, pnetid); +#else + return -ENOENT; +#endif +} + int smc_pnet_init(void) __init; void smc_pnet_exit(void); int smc_pnet_remove_by_ibdev(struct smc_ib_device *ibdev); -- cgit v1.2.3 From c6ba7c9ba43de1b57e9a53946e7ff988554c84ed Mon Sep 17 00:00:00 2001 From: Hans Wippel Date: Thu, 28 Jun 2018 19:05:07 +0200 Subject: net/smc: add base infrastructure for SMC-D and ISM SMC supports two variants: SMC-R and SMC-D. For data transport, SMC-R uses RDMA devices, SMC-D uses so-called Internal Shared Memory (ISM) devices. An ISM device only allows shared memory communication between SMC instances on the same machine. For example, this allows virtual machines on the same host to communicate via SMC without RDMA devices. This patch adds the base infrastructure for SMC-D and ISM devices to the existing SMC code. It contains the following: * ISM driver interface: This interface allows an ISM driver to register ISM devices in SMC. In the process, the driver provides a set of device ops for each device. SMC uses these ops to execute SMC specific operations on or transfer data over the device. * Core SMC-D link group, connection, and buffer support: Link groups, SMC connections and SMC buffers (in smc_core) are extended to support SMC-D. * SMC type checks: Some type checks are added to prevent using SMC-R specific code for SMC-D and vice versa. To actually use SMC-D, additional changes to pnetid, CLC, CDC, etc. are required. These are added in follow-up patches. Signed-off-by: Hans Wippel Signed-off-by: Ursula Braun Suggested-by: Thomas Richter Signed-off-by: David S. Miller --- include/net/smc.h | 62 +++++++++++ net/smc/Makefile | 2 +- net/smc/af_smc.c | 11 +- net/smc/smc_core.c | 270 +++++++++++++++++++++++++++++++++++------------ net/smc/smc_core.h | 71 +++++++++---- net/smc/smc_diag.c | 3 +- net/smc/smc_ism.c | 304 +++++++++++++++++++++++++++++++++++++++++++++++++++++ net/smc/smc_ism.h | 48 +++++++++ 8 files changed, 679 insertions(+), 92 deletions(-) create mode 100644 net/smc/smc_ism.c create mode 100644 net/smc/smc_ism.h (limited to 'include') diff --git a/include/net/smc.h b/include/net/smc.h index 2173932fab9d..824a7af8d654 100644 --- a/include/net/smc.h +++ b/include/net/smc.h @@ -20,4 +20,66 @@ struct smc_hashinfo { int smc_hash_sk(struct sock *sk); void smc_unhash_sk(struct sock *sk); + +/* SMCD/ISM device driver interface */ +struct smcd_dmb { + u64 dmb_tok; + u64 rgid; + u32 dmb_len; + u32 sba_idx; + u32 vlan_valid; + u32 vlan_id; + void *cpu_addr; + dma_addr_t dma_addr; +}; + +#define ISM_EVENT_DMB 0 +#define ISM_EVENT_GID 1 +#define ISM_EVENT_SWR 2 + +struct smcd_event { + u32 type; + u32 code; + u64 tok; + u64 time; + u64 info; +}; + +struct smcd_dev; + +struct smcd_ops { + int (*query_remote_gid)(struct smcd_dev *dev, u64 rgid, u32 vid_valid, + u32 vid); + int (*register_dmb)(struct smcd_dev *dev, struct smcd_dmb *dmb); + int (*unregister_dmb)(struct smcd_dev *dev, struct smcd_dmb *dmb); + int (*add_vlan_id)(struct smcd_dev *dev, u64 vlan_id); + int (*del_vlan_id)(struct smcd_dev *dev, u64 vlan_id); + int (*set_vlan_required)(struct smcd_dev *dev); + int (*reset_vlan_required)(struct smcd_dev *dev); + int (*signal_event)(struct smcd_dev *dev, u64 rgid, u32 trigger_irq, + u32 event_code, u64 info); + int (*move_data)(struct smcd_dev *dev, u64 dmb_tok, unsigned int idx, + bool sf, unsigned int offset, void *data, + unsigned int size); +}; + +struct smcd_dev { + const struct smcd_ops *ops; + struct device dev; + void *priv; + u64 local_gid; + struct list_head list; + spinlock_t lock; + struct smc_connection **conn; + struct list_head vlan; + struct workqueue_struct *event_wq; +}; + +struct smcd_dev *smcd_alloc_dev(struct device *parent, const char *name, + const struct smcd_ops *ops, int max_dmbs); +int smcd_register_dev(struct smcd_dev *smcd); +void smcd_unregister_dev(struct smcd_dev *smcd); +void smcd_free_dev(struct smcd_dev *smcd); +void smcd_handle_event(struct smcd_dev *dev, struct smcd_event *event); +void smcd_handle_irq(struct smcd_dev *dev, unsigned int bit); #endif /* _SMC_H */ diff --git a/net/smc/Makefile b/net/smc/Makefile index 188104654b54..4df96b4b8130 100644 --- a/net/smc/Makefile +++ b/net/smc/Makefile @@ -1,4 +1,4 @@ obj-$(CONFIG_SMC) += smc.o obj-$(CONFIG_SMC_DIAG) += smc_diag.o smc-y := af_smc.o smc_pnet.o smc_ib.o smc_clc.o smc_core.o smc_wr.o smc_llc.o -smc-y += smc_cdc.o smc_tx.o smc_rx.o smc_close.o +smc-y += smc_cdc.o smc_tx.o smc_rx.o smc_close.o smc_ism.o diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index da7f02edcd37..8ce48799cf68 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -475,8 +475,8 @@ static int smc_connect_rdma(struct smc_sock *smc, int reason_code = 0; mutex_lock(&smc_create_lgr_pending); - local_contact = smc_conn_create(smc, ibdev, ibport, &aclc->lcl, - aclc->hdr.flag); + local_contact = smc_conn_create(smc, false, aclc->hdr.flag, ibdev, + ibport, &aclc->lcl, NULL, 0); if (local_contact < 0) { if (local_contact == -ENOMEM) reason_code = SMC_CLC_DECL_MEM;/* insufficient memory*/ @@ -491,7 +491,7 @@ static int smc_connect_rdma(struct smc_sock *smc, smc_conn_save_peer_info(smc, aclc); /* create send buffer and rmb */ - if (smc_buf_create(smc)) + if (smc_buf_create(smc, false)) return smc_connect_abort(smc, SMC_CLC_DECL_MEM, local_contact); if (local_contact == SMC_FIRST_CONTACT) @@ -894,7 +894,8 @@ static int smc_listen_rdma_init(struct smc_sock *new_smc, int *local_contact) { /* allocate connection / link group */ - *local_contact = smc_conn_create(new_smc, ibdev, ibport, &pclc->lcl, 0); + *local_contact = smc_conn_create(new_smc, false, 0, ibdev, ibport, + &pclc->lcl, NULL, 0); if (*local_contact < 0) { if (*local_contact == -ENOMEM) return SMC_CLC_DECL_MEM;/* insufficient memory*/ @@ -902,7 +903,7 @@ static int smc_listen_rdma_init(struct smc_sock *new_smc, } /* create send buffer and rmb */ - if (smc_buf_create(new_smc)) + if (smc_buf_create(new_smc, false)) return SMC_CLC_DECL_MEM; return 0; diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index add82b0266f3..daa88db1841a 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -25,6 +25,7 @@ #include "smc_llc.h" #include "smc_cdc.h" #include "smc_close.h" +#include "smc_ism.h" #define SMC_LGR_NUM_INCR 256 #define SMC_LGR_FREE_DELAY_SERV (600 * HZ) @@ -46,8 +47,8 @@ static void smc_lgr_schedule_free_work(struct smc_link_group *lgr) * otherwise there is a risk of out-of-sync link groups. */ mod_delayed_work(system_wq, &lgr->free_work, - lgr->role == SMC_CLNT ? SMC_LGR_FREE_DELAY_CLNT : - SMC_LGR_FREE_DELAY_SERV); + (!lgr->is_smcd && lgr->role == SMC_CLNT) ? + SMC_LGR_FREE_DELAY_CLNT : SMC_LGR_FREE_DELAY_SERV); } /* Register connection's alert token in our lookup structure. @@ -153,16 +154,18 @@ static void smc_lgr_free_work(struct work_struct *work) free: spin_unlock_bh(&smc_lgr_list.lock); if (!delayed_work_pending(&lgr->free_work)) { - if (lgr->lnk[SMC_SINGLE_LINK].state != SMC_LNK_INACTIVE) + if (!lgr->is_smcd && + lgr->lnk[SMC_SINGLE_LINK].state != SMC_LNK_INACTIVE) smc_llc_link_inactive(&lgr->lnk[SMC_SINGLE_LINK]); smc_lgr_free(lgr); } } /* create a new SMC link group */ -static int smc_lgr_create(struct smc_sock *smc, +static int smc_lgr_create(struct smc_sock *smc, bool is_smcd, struct smc_ib_device *smcibdev, u8 ibport, - char *peer_systemid, unsigned short vlan_id) + char *peer_systemid, unsigned short vlan_id, + struct smcd_dev *smcismdev, u64 peer_gid) { struct smc_link_group *lgr; struct smc_link *lnk; @@ -170,17 +173,23 @@ static int smc_lgr_create(struct smc_sock *smc, int rc = 0; int i; + if (is_smcd && vlan_id) { + rc = smc_ism_get_vlan(smcismdev, vlan_id); + if (rc) + goto out; + } + lgr = kzalloc(sizeof(*lgr), GFP_KERNEL); if (!lgr) { rc = -ENOMEM; goto out; } - lgr->role = smc->listen_smc ? SMC_SERV : SMC_CLNT; + lgr->is_smcd = is_smcd; lgr->sync_err = 0; - memcpy(lgr->peer_systemid, peer_systemid, SMC_SYSTEMID_LEN); lgr->vlan_id = vlan_id; rwlock_init(&lgr->sndbufs_lock); rwlock_init(&lgr->rmbs_lock); + rwlock_init(&lgr->conns_lock); for (i = 0; i < SMC_RMBE_SIZES; i++) { INIT_LIST_HEAD(&lgr->sndbufs[i]); INIT_LIST_HEAD(&lgr->rmbs[i]); @@ -189,36 +198,44 @@ static int smc_lgr_create(struct smc_sock *smc, memcpy(&lgr->id, (u8 *)&smc_lgr_list.num, SMC_LGR_ID_SIZE); INIT_DELAYED_WORK(&lgr->free_work, smc_lgr_free_work); lgr->conns_all = RB_ROOT; - - lnk = &lgr->lnk[SMC_SINGLE_LINK]; - /* initialize link */ - lnk->state = SMC_LNK_ACTIVATING; - lnk->link_id = SMC_SINGLE_LINK; - lnk->smcibdev = smcibdev; - lnk->ibport = ibport; - lnk->path_mtu = smcibdev->pattr[ibport - 1].active_mtu; - if (!smcibdev->initialized) - smc_ib_setup_per_ibdev(smcibdev); - get_random_bytes(rndvec, sizeof(rndvec)); - lnk->psn_initial = rndvec[0] + (rndvec[1] << 8) + (rndvec[2] << 16); - rc = smc_llc_link_init(lnk); - if (rc) - goto free_lgr; - rc = smc_wr_alloc_link_mem(lnk); - if (rc) - goto clear_llc_lnk; - rc = smc_ib_create_protection_domain(lnk); - if (rc) - goto free_link_mem; - rc = smc_ib_create_queue_pair(lnk); - if (rc) - goto dealloc_pd; - rc = smc_wr_create_link(lnk); - if (rc) - goto destroy_qp; - + if (is_smcd) { + /* SMC-D specific settings */ + lgr->peer_gid = peer_gid; + lgr->smcd = smcismdev; + } else { + /* SMC-R specific settings */ + lgr->role = smc->listen_smc ? SMC_SERV : SMC_CLNT; + memcpy(lgr->peer_systemid, peer_systemid, SMC_SYSTEMID_LEN); + + lnk = &lgr->lnk[SMC_SINGLE_LINK]; + /* initialize link */ + lnk->state = SMC_LNK_ACTIVATING; + lnk->link_id = SMC_SINGLE_LINK; + lnk->smcibdev = smcibdev; + lnk->ibport = ibport; + lnk->path_mtu = smcibdev->pattr[ibport - 1].active_mtu; + if (!smcibdev->initialized) + smc_ib_setup_per_ibdev(smcibdev); + get_random_bytes(rndvec, sizeof(rndvec)); + lnk->psn_initial = rndvec[0] + (rndvec[1] << 8) + + (rndvec[2] << 16); + rc = smc_llc_link_init(lnk); + if (rc) + goto free_lgr; + rc = smc_wr_alloc_link_mem(lnk); + if (rc) + goto clear_llc_lnk; + rc = smc_ib_create_protection_domain(lnk); + if (rc) + goto free_link_mem; + rc = smc_ib_create_queue_pair(lnk); + if (rc) + goto dealloc_pd; + rc = smc_wr_create_link(lnk); + if (rc) + goto destroy_qp; + } smc->conn.lgr = lgr; - rwlock_init(&lgr->conns_lock); spin_lock_bh(&smc_lgr_list.lock); list_add(&lgr->list, &smc_lgr_list.list); spin_unlock_bh(&smc_lgr_list.lock); @@ -264,7 +281,10 @@ void smc_conn_free(struct smc_connection *conn) { if (!conn->lgr) return; - smc_cdc_tx_dismiss_slots(conn); + if (conn->lgr->is_smcd) + smc_ism_unset_conn(conn); + else + smc_cdc_tx_dismiss_slots(conn); smc_lgr_unregister_conn(conn); smc_buf_unuse(conn); } @@ -280,8 +300,8 @@ static void smc_link_clear(struct smc_link *lnk) smc_wr_free_link_mem(lnk); } -static void smc_buf_free(struct smc_link_group *lgr, bool is_rmb, - struct smc_buf_desc *buf_desc) +static void smcr_buf_free(struct smc_link_group *lgr, bool is_rmb, + struct smc_buf_desc *buf_desc) { struct smc_link *lnk = &lgr->lnk[SMC_SINGLE_LINK]; @@ -301,6 +321,25 @@ static void smc_buf_free(struct smc_link_group *lgr, bool is_rmb, kfree(buf_desc); } +static void smcd_buf_free(struct smc_link_group *lgr, bool is_dmb, + struct smc_buf_desc *buf_desc) +{ + if (is_dmb) + smc_ism_unregister_dmb(lgr->smcd, buf_desc); + else + kfree(buf_desc->cpu_addr); + kfree(buf_desc); +} + +static void smc_buf_free(struct smc_link_group *lgr, bool is_rmb, + struct smc_buf_desc *buf_desc) +{ + if (lgr->is_smcd) + smcd_buf_free(lgr, is_rmb, buf_desc); + else + smcr_buf_free(lgr, is_rmb, buf_desc); +} + static void __smc_lgr_free_bufs(struct smc_link_group *lgr, bool is_rmb) { struct smc_buf_desc *buf_desc, *bf_desc; @@ -332,7 +371,10 @@ static void smc_lgr_free_bufs(struct smc_link_group *lgr) void smc_lgr_free(struct smc_link_group *lgr) { smc_lgr_free_bufs(lgr); - smc_link_clear(&lgr->lnk[SMC_SINGLE_LINK]); + if (lgr->is_smcd) + smc_ism_put_vlan(lgr->smcd, lgr->vlan_id); + else + smc_link_clear(&lgr->lnk[SMC_SINGLE_LINK]); kfree(lgr); } @@ -357,7 +399,8 @@ static void __smc_lgr_terminate(struct smc_link_group *lgr) lgr->terminating = 1; if (!list_empty(&lgr->list)) /* forget lgr */ list_del_init(&lgr->list); - smc_llc_link_inactive(&lgr->lnk[SMC_SINGLE_LINK]); + if (!lgr->is_smcd) + smc_llc_link_inactive(&lgr->lnk[SMC_SINGLE_LINK]); write_lock_bh(&lgr->conns_lock); node = rb_first(&lgr->conns_all); @@ -374,7 +417,8 @@ static void __smc_lgr_terminate(struct smc_link_group *lgr) node = rb_first(&lgr->conns_all); } write_unlock_bh(&lgr->conns_lock); - wake_up(&lgr->lnk[SMC_SINGLE_LINK].wr_reg_wait); + if (!lgr->is_smcd) + wake_up(&lgr->lnk[SMC_SINGLE_LINK].wr_reg_wait); smc_lgr_schedule_free_work(lgr); } @@ -392,13 +436,40 @@ void smc_port_terminate(struct smc_ib_device *smcibdev, u8 ibport) spin_lock_bh(&smc_lgr_list.lock); list_for_each_entry_safe(lgr, l, &smc_lgr_list.list, list) { - if (lgr->lnk[SMC_SINGLE_LINK].smcibdev == smcibdev && + if (!lgr->is_smcd && + lgr->lnk[SMC_SINGLE_LINK].smcibdev == smcibdev && lgr->lnk[SMC_SINGLE_LINK].ibport == ibport) __smc_lgr_terminate(lgr); } spin_unlock_bh(&smc_lgr_list.lock); } +/* Called when SMC-D device is terminated or peer is lost */ +void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid) +{ + struct smc_link_group *lgr, *l; + LIST_HEAD(lgr_free_list); + + /* run common cleanup function and build free list */ + spin_lock_bh(&smc_lgr_list.lock); + list_for_each_entry_safe(lgr, l, &smc_lgr_list.list, list) { + if (lgr->is_smcd && lgr->smcd == dev && + (!peer_gid || lgr->peer_gid == peer_gid) && + !list_empty(&lgr->list)) { + __smc_lgr_terminate(lgr); + list_move(&lgr->list, &lgr_free_list); + } + } + spin_unlock_bh(&smc_lgr_list.lock); + + /* cancel the regular free workers and actually free lgrs */ + list_for_each_entry_safe(lgr, l, &lgr_free_list, list) { + list_del_init(&lgr->list); + cancel_delayed_work_sync(&lgr->free_work); + smc_lgr_free(lgr); + } +} + /* Determine vlan of internal TCP socket. * @vlan_id: address to store the determined vlan id into */ @@ -477,10 +548,30 @@ static int smc_link_determine_gid(struct smc_link_group *lgr) return -ENODEV; } +static bool smcr_lgr_match(struct smc_link_group *lgr, + struct smc_clc_msg_local *lcl, + enum smc_lgr_role role) +{ + return !memcmp(lgr->peer_systemid, lcl->id_for_peer, + SMC_SYSTEMID_LEN) && + !memcmp(lgr->lnk[SMC_SINGLE_LINK].peer_gid, &lcl->gid, + SMC_GID_SIZE) && + !memcmp(lgr->lnk[SMC_SINGLE_LINK].peer_mac, lcl->mac, + sizeof(lcl->mac)) && + lgr->role == role; +} + +static bool smcd_lgr_match(struct smc_link_group *lgr, + struct smcd_dev *smcismdev, u64 peer_gid) +{ + return lgr->peer_gid == peer_gid && lgr->smcd == smcismdev; +} + /* create a new SMC connection (and a new link group if necessary) */ -int smc_conn_create(struct smc_sock *smc, +int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact, struct smc_ib_device *smcibdev, u8 ibport, - struct smc_clc_msg_local *lcl, int srv_first_contact) + struct smc_clc_msg_local *lcl, struct smcd_dev *smcd, + u64 peer_gid) { struct smc_connection *conn = &smc->conn; int local_contact = SMC_FIRST_CONTACT; @@ -502,17 +593,12 @@ int smc_conn_create(struct smc_sock *smc, spin_lock_bh(&smc_lgr_list.lock); list_for_each_entry(lgr, &smc_lgr_list.list, list) { write_lock_bh(&lgr->conns_lock); - if (!memcmp(lgr->peer_systemid, lcl->id_for_peer, - SMC_SYSTEMID_LEN) && - !memcmp(lgr->lnk[SMC_SINGLE_LINK].peer_gid, &lcl->gid, - SMC_GID_SIZE) && - !memcmp(lgr->lnk[SMC_SINGLE_LINK].peer_mac, lcl->mac, - sizeof(lcl->mac)) && + if ((is_smcd ? smcd_lgr_match(lgr, smcd, peer_gid) : + smcr_lgr_match(lgr, lcl, role)) && !lgr->sync_err && - (lgr->role == role) && - (lgr->vlan_id == vlan_id) && - ((role == SMC_CLNT) || - (lgr->conns_num < SMC_RMBS_PER_LGR_MAX))) { + lgr->vlan_id == vlan_id && + (role == SMC_CLNT || + lgr->conns_num < SMC_RMBS_PER_LGR_MAX)) { /* link group found */ local_contact = SMC_REUSE_CONTACT; conn->lgr = lgr; @@ -535,12 +621,13 @@ int smc_conn_create(struct smc_sock *smc, create: if (local_contact == SMC_FIRST_CONTACT) { - rc = smc_lgr_create(smc, smcibdev, ibport, - lcl->id_for_peer, vlan_id); + rc = smc_lgr_create(smc, is_smcd, smcibdev, ibport, + lcl->id_for_peer, vlan_id, smcd, peer_gid); if (rc) goto out; smc_lgr_register_conn(conn); /* add smc conn to lgr */ - rc = smc_link_determine_gid(conn->lgr); + if (!is_smcd) + rc = smc_link_determine_gid(conn->lgr); } conn->local_tx_ctrl.common.type = SMC_CDC_MSG_TYPE; conn->local_tx_ctrl.len = SMC_WR_TX_SIZE; @@ -609,8 +696,8 @@ static inline int smc_rmb_wnd_update_limit(int rmbe_size) return min_t(int, rmbe_size / 10, SOCK_MIN_SNDBUF / 2); } -static struct smc_buf_desc *smc_new_buf_create(struct smc_link_group *lgr, - bool is_rmb, int bufsize) +static struct smc_buf_desc *smcr_new_buf_create(struct smc_link_group *lgr, + bool is_rmb, int bufsize) { struct smc_buf_desc *buf_desc; struct smc_link *lnk; @@ -668,7 +755,43 @@ static struct smc_buf_desc *smc_new_buf_create(struct smc_link_group *lgr, return buf_desc; } -static int __smc_buf_create(struct smc_sock *smc, bool is_rmb) +#define SMCD_DMBE_SIZES 7 /* 0 -> 16KB, 1 -> 32KB, .. 6 -> 1MB */ + +static struct smc_buf_desc *smcd_new_buf_create(struct smc_link_group *lgr, + bool is_dmb, int bufsize) +{ + struct smc_buf_desc *buf_desc; + int rc; + + if (smc_compress_bufsize(bufsize) > SMCD_DMBE_SIZES) + return ERR_PTR(-EAGAIN); + + /* try to alloc a new DMB */ + buf_desc = kzalloc(sizeof(*buf_desc), GFP_KERNEL); + if (!buf_desc) + return ERR_PTR(-ENOMEM); + if (is_dmb) { + rc = smc_ism_register_dmb(lgr, bufsize, buf_desc); + if (rc) { + kfree(buf_desc); + return ERR_PTR(-EAGAIN); + } + memset(buf_desc->cpu_addr, 0, bufsize); + buf_desc->len = bufsize; + } else { + buf_desc->cpu_addr = kzalloc(bufsize, GFP_KERNEL | + __GFP_NOWARN | __GFP_NORETRY | + __GFP_NOMEMALLOC); + if (!buf_desc->cpu_addr) { + kfree(buf_desc); + return ERR_PTR(-EAGAIN); + } + buf_desc->len = bufsize; + } + return buf_desc; +} + +static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) { struct smc_buf_desc *buf_desc = ERR_PTR(-ENOMEM); struct smc_connection *conn = &smc->conn; @@ -706,7 +829,11 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_rmb) break; /* found reusable slot */ } - buf_desc = smc_new_buf_create(lgr, is_rmb, bufsize); + if (is_smcd) + buf_desc = smcd_new_buf_create(lgr, is_rmb, bufsize); + else + buf_desc = smcr_new_buf_create(lgr, is_rmb, bufsize); + if (PTR_ERR(buf_desc) == -ENOMEM) break; if (IS_ERR(buf_desc)) @@ -728,6 +855,8 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_rmb) smc->sk.sk_rcvbuf = bufsize * 2; atomic_set(&conn->bytes_to_rcv, 0); conn->rmbe_update_limit = smc_rmb_wnd_update_limit(bufsize); + if (is_smcd) + smc_ism_set_conn(conn); /* map RMB/smcd_dev to conn */ } else { conn->sndbuf_desc = buf_desc; smc->sk.sk_sndbuf = bufsize * 2; @@ -740,6 +869,8 @@ void smc_sndbuf_sync_sg_for_cpu(struct smc_connection *conn) { struct smc_link_group *lgr = conn->lgr; + if (!conn->lgr || conn->lgr->is_smcd) + return; smc_ib_sync_sg_for_cpu(lgr->lnk[SMC_SINGLE_LINK].smcibdev, conn->sndbuf_desc, DMA_TO_DEVICE); } @@ -748,6 +879,8 @@ void smc_sndbuf_sync_sg_for_device(struct smc_connection *conn) { struct smc_link_group *lgr = conn->lgr; + if (!conn->lgr || conn->lgr->is_smcd) + return; smc_ib_sync_sg_for_device(lgr->lnk[SMC_SINGLE_LINK].smcibdev, conn->sndbuf_desc, DMA_TO_DEVICE); } @@ -756,6 +889,8 @@ void smc_rmb_sync_sg_for_cpu(struct smc_connection *conn) { struct smc_link_group *lgr = conn->lgr; + if (!conn->lgr || conn->lgr->is_smcd) + return; smc_ib_sync_sg_for_cpu(lgr->lnk[SMC_SINGLE_LINK].smcibdev, conn->rmb_desc, DMA_FROM_DEVICE); } @@ -764,6 +899,8 @@ void smc_rmb_sync_sg_for_device(struct smc_connection *conn) { struct smc_link_group *lgr = conn->lgr; + if (!conn->lgr || conn->lgr->is_smcd) + return; smc_ib_sync_sg_for_device(lgr->lnk[SMC_SINGLE_LINK].smcibdev, conn->rmb_desc, DMA_FROM_DEVICE); } @@ -774,16 +911,16 @@ void smc_rmb_sync_sg_for_device(struct smc_connection *conn) * the Linux implementation uses just one RMB-element per RMB, i.e. uses an * extra RMB for every connection in a link group */ -int smc_buf_create(struct smc_sock *smc) +int smc_buf_create(struct smc_sock *smc, bool is_smcd) { int rc; /* create send buffer */ - rc = __smc_buf_create(smc, false); + rc = __smc_buf_create(smc, is_smcd, false); if (rc) return rc; /* create rmb */ - rc = __smc_buf_create(smc, true); + rc = __smc_buf_create(smc, is_smcd, true); if (rc) smc_buf_free(smc->conn.lgr, false, smc->conn.sndbuf_desc); return rc; @@ -865,7 +1002,8 @@ void smc_core_exit(void) spin_unlock_bh(&smc_lgr_list.lock); list_for_each_entry_safe(lgr, lg, &lgr_freeing_list, list) { list_del_init(&lgr->list); - smc_llc_link_inactive(&lgr->lnk[SMC_SINGLE_LINK]); + if (!lgr->is_smcd) + smc_llc_link_inactive(&lgr->lnk[SMC_SINGLE_LINK]); cancel_delayed_work_sync(&lgr->free_work); smc_lgr_free(lgr); /* free link group */ } diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 93cb3523bf50..cd9268a9570e 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -124,15 +124,28 @@ struct smc_buf_desc { void *cpu_addr; /* virtual address of buffer */ struct page *pages; int len; /* length of buffer */ - struct sg_table sgt[SMC_LINKS_PER_LGR_MAX];/* virtual buffer */ - struct ib_mr *mr_rx[SMC_LINKS_PER_LGR_MAX]; - /* for rmb only: memory region - * incl. rkey provided to peer - */ - u32 order; /* allocation order */ u32 used; /* currently used / unused */ u8 reused : 1; /* new created / reused */ u8 regerr : 1; /* err during registration */ + union { + struct { /* SMC-R */ + struct sg_table sgt[SMC_LINKS_PER_LGR_MAX]; + /* virtual buffer */ + struct ib_mr *mr_rx[SMC_LINKS_PER_LGR_MAX]; + /* for rmb only: memory region + * incl. rkey provided to peer + */ + u32 order; /* allocation order */ + }; + struct { /* SMC-D */ + unsigned short sba_idx; + /* SBA index number */ + u64 token; + /* DMB token number */ + dma_addr_t dma_addr; + /* DMA address */ + }; + }; }; struct smc_rtoken { /* address/key of remote RMB */ @@ -148,12 +161,10 @@ struct smc_rtoken { /* address/key of remote RMB */ * struct smc_clc_msg_accept_confirm.rmbe_size being a 4 bit value (0..15) */ +struct smcd_dev; + struct smc_link_group { struct list_head list; - enum smc_lgr_role role; /* client or server */ - struct smc_link lnk[SMC_LINKS_PER_LGR_MAX]; /* smc link */ - char peer_systemid[SMC_SYSTEMID_LEN]; - /* unique system_id of peer */ struct rb_root conns_all; /* connection tree */ rwlock_t conns_lock; /* protects conns_all */ unsigned int conns_num; /* current # of connections */ @@ -163,17 +174,35 @@ struct smc_link_group { rwlock_t sndbufs_lock; /* protects tx buffers */ struct list_head rmbs[SMC_RMBE_SIZES]; /* rx buffers */ rwlock_t rmbs_lock; /* protects rx buffers */ - struct smc_rtoken rtokens[SMC_RMBS_PER_LGR_MAX] - [SMC_LINKS_PER_LGR_MAX]; - /* remote addr/key pairs */ - unsigned long rtokens_used_mask[BITS_TO_LONGS( - SMC_RMBS_PER_LGR_MAX)]; - /* used rtoken elements */ u8 id[SMC_LGR_ID_SIZE]; /* unique lgr id */ struct delayed_work free_work; /* delayed freeing of an lgr */ u8 sync_err : 1; /* lgr no longer fits to peer */ u8 terminating : 1;/* lgr is terminating */ + + bool is_smcd; /* SMC-R or SMC-D */ + union { + struct { /* SMC-R */ + enum smc_lgr_role role; + /* client or server */ + struct smc_link lnk[SMC_LINKS_PER_LGR_MAX]; + /* smc link */ + char peer_systemid[SMC_SYSTEMID_LEN]; + /* unique system_id of peer */ + struct smc_rtoken rtokens[SMC_RMBS_PER_LGR_MAX] + [SMC_LINKS_PER_LGR_MAX]; + /* remote addr/key pairs */ + unsigned long rtokens_used_mask[BITS_TO_LONGS + (SMC_RMBS_PER_LGR_MAX)]; + /* used rtoken elements */ + }; + struct { /* SMC-D */ + u64 peer_gid; + /* Peer GID (remote) */ + struct smcd_dev *smcd; + /* ISM device for VLAN reg. */ + }; + }; }; /* Find the connection associated with the given alert token in the link group. @@ -217,7 +246,8 @@ void smc_lgr_free(struct smc_link_group *lgr); void smc_lgr_forget(struct smc_link_group *lgr); void smc_lgr_terminate(struct smc_link_group *lgr); void smc_port_terminate(struct smc_ib_device *smcibdev, u8 ibport); -int smc_buf_create(struct smc_sock *smc); +void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid); +int smc_buf_create(struct smc_sock *smc, bool is_smcd); int smc_uncompress_bufsize(u8 compressed); int smc_rmb_rtoken_handling(struct smc_connection *conn, struct smc_clc_msg_accept_confirm *clc); @@ -227,9 +257,12 @@ void smc_sndbuf_sync_sg_for_cpu(struct smc_connection *conn); void smc_sndbuf_sync_sg_for_device(struct smc_connection *conn); void smc_rmb_sync_sg_for_cpu(struct smc_connection *conn); void smc_rmb_sync_sg_for_device(struct smc_connection *conn); + void smc_conn_free(struct smc_connection *conn); -int smc_conn_create(struct smc_sock *smc, +int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact, struct smc_ib_device *smcibdev, u8 ibport, - struct smc_clc_msg_local *lcl, int srv_first_contact); + struct smc_clc_msg_local *lcl, struct smcd_dev *smcd, + u64 peer_gid); +void smcd_conn_free(struct smc_connection *conn); void smc_core_exit(void); #endif diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c index 839354402215..64ce107c24d9 100644 --- a/net/smc/smc_diag.c +++ b/net/smc/smc_diag.c @@ -136,7 +136,8 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb, goto errout; } - if ((req->diag_ext & (1 << (SMC_DIAG_LGRINFO - 1))) && smc->conn.lgr && + if (smc->conn.lgr && !smc->conn.lgr->is_smcd && + (req->diag_ext & (1 << (SMC_DIAG_LGRINFO - 1))) && !list_empty(&smc->conn.lgr->list)) { struct smc_diag_lgrinfo linfo = { .role = smc->conn.lgr->role, diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c new file mode 100644 index 000000000000..ca1ce42fd49f --- /dev/null +++ b/net/smc/smc_ism.c @@ -0,0 +1,304 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Shared Memory Communications Direct over ISM devices (SMC-D) + * + * Functions for ISM device. + * + * Copyright IBM Corp. 2018 + */ + +#include +#include +#include + +#include "smc.h" +#include "smc_core.h" +#include "smc_ism.h" + +struct smcd_dev_list smcd_dev_list = { + .list = LIST_HEAD_INIT(smcd_dev_list.list), + .lock = __SPIN_LOCK_UNLOCKED(smcd_dev_list.lock) +}; + +/* Test if an ISM communication is possible. */ +int smc_ism_cantalk(u64 peer_gid, unsigned short vlan_id, struct smcd_dev *smcd) +{ + return smcd->ops->query_remote_gid(smcd, peer_gid, vlan_id ? 1 : 0, + vlan_id); +} + +int smc_ism_write(struct smcd_dev *smcd, const struct smc_ism_position *pos, + void *data, size_t len) +{ + int rc; + + rc = smcd->ops->move_data(smcd, pos->token, pos->index, pos->signal, + pos->offset, data, len); + + return rc < 0 ? rc : 0; +} + +/* Set a connection using this DMBE. */ +void smc_ism_set_conn(struct smc_connection *conn) +{ + unsigned long flags; + + spin_lock_irqsave(&conn->lgr->smcd->lock, flags); + conn->lgr->smcd->conn[conn->rmb_desc->sba_idx] = conn; + spin_unlock_irqrestore(&conn->lgr->smcd->lock, flags); +} + +/* Unset a connection using this DMBE. */ +void smc_ism_unset_conn(struct smc_connection *conn) +{ + unsigned long flags; + + if (!conn->rmb_desc) + return; + + spin_lock_irqsave(&conn->lgr->smcd->lock, flags); + conn->lgr->smcd->conn[conn->rmb_desc->sba_idx] = NULL; + spin_unlock_irqrestore(&conn->lgr->smcd->lock, flags); +} + +/* Register a VLAN identifier with the ISM device. Use a reference count + * and add a VLAN identifier only when the first DMB using this VLAN is + * registered. + */ +int smc_ism_get_vlan(struct smcd_dev *smcd, unsigned short vlanid) +{ + struct smc_ism_vlanid *new_vlan, *vlan; + unsigned long flags; + int rc = 0; + + if (!vlanid) /* No valid vlan id */ + return -EINVAL; + + /* create new vlan entry, in case we need it */ + new_vlan = kzalloc(sizeof(*new_vlan), GFP_KERNEL); + if (!new_vlan) + return -ENOMEM; + new_vlan->vlanid = vlanid; + refcount_set(&new_vlan->refcnt, 1); + + /* if there is an existing entry, increase count and return */ + spin_lock_irqsave(&smcd->lock, flags); + list_for_each_entry(vlan, &smcd->vlan, list) { + if (vlan->vlanid == vlanid) { + refcount_inc(&vlan->refcnt); + kfree(new_vlan); + goto out; + } + } + + /* no existing entry found. + * add new entry to device; might fail, e.g., if HW limit reached + */ + if (smcd->ops->add_vlan_id(smcd, vlanid)) { + kfree(new_vlan); + rc = -EIO; + goto out; + } + list_add_tail(&new_vlan->list, &smcd->vlan); +out: + spin_unlock_irqrestore(&smcd->lock, flags); + return rc; +} + +/* Unregister a VLAN identifier with the ISM device. Use a reference count + * and remove a VLAN identifier only when the last DMB using this VLAN is + * unregistered. + */ +int smc_ism_put_vlan(struct smcd_dev *smcd, unsigned short vlanid) +{ + struct smc_ism_vlanid *vlan; + unsigned long flags; + bool found = false; + int rc = 0; + + if (!vlanid) /* No valid vlan id */ + return -EINVAL; + + spin_lock_irqsave(&smcd->lock, flags); + list_for_each_entry(vlan, &smcd->vlan, list) { + if (vlan->vlanid == vlanid) { + if (!refcount_dec_and_test(&vlan->refcnt)) + goto out; + found = true; + break; + } + } + if (!found) { + rc = -ENOENT; + goto out; /* VLAN id not in table */ + } + + /* Found and the last reference just gone */ + if (smcd->ops->del_vlan_id(smcd, vlanid)) + rc = -EIO; + list_del(&vlan->list); + kfree(vlan); +out: + spin_unlock_irqrestore(&smcd->lock, flags); + return rc; +} + +int smc_ism_unregister_dmb(struct smcd_dev *smcd, struct smc_buf_desc *dmb_desc) +{ + struct smcd_dmb dmb; + + memset(&dmb, 0, sizeof(dmb)); + dmb.dmb_tok = dmb_desc->token; + dmb.sba_idx = dmb_desc->sba_idx; + dmb.cpu_addr = dmb_desc->cpu_addr; + dmb.dma_addr = dmb_desc->dma_addr; + dmb.dmb_len = dmb_desc->len; + return smcd->ops->unregister_dmb(smcd, &dmb); +} + +int smc_ism_register_dmb(struct smc_link_group *lgr, int dmb_len, + struct smc_buf_desc *dmb_desc) +{ + struct smcd_dmb dmb; + int rc; + + memset(&dmb, 0, sizeof(dmb)); + dmb.dmb_len = dmb_len; + dmb.sba_idx = dmb_desc->sba_idx; + dmb.vlan_id = lgr->vlan_id; + dmb.rgid = lgr->peer_gid; + rc = lgr->smcd->ops->register_dmb(lgr->smcd, &dmb); + if (!rc) { + dmb_desc->sba_idx = dmb.sba_idx; + dmb_desc->token = dmb.dmb_tok; + dmb_desc->cpu_addr = dmb.cpu_addr; + dmb_desc->dma_addr = dmb.dma_addr; + dmb_desc->len = dmb.dmb_len; + } + return rc; +} + +struct smc_ism_event_work { + struct work_struct work; + struct smcd_dev *smcd; + struct smcd_event event; +}; + +/* worker for SMC-D events */ +static void smc_ism_event_work(struct work_struct *work) +{ + struct smc_ism_event_work *wrk = + container_of(work, struct smc_ism_event_work, work); + + switch (wrk->event.type) { + case ISM_EVENT_GID: /* GID event, token is peer GID */ + smc_smcd_terminate(wrk->smcd, wrk->event.tok); + break; + case ISM_EVENT_DMB: + break; + } + kfree(wrk); +} + +static void smcd_release(struct device *dev) +{ + struct smcd_dev *smcd = container_of(dev, struct smcd_dev, dev); + + kfree(smcd->conn); + kfree(smcd); +} + +struct smcd_dev *smcd_alloc_dev(struct device *parent, const char *name, + const struct smcd_ops *ops, int max_dmbs) +{ + struct smcd_dev *smcd; + + smcd = kzalloc(sizeof(*smcd), GFP_KERNEL); + if (!smcd) + return NULL; + smcd->conn = kcalloc(max_dmbs, sizeof(struct smc_connection *), + GFP_KERNEL); + if (!smcd->conn) { + kfree(smcd); + return NULL; + } + + smcd->dev.parent = parent; + smcd->dev.release = smcd_release; + device_initialize(&smcd->dev); + dev_set_name(&smcd->dev, name); + smcd->ops = ops; + + spin_lock_init(&smcd->lock); + INIT_LIST_HEAD(&smcd->vlan); + smcd->event_wq = alloc_ordered_workqueue("ism_evt_wq-%s)", + WQ_MEM_RECLAIM, name); + return smcd; +} +EXPORT_SYMBOL_GPL(smcd_alloc_dev); + +int smcd_register_dev(struct smcd_dev *smcd) +{ + spin_lock(&smcd_dev_list.lock); + list_add_tail(&smcd->list, &smcd_dev_list.list); + spin_unlock(&smcd_dev_list.lock); + + return device_add(&smcd->dev); +} +EXPORT_SYMBOL_GPL(smcd_register_dev); + +void smcd_unregister_dev(struct smcd_dev *smcd) +{ + spin_lock(&smcd_dev_list.lock); + list_del(&smcd->list); + spin_unlock(&smcd_dev_list.lock); + flush_workqueue(smcd->event_wq); + destroy_workqueue(smcd->event_wq); + smc_smcd_terminate(smcd, 0); + + device_del(&smcd->dev); +} +EXPORT_SYMBOL_GPL(smcd_unregister_dev); + +void smcd_free_dev(struct smcd_dev *smcd) +{ + put_device(&smcd->dev); +} +EXPORT_SYMBOL_GPL(smcd_free_dev); + +/* SMCD Device event handler. Called from ISM device interrupt handler. + * Parameters are smcd device pointer, + * - event->type (0 --> DMB, 1 --> GID), + * - event->code (event code), + * - event->tok (either DMB token when event type 0, or GID when event type 1) + * - event->time (time of day) + * - event->info (debug info). + * + * Context: + * - Function called in IRQ context from ISM device driver event handler. + */ +void smcd_handle_event(struct smcd_dev *smcd, struct smcd_event *event) +{ + struct smc_ism_event_work *wrk; + + /* copy event to event work queue, and let it be handled there */ + wrk = kmalloc(sizeof(*wrk), GFP_ATOMIC); + if (!wrk) + return; + INIT_WORK(&wrk->work, smc_ism_event_work); + wrk->smcd = smcd; + wrk->event = *event; + queue_work(smcd->event_wq, &wrk->work); +} +EXPORT_SYMBOL_GPL(smcd_handle_event); + +/* SMCD Device interrupt handler. Called from ISM device interrupt handler. + * Parameters are smcd device pointer and DMB number. Find the connection and + * schedule the tasklet for this connection. + * + * Context: + * - Function called in IRQ context from ISM device driver IRQ handler. + */ +void smcd_handle_irq(struct smcd_dev *smcd, unsigned int dmbno) +{ +} +EXPORT_SYMBOL_GPL(smcd_handle_irq); diff --git a/net/smc/smc_ism.h b/net/smc/smc_ism.h new file mode 100644 index 000000000000..aee45b860b79 --- /dev/null +++ b/net/smc/smc_ism.h @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Shared Memory Communications Direct over ISM devices (SMC-D) + * + * SMC-D ISM device structure definitions. + * + * Copyright IBM Corp. 2018 + */ + +#ifndef SMCD_ISM_H +#define SMCD_ISM_H + +#include + +#include "smc.h" + +struct smcd_dev_list { /* List of SMCD devices */ + struct list_head list; + spinlock_t lock; /* Protects list of devices */ +}; + +extern struct smcd_dev_list smcd_dev_list; /* list of smcd devices */ + +struct smc_ism_vlanid { /* VLAN id set on ISM device */ + struct list_head list; + unsigned short vlanid; /* Vlan id */ + refcount_t refcnt; /* Reference count */ +}; + +struct smc_ism_position { /* ISM device position to write to */ + u64 token; /* Token of DMB */ + u32 offset; /* Offset into DMBE */ + u8 index; /* Index of DMBE */ + u8 signal; /* Generate interrupt on owner side */ +}; + +struct smcd_dev; + +int smc_ism_cantalk(u64 peer_gid, unsigned short vlan_id, struct smcd_dev *dev); +void smc_ism_set_conn(struct smc_connection *conn); +void smc_ism_unset_conn(struct smc_connection *conn); +int smc_ism_get_vlan(struct smcd_dev *dev, unsigned short vlan_id); +int smc_ism_put_vlan(struct smcd_dev *dev, unsigned short vlan_id); +int smc_ism_register_dmb(struct smc_link_group *lgr, int buf_size, + struct smc_buf_desc *dmb_desc); +int smc_ism_unregister_dmb(struct smcd_dev *dev, struct smc_buf_desc *dmb_desc); +int smc_ism_write(struct smcd_dev *dev, const struct smc_ism_position *pos, + void *data, size_t len); +#endif -- cgit v1.2.3 From 1619f770589a183af56f248de261534b255122de Mon Sep 17 00:00:00 2001 From: Hans Wippel Date: Thu, 28 Jun 2018 19:05:08 +0200 Subject: net/smc: add pnetid support for SMC-D and ISM SMC-D relies on PNETIDs to find usable SMC-D/ISM devices for a SMC connection. This patch adds SMC-D/ISM support to the current PNETID implementation. Signed-off-by: Hans Wippel Signed-off-by: Ursula Braun Suggested-by: Thomas Richter Signed-off-by: David S. Miller --- include/net/smc.h | 1 + net/smc/smc_ism.c | 2 ++ net/smc/smc_pnet.c | 41 +++++++++++++++++++++++++++++++++++++++++ net/smc/smc_pnet.h | 2 ++ 4 files changed, 46 insertions(+) (limited to 'include') diff --git a/include/net/smc.h b/include/net/smc.h index 824a7af8d654..9ef49f8b1002 100644 --- a/include/net/smc.h +++ b/include/net/smc.h @@ -73,6 +73,7 @@ struct smcd_dev { struct smc_connection **conn; struct list_head vlan; struct workqueue_struct *event_wq; + u8 pnetid[SMC_MAX_PNETID_LEN]; }; struct smcd_dev *smcd_alloc_dev(struct device *parent, const char *name, diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c index ca1ce42fd49f..f44e4dff244a 100644 --- a/net/smc/smc_ism.c +++ b/net/smc/smc_ism.c @@ -13,6 +13,7 @@ #include "smc.h" #include "smc_core.h" #include "smc_ism.h" +#include "smc_pnet.h" struct smcd_dev_list smcd_dev_list = { .list = LIST_HEAD_INIT(smcd_dev_list.list), @@ -227,6 +228,7 @@ struct smcd_dev *smcd_alloc_dev(struct device *parent, const char *name, device_initialize(&smcd->dev); dev_set_name(&smcd->dev, name); smcd->ops = ops; + smc_pnetid_by_dev_port(parent, 0, smcd->pnetid); spin_lock_init(&smcd->lock); INIT_LIST_HEAD(&smcd->vlan); diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index cdc6e23b6ce1..1b6c066d3495 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -22,6 +22,7 @@ #include "smc_pnet.h" #include "smc_ib.h" +#include "smc_ism.h" static struct nla_policy smc_pnet_policy[SMC_PNETID_MAX + 1] = { [SMC_PNETID_NAME] = { @@ -564,6 +565,27 @@ static void smc_pnet_find_roce_by_pnetid(struct net_device *ndev, spin_unlock(&smc_ib_devices.lock); } +static void smc_pnet_find_ism_by_pnetid(struct net_device *ndev, + struct smcd_dev **smcismdev) +{ + u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; + struct smcd_dev *ismdev; + + ndev = pnet_find_base_ndev(ndev); + if (smc_pnetid_by_dev_port(ndev->dev.parent, ndev->dev_port, + ndev_pnetid)) + return; /* pnetid could not be determined */ + + spin_lock(&smcd_dev_list.lock); + list_for_each_entry(ismdev, &smcd_dev_list.list, list) { + if (!memcmp(ismdev->pnetid, ndev_pnetid, SMC_MAX_PNETID_LEN)) { + *smcismdev = ismdev; + break; + } + } + spin_unlock(&smcd_dev_list.lock); +} + /* Lookup of coupled ib_device via SMC pnet table */ static void smc_pnet_find_roce_by_table(struct net_device *netdev, struct smc_ib_device **smcibdev, @@ -615,3 +637,22 @@ out_rel: out: return; } + +void smc_pnet_find_ism_resource(struct sock *sk, struct smcd_dev **smcismdev) +{ + struct dst_entry *dst = sk_dst_get(sk); + + *smcismdev = NULL; + if (!dst) + goto out; + if (!dst->dev) + goto out_rel; + + /* if possible, lookup via hardware-defined pnetid */ + smc_pnet_find_ism_by_pnetid(dst->dev, smcismdev); + +out_rel: + dst_release(dst); +out: + return; +} diff --git a/net/smc/smc_pnet.h b/net/smc/smc_pnet.h index ad4455cde9e7..1e94fd4df7bc 100644 --- a/net/smc/smc_pnet.h +++ b/net/smc/smc_pnet.h @@ -17,6 +17,7 @@ #endif struct smc_ib_device; +struct smcd_dev; static inline int smc_pnetid_by_dev_port(struct device *dev, unsigned short port, u8 *pnetid) @@ -33,5 +34,6 @@ void smc_pnet_exit(void); int smc_pnet_remove_by_ibdev(struct smc_ib_device *ibdev); void smc_pnet_find_roce_resource(struct sock *sk, struct smc_ib_device **smcibdev, u8 *ibport); +void smc_pnet_find_ism_resource(struct sock *sk, struct smcd_dev **smcismdev); #endif -- cgit v1.2.3 From 4b1b7d3b30a6d32ac1a1dcede284e76ef8a8542d Mon Sep 17 00:00:00 2001 From: Hans Wippel Date: Thu, 28 Jun 2018 19:05:12 +0200 Subject: net/smc: add SMC-D diag support This patch adds diag support for SMC-D. Signed-off-by: Hans Wippel Signed-off-by: Ursula Braun Suggested-by: Thomas Richter Signed-off-by: David S. Miller --- include/uapi/linux/smc_diag.h | 10 ++++++++++ net/smc/smc_diag.c | 15 +++++++++++++++ 2 files changed, 25 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/smc_diag.h b/include/uapi/linux/smc_diag.h index 0ae5d4685ba3..92be255e534c 100644 --- a/include/uapi/linux/smc_diag.h +++ b/include/uapi/linux/smc_diag.h @@ -35,6 +35,7 @@ enum { SMC_DIAG_CONNINFO, SMC_DIAG_LGRINFO, SMC_DIAG_SHUTDOWN, + SMC_DIAG_DMBINFO, __SMC_DIAG_MAX, }; @@ -83,4 +84,13 @@ struct smc_diag_lgrinfo { struct smc_diag_linkinfo lnk[1]; __u8 role; }; + +struct smcd_diag_dmbinfo { /* SMC-D Socket internals */ + __u32 linkid; /* Link identifier */ + __u64 peer_gid; /* Peer GID */ + __u64 my_gid; /* My GID */ + __u64 token; /* Token of DMB */ + __u64 peer_token; /* Token of remote DMBE */ +}; + #endif /* _UAPI_SMC_DIAG_H_ */ diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c index 64ce107c24d9..6d83eef1b743 100644 --- a/net/smc/smc_diag.c +++ b/net/smc/smc_diag.c @@ -156,6 +156,21 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb, if (nla_put(skb, SMC_DIAG_LGRINFO, sizeof(linfo), &linfo) < 0) goto errout; } + if (smc->conn.lgr && smc->conn.lgr->is_smcd && + (req->diag_ext & (1 << (SMC_DIAG_DMBINFO - 1))) && + !list_empty(&smc->conn.lgr->list)) { + struct smc_connection *conn = &smc->conn; + struct smcd_diag_dmbinfo dinfo = { + .linkid = *((u32 *)conn->lgr->id), + .peer_gid = conn->lgr->peer_gid, + .my_gid = conn->lgr->smcd->local_gid, + .token = conn->rmb_desc->token, + .peer_token = conn->peer_token + }; + + if (nla_put(skb, SMC_DIAG_DMBINFO, sizeof(dinfo), &dinfo) < 0) + goto errout; + } nlmsg_end(skb, nlh); return 0; -- cgit v1.2.3 From a1be5a20f137bdf436bab86c18998229908ce951 Mon Sep 17 00:00:00 2001 From: GhantaKrishnamurthy MohanKrishna Date: Fri, 29 Jun 2018 13:26:18 +0200 Subject: tipc: extend sock diag for group communication This commit extends the existing TIPC socket diagnostics framework for information related to TIPC group communication. Acked-by: Ying Xue Acked-by: Jon Maloy Signed-off-by: GhantaKrishnamurthy MohanKrishna Signed-off-by: David S. Miller --- include/uapi/linux/tipc_netlink.h | 14 ++++++++++++++ net/tipc/group.c | 32 ++++++++++++++++++++++++++++++++ net/tipc/group.h | 1 + net/tipc/socket.c | 5 +++++ 4 files changed, 52 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/tipc_netlink.h b/include/uapi/linux/tipc_netlink.h index 85c11982c89b..0ebe02ef1a86 100644 --- a/include/uapi/linux/tipc_netlink.h +++ b/include/uapi/linux/tipc_netlink.h @@ -121,6 +121,7 @@ enum { TIPC_NLA_SOCK_TIPC_STATE, /* u32 */ TIPC_NLA_SOCK_COOKIE, /* u64 */ TIPC_NLA_SOCK_PAD, /* flag */ + TIPC_NLA_SOCK_GROUP, /* nest */ __TIPC_NLA_SOCK_MAX, TIPC_NLA_SOCK_MAX = __TIPC_NLA_SOCK_MAX - 1 @@ -233,6 +234,19 @@ enum { TIPC_NLA_MON_PEER_MAX = __TIPC_NLA_MON_PEER_MAX - 1 }; +/* Nest, socket group info */ +enum { + TIPC_NLA_SOCK_GROUP_ID, /* u32 */ + TIPC_NLA_SOCK_GROUP_OPEN, /* flag */ + TIPC_NLA_SOCK_GROUP_NODE_SCOPE, /* flag */ + TIPC_NLA_SOCK_GROUP_CLUSTER_SCOPE, /* flag */ + TIPC_NLA_SOCK_GROUP_INSTANCE, /* u32 */ + TIPC_NLA_SOCK_GROUP_BC_SEND_NEXT, /* u32 */ + + __TIPC_NLA_SOCK_GROUP_MAX, + TIPC_NLA_SOCK_GROUP_MAX = __TIPC_NLA_SOCK_GROUP_MAX - 1 +}; + /* Nest, connection info */ enum { TIPC_NLA_CON_UNSPEC, diff --git a/net/tipc/group.c b/net/tipc/group.c index d7a7befeddd4..cbe39e8db39c 100644 --- a/net/tipc/group.c +++ b/net/tipc/group.c @@ -918,3 +918,35 @@ void tipc_group_member_evt(struct tipc_group *grp, } *sk_rcvbuf = tipc_group_rcvbuf_limit(grp); } + +int tipc_group_fill_sock_diag(struct tipc_group *grp, struct sk_buff *skb) +{ + struct nlattr *group = nla_nest_start(skb, TIPC_NLA_SOCK_GROUP); + + if (nla_put_u32(skb, TIPC_NLA_SOCK_GROUP_ID, + grp->type) || + nla_put_u32(skb, TIPC_NLA_SOCK_GROUP_INSTANCE, + grp->instance) || + nla_put_u32(skb, TIPC_NLA_SOCK_GROUP_BC_SEND_NEXT, + grp->bc_snd_nxt)) + goto group_msg_cancel; + + if (grp->scope == TIPC_NODE_SCOPE) + if (nla_put_flag(skb, TIPC_NLA_SOCK_GROUP_NODE_SCOPE)) + goto group_msg_cancel; + + if (grp->scope == TIPC_CLUSTER_SCOPE) + if (nla_put_flag(skb, TIPC_NLA_SOCK_GROUP_CLUSTER_SCOPE)) + goto group_msg_cancel; + + if (*grp->open) + if (nla_put_flag(skb, TIPC_NLA_SOCK_GROUP_OPEN)) + goto group_msg_cancel; + + nla_nest_end(skb, group); + return 0; + +group_msg_cancel: + nla_nest_cancel(skb, group); + return -1; +} diff --git a/net/tipc/group.h b/net/tipc/group.h index 5996af6e9f1d..76b4e5a7b39d 100644 --- a/net/tipc/group.h +++ b/net/tipc/group.h @@ -72,4 +72,5 @@ void tipc_group_update_rcv_win(struct tipc_group *grp, int blks, u32 node, u32 port, struct sk_buff_head *xmitq); u16 tipc_group_bc_snd_nxt(struct tipc_group *grp); void tipc_group_update_member(struct tipc_member *m, int len); +int tipc_group_fill_sock_diag(struct tipc_group *grp, struct sk_buff *skb); #endif diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 14a5d055717d..840dd995f631 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -3316,6 +3316,11 @@ int tipc_sk_fill_sock_diag(struct sk_buff *skb, struct netlink_callback *cb, goto stat_msg_cancel; nla_nest_end(skb, stat); + + if (tsk->group) + if (tipc_group_fill_sock_diag(tsk->group, skb)) + goto stat_msg_cancel; + nla_nest_end(skb, attrs); return 0; -- cgit v1.2.3 From 7ce3f912ae0a79e5d738a3ae1f158b281973e849 Mon Sep 17 00:00:00 2001 From: Sinan Kaya Date: Sat, 30 Jun 2018 11:24:24 -0400 Subject: PCI: Enable PASID only if entire path supports End-End TLP prefixes A PCIe endpoint carries the process address space identifier (PASID) in the TLP prefix as part of the memory read/write transaction. The address information in the TLP is relevant only for a given PASID context. An IOMMU takes PASID value and the address information from the TLP to look up the physical address in the system. PASID is an End-End TLP Prefix (PCIe r4.0, sec 6.20). Sec 2.2.10.2 says It is an error to receive a TLP with an End-End TLP Prefix by a Receiver that does not support End-End TLP Prefixes. A TLP in violation of this rule is handled as a Malformed TLP. This is a reported error associated with the Receiving Port (see Section 6.2). Prevent error condition by proactively requiring End-End TLP prefix to be supported on the entire data path between the endpoint and the root port before enabling PASID. Signed-off-by: Sinan Kaya Signed-off-by: Bjorn Helgaas --- drivers/pci/ats.c | 3 +++ drivers/pci/probe.c | 24 ++++++++++++++++++++++++ include/linux/pci.h | 1 + include/uapi/linux/pci_regs.h | 1 + 4 files changed, 29 insertions(+) (limited to 'include') diff --git a/drivers/pci/ats.c b/drivers/pci/ats.c index 4923a2a8e14b..5b78f3b1b918 100644 --- a/drivers/pci/ats.c +++ b/drivers/pci/ats.c @@ -273,6 +273,9 @@ int pci_enable_pasid(struct pci_dev *pdev, int features) if (WARN_ON(pdev->pasid_enabled)) return -EBUSY; + if (!pdev->eetlp_prefix_path) + return -EINVAL; + pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PASID); if (!pos) return -EINVAL; diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index ac876e32de4b..4c35c2909d57 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2042,6 +2042,29 @@ static void pci_configure_ltr(struct pci_dev *dev) #endif } +static void pci_configure_eetlp_prefix(struct pci_dev *dev) +{ +#ifdef CONFIG_PCI_PASID + struct pci_dev *bridge; + u32 cap; + + if (!pci_is_pcie(dev)) + return; + + pcie_capability_read_dword(dev, PCI_EXP_DEVCAP2, &cap); + if (!(cap & PCI_EXP_DEVCAP2_EE_PREFIX)) + return; + + if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT) + dev->eetlp_prefix_path = 1; + else { + bridge = pci_upstream_bridge(dev); + if (bridge && bridge->eetlp_prefix_path) + dev->eetlp_prefix_path = 1; + } +#endif +} + static void pci_configure_device(struct pci_dev *dev) { struct hotplug_params hpp; @@ -2051,6 +2074,7 @@ static void pci_configure_device(struct pci_dev *dev) pci_configure_extended_tags(dev, NULL); pci_configure_relaxed_ordering(dev); pci_configure_ltr(dev); + pci_configure_eetlp_prefix(dev); memset(&hpp, 0, sizeof(hpp)); ret = pci_get_hp_params(dev, &hpp); diff --git a/include/linux/pci.h b/include/linux/pci.h index 340029b2fb38..6ba818449095 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -350,6 +350,7 @@ struct pci_dev { unsigned int ltr_path:1; /* Latency Tolerance Reporting supported from root to here */ #endif + unsigned int eetlp_prefix_path:1; /* End-to-End TLP Prefix */ pci_channel_state_t error_state; /* Current connectivity state */ struct device dev; /* Generic device interface */ diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index 4da87e2ef8a8..04d7480db714 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -636,6 +636,7 @@ #define PCI_EXP_DEVCAP2_OBFF_MASK 0x000c0000 /* OBFF support mechanism */ #define PCI_EXP_DEVCAP2_OBFF_MSG 0x00040000 /* New message signaling */ #define PCI_EXP_DEVCAP2_OBFF_WAKE 0x00080000 /* Re-use WAKE# for OBFF */ +#define PCI_EXP_DEVCAP2_EE_PREFIX 0x00200000 /* End-End TLP Prefix */ #define PCI_EXP_DEVCTL2 40 /* Device Control 2 */ #define PCI_EXP_DEVCTL2_COMP_TIMEOUT 0x000f /* Completion Timeout Value */ #define PCI_EXP_DEVCTL2_COMP_TMOUT_DIS 0x0010 /* Completion Timeout Disable */ -- cgit v1.2.3 From bb29648102335586e9a66289a1d98a0cb392b6e5 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 18 Jun 2018 10:22:38 -0700 Subject: crypto: vmac - separate tfm and request context syzbot reported a crash in vmac_final() when multiple threads concurrently use the same "vmac(aes)" transform through AF_ALG. The bug is pretty fundamental: the VMAC template doesn't separate per-request state from per-tfm (per-key) state like the other hash algorithms do, but rather stores it all in the tfm context. That's wrong. Also, vmac_final() incorrectly zeroes most of the state including the derived keys and cached pseudorandom pad. Therefore, only the first VMAC invocation with a given key calculates the correct digest. Fix these bugs by splitting the per-tfm state from the per-request state and using the proper init/update/final sequencing for requests. Reproducer for the crash: #include #include #include int main() { int fd; struct sockaddr_alg addr = { .salg_type = "hash", .salg_name = "vmac(aes)", }; char buf[256] = { 0 }; fd = socket(AF_ALG, SOCK_SEQPACKET, 0); bind(fd, (void *)&addr, sizeof(addr)); setsockopt(fd, SOL_ALG, ALG_SET_KEY, buf, 16); fork(); fd = accept(fd, NULL, NULL); for (;;) write(fd, buf, 256); } The immediate cause of the crash is that vmac_ctx_t.partial_size exceeds VMAC_NHBYTES, causing vmac_final() to memset() a negative length. Reported-by: syzbot+264bca3a6e8d645550d3@syzkaller.appspotmail.com Fixes: f1939f7c5645 ("crypto: vmac - New hash algorithm for intel_txt support") Cc: # v2.6.32+ Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu --- crypto/vmac.c | 408 ++++++++++++++++++++++---------------------------- include/crypto/vmac.h | 63 -------- 2 files changed, 181 insertions(+), 290 deletions(-) delete mode 100644 include/crypto/vmac.h (limited to 'include') diff --git a/crypto/vmac.c b/crypto/vmac.c index 3034454a3713..bb2fc787d615 100644 --- a/crypto/vmac.c +++ b/crypto/vmac.c @@ -1,6 +1,10 @@ /* - * Modified to interface to the Linux kernel + * VMAC: Message Authentication Code using Universal Hashing + * + * Reference: https://tools.ietf.org/html/draft-krovetz-vmac-01 + * * Copyright (c) 2009, Intel Corporation. + * Copyright (c) 2018, Google Inc. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -16,14 +20,15 @@ * Place - Suite 330, Boston, MA 02111-1307 USA. */ -/* -------------------------------------------------------------------------- - * VMAC and VHASH Implementation by Ted Krovetz (tdk@acm.org) and Wei Dai. - * This implementation is herby placed in the public domain. - * The authors offers no warranty. Use at your own risk. - * Please send bug reports to the authors. - * Last modified: 17 APR 08, 1700 PDT - * ----------------------------------------------------------------------- */ +/* + * Derived from: + * VMAC and VHASH Implementation by Ted Krovetz (tdk@acm.org) and Wei Dai. + * This implementation is herby placed in the public domain. + * The authors offers no warranty. Use at your own risk. + * Last modified: 17 APR 08, 1700 PDT + */ +#include #include #include #include @@ -31,9 +36,35 @@ #include #include #include -#include #include +/* + * User definable settings. + */ +#define VMAC_TAG_LEN 64 +#define VMAC_KEY_SIZE 128/* Must be 128, 192 or 256 */ +#define VMAC_KEY_LEN (VMAC_KEY_SIZE/8) +#define VMAC_NHBYTES 128/* Must 2^i for any 3 < i < 13 Standard = 128*/ + +/* per-transform (per-key) context */ +struct vmac_tfm_ctx { + struct crypto_cipher *cipher; + u64 nhkey[(VMAC_NHBYTES/8)+2*(VMAC_TAG_LEN/64-1)]; + u64 polykey[2*VMAC_TAG_LEN/64]; + u64 l3key[2*VMAC_TAG_LEN/64]; +}; + +/* per-request context */ +struct vmac_desc_ctx { + union { + u8 partial[VMAC_NHBYTES]; /* partial block */ + __le64 partial_words[VMAC_NHBYTES / 8]; + }; + unsigned int partial_size; /* size of the partial block */ + bool first_block_processed; + u64 polytmp[2*VMAC_TAG_LEN/64]; /* running total of L2-hash */ +}; + /* * Constants and masks */ @@ -318,13 +349,6 @@ static void poly_step_func(u64 *ahi, u64 *alo, } while (0) #endif -static void vhash_abort(struct vmac_ctx *ctx) -{ - ctx->polytmp[0] = ctx->polykey[0] ; - ctx->polytmp[1] = ctx->polykey[1] ; - ctx->first_block_processed = 0; -} - static u64 l3hash(u64 p1, u64 p2, u64 k1, u64 k2, u64 len) { u64 rh, rl, t, z = 0; @@ -364,280 +388,209 @@ static u64 l3hash(u64 p1, u64 p2, u64 k1, u64 k2, u64 len) return rl; } -static void vhash_update(const unsigned char *m, - unsigned int mbytes, /* Pos multiple of VMAC_NHBYTES */ - struct vmac_ctx *ctx) +/* L1 and L2-hash one or more VMAC_NHBYTES-byte blocks */ +static void vhash_blocks(const struct vmac_tfm_ctx *tctx, + struct vmac_desc_ctx *dctx, + const __le64 *mptr, unsigned int blocks) { - u64 rh, rl, *mptr; - const u64 *kptr = (u64 *)ctx->nhkey; - int i; - u64 ch, cl; - u64 pkh = ctx->polykey[0]; - u64 pkl = ctx->polykey[1]; - - if (!mbytes) - return; - - BUG_ON(mbytes % VMAC_NHBYTES); - - mptr = (u64 *)m; - i = mbytes / VMAC_NHBYTES; /* Must be non-zero */ - - ch = ctx->polytmp[0]; - cl = ctx->polytmp[1]; - - if (!ctx->first_block_processed) { - ctx->first_block_processed = 1; + const u64 *kptr = tctx->nhkey; + const u64 pkh = tctx->polykey[0]; + const u64 pkl = tctx->polykey[1]; + u64 ch = dctx->polytmp[0]; + u64 cl = dctx->polytmp[1]; + u64 rh, rl; + + if (!dctx->first_block_processed) { + dctx->first_block_processed = true; nh_vmac_nhbytes(mptr, kptr, VMAC_NHBYTES/8, rh, rl); rh &= m62; ADD128(ch, cl, rh, rl); mptr += (VMAC_NHBYTES/sizeof(u64)); - i--; + blocks--; } - while (i--) { + while (blocks--) { nh_vmac_nhbytes(mptr, kptr, VMAC_NHBYTES/8, rh, rl); rh &= m62; poly_step(ch, cl, pkh, pkl, rh, rl); mptr += (VMAC_NHBYTES/sizeof(u64)); } - ctx->polytmp[0] = ch; - ctx->polytmp[1] = cl; + dctx->polytmp[0] = ch; + dctx->polytmp[1] = cl; } -static u64 vhash(unsigned char m[], unsigned int mbytes, - u64 *tagl, struct vmac_ctx *ctx) +static int vmac_setkey(struct crypto_shash *tfm, + const u8 *key, unsigned int keylen) { - u64 rh, rl, *mptr; - const u64 *kptr = (u64 *)ctx->nhkey; - int i, remaining; - u64 ch, cl; - u64 pkh = ctx->polykey[0]; - u64 pkl = ctx->polykey[1]; - - mptr = (u64 *)m; - i = mbytes / VMAC_NHBYTES; - remaining = mbytes % VMAC_NHBYTES; - - if (ctx->first_block_processed) { - ch = ctx->polytmp[0]; - cl = ctx->polytmp[1]; - } else if (i) { - nh_vmac_nhbytes(mptr, kptr, VMAC_NHBYTES/8, ch, cl); - ch &= m62; - ADD128(ch, cl, pkh, pkl); - mptr += (VMAC_NHBYTES/sizeof(u64)); - i--; - } else if (remaining) { - nh_16(mptr, kptr, 2*((remaining+15)/16), ch, cl); - ch &= m62; - ADD128(ch, cl, pkh, pkl); - mptr += (VMAC_NHBYTES/sizeof(u64)); - goto do_l3; - } else {/* Empty String */ - ch = pkh; cl = pkl; - goto do_l3; - } - - while (i--) { - nh_vmac_nhbytes(mptr, kptr, VMAC_NHBYTES/8, rh, rl); - rh &= m62; - poly_step(ch, cl, pkh, pkl, rh, rl); - mptr += (VMAC_NHBYTES/sizeof(u64)); - } - if (remaining) { - nh_16(mptr, kptr, 2*((remaining+15)/16), rh, rl); - rh &= m62; - poly_step(ch, cl, pkh, pkl, rh, rl); - } - -do_l3: - vhash_abort(ctx); - remaining *= 8; - return l3hash(ch, cl, ctx->l3key[0], ctx->l3key[1], remaining); -} + struct vmac_tfm_ctx *tctx = crypto_shash_ctx(tfm); + __be64 out[2]; + u8 in[16] = { 0 }; + unsigned int i; + int err; -static u64 vmac(unsigned char m[], unsigned int mbytes, - const unsigned char n[16], u64 *tagl, - struct vmac_ctx_t *ctx) -{ - u64 *in_n, *out_p; - u64 p, h; - int i; - - in_n = ctx->__vmac_ctx.cached_nonce; - out_p = ctx->__vmac_ctx.cached_aes; - - i = n[15] & 1; - if ((*(u64 *)(n+8) != in_n[1]) || (*(u64 *)(n) != in_n[0])) { - in_n[0] = *(u64 *)(n); - in_n[1] = *(u64 *)(n+8); - ((unsigned char *)in_n)[15] &= 0xFE; - crypto_cipher_encrypt_one(ctx->child, - (unsigned char *)out_p, (unsigned char *)in_n); - - ((unsigned char *)in_n)[15] |= (unsigned char)(1-i); + if (keylen != VMAC_KEY_LEN) { + crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN); + return -EINVAL; } - p = be64_to_cpup(out_p + i); - h = vhash(m, mbytes, (u64 *)0, &ctx->__vmac_ctx); - return le64_to_cpu(p + h); -} -static int vmac_set_key(unsigned char user_key[], struct vmac_ctx_t *ctx) -{ - u64 in[2] = {0}, out[2]; - unsigned i; - int err = 0; - - err = crypto_cipher_setkey(ctx->child, user_key, VMAC_KEY_LEN); + err = crypto_cipher_setkey(tctx->cipher, key, keylen); if (err) return err; /* Fill nh key */ - ((unsigned char *)in)[0] = 0x80; - for (i = 0; i < sizeof(ctx->__vmac_ctx.nhkey)/8; i += 2) { - crypto_cipher_encrypt_one(ctx->child, - (unsigned char *)out, (unsigned char *)in); - ctx->__vmac_ctx.nhkey[i] = be64_to_cpup(out); - ctx->__vmac_ctx.nhkey[i+1] = be64_to_cpup(out+1); - ((unsigned char *)in)[15] += 1; + in[0] = 0x80; + for (i = 0; i < ARRAY_SIZE(tctx->nhkey); i += 2) { + crypto_cipher_encrypt_one(tctx->cipher, (u8 *)out, in); + tctx->nhkey[i] = be64_to_cpu(out[0]); + tctx->nhkey[i+1] = be64_to_cpu(out[1]); + in[15]++; } /* Fill poly key */ - ((unsigned char *)in)[0] = 0xC0; - in[1] = 0; - for (i = 0; i < sizeof(ctx->__vmac_ctx.polykey)/8; i += 2) { - crypto_cipher_encrypt_one(ctx->child, - (unsigned char *)out, (unsigned char *)in); - ctx->__vmac_ctx.polytmp[i] = - ctx->__vmac_ctx.polykey[i] = - be64_to_cpup(out) & mpoly; - ctx->__vmac_ctx.polytmp[i+1] = - ctx->__vmac_ctx.polykey[i+1] = - be64_to_cpup(out+1) & mpoly; - ((unsigned char *)in)[15] += 1; + in[0] = 0xC0; + in[15] = 0; + for (i = 0; i < ARRAY_SIZE(tctx->polykey); i += 2) { + crypto_cipher_encrypt_one(tctx->cipher, (u8 *)out, in); + tctx->polykey[i] = be64_to_cpu(out[0]) & mpoly; + tctx->polykey[i+1] = be64_to_cpu(out[1]) & mpoly; + in[15]++; } /* Fill ip key */ - ((unsigned char *)in)[0] = 0xE0; - in[1] = 0; - for (i = 0; i < sizeof(ctx->__vmac_ctx.l3key)/8; i += 2) { + in[0] = 0xE0; + in[15] = 0; + for (i = 0; i < ARRAY_SIZE(tctx->l3key); i += 2) { do { - crypto_cipher_encrypt_one(ctx->child, - (unsigned char *)out, (unsigned char *)in); - ctx->__vmac_ctx.l3key[i] = be64_to_cpup(out); - ctx->__vmac_ctx.l3key[i+1] = be64_to_cpup(out+1); - ((unsigned char *)in)[15] += 1; - } while (ctx->__vmac_ctx.l3key[i] >= p64 - || ctx->__vmac_ctx.l3key[i+1] >= p64); + crypto_cipher_encrypt_one(tctx->cipher, (u8 *)out, in); + tctx->l3key[i] = be64_to_cpu(out[0]); + tctx->l3key[i+1] = be64_to_cpu(out[1]); + in[15]++; + } while (tctx->l3key[i] >= p64 || tctx->l3key[i+1] >= p64); } - /* Invalidate nonce/aes cache and reset other elements */ - ctx->__vmac_ctx.cached_nonce[0] = (u64)-1; /* Ensure illegal nonce */ - ctx->__vmac_ctx.cached_nonce[1] = (u64)0; /* Ensure illegal nonce */ - ctx->__vmac_ctx.first_block_processed = 0; - - return err; + return 0; } -static int vmac_setkey(struct crypto_shash *parent, - const u8 *key, unsigned int keylen) +static int vmac_init(struct shash_desc *desc) { - struct vmac_ctx_t *ctx = crypto_shash_ctx(parent); - - if (keylen != VMAC_KEY_LEN) { - crypto_shash_set_flags(parent, CRYPTO_TFM_RES_BAD_KEY_LEN); - return -EINVAL; - } - - return vmac_set_key((u8 *)key, ctx); -} + const struct vmac_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm); + struct vmac_desc_ctx *dctx = shash_desc_ctx(desc); -static int vmac_init(struct shash_desc *pdesc) -{ + dctx->partial_size = 0; + dctx->first_block_processed = false; + memcpy(dctx->polytmp, tctx->polykey, sizeof(dctx->polytmp)); return 0; } -static int vmac_update(struct shash_desc *pdesc, const u8 *p, - unsigned int len) +static int vmac_update(struct shash_desc *desc, const u8 *p, unsigned int len) { - struct crypto_shash *parent = pdesc->tfm; - struct vmac_ctx_t *ctx = crypto_shash_ctx(parent); - int expand; - int min; - - expand = VMAC_NHBYTES - ctx->partial_size > 0 ? - VMAC_NHBYTES - ctx->partial_size : 0; - - min = len < expand ? len : expand; - - memcpy(ctx->partial + ctx->partial_size, p, min); - ctx->partial_size += min; - - if (len < expand) - return 0; - - vhash_update(ctx->partial, VMAC_NHBYTES, &ctx->__vmac_ctx); - ctx->partial_size = 0; - - len -= expand; - p += expand; + const struct vmac_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm); + struct vmac_desc_ctx *dctx = shash_desc_ctx(desc); + unsigned int n; + + if (dctx->partial_size) { + n = min(len, VMAC_NHBYTES - dctx->partial_size); + memcpy(&dctx->partial[dctx->partial_size], p, n); + dctx->partial_size += n; + p += n; + len -= n; + if (dctx->partial_size == VMAC_NHBYTES) { + vhash_blocks(tctx, dctx, dctx->partial_words, 1); + dctx->partial_size = 0; + } + } - if (len % VMAC_NHBYTES) { - memcpy(ctx->partial, p + len - (len % VMAC_NHBYTES), - len % VMAC_NHBYTES); - ctx->partial_size = len % VMAC_NHBYTES; + if (len >= VMAC_NHBYTES) { + n = round_down(len, VMAC_NHBYTES); + /* TODO: 'p' may be misaligned here */ + vhash_blocks(tctx, dctx, (const __le64 *)p, n / VMAC_NHBYTES); + p += n; + len -= n; } - vhash_update(p, len - len % VMAC_NHBYTES, &ctx->__vmac_ctx); + if (len) { + memcpy(dctx->partial, p, len); + dctx->partial_size = len; + } return 0; } -static int vmac_final(struct shash_desc *pdesc, u8 *out) +static u64 vhash_final(const struct vmac_tfm_ctx *tctx, + struct vmac_desc_ctx *dctx) { - struct crypto_shash *parent = pdesc->tfm; - struct vmac_ctx_t *ctx = crypto_shash_ctx(parent); - vmac_t mac; - u8 nonce[16] = {}; - - /* vmac() ends up accessing outside the array bounds that - * we specify. In appears to access up to the next 2-word - * boundary. We'll just be uber cautious and zero the - * unwritten bytes in the buffer. - */ - if (ctx->partial_size) { - memset(ctx->partial + ctx->partial_size, 0, - VMAC_NHBYTES - ctx->partial_size); + unsigned int partial = dctx->partial_size; + u64 ch = dctx->polytmp[0]; + u64 cl = dctx->polytmp[1]; + + /* L1 and L2-hash the final block if needed */ + if (partial) { + /* Zero-pad to next 128-bit boundary */ + unsigned int n = round_up(partial, 16); + u64 rh, rl; + + memset(&dctx->partial[partial], 0, n - partial); + nh_16(dctx->partial_words, tctx->nhkey, n / 8, rh, rl); + rh &= m62; + if (dctx->first_block_processed) + poly_step(ch, cl, tctx->polykey[0], tctx->polykey[1], + rh, rl); + else + ADD128(ch, cl, rh, rl); } - mac = vmac(ctx->partial, ctx->partial_size, nonce, NULL, ctx); - memcpy(out, &mac, sizeof(vmac_t)); - memzero_explicit(&mac, sizeof(vmac_t)); - memset(&ctx->__vmac_ctx, 0, sizeof(struct vmac_ctx)); - ctx->partial_size = 0; + + /* L3-hash the 128-bit output of L2-hash */ + return l3hash(ch, cl, tctx->l3key[0], tctx->l3key[1], partial * 8); +} + +static int vmac_final(struct shash_desc *desc, u8 *out) +{ + const struct vmac_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm); + struct vmac_desc_ctx *dctx = shash_desc_ctx(desc); + static const u8 nonce[16] = {}; /* TODO: this is insecure */ + union { + u8 bytes[16]; + __be64 pads[2]; + } block; + int index; + u64 hash, pad; + + /* Finish calculating the VHASH of the message */ + hash = vhash_final(tctx, dctx); + + /* Generate pseudorandom pad by encrypting the nonce */ + memcpy(&block, nonce, 16); + index = block.bytes[15] & 1; + block.bytes[15] &= ~1; + crypto_cipher_encrypt_one(tctx->cipher, block.bytes, block.bytes); + pad = be64_to_cpu(block.pads[index]); + + /* The VMAC is the sum of VHASH and the pseudorandom pad */ + put_unaligned_le64(hash + pad, out); return 0; } static int vmac_init_tfm(struct crypto_tfm *tfm) { - struct crypto_cipher *cipher; - struct crypto_instance *inst = (void *)tfm->__crt_alg; + struct crypto_instance *inst = crypto_tfm_alg_instance(tfm); struct crypto_spawn *spawn = crypto_instance_ctx(inst); - struct vmac_ctx_t *ctx = crypto_tfm_ctx(tfm); + struct vmac_tfm_ctx *tctx = crypto_tfm_ctx(tfm); + struct crypto_cipher *cipher; cipher = crypto_spawn_cipher(spawn); if (IS_ERR(cipher)) return PTR_ERR(cipher); - ctx->child = cipher; + tctx->cipher = cipher; return 0; } static void vmac_exit_tfm(struct crypto_tfm *tfm) { - struct vmac_ctx_t *ctx = crypto_tfm_ctx(tfm); - crypto_free_cipher(ctx->child); + struct vmac_tfm_ctx *tctx = crypto_tfm_ctx(tfm); + + crypto_free_cipher(tctx->cipher); } static int vmac_create(struct crypto_template *tmpl, struct rtattr **tb) @@ -674,11 +627,12 @@ static int vmac_create(struct crypto_template *tmpl, struct rtattr **tb) inst->alg.base.cra_blocksize = alg->cra_blocksize; inst->alg.base.cra_alignmask = alg->cra_alignmask; - inst->alg.digestsize = sizeof(vmac_t); - inst->alg.base.cra_ctxsize = sizeof(struct vmac_ctx_t); + inst->alg.base.cra_ctxsize = sizeof(struct vmac_tfm_ctx); inst->alg.base.cra_init = vmac_init_tfm; inst->alg.base.cra_exit = vmac_exit_tfm; + inst->alg.descsize = sizeof(struct vmac_desc_ctx); + inst->alg.digestsize = VMAC_TAG_LEN / 8; inst->alg.init = vmac_init; inst->alg.update = vmac_update; inst->alg.final = vmac_final; diff --git a/include/crypto/vmac.h b/include/crypto/vmac.h deleted file mode 100644 index 6b700c7b2fe1..000000000000 --- a/include/crypto/vmac.h +++ /dev/null @@ -1,63 +0,0 @@ -/* - * Modified to interface to the Linux kernel - * Copyright (c) 2009, Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 59 Temple - * Place - Suite 330, Boston, MA 02111-1307 USA. - */ - -#ifndef __CRYPTO_VMAC_H -#define __CRYPTO_VMAC_H - -/* -------------------------------------------------------------------------- - * VMAC and VHASH Implementation by Ted Krovetz (tdk@acm.org) and Wei Dai. - * This implementation is herby placed in the public domain. - * The authors offers no warranty. Use at your own risk. - * Please send bug reports to the authors. - * Last modified: 17 APR 08, 1700 PDT - * ----------------------------------------------------------------------- */ - -/* - * User definable settings. - */ -#define VMAC_TAG_LEN 64 -#define VMAC_KEY_SIZE 128/* Must be 128, 192 or 256 */ -#define VMAC_KEY_LEN (VMAC_KEY_SIZE/8) -#define VMAC_NHBYTES 128/* Must 2^i for any 3 < i < 13 Standard = 128*/ - -/* - * This implementation uses u32 and u64 as names for unsigned 32- - * and 64-bit integer types. These are defined in C99 stdint.h. The - * following may need adaptation if you are not running a C99 or - * Microsoft C environment. - */ -struct vmac_ctx { - u64 nhkey[(VMAC_NHBYTES/8)+2*(VMAC_TAG_LEN/64-1)]; - u64 polykey[2*VMAC_TAG_LEN/64]; - u64 l3key[2*VMAC_TAG_LEN/64]; - u64 polytmp[2*VMAC_TAG_LEN/64]; - u64 cached_nonce[2]; - u64 cached_aes[2]; - int first_block_processed; -}; - -typedef u64 vmac_t; - -struct vmac_ctx_t { - struct crypto_cipher *child; - struct vmac_ctx __vmac_ctx; - u8 partial[VMAC_NHBYTES]; /* partial block */ - int partial_size; /* size of the partial block */ -}; - -#endif /* __CRYPTO_VMAC_H */ -- cgit v1.2.3 From 80d19669ecd34423e85ca04f2210b0e42a47cb16 Mon Sep 17 00:00:00 2001 From: Amritha Nambiar Date: Fri, 29 Jun 2018 21:26:41 -0700 Subject: net: Refactor XPS for CPUs and Rx queues Refactor XPS code to support Tx queue selection based on CPU(s) map or Rx queue(s) map. Signed-off-by: Amritha Nambiar Signed-off-by: David S. Miller --- include/linux/cpumask.h | 11 ++- include/linux/netdevice.h | 98 ++++++++++++++++++++- net/core/dev.c | 211 ++++++++++++++++++++++++++++++---------------- net/core/net-sysfs.c | 4 +- 4 files changed, 244 insertions(+), 80 deletions(-) (limited to 'include') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index bf53d893ad02..57f20a0a7794 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -115,12 +115,17 @@ extern struct cpumask __cpu_active_mask; #define cpu_active(cpu) ((cpu) == 0) #endif -/* verify cpu argument to cpumask_* operators */ -static inline unsigned int cpumask_check(unsigned int cpu) +static inline void cpu_max_bits_warn(unsigned int cpu, unsigned int bits) { #ifdef CONFIG_DEBUG_PER_CPU_MAPS - WARN_ON_ONCE(cpu >= nr_cpumask_bits); + WARN_ON_ONCE(cpu >= bits); #endif /* CONFIG_DEBUG_PER_CPU_MAPS */ +} + +/* verify cpu argument to cpumask_* operators */ +static inline unsigned int cpumask_check(unsigned int cpu) +{ + cpu_max_bits_warn(cpu, nr_cpumask_bits); return cpu; } diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c6b377a15869..8bf8d6149f79 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -731,10 +731,15 @@ struct xps_map { */ struct xps_dev_maps { struct rcu_head rcu; - struct xps_map __rcu *cpu_map[0]; + struct xps_map __rcu *attr_map[0]; /* Either CPUs map or RXQs map */ }; -#define XPS_DEV_MAPS_SIZE(_tcs) (sizeof(struct xps_dev_maps) + \ + +#define XPS_CPU_DEV_MAPS_SIZE(_tcs) (sizeof(struct xps_dev_maps) + \ (nr_cpu_ids * (_tcs) * sizeof(struct xps_map *))) + +#define XPS_RXQ_DEV_MAPS_SIZE(_tcs, _rxqs) (sizeof(struct xps_dev_maps) +\ + (_rxqs * (_tcs) * sizeof(struct xps_map *))) + #endif /* CONFIG_XPS */ #define TC_MAX_QUEUE 16 @@ -1910,7 +1915,8 @@ struct net_device { int watchdog_timeo; #ifdef CONFIG_XPS - struct xps_dev_maps __rcu *xps_maps; + struct xps_dev_maps __rcu *xps_cpus_map; + struct xps_dev_maps __rcu *xps_rxqs_map; #endif #ifdef CONFIG_NET_CLS_ACT struct mini_Qdisc __rcu *miniq_egress; @@ -3259,6 +3265,92 @@ static inline void netif_wake_subqueue(struct net_device *dev, u16 queue_index) #ifdef CONFIG_XPS int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, u16 index); +int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask, + u16 index, bool is_rxqs_map); + +/** + * netif_attr_test_mask - Test a CPU or Rx queue set in a mask + * @j: CPU/Rx queue index + * @mask: bitmask of all cpus/rx queues + * @nr_bits: number of bits in the bitmask + * + * Test if a CPU or Rx queue index is set in a mask of all CPU/Rx queues. + */ +static inline bool netif_attr_test_mask(unsigned long j, + const unsigned long *mask, + unsigned int nr_bits) +{ + cpu_max_bits_warn(j, nr_bits); + return test_bit(j, mask); +} + +/** + * netif_attr_test_online - Test for online CPU/Rx queue + * @j: CPU/Rx queue index + * @online_mask: bitmask for CPUs/Rx queues that are online + * @nr_bits: number of bits in the bitmask + * + * Returns true if a CPU/Rx queue is online. + */ +static inline bool netif_attr_test_online(unsigned long j, + const unsigned long *online_mask, + unsigned int nr_bits) +{ + cpu_max_bits_warn(j, nr_bits); + + if (online_mask) + return test_bit(j, online_mask); + + return (j < nr_bits); +} + +/** + * netif_attrmask_next - get the next CPU/Rx queue in a cpu/Rx queues mask + * @n: CPU/Rx queue index + * @srcp: the cpumask/Rx queue mask pointer + * @nr_bits: number of bits in the bitmask + * + * Returns >= nr_bits if no further CPUs/Rx queues set. + */ +static inline unsigned int netif_attrmask_next(int n, const unsigned long *srcp, + unsigned int nr_bits) +{ + /* -1 is a legal arg here. */ + if (n != -1) + cpu_max_bits_warn(n, nr_bits); + + if (srcp) + return find_next_bit(srcp, nr_bits, n + 1); + + return n + 1; +} + +/** + * netif_attrmask_next_and - get the next CPU/Rx queue in *src1p & *src2p + * @n: CPU/Rx queue index + * @src1p: the first CPUs/Rx queues mask pointer + * @src2p: the second CPUs/Rx queues mask pointer + * @nr_bits: number of bits in the bitmask + * + * Returns >= nr_bits if no further CPUs/Rx queues set in both. + */ +static inline int netif_attrmask_next_and(int n, const unsigned long *src1p, + const unsigned long *src2p, + unsigned int nr_bits) +{ + /* -1 is a legal arg here. */ + if (n != -1) + cpu_max_bits_warn(n, nr_bits); + + if (src1p && src2p) + return find_next_and_bit(src1p, src2p, nr_bits, n + 1); + else if (src1p) + return find_next_bit(src1p, nr_bits, n + 1); + else if (src2p) + return find_next_bit(src2p, nr_bits, n + 1); + + return n + 1; +} #else static inline int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, diff --git a/net/core/dev.c b/net/core/dev.c index dffed642e686..71059558dc39 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2092,7 +2092,7 @@ static bool remove_xps_queue(struct xps_dev_maps *dev_maps, int pos; if (dev_maps) - map = xmap_dereference(dev_maps->cpu_map[tci]); + map = xmap_dereference(dev_maps->attr_map[tci]); if (!map) return false; @@ -2105,7 +2105,7 @@ static bool remove_xps_queue(struct xps_dev_maps *dev_maps, break; } - RCU_INIT_POINTER(dev_maps->cpu_map[tci], NULL); + RCU_INIT_POINTER(dev_maps->attr_map[tci], NULL); kfree_rcu(map, rcu); return false; } @@ -2135,31 +2135,58 @@ static bool remove_xps_queue_cpu(struct net_device *dev, return active; } +static void clean_xps_maps(struct net_device *dev, const unsigned long *mask, + struct xps_dev_maps *dev_maps, unsigned int nr_ids, + u16 offset, u16 count, bool is_rxqs_map) +{ + bool active = false; + int i, j; + + for (j = -1; j = netif_attrmask_next(j, mask, nr_ids), + j < nr_ids;) + active |= remove_xps_queue_cpu(dev, dev_maps, j, offset, + count); + if (!active) { + if (is_rxqs_map) { + RCU_INIT_POINTER(dev->xps_rxqs_map, NULL); + } else { + RCU_INIT_POINTER(dev->xps_cpus_map, NULL); + + for (i = offset + (count - 1); count--; i--) + netdev_queue_numa_node_write( + netdev_get_tx_queue(dev, i), + NUMA_NO_NODE); + } + kfree_rcu(dev_maps, rcu); + } +} + static void netif_reset_xps_queues(struct net_device *dev, u16 offset, u16 count) { + const unsigned long *possible_mask = NULL; struct xps_dev_maps *dev_maps; - int cpu, i; - bool active = false; + unsigned int nr_ids; mutex_lock(&xps_map_mutex); - dev_maps = xmap_dereference(dev->xps_maps); - if (!dev_maps) - goto out_no_maps; - - for_each_possible_cpu(cpu) - active |= remove_xps_queue_cpu(dev, dev_maps, cpu, - offset, count); + dev_maps = xmap_dereference(dev->xps_rxqs_map); + if (dev_maps) { + nr_ids = dev->num_rx_queues; + clean_xps_maps(dev, possible_mask, dev_maps, nr_ids, offset, + count, true); - if (!active) { - RCU_INIT_POINTER(dev->xps_maps, NULL); - kfree_rcu(dev_maps, rcu); } - for (i = offset + (count - 1); count--; i--) - netdev_queue_numa_node_write(netdev_get_tx_queue(dev, i), - NUMA_NO_NODE); + dev_maps = xmap_dereference(dev->xps_cpus_map); + if (!dev_maps) + goto out_no_maps; + + if (num_possible_cpus() > 1) + possible_mask = cpumask_bits(cpu_possible_mask); + nr_ids = nr_cpu_ids; + clean_xps_maps(dev, possible_mask, dev_maps, nr_ids, offset, count, + false); out_no_maps: mutex_unlock(&xps_map_mutex); @@ -2170,8 +2197,8 @@ static void netif_reset_xps_queues_gt(struct net_device *dev, u16 index) netif_reset_xps_queues(dev, index, dev->num_tx_queues - index); } -static struct xps_map *expand_xps_map(struct xps_map *map, - int cpu, u16 index) +static struct xps_map *expand_xps_map(struct xps_map *map, int attr_index, + u16 index, bool is_rxqs_map) { struct xps_map *new_map; int alloc_len = XPS_MIN_MAP_ALLOC; @@ -2183,7 +2210,7 @@ static struct xps_map *expand_xps_map(struct xps_map *map, return map; } - /* Need to add queue to this CPU's existing map */ + /* Need to add tx-queue to this CPU's/rx-queue's existing map */ if (map) { if (pos < map->alloc_len) return map; @@ -2191,9 +2218,14 @@ static struct xps_map *expand_xps_map(struct xps_map *map, alloc_len = map->alloc_len * 2; } - /* Need to allocate new map to store queue on this CPU's map */ - new_map = kzalloc_node(XPS_MAP_SIZE(alloc_len), GFP_KERNEL, - cpu_to_node(cpu)); + /* Need to allocate new map to store tx-queue on this CPU's/rx-queue's + * map + */ + if (is_rxqs_map) + new_map = kzalloc(XPS_MAP_SIZE(alloc_len), GFP_KERNEL); + else + new_map = kzalloc_node(XPS_MAP_SIZE(alloc_len), GFP_KERNEL, + cpu_to_node(attr_index)); if (!new_map) return NULL; @@ -2205,14 +2237,16 @@ static struct xps_map *expand_xps_map(struct xps_map *map, return new_map; } -int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, - u16 index) +int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask, + u16 index, bool is_rxqs_map) { + const unsigned long *online_mask = NULL, *possible_mask = NULL; struct xps_dev_maps *dev_maps, *new_dev_maps = NULL; - int i, cpu, tci, numa_node_id = -2; + int i, j, tci, numa_node_id = -2; int maps_sz, num_tc = 1, tc = 0; struct xps_map *map, *new_map; bool active = false; + unsigned int nr_ids; if (dev->num_tc) { num_tc = dev->num_tc; @@ -2221,16 +2255,27 @@ int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, return -EINVAL; } - maps_sz = XPS_DEV_MAPS_SIZE(num_tc); - if (maps_sz < L1_CACHE_BYTES) - maps_sz = L1_CACHE_BYTES; - mutex_lock(&xps_map_mutex); + if (is_rxqs_map) { + maps_sz = XPS_RXQ_DEV_MAPS_SIZE(num_tc, dev->num_rx_queues); + dev_maps = xmap_dereference(dev->xps_rxqs_map); + nr_ids = dev->num_rx_queues; + } else { + maps_sz = XPS_CPU_DEV_MAPS_SIZE(num_tc); + if (num_possible_cpus() > 1) { + online_mask = cpumask_bits(cpu_online_mask); + possible_mask = cpumask_bits(cpu_possible_mask); + } + dev_maps = xmap_dereference(dev->xps_cpus_map); + nr_ids = nr_cpu_ids; + } - dev_maps = xmap_dereference(dev->xps_maps); + if (maps_sz < L1_CACHE_BYTES) + maps_sz = L1_CACHE_BYTES; /* allocate memory for queue storage */ - for_each_cpu_and(cpu, cpu_online_mask, mask) { + for (j = -1; j = netif_attrmask_next_and(j, online_mask, mask, nr_ids), + j < nr_ids;) { if (!new_dev_maps) new_dev_maps = kzalloc(maps_sz, GFP_KERNEL); if (!new_dev_maps) { @@ -2238,73 +2283,81 @@ int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, return -ENOMEM; } - tci = cpu * num_tc + tc; - map = dev_maps ? xmap_dereference(dev_maps->cpu_map[tci]) : + tci = j * num_tc + tc; + map = dev_maps ? xmap_dereference(dev_maps->attr_map[tci]) : NULL; - map = expand_xps_map(map, cpu, index); + map = expand_xps_map(map, j, index, is_rxqs_map); if (!map) goto error; - RCU_INIT_POINTER(new_dev_maps->cpu_map[tci], map); + RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map); } if (!new_dev_maps) goto out_no_new_maps; - for_each_possible_cpu(cpu) { + for (j = -1; j = netif_attrmask_next(j, possible_mask, nr_ids), + j < nr_ids;) { /* copy maps belonging to foreign traffic classes */ - for (i = tc, tci = cpu * num_tc; dev_maps && i--; tci++) { + for (i = tc, tci = j * num_tc; dev_maps && i--; tci++) { /* fill in the new device map from the old device map */ - map = xmap_dereference(dev_maps->cpu_map[tci]); - RCU_INIT_POINTER(new_dev_maps->cpu_map[tci], map); + map = xmap_dereference(dev_maps->attr_map[tci]); + RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map); } /* We need to explicitly update tci as prevous loop * could break out early if dev_maps is NULL. */ - tci = cpu * num_tc + tc; + tci = j * num_tc + tc; - if (cpumask_test_cpu(cpu, mask) && cpu_online(cpu)) { - /* add queue to CPU maps */ + if (netif_attr_test_mask(j, mask, nr_ids) && + netif_attr_test_online(j, online_mask, nr_ids)) { + /* add tx-queue to CPU/rx-queue maps */ int pos = 0; - map = xmap_dereference(new_dev_maps->cpu_map[tci]); + map = xmap_dereference(new_dev_maps->attr_map[tci]); while ((pos < map->len) && (map->queues[pos] != index)) pos++; if (pos == map->len) map->queues[map->len++] = index; #ifdef CONFIG_NUMA - if (numa_node_id == -2) - numa_node_id = cpu_to_node(cpu); - else if (numa_node_id != cpu_to_node(cpu)) - numa_node_id = -1; + if (!is_rxqs_map) { + if (numa_node_id == -2) + numa_node_id = cpu_to_node(j); + else if (numa_node_id != cpu_to_node(j)) + numa_node_id = -1; + } #endif } else if (dev_maps) { /* fill in the new device map from the old device map */ - map = xmap_dereference(dev_maps->cpu_map[tci]); - RCU_INIT_POINTER(new_dev_maps->cpu_map[tci], map); + map = xmap_dereference(dev_maps->attr_map[tci]); + RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map); } /* copy maps belonging to foreign traffic classes */ for (i = num_tc - tc, tci++; dev_maps && --i; tci++) { /* fill in the new device map from the old device map */ - map = xmap_dereference(dev_maps->cpu_map[tci]); - RCU_INIT_POINTER(new_dev_maps->cpu_map[tci], map); + map = xmap_dereference(dev_maps->attr_map[tci]); + RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map); } } - rcu_assign_pointer(dev->xps_maps, new_dev_maps); + if (is_rxqs_map) + rcu_assign_pointer(dev->xps_rxqs_map, new_dev_maps); + else + rcu_assign_pointer(dev->xps_cpus_map, new_dev_maps); /* Cleanup old maps */ if (!dev_maps) goto out_no_old_maps; - for_each_possible_cpu(cpu) { - for (i = num_tc, tci = cpu * num_tc; i--; tci++) { - new_map = xmap_dereference(new_dev_maps->cpu_map[tci]); - map = xmap_dereference(dev_maps->cpu_map[tci]); + for (j = -1; j = netif_attrmask_next(j, possible_mask, nr_ids), + j < nr_ids;) { + for (i = num_tc, tci = j * num_tc; i--; tci++) { + new_map = xmap_dereference(new_dev_maps->attr_map[tci]); + map = xmap_dereference(dev_maps->attr_map[tci]); if (map && map != new_map) kfree_rcu(map, rcu); } @@ -2317,19 +2370,23 @@ out_no_old_maps: active = true; out_no_new_maps: - /* update Tx queue numa node */ - netdev_queue_numa_node_write(netdev_get_tx_queue(dev, index), - (numa_node_id >= 0) ? numa_node_id : - NUMA_NO_NODE); + if (!is_rxqs_map) { + /* update Tx queue numa node */ + netdev_queue_numa_node_write(netdev_get_tx_queue(dev, index), + (numa_node_id >= 0) ? + numa_node_id : NUMA_NO_NODE); + } if (!dev_maps) goto out_no_maps; - /* removes queue from unused CPUs */ - for_each_possible_cpu(cpu) { - for (i = tc, tci = cpu * num_tc; i--; tci++) + /* removes tx-queue from unused CPUs/rx-queues */ + for (j = -1; j = netif_attrmask_next(j, possible_mask, nr_ids), + j < nr_ids;) { + for (i = tc, tci = j * num_tc; i--; tci++) active |= remove_xps_queue(dev_maps, tci, index); - if (!cpumask_test_cpu(cpu, mask) || !cpu_online(cpu)) + if (!netif_attr_test_mask(j, mask, nr_ids) || + !netif_attr_test_online(j, online_mask, nr_ids)) active |= remove_xps_queue(dev_maps, tci, index); for (i = num_tc - tc, tci++; --i; tci++) active |= remove_xps_queue(dev_maps, tci, index); @@ -2337,7 +2394,10 @@ out_no_new_maps: /* free map if not active */ if (!active) { - RCU_INIT_POINTER(dev->xps_maps, NULL); + if (is_rxqs_map) + RCU_INIT_POINTER(dev->xps_rxqs_map, NULL); + else + RCU_INIT_POINTER(dev->xps_cpus_map, NULL); kfree_rcu(dev_maps, rcu); } @@ -2347,11 +2407,12 @@ out_no_maps: return 0; error: /* remove any maps that we added */ - for_each_possible_cpu(cpu) { - for (i = num_tc, tci = cpu * num_tc; i--; tci++) { - new_map = xmap_dereference(new_dev_maps->cpu_map[tci]); + for (j = -1; j = netif_attrmask_next(j, possible_mask, nr_ids), + j < nr_ids;) { + for (i = num_tc, tci = j * num_tc; i--; tci++) { + new_map = xmap_dereference(new_dev_maps->attr_map[tci]); map = dev_maps ? - xmap_dereference(dev_maps->cpu_map[tci]) : + xmap_dereference(dev_maps->attr_map[tci]) : NULL; if (new_map && new_map != map) kfree(new_map); @@ -2363,6 +2424,12 @@ error: kfree(new_dev_maps); return -ENOMEM; } + +int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, + u16 index) +{ + return __netif_set_xps_queue(dev, cpumask_bits(mask), index, false); +} EXPORT_SYMBOL(netif_set_xps_queue); #endif @@ -3384,7 +3451,7 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb) int queue_index = -1; rcu_read_lock(); - dev_maps = rcu_dereference(dev->xps_maps); + dev_maps = rcu_dereference(dev->xps_cpus_map); if (dev_maps) { unsigned int tci = skb->sender_cpu - 1; @@ -3393,7 +3460,7 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb) tci += netdev_get_prio_tc_map(dev, skb->priority); } - map = rcu_dereference(dev_maps->cpu_map[tci]); + map = rcu_dereference(dev_maps->attr_map[tci]); if (map) { if (map->len == 1) queue_index = map->queues[0]; diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index bb7e80f4ced3..b39987c81d53 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -1227,13 +1227,13 @@ static ssize_t xps_cpus_show(struct netdev_queue *queue, return -ENOMEM; rcu_read_lock(); - dev_maps = rcu_dereference(dev->xps_maps); + dev_maps = rcu_dereference(dev->xps_cpus_map); if (dev_maps) { for_each_possible_cpu(cpu) { int i, tci = cpu * num_tc + tc; struct xps_map *map; - map = rcu_dereference(dev_maps->cpu_map[tci]); + map = rcu_dereference(dev_maps->attr_map[tci]); if (!map) continue; -- cgit v1.2.3 From 755c31cd85aea35cf7a5e7253851b52c08eff6e9 Mon Sep 17 00:00:00 2001 From: Amritha Nambiar Date: Fri, 29 Jun 2018 21:26:51 -0700 Subject: net: sock: Change tx_queue_mapping in sock_common to unsigned short Change 'skc_tx_queue_mapping' field in sock_common structure from 'int' to 'unsigned short' type with ~0 indicating unset and other positive queue values being set. This will accommodate adding a new 'unsigned short' field in sock_common in the next patch for rx_queue_mapping. Signed-off-by: Amritha Nambiar Signed-off-by: David S. Miller --- include/net/sock.h | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index b3b75419eafe..37b09c84504b 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -214,7 +214,7 @@ struct sock_common { struct hlist_node skc_node; struct hlist_nulls_node skc_nulls_node; }; - int skc_tx_queue_mapping; + unsigned short skc_tx_queue_mapping; union { int skc_incoming_cpu; u32 skc_rcv_wnd; @@ -1681,17 +1681,25 @@ static inline int sk_receive_skb(struct sock *sk, struct sk_buff *skb, static inline void sk_tx_queue_set(struct sock *sk, int tx_queue) { + /* sk_tx_queue_mapping accept only upto a 16-bit value */ + if (WARN_ON_ONCE((unsigned short)tx_queue >= USHRT_MAX)) + return; sk->sk_tx_queue_mapping = tx_queue; } +#define NO_QUEUE_MAPPING USHRT_MAX + static inline void sk_tx_queue_clear(struct sock *sk) { - sk->sk_tx_queue_mapping = -1; + sk->sk_tx_queue_mapping = NO_QUEUE_MAPPING; } static inline int sk_tx_queue_get(const struct sock *sk) { - return sk ? sk->sk_tx_queue_mapping : -1; + if (sk && sk->sk_tx_queue_mapping != NO_QUEUE_MAPPING) + return sk->sk_tx_queue_mapping; + + return -1; } static inline void sk_set_socket(struct sock *sk, struct socket *sock) -- cgit v1.2.3 From c6345ce7d361dce1b5d02a2181ccb598c27fd7ae Mon Sep 17 00:00:00 2001 From: Amritha Nambiar Date: Fri, 29 Jun 2018 21:26:57 -0700 Subject: net: Record receive queue number for a connection This patch adds a new field to sock_common 'skc_rx_queue_mapping' which holds the receive queue number for the connection. The Rx queue is marked in tcp_finish_connect() to allow a client app to do SO_INCOMING_NAPI_ID after a connect() call to get the right queue association for a socket. Rx queue is also marked in tcp_conn_request() to allow syn-ack to go on the right tx-queue associated with the queue on which syn is received. Signed-off-by: Amritha Nambiar Signed-off-by: Sridhar Samudrala Signed-off-by: David S. Miller --- include/net/busy_poll.h | 1 + include/net/sock.h | 28 ++++++++++++++++++++++++++++ net/core/sock.c | 2 ++ net/ipv4/tcp_input.c | 3 +++ 4 files changed, 34 insertions(+) (limited to 'include') diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h index c5187438af38..9e36fda652b7 100644 --- a/include/net/busy_poll.h +++ b/include/net/busy_poll.h @@ -151,6 +151,7 @@ static inline void sk_mark_napi_id(struct sock *sk, const struct sk_buff *skb) #ifdef CONFIG_NET_RX_BUSY_POLL sk->sk_napi_id = skb->napi_id; #endif + sk_rx_queue_set(sk, skb); } /* variant used for unconnected sockets */ diff --git a/include/net/sock.h b/include/net/sock.h index 37b09c84504b..2b097cc89727 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -139,6 +139,7 @@ typedef __u64 __bitwise __addrpair; * @skc_node: main hash linkage for various protocol lookup tables * @skc_nulls_node: main hash linkage for TCP/UDP/UDP-Lite protocol * @skc_tx_queue_mapping: tx queue number for this connection + * @skc_rx_queue_mapping: rx queue number for this connection * @skc_flags: place holder for sk_flags * %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE, * %SO_OOBINLINE settings, %SO_TIMESTAMPING settings @@ -215,6 +216,9 @@ struct sock_common { struct hlist_nulls_node skc_nulls_node; }; unsigned short skc_tx_queue_mapping; +#ifdef CONFIG_XPS + unsigned short skc_rx_queue_mapping; +#endif union { int skc_incoming_cpu; u32 skc_rcv_wnd; @@ -326,6 +330,9 @@ struct sock { #define sk_nulls_node __sk_common.skc_nulls_node #define sk_refcnt __sk_common.skc_refcnt #define sk_tx_queue_mapping __sk_common.skc_tx_queue_mapping +#ifdef CONFIG_XPS +#define sk_rx_queue_mapping __sk_common.skc_rx_queue_mapping +#endif #define sk_dontcopy_begin __sk_common.skc_dontcopy_begin #define sk_dontcopy_end __sk_common.skc_dontcopy_end @@ -1702,6 +1709,27 @@ static inline int sk_tx_queue_get(const struct sock *sk) return -1; } +static inline void sk_rx_queue_set(struct sock *sk, const struct sk_buff *skb) +{ +#ifdef CONFIG_XPS + if (skb_rx_queue_recorded(skb)) { + u16 rx_queue = skb_get_rx_queue(skb); + + if (WARN_ON_ONCE(rx_queue == NO_QUEUE_MAPPING)) + return; + + sk->sk_rx_queue_mapping = rx_queue; + } +#endif +} + +static inline void sk_rx_queue_clear(struct sock *sk) +{ +#ifdef CONFIG_XPS + sk->sk_rx_queue_mapping = NO_QUEUE_MAPPING; +#endif +} + static inline void sk_set_socket(struct sock *sk, struct socket *sock) { sk_tx_queue_clear(sk); diff --git a/net/core/sock.c b/net/core/sock.c index bcc41829a16d..dac6d785186b 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2818,6 +2818,8 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_pacing_rate = ~0U; sk->sk_pacing_shift = 10; sk->sk_incoming_cpu = -1; + + sk_rx_queue_clear(sk); /* * Before updating sk_refcnt, we must commit prior changes to memory * (Documentation/RCU/rculist_nulls.txt for details) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index eecd359595fc..a4731995e899 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -78,6 +78,7 @@ #include #include #include +#include int sysctl_tcp_max_orphans __read_mostly = NR_FILE; @@ -5592,6 +5593,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb) if (skb) { icsk->icsk_af_ops->sk_rx_dst_set(sk, skb); security_inet_conn_established(sk, skb); + sk_mark_napi_id(sk, skb); } tcp_init_transfer(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB); @@ -6420,6 +6422,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, tcp_rsk(req)->snt_isn = isn; tcp_rsk(req)->txhash = net_tx_rndhash(); tcp_openreq_init_rwin(req, sk, dst); + sk_rx_queue_set(req_to_sk(req), skb); if (!want_cookie) { tcp_reqsk_record_syn(sk, req, skb); fastopen_sk = tcp_try_fastopen(sk, skb, req, &foc, dst); -- cgit v1.2.3 From fc9bab24e9c654f62f3d411fc0b041be9e487e9d Mon Sep 17 00:00:00 2001 From: Amritha Nambiar Date: Fri, 29 Jun 2018 21:27:02 -0700 Subject: net: Enable Tx queue selection based on Rx queues This patch adds support to pick Tx queue based on the Rx queue(s) map configuration set by the admin through the sysfs attribute for each Tx queue. If the user configuration for receive queue(s) map does not apply, then the Tx queue selection falls back to CPU(s) map based selection and finally to hashing. Signed-off-by: Amritha Nambiar Signed-off-by: David S. Miller --- include/net/sock.h | 10 +++++++++ net/core/dev.c | 62 +++++++++++++++++++++++++++++++++++++++--------------- 2 files changed, 55 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index 2b097cc89727..2ed99bfa4595 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1730,6 +1730,16 @@ static inline void sk_rx_queue_clear(struct sock *sk) #endif } +#ifdef CONFIG_XPS +static inline int sk_rx_queue_get(const struct sock *sk) +{ + if (sk && sk->sk_rx_queue_mapping != NO_QUEUE_MAPPING) + return sk->sk_rx_queue_mapping; + + return -1; +} +#endif + static inline void sk_set_socket(struct sock *sk, struct socket *sock) { sk_tx_queue_clear(sk); diff --git a/net/core/dev.c b/net/core/dev.c index 43b5575e40c5..08d58e0debe5 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3459,35 +3459,63 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) } #endif /* CONFIG_NET_EGRESS */ -static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb) +#ifdef CONFIG_XPS +static int __get_xps_queue_idx(struct net_device *dev, struct sk_buff *skb, + struct xps_dev_maps *dev_maps, unsigned int tci) +{ + struct xps_map *map; + int queue_index = -1; + + if (dev->num_tc) { + tci *= dev->num_tc; + tci += netdev_get_prio_tc_map(dev, skb->priority); + } + + map = rcu_dereference(dev_maps->attr_map[tci]); + if (map) { + if (map->len == 1) + queue_index = map->queues[0]; + else + queue_index = map->queues[reciprocal_scale( + skb_get_hash(skb), map->len)]; + if (unlikely(queue_index >= dev->real_num_tx_queues)) + queue_index = -1; + } + return queue_index; +} +#endif + +static int get_xps_queue(struct net_device *dev, struct sk_buff *skb) { #ifdef CONFIG_XPS struct xps_dev_maps *dev_maps; - struct xps_map *map; + struct sock *sk = skb->sk; int queue_index = -1; if (!static_key_false(&xps_needed)) return -1; rcu_read_lock(); - dev_maps = rcu_dereference(dev->xps_cpus_map); + if (!static_key_false(&xps_rxqs_needed)) + goto get_cpus_map; + + dev_maps = rcu_dereference(dev->xps_rxqs_map); if (dev_maps) { - unsigned int tci = skb->sender_cpu - 1; + int tci = sk_rx_queue_get(sk); - if (dev->num_tc) { - tci *= dev->num_tc; - tci += netdev_get_prio_tc_map(dev, skb->priority); - } + if (tci >= 0 && tci < dev->num_rx_queues) + queue_index = __get_xps_queue_idx(dev, skb, dev_maps, + tci); + } - map = rcu_dereference(dev_maps->attr_map[tci]); - if (map) { - if (map->len == 1) - queue_index = map->queues[0]; - else - queue_index = map->queues[reciprocal_scale(skb_get_hash(skb), - map->len)]; - if (unlikely(queue_index >= dev->real_num_tx_queues)) - queue_index = -1; +get_cpus_map: + if (queue_index < 0) { + dev_maps = rcu_dereference(dev->xps_cpus_map); + if (dev_maps) { + unsigned int tci = skb->sender_cpu - 1; + + queue_index = __get_xps_queue_idx(dev, skb, dev_maps, + tci); } } rcu_read_unlock(); -- cgit v1.2.3 From f308d7353d1f5c3ddedc784a367edc72fc51bbaa Mon Sep 17 00:00:00 2001 From: Stefan Agner Date: Sun, 24 Jun 2018 23:27:22 +0200 Subject: mtd: rawnand: add Reed-Solomon error correction algorithm Add Reed-Solomon (RS) to the enumeration of ECC algorithms. Signed-off-by: Stefan Agner Reviewed-by: Boris Brezillon Acked-by: Rob Herring Signed-off-by: Miquel Raynal --- Documentation/devicetree/bindings/mtd/nand.txt | 2 +- drivers/mtd/nand/raw/nand_base.c | 1 + include/linux/mtd/rawnand.h | 1 + 3 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/Documentation/devicetree/bindings/mtd/nand.txt b/Documentation/devicetree/bindings/mtd/nand.txt index 8bb11d809429..eaef8c657aa5 100644 --- a/Documentation/devicetree/bindings/mtd/nand.txt +++ b/Documentation/devicetree/bindings/mtd/nand.txt @@ -25,7 +25,7 @@ Optional NAND chip properties: Deprecated values: "soft_bch": use "soft" and nand-ecc-algo instead - nand-ecc-algo: string, algorithm of NAND ECC. - Supported values are: "hamming", "bch". + Valid values are: "hamming", "bch", "rs". - nand-bus-width : 8 or 16 bus width if not present 8 - nand-on-flash-bbt: boolean to enable on flash bbt option if not present false diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index b01d15ec4c56..d0af5347f89d 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -5777,6 +5777,7 @@ static int of_get_nand_ecc_mode(struct device_node *np) static const char * const nand_ecc_algos[] = { [NAND_ECC_HAMMING] = "hamming", [NAND_ECC_BCH] = "bch", + [NAND_ECC_RS] = "rs", }; static int of_get_nand_ecc_algo(struct device_node *np) diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 3e8ec3b8a39c..2d9cb7acbc3d 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -121,6 +121,7 @@ enum nand_ecc_algo { NAND_ECC_UNKNOWN, NAND_ECC_HAMMING, NAND_ECC_BCH, + NAND_ECC_RS, }; /* -- cgit v1.2.3 From f922bd798bb94e0adcce26ddd811245443173268 Mon Sep 17 00:00:00 2001 From: Stefan Agner Date: Sun, 24 Jun 2018 23:27:23 +0200 Subject: mtd: rawnand: add an option to specify NAND chip as a boot device Allow to define a NAND chip as a boot device. This can be helpful for the selection of the ECC algorithm and strength in case the boot ROM supports only a subset of controller provided options. Signed-off-by: Stefan Agner Reviewed-by: Boris Brezillon Acked-by: Rob Herring Signed-off-by: Miquel Raynal --- Documentation/devicetree/bindings/mtd/nand.txt | 4 ++++ drivers/mtd/nand/raw/nand_base.c | 3 +++ include/linux/mtd/rawnand.h | 6 ++++++ 3 files changed, 13 insertions(+) (limited to 'include') diff --git a/Documentation/devicetree/bindings/mtd/nand.txt b/Documentation/devicetree/bindings/mtd/nand.txt index eaef8c657aa5..e949c778e983 100644 --- a/Documentation/devicetree/bindings/mtd/nand.txt +++ b/Documentation/devicetree/bindings/mtd/nand.txt @@ -43,6 +43,10 @@ Optional NAND chip properties: This is particularly useful when only the in-band area is used by the upper layers, and you want to make your NAND as reliable as possible. +- nand-is-boot-medium: Whether the NAND chip is a boot medium. Drivers might use + this information to select ECC algorithms supported by + the boot ROM or similar restrictions. + - nand-rb: shall contain the native Ready/Busy ids. The ECC strength and ECC step size properties define the correction capability diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index d0af5347f89d..1c633f80c3e1 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -5859,6 +5859,9 @@ static int nand_dt_init(struct nand_chip *chip) if (of_get_nand_bus_width(dn) == 16) chip->options |= NAND_BUSWIDTH_16; + if (of_property_read_bool(dn, "nand-is-boot-medium")) + chip->options |= NAND_IS_BOOT_MEDIUM; + if (of_get_nand_on_flash_bbt(dn)) chip->bbt_options |= NAND_BBT_USE_FLASH; diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 2d9cb7acbc3d..80aeeca03f36 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -219,6 +219,12 @@ enum nand_ecc_algo { */ #define NAND_WAIT_TCCS 0x00200000 +/* + * Whether the NAND chip is a boot medium. Drivers might use this information + * to select ECC algorithms supported by the boot ROM or similar restrictions. + */ +#define NAND_IS_BOOT_MEDIUM 0x00400000 + /* Options set by nand scan */ /* Nand scan has allocated controller struct */ #define NAND_CONTROLLER_ALLOC 0x80000000 -- cgit v1.2.3 From 00ce4e039ad5bded462931606c3063ff691964b7 Mon Sep 17 00:00:00 2001 From: Chris Packham Date: Mon, 25 Jun 2018 10:44:44 +1200 Subject: mtd: rawnand: add manufacturer fixup for ONFI parameter page This is called after the ONFI parameter page checksum is verified and allows us to override the contents of the parameter page. Suggested-by: Boris Brezillon Signed-off-by: Chris Packham Reviewed-by: Boris Brezillon Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/nand_base.c | 4 ++++ include/linux/mtd/rawnand.h | 4 ++++ 2 files changed, 8 insertions(+) (limited to 'include') diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index 1c633f80c3e1..f362c09a71d7 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -5168,6 +5168,10 @@ static int nand_flash_detect_onfi(struct nand_chip *chip) } } + if (chip->manufacturer.desc && chip->manufacturer.desc->ops && + chip->manufacturer.desc->ops->fixup_onfi_param_page) + chip->manufacturer.desc->ops->fixup_onfi_param_page(chip, p); + /* Check version */ val = le16_to_cpu(p->revision); if (val & (1 << 5)) diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 80aeeca03f36..dc4538b58b84 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -785,11 +785,15 @@ nand_get_sdr_timings(const struct nand_data_interface *conf) * implementation) if any. * @cleanup: the ->init() function may have allocated resources, ->cleanup() * is here to let vendor specific code release those resources. + * @fixup_onfi_param_page: apply vendor specific fixups to the ONFI parameter + * page. This is called after the checksum is verified. */ struct nand_manufacturer_ops { void (*detect)(struct nand_chip *chip); int (*init)(struct nand_chip *chip); void (*cleanup)(struct nand_chip *chip); + void (*fixup_onfi_param_page)(struct nand_chip *chip, + struct nand_onfi_params *p); }; /** -- cgit v1.2.3 From 872b71ff084ab125c68073d9e69acfd7095f2015 Mon Sep 17 00:00:00 2001 From: Chris Packham Date: Mon, 25 Jun 2018 10:44:45 +1200 Subject: mtd: rawnand: add defines for ONFI version bits Add defines for the ONFI version bits and use them in nand_flash_detect_onfi(). Signed-off-by: Chris Packham Reviewed-by: Boris Brezillon Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/nand_base.c | 10 +++++----- include/linux/mtd/rawnand.h | 11 +++++++++++ 2 files changed, 16 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index f362c09a71d7..dbf6e80e9ab5 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -5174,15 +5174,15 @@ static int nand_flash_detect_onfi(struct nand_chip *chip) /* Check version */ val = le16_to_cpu(p->revision); - if (val & (1 << 5)) + if (val & ONFI_VERSION_2_3) chip->parameters.onfi.version = 23; - else if (val & (1 << 4)) + else if (val & ONFI_VERSION_2_2) chip->parameters.onfi.version = 22; - else if (val & (1 << 3)) + else if (val & ONFI_VERSION_2_1) chip->parameters.onfi.version = 21; - else if (val & (1 << 2)) + else if (val & ONFI_VERSION_2_0) chip->parameters.onfi.version = 20; - else if (val & (1 << 1)) + else if (val & ONFI_VERSION_1_0) chip->parameters.onfi.version = 10; if (!chip->parameters.onfi.version) { diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index dc4538b58b84..fbac4741da52 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -237,6 +237,17 @@ enum nand_ecc_algo { /* Keep gcc happy */ struct nand_chip; +/* ONFI version bits */ +#define ONFI_VERSION_1_0 BIT(1) +#define ONFI_VERSION_2_0 BIT(2) +#define ONFI_VERSION_2_1 BIT(3) +#define ONFI_VERSION_2_2 BIT(4) +#define ONFI_VERSION_2_3 BIT(5) +#define ONFI_VERSION_3_0 BIT(6) +#define ONFI_VERSION_3_1 BIT(7) +#define ONFI_VERSION_3_2 BIT(8) +#define ONFI_VERSION_4_0 BIT(9) + /* ONFI features */ #define ONFI_FEATURE_16_BIT_BUS (1 << 0) #define ONFI_FEATURE_EXT_PARAM_PAGE (1 << 7) -- cgit v1.2.3 From 1b48b7202c43e41c9f05d39901567dbcad5dc307 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Thu, 3 May 2018 16:25:49 +0200 Subject: dma-fence: remove fill_driver_data callback MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Noticed while I was typing docs. Entirely unused. v2: Remove reference in @timeline_value_str too. While at it clarify why timeline_value_str has a fence parameter - we don't have an explicit timeline structure unfortunately. Cc: Eric Anholt Reviewed-by: Eric Anholt Reviewed-by: Christian König (v1) Cc: Christian König (v1) Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20180503142603.28513-2-daniel.vetter@ffwll.ch --- include/linux/dma-fence.h | 16 +++------------- 1 file changed, 3 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index eb9b05aa5aea..111aefe1c956 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -217,17 +217,6 @@ struct dma_fence_ops { */ void (*release)(struct dma_fence *fence); - /** - * @fill_driver_data: - * - * Callback to fill in free-form debug info. - * - * Returns amount of bytes filled, or negative error on failure. - * - * This callback is optional. - */ - int (*fill_driver_data)(struct dma_fence *fence, void *data, int size); - /** * @fence_value_str: * @@ -242,8 +231,9 @@ struct dma_fence_ops { * @timeline_value_str: * * Fills in the current value of the timeline as a string, like the - * sequence number. This should match what @fill_driver_data prints for - * the most recently signalled fence (assuming no delayed signalling). + * sequence number. Note that the specific fence passed to this function + * should not matter, drivers should only use it to look up the + * corresponding timeline structures. */ void (*timeline_value_str)(struct dma_fence *fence, char *str, int size); -- cgit v1.2.3 From c701317a3eb8c012364a8d468f20eabf6df1ad77 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Fri, 4 May 2018 16:10:34 +0200 Subject: dma-fence: Make ->enable_signaling optional MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Many drivers have a trivial implementation for ->enable_signaling. Let's make it optional by assuming that signalling is already available when the callback isn't present. v2: Don't do the trick to set the ENABLE_SIGNAL_BIT unconditionally, it results in an expensive spinlock take for everyone. Instead just check if the callback is present. Suggested by Maarten. Also move misplaced kerneldoc hunk to the right patch. Cc: Maarten Lankhorst Reviewed-by: Christian König (v1) Reviewed-by: Maarten Lankhorst Signed-off-by: Daniel Vetter Cc: Sumit Semwal Cc: Gustavo Padovan Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Link: https://patchwork.freedesktop.org/patch/msgid/20180504141034.27727-1-daniel.vetter@ffwll.ch --- drivers/dma-buf/dma-fence.c | 9 +++++---- include/linux/dma-fence.h | 3 ++- 2 files changed, 7 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c index 4edb9fd3cf47..dd01a1720be9 100644 --- a/drivers/dma-buf/dma-fence.c +++ b/drivers/dma-buf/dma-fence.c @@ -200,7 +200,8 @@ void dma_fence_enable_sw_signaling(struct dma_fence *fence) if (!test_and_set_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &fence->flags) && - !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) { + !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags) && + fence->ops->enable_signaling) { trace_dma_fence_enable_signal(fence); spin_lock_irqsave(fence->lock, flags); @@ -260,7 +261,7 @@ int dma_fence_add_callback(struct dma_fence *fence, struct dma_fence_cb *cb, if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) ret = -ENOENT; - else if (!was_set) { + else if (!was_set && fence->ops->enable_signaling) { trace_dma_fence_enable_signal(fence); if (!fence->ops->enable_signaling(fence)) { @@ -388,7 +389,7 @@ dma_fence_default_wait(struct dma_fence *fence, bool intr, signed long timeout) if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) goto out; - if (!was_set) { + if (!was_set && fence->ops->enable_signaling) { trace_dma_fence_enable_signal(fence); if (!fence->ops->enable_signaling(fence)) { @@ -560,7 +561,7 @@ dma_fence_init(struct dma_fence *fence, const struct dma_fence_ops *ops, spinlock_t *lock, u64 context, unsigned seqno) { BUG_ON(!lock); - BUG_ON(!ops || !ops->wait || !ops->enable_signaling || + BUG_ON(!ops || !ops->wait || !ops->get_driver_name || !ops->get_timeline_name); kref_init(&fence->refcount); diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index 111aefe1c956..c053d19e1e24 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -166,7 +166,8 @@ struct dma_fence_ops { * released when the fence is signalled (through e.g. the interrupt * handler). * - * This callback is mandatory. + * This callback is optional. If this callback is not present, then the + * driver must always have signaling enabled. */ bool (*enable_signaling)(struct dma_fence *fence); -- cgit v1.2.3 From 78c9c4dfbf8c04883941445a195276bb4bb92c76 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 26 Jun 2018 15:21:32 +0200 Subject: posix-timers: Sanitize overrun handling The posix timer overrun handling is broken because the forwarding functions can return a huge number of overruns which does not fit in an int. As a consequence timer_getoverrun(2) and siginfo::si_overrun can turn into random number generators. The k_clock::timer_forward() callbacks return a 64 bit value now. Make k_itimer::ti_overrun[_last] 64bit as well, so the kernel internal accounting is correct. 3Remove the temporary (int) casts. Add a helper function which clamps the overrun value returned to user space via timer_getoverrun(2) or siginfo::si_overrun limited to a positive value between 0 and INT_MAX. INT_MAX is an indicator for user space that the overrun value has been clamped. Reported-by: Team OWL337 Signed-off-by: Thomas Gleixner Acked-by: John Stultz Cc: Peter Zijlstra Cc: Michael Kerrisk Link: https://lkml.kernel.org/r/20180626132705.018623573@linutronix.de --- include/linux/posix-timers.h | 4 ++-- kernel/time/posix-cpu-timers.c | 2 +- kernel/time/posix-timers.c | 31 ++++++++++++++++++++----------- 3 files changed, 23 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index c85704fcdbd2..ee7e987ea1b4 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -95,8 +95,8 @@ struct k_itimer { clockid_t it_clock; timer_t it_id; int it_active; - int it_overrun; - int it_overrun_last; + s64 it_overrun; + s64 it_overrun_last; int it_requeue_pending; int it_sigev_notify; ktime_t it_interval; diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 5a6251ac6f7a..562cc3891b57 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -85,7 +85,7 @@ static void bump_cpu_timer(struct k_itimer *timer, u64 now) continue; timer->it.cpu.expires += incr; - timer->it_overrun += 1 << i; + timer->it_overrun += 1LL << i; delta -= incr; } } diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index db1d65963a57..3ac7295306dc 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -283,6 +283,17 @@ static __init int init_posix_timers(void) } __initcall(init_posix_timers); +/* + * The siginfo si_overrun field and the return value of timer_getoverrun(2) + * are of type int. Clamp the overrun value to INT_MAX + */ +static inline int timer_overrun_to_int(struct k_itimer *timr, int baseval) +{ + s64 sum = timr->it_overrun_last + (s64)baseval; + + return sum > (s64)INT_MAX ? INT_MAX : (int)sum; +} + static void common_hrtimer_rearm(struct k_itimer *timr) { struct hrtimer *timer = &timr->it.real.timer; @@ -290,9 +301,8 @@ static void common_hrtimer_rearm(struct k_itimer *timr) if (!timr->it_interval) return; - timr->it_overrun += (unsigned int) hrtimer_forward(timer, - timer->base->get_time(), - timr->it_interval); + timr->it_overrun += hrtimer_forward(timer, timer->base->get_time(), + timr->it_interval); hrtimer_restart(timer); } @@ -321,10 +331,10 @@ void posixtimer_rearm(struct siginfo *info) timr->it_active = 1; timr->it_overrun_last = timr->it_overrun; - timr->it_overrun = -1; + timr->it_overrun = -1LL; ++timr->it_requeue_pending; - info->si_overrun += timr->it_overrun_last; + info->si_overrun = timer_overrun_to_int(timr, info->si_overrun); } unlock_timer(timr, flags); @@ -418,9 +428,8 @@ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer) now = ktime_add(now, kj); } #endif - timr->it_overrun += (unsigned int) - hrtimer_forward(timer, now, - timr->it_interval); + timr->it_overrun += hrtimer_forward(timer, now, + timr->it_interval); ret = HRTIMER_RESTART; ++timr->it_requeue_pending; timr->it_active = 1; @@ -524,7 +533,7 @@ static int do_timer_create(clockid_t which_clock, struct sigevent *event, new_timer->it_id = (timer_t) new_timer_id; new_timer->it_clock = which_clock; new_timer->kclock = kc; - new_timer->it_overrun = -1; + new_timer->it_overrun = -1LL; if (event) { rcu_read_lock(); @@ -702,7 +711,7 @@ void common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting) * expiry time forward by intervals, so expiry is > now. */ if (iv && (timr->it_requeue_pending & REQUEUE_PENDING || sig_none)) - timr->it_overrun += (int)kc->timer_forward(timr, now); + timr->it_overrun += kc->timer_forward(timr, now); remaining = kc->timer_remaining(timr, now); /* Return 0 only, when the timer is expired and not pending */ @@ -791,7 +800,7 @@ SYSCALL_DEFINE1(timer_getoverrun, timer_t, timer_id) if (!timr) return -EINVAL; - overrun = timr->it_overrun_last; + overrun = timer_overrun_to_int(timr, 0); unlock_timer(timr, flags); return overrun; -- cgit v1.2.3 From d573454d9b4f00061da314460908e19476d2ff6d Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 2 Jul 2018 06:30:28 +0000 Subject: ASoC: simple-card: convert to SPDX identifiers Signed-off-by: Kuninori Morimoto Signed-off-by: Mark Brown --- include/sound/simple_card.h | 7 ++----- sound/soc/generic/simple-card.c | 17 +++++++---------- 2 files changed, 9 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/sound/simple_card.h b/include/sound/simple_card.h index a6a2e1547092..d264e5463f22 100644 --- a/include/sound/simple_card.h +++ b/include/sound/simple_card.h @@ -1,12 +1,9 @@ -/* +/* SPDX-License-Identifier: GPL-2.0 + * * ASoC simple sound card support * * Copyright (C) 2012 Renesas Solutions Corp. * Kuninori Morimoto - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef __SIMPLE_CARD_H diff --git a/sound/soc/generic/simple-card.c b/sound/soc/generic/simple-card.c index c5b6e04cd926..64bf3560c1d1 100644 --- a/sound/soc/generic/simple-card.c +++ b/sound/soc/generic/simple-card.c @@ -1,13 +1,10 @@ -/* - * ASoC simple sound card support - * - * Copyright (C) 2012 Renesas Solutions Corp. - * Kuninori Morimoto - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ +// SPDX-License-Identifier: GPL-2.0 +// +// ASoC simple sound card support +// +// Copyright (C) 2012 Renesas Solutions Corp. +// Kuninori Morimoto + #include #include #include -- cgit v1.2.3 From d613a7f45ebb2f113444630fcbbb8a074c741998 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 2 Jul 2018 06:30:44 +0000 Subject: ASoC: simple-card-utils: convert to SPDX identifiers Signed-off-by: Kuninori Morimoto Signed-off-by: Mark Brown --- include/sound/simple_card_utils.h | 8 +++----- sound/soc/generic/simple-card-utils.c | 15 ++++++--------- 2 files changed, 9 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/sound/simple_card_utils.h b/include/sound/simple_card_utils.h index f82acef3b992..8bc5e2d8b13c 100644 --- a/include/sound/simple_card_utils.h +++ b/include/sound/simple_card_utils.h @@ -1,12 +1,10 @@ -/* +/* SPDX-License-Identifier: GPL-2.0 + * * simple_card_utils.h * * Copyright (c) 2016 Kuninori Morimoto - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ + #ifndef __SIMPLE_CARD_UTILS_H #define __SIMPLE_CARD_UTILS_H diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c index 4398c9580929..d3f3f0fec74c 100644 --- a/sound/soc/generic/simple-card-utils.c +++ b/sound/soc/generic/simple-card-utils.c @@ -1,12 +1,9 @@ -/* - * simple-card-utils.c - * - * Copyright (c) 2016 Kuninori Morimoto - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ +// SPDX-License-Identifier: GPL-2.0 +// +// simple-card-utils.c +// +// Copyright (c) 2016 Kuninori Morimoto + #include #include #include -- cgit v1.2.3 From e2cfd2c9673f4e9d08971fed53fe1f41d8270ef0 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 2 Jul 2018 06:22:15 +0000 Subject: ASoC: soc-dai.h: convert to SPDX identifiers Signed-off-by: Kuninori Morimoto Signed-off-by: Mark Brown --- include/sound/soc-dai.h | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/sound/soc-dai.h b/include/sound/soc-dai.h index e6f8c40ed43c..a14bc0608ae9 100644 --- a/include/sound/soc-dai.h +++ b/include/sound/soc-dai.h @@ -1,12 +1,9 @@ -/* +/* SPDX-License-Identifier: GPL-2.0 + * * linux/sound/soc-dai.h -- ALSA SoC Layer * * Copyright: 2005-2008 Wolfson Microelectronics. PLC. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * * Digital Audio Interface (DAI) API. */ -- cgit v1.2.3 From b53c34b4b73eb65e6480ada6ec8ddbcc2d4e9817 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 2 Jul 2018 06:22:58 +0000 Subject: ASoC: soc-dpcm.h: convert to SPDX identifiers Signed-off-by: Kuninori Morimoto Signed-off-by: Mark Brown --- include/sound/soc-dpcm.h | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/sound/soc-dpcm.h b/include/sound/soc-dpcm.h index 806059052bfc..9bb92f187af8 100644 --- a/include/sound/soc-dpcm.h +++ b/include/sound/soc-dpcm.h @@ -1,11 +1,8 @@ -/* +/* SPDX-License-Identifier: GPL-2.0 + * * linux/sound/soc-dpcm.h -- ALSA SoC Dynamic PCM Support * * Author: Liam Girdwood - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef __LINUX_SND_SOC_DPCM_H -- cgit v1.2.3 From 7730bb13c7472620b585783f248b2dccd09d1819 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 2 Jul 2018 06:24:04 +0000 Subject: ASoC: soc-acpi: convert to SPDX identifiers Signed-off-by: Kuninori Morimoto Signed-off-by: Mark Brown --- include/sound/soc-acpi-intel-match.h | 14 ++------------ include/sound/soc-acpi.h | 13 ++----------- sound/soc/soc-acpi.c | 20 +++++--------------- 3 files changed, 9 insertions(+), 38 deletions(-) (limited to 'include') diff --git a/include/sound/soc-acpi-intel-match.h b/include/sound/soc-acpi-intel-match.h index 917ddd0f2762..bb1d24b703fb 100644 --- a/include/sound/soc-acpi-intel-match.h +++ b/include/sound/soc-acpi-intel-match.h @@ -1,16 +1,6 @@ - -/* - * Copyright (C) 2017, Intel Corporation. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License version - * 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. +/* SPDX-License-Identifier: GPL-2.0 * + * Copyright (C) 2017, Intel Corporation. All rights reserved. */ #ifndef __LINUX_SND_SOC_ACPI_INTEL_MATCH_H diff --git a/include/sound/soc-acpi.h b/include/sound/soc-acpi.h index 082224275f52..e45b2330d16a 100644 --- a/include/sound/soc-acpi.h +++ b/include/sound/soc-acpi.h @@ -1,15 +1,6 @@ -/* - * Copyright (C) 2013-15, Intel Corporation. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License version - * 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. +/* SPDX-License-Identifier: GPL-2.0 * + * Copyright (C) 2013-15, Intel Corporation. All rights reserved. */ #ifndef __LINUX_SND_SOC_ACPI_H diff --git a/sound/soc/soc-acpi.c b/sound/soc/soc-acpi.c index 3d7e1ff79139..b8e72b52db30 100644 --- a/sound/soc/soc-acpi.c +++ b/sound/soc/soc-acpi.c @@ -1,18 +1,8 @@ -/* - * soc-apci.c - support for ACPI enumeration. - * - * Copyright (c) 2013-15, Intel Corporation. - * - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - */ +// SPDX-License-Identifier: GPL-2.0 +// +// soc-apci.c - support for ACPI enumeration. +// +// Copyright (c) 2013-15, Intel Corporation. #include -- cgit v1.2.3 From 873486ed4af3e11bfc20832dff7b124ba652bf77 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 2 Jul 2018 06:24:18 +0000 Subject: ASoC: soc-core: convert to SPDX identifiers Signed-off-by: Kuninori Morimoto Signed-off-by: Mark Brown --- include/sound/soc.h | 11 ++++------- sound/soc/soc-core.c | 41 ++++++++++++++++++----------------------- 2 files changed, 22 insertions(+), 30 deletions(-) (limited to 'include') diff --git a/include/sound/soc.h b/include/sound/soc.h index f7579f82cc00..16f0bf10cc42 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -1,13 +1,10 @@ -/* +/* SPDX-License-Identifier: GPL-2.0 + * * linux/sound/soc.h -- ALSA SoC Layer * - * Author: Liam Girdwood - * Created: Aug 11th 2005 + * Author: Liam Girdwood + * Created: Aug 11th 2005 * Copyright: Wolfson Microelectronics. PLC. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef __LINUX_SND_SOC_H diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index 4663de3cf495..68b08781c832 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -1,26 +1,21 @@ -/* - * soc-core.c -- ALSA SoC Audio Layer - * - * Copyright 2005 Wolfson Microelectronics PLC. - * Copyright 2005 Openedhand Ltd. - * Copyright (C) 2010 Slimlogic Ltd. - * Copyright (C) 2010 Texas Instruments Inc. - * - * Author: Liam Girdwood - * with code, comments and ideas from :- - * Richard Purdie - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * - * TODO: - * o Add hw rules to enforce rates, etc. - * o More testing with other codecs/machines. - * o Add more codecs and platforms to ensure good API coverage. - * o Support TDM on PCM and I2S - */ +// SPDX-License-Identifier: GPL-2.0+ +// +// soc-core.c -- ALSA SoC Audio Layer +// +// Copyright 2005 Wolfson Microelectronics PLC. +// Copyright 2005 Openedhand Ltd. +// Copyright (C) 2010 Slimlogic Ltd. +// Copyright (C) 2010 Texas Instruments Inc. +// +// Author: Liam Girdwood +// with code, comments and ideas from :- +// Richard Purdie +// +// TODO: +// o Add hw rules to enforce rates, etc. +// o More testing with other codecs/machines. +// o Add more codecs and platforms to ensure good API coverage. +// o Support TDM on PCM and I2S #include #include -- cgit v1.2.3 From c01f3af4d32071915119ffcb933e75d7c165378e Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 2 Jul 2018 06:24:31 +0000 Subject: ASoC: soc-dapm: convert to SPDX identifiers Signed-off-by: Kuninori Morimoto Signed-off-by: Mark Brown --- include/sound/soc-dapm.h | 11 ++++------- sound/soc/soc-dapm.c | 42 ++++++++++++++++++------------------------ 2 files changed, 22 insertions(+), 31 deletions(-) (limited to 'include') diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h index a6ce2de4e20a..af9ef16cc34d 100644 --- a/include/sound/soc-dapm.h +++ b/include/sound/soc-dapm.h @@ -1,13 +1,10 @@ -/* +/* SPDX-License-Identifier: GPL-2.0 + * * linux/sound/soc-dapm.h -- ALSA SoC Dynamic Audio Power Management * - * Author: Liam Girdwood - * Created: Aug 11th 2005 + * Author: Liam Girdwood + * Created: Aug 11th 2005 * Copyright: Wolfson Microelectronics. PLC. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef __LINUX_SND_SOC_DAPM_H diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index a099c3e45504..0602b2888d52 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -1,27 +1,21 @@ -/* - * soc-dapm.c -- ALSA SoC Dynamic Audio Power Management - * - * Copyright 2005 Wolfson Microelectronics PLC. - * Author: Liam Girdwood - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * - * Features: - * o Changes power status of internal codec blocks depending on the - * dynamic configuration of codec internal audio paths and active - * DACs/ADCs. - * o Platform power domain - can support external components i.e. amps and - * mic/headphone insertion events. - * o Automatic Mic Bias support - * o Jack insertion power event initiation - e.g. hp insertion will enable - * sinks, dacs, etc - * o Delayed power down of audio subsystem to reduce pops between a quick - * device reopen. - * - */ +// SPDX-License-Identifier: GPL-2.0+ +// +// soc-dapm.c -- ALSA SoC Dynamic Audio Power Management +// +// Copyright 2005 Wolfson Microelectronics PLC. +// Author: Liam Girdwood +// +// Features: +// o Changes power status of internal codec blocks depending on the +// dynamic configuration of codec internal audio paths and active +// DACs/ADCs. +// o Platform power domain - can support external components i.e. amps and +// mic/headphone insertion events. +// o Automatic Mic Bias support +// o Jack insertion power event initiation - e.g. hp insertion will enable +// sinks, dacs, etc +// o Delayed power down of audio subsystem to reduce pops between a quick +// device reopen. #include #include -- cgit v1.2.3 From f2b6a1b25fecc48a46c8a41636101af8a41c88a8 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 2 Jul 2018 06:24:45 +0000 Subject: ASoC: soc-topology: convert to SPDX identifiers Signed-off-by: Kuninori Morimoto Signed-off-by: Mark Brown --- include/sound/soc-topology.h | 7 ++----- sound/soc/soc-topology.c | 47 ++++++++++++++++++++------------------------ 2 files changed, 23 insertions(+), 31 deletions(-) (limited to 'include') diff --git a/include/sound/soc-topology.h b/include/sound/soc-topology.h index 401ef2c45d6c..fa4b8413d2e2 100644 --- a/include/sound/soc-topology.h +++ b/include/sound/soc-topology.h @@ -1,13 +1,10 @@ -/* +/* SPDX-License-Identifier: GPL-2.0 + * * linux/sound/soc-topology.h -- ALSA SoC Firmware Controls and DAPM * * Copyright (C) 2012 Texas Instruments Inc. * Copyright (C) 2015 Intel Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * * Simple file API to load FW that includes mixers, coefficients, DAPM graphs, * algorithms, equalisers, DAIs, widgets, FE caps, BE caps, codec link caps etc. */ diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c index 05d177d689e2..66e77e020745 100644 --- a/sound/soc/soc-topology.c +++ b/sound/soc/soc-topology.c @@ -1,29 +1,24 @@ -/* - * soc-topology.c -- ALSA SoC Topology - * - * Copyright (C) 2012 Texas Instruments Inc. - * Copyright (C) 2015 Intel Corporation. - * - * Authors: Liam Girdwood - * K, Mythri P - * Prusty, Subhransu S - * B, Jayachandran - * Abdullah, Omair M - * Jin, Yao - * Lin, Mengdong - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * - * Add support to read audio firmware topology alongside firmware text. The - * topology data can contain kcontrols, DAPM graphs, widgets, DAIs, DAI links, - * equalizers, firmware, coefficients etc. - * - * This file only manages the core ALSA and ASoC components, all other bespoke - * firmware topology data is passed to component drivers for bespoke handling. - */ +// SPDX-License-Identifier: GPL-2.0+ +// +// soc-topology.c -- ALSA SoC Topology +// +// Copyright (C) 2012 Texas Instruments Inc. +// Copyright (C) 2015 Intel Corporation. +// +// Authors: Liam Girdwood +// K, Mythri P +// Prusty, Subhransu S +// B, Jayachandran +// Abdullah, Omair M +// Jin, Yao +// Lin, Mengdong +// +// Add support to read audio firmware topology alongside firmware text. The +// topology data can contain kcontrols, DAPM graphs, widgets, DAIs, DAI links, +// equalizers, firmware, coefficients etc. +// +// This file only manages the core ALSA and ASoC components, all other bespoke +// firmware topology data is passed to component drivers for bespoke handling. #include #include -- cgit v1.2.3 From b3ed4c86a700b494fc5058a52531eeb14d6fe00f Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 2 Jul 2018 06:24:57 +0000 Subject: ASoC: soc-compress: convert to SPDX identifiers Signed-off-by: Kuninori Morimoto Signed-off-by: Mark Brown --- include/sound/compress_driver.h | 21 +++------------------ sound/soc/soc-compress.c | 24 +++++++++--------------- 2 files changed, 12 insertions(+), 33 deletions(-) (limited to 'include') diff --git a/include/sound/compress_driver.h b/include/sound/compress_driver.h index 9924bc9cbc7c..ea8c93bbb0e0 100644 --- a/include/sound/compress_driver.h +++ b/include/sound/compress_driver.h @@ -1,27 +1,12 @@ -/* +/* SPDX-License-Identifier: GPL-2.0 + * * compress_driver.h - compress offload driver definations * * Copyright (C) 2011 Intel Corporation * Authors: Vinod Koul * Pierre-Louis Bossart - * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA. - * - * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - * */ + #ifndef __COMPRESS_DRIVER_H #define __COMPRESS_DRIVER_H diff --git a/sound/soc/soc-compress.c b/sound/soc/soc-compress.c index e095115fa9f9..b9e1673fea51 100644 --- a/sound/soc/soc-compress.c +++ b/sound/soc/soc-compress.c @@ -1,18 +1,12 @@ -/* - * soc-compress.c -- ALSA SoC Compress - * - * Copyright (C) 2012 Intel Corp. - * - * Authors: Namarta Kohli - * Ramesh Babu K V - * Vinod Koul - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * - */ +// SPDX-License-Identifier: GPL-2.0+ +// +// soc-compress.c -- ALSA SoC Compress +// +// Copyright (C) 2012 Intel Corp. +// +// Authors: Namarta Kohli +// Ramesh Babu K V +// Vinod Koul #include #include -- cgit v1.2.3 From 1356a6071cf4d7187652cd2b18dfab4763e0dba6 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 2 Jul 2018 06:25:11 +0000 Subject: ASoC: soc-generic-dmaengine-pcm: convert to SPDX identifiers Signed-off-by: Kuninori Morimoto Signed-off-by: Mark Brown --- include/sound/dmaengine_pcm.h | 14 +++----------- sound/soc/soc-generic-dmaengine-pcm.c | 19 +++++-------------- 2 files changed, 8 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/include/sound/dmaengine_pcm.h b/include/sound/dmaengine_pcm.h index e3481eebdd98..2c4cfaa135a6 100644 --- a/include/sound/dmaengine_pcm.h +++ b/include/sound/dmaengine_pcm.h @@ -1,17 +1,9 @@ -/* +/* SPDX-License-Identifier: GPL-2.0+ + * * Copyright (C) 2012, Analog Devices Inc. * Author: Lars-Peter Clausen - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 675 Mass Ave, Cambridge, MA 02139, USA. - * */ + #ifndef __SOUND_DMAENGINE_PCM_H__ #define __SOUND_DMAENGINE_PCM_H__ diff --git a/sound/soc/soc-generic-dmaengine-pcm.c b/sound/soc/soc-generic-dmaengine-pcm.c index 56a541b9ff9e..13bdca6e41c5 100644 --- a/sound/soc/soc-generic-dmaengine-pcm.c +++ b/sound/soc/soc-generic-dmaengine-pcm.c @@ -1,17 +1,8 @@ -/* - * Copyright (C) 2013, Analog Devices Inc. - * Author: Lars-Peter Clausen - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 675 Mass Ave, Cambridge, MA 02139, USA. - * - */ +// SPDX-License-Identifier: GPL-2.0+ +// +// Copyright (C) 2013, Analog Devices Inc. +// Author: Lars-Peter Clausen + #include #include #include -- cgit v1.2.3 From 1a8f0a3c13c136951de7ea24ccb148e745db98a2 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 2 Jul 2018 06:26:27 +0000 Subject: ASoC: ac97: convert to SPDX identifiers Signed-off-by: Kuninori Morimoto Signed-off-by: Mark Brown --- include/sound/ac97/codec.h | 8 +++----- include/sound/ac97/compat.h | 9 +++------ include/sound/ac97/controller.h | 8 +++----- include/sound/ac97/regs.h | 20 ++------------------ include/sound/ac97_codec.h | 25 +++++-------------------- sound/soc/soc-ac97.c | 29 ++++++++++++----------------- 6 files changed, 28 insertions(+), 71 deletions(-) (limited to 'include') diff --git a/include/sound/ac97/codec.h b/include/sound/ac97/codec.h index ec04be9ab119..9792d25fa369 100644 --- a/include/sound/ac97/codec.h +++ b/include/sound/ac97/codec.h @@ -1,10 +1,8 @@ -/* - * Copyright (C) 2016 Robert Jarzmik +/* SPDX-License-Identifier: GPL-2.0 * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. + * Copyright (C) 2016 Robert Jarzmik */ + #ifndef __SOUND_AC97_CODEC2_H #define __SOUND_AC97_CODEC2_H diff --git a/include/sound/ac97/compat.h b/include/sound/ac97/compat.h index 1351cba40048..57e19afa31ab 100644 --- a/include/sound/ac97/compat.h +++ b/include/sound/ac97/compat.h @@ -1,14 +1,11 @@ -/* - * Copyright (C) 2016 Robert Jarzmik +/* SPDX-License-Identifier: GPL-2.0 * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. + * Copyright (C) 2016 Robert Jarzmik * * This file is for backward compatibility with snd_ac97 structure and its * multiple usages, such as the snd_ac97_bus and snd_ac97_build_ops. - * */ + #ifndef AC97_COMPAT_H #define AC97_COMPAT_H diff --git a/include/sound/ac97/controller.h b/include/sound/ac97/controller.h index b36ecdd64f14..06b5afb7fa6b 100644 --- a/include/sound/ac97/controller.h +++ b/include/sound/ac97/controller.h @@ -1,10 +1,8 @@ -/* - * Copyright (C) 2016 Robert Jarzmik +/* SPDX-License-Identifier: GPL-2.0 * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. + * Copyright (C) 2016 Robert Jarzmik */ + #ifndef AC97_CONTROLLER_H #define AC97_CONTROLLER_H diff --git a/include/sound/ac97/regs.h b/include/sound/ac97/regs.h index 9a4fa0c3264a..843f73f3705a 100644 --- a/include/sound/ac97/regs.h +++ b/include/sound/ac97/regs.h @@ -1,27 +1,11 @@ -/* +/* SPDX-License-Identifier: GPL-2.0+ + * * Copyright (c) by Jaroslav Kysela * Universal interface for Audio Codec '97 * * For more details look to AC '97 component specification revision 2.1 * by Intel Corporation (http://developer.intel.com). - * - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * */ - /* * AC'97 codec registers */ diff --git a/include/sound/ac97_codec.h b/include/sound/ac97_codec.h index 89d311a503d3..cc383991c0fe 100644 --- a/include/sound/ac97_codec.h +++ b/include/sound/ac97_codec.h @@ -1,30 +1,15 @@ -#ifndef __SOUND_AC97_CODEC_H -#define __SOUND_AC97_CODEC_H - -/* +/* SPDX-License-Identifier: GPL-2.0+ + * * Copyright (c) by Jaroslav Kysela * Universal interface for Audio Codec '97 * * For more details look to AC '97 component specification revision 2.1 * by Intel Corporation (http://developer.intel.com). - * - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * */ +#ifndef __SOUND_AC97_CODEC_H +#define __SOUND_AC97_CODEC_H + #include #include #include diff --git a/sound/soc/soc-ac97.c b/sound/soc/soc-ac97.c index 3f424f214bca..c086786e4471 100644 --- a/sound/soc/soc-ac97.c +++ b/sound/soc/soc-ac97.c @@ -1,20 +1,15 @@ -/* - * soc-ac97.c -- ALSA SoC Audio Layer AC97 support - * - * Copyright 2005 Wolfson Microelectronics PLC. - * Copyright 2005 Openedhand Ltd. - * Copyright (C) 2010 Slimlogic Ltd. - * Copyright (C) 2010 Texas Instruments Inc. - * - * Author: Liam Girdwood - * with code, comments and ideas from :- - * Richard Purdie - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - */ +// SPDX-License-Identifier: GPL-2.0+ +// +// soc-ac97.c -- ALSA SoC Audio Layer AC97 support +// +// Copyright 2005 Wolfson Microelectronics PLC. +// Copyright 2005 Openedhand Ltd. +// Copyright (C) 2010 Slimlogic Ltd. +// Copyright (C) 2010 Texas Instruments Inc. +// +// Author: Liam Girdwood +// with code, comments and ideas from :- +// Richard Purdie #include #include -- cgit v1.2.3 From 05739375f1c0a1048fea8b9c4cb54d9e4a891938 Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Fri, 29 Jun 2018 14:59:40 +0200 Subject: ASoC: pxa-ssp: remove .set_pll() and .set_clkdiv() callbacks The .set_pll() and .set_clkdiv() callbacks are considered legacy and should not be used anymore. In order to support PXA boards on DT platforms, remove them and let the code figure out the correct dividers and PLL base frequencies itself. Signed-off-by: Daniel Mack Signed-off-by: Mark Brown --- include/linux/pxa2xx_ssp.h | 8 +++ sound/soc/pxa/pxa-ssp.c | 146 ++++++++++++++++++++++----------------------- 2 files changed, 81 insertions(+), 73 deletions(-) (limited to 'include') diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h index 03a7ca46735b..13b4244d44c1 100644 --- a/include/linux/pxa2xx_ssp.h +++ b/include/linux/pxa2xx_ssp.h @@ -171,6 +171,14 @@ #define SSACD_SCDB (1 << 3) /* SSPSYSCLK Divider Bypass */ #define SSACD_ACPS(x) ((x) << 4) /* Audio clock PLL select */ #define SSACD_ACDS(x) ((x) << 0) /* Audio clock divider select */ +#define SSACD_ACDS_1 (0) +#define SSACD_ACDS_2 (1) +#define SSACD_ACDS_4 (2) +#define SSACD_ACDS_8 (3) +#define SSACD_ACDS_16 (4) +#define SSACD_ACDS_32 (5) +#define SSACD_SCDB_4X (0) +#define SSACD_SCDB_1X (1) #define SSACD_SCDX8 (1 << 7) /* SYSCLK division ratio select */ /* LPSS SSP */ diff --git a/sound/soc/pxa/pxa-ssp.c b/sound/soc/pxa/pxa-ssp.c index 01d54697ede4..f8339bb01251 100644 --- a/sound/soc/pxa/pxa-ssp.c +++ b/sound/soc/pxa/pxa-ssp.c @@ -41,6 +41,7 @@ */ struct ssp_priv { struct ssp_device *ssp; + unsigned long ssp_clk; unsigned int sysclk; unsigned int dai_fmt; unsigned int configured_dai_fmt; @@ -192,21 +193,6 @@ static void pxa_ssp_set_scr(struct ssp_device *ssp, u32 div) pxa_ssp_write_reg(ssp, SSCR0, sscr0); } -/** - * pxa_ssp_get_clkdiv - get SSP clock divider - */ -static u32 pxa_ssp_get_scr(struct ssp_device *ssp) -{ - u32 sscr0 = pxa_ssp_read_reg(ssp, SSCR0); - u32 div; - - if (ssp->type == PXA25x_SSP) - div = ((sscr0 >> 8) & 0xff) * 2 + 2; - else - div = ((sscr0 >> 8) & 0xfff) + 1; - return div; -} - /* * Set the SSP ports SYSCLK. */ @@ -262,67 +248,18 @@ static int pxa_ssp_set_dai_sysclk(struct snd_soc_dai *cpu_dai, return 0; } -/* - * Set the SSP clock dividers. - */ -static int pxa_ssp_set_dai_clkdiv(struct snd_soc_dai *cpu_dai, - int div_id, int div) -{ - struct ssp_priv *priv = snd_soc_dai_get_drvdata(cpu_dai); - struct ssp_device *ssp = priv->ssp; - int val; - - switch (div_id) { - case PXA_SSP_AUDIO_DIV_ACDS: - val = (pxa_ssp_read_reg(ssp, SSACD) & ~0x7) | SSACD_ACDS(div); - pxa_ssp_write_reg(ssp, SSACD, val); - break; - case PXA_SSP_AUDIO_DIV_SCDB: - val = pxa_ssp_read_reg(ssp, SSACD); - val &= ~SSACD_SCDB; - if (ssp->type == PXA3xx_SSP) - val &= ~SSACD_SCDX8; - switch (div) { - case PXA_SSP_CLK_SCDB_1: - val |= SSACD_SCDB; - break; - case PXA_SSP_CLK_SCDB_4: - break; - case PXA_SSP_CLK_SCDB_8: - if (ssp->type == PXA3xx_SSP) - val |= SSACD_SCDX8; - else - return -EINVAL; - break; - default: - return -EINVAL; - } - pxa_ssp_write_reg(ssp, SSACD, val); - break; - case PXA_SSP_DIV_SCR: - pxa_ssp_set_scr(ssp, div); - break; - default: - return -ENODEV; - } - - return 0; -} - /* * Configure the PLL frequency pxa27x and (afaik - pxa320 only) */ -static int pxa_ssp_set_dai_pll(struct snd_soc_dai *cpu_dai, int pll_id, - int source, unsigned int freq_in, unsigned int freq_out) +static int pxa_ssp_set_pll(struct ssp_priv *priv, unsigned int freq) { - struct ssp_priv *priv = snd_soc_dai_get_drvdata(cpu_dai); struct ssp_device *ssp = priv->ssp; u32 ssacd = pxa_ssp_read_reg(ssp, SSACD) & ~0x70; if (ssp->type == PXA3xx_SSP) pxa_ssp_write_reg(ssp, SSACDD, 0); - switch (freq_out) { + switch (freq) { case 5622000: break; case 11345000: @@ -353,7 +290,7 @@ static int pxa_ssp_set_dai_pll(struct snd_soc_dai *cpu_dai, int pll_id, u64 tmp = 19968; tmp *= 1000000; - do_div(tmp, freq_out); + do_div(tmp, freq); val = tmp; val = (val << 16) | 64; @@ -363,7 +300,7 @@ static int pxa_ssp_set_dai_pll(struct snd_soc_dai *cpu_dai, int pll_id, dev_dbg(&ssp->pdev->dev, "Using SSACDD %x to supply %uHz\n", - val, freq_out); + val, freq); break; } @@ -568,6 +505,24 @@ static int pxa_ssp_configure_dai_fmt(struct ssp_priv *priv) return 0; } +struct pxa_ssp_clock_mode { + int rate; + int pll; + u8 acds; + u8 scdb; +}; + +static const struct pxa_ssp_clock_mode pxa_ssp_clock_modes[] = { + { .rate = 8000, .pll = 32842000, .acds = SSACD_ACDS_32, .scdb = SSACD_SCDB_4X }, + { .rate = 11025, .pll = 5622000, .acds = SSACD_ACDS_4, .scdb = SSACD_SCDB_4X }, + { .rate = 16000, .pll = 32842000, .acds = SSACD_ACDS_16, .scdb = SSACD_SCDB_4X }, + { .rate = 22050, .pll = 5622000, .acds = SSACD_ACDS_2, .scdb = SSACD_SCDB_4X }, + { .rate = 44100, .pll = 11345000, .acds = SSACD_ACDS_2, .scdb = SSACD_SCDB_4X }, + { .rate = 48000, .pll = 12235000, .acds = SSACD_ACDS_2, .scdb = SSACD_SCDB_4X }, + { .rate = 96000, .pll = 12235000, .acds = SSACD_ACDS_4, .scdb = SSACD_SCDB_1X }, + {} +}; + /* * Set the SSP audio DMA parameters and sample size. * Can be called multiple times by oss emulation. @@ -579,11 +534,12 @@ static int pxa_ssp_hw_params(struct snd_pcm_substream *substream, struct ssp_priv *priv = snd_soc_dai_get_drvdata(cpu_dai); struct ssp_device *ssp = priv->ssp; int chn = params_channels(params); - u32 sscr0; - u32 sspsp; + u32 sscr0, sspsp; int width = snd_pcm_format_physical_width(params_format(params)); int ttsa = pxa_ssp_read_reg(ssp, SSTSA) & 0xf; struct snd_dmaengine_dai_dma_data *dma_data; + int rate = params_rate(params); + int bclk = rate * chn * (width / 8); int ret; dma_data = snd_soc_dai_get_dma_data(cpu_dai, substream); @@ -623,11 +579,57 @@ static int pxa_ssp_hw_params(struct snd_pcm_substream *substream, } pxa_ssp_write_reg(ssp, SSCR0, sscr0); + if (sscr0 & SSCR0_ACS) { + ret = pxa_ssp_set_pll(priv, bclk); + + /* + * If we were able to generate the bclk directly, + * all is fine. Otherwise, look up the closest rate + * from the table and also set the dividers. + */ + + if (ret < 0) { + const struct pxa_ssp_clock_mode *m; + int ssacd, acds; + + for (m = pxa_ssp_clock_modes; m->rate; m++) { + if (m->rate == rate) + break; + } + + if (!m->rate) + return -EINVAL; + + acds = m->acds; + + /* The values in the table are for 16 bits */ + if (width == 32) + acds--; + + ret = pxa_ssp_set_pll(priv, bclk); + if (ret < 0) + return ret; + + ssacd = pxa_ssp_read_reg(ssp, SSACD); + ssacd &= ~(SSACD_ACDS(7) | SSACD_SCDB_1X); + ssacd |= SSACD_ACDS(m->acds); + ssacd |= m->scdb; + pxa_ssp_write_reg(ssp, SSACD, ssacd); + } + } else if (sscr0 & SSCR0_ECS) { + /* + * For setups with external clocking, the PLL and its diviers + * are not active. Instead, the SCR bits in SSCR0 can be used + * to divide the clock. + */ + pxa_ssp_set_scr(ssp, bclk / rate); + } + switch (priv->dai_fmt & SND_SOC_DAIFMT_FORMAT_MASK) { case SND_SOC_DAIFMT_I2S: sspsp = pxa_ssp_read_reg(ssp, SSPSP); - if ((pxa_ssp_get_scr(ssp) == 4) && (width == 16)) { + if (((priv->sysclk / bclk) == 64) && (width == 16)) { /* This is a special case where the bitclk is 64fs * and we're not dealing with 2*32 bits of audio * samples. @@ -812,8 +814,6 @@ static const struct snd_soc_dai_ops pxa_ssp_dai_ops = { .trigger = pxa_ssp_trigger, .hw_params = pxa_ssp_hw_params, .set_sysclk = pxa_ssp_set_dai_sysclk, - .set_clkdiv = pxa_ssp_set_dai_clkdiv, - .set_pll = pxa_ssp_set_dai_pll, .set_fmt = pxa_ssp_set_dai_fmt, .set_tdm_slot = pxa_ssp_set_dai_tdm_slot, .set_tristate = pxa_ssp_set_dai_tristate, -- cgit v1.2.3 From 88763a5cf80ca59a7c3bea32681ce8f697d9995f Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Tue, 26 Jun 2018 12:53:29 +0200 Subject: powercap / idle_inject: Add an idle injection framework Initially, the cpu_cooling device for ARM was changed by adding a new policy inserting idle cycles. The intel_powerclamp driver does a similar action. Instead of implementing idle injections privately in the cpu_cooling device, move the idle injection code in a dedicated framework and give the opportunity to other frameworks to make use of it. The framework relies on the smpboot kthreads which handles via its main loop the common code for hotplugging and [un]parking. This code was previously tested with the cpu cooling device and went through several iterations. It results now in split code and API exported in the header file. It was tested with the cpu cooling device with success. Signed-off-by: Daniel Lezcano Reviewed-by: Viresh Kumar [ rjw: Rewrite of all comments ] Signed-off-by: Rafael J. Wysocki --- drivers/powercap/Kconfig | 10 ++ drivers/powercap/Makefile | 1 + drivers/powercap/idle_inject.c | 356 +++++++++++++++++++++++++++++++++++++++++ include/linux/idle_inject.h | 29 ++++ 4 files changed, 396 insertions(+) create mode 100644 drivers/powercap/idle_inject.c create mode 100644 include/linux/idle_inject.h (limited to 'include') diff --git a/drivers/powercap/Kconfig b/drivers/powercap/Kconfig index 85727ef6ce8e..6ac27e5908f5 100644 --- a/drivers/powercap/Kconfig +++ b/drivers/powercap/Kconfig @@ -29,4 +29,14 @@ config INTEL_RAPL controller, CPU core (Power Plance 0), graphics uncore (Power Plane 1), etc. +config IDLE_INJECT + bool "Idle injection framework" + depends on CPU_IDLE + default n + help + This enables support for the idle injection framework. It + provides a way to force idle periods on a set of specified + CPUs for power capping. Idle period can be injected + synchronously on a set of specified CPUs or alternatively + on a per CPU basis. endif diff --git a/drivers/powercap/Makefile b/drivers/powercap/Makefile index 0a21ef31372b..1b328854b36e 100644 --- a/drivers/powercap/Makefile +++ b/drivers/powercap/Makefile @@ -1,2 +1,3 @@ obj-$(CONFIG_POWERCAP) += powercap_sys.o obj-$(CONFIG_INTEL_RAPL) += intel_rapl.o +obj-$(CONFIG_IDLE_INJECT) += idle_inject.o diff --git a/drivers/powercap/idle_inject.c b/drivers/powercap/idle_inject.c new file mode 100644 index 000000000000..24ff2a068978 --- /dev/null +++ b/drivers/powercap/idle_inject.c @@ -0,0 +1,356 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright 2018 Linaro Limited + * + * Author: Daniel Lezcano + * + * The idle injection framework provides a way to force CPUs to enter idle + * states for a specified fraction of time over a specified period. + * + * It relies on the smpboot kthreads feature providing common code for CPU + * hotplug and thread [un]parking. + * + * All of the kthreads used for idle injection are created at init time. + * + * Next, the users of the the idle injection framework provide a cpumask via + * its register function. The kthreads will be synchronized with respect to + * this cpumask. + * + * The idle + run duration is specified via separate helpers and that allows + * idle injection to be started. + * + * The idle injection kthreads will call play_idle() with the idle duration + * specified as per the above. + * + * After all of them have been woken up, a timer is set to start the next idle + * injection cycle. + * + * The timer interrupt handler will wake up the idle injection kthreads for + * all of the CPUs in the cpumask provided by the user. + * + * Idle injection is stopped synchronously and no leftover idle injection + * kthread activity after its completion is guaranteed. + * + * It is up to the user of this framework to provide a lock for higher-level + * synchronization to prevent race conditions like starting idle injection + * while unregistering from the framework. + */ +#define pr_fmt(fmt) "ii_dev: " fmt + +#include +#include +#include +#include +#include +#include + +#include + +/** + * struct idle_inject_thread - task on/off switch structure + * @tsk: task injecting the idle cycles + * @should_run: whether or not to run the task (for the smpboot kthread API) + */ +struct idle_inject_thread { + struct task_struct *tsk; + int should_run; +}; + +/** + * struct idle_inject_device - idle injection data + * @timer: idle injection period timer + * @idle_duration_ms: duration of CPU idle time to inject + * @run_duration_ms: duration of CPU run time to allow + * @cpumask: mask of CPUs affected by idle injection + */ +struct idle_inject_device { + struct hrtimer timer; + unsigned int idle_duration_ms; + unsigned int run_duration_ms; + unsigned long int cpumask[0]; +}; + +static DEFINE_PER_CPU(struct idle_inject_thread, idle_inject_thread); +static DEFINE_PER_CPU(struct idle_inject_device *, idle_inject_device); + +/** + * idle_inject_wakeup - Wake up idle injection threads + * @ii_dev: target idle injection device + * + * Every idle injection task associated with the given idle injection device + * and running on an online CPU will be woken up. + */ +static void idle_inject_wakeup(struct idle_inject_device *ii_dev) +{ + struct idle_inject_thread *iit; + unsigned int cpu; + + for_each_cpu_and(cpu, to_cpumask(ii_dev->cpumask), cpu_online_mask) { + iit = per_cpu_ptr(&idle_inject_thread, cpu); + iit->should_run = 1; + wake_up_process(iit->tsk); + } +} + +/** + * idle_inject_timer_fn - idle injection timer function + * @timer: idle injection hrtimer + * + * This function is called when the idle injection timer expires. It wakes up + * idle injection tasks associated with the timer and they, in turn, invoke + * play_idle() to inject a specified amount of CPU idle time. + * + * Return: HRTIMER_RESTART. + */ +static enum hrtimer_restart idle_inject_timer_fn(struct hrtimer *timer) +{ + unsigned int duration_ms; + struct idle_inject_device *ii_dev = + container_of(timer, struct idle_inject_device, timer); + + duration_ms = READ_ONCE(ii_dev->run_duration_ms); + duration_ms += READ_ONCE(ii_dev->idle_duration_ms); + + idle_inject_wakeup(ii_dev); + + hrtimer_forward_now(timer, ms_to_ktime(duration_ms)); + + return HRTIMER_RESTART; +} + +/** + * idle_inject_fn - idle injection work function + * @cpu: the CPU owning the task + * + * This function calls play_idle() to inject a specified amount of CPU idle + * time. + */ +static void idle_inject_fn(unsigned int cpu) +{ + struct idle_inject_device *ii_dev; + struct idle_inject_thread *iit; + + ii_dev = per_cpu(idle_inject_device, cpu); + iit = per_cpu_ptr(&idle_inject_thread, cpu); + + /* + * Let the smpboot main loop know that the task should not run again. + */ + iit->should_run = 0; + + play_idle(READ_ONCE(ii_dev->idle_duration_ms)); +} + +/** + * idle_inject_set_duration - idle and run duration update helper + * @run_duration_ms: CPU run time to allow in milliseconds + * @idle_duration_ms: CPU idle time to inject in milliseconds + */ +void idle_inject_set_duration(struct idle_inject_device *ii_dev, + unsigned int run_duration_ms, + unsigned int idle_duration_ms) +{ + if (run_duration_ms && idle_duration_ms) { + WRITE_ONCE(ii_dev->run_duration_ms, run_duration_ms); + WRITE_ONCE(ii_dev->idle_duration_ms, idle_duration_ms); + } +} + +/** + * idle_inject_get_duration - idle and run duration retrieval helper + * @run_duration_ms: memory location to store the current CPU run time + * @idle_duration_ms: memory location to store the current CPU idle time + */ +void idle_inject_get_duration(struct idle_inject_device *ii_dev, + unsigned int *run_duration_ms, + unsigned int *idle_duration_ms) +{ + *run_duration_ms = READ_ONCE(ii_dev->run_duration_ms); + *idle_duration_ms = READ_ONCE(ii_dev->idle_duration_ms); +} + +/** + * idle_inject_start - start idle injections + * @ii_dev: idle injection control device structure + * + * The function starts idle injection by first waking up all of the idle + * injection kthreads associated with @ii_dev to let them inject CPU idle time + * sets up a timer to start the next idle injection period. + * + * Return: -EINVAL if the CPU idle or CPU run time is not set or 0 on success. + */ +int idle_inject_start(struct idle_inject_device *ii_dev) +{ + unsigned int idle_duration_ms = READ_ONCE(ii_dev->idle_duration_ms); + unsigned int run_duration_ms = READ_ONCE(ii_dev->run_duration_ms); + + if (!idle_duration_ms || !run_duration_ms) + return -EINVAL; + + pr_debug("Starting injecting idle cycles on CPUs '%*pbl'\n", + cpumask_pr_args(to_cpumask(ii_dev->cpumask))); + + idle_inject_wakeup(ii_dev); + + hrtimer_start(&ii_dev->timer, + ms_to_ktime(idle_duration_ms + run_duration_ms), + HRTIMER_MODE_REL); + + return 0; +} + +/** + * idle_inject_stop - stops idle injections + * @ii_dev: idle injection control device structure + * + * The function stops idle injection and waits for the threads to finish work. + * If CPU idle time is being injected when this function runs, then it will + * wait until the end of the cycle. + * + * When it returns, there is no more idle injection kthread activity. The + * kthreads are scheduled out and the periodic timer is off. + */ +void idle_inject_stop(struct idle_inject_device *ii_dev) +{ + struct idle_inject_thread *iit; + unsigned int cpu; + + pr_debug("Stopping idle injection on CPUs '%*pbl'\n", + cpumask_pr_args(to_cpumask(ii_dev->cpumask))); + + hrtimer_cancel(&ii_dev->timer); + + /* + * Stopping idle injection requires all of the idle injection kthreads + * associated with the given cpumask to be parked and stay that way, so + * prevent CPUs from going online at this point. Any CPUs going online + * after the loop below will be covered by clearing the should_run flag + * that will cause the smpboot main loop to schedule them out. + */ + cpu_hotplug_disable(); + + /* + * Iterate over all (online + offline) CPUs here in case one of them + * goes offline with the should_run flag set so as to prevent its idle + * injection kthread from running when the CPU goes online again after + * the ii_dev has been freed. + */ + for_each_cpu(cpu, to_cpumask(ii_dev->cpumask)) { + iit = per_cpu_ptr(&idle_inject_thread, cpu); + iit->should_run = 0; + + wait_task_inactive(iit->tsk, 0); + } + + cpu_hotplug_enable(); +} + +/** + * idle_inject_setup - prepare the current task for idle injection + * @cpu: not used + * + * Called once, this function is in charge of setting the current task's + * scheduler parameters to make it an RT task. + */ +static void idle_inject_setup(unsigned int cpu) +{ + struct sched_param param = { .sched_priority = MAX_USER_RT_PRIO / 2 }; + + sched_setscheduler(current, SCHED_FIFO, ¶m); +} + +/** + * idle_inject_should_run - function helper for the smpboot API + * @cpu: CPU the kthread is running on + * + * Return: whether or not the thread can run. + */ +static int idle_inject_should_run(unsigned int cpu) +{ + struct idle_inject_thread *iit = + per_cpu_ptr(&idle_inject_thread, cpu); + + return iit->should_run; +} + +/** + * idle_inject_register - initialize idle injection on a set of CPUs + * @cpumask: CPUs to be affected by idle injection + * + * This function creates an idle injection control device structure for the + * given set of CPUs and initializes the timer associated with it. It does not + * start any injection cycles. + * + * Return: NULL if memory allocation fails, idle injection control device + * pointer on success. + */ +struct idle_inject_device *idle_inject_register(struct cpumask *cpumask) +{ + struct idle_inject_device *ii_dev; + int cpu, cpu_rb; + + ii_dev = kzalloc(sizeof(*ii_dev) + cpumask_size(), GFP_KERNEL); + if (!ii_dev) + return NULL; + + cpumask_copy(to_cpumask(ii_dev->cpumask), cpumask); + hrtimer_init(&ii_dev->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + ii_dev->timer.function = idle_inject_timer_fn; + + for_each_cpu(cpu, to_cpumask(ii_dev->cpumask)) { + + if (per_cpu(idle_inject_device, cpu)) { + pr_err("cpu%d is already registered\n", cpu); + goto out_rollback; + } + + per_cpu(idle_inject_device, cpu) = ii_dev; + } + + return ii_dev; + +out_rollback: + for_each_cpu(cpu_rb, to_cpumask(ii_dev->cpumask)) { + if (cpu == cpu_rb) + break; + per_cpu(idle_inject_device, cpu_rb) = NULL; + } + + kfree(ii_dev); + + return NULL; +} + +/** + * idle_inject_unregister - unregister idle injection control device + * @ii_dev: idle injection control device to unregister + * + * The function stops idle injection for the given control device, + * unregisters its kthreads and frees memory allocated when that device was + * created. + */ +void idle_inject_unregister(struct idle_inject_device *ii_dev) +{ + unsigned int cpu; + + idle_inject_stop(ii_dev); + + for_each_cpu(cpu, to_cpumask(ii_dev->cpumask)) + per_cpu(idle_inject_device, cpu) = NULL; + + kfree(ii_dev); +} + +static struct smp_hotplug_thread idle_inject_threads = { + .store = &idle_inject_thread.tsk, + .setup = idle_inject_setup, + .thread_fn = idle_inject_fn, + .thread_comm = "idle_inject/%u", + .thread_should_run = idle_inject_should_run, +}; + +static int __init idle_inject_init(void) +{ + return smpboot_register_percpu_thread(&idle_inject_threads); +} +early_initcall(idle_inject_init); diff --git a/include/linux/idle_inject.h b/include/linux/idle_inject.h new file mode 100644 index 000000000000..bdc0293fb6cb --- /dev/null +++ b/include/linux/idle_inject.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2018 Linaro Ltd + * + * Author: Daniel Lezcano + * + */ +#ifndef __IDLE_INJECT_H__ +#define __IDLE_INJECT_H__ + +/* private idle injection device structure */ +struct idle_inject_device; + +struct idle_inject_device *idle_inject_register(struct cpumask *cpumask); + +void idle_inject_unregister(struct idle_inject_device *ii_dev); + +int idle_inject_start(struct idle_inject_device *ii_dev); + +void idle_inject_stop(struct idle_inject_device *ii_dev); + +void idle_inject_set_duration(struct idle_inject_device *ii_dev, + unsigned int run_duration_ms, + unsigned int idle_duration_ms); + +void idle_inject_get_duration(struct idle_inject_device *ii_dev, + unsigned int *run_duration_ms, + unsigned int *idle_duration_ms); +#endif /* __IDLE_INJECT_H__ */ -- cgit v1.2.3 From d6f19938eb031ee2158272757db33258153ae59c Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Sun, 1 Jul 2018 23:31:30 +0800 Subject: net: expose sk wmem in sock_exceed_buf_limit tracepoint Currently trace_sock_exceed_buf_limit() only show rmem info, but wmem limit may also be hit. So expose wmem info in this tracepoint as well. Regarding memcg, I think it is better to introduce a new tracepoint(if that is needed), i.e. trace_memcg_limit_hit other than show memcg info in trace_sock_exceed_buf_limit. Signed-off-by: Yafang Shao Signed-off-by: David S. Miller --- include/trace/events/sock.h | 30 +++++++++++++++++++++++++----- net/core/sock.c | 6 ++++-- 2 files changed, 29 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/trace/events/sock.h b/include/trace/events/sock.h index 3176a3931107..a0c4b8a30966 100644 --- a/include/trace/events/sock.h +++ b/include/trace/events/sock.h @@ -35,6 +35,10 @@ EM(TCP_CLOSING) \ EMe(TCP_NEW_SYN_RECV) +#define skmem_kind_names \ + EM(SK_MEM_SEND) \ + EMe(SK_MEM_RECV) + /* enums need to be exported to user space */ #undef EM #undef EMe @@ -44,6 +48,7 @@ family_names inet_protocol_names tcp_state_names +skmem_kind_names #undef EM #undef EMe @@ -59,6 +64,9 @@ tcp_state_names #define show_tcp_state_name(val) \ __print_symbolic(val, tcp_state_names) +#define show_skmem_kind_names(val) \ + __print_symbolic(val, skmem_kind_names) + TRACE_EVENT(sock_rcvqueue_full, TP_PROTO(struct sock *sk, struct sk_buff *skb), @@ -83,9 +91,9 @@ TRACE_EVENT(sock_rcvqueue_full, TRACE_EVENT(sock_exceed_buf_limit, - TP_PROTO(struct sock *sk, struct proto *prot, long allocated), + TP_PROTO(struct sock *sk, struct proto *prot, long allocated, int kind), - TP_ARGS(sk, prot, allocated), + TP_ARGS(sk, prot, allocated, kind), TP_STRUCT__entry( __array(char, name, 32) @@ -93,6 +101,10 @@ TRACE_EVENT(sock_exceed_buf_limit, __field(long, allocated) __field(int, sysctl_rmem) __field(int, rmem_alloc) + __field(int, sysctl_wmem) + __field(int, wmem_alloc) + __field(int, wmem_queued) + __field(int, kind) ), TP_fast_assign( @@ -101,17 +113,25 @@ TRACE_EVENT(sock_exceed_buf_limit, __entry->allocated = allocated; __entry->sysctl_rmem = sk_get_rmem0(sk, prot); __entry->rmem_alloc = atomic_read(&sk->sk_rmem_alloc); + __entry->sysctl_wmem = sk_get_wmem0(sk, prot); + __entry->wmem_alloc = refcount_read(&sk->sk_wmem_alloc); + __entry->wmem_queued = sk->sk_wmem_queued; + __entry->kind = kind; ), - TP_printk("proto:%s sysctl_mem=%ld,%ld,%ld allocated=%ld " - "sysctl_rmem=%d rmem_alloc=%d", + TP_printk("proto:%s sysctl_mem=%ld,%ld,%ld allocated=%ld sysctl_rmem=%d rmem_alloc=%d sysctl_wmem=%d wmem_alloc=%d wmem_queued=%d kind=%s", __entry->name, __entry->sysctl_mem[0], __entry->sysctl_mem[1], __entry->sysctl_mem[2], __entry->allocated, __entry->sysctl_rmem, - __entry->rmem_alloc) + __entry->rmem_alloc, + __entry->sysctl_wmem, + __entry->wmem_alloc, + __entry->wmem_queued, + show_skmem_kind_names(__entry->kind) + ) ); TRACE_EVENT(inet_sock_set_state, diff --git a/net/core/sock.c b/net/core/sock.c index dac6d785186b..8b69ac96a850 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2401,9 +2401,10 @@ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind) { struct proto *prot = sk->sk_prot; long allocated = sk_memory_allocated_add(sk, amt); + bool charged = true; if (mem_cgroup_sockets_enabled && sk->sk_memcg && - !mem_cgroup_charge_skmem(sk->sk_memcg, amt)) + !(charged = mem_cgroup_charge_skmem(sk->sk_memcg, amt))) goto suppress_allocation; /* Under limit. */ @@ -2461,7 +2462,8 @@ suppress_allocation: return 1; } - trace_sock_exceed_buf_limit(sk, prot, allocated); + if (kind == SK_MEM_SEND || (kind == SK_MEM_RECV && charged)) + trace_sock_exceed_buf_limit(sk, prot, allocated, kind); sk_memory_allocated_sub(sk, amt); -- cgit v1.2.3 From a7ca13826e478f9b201eb2f9f20de0b978a82ad9 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Fri, 29 Jun 2018 14:11:19 +1000 Subject: gpio: aspeed: Add interfaces for co-processor to grab GPIOs On the Aspeed chip, the GPIOs can be under control of the ARM chip or of the ColdFire coprocessor. (There's a third command source, the LPC bus, which we don't use or support yet). The control of which master is allowed to modify a given GPIO is per-bank (8 GPIOs). Unfortunately, systems already exist for which we want to use GPIOs of both sources in the same bank. This provides an API exported by the gpio-aspeed driver that an aspeed coprocessor driver can use to "grab" some GPIOs for use by the coprocessor, and allow the coprocessor driver to provide callbacks for arbitrating access. Once at least one GPIO of a given bank has been "grabbed" by the coprocessor, the entire bank is marked as being under coprocessor control. It's command source is switched to the coprocessor. If the ARM then tries to write to a GPIO in such a marked bank, the provided callbacks are used to request access from the coprocessor driver, which is responsible to doing whatever is necessary to "pause" the coprocessor or prevent it from trying to use the GPIOs while the ARM is doing its accesses. During that time, the command source for the bank is temporarily switched back to the ARM. Signed-off-by: Benjamin Herrenschmidt Reviewed-by: Joel Stanley Reviewed-by: Andrew Jeffery Signed-off-by: Linus Walleij --- drivers/gpio/gpio-aspeed.c | 251 ++++++++++++++++++++++++++++++++++++++++---- include/linux/gpio/aspeed.h | 15 +++ 2 files changed, 246 insertions(+), 20 deletions(-) create mode 100644 include/linux/gpio/aspeed.h (limited to 'include') diff --git a/drivers/gpio/gpio-aspeed.c b/drivers/gpio/gpio-aspeed.c index b3968f66b1d2..1e00f4045f9d 100644 --- a/drivers/gpio/gpio-aspeed.c +++ b/drivers/gpio/gpio-aspeed.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -22,6 +23,15 @@ #include #include +/* + * These two headers aren't meant to be used by GPIO drivers. We need + * them in order to access gpio_chip_hwgpio() which we need to implement + * the aspeed specific API which allows the coprocessor to request + * access to some GPIOs and to arbitrate between coprocessor and ARM. + */ +#include +#include "gpiolib.h" + struct aspeed_bank_props { unsigned int bank; u32 input; @@ -56,6 +66,7 @@ struct aspeed_gpio { struct clk *clk; u32 *dcache; + u8 *cf_copro_bankmap; }; struct aspeed_gpio_bank { @@ -83,6 +94,9 @@ struct aspeed_gpio_bank { static const int debounce_timers[4] = { 0x00, 0x50, 0x54, 0x58 }; +static const struct aspeed_gpio_copro_ops *copro_ops; +static void *copro_data; + static const struct aspeed_gpio_bank aspeed_gpio_banks[] = { { .val_regs = 0x0000, @@ -323,6 +337,50 @@ static void aspeed_gpio_change_cmd_source(struct aspeed_gpio *gpio, iowrite32(reg, c0); } +static bool aspeed_gpio_copro_request(struct aspeed_gpio *gpio, + unsigned int offset) +{ + const struct aspeed_gpio_bank *bank = to_bank(offset); + + if (!copro_ops || !gpio->cf_copro_bankmap) + return false; + if (!gpio->cf_copro_bankmap[offset >> 3]) + return false; + if (!copro_ops->request_access) + return false; + + /* Pause the coprocessor */ + copro_ops->request_access(copro_data); + + /* Change command source back to ARM */ + aspeed_gpio_change_cmd_source(gpio, bank, offset >> 3, GPIO_CMDSRC_ARM); + + /* Update cache */ + gpio->dcache[GPIO_BANK(offset)] = ioread32(bank_reg(gpio, bank, reg_rdata)); + + return true; +} + +static void aspeed_gpio_copro_release(struct aspeed_gpio *gpio, + unsigned int offset) +{ + const struct aspeed_gpio_bank *bank = to_bank(offset); + + if (!copro_ops || !gpio->cf_copro_bankmap) + return; + if (!gpio->cf_copro_bankmap[offset >> 3]) + return; + if (!copro_ops->release_access) + return; + + /* Change command source back to ColdFire */ + aspeed_gpio_change_cmd_source(gpio, bank, offset >> 3, + GPIO_CMDSRC_COLDFIRE); + + /* Restart the coprocessor */ + copro_ops->release_access(copro_data); +} + static int aspeed_gpio_get(struct gpio_chip *gc, unsigned int offset) { struct aspeed_gpio *gpio = gpiochip_get_data(gc); @@ -356,11 +414,15 @@ static void aspeed_gpio_set(struct gpio_chip *gc, unsigned int offset, { struct aspeed_gpio *gpio = gpiochip_get_data(gc); unsigned long flags; + bool copro; spin_lock_irqsave(&gpio->lock, flags); + copro = aspeed_gpio_copro_request(gpio, offset); __aspeed_gpio_set(gc, offset, val); + if (copro) + aspeed_gpio_copro_release(gpio, offset); spin_unlock_irqrestore(&gpio->lock, flags); } @@ -368,7 +430,9 @@ static int aspeed_gpio_dir_in(struct gpio_chip *gc, unsigned int offset) { struct aspeed_gpio *gpio = gpiochip_get_data(gc); const struct aspeed_gpio_bank *bank = to_bank(offset); + void __iomem *addr = bank_reg(gpio, bank, reg_dir); unsigned long flags; + bool copro; u32 reg; if (!have_input(gpio, offset)) @@ -376,8 +440,13 @@ static int aspeed_gpio_dir_in(struct gpio_chip *gc, unsigned int offset) spin_lock_irqsave(&gpio->lock, flags); - reg = ioread32(bank_reg(gpio, bank, reg_dir)); - iowrite32(reg & ~GPIO_BIT(offset), bank_reg(gpio, bank, reg_dir)); + reg = ioread32(addr); + reg &= ~GPIO_BIT(offset); + + copro = aspeed_gpio_copro_request(gpio, offset); + iowrite32(reg, addr); + if (copro) + aspeed_gpio_copro_release(gpio, offset); spin_unlock_irqrestore(&gpio->lock, flags); @@ -389,7 +458,9 @@ static int aspeed_gpio_dir_out(struct gpio_chip *gc, { struct aspeed_gpio *gpio = gpiochip_get_data(gc); const struct aspeed_gpio_bank *bank = to_bank(offset); + void __iomem *addr = bank_reg(gpio, bank, reg_dir); unsigned long flags; + bool copro; u32 reg; if (!have_output(gpio, offset)) @@ -397,10 +468,15 @@ static int aspeed_gpio_dir_out(struct gpio_chip *gc, spin_lock_irqsave(&gpio->lock, flags); + reg = ioread32(addr); + reg |= GPIO_BIT(offset); + + copro = aspeed_gpio_copro_request(gpio, offset); __aspeed_gpio_set(gc, offset, val); - reg = ioread32(bank_reg(gpio, bank, reg_dir)); - iowrite32(reg | GPIO_BIT(offset), bank_reg(gpio, bank, reg_dir)); + iowrite32(reg, addr); + if (copro) + aspeed_gpio_copro_release(gpio, offset); spin_unlock_irqrestore(&gpio->lock, flags); return 0; @@ -430,24 +506,23 @@ static int aspeed_gpio_get_direction(struct gpio_chip *gc, unsigned int offset) } static inline int irqd_to_aspeed_gpio_data(struct irq_data *d, - struct aspeed_gpio **gpio, - const struct aspeed_gpio_bank **bank, - u32 *bit) + struct aspeed_gpio **gpio, + const struct aspeed_gpio_bank **bank, + u32 *bit, int *offset) { - int offset; struct aspeed_gpio *internal; - offset = irqd_to_hwirq(d); + *offset = irqd_to_hwirq(d); internal = irq_data_get_irq_chip_data(d); /* This might be a bit of a questionable place to check */ - if (!have_irq(internal, offset)) + if (!have_irq(internal, *offset)) return -ENOTSUPP; *gpio = internal; - *bank = to_bank(offset); - *bit = GPIO_BIT(offset); + *bank = to_bank(*offset); + *bit = GPIO_BIT(*offset); return 0; } @@ -458,17 +533,23 @@ static void aspeed_gpio_irq_ack(struct irq_data *d) struct aspeed_gpio *gpio; unsigned long flags; void __iomem *status_addr; + int rc, offset; + bool copro; u32 bit; - int rc; - rc = irqd_to_aspeed_gpio_data(d, &gpio, &bank, &bit); + rc = irqd_to_aspeed_gpio_data(d, &gpio, &bank, &bit, &offset); if (rc) return; status_addr = bank_reg(gpio, bank, reg_irq_status); spin_lock_irqsave(&gpio->lock, flags); + copro = aspeed_gpio_copro_request(gpio, offset); + iowrite32(bit, status_addr); + + if (copro) + aspeed_gpio_copro_release(gpio, offset); spin_unlock_irqrestore(&gpio->lock, flags); } @@ -479,15 +560,17 @@ static void aspeed_gpio_irq_set_mask(struct irq_data *d, bool set) unsigned long flags; u32 reg, bit; void __iomem *addr; - int rc; + int rc, offset; + bool copro; - rc = irqd_to_aspeed_gpio_data(d, &gpio, &bank, &bit); + rc = irqd_to_aspeed_gpio_data(d, &gpio, &bank, &bit, &offset); if (rc) return; addr = bank_reg(gpio, bank, reg_irq_enable); spin_lock_irqsave(&gpio->lock, flags); + copro = aspeed_gpio_copro_request(gpio, offset); reg = ioread32(addr); if (set) @@ -496,6 +579,8 @@ static void aspeed_gpio_irq_set_mask(struct irq_data *d, bool set) reg &= ~bit; iowrite32(reg, addr); + if (copro) + aspeed_gpio_copro_release(gpio, offset); spin_unlock_irqrestore(&gpio->lock, flags); } @@ -520,9 +605,10 @@ static int aspeed_gpio_set_type(struct irq_data *d, unsigned int type) struct aspeed_gpio *gpio; unsigned long flags; void __iomem *addr; - int rc; + int rc, offset; + bool copro; - rc = irqd_to_aspeed_gpio_data(d, &gpio, &bank, &bit); + rc = irqd_to_aspeed_gpio_data(d, &gpio, &bank, &bit, &offset); if (rc) return -EINVAL; @@ -548,6 +634,7 @@ static int aspeed_gpio_set_type(struct irq_data *d, unsigned int type) } spin_lock_irqsave(&gpio->lock, flags); + copro = aspeed_gpio_copro_request(gpio, offset); addr = bank_reg(gpio, bank, reg_irq_type0); reg = ioread32(addr); @@ -564,6 +651,8 @@ static int aspeed_gpio_set_type(struct irq_data *d, unsigned int type) reg = (reg & ~bit) | type2; iowrite32(reg, addr); + if (copro) + aspeed_gpio_copro_release(gpio, offset); spin_unlock_irqrestore(&gpio->lock, flags); irq_set_handler_locked(d, handler); @@ -658,11 +747,14 @@ static int aspeed_gpio_reset_tolerance(struct gpio_chip *chip, struct aspeed_gpio *gpio = gpiochip_get_data(chip); unsigned long flags; void __iomem *treg; + bool copro; u32 val; treg = bank_reg(gpio, to_bank(offset), reg_tolerance); spin_lock_irqsave(&gpio->lock, flags); + copro = aspeed_gpio_copro_request(gpio, offset); + val = readl(treg); if (enable) @@ -671,6 +763,9 @@ static int aspeed_gpio_reset_tolerance(struct gpio_chip *chip, val &= ~GPIO_BIT(offset); writel(val, treg); + + if (copro) + aspeed_gpio_copro_release(gpio, offset); spin_unlock_irqrestore(&gpio->lock, flags); return 0; @@ -766,6 +861,9 @@ static void configure_timer(struct aspeed_gpio *gpio, unsigned int offset, void __iomem *addr; u32 val; + /* Note: Debounce timer isn't under control of the command + * source registers, so no need to sync with the coprocessor + */ addr = bank_reg(gpio, bank, reg_debounce_sel1); val = ioread32(addr); iowrite32((val & ~mask) | GPIO_SET_DEBOUNCE1(timer, offset), addr); @@ -912,6 +1010,111 @@ static int aspeed_gpio_set_config(struct gpio_chip *chip, unsigned int offset, return -ENOTSUPP; } +/** + * aspeed_gpio_copro_set_ops - Sets the callbacks used for handhsaking with + * the coprocessor for shared GPIO banks + * @ops: The callbacks + * @data: Pointer passed back to the callbacks + */ +int aspeed_gpio_copro_set_ops(const struct aspeed_gpio_copro_ops *ops, void *data) +{ + copro_data = data; + copro_ops = ops; + + return 0; +} +EXPORT_SYMBOL_GPL(aspeed_gpio_copro_set_ops); + +/** + * aspeed_gpio_copro_grab_gpio - Mark a GPIO used by the coprocessor. The entire + * bank gets marked and any access from the ARM will + * result in handshaking via callbacks. + * @desc: The GPIO to be marked + * @vreg_offset: If non-NULL, returns the value register offset in the GPIO space + * @dreg_offset: If non-NULL, returns the data latch register offset in the GPIO space + * @bit: If non-NULL, returns the bit number of the GPIO in the registers + */ +int aspeed_gpio_copro_grab_gpio(struct gpio_desc *desc, + u16 *vreg_offset, u16 *dreg_offset, u8 *bit) +{ + struct gpio_chip *chip = gpiod_to_chip(desc); + struct aspeed_gpio *gpio = gpiochip_get_data(chip); + int rc = 0, bindex, offset = gpio_chip_hwgpio(desc); + const struct aspeed_gpio_bank *bank = to_bank(offset); + unsigned long flags; + + if (!gpio->cf_copro_bankmap) + gpio->cf_copro_bankmap = kzalloc(gpio->config->nr_gpios >> 3, GFP_KERNEL); + if (!gpio->cf_copro_bankmap) + return -ENOMEM; + if (offset < 0 || offset > gpio->config->nr_gpios) + return -EINVAL; + bindex = offset >> 3; + + spin_lock_irqsave(&gpio->lock, flags); + + /* Sanity check, this shouldn't happen */ + if (gpio->cf_copro_bankmap[bindex] == 0xff) { + rc = -EIO; + goto bail; + } + gpio->cf_copro_bankmap[bindex]++; + + /* Switch command source */ + if (gpio->cf_copro_bankmap[bindex] == 1) + aspeed_gpio_change_cmd_source(gpio, bank, bindex, + GPIO_CMDSRC_COLDFIRE); + + if (vreg_offset) + *vreg_offset = bank->val_regs; + if (dreg_offset) + *dreg_offset = bank->rdata_reg; + if (bit) + *bit = GPIO_OFFSET(offset); + bail: + spin_unlock_irqrestore(&gpio->lock, flags); + return rc; +} +EXPORT_SYMBOL_GPL(aspeed_gpio_copro_grab_gpio); + +/** + * aspeed_gpio_copro_release_gpio - Unmark a GPIO used by the coprocessor. + * @desc: The GPIO to be marked + */ +int aspeed_gpio_copro_release_gpio(struct gpio_desc *desc) +{ + struct gpio_chip *chip = gpiod_to_chip(desc); + struct aspeed_gpio *gpio = gpiochip_get_data(chip); + int rc = 0, bindex, offset = gpio_chip_hwgpio(desc); + const struct aspeed_gpio_bank *bank = to_bank(offset); + unsigned long flags; + + if (!gpio->cf_copro_bankmap) + return -ENXIO; + + if (offset < 0 || offset > gpio->config->nr_gpios) + return -EINVAL; + bindex = offset >> 3; + + spin_lock_irqsave(&gpio->lock, flags); + + /* Sanity check, this shouldn't happen */ + if (gpio->cf_copro_bankmap[bindex] == 0) { + rc = -EIO; + goto bail; + } + gpio->cf_copro_bankmap[bindex]--; + + /* Switch command source */ + if (gpio->cf_copro_bankmap[bindex] == 0) + aspeed_gpio_change_cmd_source(gpio, bank, bindex, + GPIO_CMDSRC_ARM); + bail: + spin_unlock_irqrestore(&gpio->lock, flags); + return rc; +} +EXPORT_SYMBOL_GPL(aspeed_gpio_copro_release_gpio); + /* * Any banks not specified in a struct aspeed_bank_props array are assumed to * have the properties: @@ -1002,10 +1205,18 @@ static int __init aspeed_gpio_probe(struct platform_device *pdev) if (!gpio->dcache) return -ENOMEM; - /* Populate it with initial values read from the HW */ + /* + * Populate it with initial values read from the HW and switch + * all command sources to the ARM by default + */ for (i = 0; i < banks; i++) { - void __iomem *addr = bank_reg(gpio, &aspeed_gpio_banks[i], reg_rdata); + const struct aspeed_gpio_bank *bank = &aspeed_gpio_banks[i]; + void __iomem *addr = bank_reg(gpio, bank, reg_rdata); gpio->dcache[i] = ioread32(addr); + aspeed_gpio_change_cmd_source(gpio, bank, 0, GPIO_CMDSRC_ARM); + aspeed_gpio_change_cmd_source(gpio, bank, 1, GPIO_CMDSRC_ARM); + aspeed_gpio_change_cmd_source(gpio, bank, 2, GPIO_CMDSRC_ARM); + aspeed_gpio_change_cmd_source(gpio, bank, 3, GPIO_CMDSRC_ARM); } rc = devm_gpiochip_add_data(&pdev->dev, &gpio->chip, gpio); diff --git a/include/linux/gpio/aspeed.h b/include/linux/gpio/aspeed.h new file mode 100644 index 000000000000..1bfb3cdc86d0 --- /dev/null +++ b/include/linux/gpio/aspeed.h @@ -0,0 +1,15 @@ +#ifndef __GPIO_ASPEED_H +#define __GPIO_ASPEED_H + +struct aspeed_gpio_copro_ops { + int (*request_access)(void *data); + int (*release_access)(void *data); +}; + +int aspeed_gpio_copro_grab_gpio(struct gpio_desc *desc, + u16 *vreg_offset, u16 *dreg_offset, u8 *bit); +int aspeed_gpio_copro_release_gpio(struct gpio_desc *desc); +int aspeed_gpio_copro_set_ops(const struct aspeed_gpio_copro_ops *ops, void *data); + + +#endif /* __GPIO_ASPEED_H */ -- cgit v1.2.3 From 62f77ad0969594ee428043523bf28329df191b39 Mon Sep 17 00:00:00 2001 From: Ville Syrjälä Date: Tue, 26 Jun 2018 22:47:07 +0300 Subject: drm: Add drm_plane_mask() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add drm_plane_mask() which returns the 1< Link: https://patchwork.freedesktop.org/patch/msgid/20180626194716.12522-1-ville.syrjala@linux.intel.com Reviewed-by: Rodrigo Vivi --- drivers/gpu/drm/drm_atomic.c | 4 ++-- drivers/gpu/drm/drm_framebuffer.c | 2 +- drivers/gpu/drm/drm_simple_kms_helper.c | 2 +- include/drm/drm_plane.h | 14 ++++++++++++-- 4 files changed, 16 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c index 178842380f75..684c9d3a1d6c 100644 --- a/drivers/gpu/drm/drm_atomic.c +++ b/drivers/gpu/drm/drm_atomic.c @@ -1581,7 +1581,7 @@ drm_atomic_set_crtc_for_plane(struct drm_plane_state *plane_state, if (WARN_ON(IS_ERR(crtc_state))) return PTR_ERR(crtc_state); - crtc_state->plane_mask &= ~(1 << drm_plane_index(plane)); + crtc_state->plane_mask &= ~drm_plane_mask(plane); } plane_state->crtc = crtc; @@ -1591,7 +1591,7 @@ drm_atomic_set_crtc_for_plane(struct drm_plane_state *plane_state, crtc); if (IS_ERR(crtc_state)) return PTR_ERR(crtc_state); - crtc_state->plane_mask |= (1 << drm_plane_index(plane)); + crtc_state->plane_mask |= drm_plane_mask(plane); } if (crtc) diff --git a/drivers/gpu/drm/drm_framebuffer.c b/drivers/gpu/drm/drm_framebuffer.c index ed90974a452a..781af1d42d76 100644 --- a/drivers/gpu/drm/drm_framebuffer.c +++ b/drivers/gpu/drm/drm_framebuffer.c @@ -847,7 +847,7 @@ retry: if (ret) goto unlock; - plane_mask |= BIT(drm_plane_index(plane)); + plane_mask |= drm_plane_mask(plane); } /* This list is only filled when disable_crtcs is set. */ diff --git a/drivers/gpu/drm/drm_simple_kms_helper.c b/drivers/gpu/drm/drm_simple_kms_helper.c index 7a00455ca568..9d87961da1db 100644 --- a/drivers/gpu/drm/drm_simple_kms_helper.c +++ b/drivers/gpu/drm/drm_simple_kms_helper.c @@ -52,7 +52,7 @@ static int drm_simple_kms_crtc_check(struct drm_crtc *crtc, struct drm_crtc_state *state) { bool has_primary = state->plane_mask & - BIT(drm_plane_index(crtc->primary)); + drm_plane_mask(crtc->primary); /* We always want to have an active plane with an active CRTC */ if (has_primary != state->enable) diff --git a/include/drm/drm_plane.h b/include/drm/drm_plane.h index 7d4d6c7f0afd..cee9dfaaa740 100644 --- a/include/drm/drm_plane.h +++ b/include/drm/drm_plane.h @@ -639,10 +639,20 @@ void drm_plane_cleanup(struct drm_plane *plane); * Given a registered plane, return the index of that plane within a DRM * device's list of planes. */ -static inline unsigned int drm_plane_index(struct drm_plane *plane) +static inline unsigned int drm_plane_index(const struct drm_plane *plane) { return plane->index; } + +/** + * drm_plane_mask - find the mask of a registered plane + * @plane: plane to find mask for + */ +static inline u32 drm_plane_mask(const struct drm_plane *plane) +{ + return 1 << drm_plane_index(plane); +} + struct drm_plane * drm_plane_from_index(struct drm_device *dev, int idx); void drm_plane_force_disable(struct drm_plane *plane); @@ -678,7 +688,7 @@ static inline struct drm_plane *drm_plane_find(struct drm_device *dev, */ #define drm_for_each_plane_mask(plane, dev, plane_mask) \ list_for_each_entry((plane), &(dev)->mode_config.plane_list, head) \ - for_each_if ((plane_mask) & (1 << drm_plane_index(plane))) + for_each_if ((plane_mask) & drm_plane_mask(plane)) /** * drm_for_each_legacy_plane - iterate over all planes for legacy userspace -- cgit v1.2.3 From 6f3be036da5cf6b192966ebea250cf9c8b1fd4a0 Mon Sep 17 00:00:00 2001 From: Ville Syrjälä Date: Tue, 26 Jun 2018 22:47:09 +0300 Subject: drm: Add drm_encoder_mask() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add drm_encoder_mask() which returns the 1< Link: https://patchwork.freedesktop.org/patch/msgid/20180626194716.12522-3-ville.syrjala@linux.intel.com Reviewed-by: Rodrigo Vivi --- drivers/gpu/drm/drm_atomic_helper.c | 10 +++++----- include/drm/drm_encoder.h | 16 ++++++++++++++-- 2 files changed, 19 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index 4f487ceffe68..8008a7de2e10 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -121,7 +121,7 @@ static int handle_conflicting_encoders(struct drm_atomic_state *state, new_encoder = drm_atomic_helper_best_encoder(connector); if (new_encoder) { - if (encoder_mask & (1 << drm_encoder_index(new_encoder))) { + if (encoder_mask & drm_encoder_mask(new_encoder)) { DRM_DEBUG_ATOMIC("[ENCODER:%d:%s] on [CONNECTOR:%d:%s] already assigned\n", new_encoder->base.id, new_encoder->name, connector->base.id, connector->name); @@ -129,7 +129,7 @@ static int handle_conflicting_encoders(struct drm_atomic_state *state, return -EINVAL; } - encoder_mask |= 1 << drm_encoder_index(new_encoder); + encoder_mask |= drm_encoder_mask(new_encoder); } } @@ -155,7 +155,7 @@ static int handle_conflicting_encoders(struct drm_atomic_state *state, continue; encoder = connector->state->best_encoder; - if (!encoder || !(encoder_mask & (1 << drm_encoder_index(encoder)))) + if (!encoder || !(encoder_mask & drm_encoder_mask(encoder))) continue; if (!disable_conflicting_encoders) { @@ -223,7 +223,7 @@ set_best_encoder(struct drm_atomic_state *state, crtc_state = drm_atomic_get_new_crtc_state(state, crtc); crtc_state->encoder_mask &= - ~(1 << drm_encoder_index(conn_state->best_encoder)); + ~drm_encoder_mask(conn_state->best_encoder); } } @@ -234,7 +234,7 @@ set_best_encoder(struct drm_atomic_state *state, crtc_state = drm_atomic_get_new_crtc_state(state, crtc); crtc_state->encoder_mask |= - 1 << drm_encoder_index(encoder); + drm_encoder_mask(encoder); } } diff --git a/include/drm/drm_encoder.h b/include/drm/drm_encoder.h index fb299696c7c4..4f597c0730b4 100644 --- a/include/drm/drm_encoder.h +++ b/include/drm/drm_encoder.h @@ -191,11 +191,23 @@ int drm_encoder_init(struct drm_device *dev, * Given a registered encoder, return the index of that encoder within a DRM * device's list of encoders. */ -static inline unsigned int drm_encoder_index(struct drm_encoder *encoder) +static inline unsigned int drm_encoder_index(const struct drm_encoder *encoder) { return encoder->index; } +/** + * drm_encoder_mask - find the mask of a registered ENCODER + * @encoder: encoder to find mask for + * + * Given a registered encoder, return the mask bit of that encoder for an + * encoder's possible_clones field. + */ +static inline u32 drm_encoder_mask(const struct drm_encoder *encoder) +{ + return 1 << drm_encoder_index(encoder); +} + /** * drm_encoder_crtc_ok - can a given crtc drive a given encoder? * @encoder: encoder to test @@ -241,7 +253,7 @@ void drm_encoder_cleanup(struct drm_encoder *encoder); */ #define drm_for_each_encoder_mask(encoder, dev, encoder_mask) \ list_for_each_entry((encoder), &(dev)->mode_config.encoder_list, head) \ - for_each_if ((encoder_mask) & (1 << drm_encoder_index(encoder))) + for_each_if ((encoder_mask) & drm_encoder_mask(encoder)) /** * drm_for_each_encoder - iterate over all encoders -- cgit v1.2.3 From 737057321f3c2d30b98fa8006b7af1869c32a68b Mon Sep 17 00:00:00 2001 From: Ville Syrjälä Date: Tue, 26 Jun 2018 22:47:10 +0300 Subject: drm: Add drm_connector_mask() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add drm_connector_mask() which returns the 1< Link: https://patchwork.freedesktop.org/patch/msgid/20180626194716.12522-4-ville.syrjala@linux.intel.com Reviewed-by: Rodrigo Vivi --- drivers/gpu/drm/drm_atomic.c | 6 +++--- include/drm/drm_connector.h | 8 +++++++- 2 files changed, 10 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c index 684c9d3a1d6c..d5cefb1cb2a2 100644 --- a/drivers/gpu/drm/drm_atomic.c +++ b/drivers/gpu/drm/drm_atomic.c @@ -1700,7 +1700,7 @@ drm_atomic_set_crtc_for_connector(struct drm_connector_state *conn_state, conn_state->crtc); crtc_state->connector_mask &= - ~(1 << drm_connector_index(conn_state->connector)); + ~drm_connector_mask(conn_state->connector); drm_connector_put(conn_state->connector); conn_state->crtc = NULL; @@ -1712,7 +1712,7 @@ drm_atomic_set_crtc_for_connector(struct drm_connector_state *conn_state, return PTR_ERR(crtc_state); crtc_state->connector_mask |= - 1 << drm_connector_index(conn_state->connector); + drm_connector_mask(conn_state->connector); drm_connector_get(conn_state->connector); conn_state->crtc = crtc; @@ -1839,7 +1839,7 @@ drm_atomic_add_affected_connectors(struct drm_atomic_state *state, */ drm_connector_list_iter_begin(state->dev, &conn_iter); drm_for_each_connector_iter(connector, &conn_iter) { - if (!(crtc_state->connector_mask & (1 << drm_connector_index(connector)))) + if (!(crtc_state->connector_mask & drm_connector_mask(connector))) continue; conn_state = drm_atomic_get_connector_state(state, connector); diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h index 14ab58ade87f..bf0f0f0786d3 100644 --- a/include/drm/drm_connector.h +++ b/include/drm/drm_connector.h @@ -1030,11 +1030,17 @@ int drm_mode_connector_attach_encoder(struct drm_connector *connector, struct drm_encoder *encoder); void drm_connector_cleanup(struct drm_connector *connector); -static inline unsigned drm_connector_index(struct drm_connector *connector) + +static inline unsigned int drm_connector_index(const struct drm_connector *connector) { return connector->index; } +static inline u32 drm_connector_mask(const struct drm_connector *connector) +{ + return 1 << connector->index; +} + /** * drm_connector_lookup - lookup connector object * @dev: DRM device -- cgit v1.2.3 From 60a866685006bae0c3db20e4bae31887eb452ff1 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 26 Jun 2018 06:49:08 -0300 Subject: gpio.h: fix location of gpio legacy documentation The location of this doc file was moved. Change its reference accordingly. Fixes: 7ee2c13080c9 ("Documentation: gpio: Move legacy documentation to driver-api") Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Jonathan Corbet --- include/linux/gpio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/gpio.h b/include/linux/gpio.h index 91ed23468530..39745b8bdd65 100644 --- a/include/linux/gpio.h +++ b/include/linux/gpio.h @@ -14,7 +14,7 @@ #include -/* see Documentation/gpio/gpio-legacy.txt */ +/* see Documentation/driver-api/gpio/legacy.rst */ /* make these flag values available regardless of GPIO kconfig options */ #define GPIOF_DIR_OUT (0 << 0) -- cgit v1.2.3 From 317f89712d7aa4acc2d93df27b753d4489826cc5 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Fri, 22 Jun 2018 14:52:51 -0700 Subject: scsi: target: Rename transport_init_session() into transport_alloc_session() Signed-off-by: Bart Van Assche Reviewed-by: Mike Christie Cc: Mike Christie Cc: Hannes Reinecke Cc: Christoph Hellwig Signed-off-by: Martin K. Petersen --- drivers/target/iscsi/iscsi_target_login.c | 2 +- drivers/target/target_core_transport.c | 26 ++++++++++++++++++++++---- include/target/target_core_fabric.h | 2 +- 3 files changed, 24 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c index 99501785cdc1..923b1a9fc3dc 100644 --- a/drivers/target/iscsi/iscsi_target_login.c +++ b/drivers/target/iscsi/iscsi_target_login.c @@ -369,7 +369,7 @@ static int iscsi_login_zero_tsih_s1( return -ENOMEM; } - sess->se_sess = transport_init_session(TARGET_PROT_NORMAL); + sess->se_sess = transport_alloc_session(TARGET_PROT_NORMAL); if (IS_ERR(sess->se_sess)) { iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR, ISCSI_LOGIN_STATUS_NO_RESOURCES); diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 5e8329c5ddd0..880e07f40099 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -224,7 +224,11 @@ void transport_subsystem_check_init(void) sub_api_initialized = 1; } -struct se_session *transport_init_session(enum target_prot_op sup_prot_ops) +/** + * transport_alloc_session - allocate a session object and initialize it + * @sup_prot_ops: bitmask that defines which T10-PI modes are supported. + */ +struct se_session *transport_alloc_session(enum target_prot_op sup_prot_ops) { struct se_session *se_sess; @@ -243,8 +247,15 @@ struct se_session *transport_init_session(enum target_prot_op sup_prot_ops) return se_sess; } -EXPORT_SYMBOL(transport_init_session); +EXPORT_SYMBOL(transport_alloc_session); +/** + * transport_alloc_session_tags - allocate target driver private data + * @se_sess: Session pointer. + * @tag_num: Maximum number of in-flight commands between initiator and target. + * @tag_size: Size in bytes of the private data a target driver associates with + * each command. + */ int transport_alloc_session_tags(struct se_session *se_sess, unsigned int tag_num, unsigned int tag_size) { @@ -274,6 +285,13 @@ int transport_alloc_session_tags(struct se_session *se_sess, } EXPORT_SYMBOL(transport_alloc_session_tags); +/** + * transport_init_session_tags - allocate a session and target driver private data + * @tag_num: Maximum number of in-flight commands between initiator and target. + * @tag_size: Size in bytes of the private data a target driver associates with + * each command. + * @sup_prot_ops: bitmask that defines which T10-PI modes are supported. + */ struct se_session *transport_init_session_tags(unsigned int tag_num, unsigned int tag_size, enum target_prot_op sup_prot_ops) @@ -292,7 +310,7 @@ struct se_session *transport_init_session_tags(unsigned int tag_num, return ERR_PTR(-EINVAL); } - se_sess = transport_init_session(sup_prot_ops); + se_sess = transport_alloc_session(sup_prot_ops); if (IS_ERR(se_sess)) return se_sess; @@ -402,7 +420,7 @@ target_alloc_session(struct se_portal_group *tpg, if (tag_num != 0) sess = transport_init_session_tags(tag_num, tag_size, prot_op); else - sess = transport_init_session(prot_op); + sess = transport_alloc_session(prot_op); if (IS_ERR(sess)) return sess; diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h index b297aa0d9651..010df9d5b977 100644 --- a/include/target/target_core_fabric.h +++ b/include/target/target_core_fabric.h @@ -115,7 +115,7 @@ struct se_session *target_alloc_session(struct se_portal_group *, int (*callback)(struct se_portal_group *, struct se_session *, void *)); -struct se_session *transport_init_session(enum target_prot_op); +struct se_session *transport_alloc_session(enum target_prot_op); int transport_alloc_session_tags(struct se_session *, unsigned int, unsigned int); struct se_session *transport_init_session_tags(unsigned int, unsigned int, -- cgit v1.2.3 From d1bff07f387c05cfaba1ea505fc2ee5eac6b2c21 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Fri, 22 Jun 2018 14:52:52 -0700 Subject: scsi: target: Introduce transport_init_session() Other than initializing xcopy_pt_sess.sess_wait_list, this patch does not change any functionality. Signed-off-by: Bart Van Assche Reviewed-by: Mike Christie Cc: Mike Christie Cc: Christoph Hellwig Cc: Hannes Reinecke Signed-off-by: Martin K. Petersen --- drivers/target/target_core_transport.c | 22 +++++++++++++++++----- drivers/target/target_core_xcopy.c | 5 +---- include/target/target_core_fabric.h | 1 + 3 files changed, 19 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 880e07f40099..595b2f12ca6a 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -224,6 +224,22 @@ void transport_subsystem_check_init(void) sub_api_initialized = 1; } +/** + * transport_init_session - initialize a session object + * @se_sess: Session object pointer. + * + * The caller must have zero-initialized @se_sess before calling this function. + */ +void transport_init_session(struct se_session *se_sess) +{ + INIT_LIST_HEAD(&se_sess->sess_list); + INIT_LIST_HEAD(&se_sess->sess_acl_list); + INIT_LIST_HEAD(&se_sess->sess_cmd_list); + INIT_LIST_HEAD(&se_sess->sess_wait_list); + spin_lock_init(&se_sess->sess_cmd_lock); +} +EXPORT_SYMBOL(transport_init_session); + /** * transport_alloc_session - allocate a session object and initialize it * @sup_prot_ops: bitmask that defines which T10-PI modes are supported. @@ -238,11 +254,7 @@ struct se_session *transport_alloc_session(enum target_prot_op sup_prot_ops) " se_sess_cache\n"); return ERR_PTR(-ENOMEM); } - INIT_LIST_HEAD(&se_sess->sess_list); - INIT_LIST_HEAD(&se_sess->sess_acl_list); - INIT_LIST_HEAD(&se_sess->sess_cmd_list); - INIT_LIST_HEAD(&se_sess->sess_wait_list); - spin_lock_init(&se_sess->sess_cmd_lock); + transport_init_session(se_sess); se_sess->sup_prot_ops = sup_prot_ops; return se_sess; diff --git a/drivers/target/target_core_xcopy.c b/drivers/target/target_core_xcopy.c index 9ee89e00cd77..2718a933c0c6 100644 --- a/drivers/target/target_core_xcopy.c +++ b/drivers/target/target_core_xcopy.c @@ -497,10 +497,7 @@ int target_xcopy_setup_pt(void) INIT_LIST_HEAD(&xcopy_pt_nacl.acl_list); INIT_LIST_HEAD(&xcopy_pt_nacl.acl_sess_list); memset(&xcopy_pt_sess, 0, sizeof(struct se_session)); - INIT_LIST_HEAD(&xcopy_pt_sess.sess_list); - INIT_LIST_HEAD(&xcopy_pt_sess.sess_acl_list); - INIT_LIST_HEAD(&xcopy_pt_sess.sess_cmd_list); - spin_lock_init(&xcopy_pt_sess.sess_cmd_lock); + transport_init_session(&xcopy_pt_sess); xcopy_pt_nacl.se_tpg = &xcopy_pt_tpg; xcopy_pt_nacl.nacl_sess = &xcopy_pt_sess; diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h index 010df9d5b977..84a681b6e5ca 100644 --- a/include/target/target_core_fabric.h +++ b/include/target/target_core_fabric.h @@ -115,6 +115,7 @@ struct se_session *target_alloc_session(struct se_portal_group *, int (*callback)(struct se_portal_group *, struct se_session *, void *)); +void transport_init_session(struct se_session *); struct se_session *transport_alloc_session(enum target_prot_op); int transport_alloc_session_tags(struct se_session *, unsigned int, unsigned int); -- cgit v1.2.3 From 00d909a10710a3416272d4179adf3837b9a9f3c2 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Fri, 22 Jun 2018 14:52:53 -0700 Subject: scsi: target: Make the session shutdown code also wait for commands that are being aborted Target drivers must call target_sess_cmd_list_set_waiting() and target_wait_for_sess_cmds() before freeing a session. Since freeing a session is only safe after all commands that are associated with a session have finished, make target_wait_for_sess_cmds() also wait for commands that are being aborted. Instead of setting a flag in each pending command from target_sess_cmd_list_set_waiting() and waiting in target_wait_for_sess_cmds() on a per-command completion, only set a per-session flag in the former function and wait on a per-session completion in the latter function. This change is safe because once a SCSI initiator system has submitted a command a target system is always allowed to execute it to completion. See also commit 0f4a943168f3 ("target: Fix remote-port TMR ABORT + se_cmd fabric stop"). This patch is based on the following two patches: * Bart Van Assche, target: Simplify session shutdown code, February 19, 2015 (https://github.com/bvanassche/linux/commit/8df5463d7d7619f2f1b70cfe5172eaef0aa52815). * Christoph Hellwig, target: Rework session shutdown code, December 7, 2015 (http://thread.gmane.org/gmane.linux.scsi.target.devel/10695). Signed-off-by: Bart Van Assche Reviewed-by: Mike Christie Cc: Hannes Reinecke Cc: Christoph Hellwig Cc: Sagi Grimberg Signed-off-by: Martin K. Petersen --- drivers/target/target_core_tmr.c | 5 +-- drivers/target/target_core_transport.c | 77 ++++++++++------------------------ include/target/target_core_base.h | 3 +- 3 files changed, 24 insertions(+), 61 deletions(-) (limited to 'include') diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c index 9c7bc1ca341a..da8125dd3a4c 100644 --- a/drivers/target/target_core_tmr.c +++ b/drivers/target/target_core_tmr.c @@ -142,7 +142,7 @@ static bool __target_check_io_state(struct se_cmd *se_cmd, return false; } } - if (sess->sess_tearing_down || se_cmd->cmd_wait_set) { + if (sess->sess_tearing_down) { pr_debug("Attempted to abort io tag: %llu already shutdown," " skipping\n", se_cmd->tag); spin_unlock(&se_cmd->t_state_lock); @@ -187,7 +187,6 @@ void core_tmr_abort_task( if (!__target_check_io_state(se_cmd, se_sess, 0)) continue; - list_del_init(&se_cmd->se_cmd_list); spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags); cancel_work_sync(&se_cmd->work); @@ -259,7 +258,7 @@ static void core_tmr_drain_tmr_list( spin_unlock(&sess->sess_cmd_lock); continue; } - if (sess->sess_tearing_down || cmd->cmd_wait_set) { + if (sess->sess_tearing_down) { spin_unlock(&cmd->t_state_lock); spin_unlock(&sess->sess_cmd_lock); continue; diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 595b2f12ca6a..087dddfc5c35 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -235,8 +235,8 @@ void transport_init_session(struct se_session *se_sess) INIT_LIST_HEAD(&se_sess->sess_list); INIT_LIST_HEAD(&se_sess->sess_acl_list); INIT_LIST_HEAD(&se_sess->sess_cmd_list); - INIT_LIST_HEAD(&se_sess->sess_wait_list); spin_lock_init(&se_sess->sess_cmd_lock); + init_waitqueue_head(&se_sess->cmd_list_wq); } EXPORT_SYMBOL(transport_init_session); @@ -2728,13 +2728,15 @@ static void target_release_cmd_kref(struct kref *kref) if (se_sess) { spin_lock_irqsave(&se_sess->sess_cmd_lock, flags); list_del_init(&se_cmd->se_cmd_list); + if (list_empty(&se_sess->sess_cmd_list)) + wake_up(&se_sess->cmd_list_wq); spin_lock(&se_cmd->t_state_lock); fabric_stop = (se_cmd->transport_state & CMD_T_FABRIC_STOP) && (se_cmd->transport_state & CMD_T_ABORTED); spin_unlock(&se_cmd->t_state_lock); - if (se_cmd->cmd_wait_set || fabric_stop) { + if (fabric_stop) { spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags); target_free_cmd_mem(se_cmd); complete(&se_cmd->cmd_wait_comp); @@ -2863,78 +2865,41 @@ void target_show_cmd(const char *pfx, struct se_cmd *cmd) EXPORT_SYMBOL(target_show_cmd); /** - * target_sess_cmd_list_set_waiting - Flag all commands in - * sess_cmd_list to complete cmd_wait_comp. Set - * sess_tearing_down so no more commands are queued. + * target_sess_cmd_list_set_waiting - Set sess_tearing_down so no new commands are queued. * @se_sess: session to flag */ void target_sess_cmd_list_set_waiting(struct se_session *se_sess) { - struct se_cmd *se_cmd, *tmp_cmd; unsigned long flags; - int rc; spin_lock_irqsave(&se_sess->sess_cmd_lock, flags); - if (se_sess->sess_tearing_down) { - spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags); - return; - } se_sess->sess_tearing_down = 1; - list_splice_init(&se_sess->sess_cmd_list, &se_sess->sess_wait_list); - - list_for_each_entry_safe(se_cmd, tmp_cmd, - &se_sess->sess_wait_list, se_cmd_list) { - rc = kref_get_unless_zero(&se_cmd->cmd_kref); - if (rc) { - se_cmd->cmd_wait_set = 1; - spin_lock(&se_cmd->t_state_lock); - se_cmd->transport_state |= CMD_T_FABRIC_STOP; - spin_unlock(&se_cmd->t_state_lock); - } else - list_del_init(&se_cmd->se_cmd_list); - } - spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags); } EXPORT_SYMBOL(target_sess_cmd_list_set_waiting); /** - * target_wait_for_sess_cmds - Wait for outstanding descriptors + * target_wait_for_sess_cmds - Wait for outstanding commands * @se_sess: session to wait for active I/O */ void target_wait_for_sess_cmds(struct se_session *se_sess) { - struct se_cmd *se_cmd, *tmp_cmd; - unsigned long flags; - bool tas; - - list_for_each_entry_safe(se_cmd, tmp_cmd, - &se_sess->sess_wait_list, se_cmd_list) { - pr_debug("Waiting for se_cmd: %p t_state: %d, fabric state:" - " %d\n", se_cmd, se_cmd->t_state, - se_cmd->se_tfo->get_cmd_state(se_cmd)); - - spin_lock_irqsave(&se_cmd->t_state_lock, flags); - tas = (se_cmd->transport_state & CMD_T_TAS); - spin_unlock_irqrestore(&se_cmd->t_state_lock, flags); - - if (!target_put_sess_cmd(se_cmd)) { - if (tas) - target_put_sess_cmd(se_cmd); - } - - wait_for_completion(&se_cmd->cmd_wait_comp); - pr_debug("After cmd_wait_comp: se_cmd: %p t_state: %d" - " fabric state: %d\n", se_cmd, se_cmd->t_state, - se_cmd->se_tfo->get_cmd_state(se_cmd)); - - se_cmd->se_tfo->release_cmd(se_cmd); - } - - spin_lock_irqsave(&se_sess->sess_cmd_lock, flags); - WARN_ON(!list_empty(&se_sess->sess_cmd_list)); - spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags); + struct se_cmd *cmd; + int ret; + WARN_ON_ONCE(!se_sess->sess_tearing_down); + + spin_lock_irq(&se_sess->sess_cmd_lock); + do { + ret = wait_event_interruptible_lock_irq_timeout( + se_sess->cmd_list_wq, + list_empty(&se_sess->sess_cmd_list), + se_sess->sess_cmd_lock, 180 * HZ); + list_for_each_entry(cmd, &se_sess->sess_cmd_list, se_cmd_list) + target_show_cmd("session shutdown: still waiting for ", + cmd); + } while (ret <= 0); + spin_unlock_irq(&se_sess->sess_cmd_lock); } EXPORT_SYMBOL(target_wait_for_sess_cmds); diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index 448f291125c2..906c1fc485e4 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -443,7 +443,6 @@ struct se_cmd { u8 scsi_asc; u8 scsi_ascq; u16 scsi_sense_length; - unsigned cmd_wait_set:1; unsigned unknown_data_length:1; bool state_active:1; u64 tag; /* SAM command identifier aka task tag */ @@ -606,8 +605,8 @@ struct se_session { struct list_head sess_list; struct list_head sess_acl_list; struct list_head sess_cmd_list; - struct list_head sess_wait_list; spinlock_t sess_cmd_lock; + wait_queue_head_t cmd_list_wq; void *sess_cmd_map; struct sbitmap_queue sess_tag_pool; }; -- cgit v1.2.3 From 7b2cc7dc0dbf5da9cf16ffcf1ca8e904ab574ff5 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Fri, 22 Jun 2018 14:52:59 -0700 Subject: scsi: target: Simplify the code for waiting for command completion Instead of embedding the completion that is used for waiting for command completion in struct se_cmd, let the context that waits for command completion allocate it. This makes it possible to have a single code path for non-aborted and aborted commands in target_release_cmd_kref() and avoids that transport_generic_free_cmd() has to call cmd->se_tfo->release_cmd() directly. This patch does not change any functionality. Note: transport_generic_free_cmd() only waits until the se_cmd reference count has reached zero after it has set both CMD_T_FABRIC_STOP and CMD_T_ABORTED. Signed-off-by: Bart Van Assche Reviewed-by: Mike Christie Cc: Hannes Reinecke Cc: Christoph Hellwig Signed-off-by: Martin K. Petersen --- drivers/target/target_core_transport.c | 24 ++++++++---------------- include/target/target_core_base.h | 2 +- 2 files changed, 9 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index ebd54fc1f13a..cb48dbc2c9ba 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -1309,7 +1309,7 @@ void transport_init_se_cmd( INIT_LIST_HEAD(&cmd->se_cmd_list); INIT_LIST_HEAD(&cmd->state_list); init_completion(&cmd->t_transport_stop_comp); - init_completion(&cmd->cmd_wait_comp); + cmd->compl = NULL; spin_lock_init(&cmd->t_state_lock); INIT_WORK(&cmd->work, NULL); kref_init(&cmd->cmd_kref); @@ -2658,6 +2658,7 @@ static void target_wait_free_cmd(struct se_cmd *cmd, bool *aborted, bool *tas) */ int transport_generic_free_cmd(struct se_cmd *cmd, int wait_for_tasks) { + DECLARE_COMPLETION_ONSTACK(compl); int ret = 0; bool aborted = false, tas = false; @@ -2676,12 +2677,13 @@ int transport_generic_free_cmd(struct se_cmd *cmd, int wait_for_tasks) if (cmd->se_lun) transport_lun_remove_cmd(cmd); } + if (aborted) + cmd->compl = &compl; if (!aborted || tas) ret = target_put_sess_cmd(cmd); if (aborted) { pr_debug("Detected CMD_T_ABORTED for ITT: %llu\n", cmd->tag); - wait_for_completion(&cmd->cmd_wait_comp); - cmd->se_tfo->release_cmd(cmd); + wait_for_completion(&compl); ret = 1; } return ret; @@ -2742,31 +2744,21 @@ static void target_release_cmd_kref(struct kref *kref) { struct se_cmd *se_cmd = container_of(kref, struct se_cmd, cmd_kref); struct se_session *se_sess = se_cmd->se_sess; + struct completion *compl = se_cmd->compl; unsigned long flags; - bool fabric_stop; if (se_sess) { spin_lock_irqsave(&se_sess->sess_cmd_lock, flags); list_del_init(&se_cmd->se_cmd_list); if (list_empty(&se_sess->sess_cmd_list)) wake_up(&se_sess->cmd_list_wq); - - spin_lock(&se_cmd->t_state_lock); - fabric_stop = (se_cmd->transport_state & CMD_T_FABRIC_STOP) && - (se_cmd->transport_state & CMD_T_ABORTED); - spin_unlock(&se_cmd->t_state_lock); - - if (fabric_stop) { - spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags); - target_free_cmd_mem(se_cmd); - complete(&se_cmd->cmd_wait_comp); - return; - } spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags); } target_free_cmd_mem(se_cmd); se_cmd->se_tfo->release_cmd(se_cmd); + if (compl) + complete(compl); } /** diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index 906c1fc485e4..ca59e065c1fd 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -475,7 +475,7 @@ struct se_cmd { struct se_session *se_sess; struct se_tmr_req *se_tmr_req; struct list_head se_cmd_list; - struct completion cmd_wait_comp; + struct completion *compl; const struct target_core_fabric_ops *se_tfo; sense_reason_t (*execute_cmd)(struct se_cmd *); sense_reason_t (*transport_complete_callback)(struct se_cmd *, bool, int *); -- cgit v1.2.3 From aa090eabcb341b0c023e802884235c29598df1e5 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Fri, 22 Jun 2018 14:53:02 -0700 Subject: scsi: target: Remove second argument from fabric_make_tpg() Since most target drivers do not use the second fabric_make_tpg() argument ("group") and since it is trivial to derive the group pointer from the wwn pointer, do not pass the group pointer to fabric_make_tpg(). Signed-off-by: Bart Van Assche Reviewed-by: Mike Christie Cc: Felipe Balbi Cc: Hannes Reinecke Cc: Christoph Hellwig Signed-off-by: Martin K. Petersen --- drivers/infiniband/ulp/srpt/ib_srpt.c | 2 -- drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c | 1 - drivers/scsi/qla2xxx/tcm_qla2xxx.c | 12 ++++-------- drivers/target/iscsi/iscsi_target_configfs.c | 6 ++---- drivers/target/loopback/tcm_loop.c | 6 ++---- drivers/target/sbp/sbp_target.c | 6 ++---- drivers/target/target_core_fabric_configfs.c | 2 +- drivers/target/tcm_fc/tfc_conf.c | 5 +---- drivers/usb/gadget/function/f_tcm.c | 8 +++----- drivers/vhost/scsi.c | 4 +--- drivers/xen/xen-scsiback.c | 4 +--- include/target/target_core_fabric.h | 2 +- 12 files changed, 18 insertions(+), 40 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c index 3081c629a7f7..07b3e1c583bd 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.c +++ b/drivers/infiniband/ulp/srpt/ib_srpt.c @@ -3597,11 +3597,9 @@ static struct configfs_attribute *srpt_tpg_attrs[] = { /** * srpt_make_tpg - configfs callback invoked for mkdir /sys/kernel/config/target/$driver/$port/$tpg * @wwn: Corresponds to $driver/$port. - * @group: Not used. * @name: $tpg. */ static struct se_portal_group *srpt_make_tpg(struct se_wwn *wwn, - struct config_group *group, const char *name) { struct srpt_port *sport = wwn->priv; diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c index c3a76af9f5fa..fdda04e5cf94 100644 --- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c +++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c @@ -3928,7 +3928,6 @@ static void ibmvscsis_drop_tport(struct se_wwn *wwn) } static struct se_portal_group *ibmvscsis_make_tpg(struct se_wwn *wwn, - struct config_group *group, const char *name) { struct ibmvscsis_tport *tport = diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c index 7732e9336d43..cfb5d6067f9f 100644 --- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c +++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c @@ -1049,10 +1049,8 @@ static struct configfs_attribute *tcm_qla2xxx_tpg_attrs[] = { NULL, }; -static struct se_portal_group *tcm_qla2xxx_make_tpg( - struct se_wwn *wwn, - struct config_group *group, - const char *name) +static struct se_portal_group *tcm_qla2xxx_make_tpg(struct se_wwn *wwn, + const char *name) { struct tcm_qla2xxx_lport *lport = container_of(wwn, struct tcm_qla2xxx_lport, lport_wwn); @@ -1171,10 +1169,8 @@ static struct configfs_attribute *tcm_qla2xxx_npiv_tpg_attrs[] = { NULL, }; -static struct se_portal_group *tcm_qla2xxx_npiv_make_tpg( - struct se_wwn *wwn, - struct config_group *group, - const char *name) +static struct se_portal_group *tcm_qla2xxx_npiv_make_tpg(struct se_wwn *wwn, + const char *name) { struct tcm_qla2xxx_lport *lport = container_of(wwn, struct tcm_qla2xxx_lport, lport_wwn); diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c index 0bc346b2c27c..1fcd9bc7189d 100644 --- a/drivers/target/iscsi/iscsi_target_configfs.c +++ b/drivers/target/iscsi/iscsi_target_configfs.c @@ -1090,10 +1090,8 @@ static struct configfs_attribute *lio_target_tpg_attrs[] = { /* Start items for lio_target_tiqn_cit */ -static struct se_portal_group *lio_target_tiqn_addtpg( - struct se_wwn *wwn, - struct config_group *group, - const char *name) +static struct se_portal_group *lio_target_tiqn_addtpg(struct se_wwn *wwn, + const char *name) { struct iscsi_portal_group *tpg; struct iscsi_tiqn *tiqn; diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c index 60d5b918c4ac..4c8a97711291 100644 --- a/drivers/target/loopback/tcm_loop.c +++ b/drivers/target/loopback/tcm_loop.c @@ -983,10 +983,8 @@ static struct configfs_attribute *tcm_loop_tpg_attrs[] = { /* Start items for tcm_loop_naa_cit */ -static struct se_portal_group *tcm_loop_make_naa_tpg( - struct se_wwn *wwn, - struct config_group *group, - const char *name) +static struct se_portal_group *tcm_loop_make_naa_tpg(struct se_wwn *wwn, + const char *name) { struct tcm_loop_hba *tl_hba = container_of(wwn, struct tcm_loop_hba, tl_hba_wwn); diff --git a/drivers/target/sbp/sbp_target.c b/drivers/target/sbp/sbp_target.c index 42b21f2ac8b0..b61b79ac98ff 100644 --- a/drivers/target/sbp/sbp_target.c +++ b/drivers/target/sbp/sbp_target.c @@ -2006,10 +2006,8 @@ static void sbp_pre_unlink_lun( pr_err("unlink LUN: failed to update unit directory\n"); } -static struct se_portal_group *sbp_make_tpg( - struct se_wwn *wwn, - struct config_group *group, - const char *name) +static struct se_portal_group *sbp_make_tpg(struct se_wwn *wwn, + const char *name) { struct sbp_tport *tport = container_of(wwn, struct sbp_tport, tport_wwn); diff --git a/drivers/target/target_core_fabric_configfs.c b/drivers/target/target_core_fabric_configfs.c index e1416b007aa4..1fa436e865f9 100644 --- a/drivers/target/target_core_fabric_configfs.c +++ b/drivers/target/target_core_fabric_configfs.c @@ -841,7 +841,7 @@ static struct config_group *target_fabric_make_tpg( return ERR_PTR(-ENOSYS); } - se_tpg = tf->tf_ops->fabric_make_tpg(wwn, group, name); + se_tpg = tf->tf_ops->fabric_make_tpg(wwn, name); if (!se_tpg || IS_ERR(se_tpg)) return ERR_PTR(-EINVAL); diff --git a/drivers/target/tcm_fc/tfc_conf.c b/drivers/target/tcm_fc/tfc_conf.c index 42ee91123dca..e55c4d537592 100644 --- a/drivers/target/tcm_fc/tfc_conf.c +++ b/drivers/target/tcm_fc/tfc_conf.c @@ -223,10 +223,7 @@ static int ft_init_nodeacl(struct se_node_acl *nacl, const char *name) /* * local_port port_group (tpg) ops. */ -static struct se_portal_group *ft_add_tpg( - struct se_wwn *wwn, - struct config_group *group, - const char *name) +static struct se_portal_group *ft_add_tpg(struct se_wwn *wwn, const char *name) { struct ft_lport_wwn *ft_wwn; struct ft_tpg *tpg; diff --git a/drivers/usb/gadget/function/f_tcm.c b/drivers/usb/gadget/function/f_tcm.c index 5003e857dce7..4f183176b0b4 100644 --- a/drivers/usb/gadget/function/f_tcm.c +++ b/drivers/usb/gadget/function/f_tcm.c @@ -1344,10 +1344,8 @@ static int usbg_init_nodeacl(struct se_node_acl *se_nacl, const char *name) return 0; } -static struct se_portal_group *usbg_make_tpg( - struct se_wwn *wwn, - struct config_group *group, - const char *name) +static struct se_portal_group *usbg_make_tpg(struct se_wwn *wwn, + const char *name) { struct usbg_tport *tport = container_of(wwn, struct usbg_tport, tport_wwn); @@ -1380,7 +1378,7 @@ static struct se_portal_group *usbg_make_tpg( goto unlock_dep; } else { ret = configfs_depend_item_unlocked( - group->cg_subsys, + wwn->wwn_group.cg_subsys, &opts->func_inst.group.cg_item); if (ret) goto unlock_dep; diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index ebaf831285ea..c84a6edd4c25 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -1912,9 +1912,7 @@ static struct configfs_attribute *vhost_scsi_tpg_attrs[] = { }; static struct se_portal_group * -vhost_scsi_make_tpg(struct se_wwn *wwn, - struct config_group *group, - const char *name) +vhost_scsi_make_tpg(struct se_wwn *wwn, const char *name) { struct vhost_scsi_tport *tport = container_of(wwn, struct vhost_scsi_tport, tport_wwn); diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c index 764dd9aa0131..fd77ccfc7d6e 100644 --- a/drivers/xen/xen-scsiback.c +++ b/drivers/xen/xen-scsiback.c @@ -1732,9 +1732,7 @@ static void scsiback_port_unlink(struct se_portal_group *se_tpg, } static struct se_portal_group * -scsiback_make_tpg(struct se_wwn *wwn, - struct config_group *group, - const char *name) +scsiback_make_tpg(struct se_wwn *wwn, const char *name) { struct scsiback_tport *tport = container_of(wwn, struct scsiback_tport, tport_wwn); diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h index 84a681b6e5ca..f61aa716cfe1 100644 --- a/include/target/target_core_fabric.h +++ b/include/target/target_core_fabric.h @@ -79,7 +79,7 @@ struct target_core_fabric_ops { void (*fabric_drop_wwn)(struct se_wwn *); void (*add_wwn_groups)(struct se_wwn *); struct se_portal_group *(*fabric_make_tpg)(struct se_wwn *, - struct config_group *, const char *); + const char *); void (*fabric_drop_tpg)(struct se_portal_group *); int (*fabric_post_link)(struct se_portal_group *, struct se_lun *); -- cgit v1.2.3 From e936a38ac92dd40867ac3b52cfd8f3f70fe717a5 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Fri, 22 Jun 2018 14:53:07 -0700 Subject: scsi: target: Remove se_dev_entry.ua_count se_dev_entry.ua_count is only used to check whether or not se_dev_entry.ua_list is empty. Use list_empty_careful() instead. Checking whether or not ua_list is empty without holding the lock that protects that list is fine because the code that dequeues from that list will check again whether or not that list is empty. Signed-off-by: Bart Van Assche Reviewed-by: Mike Christie Cc: Mike Christie Cc: Christoph Hellwig Cc: Hannes Reinecke Signed-off-by: Martin K. Petersen --- drivers/target/target_core_device.c | 1 - drivers/target/target_core_ua.c | 12 ++---------- include/target/target_core_base.h | 1 - 3 files changed, 2 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index e5c90afb40e6..73675eec740d 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -336,7 +336,6 @@ int core_enable_device_list_for_node( return -ENOMEM; } - atomic_set(&new->ua_count, 0); spin_lock_init(&new->ua_lock); INIT_LIST_HEAD(&new->ua_list); INIT_LIST_HEAD(&new->lun_link); diff --git a/drivers/target/target_core_ua.c b/drivers/target/target_core_ua.c index 9399b38339f9..c8ac242ce888 100644 --- a/drivers/target/target_core_ua.c +++ b/drivers/target/target_core_ua.c @@ -55,7 +55,7 @@ target_scsi3_ua_check(struct se_cmd *cmd) rcu_read_unlock(); return 0; } - if (!atomic_read(&deve->ua_count)) { + if (list_empty_careful(&deve->ua_list)) { rcu_read_unlock(); return 0; } @@ -154,7 +154,6 @@ int core_scsi3_ua_allocate( &deve->ua_list); spin_unlock(&deve->ua_lock); - atomic_inc_mb(&deve->ua_count); return 0; } list_add_tail(&ua->ua_nacl_list, &deve->ua_list); @@ -164,7 +163,6 @@ int core_scsi3_ua_allocate( " 0x%02x, ASCQ: 0x%02x\n", deve->mapped_lun, asc, ascq); - atomic_inc_mb(&deve->ua_count); return 0; } @@ -196,8 +194,6 @@ void core_scsi3_ua_release_all( list_for_each_entry_safe(ua, ua_p, &deve->ua_list, ua_nacl_list) { list_del(&ua->ua_nacl_list); kmem_cache_free(se_ua_cache, ua); - - atomic_dec_mb(&deve->ua_count); } spin_unlock(&deve->ua_lock); } @@ -263,8 +259,6 @@ bool core_scsi3_ua_for_check_condition(struct se_cmd *cmd, u8 *key, u8 *asc, } list_del(&ua->ua_nacl_list); kmem_cache_free(se_ua_cache, ua); - - atomic_dec_mb(&deve->ua_count); } spin_unlock(&deve->ua_lock); rcu_read_unlock(); @@ -304,7 +298,7 @@ int core_scsi3_ua_clear_for_request_sense( rcu_read_unlock(); return -EINVAL; } - if (!atomic_read(&deve->ua_count)) { + if (list_empty_careful(&deve->ua_list)) { rcu_read_unlock(); return -EPERM; } @@ -327,8 +321,6 @@ int core_scsi3_ua_clear_for_request_sense( } list_del(&ua->ua_nacl_list); kmem_cache_free(se_ua_cache, ua); - - atomic_dec_mb(&deve->ua_count); } spin_unlock(&deve->ua_lock); rcu_read_unlock(); diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index ca59e065c1fd..7a4ee7852ca4 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -638,7 +638,6 @@ struct se_dev_entry { atomic_long_t total_cmds; atomic_long_t read_bytes; atomic_long_t write_bytes; - atomic_t ua_count; /* Used for PR SPEC_I_PT=1 and REGISTER_AND_MOVE */ struct kref pr_kref; struct completion pr_comp; -- cgit v1.2.3 From 9cf57731b63e37ed995b46690adc604891a9a28f Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 7 Jun 2018 10:52:03 +0200 Subject: watchdog/softlockup: Replace "watchdog/%u" threads with cpu_stop_work Oleg suggested to replace the "watchdog/%u" threads with cpu_stop_work. That removes one thread per CPU while at the same time fixes softlockup vs SCHED_DEADLINE. But more importantly, it does away with the single smpboot_update_cpumask_percpu_thread() user, which allows cleanups/shrinkage of the smpboot interface. Suggested-by: Oleg Nesterov Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + include/linux/nmi.h | 5 ++ kernel/cpu.c | 5 ++ kernel/watchdog.c | 137 ++++++++++++++++++++------------------------- 4 files changed, 71 insertions(+), 77 deletions(-) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 8796ba387152..4cf06a64bc02 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -164,6 +164,7 @@ enum cpuhp_state { CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE, CPUHP_AP_PERF_POWERPC_CORE_IMC_ONLINE, CPUHP_AP_PERF_POWERPC_THREAD_IMC_ONLINE, + CPUHP_AP_WATCHDOG_ONLINE, CPUHP_AP_WORKQUEUE_ONLINE, CPUHP_AP_RCUTREE_ONLINE, CPUHP_AP_ONLINE_DYN, diff --git a/include/linux/nmi.h b/include/linux/nmi.h index b8d868d23e79..80664bbeca43 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -33,10 +33,15 @@ extern int sysctl_hardlockup_all_cpu_backtrace; #define sysctl_hardlockup_all_cpu_backtrace 0 #endif /* !CONFIG_SMP */ +extern int lockup_detector_online_cpu(unsigned int cpu); +extern int lockup_detector_offline_cpu(unsigned int cpu); + #else /* CONFIG_LOCKUP_DETECTOR */ static inline void lockup_detector_init(void) { } static inline void lockup_detector_soft_poweroff(void) { } static inline void lockup_detector_cleanup(void) { } +#define lockup_detector_online_cpu NULL +#define lockup_detector_offline_cpu NULL #endif /* !CONFIG_LOCKUP_DETECTOR */ #ifdef CONFIG_SOFTLOCKUP_DETECTOR diff --git a/kernel/cpu.c b/kernel/cpu.c index 0db8938fbb23..191097c45fb1 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -1344,6 +1344,11 @@ static struct cpuhp_step cpuhp_hp_states[] = { .startup.single = perf_event_init_cpu, .teardown.single = perf_event_exit_cpu, }, + [CPUHP_AP_WATCHDOG_ONLINE] = { + .name = "lockup_detector:online", + .startup.single = lockup_detector_online_cpu, + .teardown.single = lockup_detector_offline_cpu, + }, [CPUHP_AP_WORKQUEUE_ONLINE] = { .name = "workqueue:online", .startup.single = workqueue_online_cpu, diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 576d18045811..b81f777838d5 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -18,18 +18,14 @@ #include #include #include -#include -#include -#include #include -#include #include #include #include +#include #include #include -#include static DEFINE_MUTEX(watchdog_mutex); @@ -169,11 +165,10 @@ static void lockup_detector_update_enable(void) unsigned int __read_mostly softlockup_panic = CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE; -static bool softlockup_threads_initialized __read_mostly; +static bool softlockup_initialized __read_mostly; static u64 __read_mostly sample_period; static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts); -static DEFINE_PER_CPU(struct task_struct *, softlockup_watchdog); static DEFINE_PER_CPU(struct hrtimer, watchdog_hrtimer); static DEFINE_PER_CPU(bool, softlockup_touch_sync); static DEFINE_PER_CPU(bool, soft_watchdog_warn); @@ -335,6 +330,25 @@ static void watchdog_interrupt_count(void) __this_cpu_inc(hrtimer_interrupts); } +/* + * The watchdog thread function - touches the timestamp. + * + * It only runs once every sample_period seconds (4 seconds by + * default) to reset the softlockup timestamp. If this gets delayed + * for more than 2*watchdog_thresh seconds then the debug-printout + * triggers in watchdog_timer_fn(). + */ +static int softlockup_fn(void *data) +{ + __this_cpu_write(soft_lockup_hrtimer_cnt, + __this_cpu_read(hrtimer_interrupts)); + __touch_watchdog(); + + return 0; +} + +static DEFINE_PER_CPU(struct cpu_stop_work, softlockup_stop_work); + /* watchdog kicker functions */ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) { @@ -350,7 +364,9 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) watchdog_interrupt_count(); /* kick the softlockup detector */ - wake_up_process(__this_cpu_read(softlockup_watchdog)); + stop_one_cpu_nowait(smp_processor_id(), + softlockup_fn, NULL, + this_cpu_ptr(&softlockup_stop_work)); /* .. and repeat */ hrtimer_forward_now(hrtimer, ns_to_ktime(sample_period)); @@ -448,17 +464,12 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) return HRTIMER_RESTART; } -static void watchdog_set_prio(unsigned int policy, unsigned int prio) -{ - struct sched_param param = { .sched_priority = prio }; - - sched_setscheduler(current, policy, ¶m); -} - static void watchdog_enable(unsigned int cpu) { struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer); + WARN_ON_ONCE(cpu != smp_processor_id()); + /* * Start the timer first to prevent the NMI watchdog triggering * before the timer has a chance to fire. @@ -473,15 +484,14 @@ static void watchdog_enable(unsigned int cpu) /* Enable the perf event */ if (watchdog_enabled & NMI_WATCHDOG_ENABLED) watchdog_nmi_enable(cpu); - - watchdog_set_prio(SCHED_FIFO, MAX_RT_PRIO - 1); } static void watchdog_disable(unsigned int cpu) { struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer); - watchdog_set_prio(SCHED_NORMAL, 0); + WARN_ON_ONCE(cpu != smp_processor_id()); + /* * Disable the perf event first. That prevents that a large delay * between disabling the timer and disabling the perf event causes @@ -491,77 +501,63 @@ static void watchdog_disable(unsigned int cpu) hrtimer_cancel(hrtimer); } -static void watchdog_cleanup(unsigned int cpu, bool online) +static int softlockup_stop_fn(void *data) { - watchdog_disable(cpu); + watchdog_disable(smp_processor_id()); + return 0; } -static int watchdog_should_run(unsigned int cpu) +static void softlockup_stop_all(void) { - return __this_cpu_read(hrtimer_interrupts) != - __this_cpu_read(soft_lockup_hrtimer_cnt); + int cpu; + + if (!softlockup_initialized) + return; + + for_each_cpu(cpu, &watchdog_allowed_mask) + smp_call_on_cpu(cpu, softlockup_stop_fn, NULL, false); + + cpumask_clear(&watchdog_allowed_mask); } -/* - * The watchdog thread function - touches the timestamp. - * - * It only runs once every sample_period seconds (4 seconds by - * default) to reset the softlockup timestamp. If this gets delayed - * for more than 2*watchdog_thresh seconds then the debug-printout - * triggers in watchdog_timer_fn(). - */ -static void watchdog(unsigned int cpu) +static int softlockup_start_fn(void *data) { - __this_cpu_write(soft_lockup_hrtimer_cnt, - __this_cpu_read(hrtimer_interrupts)); - __touch_watchdog(); + watchdog_enable(smp_processor_id()); + return 0; } -static struct smp_hotplug_thread watchdog_threads = { - .store = &softlockup_watchdog, - .thread_should_run = watchdog_should_run, - .thread_fn = watchdog, - .thread_comm = "watchdog/%u", - .setup = watchdog_enable, - .cleanup = watchdog_cleanup, - .park = watchdog_disable, - .unpark = watchdog_enable, -}; - -static void softlockup_update_smpboot_threads(void) +static void softlockup_start_all(void) { - lockdep_assert_held(&watchdog_mutex); - - if (!softlockup_threads_initialized) - return; + int cpu; - smpboot_update_cpumask_percpu_thread(&watchdog_threads, - &watchdog_allowed_mask); + cpumask_copy(&watchdog_allowed_mask, &watchdog_cpumask); + for_each_cpu(cpu, &watchdog_allowed_mask) + smp_call_on_cpu(cpu, softlockup_start_fn, NULL, false); } -/* Temporarily park all watchdog threads */ -static void softlockup_park_all_threads(void) +int lockup_detector_online_cpu(unsigned int cpu) { - cpumask_clear(&watchdog_allowed_mask); - softlockup_update_smpboot_threads(); + watchdog_enable(cpu); + return 0; } -/* Unpark enabled threads */ -static void softlockup_unpark_threads(void) +int lockup_detector_offline_cpu(unsigned int cpu) { - cpumask_copy(&watchdog_allowed_mask, &watchdog_cpumask); - softlockup_update_smpboot_threads(); + watchdog_disable(cpu); + return 0; } static void lockup_detector_reconfigure(void) { cpus_read_lock(); watchdog_nmi_stop(); - softlockup_park_all_threads(); + + softlockup_stop_all(); set_sample_period(); lockup_detector_update_enable(); if (watchdog_enabled && watchdog_thresh) - softlockup_unpark_threads(); + softlockup_start_all(); + watchdog_nmi_start(); cpus_read_unlock(); /* @@ -580,8 +576,6 @@ static void lockup_detector_reconfigure(void) */ static __init void lockup_detector_setup(void) { - int ret; - /* * If sysctl is off and watchdog got disabled on the command line, * nothing to do here. @@ -592,24 +586,13 @@ static __init void lockup_detector_setup(void) !(watchdog_enabled && watchdog_thresh)) return; - ret = smpboot_register_percpu_thread_cpumask(&watchdog_threads, - &watchdog_allowed_mask); - if (ret) { - pr_err("Failed to initialize soft lockup detector threads\n"); - return; - } - mutex_lock(&watchdog_mutex); - softlockup_threads_initialized = true; lockup_detector_reconfigure(); + softlockup_initialized = true; mutex_unlock(&watchdog_mutex); } #else /* CONFIG_SOFTLOCKUP_DETECTOR */ -static inline int watchdog_park_threads(void) { return 0; } -static inline void watchdog_unpark_threads(void) { } -static inline int watchdog_enable_all_cpus(void) { return 0; } -static inline void watchdog_disable_all_cpus(void) { } static void lockup_detector_reconfigure(void) { cpus_read_lock(); -- cgit v1.2.3 From 167a88677b05d6a810f23b871cfb2b5db1808e60 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 7 Jun 2018 10:53:01 +0200 Subject: smpboot: Remove cpumask from the API Now that the sole use of the whole smpboot_*cpumask() API is gone, remove it. Suggested-by: Oleg Nesterov Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/smpboot.h | 15 +------------- kernel/smpboot.c | 54 +++++-------------------------------------------- 2 files changed, 6 insertions(+), 63 deletions(-) (limited to 'include') diff --git a/include/linux/smpboot.h b/include/linux/smpboot.h index c174844cf663..d0884b525001 100644 --- a/include/linux/smpboot.h +++ b/include/linux/smpboot.h @@ -25,8 +25,6 @@ struct smpboot_thread_data; * parked (cpu offline) * @unpark: Optional unpark function, called when the thread is * unparked (cpu online) - * @cpumask: Internal state. To update which threads are unparked, - * call smpboot_update_cpumask_percpu_thread(). * @selfparking: Thread is not parked by the park function. * @thread_comm: The base name of the thread */ @@ -40,23 +38,12 @@ struct smp_hotplug_thread { void (*cleanup)(unsigned int cpu, bool online); void (*park)(unsigned int cpu); void (*unpark)(unsigned int cpu); - cpumask_var_t cpumask; bool selfparking; const char *thread_comm; }; -int smpboot_register_percpu_thread_cpumask(struct smp_hotplug_thread *plug_thread, - const struct cpumask *cpumask); - -static inline int -smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread) -{ - return smpboot_register_percpu_thread_cpumask(plug_thread, - cpu_possible_mask); -} +int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread); void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread); -void smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread, - const struct cpumask *); #endif diff --git a/kernel/smpboot.c b/kernel/smpboot.c index 5043e7433f4b..c230c2dd48e1 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -238,8 +238,7 @@ int smpboot_unpark_threads(unsigned int cpu) mutex_lock(&smpboot_threads_lock); list_for_each_entry(cur, &hotplug_threads, list) - if (cpumask_test_cpu(cpu, cur->cpumask)) - smpboot_unpark_thread(cur, cpu); + smpboot_unpark_thread(cur, cpu); mutex_unlock(&smpboot_threads_lock); return 0; } @@ -280,34 +279,26 @@ static void smpboot_destroy_threads(struct smp_hotplug_thread *ht) } /** - * smpboot_register_percpu_thread_cpumask - Register a per_cpu thread related + * smpboot_register_percpu_thread - Register a per_cpu thread related * to hotplug * @plug_thread: Hotplug thread descriptor - * @cpumask: The cpumask where threads run * * Creates and starts the threads on all online cpus. */ -int smpboot_register_percpu_thread_cpumask(struct smp_hotplug_thread *plug_thread, - const struct cpumask *cpumask) +int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread) { unsigned int cpu; int ret = 0; - if (!alloc_cpumask_var(&plug_thread->cpumask, GFP_KERNEL)) - return -ENOMEM; - cpumask_copy(plug_thread->cpumask, cpumask); - get_online_cpus(); mutex_lock(&smpboot_threads_lock); for_each_online_cpu(cpu) { ret = __smpboot_create_thread(plug_thread, cpu); if (ret) { smpboot_destroy_threads(plug_thread); - free_cpumask_var(plug_thread->cpumask); goto out; } - if (cpumask_test_cpu(cpu, cpumask)) - smpboot_unpark_thread(plug_thread, cpu); + smpboot_unpark_thread(plug_thread, cpu); } list_add(&plug_thread->list, &hotplug_threads); out: @@ -315,7 +306,7 @@ out: put_online_cpus(); return ret; } -EXPORT_SYMBOL_GPL(smpboot_register_percpu_thread_cpumask); +EXPORT_SYMBOL_GPL(smpboot_register_percpu_thread); /** * smpboot_unregister_percpu_thread - Unregister a per_cpu thread related to hotplug @@ -331,44 +322,9 @@ void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread) smpboot_destroy_threads(plug_thread); mutex_unlock(&smpboot_threads_lock); put_online_cpus(); - free_cpumask_var(plug_thread->cpumask); } EXPORT_SYMBOL_GPL(smpboot_unregister_percpu_thread); -/** - * smpboot_update_cpumask_percpu_thread - Adjust which per_cpu hotplug threads stay parked - * @plug_thread: Hotplug thread descriptor - * @new: Revised mask to use - * - * The cpumask field in the smp_hotplug_thread must not be updated directly - * by the client, but only by calling this function. - * This function can only be called on a registered smp_hotplug_thread. - */ -void smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread, - const struct cpumask *new) -{ - struct cpumask *old = plug_thread->cpumask; - static struct cpumask tmp; - unsigned int cpu; - - lockdep_assert_cpus_held(); - mutex_lock(&smpboot_threads_lock); - - /* Park threads that were exclusively enabled on the old mask. */ - cpumask_andnot(&tmp, old, new); - for_each_cpu_and(cpu, &tmp, cpu_online_mask) - smpboot_park_thread(plug_thread, cpu); - - /* Unpark threads that are exclusively enabled on the new mask. */ - cpumask_andnot(&tmp, new, old); - for_each_cpu_and(cpu, &tmp, cpu_online_mask) - smpboot_unpark_thread(plug_thread, cpu); - - cpumask_copy(old, new); - - mutex_unlock(&smpboot_threads_lock); -} - static DEFINE_PER_CPU(atomic_t, cpu_hotplug_state) = ATOMIC_INIT(CPU_POST_DEAD); /* -- cgit v1.2.3 From 070473bcf703366e9acb14e172d5b6563cc07a26 Mon Sep 17 00:00:00 2001 From: Russell King Date: Mon, 2 Jul 2018 17:21:23 +0100 Subject: drm: add missing ctx argument to plane transitional helpers In commits: 34a2ab5e0689 ("drm: Add acquire ctx parameter to ->update_plane") 1931529448bc ("drm: Add acquire ctx parameter to ->plane_disable") a pointer to a drm_modeset_acquire_ctx structure was added as an argument to the method prototypes. The transitional helpers are supposed to be directly plugged in as implementations of these methods, but doing so generates a warning. Add the missing argument. A number of buggy users were added for drm_plane_helper_disable() which need to be fixed up for this change, which we do by passing a NULL ctx argument. Fixes: 1931529448bc ("drm: Add acquire ctx parameter to ->plane_disable") Signed-off-by: Russell King Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/E1fa1Zr-0005gT-VF@rmk-PC.armlinux.org.uk --- drivers/gpu/drm/arc/arcpgu_crtc.c | 2 +- drivers/gpu/drm/arm/hdlcd_crtc.c | 2 +- drivers/gpu/drm/drm_plane_helper.c | 8 ++++++-- drivers/gpu/drm/msm/disp/mdp4/mdp4_plane.c | 2 +- drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c | 2 +- drivers/gpu/drm/sti/sti_cursor.c | 2 +- drivers/gpu/drm/sti/sti_gdp.c | 2 +- drivers/gpu/drm/sti/sti_hqvdp.c | 2 +- drivers/gpu/drm/vc4/vc4_plane.c | 2 +- drivers/gpu/drm/zte/zx_plane.c | 2 +- include/drm/drm_plane_helper.h | 6 ++++-- 11 files changed, 19 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/arc/arcpgu_crtc.c b/drivers/gpu/drm/arc/arcpgu_crtc.c index c3349b8fb58b..965cda48dc13 100644 --- a/drivers/gpu/drm/arc/arcpgu_crtc.c +++ b/drivers/gpu/drm/arc/arcpgu_crtc.c @@ -186,7 +186,7 @@ static const struct drm_plane_helper_funcs arc_pgu_plane_helper_funcs = { static void arc_pgu_plane_destroy(struct drm_plane *plane) { - drm_plane_helper_disable(plane); + drm_plane_helper_disable(plane, NULL); drm_plane_cleanup(plane); } diff --git a/drivers/gpu/drm/arm/hdlcd_crtc.c b/drivers/gpu/drm/arm/hdlcd_crtc.c index cf5cbd63ecdf..f3f08cd6e9ef 100644 --- a/drivers/gpu/drm/arm/hdlcd_crtc.c +++ b/drivers/gpu/drm/arm/hdlcd_crtc.c @@ -282,7 +282,7 @@ static const struct drm_plane_helper_funcs hdlcd_plane_helper_funcs = { static void hdlcd_plane_destroy(struct drm_plane *plane) { - drm_plane_helper_disable(plane); + drm_plane_helper_disable(plane, NULL); drm_plane_cleanup(plane); } diff --git a/drivers/gpu/drm/drm_plane_helper.c b/drivers/gpu/drm/drm_plane_helper.c index 2010794943bc..621f17643bb0 100644 --- a/drivers/gpu/drm/drm_plane_helper.c +++ b/drivers/gpu/drm/drm_plane_helper.c @@ -440,6 +440,7 @@ out: * @src_y: y offset of @fb for panning * @src_w: width of source rectangle in @fb * @src_h: height of source rectangle in @fb + * @ctx: lock acquire context, not used here * * Provides a default plane update handler using the atomic plane update * functions. It is fully left to the driver to check plane constraints and @@ -455,7 +456,8 @@ int drm_plane_helper_update(struct drm_plane *plane, struct drm_crtc *crtc, int crtc_x, int crtc_y, unsigned int crtc_w, unsigned int crtc_h, uint32_t src_x, uint32_t src_y, - uint32_t src_w, uint32_t src_h) + uint32_t src_w, uint32_t src_h, + struct drm_modeset_acquire_ctx *ctx) { struct drm_plane_state *plane_state; @@ -489,6 +491,7 @@ EXPORT_SYMBOL(drm_plane_helper_update); /** * drm_plane_helper_disable() - Transitional helper for plane disable * @plane: plane to disable + * @ctx: lock acquire context, not used here * * Provides a default plane disable handler using the atomic plane update * functions. It is fully left to the driver to check plane constraints and @@ -499,7 +502,8 @@ EXPORT_SYMBOL(drm_plane_helper_update); * RETURNS: * Zero on success, error code on failure */ -int drm_plane_helper_disable(struct drm_plane *plane) +int drm_plane_helper_disable(struct drm_plane *plane, + struct drm_modeset_acquire_ctx *ctx) { struct drm_plane_state *plane_state; struct drm_framebuffer *old_fb; diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_plane.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_plane.c index 7b641fa6dc4d..79ff653d8081 100644 --- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_plane.c +++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_plane.c @@ -68,7 +68,7 @@ static void mdp4_plane_destroy(struct drm_plane *plane) { struct mdp4_plane *mdp4_plane = to_mdp4_plane(plane); - drm_plane_helper_disable(plane); + drm_plane_helper_disable(plane, NULL); drm_plane_cleanup(plane); kfree(mdp4_plane); diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c index c4f115fe96ff..7d306c5acd09 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c @@ -46,7 +46,7 @@ static void mdp5_plane_destroy(struct drm_plane *plane) { struct mdp5_plane *mdp5_plane = to_mdp5_plane(plane); - drm_plane_helper_disable(plane); + drm_plane_helper_disable(plane, NULL); drm_plane_cleanup(plane); kfree(mdp5_plane); diff --git a/drivers/gpu/drm/sti/sti_cursor.c b/drivers/gpu/drm/sti/sti_cursor.c index df0a282b9615..57b870e1e696 100644 --- a/drivers/gpu/drm/sti/sti_cursor.c +++ b/drivers/gpu/drm/sti/sti_cursor.c @@ -332,7 +332,7 @@ static void sti_cursor_destroy(struct drm_plane *drm_plane) { DRM_DEBUG_DRIVER("\n"); - drm_plane_helper_disable(drm_plane); + drm_plane_helper_disable(drm_plane, NULL); drm_plane_cleanup(drm_plane); } diff --git a/drivers/gpu/drm/sti/sti_gdp.c b/drivers/gpu/drm/sti/sti_gdp.c index 49813d34bdf0..c32de6cbf061 100644 --- a/drivers/gpu/drm/sti/sti_gdp.c +++ b/drivers/gpu/drm/sti/sti_gdp.c @@ -883,7 +883,7 @@ static void sti_gdp_destroy(struct drm_plane *drm_plane) { DRM_DEBUG_DRIVER("\n"); - drm_plane_helper_disable(drm_plane); + drm_plane_helper_disable(drm_plane, NULL); drm_plane_cleanup(drm_plane); } diff --git a/drivers/gpu/drm/sti/sti_hqvdp.c b/drivers/gpu/drm/sti/sti_hqvdp.c index 106be8c4e58b..03ac3b4a4469 100644 --- a/drivers/gpu/drm/sti/sti_hqvdp.c +++ b/drivers/gpu/drm/sti/sti_hqvdp.c @@ -1260,7 +1260,7 @@ static void sti_hqvdp_destroy(struct drm_plane *drm_plane) { DRM_DEBUG_DRIVER("\n"); - drm_plane_helper_disable(drm_plane); + drm_plane_helper_disable(drm_plane, NULL); drm_plane_cleanup(drm_plane); } diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c index 8604fd2e7c5a..9d7a36f148cf 100644 --- a/drivers/gpu/drm/vc4/vc4_plane.c +++ b/drivers/gpu/drm/vc4/vc4_plane.c @@ -902,7 +902,7 @@ static const struct drm_plane_helper_funcs vc4_plane_helper_funcs = { static void vc4_plane_destroy(struct drm_plane *plane) { - drm_plane_helper_disable(plane); + drm_plane_helper_disable(plane, NULL); drm_plane_cleanup(plane); } diff --git a/drivers/gpu/drm/zte/zx_plane.c b/drivers/gpu/drm/zte/zx_plane.c index d1931f5ea0b2..ae8c53b4b261 100644 --- a/drivers/gpu/drm/zte/zx_plane.c +++ b/drivers/gpu/drm/zte/zx_plane.c @@ -446,7 +446,7 @@ static const struct drm_plane_helper_funcs zx_gl_plane_helper_funcs = { static void zx_plane_destroy(struct drm_plane *plane) { - drm_plane_helper_disable(plane); + drm_plane_helper_disable(plane, NULL); drm_plane_cleanup(plane); } diff --git a/include/drm/drm_plane_helper.h b/include/drm/drm_plane_helper.h index 28d7ce620729..26cee2934781 100644 --- a/include/drm/drm_plane_helper.h +++ b/include/drm/drm_plane_helper.h @@ -67,8 +67,10 @@ int drm_plane_helper_update(struct drm_plane *plane, struct drm_crtc *crtc, int crtc_x, int crtc_y, unsigned int crtc_w, unsigned int crtc_h, uint32_t src_x, uint32_t src_y, - uint32_t src_w, uint32_t src_h); -int drm_plane_helper_disable(struct drm_plane *plane); + uint32_t src_w, uint32_t src_h, + struct drm_modeset_acquire_ctx *ctx); +int drm_plane_helper_disable(struct drm_plane *plane, + struct drm_modeset_acquire_ctx *ctx); /* For use by drm_crtc_helper.c */ int drm_plane_helper_commit(struct drm_plane *plane, -- cgit v1.2.3 From 55f036ca7e74b85e34958af3d22121c656796413 Mon Sep 17 00:00:00 2001 From: Peter Ziljstra Date: Fri, 15 Jun 2018 10:07:12 +0200 Subject: locking: WW mutex cleanup Make the WW mutex code more readable by adding comments, splitting up functions and pointing out that we're actually using the Wait-Die algorithm. Cc: Ingo Molnar Cc: Jonathan Corbet Cc: Gustavo Padovan Cc: Maarten Lankhorst Cc: Sean Paul Cc: David Airlie Cc: Davidlohr Bueso Cc: "Paul E. McKenney" Cc: Josh Triplett Cc: Thomas Gleixner Cc: Kate Stewart Cc: Philippe Ombredanne Cc: Greg Kroah-Hartman Cc: linux-doc@vger.kernel.org Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Co-authored-by: Thomas Hellstrom Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Hellstrom Acked-by: Ingo Molnar --- Documentation/locking/ww-mutex-design.txt | 12 +- include/linux/ww_mutex.h | 28 ++--- kernel/locking/mutex.c | 202 ++++++++++++++++++------------ 3 files changed, 145 insertions(+), 97 deletions(-) (limited to 'include') diff --git a/Documentation/locking/ww-mutex-design.txt b/Documentation/locking/ww-mutex-design.txt index 34c3a1b50b9a..2fd7f2a2af21 100644 --- a/Documentation/locking/ww-mutex-design.txt +++ b/Documentation/locking/ww-mutex-design.txt @@ -32,10 +32,10 @@ the oldest task) wins, and the one with the higher reservation id (i.e. the younger task) unlocks all of the buffers that it has already locked, and then tries again. -In the RDBMS literature this deadlock handling approach is called wait/wound: +In the RDBMS literature this deadlock handling approach is called wait/die: The older tasks waits until it can acquire the contended lock. The younger tasks needs to back off and drop all the locks it is currently holding, i.e. the -younger task is wounded. +younger task dies. Concepts -------- @@ -56,9 +56,9 @@ Furthermore there are three different class of w/w lock acquire functions: * Normal lock acquisition with a context, using ww_mutex_lock. -* Slowpath lock acquisition on the contending lock, used by the wounded task - after having dropped all already acquired locks. These functions have the - _slow postfix. +* Slowpath lock acquisition on the contending lock, used by the task that just + killed its transaction after having dropped all already acquired locks. + These functions have the _slow postfix. From a simple semantics point-of-view the _slow functions are not strictly required, since simply calling the normal ww_mutex_lock functions on the @@ -220,7 +220,7 @@ mutexes are a natural fit for such a case for two reasons: Note that this approach differs in two important ways from the above methods: - Since the list of objects is dynamically constructed (and might very well be - different when retrying due to hitting the -EDEADLK wound condition) there's + different when retrying due to hitting the -EDEADLK die condition) there's no need to keep any object on a persistent list when it's not locked. We can therefore move the list_head into the object itself. - On the other hand the dynamic object list construction also means that the -EALREADY return diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h index 39fda195bf78..f82fce2229c8 100644 --- a/include/linux/ww_mutex.h +++ b/include/linux/ww_mutex.h @@ -6,7 +6,7 @@ * * Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar * - * Wound/wait implementation: + * Wait/Die implementation: * Copyright (C) 2013 Canonical Ltd. * * This file contains the main data structure and API definitions. @@ -28,9 +28,9 @@ struct ww_class { struct ww_acquire_ctx { struct task_struct *task; unsigned long stamp; - unsigned acquired; + unsigned int acquired; #ifdef CONFIG_DEBUG_MUTEXES - unsigned done_acquire; + unsigned int done_acquire; struct ww_class *ww_class; struct ww_mutex *contending_lock; #endif @@ -38,8 +38,8 @@ struct ww_acquire_ctx { struct lockdep_map dep_map; #endif #ifdef CONFIG_DEBUG_WW_MUTEX_SLOWPATH - unsigned deadlock_inject_interval; - unsigned deadlock_inject_countdown; + unsigned int deadlock_inject_interval; + unsigned int deadlock_inject_countdown; #endif }; @@ -102,7 +102,7 @@ static inline void ww_mutex_init(struct ww_mutex *lock, * * Context-based w/w mutex acquiring can be done in any order whatsoever within * a given lock class. Deadlocks will be detected and handled with the - * wait/wound logic. + * wait/die logic. * * Mixing of context-based w/w mutex acquiring and single w/w mutex locking can * result in undetected deadlocks and is so forbidden. Mixing different contexts @@ -195,13 +195,13 @@ static inline void ww_acquire_fini(struct ww_acquire_ctx *ctx) * Lock the w/w mutex exclusively for this task. * * Deadlocks within a given w/w class of locks are detected and handled with the - * wait/wound algorithm. If the lock isn't immediately avaiable this function + * wait/die algorithm. If the lock isn't immediately available this function * will either sleep until it is (wait case). Or it selects the current context - * for backing off by returning -EDEADLK (wound case). Trying to acquire the + * for backing off by returning -EDEADLK (die case). Trying to acquire the * same lock with the same context twice is also detected and signalled by * returning -EALREADY. Returns 0 if the mutex was successfully acquired. * - * In the wound case the caller must release all currently held w/w mutexes for + * In the die case the caller must release all currently held w/w mutexes for * the given context and then wait for this contending lock to be available by * calling ww_mutex_lock_slow. Alternatively callers can opt to not acquire this * lock and proceed with trying to acquire further w/w mutexes (e.g. when @@ -226,14 +226,14 @@ extern int /* __must_check */ ww_mutex_lock(struct ww_mutex *lock, struct ww_acq * Lock the w/w mutex exclusively for this task. * * Deadlocks within a given w/w class of locks are detected and handled with the - * wait/wound algorithm. If the lock isn't immediately avaiable this function + * wait/die algorithm. If the lock isn't immediately available this function * will either sleep until it is (wait case). Or it selects the current context - * for backing off by returning -EDEADLK (wound case). Trying to acquire the + * for backing off by returning -EDEADLK (die case). Trying to acquire the * same lock with the same context twice is also detected and signalled by * returning -EALREADY. Returns 0 if the mutex was successfully acquired. If a * signal arrives while waiting for the lock then this function returns -EINTR. * - * In the wound case the caller must release all currently held w/w mutexes for + * In the die case the caller must release all currently held w/w mutexes for * the given context and then wait for this contending lock to be available by * calling ww_mutex_lock_slow_interruptible. Alternatively callers can opt to * not acquire this lock and proceed with trying to acquire further w/w mutexes @@ -256,7 +256,7 @@ extern int __must_check ww_mutex_lock_interruptible(struct ww_mutex *lock, * @lock: the mutex to be acquired * @ctx: w/w acquire context * - * Acquires a w/w mutex with the given context after a wound case. This function + * Acquires a w/w mutex with the given context after a die case. This function * will sleep until the lock becomes available. * * The caller must have released all w/w mutexes already acquired with the @@ -290,7 +290,7 @@ ww_mutex_lock_slow(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) * @lock: the mutex to be acquired * @ctx: w/w acquire context * - * Acquires a w/w mutex with the given context after a wound case. This function + * Acquires a w/w mutex with the given context after a die case. This function * will sleep until the lock becomes available and returns 0 when the lock has * been acquired. If a signal arrives while waiting for the lock then this * function returns -EINTR. diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index f44f658ae629..cfe48419b7d0 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -244,6 +244,17 @@ void __sched mutex_lock(struct mutex *lock) EXPORT_SYMBOL(mutex_lock); #endif +/* + * Wait-Die: + * The newer transactions are killed when: + * It (the new transaction) makes a request for a lock being held + * by an older transaction. + */ + +/* + * Associate the ww_mutex @ww with the context @ww_ctx under which we acquired + * it. + */ static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww, struct ww_acquire_ctx *ww_ctx) { @@ -282,26 +293,53 @@ ww_mutex_lock_acquired(struct ww_mutex *ww, struct ww_acquire_ctx *ww_ctx) DEBUG_LOCKS_WARN_ON(ww_ctx->ww_class != ww->ww_class); #endif ww_ctx->acquired++; + ww->ctx = ww_ctx; } +/* + * Determine if context @a is 'after' context @b. IOW, @a is a younger + * transaction than @b and depending on algorithm either needs to wait for + * @b or die. + */ static inline bool __sched __ww_ctx_stamp_after(struct ww_acquire_ctx *a, struct ww_acquire_ctx *b) { - return a->stamp - b->stamp <= LONG_MAX && - (a->stamp != b->stamp || a > b); + + return (signed long)(a->stamp - b->stamp) > 0; +} + +/* + * Wait-Die; wake a younger waiter context (when locks held) such that it can + * die. + * + * Among waiters with context, only the first one can have other locks acquired + * already (ctx->acquired > 0), because __ww_mutex_add_waiter() and + * __ww_mutex_check_kill() wake any but the earliest context. + */ +static bool __sched +__ww_mutex_die(struct mutex *lock, struct mutex_waiter *waiter, + struct ww_acquire_ctx *ww_ctx) +{ + if (waiter->ww_ctx->acquired > 0 && + __ww_ctx_stamp_after(waiter->ww_ctx, ww_ctx)) { + debug_mutex_wake_waiter(lock, waiter); + wake_up_process(waiter->task); + } + + return true; } /* - * Wake up any waiters that may have to back off when the lock is held by the - * given context. + * We just acquired @lock under @ww_ctx, if there are later contexts waiting + * behind us on the wait-list, check if they need to die. * - * Due to the invariants on the wait list, this can only affect the first - * waiter with a context. + * See __ww_mutex_add_waiter() for the list-order construction; basically the + * list is ordered by stamp, smallest (oldest) first. * * The current task must not be on the wait list. */ static void __sched -__ww_mutex_wakeup_for_backoff(struct mutex *lock, struct ww_acquire_ctx *ww_ctx) +__ww_mutex_check_waiters(struct mutex *lock, struct ww_acquire_ctx *ww_ctx) { struct mutex_waiter *cur; @@ -311,30 +349,23 @@ __ww_mutex_wakeup_for_backoff(struct mutex *lock, struct ww_acquire_ctx *ww_ctx) if (!cur->ww_ctx) continue; - if (cur->ww_ctx->acquired > 0 && - __ww_ctx_stamp_after(cur->ww_ctx, ww_ctx)) { - debug_mutex_wake_waiter(lock, cur); - wake_up_process(cur->task); - } - - break; + if (__ww_mutex_die(lock, cur, ww_ctx)) + break; } } /* - * After acquiring lock with fastpath or when we lost out in contested - * slowpath, set ctx and wake up any waiters so they can recheck. + * After acquiring lock with fastpath, where we do not hold wait_lock, set ctx + * and wake up any waiters so they can recheck. */ static __always_inline void ww_mutex_set_context_fastpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) { ww_mutex_lock_acquired(lock, ctx); - lock->ctx = ctx; - /* * The lock->ctx update should be visible on all cores before - * the atomic read is done, otherwise contended waiters might be + * the WAITERS check is done, otherwise contended waiters might be * missed. The contended waiters will either see ww_ctx == NULL * and keep spinning, or it will acquire wait_lock, add itself * to waiter list and sleep. @@ -348,29 +379,14 @@ ww_mutex_set_context_fastpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) return; /* - * Uh oh, we raced in fastpath, wake up everyone in this case, - * so they can see the new lock->ctx. + * Uh oh, we raced in fastpath, check if any of the waiters need to + * die. */ spin_lock(&lock->base.wait_lock); - __ww_mutex_wakeup_for_backoff(&lock->base, ctx); + __ww_mutex_check_waiters(&lock->base, ctx); spin_unlock(&lock->base.wait_lock); } -/* - * After acquiring lock in the slowpath set ctx. - * - * Unlike for the fast path, the caller ensures that waiters are woken up where - * necessary. - * - * Callers must hold the mutex wait_lock. - */ -static __always_inline void -ww_mutex_set_context_slowpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) -{ - ww_mutex_lock_acquired(lock, ctx); - lock->ctx = ctx; -} - #ifdef CONFIG_MUTEX_SPIN_ON_OWNER static inline @@ -646,37 +662,73 @@ void __sched ww_mutex_unlock(struct ww_mutex *lock) } EXPORT_SYMBOL(ww_mutex_unlock); + +static __always_inline int __sched +__ww_mutex_kill(struct mutex *lock, struct ww_acquire_ctx *ww_ctx) +{ + if (ww_ctx->acquired > 0) { +#ifdef CONFIG_DEBUG_MUTEXES + struct ww_mutex *ww; + + ww = container_of(lock, struct ww_mutex, base); + DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock); + ww_ctx->contending_lock = ww; +#endif + return -EDEADLK; + } + + return 0; +} + + +/* + * Check whether we need to kill the transaction for the current lock acquire. + * + * Wait-Die: If we're trying to acquire a lock already held by an older + * context, kill ourselves. + * + * Since __ww_mutex_add_waiter() orders the wait-list on stamp, we only have to + * look at waiters before us in the wait-list. + */ static inline int __sched -__ww_mutex_lock_check_stamp(struct mutex *lock, struct mutex_waiter *waiter, - struct ww_acquire_ctx *ctx) +__ww_mutex_check_kill(struct mutex *lock, struct mutex_waiter *waiter, + struct ww_acquire_ctx *ctx) { struct ww_mutex *ww = container_of(lock, struct ww_mutex, base); struct ww_acquire_ctx *hold_ctx = READ_ONCE(ww->ctx); struct mutex_waiter *cur; + if (ctx->acquired == 0) + return 0; + if (hold_ctx && __ww_ctx_stamp_after(ctx, hold_ctx)) - goto deadlock; + return __ww_mutex_kill(lock, ctx); /* * If there is a waiter in front of us that has a context, then its - * stamp is earlier than ours and we must back off. + * stamp is earlier than ours and we must kill ourself. */ cur = waiter; list_for_each_entry_continue_reverse(cur, &lock->wait_list, list) { - if (cur->ww_ctx) - goto deadlock; + if (!cur->ww_ctx) + continue; + + return __ww_mutex_kill(lock, ctx); } return 0; - -deadlock: -#ifdef CONFIG_DEBUG_MUTEXES - DEBUG_LOCKS_WARN_ON(ctx->contending_lock); - ctx->contending_lock = ww; -#endif - return -EDEADLK; } +/* + * Add @waiter to the wait-list, keep the wait-list ordered by stamp, smallest + * first. Such that older contexts are preferred to acquire the lock over + * younger contexts. + * + * Waiters without context are interspersed in FIFO order. + * + * Furthermore, for Wait-Die kill ourself immediately when possible (there are + * older contexts already waiting) to avoid unnecessary waiting. + */ static inline int __sched __ww_mutex_add_waiter(struct mutex_waiter *waiter, struct mutex *lock, @@ -693,7 +745,7 @@ __ww_mutex_add_waiter(struct mutex_waiter *waiter, /* * Add the waiter before the first waiter with a higher stamp. * Waiters without a context are skipped to avoid starving - * them. + * them. Wait-Die waiters may die here. */ pos = &lock->wait_list; list_for_each_entry_reverse(cur, &lock->wait_list, list) { @@ -701,34 +753,27 @@ __ww_mutex_add_waiter(struct mutex_waiter *waiter, continue; if (__ww_ctx_stamp_after(ww_ctx, cur->ww_ctx)) { - /* Back off immediately if necessary. */ - if (ww_ctx->acquired > 0) { -#ifdef CONFIG_DEBUG_MUTEXES - struct ww_mutex *ww; + /* + * Wait-Die: if we find an older context waiting, there + * is no point in queueing behind it, as we'd have to + * die the moment it would acquire the lock. + */ + int ret = __ww_mutex_kill(lock, ww_ctx); - ww = container_of(lock, struct ww_mutex, base); - DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock); - ww_ctx->contending_lock = ww; -#endif - return -EDEADLK; - } + if (ret) + return ret; break; } pos = &cur->list; - /* - * Wake up the waiter so that it gets a chance to back - * off. - */ - if (cur->ww_ctx->acquired > 0) { - debug_mutex_wake_waiter(lock, cur); - wake_up_process(cur->task); - } + /* Wait-Die: ensure younger waiters die. */ + __ww_mutex_die(lock, cur, ww_ctx); } list_add_tail(&waiter->list, pos); + return 0; } @@ -772,7 +817,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, */ if (__mutex_trylock(lock)) { if (use_ww_ctx && ww_ctx) - __ww_mutex_wakeup_for_backoff(lock, ww_ctx); + __ww_mutex_check_waiters(lock, ww_ctx); goto skip_wait; } @@ -790,10 +835,13 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, waiter.ww_ctx = MUTEX_POISON_WW_CTX; #endif } else { - /* Add in stamp order, waking up waiters that must back off. */ + /* + * Add in stamp order, waking up waiters that must kill + * themselves. + */ ret = __ww_mutex_add_waiter(&waiter, lock, ww_ctx); if (ret) - goto err_early_backoff; + goto err_early_kill; waiter.ww_ctx = ww_ctx; } @@ -815,7 +863,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, goto acquired; /* - * Check for signals and wound conditions while holding + * Check for signals and kill conditions while holding * wait_lock. This ensures the lock cancellation is ordered * against mutex_unlock() and wake-ups do not go missing. */ @@ -824,8 +872,8 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, goto err; } - if (use_ww_ctx && ww_ctx && ww_ctx->acquired > 0) { - ret = __ww_mutex_lock_check_stamp(lock, &waiter, ww_ctx); + if (use_ww_ctx && ww_ctx) { + ret = __ww_mutex_check_kill(lock, &waiter, ww_ctx); if (ret) goto err; } @@ -870,7 +918,7 @@ skip_wait: lock_acquired(&lock->dep_map, ip); if (use_ww_ctx && ww_ctx) - ww_mutex_set_context_slowpath(ww, ww_ctx); + ww_mutex_lock_acquired(ww, ww_ctx); spin_unlock(&lock->wait_lock); preempt_enable(); @@ -879,7 +927,7 @@ skip_wait: err: __set_current_state(TASK_RUNNING); mutex_remove_waiter(lock, &waiter, current); -err_early_backoff: +err_early_kill: spin_unlock(&lock->wait_lock); debug_mutex_free_waiter(&waiter); mutex_release(&lock->dep_map, 1, ip); -- cgit v1.2.3 From 08295b3b5beec9aac0f7a9db86f0fc3792039da3 Mon Sep 17 00:00:00 2001 From: Thomas Hellstrom Date: Fri, 15 Jun 2018 10:17:38 +0200 Subject: locking: Implement an algorithm choice for Wound-Wait mutexes The current Wound-Wait mutex algorithm is actually not Wound-Wait but Wait-Die. Implement also Wound-Wait as a per-ww-class choice. Wound-Wait is, contrary to Wait-Die a preemptive algorithm and is known to generate fewer backoffs. Testing reveals that this is true if the number of simultaneous contending transactions is small. As the number of simultaneous contending threads increases, Wait-Wound becomes inferior to Wait-Die in terms of elapsed time. Possibly due to the larger number of held locks of sleeping transactions. Update documentation and callers. Timings using git://people.freedesktop.org/~thomash/ww_mutex_test tag patch-18-06-15 Each thread runs 100000 batches of lock / unlock 800 ww mutexes randomly chosen out of 100000. Four core Intel x86_64: Algorithm #threads Rollbacks time Wound-Wait 4 ~100 ~17s. Wait-Die 4 ~150000 ~19s. Wound-Wait 16 ~360000 ~109s. Wait-Die 16 ~450000 ~82s. Cc: Ingo Molnar Cc: Jonathan Corbet Cc: Gustavo Padovan Cc: Maarten Lankhorst Cc: Sean Paul Cc: David Airlie Cc: Davidlohr Bueso Cc: "Paul E. McKenney" Cc: Josh Triplett Cc: Thomas Gleixner Cc: Kate Stewart Cc: Philippe Ombredanne Cc: Greg Kroah-Hartman Cc: linux-doc@vger.kernel.org Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Co-authored-by: Peter Zijlstra Signed-off-by: Thomas Hellstrom Acked-by: Peter Zijlstra (Intel) Acked-by: Ingo Molnar --- Documentation/locking/ww-mutex-design.txt | 57 +++++++++-- drivers/dma-buf/reservation.c | 2 +- drivers/gpu/drm/drm_modeset_lock.c | 2 +- include/linux/ww_mutex.h | 17 ++- kernel/locking/locktorture.c | 2 +- kernel/locking/mutex.c | 165 +++++++++++++++++++++++++++--- kernel/locking/test-ww_mutex.c | 2 +- lib/locking-selftest.c | 2 +- 8 files changed, 213 insertions(+), 36 deletions(-) (limited to 'include') diff --git a/Documentation/locking/ww-mutex-design.txt b/Documentation/locking/ww-mutex-design.txt index 2fd7f2a2af21..f0ed7c30e695 100644 --- a/Documentation/locking/ww-mutex-design.txt +++ b/Documentation/locking/ww-mutex-design.txt @@ -1,4 +1,4 @@ -Wait/Wound Deadlock-Proof Mutex Design +Wound/Wait Deadlock-Proof Mutex Design ====================================== Please read mutex-design.txt first, as it applies to wait/wound mutexes too. @@ -32,10 +32,26 @@ the oldest task) wins, and the one with the higher reservation id (i.e. the younger task) unlocks all of the buffers that it has already locked, and then tries again. -In the RDBMS literature this deadlock handling approach is called wait/die: -The older tasks waits until it can acquire the contended lock. The younger tasks -needs to back off and drop all the locks it is currently holding, i.e. the -younger task dies. +In the RDBMS literature, a reservation ticket is associated with a transaction. +and the deadlock handling approach is called Wait-Die. The name is based on +the actions of a locking thread when it encounters an already locked mutex. +If the transaction holding the lock is younger, the locking transaction waits. +If the transaction holding the lock is older, the locking transaction backs off +and dies. Hence Wait-Die. +There is also another algorithm called Wound-Wait: +If the transaction holding the lock is younger, the locking transaction +wounds the transaction holding the lock, requesting it to die. +If the transaction holding the lock is older, it waits for the other +transaction. Hence Wound-Wait. +The two algorithms are both fair in that a transaction will eventually succeed. +However, the Wound-Wait algorithm is typically stated to generate fewer backoffs +compared to Wait-Die, but is, on the other hand, associated with more work than +Wait-Die when recovering from a backoff. Wound-Wait is also a preemptive +algorithm in that transactions are wounded by other transactions, and that +requires a reliable way to pick up up the wounded condition and preempt the +running transaction. Note that this is not the same as process preemption. A +Wound-Wait transaction is considered preempted when it dies (returning +-EDEADLK) following a wound. Concepts -------- @@ -47,10 +63,12 @@ Acquire context: To ensure eventual forward progress it is important the a task trying to acquire locks doesn't grab a new reservation id, but keeps the one it acquired when starting the lock acquisition. This ticket is stored in the acquire context. Furthermore the acquire context keeps track of debugging state -to catch w/w mutex interface abuse. +to catch w/w mutex interface abuse. An acquire context is representing a +transaction. W/w class: In contrast to normal mutexes the lock class needs to be explicit for -w/w mutexes, since it is required to initialize the acquire context. +w/w mutexes, since it is required to initialize the acquire context. The lock +class also specifies what algorithm to use, Wound-Wait or Wait-Die. Furthermore there are three different class of w/w lock acquire functions: @@ -90,6 +108,12 @@ provided. Usage ----- +The algorithm (Wait-Die vs Wound-Wait) is chosen by using either +DEFINE_WW_CLASS() (Wound-Wait) or DEFINE_WD_CLASS() (Wait-Die) +As a rough rule of thumb, use Wound-Wait iff you +expect the number of simultaneous competing transactions to be typically small, +and you want to reduce the number of rollbacks. + Three different ways to acquire locks within the same w/w class. Common definitions for methods #1 and #2: @@ -312,12 +336,23 @@ Design: We maintain the following invariants for the wait list: (1) Waiters with an acquire context are sorted by stamp order; waiters without an acquire context are interspersed in FIFO order. - (2) Among waiters with contexts, only the first one can have other locks - acquired already (ctx->acquired > 0). Note that this waiter may come - after other waiters without contexts in the list. + (2) For Wait-Die, among waiters with contexts, only the first one can have + other locks acquired already (ctx->acquired > 0). Note that this waiter + may come after other waiters without contexts in the list. + + The Wound-Wait preemption is implemented with a lazy-preemption scheme: + The wounded status of the transaction is checked only when there is + contention for a new lock and hence a true chance of deadlock. In that + situation, if the transaction is wounded, it backs off, clears the + wounded status and retries. A great benefit of implementing preemption in + this way is that the wounded transaction can identify a contending lock to + wait for before restarting the transaction. Just blindly restarting the + transaction would likely make the transaction end up in a situation where + it would have to back off again. In general, not much contention is expected. The locks are typically used to - serialize access to resources for devices. + serialize access to resources for devices, and optimization focus should + therefore be directed towards the uncontended cases. Lockdep: Special care has been taken to warn for as many cases of api abuse diff --git a/drivers/dma-buf/reservation.c b/drivers/dma-buf/reservation.c index 314eb1071cce..20bf90f4ee63 100644 --- a/drivers/dma-buf/reservation.c +++ b/drivers/dma-buf/reservation.c @@ -46,7 +46,7 @@ * write-side updates. */ -DEFINE_WW_CLASS(reservation_ww_class); +DEFINE_WD_CLASS(reservation_ww_class); EXPORT_SYMBOL(reservation_ww_class); struct lock_class_key reservation_seqcount_class; diff --git a/drivers/gpu/drm/drm_modeset_lock.c b/drivers/gpu/drm/drm_modeset_lock.c index 8a5100685875..638be2eb67b4 100644 --- a/drivers/gpu/drm/drm_modeset_lock.c +++ b/drivers/gpu/drm/drm_modeset_lock.c @@ -70,7 +70,7 @@ * lists and lookup data structures. */ -static DEFINE_WW_CLASS(crtc_ww_class); +static DEFINE_WD_CLASS(crtc_ww_class); /** * drm_modeset_lock_all - take all modeset locks diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h index f82fce2229c8..3af7c0e03be5 100644 --- a/include/linux/ww_mutex.h +++ b/include/linux/ww_mutex.h @@ -8,6 +8,8 @@ * * Wait/Die implementation: * Copyright (C) 2013 Canonical Ltd. + * Choice of algorithm: + * Copyright (C) 2018 WMWare Inc. * * This file contains the main data structure and API definitions. */ @@ -23,12 +25,15 @@ struct ww_class { struct lock_class_key mutex_key; const char *acquire_name; const char *mutex_name; + unsigned int is_wait_die; }; struct ww_acquire_ctx { struct task_struct *task; unsigned long stamp; unsigned int acquired; + unsigned short wounded; + unsigned short is_wait_die; #ifdef CONFIG_DEBUG_MUTEXES unsigned int done_acquire; struct ww_class *ww_class; @@ -58,17 +63,21 @@ struct ww_mutex { # define __WW_CLASS_MUTEX_INITIALIZER(lockname, class) #endif -#define __WW_CLASS_INITIALIZER(ww_class) \ +#define __WW_CLASS_INITIALIZER(ww_class, _is_wait_die) \ { .stamp = ATOMIC_LONG_INIT(0) \ , .acquire_name = #ww_class "_acquire" \ - , .mutex_name = #ww_class "_mutex" } + , .mutex_name = #ww_class "_mutex" \ + , .is_wait_die = _is_wait_die } #define __WW_MUTEX_INITIALIZER(lockname, class) \ { .base = __MUTEX_INITIALIZER(lockname.base) \ __WW_CLASS_MUTEX_INITIALIZER(lockname, class) } +#define DEFINE_WD_CLASS(classname) \ + struct ww_class classname = __WW_CLASS_INITIALIZER(classname, 1) + #define DEFINE_WW_CLASS(classname) \ - struct ww_class classname = __WW_CLASS_INITIALIZER(classname) + struct ww_class classname = __WW_CLASS_INITIALIZER(classname, 0) #define DEFINE_WW_MUTEX(mutexname, ww_class) \ struct ww_mutex mutexname = __WW_MUTEX_INITIALIZER(mutexname, ww_class) @@ -123,6 +132,8 @@ static inline void ww_acquire_init(struct ww_acquire_ctx *ctx, ctx->task = current; ctx->stamp = atomic_long_inc_return_relaxed(&ww_class->stamp); ctx->acquired = 0; + ctx->wounded = false; + ctx->is_wait_die = ww_class->is_wait_die; #ifdef CONFIG_DEBUG_MUTEXES ctx->ww_class = ww_class; ctx->done_acquire = 0; diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c index 8402b3349dca..c28224347d69 100644 --- a/kernel/locking/locktorture.c +++ b/kernel/locking/locktorture.c @@ -365,7 +365,7 @@ static struct lock_torture_ops mutex_lock_ops = { }; #include -static DEFINE_WW_CLASS(torture_ww_class); +static DEFINE_WD_CLASS(torture_ww_class); static DEFINE_WW_MUTEX(torture_ww_mutex_0, &torture_ww_class); static DEFINE_WW_MUTEX(torture_ww_mutex_1, &torture_ww_class); static DEFINE_WW_MUTEX(torture_ww_mutex_2, &torture_ww_class); diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index cfe48419b7d0..1a81a1257b3f 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -173,6 +173,21 @@ static inline bool __mutex_waiter_is_first(struct mutex *lock, struct mutex_wait return list_first_entry(&lock->wait_list, struct mutex_waiter, list) == waiter; } +/* + * Add @waiter to a given location in the lock wait_list and set the + * FLAG_WAITERS flag if it's the first waiter. + */ +static void __sched +__mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter, + struct list_head *list) +{ + debug_mutex_add_waiter(lock, waiter, current); + + list_add_tail(&waiter->list, list); + if (__mutex_waiter_is_first(lock, waiter)) + __mutex_set_flag(lock, MUTEX_FLAG_WAITERS); +} + /* * Give up ownership to a specific task, when @task = NULL, this is equivalent * to a regular unlock. Sets PICKUP on a handoff, clears HANDOF, preserves @@ -249,6 +264,11 @@ EXPORT_SYMBOL(mutex_lock); * The newer transactions are killed when: * It (the new transaction) makes a request for a lock being held * by an older transaction. + * + * Wound-Wait: + * The newer transactions are wounded when: + * An older transaction makes a request for a lock being held by + * the newer transaction. */ /* @@ -320,6 +340,9 @@ static bool __sched __ww_mutex_die(struct mutex *lock, struct mutex_waiter *waiter, struct ww_acquire_ctx *ww_ctx) { + if (!ww_ctx->is_wait_die) + return false; + if (waiter->ww_ctx->acquired > 0 && __ww_ctx_stamp_after(waiter->ww_ctx, ww_ctx)) { debug_mutex_wake_waiter(lock, waiter); @@ -329,13 +352,65 @@ __ww_mutex_die(struct mutex *lock, struct mutex_waiter *waiter, return true; } +/* + * Wound-Wait; wound a younger @hold_ctx if it holds the lock. + * + * Wound the lock holder if there are waiters with older transactions than + * the lock holders. Even if multiple waiters may wound the lock holder, + * it's sufficient that only one does. + */ +static bool __ww_mutex_wound(struct mutex *lock, + struct ww_acquire_ctx *ww_ctx, + struct ww_acquire_ctx *hold_ctx) +{ + struct task_struct *owner = __mutex_owner(lock); + + lockdep_assert_held(&lock->wait_lock); + + /* + * Possible through __ww_mutex_add_waiter() when we race with + * ww_mutex_set_context_fastpath(). In that case we'll get here again + * through __ww_mutex_check_waiters(). + */ + if (!hold_ctx) + return false; + + /* + * Can have !owner because of __mutex_unlock_slowpath(), but if owner, + * it cannot go away because we'll have FLAG_WAITERS set and hold + * wait_lock. + */ + if (!owner) + return false; + + if (ww_ctx->acquired > 0 && __ww_ctx_stamp_after(hold_ctx, ww_ctx)) { + hold_ctx->wounded = 1; + + /* + * wake_up_process() paired with set_current_state() + * inserts sufficient barriers to make sure @owner either sees + * it's wounded in __ww_mutex_lock_check_stamp() or has a + * wakeup pending to re-read the wounded state. + */ + if (owner != current) + wake_up_process(owner); + + return true; + } + + return false; +} + /* * We just acquired @lock under @ww_ctx, if there are later contexts waiting - * behind us on the wait-list, check if they need to die. + * behind us on the wait-list, check if they need to die, or wound us. * * See __ww_mutex_add_waiter() for the list-order construction; basically the * list is ordered by stamp, smallest (oldest) first. * + * This relies on never mixing wait-die/wound-wait on the same wait-list; + * which is currently ensured by that being a ww_class property. + * * The current task must not be on the wait list. */ static void __sched @@ -349,7 +424,8 @@ __ww_mutex_check_waiters(struct mutex *lock, struct ww_acquire_ctx *ww_ctx) if (!cur->ww_ctx) continue; - if (__ww_mutex_die(lock, cur, ww_ctx)) + if (__ww_mutex_die(lock, cur, ww_ctx) || + __ww_mutex_wound(lock, cur->ww_ctx, ww_ctx)) break; } } @@ -370,17 +446,23 @@ ww_mutex_set_context_fastpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) * and keep spinning, or it will acquire wait_lock, add itself * to waiter list and sleep. */ - smp_mb(); /* ^^^ */ + smp_mb(); /* See comments above and below. */ /* - * Check if lock is contended, if not there is nobody to wake up + * [W] ww->ctx = ctx [W] MUTEX_FLAG_WAITERS + * MB MB + * [R] MUTEX_FLAG_WAITERS [R] ww->ctx + * + * The memory barrier above pairs with the memory barrier in + * __ww_mutex_add_waiter() and makes sure we either observe ww->ctx + * and/or !empty list. */ if (likely(!(atomic_long_read(&lock->base.owner) & MUTEX_FLAG_WAITERS))) return; /* * Uh oh, we raced in fastpath, check if any of the waiters need to - * die. + * die or wound us. */ spin_lock(&lock->base.wait_lock); __ww_mutex_check_waiters(&lock->base, ctx); @@ -682,7 +764,9 @@ __ww_mutex_kill(struct mutex *lock, struct ww_acquire_ctx *ww_ctx) /* - * Check whether we need to kill the transaction for the current lock acquire. + * Check the wound condition for the current lock acquire. + * + * Wound-Wait: If we're wounded, kill ourself. * * Wait-Die: If we're trying to acquire a lock already held by an older * context, kill ourselves. @@ -701,6 +785,13 @@ __ww_mutex_check_kill(struct mutex *lock, struct mutex_waiter *waiter, if (ctx->acquired == 0) return 0; + if (!ctx->is_wait_die) { + if (ctx->wounded) + return __ww_mutex_kill(lock, ctx); + + return 0; + } + if (hold_ctx && __ww_ctx_stamp_after(ctx, hold_ctx)) return __ww_mutex_kill(lock, ctx); @@ -727,7 +818,8 @@ __ww_mutex_check_kill(struct mutex *lock, struct mutex_waiter *waiter, * Waiters without context are interspersed in FIFO order. * * Furthermore, for Wait-Die kill ourself immediately when possible (there are - * older contexts already waiting) to avoid unnecessary waiting. + * older contexts already waiting) to avoid unnecessary waiting and for + * Wound-Wait ensure we wound the owning context when it is younger. */ static inline int __sched __ww_mutex_add_waiter(struct mutex_waiter *waiter, @@ -736,16 +828,21 @@ __ww_mutex_add_waiter(struct mutex_waiter *waiter, { struct mutex_waiter *cur; struct list_head *pos; + bool is_wait_die; if (!ww_ctx) { - list_add_tail(&waiter->list, &lock->wait_list); + __mutex_add_waiter(lock, waiter, &lock->wait_list); return 0; } + is_wait_die = ww_ctx->is_wait_die; + /* * Add the waiter before the first waiter with a higher stamp. * Waiters without a context are skipped to avoid starving - * them. Wait-Die waiters may die here. + * them. Wait-Die waiters may die here. Wound-Wait waiters + * never die here, but they are sorted in stamp order and + * may wound the lock holder. */ pos = &lock->wait_list; list_for_each_entry_reverse(cur, &lock->wait_list, list) { @@ -758,10 +855,12 @@ __ww_mutex_add_waiter(struct mutex_waiter *waiter, * is no point in queueing behind it, as we'd have to * die the moment it would acquire the lock. */ - int ret = __ww_mutex_kill(lock, ww_ctx); + if (is_wait_die) { + int ret = __ww_mutex_kill(lock, ww_ctx); - if (ret) - return ret; + if (ret) + return ret; + } break; } @@ -772,7 +871,23 @@ __ww_mutex_add_waiter(struct mutex_waiter *waiter, __ww_mutex_die(lock, cur, ww_ctx); } - list_add_tail(&waiter->list, pos); + __mutex_add_waiter(lock, waiter, pos); + + /* + * Wound-Wait: if we're blocking on a mutex owned by a younger context, + * wound that such that we might proceed. + */ + if (!is_wait_die) { + struct ww_mutex *ww = container_of(lock, struct ww_mutex, base); + + /* + * See ww_mutex_set_context_fastpath(). Orders setting + * MUTEX_FLAG_WAITERS vs the ww->ctx load, + * such that either we or the fastpath will wound @ww->ctx. + */ + smp_mb(); + __ww_mutex_wound(lock, ww_ctx, ww->ctx); + } return 0; } @@ -796,6 +911,14 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, if (use_ww_ctx && ww_ctx) { if (unlikely(ww_ctx == READ_ONCE(ww->ctx))) return -EALREADY; + + /* + * Reset the wounded flag after a kill. No other process can + * race and wound us here since they can't have a valid owner + * pointer if we don't have any locks held. + */ + if (ww_ctx->acquired == 0) + ww_ctx->wounded = 0; } preempt_disable(); @@ -829,7 +952,8 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, if (!use_ww_ctx) { /* add waiting tasks to the end of the waitqueue (FIFO): */ - list_add_tail(&waiter.list, &lock->wait_list); + __mutex_add_waiter(lock, &waiter, &lock->wait_list); + #ifdef CONFIG_DEBUG_MUTEXES waiter.ww_ctx = MUTEX_POISON_WW_CTX; @@ -848,9 +972,6 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, waiter.task = current; - if (__mutex_waiter_is_first(lock, &waiter)) - __mutex_set_flag(lock, MUTEX_FLAG_WAITERS); - set_current_state(state); for (;;) { /* @@ -907,6 +1028,16 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, acquired: __set_current_state(TASK_RUNNING); + if (use_ww_ctx && ww_ctx) { + /* + * Wound-Wait; we stole the lock (!first_waiter), check the + * waiters as anyone might want to wound us. + */ + if (!ww_ctx->is_wait_die && + !__mutex_waiter_is_first(lock, &waiter)) + __ww_mutex_check_waiters(lock, ww_ctx); + } + mutex_remove_waiter(lock, &waiter, current); if (likely(list_empty(&lock->wait_list))) __mutex_clear_flag(lock, MUTEX_FLAGS); diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/test-ww_mutex.c index 0e4cd64ad2c0..5b915b370d5a 100644 --- a/kernel/locking/test-ww_mutex.c +++ b/kernel/locking/test-ww_mutex.c @@ -26,7 +26,7 @@ #include #include -static DEFINE_WW_CLASS(ww_class); +static DEFINE_WD_CLASS(ww_class); struct workqueue_struct *wq; struct test_mutex { diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c index b5c1293ce147..1e1bbf171eca 100644 --- a/lib/locking-selftest.c +++ b/lib/locking-selftest.c @@ -29,7 +29,7 @@ */ static unsigned int debug_locks_verbose; -static DEFINE_WW_CLASS(ww_lockdep); +static DEFINE_WD_CLASS(ww_lockdep); static int __init setup_debug_locks_verbose(char *str) { -- cgit v1.2.3 From 6c0ad1df179b8d26ecd5e9954c36146fa87c1b0c Mon Sep 17 00:00:00 2001 From: Yixun Lan Date: Mon, 2 Jul 2018 21:31:17 +0000 Subject: clk: meson-axg: add pcie and mipi clock bindings Add the pcie and mipi clock dt-bindings for the pcie driver. Since the mipi clock isalso used by the pcie driver, we add it together in this patch. Tested-by: Jianxin Qin Signed-off-by: Yixun Lan Signed-off-by: Jerome Brunet --- include/dt-bindings/clock/axg-clkc.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/clock/axg-clkc.h b/include/dt-bindings/clock/axg-clkc.h index 555937a25504..70371228b7e0 100644 --- a/include/dt-bindings/clock/axg-clkc.h +++ b/include/dt-bindings/clock/axg-clkc.h @@ -68,5 +68,8 @@ #define CLKID_SD_EMMC_B_CLK0 59 #define CLKID_SD_EMMC_C_CLK0 60 #define CLKID_HIFI_PLL 69 +#define CLKID_PCIE_CML_EN0 79 +#define CLKID_PCIE_CML_EN1 80 +#define CLKID_MIPI_ENABLE 81 #endif /* __AXG_CLKC_H */ -- cgit v1.2.3 From 418cc6ca06071e7b7d75c0d525d80a6f49a763d6 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Thu, 3 May 2018 16:25:52 +0200 Subject: dma-fence: Make ->wait callback optional MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Almost everyone uses dma_fence_default_wait. v2: Also remove the BUG_ON(!ops->wait) (Chris). Reviewed-by: Christian König (v1) Signed-off-by: Daniel Vetter Cc: Chris Wilson Cc: Sumit Semwal Cc: Gustavo Padovan Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Link: https://patchwork.freedesktop.org/patch/msgid/20180503142603.28513-5-daniel.vetter@ffwll.ch --- drivers/dma-buf/dma-fence-array.c | 1 - drivers/dma-buf/dma-fence.c | 8 +++++--- drivers/dma-buf/sw_sync.c | 1 - include/linux/dma-fence.h | 13 ++++++++----- 4 files changed, 13 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/drivers/dma-buf/dma-fence-array.c b/drivers/dma-buf/dma-fence-array.c index dd1edfb27b61..a8c254497251 100644 --- a/drivers/dma-buf/dma-fence-array.c +++ b/drivers/dma-buf/dma-fence-array.c @@ -104,7 +104,6 @@ const struct dma_fence_ops dma_fence_array_ops = { .get_timeline_name = dma_fence_array_get_timeline_name, .enable_signaling = dma_fence_array_enable_signaling, .signaled = dma_fence_array_signaled, - .wait = dma_fence_default_wait, .release = dma_fence_array_release, }; EXPORT_SYMBOL(dma_fence_array_ops); diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c index ea343f992112..7a92f85a4cec 100644 --- a/drivers/dma-buf/dma-fence.c +++ b/drivers/dma-buf/dma-fence.c @@ -158,7 +158,10 @@ dma_fence_wait_timeout(struct dma_fence *fence, bool intr, signed long timeout) return -EINVAL; trace_dma_fence_wait_start(fence); - ret = fence->ops->wait(fence, intr, timeout); + if (fence->ops->wait) + ret = fence->ops->wait(fence, intr, timeout); + else + ret = dma_fence_default_wait(fence, intr, timeout); trace_dma_fence_wait_end(fence); return ret; } @@ -556,8 +559,7 @@ dma_fence_init(struct dma_fence *fence, const struct dma_fence_ops *ops, spinlock_t *lock, u64 context, unsigned seqno) { BUG_ON(!lock); - BUG_ON(!ops || !ops->wait || - !ops->get_driver_name || !ops->get_timeline_name); + BUG_ON(!ops || !ops->get_driver_name || !ops->get_timeline_name); kref_init(&fence->refcount); fence->ops = ops; diff --git a/drivers/dma-buf/sw_sync.c b/drivers/dma-buf/sw_sync.c index 3d78ca89a605..53c1d6d36a64 100644 --- a/drivers/dma-buf/sw_sync.c +++ b/drivers/dma-buf/sw_sync.c @@ -188,7 +188,6 @@ static const struct dma_fence_ops timeline_fence_ops = { .get_timeline_name = timeline_fence_get_timeline_name, .enable_signaling = timeline_fence_enable_signaling, .signaled = timeline_fence_signaled, - .wait = dma_fence_default_wait, .release = timeline_fence_release, .fence_value_str = timeline_fence_value_str, .timeline_value_str = timeline_fence_timeline_value_str, diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index c053d19e1e24..02dba8cd033d 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -191,11 +191,14 @@ struct dma_fence_ops { /** * @wait: * - * Custom wait implementation, or dma_fence_default_wait. + * Custom wait implementation, defaults to dma_fence_default_wait() if + * not set. * - * Must not be NULL, set to dma_fence_default_wait for default implementation. - * the dma_fence_default_wait implementation should work for any fence, as long - * as enable_signaling works correctly. + * The dma_fence_default_wait implementation should work for any fence, as long + * as @enable_signaling works correctly. This hook allows drivers to + * have an optimized version for the case where a process context is + * already available, e.g. if @enable_signaling for the general case + * needs to set up a worker thread. * * Must return -ERESTARTSYS if the wait is intr = true and the wait was * interrupted, and remaining jiffies if fence has signaled, or 0 if wait @@ -203,7 +206,7 @@ struct dma_fence_ops { * which should be treated as if the fence is signaled. For example a hardware * lockup could be reported like that. * - * This callback is mandatory. + * This callback is optional. */ signed long (*wait)(struct dma_fence *fence, bool intr, signed long timeout); -- cgit v1.2.3 From a655de808cbde6c58b3298e704d786b53f59fb5d Mon Sep 17 00:00:00 2001 From: Liam Girdwood Date: Mon, 2 Jul 2018 16:59:54 +0100 Subject: ASoC: core: Allow topology to override machine driver FE DAI link config. Machine drivers statically define a number of DAI links that currently cannot be changed or removed by topology. This means PCMs and platform components cannot be changed by topology at runtime AND machine drivers are tightly coupled to topology. This patch allows topology to override the machine driver DAI link config in order to reuse machine drivers with different topologies and platform components. The patch supports :- 1) create new FE PCMs with a topology defined PCM ID. 2) destroy existing static FE PCMs 3) change the platform component driver. 4) assign any new HW params fixups. 5) assign a new card name prefix to differentiate this topology to userspace. The patch requires no changes to the machine drivers, but does add some platform component flags that the platform component driver can assign before loading topologies. Signed-off-by: Liam Girdwood Signed-off-by: Mark Brown --- include/sound/soc.h | 13 +++++++ sound/soc/soc-core.c | 101 +++++++++++++++++++++++++++++++++++++++++++++++++-- sound/soc/soc-pcm.c | 12 ++++++ 3 files changed, 123 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/sound/soc.h b/include/sound/soc.h index 16f0bf10cc42..870ba6b64817 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -803,6 +803,14 @@ struct snd_soc_component_driver { unsigned int use_pmdown_time:1; /* care pmdown_time at stop */ unsigned int endianness:1; unsigned int non_legacy_dai_naming:1; + + /* this component uses topology and ignore machine driver FEs */ + const char *ignore_machine; + const char *topology_name_prefix; + int (*be_hw_params_fixup)(struct snd_soc_pcm_runtime *rtd, + struct snd_pcm_hw_params *params); + bool use_dai_pcm_id; /* use the DAI link PCM ID as PCM device number */ + int be_pcm_base; /* base device ID for all BE PCMs */ }; struct snd_soc_component { @@ -960,6 +968,9 @@ struct snd_soc_dai_link { /* pmdown_time is ignored at stop */ unsigned int ignore_pmdown_time:1; + /* Do not create a PCM for this DAI link (Backend link) */ + unsigned int ignore:1; + struct list_head list; /* DAI link list of the soc card */ struct snd_soc_dobj dobj; /* For topology */ }; @@ -999,6 +1010,7 @@ struct snd_soc_card { const char *long_name; const char *driver_name; char dmi_longname[80]; + char topology_shortname[32]; struct device *dev; struct snd_card *snd_card; @@ -1008,6 +1020,7 @@ struct snd_soc_card { struct mutex dapm_mutex; bool instantiated; + bool topology_shortname_created; int (*probe)(struct snd_soc_card *card); int (*late_probe)(struct snd_soc_card *card); diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index 68b08781c832..00bd58d167dd 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -847,6 +847,9 @@ static int soc_bind_dai_link(struct snd_soc_card *card, const char *platform_name; int i; + if (dai_link->ignore) + return 0; + dev_dbg(card->dev, "ASoC: binding %s\n", dai_link->name); if (soc_is_dai_link_bound(card, dai_link)) { @@ -1456,7 +1459,9 @@ static int soc_probe_link_dais(struct snd_soc_card *card, { struct snd_soc_dai_link *dai_link = rtd->dai_link; struct snd_soc_dai *cpu_dai = rtd->cpu_dai; - int i, ret; + struct snd_soc_rtdcom_list *rtdcom; + struct snd_soc_component *component; + int i, ret, num; dev_dbg(card->dev, "ASoC: probe %s dai link %d late %d\n", card->name, rtd->num, order); @@ -1502,9 +1507,28 @@ static int soc_probe_link_dais(struct snd_soc_card *card, soc_dpcm_debugfs_add(rtd); #endif + num = rtd->num; + + /* + * most drivers will register their PCMs using DAI link ordering but + * topology based drivers can use the DAI link id field to set PCM + * device number and then use rtd + a base offset of the BEs. + */ + for_each_rtdcom(rtd, rtdcom) { + component = rtdcom->component; + + if (!component->driver->use_dai_pcm_id) + continue; + + if (rtd->dai_link->no_pcm) + num += component->driver->be_pcm_base; + else + num = rtd->dai_link->id; + } + if (cpu_dai->driver->compress_new) { /*create compress_device"*/ - ret = cpu_dai->driver->compress_new(rtd, rtd->num); + ret = cpu_dai->driver->compress_new(rtd, num); if (ret < 0) { dev_err(card->dev, "ASoC: can't create compress %s\n", dai_link->stream_name); @@ -1514,7 +1538,7 @@ static int soc_probe_link_dais(struct snd_soc_card *card, if (!dai_link->params) { /* create the pcm */ - ret = soc_new_pcm(rtd, rtd->num); + ret = soc_new_pcm(rtd, num); if (ret < 0) { dev_err(card->dev, "ASoC: can't create pcm %s :%d\n", dai_link->stream_name, ret); @@ -1841,6 +1865,74 @@ int snd_soc_set_dmi_name(struct snd_soc_card *card, const char *flavour) EXPORT_SYMBOL_GPL(snd_soc_set_dmi_name); #endif /* CONFIG_DMI */ +static void soc_check_tplg_fes(struct snd_soc_card *card) +{ + struct snd_soc_component *component; + const struct snd_soc_component_driver *comp_drv; + struct snd_soc_dai_link *dai_link; + int i; + + list_for_each_entry(component, &component_list, list) { + + /* does this component override FEs ? */ + if (!component->driver->ignore_machine) + continue; + + /* for this machine ? */ + if (strcmp(component->driver->ignore_machine, + card->dev->driver->name)) + continue; + + /* machine matches, so override the rtd data */ + for (i = 0; i < card->num_links; i++) { + + dai_link = &card->dai_link[i]; + + /* ignore this FE */ + if (dai_link->dynamic) { + dai_link->ignore = true; + continue; + } + + dev_info(card->dev, "info: override FE DAI link %s\n", + card->dai_link[i].name); + + /* override platform component */ + dai_link->platform_name = component->name; + + /* convert non BE into BE */ + dai_link->no_pcm = 1; + + /* override any BE fixups */ + dai_link->be_hw_params_fixup = + component->driver->be_hw_params_fixup; + + /* most BE links don't set stream name, so set it to + * dai link name if it's NULL to help bind widgets. + */ + if (!dai_link->stream_name) + dai_link->stream_name = dai_link->name; + } + + /* Inform userspace we are using alternate topology */ + if (component->driver->topology_name_prefix) { + + /* topology shortname created ? */ + if (!card->topology_shortname_created) { + comp_drv = component->driver; + + snprintf(card->topology_shortname, 32, "%s-%s", + comp_drv->topology_name_prefix, + card->name); + card->topology_shortname_created = true; + } + + /* use topology shortname */ + card->name = card->topology_shortname; + } + } +} + static int snd_soc_instantiate_card(struct snd_soc_card *card) { struct snd_soc_pcm_runtime *rtd; @@ -1850,6 +1942,9 @@ static int snd_soc_instantiate_card(struct snd_soc_card *card) mutex_lock(&client_mutex); mutex_lock_nested(&card->mutex, SND_SOC_CARD_CLASS_INIT); + /* check whether any platform is ignore machine FE and using topology */ + soc_check_tplg_fes(card); + /* bind DAIs */ for (i = 0; i < card->num_links; i++) { ret = soc_bind_dai_link(card, &card->dai_link[i]); diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index c2a31b51da4f..b7e67b871c0c 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -859,8 +859,20 @@ int soc_dai_hw_params(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params, struct snd_soc_dai *dai) { + struct snd_soc_pcm_runtime *rtd = substream->private_data; int ret; + /* perform any topology hw_params fixups before DAI */ + if (rtd->dai_link->be_hw_params_fixup) { + ret = rtd->dai_link->be_hw_params_fixup(rtd, params); + if (ret < 0) { + dev_err(rtd->dev, + "ASoC: hw_params topology fixup failed %d\n", + ret); + return ret; + } + } + if (dai->driver->ops->hw_params) { ret = dai->driver->ops->hw_params(substream, params, dai); if (ret < 0) { -- cgit v1.2.3 From cfb8282e18e292a8efc4d13ea1e4547a47dfb2d0 Mon Sep 17 00:00:00 2001 From: Amit Nischal Date: Mon, 11 Jun 2018 12:08:15 +0530 Subject: clk: qcom: Enable clocks which needs to be always on for SDM845 There are certain clocks which needs to be always enabled for system operation. Add support for the same by adding 'CLK_IS_CRITICAL' flag for such clocks. Signed-off-by: Amit Nischal Signed-off-by: Stephen Boyd --- drivers/clk/qcom/gcc-sdm845.c | 43 ++++++++++++++++++++++++++--- include/dt-bindings/clock/qcom,gcc-sdm845.h | 2 ++ 2 files changed, 41 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/clk/qcom/gcc-sdm845.c b/drivers/clk/qcom/gcc-sdm845.c index e78e6f5b99fc..0f694ed4238a 100644 --- a/drivers/clk/qcom/gcc-sdm845.c +++ b/drivers/clk/qcom/gcc-sdm845.c @@ -1103,6 +1103,7 @@ static struct clk_branch gcc_camera_ahb_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_camera_ahb_clk", + .flags = CLK_IS_CRITICAL, .ops = &clk_branch2_ops, }, }, @@ -1129,6 +1130,7 @@ static struct clk_branch gcc_camera_xo_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_camera_xo_clk", + .flags = CLK_IS_CRITICAL, .ops = &clk_branch2_ops, }, }, @@ -1270,6 +1272,7 @@ static struct clk_branch gcc_disp_ahb_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_disp_ahb_clk", + .flags = CLK_IS_CRITICAL, .ops = &clk_branch2_ops, }, }, @@ -1328,6 +1331,7 @@ static struct clk_branch gcc_disp_xo_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_disp_xo_clk", + .flags = CLK_IS_CRITICAL, .ops = &clk_branch2_ops, }, }, @@ -1397,6 +1401,7 @@ static struct clk_branch gcc_gpu_cfg_ahb_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_gpu_cfg_ahb_clk", + .flags = CLK_IS_CRITICAL, .ops = &clk_branch2_ops, }, }, @@ -2985,6 +2990,7 @@ static struct clk_branch gcc_video_ahb_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_video_ahb_clk", + .flags = CLK_IS_CRITICAL, .ops = &clk_branch2_ops, }, }, @@ -3011,6 +3017,7 @@ static struct clk_branch gcc_video_xo_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_video_xo_clk", + .flags = CLK_IS_CRITICAL, .ops = &clk_branch2_ops, }, }, @@ -3049,6 +3056,36 @@ static struct clk_branch gcc_vs_ctrl_clk = { }, }; +static struct clk_branch gcc_cpuss_dvm_bus_clk = { + .halt_reg = 0x48190, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x48190, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_cpuss_dvm_bus_clk", + .flags = CLK_IS_CRITICAL, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_cpuss_gnoc_clk = { + .halt_reg = 0x48004, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x48004, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x52004, + .enable_mask = BIT(22), + .hw.init = &(struct clk_init_data){ + .name = "gcc_cpuss_gnoc_clk", + .flags = CLK_IS_CRITICAL, + .ops = &clk_branch2_ops, + }, + }, +}; + static struct gdsc pcie_0_gdsc = { .gdscr = 0x6b004, .pd = { @@ -3344,6 +3381,8 @@ static struct clk_regmap *gcc_sdm845_clocks[] = { [GPLL0] = &gpll0.clkr, [GPLL0_OUT_EVEN] = &gpll0_out_even.clkr, [GPLL4] = &gpll4.clkr, + [GCC_CPUSS_DVM_BUS_CLK] = &gcc_cpuss_dvm_bus_clk.clkr, + [GCC_CPUSS_GNOC_CLK] = &gcc_cpuss_gnoc_clk.clkr, }; static const struct qcom_reset_map gcc_sdm845_resets[] = { @@ -3433,10 +3472,6 @@ static int gcc_sdm845_probe(struct platform_device *pdev) regmap_update_bits(regmap, 0x09ffc, 0x3, 0x3); regmap_update_bits(regmap, 0x71028, 0x3, 0x3); - /* Enable CPUSS clocks */ - regmap_update_bits(regmap, 0x48190, BIT(0), 0x1); - regmap_update_bits(regmap, 0x52004, BIT(22), 0x1); - return qcom_cc_really_probe(pdev, &gcc_sdm845_desc, regmap); } diff --git a/include/dt-bindings/clock/qcom,gcc-sdm845.h b/include/dt-bindings/clock/qcom,gcc-sdm845.h index aca61264f12c..f96fc2dbf60e 100644 --- a/include/dt-bindings/clock/qcom,gcc-sdm845.h +++ b/include/dt-bindings/clock/qcom,gcc-sdm845.h @@ -192,6 +192,8 @@ #define GCC_VS_CTRL_CLK_SRC 182 #define GCC_VSENSOR_CLK_SRC 183 #define GPLL4 184 +#define GCC_CPUSS_DVM_BUS_CLK 185 +#define GCC_CPUSS_GNOC_CLK 186 /* GCC Resets */ #define GCC_MMSS_BCR 0 -- cgit v1.2.3 From f1d34bfd70b1b4543a139ea28bad4c001c5f413d Mon Sep 17 00:00:00 2001 From: Thomas Hellstrom Date: Tue, 19 Jun 2018 15:02:16 +0200 Subject: drm/vmwgfx: Replace vmw_dma_buffer with vmw_buffer_object Initially vmware buffer objects were only used as DMA buffers, so the name DMA buffer was a natural one. However, currently they are used also as dumb buffers and MOBs backing guest backed objects so renaming them to buffer objects is logical. Particularly since there is a dmabuf subsystem in the kernel where a dma buffer means something completely different. This also renames user-space api structures and IOCTL names correspondingly, but the old names remain defined for now and the ABI hasn't changed. There are a couple of minor style changes to make checkpatch happy. Signed-off-by: Thomas Hellstrom Reviewed-by: Sinclair Yeh Reviewed-by: Deepak Rawat --- drivers/gpu/drm/vmwgfx/Makefile | 4 +- drivers/gpu/drm/vmwgfx/vmwgfx_bo.c | 376 ++++++++++++ drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c | 887 ----------------------------- drivers/gpu/drm/vmwgfx/vmwgfx_context.c | 10 +- drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c | 10 +- drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c | 376 ------------ drivers/gpu/drm/vmwgfx/vmwgfx_drv.c | 18 +- drivers/gpu/drm/vmwgfx/vmwgfx_drv.h | 129 ++--- drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c | 86 ++- drivers/gpu/drm/vmwgfx/vmwgfx_fb.c | 16 +- drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c | 4 +- drivers/gpu/drm/vmwgfx/vmwgfx_kms.c | 203 ++++--- drivers/gpu/drm/vmwgfx/vmwgfx_kms.h | 58 +- drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c | 10 +- drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c | 24 +- drivers/gpu/drm/vmwgfx/vmwgfx_resource.c | 280 ++++----- drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c | 100 ++-- drivers/gpu/drm/vmwgfx/vmwgfx_shader.c | 22 +- drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c | 64 +-- drivers/gpu/drm/vmwgfx/vmwgfx_surface.c | 37 +- drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c | 887 +++++++++++++++++++++++++++++ include/uapi/drm/vmwgfx_drm.h | 61 +- 22 files changed, 1822 insertions(+), 1840 deletions(-) create mode 100644 drivers/gpu/drm/vmwgfx/vmwgfx_bo.c delete mode 100644 drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c delete mode 100644 drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c create mode 100644 drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c (limited to 'include') diff --git a/drivers/gpu/drm/vmwgfx/Makefile b/drivers/gpu/drm/vmwgfx/Makefile index 794cc9d5c9b0..09b2aa08363e 100644 --- a/drivers/gpu/drm/vmwgfx/Makefile +++ b/drivers/gpu/drm/vmwgfx/Makefile @@ -1,9 +1,9 @@ # SPDX-License-Identifier: GPL-2.0 vmwgfx-y := vmwgfx_execbuf.o vmwgfx_gmr.o vmwgfx_kms.o vmwgfx_drv.o \ - vmwgfx_fb.o vmwgfx_ioctl.o vmwgfx_resource.o vmwgfx_buffer.o \ + vmwgfx_fb.o vmwgfx_ioctl.o vmwgfx_resource.o vmwgfx_ttm_buffer.o \ vmwgfx_fifo.o vmwgfx_irq.o vmwgfx_ldu.o vmwgfx_ttm_glue.o \ vmwgfx_overlay.o vmwgfx_marker.o vmwgfx_gmrid_manager.o \ - vmwgfx_fence.o vmwgfx_dmabuf.o vmwgfx_scrn.o vmwgfx_context.o \ + vmwgfx_fence.o vmwgfx_bo.o vmwgfx_scrn.o vmwgfx_context.o \ vmwgfx_surface.o vmwgfx_prime.o vmwgfx_mob.o vmwgfx_shader.o \ vmwgfx_cmdbuf_res.o vmwgfx_cmdbuf.o vmwgfx_stdu.o \ vmwgfx_cotable.o vmwgfx_so.o vmwgfx_binding.o vmwgfx_msg.o \ diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c new file mode 100644 index 000000000000..f26f658cccdb --- /dev/null +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c @@ -0,0 +1,376 @@ +/************************************************************************** + * + * Copyright © 2011-2015 VMware, Inc., Palo Alto, CA., USA + * All Rights Reserved. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the + * "Software"), to deal in the Software without restriction, including + * without limitation the rights to use, copy, modify, merge, publish, + * distribute, sub license, and/or sell copies of the Software, and to + * permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice (including the + * next paragraph) shall be included in all copies or substantial portions + * of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, + * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + * USE OR OTHER DEALINGS IN THE SOFTWARE. + * + **************************************************************************/ + +#include + +#include +#include "vmwgfx_drv.h" + + +/** + * vmw_bo_pin_in_placement - Validate a buffer to placement. + * + * @dev_priv: Driver private. + * @buf: DMA buffer to move. + * @placement: The placement to pin it. + * @interruptible: Use interruptible wait. + * + * Returns + * -ERESTARTSYS if interrupted by a signal. + */ +int vmw_bo_pin_in_placement(struct vmw_private *dev_priv, + struct vmw_buffer_object *buf, + struct ttm_placement *placement, + bool interruptible) +{ + struct ttm_operation_ctx ctx = {interruptible, false }; + struct ttm_buffer_object *bo = &buf->base; + int ret; + uint32_t new_flags; + + ret = ttm_write_lock(&dev_priv->reservation_sem, interruptible); + if (unlikely(ret != 0)) + return ret; + + vmw_execbuf_release_pinned_bo(dev_priv); + + ret = ttm_bo_reserve(bo, interruptible, false, NULL); + if (unlikely(ret != 0)) + goto err; + + if (buf->pin_count > 0) + ret = ttm_bo_mem_compat(placement, &bo->mem, + &new_flags) == true ? 0 : -EINVAL; + else + ret = ttm_bo_validate(bo, placement, &ctx); + + if (!ret) + vmw_bo_pin_reserved(buf, true); + + ttm_bo_unreserve(bo); + +err: + ttm_write_unlock(&dev_priv->reservation_sem); + return ret; +} + +/** + * vmw_bo_pin_in_vram_or_gmr - Move a buffer to vram or gmr. + * + * This function takes the reservation_sem in write mode. + * Flushes and unpins the query bo to avoid failures. + * + * @dev_priv: Driver private. + * @buf: DMA buffer to move. + * @pin: Pin buffer if true. + * @interruptible: Use interruptible wait. + * + * Returns + * -ERESTARTSYS if interrupted by a signal. + */ +int vmw_bo_pin_in_vram_or_gmr(struct vmw_private *dev_priv, + struct vmw_buffer_object *buf, + bool interruptible) +{ + struct ttm_operation_ctx ctx = {interruptible, false }; + struct ttm_buffer_object *bo = &buf->base; + int ret; + uint32_t new_flags; + + ret = ttm_write_lock(&dev_priv->reservation_sem, interruptible); + if (unlikely(ret != 0)) + return ret; + + vmw_execbuf_release_pinned_bo(dev_priv); + + ret = ttm_bo_reserve(bo, interruptible, false, NULL); + if (unlikely(ret != 0)) + goto err; + + if (buf->pin_count > 0) { + ret = ttm_bo_mem_compat(&vmw_vram_gmr_placement, &bo->mem, + &new_flags) == true ? 0 : -EINVAL; + goto out_unreserve; + } + + ret = ttm_bo_validate(bo, &vmw_vram_gmr_placement, &ctx); + if (likely(ret == 0) || ret == -ERESTARTSYS) + goto out_unreserve; + + ret = ttm_bo_validate(bo, &vmw_vram_placement, &ctx); + +out_unreserve: + if (!ret) + vmw_bo_pin_reserved(buf, true); + + ttm_bo_unreserve(bo); +err: + ttm_write_unlock(&dev_priv->reservation_sem); + return ret; +} + +/** + * vmw_bo_pin_in_vram - Move a buffer to vram. + * + * This function takes the reservation_sem in write mode. + * Flushes and unpins the query bo to avoid failures. + * + * @dev_priv: Driver private. + * @buf: DMA buffer to move. + * @interruptible: Use interruptible wait. + * + * Returns + * -ERESTARTSYS if interrupted by a signal. + */ +int vmw_bo_pin_in_vram(struct vmw_private *dev_priv, + struct vmw_buffer_object *buf, + bool interruptible) +{ + return vmw_bo_pin_in_placement(dev_priv, buf, &vmw_vram_placement, + interruptible); +} + +/** + * vmw_bo_pin_in_start_of_vram - Move a buffer to start of vram. + * + * This function takes the reservation_sem in write mode. + * Flushes and unpins the query bo to avoid failures. + * + * @dev_priv: Driver private. + * @buf: DMA buffer to pin. + * @interruptible: Use interruptible wait. + * + * Returns + * -ERESTARTSYS if interrupted by a signal. + */ +int vmw_bo_pin_in_start_of_vram(struct vmw_private *dev_priv, + struct vmw_buffer_object *buf, + bool interruptible) +{ + struct ttm_operation_ctx ctx = {interruptible, false }; + struct ttm_buffer_object *bo = &buf->base; + struct ttm_placement placement; + struct ttm_place place; + int ret = 0; + uint32_t new_flags; + + place = vmw_vram_placement.placement[0]; + place.lpfn = bo->num_pages; + placement.num_placement = 1; + placement.placement = &place; + placement.num_busy_placement = 1; + placement.busy_placement = &place; + + ret = ttm_write_lock(&dev_priv->reservation_sem, interruptible); + if (unlikely(ret != 0)) + return ret; + + vmw_execbuf_release_pinned_bo(dev_priv); + ret = ttm_bo_reserve(bo, interruptible, false, NULL); + if (unlikely(ret != 0)) + goto err_unlock; + + /* + * Is this buffer already in vram but not at the start of it? + * In that case, evict it first because TTM isn't good at handling + * that situation. + */ + if (bo->mem.mem_type == TTM_PL_VRAM && + bo->mem.start < bo->num_pages && + bo->mem.start > 0 && + buf->pin_count == 0) { + ctx.interruptible = false; + (void) ttm_bo_validate(bo, &vmw_sys_placement, &ctx); + } + + if (buf->pin_count > 0) + ret = ttm_bo_mem_compat(&placement, &bo->mem, + &new_flags) == true ? 0 : -EINVAL; + else + ret = ttm_bo_validate(bo, &placement, &ctx); + + /* For some reason we didn't end up at the start of vram */ + WARN_ON(ret == 0 && bo->offset != 0); + if (!ret) + vmw_bo_pin_reserved(buf, true); + + ttm_bo_unreserve(bo); +err_unlock: + ttm_write_unlock(&dev_priv->reservation_sem); + + return ret; +} + +/** + * vmw_bo_unpin - Unpin the buffer given buffer, does not move the buffer. + * + * This function takes the reservation_sem in write mode. + * + * @dev_priv: Driver private. + * @buf: DMA buffer to unpin. + * @interruptible: Use interruptible wait. + * + * Returns + * -ERESTARTSYS if interrupted by a signal. + */ +int vmw_bo_unpin(struct vmw_private *dev_priv, + struct vmw_buffer_object *buf, + bool interruptible) +{ + struct ttm_buffer_object *bo = &buf->base; + int ret; + + ret = ttm_read_lock(&dev_priv->reservation_sem, interruptible); + if (unlikely(ret != 0)) + return ret; + + ret = ttm_bo_reserve(bo, interruptible, false, NULL); + if (unlikely(ret != 0)) + goto err; + + vmw_bo_pin_reserved(buf, false); + + ttm_bo_unreserve(bo); + +err: + ttm_read_unlock(&dev_priv->reservation_sem); + return ret; +} + +/** + * vmw_bo_get_guest_ptr - Get the guest ptr representing the current placement + * of a buffer. + * + * @bo: Pointer to a struct ttm_buffer_object. Must be pinned or reserved. + * @ptr: SVGAGuestPtr returning the result. + */ +void vmw_bo_get_guest_ptr(const struct ttm_buffer_object *bo, + SVGAGuestPtr *ptr) +{ + if (bo->mem.mem_type == TTM_PL_VRAM) { + ptr->gmrId = SVGA_GMR_FRAMEBUFFER; + ptr->offset = bo->offset; + } else { + ptr->gmrId = bo->mem.start; + ptr->offset = 0; + } +} + + +/** + * vmw_bo_pin_reserved - Pin or unpin a buffer object without moving it. + * + * @vbo: The buffer object. Must be reserved. + * @pin: Whether to pin or unpin. + * + */ +void vmw_bo_pin_reserved(struct vmw_buffer_object *vbo, bool pin) +{ + struct ttm_operation_ctx ctx = { false, true }; + struct ttm_place pl; + struct ttm_placement placement; + struct ttm_buffer_object *bo = &vbo->base; + uint32_t old_mem_type = bo->mem.mem_type; + int ret; + + lockdep_assert_held(&bo->resv->lock.base); + + if (pin) { + if (vbo->pin_count++ > 0) + return; + } else { + WARN_ON(vbo->pin_count <= 0); + if (--vbo->pin_count > 0) + return; + } + + pl.fpfn = 0; + pl.lpfn = 0; + pl.flags = TTM_PL_FLAG_VRAM | VMW_PL_FLAG_GMR | VMW_PL_FLAG_MOB + | TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED; + if (pin) + pl.flags |= TTM_PL_FLAG_NO_EVICT; + + memset(&placement, 0, sizeof(placement)); + placement.num_placement = 1; + placement.placement = &pl; + + ret = ttm_bo_validate(bo, &placement, &ctx); + + BUG_ON(ret != 0 || bo->mem.mem_type != old_mem_type); +} + + +/* + * vmw_buffer_object_unmap - Tear down a cached buffer object map. + * + * @vbo: The buffer object whose map we are tearing down. + * + * This function tears down a cached map set up using + * vmw_buffer_object_map_and_cache(). + */ +void vmw_buffer_object_unmap(struct vmw_buffer_object *vbo) +{ + if (vbo->map.bo == NULL) + return; + + ttm_bo_kunmap(&vbo->map); +} + + +/* + * vmw_buffer_object_map_and_cache - Map a buffer object and cache the map + * + * @vbo: The buffer object to map + * Return: A kernel virtual address or NULL if mapping failed. + * + * This function maps a buffer object into the kernel address space, or + * returns the virtual kernel address of an already existing map. The virtual + * address remains valid as long as the buffer object is pinned or reserved. + * The cached map is torn down on either + * 1) Buffer object move + * 2) Buffer object swapout + * 3) Buffer object destruction + * + */ +void *vmw_buffer_object_map_and_cache(struct vmw_buffer_object *vbo) +{ + struct ttm_buffer_object *bo = &vbo->base; + bool not_used; + void *virtual; + int ret; + + virtual = ttm_kmap_obj_virtual(&vbo->map, ¬_used); + if (virtual) + return virtual; + + ret = ttm_bo_kmap(bo, 0, bo->num_pages, &vbo->map); + if (ret) + DRM_ERROR("Buffer object map failed: %d.\n", ret); + + return ttm_kmap_obj_virtual(&vbo->map, ¬_used); +} diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c deleted file mode 100644 index 21111fd091f9..000000000000 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c +++ /dev/null @@ -1,887 +0,0 @@ -/************************************************************************** - * - * Copyright © 2009-2015 VMware, Inc., Palo Alto, CA., USA - * All Rights Reserved. - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the - * "Software"), to deal in the Software without restriction, including - * without limitation the rights to use, copy, modify, merge, publish, - * distribute, sub license, and/or sell copies of the Software, and to - * permit persons to whom the Software is furnished to do so, subject to - * the following conditions: - * - * The above copyright notice and this permission notice (including the - * next paragraph) shall be included in all copies or substantial portions - * of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL - * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, - * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR - * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE - * USE OR OTHER DEALINGS IN THE SOFTWARE. - * - **************************************************************************/ - -#include "vmwgfx_drv.h" -#include -#include -#include - -static const struct ttm_place vram_placement_flags = { - .fpfn = 0, - .lpfn = 0, - .flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED -}; - -static const struct ttm_place vram_ne_placement_flags = { - .fpfn = 0, - .lpfn = 0, - .flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED | TTM_PL_FLAG_NO_EVICT -}; - -static const struct ttm_place sys_placement_flags = { - .fpfn = 0, - .lpfn = 0, - .flags = TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED -}; - -static const struct ttm_place sys_ne_placement_flags = { - .fpfn = 0, - .lpfn = 0, - .flags = TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED | TTM_PL_FLAG_NO_EVICT -}; - -static const struct ttm_place gmr_placement_flags = { - .fpfn = 0, - .lpfn = 0, - .flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED -}; - -static const struct ttm_place gmr_ne_placement_flags = { - .fpfn = 0, - .lpfn = 0, - .flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED | TTM_PL_FLAG_NO_EVICT -}; - -static const struct ttm_place mob_placement_flags = { - .fpfn = 0, - .lpfn = 0, - .flags = VMW_PL_FLAG_MOB | TTM_PL_FLAG_CACHED -}; - -static const struct ttm_place mob_ne_placement_flags = { - .fpfn = 0, - .lpfn = 0, - .flags = VMW_PL_FLAG_MOB | TTM_PL_FLAG_CACHED | TTM_PL_FLAG_NO_EVICT -}; - -struct ttm_placement vmw_vram_placement = { - .num_placement = 1, - .placement = &vram_placement_flags, - .num_busy_placement = 1, - .busy_placement = &vram_placement_flags -}; - -static const struct ttm_place vram_gmr_placement_flags[] = { - { - .fpfn = 0, - .lpfn = 0, - .flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED - }, { - .fpfn = 0, - .lpfn = 0, - .flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED - } -}; - -static const struct ttm_place gmr_vram_placement_flags[] = { - { - .fpfn = 0, - .lpfn = 0, - .flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED - }, { - .fpfn = 0, - .lpfn = 0, - .flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED - } -}; - -struct ttm_placement vmw_vram_gmr_placement = { - .num_placement = 2, - .placement = vram_gmr_placement_flags, - .num_busy_placement = 1, - .busy_placement = &gmr_placement_flags -}; - -static const struct ttm_place vram_gmr_ne_placement_flags[] = { - { - .fpfn = 0, - .lpfn = 0, - .flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED | - TTM_PL_FLAG_NO_EVICT - }, { - .fpfn = 0, - .lpfn = 0, - .flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED | - TTM_PL_FLAG_NO_EVICT - } -}; - -struct ttm_placement vmw_vram_gmr_ne_placement = { - .num_placement = 2, - .placement = vram_gmr_ne_placement_flags, - .num_busy_placement = 1, - .busy_placement = &gmr_ne_placement_flags -}; - -struct ttm_placement vmw_vram_sys_placement = { - .num_placement = 1, - .placement = &vram_placement_flags, - .num_busy_placement = 1, - .busy_placement = &sys_placement_flags -}; - -struct ttm_placement vmw_vram_ne_placement = { - .num_placement = 1, - .placement = &vram_ne_placement_flags, - .num_busy_placement = 1, - .busy_placement = &vram_ne_placement_flags -}; - -struct ttm_placement vmw_sys_placement = { - .num_placement = 1, - .placement = &sys_placement_flags, - .num_busy_placement = 1, - .busy_placement = &sys_placement_flags -}; - -struct ttm_placement vmw_sys_ne_placement = { - .num_placement = 1, - .placement = &sys_ne_placement_flags, - .num_busy_placement = 1, - .busy_placement = &sys_ne_placement_flags -}; - -static const struct ttm_place evictable_placement_flags[] = { - { - .fpfn = 0, - .lpfn = 0, - .flags = TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED - }, { - .fpfn = 0, - .lpfn = 0, - .flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED - }, { - .fpfn = 0, - .lpfn = 0, - .flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED - }, { - .fpfn = 0, - .lpfn = 0, - .flags = VMW_PL_FLAG_MOB | TTM_PL_FLAG_CACHED - } -}; - -static const struct ttm_place nonfixed_placement_flags[] = { - { - .fpfn = 0, - .lpfn = 0, - .flags = TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED - }, { - .fpfn = 0, - .lpfn = 0, - .flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED - }, { - .fpfn = 0, - .lpfn = 0, - .flags = VMW_PL_FLAG_MOB | TTM_PL_FLAG_CACHED - } -}; - -struct ttm_placement vmw_evictable_placement = { - .num_placement = 4, - .placement = evictable_placement_flags, - .num_busy_placement = 1, - .busy_placement = &sys_placement_flags -}; - -struct ttm_placement vmw_srf_placement = { - .num_placement = 1, - .num_busy_placement = 2, - .placement = &gmr_placement_flags, - .busy_placement = gmr_vram_placement_flags -}; - -struct ttm_placement vmw_mob_placement = { - .num_placement = 1, - .num_busy_placement = 1, - .placement = &mob_placement_flags, - .busy_placement = &mob_placement_flags -}; - -struct ttm_placement vmw_mob_ne_placement = { - .num_placement = 1, - .num_busy_placement = 1, - .placement = &mob_ne_placement_flags, - .busy_placement = &mob_ne_placement_flags -}; - -struct ttm_placement vmw_nonfixed_placement = { - .num_placement = 3, - .placement = nonfixed_placement_flags, - .num_busy_placement = 1, - .busy_placement = &sys_placement_flags -}; - -struct vmw_ttm_tt { - struct ttm_dma_tt dma_ttm; - struct vmw_private *dev_priv; - int gmr_id; - struct vmw_mob *mob; - int mem_type; - struct sg_table sgt; - struct vmw_sg_table vsgt; - uint64_t sg_alloc_size; - bool mapped; -}; - -const size_t vmw_tt_size = sizeof(struct vmw_ttm_tt); - -/** - * Helper functions to advance a struct vmw_piter iterator. - * - * @viter: Pointer to the iterator. - * - * These functions return false if past the end of the list, - * true otherwise. Functions are selected depending on the current - * DMA mapping mode. - */ -static bool __vmw_piter_non_sg_next(struct vmw_piter *viter) -{ - return ++(viter->i) < viter->num_pages; -} - -static bool __vmw_piter_sg_next(struct vmw_piter *viter) -{ - return __sg_page_iter_next(&viter->iter); -} - - -/** - * Helper functions to return a pointer to the current page. - * - * @viter: Pointer to the iterator - * - * These functions return a pointer to the page currently - * pointed to by @viter. Functions are selected depending on the - * current mapping mode. - */ -static struct page *__vmw_piter_non_sg_page(struct vmw_piter *viter) -{ - return viter->pages[viter->i]; -} - -static struct page *__vmw_piter_sg_page(struct vmw_piter *viter) -{ - return sg_page_iter_page(&viter->iter); -} - - -/** - * Helper functions to return the DMA address of the current page. - * - * @viter: Pointer to the iterator - * - * These functions return the DMA address of the page currently - * pointed to by @viter. Functions are selected depending on the - * current mapping mode. - */ -static dma_addr_t __vmw_piter_phys_addr(struct vmw_piter *viter) -{ - return page_to_phys(viter->pages[viter->i]); -} - -static dma_addr_t __vmw_piter_dma_addr(struct vmw_piter *viter) -{ - return viter->addrs[viter->i]; -} - -static dma_addr_t __vmw_piter_sg_addr(struct vmw_piter *viter) -{ - return sg_page_iter_dma_address(&viter->iter); -} - - -/** - * vmw_piter_start - Initialize a struct vmw_piter. - * - * @viter: Pointer to the iterator to initialize - * @vsgt: Pointer to a struct vmw_sg_table to initialize from - * - * Note that we're following the convention of __sg_page_iter_start, so that - * the iterator doesn't point to a valid page after initialization; it has - * to be advanced one step first. - */ -void vmw_piter_start(struct vmw_piter *viter, const struct vmw_sg_table *vsgt, - unsigned long p_offset) -{ - viter->i = p_offset - 1; - viter->num_pages = vsgt->num_pages; - switch (vsgt->mode) { - case vmw_dma_phys: - viter->next = &__vmw_piter_non_sg_next; - viter->dma_address = &__vmw_piter_phys_addr; - viter->page = &__vmw_piter_non_sg_page; - viter->pages = vsgt->pages; - break; - case vmw_dma_alloc_coherent: - viter->next = &__vmw_piter_non_sg_next; - viter->dma_address = &__vmw_piter_dma_addr; - viter->page = &__vmw_piter_non_sg_page; - viter->addrs = vsgt->addrs; - viter->pages = vsgt->pages; - break; - case vmw_dma_map_populate: - case vmw_dma_map_bind: - viter->next = &__vmw_piter_sg_next; - viter->dma_address = &__vmw_piter_sg_addr; - viter->page = &__vmw_piter_sg_page; - __sg_page_iter_start(&viter->iter, vsgt->sgt->sgl, - vsgt->sgt->orig_nents, p_offset); - break; - default: - BUG(); - } -} - -/** - * vmw_ttm_unmap_from_dma - unmap device addresses previsouly mapped for - * TTM pages - * - * @vmw_tt: Pointer to a struct vmw_ttm_backend - * - * Used to free dma mappings previously mapped by vmw_ttm_map_for_dma. - */ -static void vmw_ttm_unmap_from_dma(struct vmw_ttm_tt *vmw_tt) -{ - struct device *dev = vmw_tt->dev_priv->dev->dev; - - dma_unmap_sg(dev, vmw_tt->sgt.sgl, vmw_tt->sgt.nents, - DMA_BIDIRECTIONAL); - vmw_tt->sgt.nents = vmw_tt->sgt.orig_nents; -} - -/** - * vmw_ttm_map_for_dma - map TTM pages to get device addresses - * - * @vmw_tt: Pointer to a struct vmw_ttm_backend - * - * This function is used to get device addresses from the kernel DMA layer. - * However, it's violating the DMA API in that when this operation has been - * performed, it's illegal for the CPU to write to the pages without first - * unmapping the DMA mappings, or calling dma_sync_sg_for_cpu(). It is - * therefore only legal to call this function if we know that the function - * dma_sync_sg_for_cpu() is a NOP, and dma_sync_sg_for_device() is at most - * a CPU write buffer flush. - */ -static int vmw_ttm_map_for_dma(struct vmw_ttm_tt *vmw_tt) -{ - struct device *dev = vmw_tt->dev_priv->dev->dev; - int ret; - - ret = dma_map_sg(dev, vmw_tt->sgt.sgl, vmw_tt->sgt.orig_nents, - DMA_BIDIRECTIONAL); - if (unlikely(ret == 0)) - return -ENOMEM; - - vmw_tt->sgt.nents = ret; - - return 0; -} - -/** - * vmw_ttm_map_dma - Make sure TTM pages are visible to the device - * - * @vmw_tt: Pointer to a struct vmw_ttm_tt - * - * Select the correct function for and make sure the TTM pages are - * visible to the device. Allocate storage for the device mappings. - * If a mapping has already been performed, indicated by the storage - * pointer being non NULL, the function returns success. - */ -static int vmw_ttm_map_dma(struct vmw_ttm_tt *vmw_tt) -{ - struct vmw_private *dev_priv = vmw_tt->dev_priv; - struct ttm_mem_global *glob = vmw_mem_glob(dev_priv); - struct vmw_sg_table *vsgt = &vmw_tt->vsgt; - struct ttm_operation_ctx ctx = { - .interruptible = true, - .no_wait_gpu = false - }; - struct vmw_piter iter; - dma_addr_t old; - int ret = 0; - static size_t sgl_size; - static size_t sgt_size; - - if (vmw_tt->mapped) - return 0; - - vsgt->mode = dev_priv->map_mode; - vsgt->pages = vmw_tt->dma_ttm.ttm.pages; - vsgt->num_pages = vmw_tt->dma_ttm.ttm.num_pages; - vsgt->addrs = vmw_tt->dma_ttm.dma_address; - vsgt->sgt = &vmw_tt->sgt; - - switch (dev_priv->map_mode) { - case vmw_dma_map_bind: - case vmw_dma_map_populate: - if (unlikely(!sgl_size)) { - sgl_size = ttm_round_pot(sizeof(struct scatterlist)); - sgt_size = ttm_round_pot(sizeof(struct sg_table)); - } - vmw_tt->sg_alloc_size = sgt_size + sgl_size * vsgt->num_pages; - ret = ttm_mem_global_alloc(glob, vmw_tt->sg_alloc_size, &ctx); - if (unlikely(ret != 0)) - return ret; - - ret = sg_alloc_table_from_pages(&vmw_tt->sgt, vsgt->pages, - vsgt->num_pages, 0, - (unsigned long) - vsgt->num_pages << PAGE_SHIFT, - GFP_KERNEL); - if (unlikely(ret != 0)) - goto out_sg_alloc_fail; - - if (vsgt->num_pages > vmw_tt->sgt.nents) { - uint64_t over_alloc = - sgl_size * (vsgt->num_pages - - vmw_tt->sgt.nents); - - ttm_mem_global_free(glob, over_alloc); - vmw_tt->sg_alloc_size -= over_alloc; - } - - ret = vmw_ttm_map_for_dma(vmw_tt); - if (unlikely(ret != 0)) - goto out_map_fail; - - break; - default: - break; - } - - old = ~((dma_addr_t) 0); - vmw_tt->vsgt.num_regions = 0; - for (vmw_piter_start(&iter, vsgt, 0); vmw_piter_next(&iter);) { - dma_addr_t cur = vmw_piter_dma_addr(&iter); - - if (cur != old + PAGE_SIZE) - vmw_tt->vsgt.num_regions++; - old = cur; - } - - vmw_tt->mapped = true; - return 0; - -out_map_fail: - sg_free_table(vmw_tt->vsgt.sgt); - vmw_tt->vsgt.sgt = NULL; -out_sg_alloc_fail: - ttm_mem_global_free(glob, vmw_tt->sg_alloc_size); - return ret; -} - -/** - * vmw_ttm_unmap_dma - Tear down any TTM page device mappings - * - * @vmw_tt: Pointer to a struct vmw_ttm_tt - * - * Tear down any previously set up device DMA mappings and free - * any storage space allocated for them. If there are no mappings set up, - * this function is a NOP. - */ -static void vmw_ttm_unmap_dma(struct vmw_ttm_tt *vmw_tt) -{ - struct vmw_private *dev_priv = vmw_tt->dev_priv; - - if (!vmw_tt->vsgt.sgt) - return; - - switch (dev_priv->map_mode) { - case vmw_dma_map_bind: - case vmw_dma_map_populate: - vmw_ttm_unmap_from_dma(vmw_tt); - sg_free_table(vmw_tt->vsgt.sgt); - vmw_tt->vsgt.sgt = NULL; - ttm_mem_global_free(vmw_mem_glob(dev_priv), - vmw_tt->sg_alloc_size); - break; - default: - break; - } - vmw_tt->mapped = false; -} - - -/** - * vmw_bo_map_dma - Make sure buffer object pages are visible to the device - * - * @bo: Pointer to a struct ttm_buffer_object - * - * Wrapper around vmw_ttm_map_dma, that takes a TTM buffer object pointer - * instead of a pointer to a struct vmw_ttm_backend as argument. - * Note that the buffer object must be either pinned or reserved before - * calling this function. - */ -int vmw_bo_map_dma(struct ttm_buffer_object *bo) -{ - struct vmw_ttm_tt *vmw_tt = - container_of(bo->ttm, struct vmw_ttm_tt, dma_ttm.ttm); - - return vmw_ttm_map_dma(vmw_tt); -} - - -/** - * vmw_bo_unmap_dma - Make sure buffer object pages are visible to the device - * - * @bo: Pointer to a struct ttm_buffer_object - * - * Wrapper around vmw_ttm_unmap_dma, that takes a TTM buffer object pointer - * instead of a pointer to a struct vmw_ttm_backend as argument. - */ -void vmw_bo_unmap_dma(struct ttm_buffer_object *bo) -{ - struct vmw_ttm_tt *vmw_tt = - container_of(bo->ttm, struct vmw_ttm_tt, dma_ttm.ttm); - - vmw_ttm_unmap_dma(vmw_tt); -} - - -/** - * vmw_bo_sg_table - Return a struct vmw_sg_table object for a - * TTM buffer object - * - * @bo: Pointer to a struct ttm_buffer_object - * - * Returns a pointer to a struct vmw_sg_table object. The object should - * not be freed after use. - * Note that for the device addresses to be valid, the buffer object must - * either be reserved or pinned. - */ -const struct vmw_sg_table *vmw_bo_sg_table(struct ttm_buffer_object *bo) -{ - struct vmw_ttm_tt *vmw_tt = - container_of(bo->ttm, struct vmw_ttm_tt, dma_ttm.ttm); - - return &vmw_tt->vsgt; -} - - -static int vmw_ttm_bind(struct ttm_tt *ttm, struct ttm_mem_reg *bo_mem) -{ - struct vmw_ttm_tt *vmw_be = - container_of(ttm, struct vmw_ttm_tt, dma_ttm.ttm); - int ret; - - ret = vmw_ttm_map_dma(vmw_be); - if (unlikely(ret != 0)) - return ret; - - vmw_be->gmr_id = bo_mem->start; - vmw_be->mem_type = bo_mem->mem_type; - - switch (bo_mem->mem_type) { - case VMW_PL_GMR: - return vmw_gmr_bind(vmw_be->dev_priv, &vmw_be->vsgt, - ttm->num_pages, vmw_be->gmr_id); - case VMW_PL_MOB: - if (unlikely(vmw_be->mob == NULL)) { - vmw_be->mob = - vmw_mob_create(ttm->num_pages); - if (unlikely(vmw_be->mob == NULL)) - return -ENOMEM; - } - - return vmw_mob_bind(vmw_be->dev_priv, vmw_be->mob, - &vmw_be->vsgt, ttm->num_pages, - vmw_be->gmr_id); - default: - BUG(); - } - return 0; -} - -static int vmw_ttm_unbind(struct ttm_tt *ttm) -{ - struct vmw_ttm_tt *vmw_be = - container_of(ttm, struct vmw_ttm_tt, dma_ttm.ttm); - - switch (vmw_be->mem_type) { - case VMW_PL_GMR: - vmw_gmr_unbind(vmw_be->dev_priv, vmw_be->gmr_id); - break; - case VMW_PL_MOB: - vmw_mob_unbind(vmw_be->dev_priv, vmw_be->mob); - break; - default: - BUG(); - } - - if (vmw_be->dev_priv->map_mode == vmw_dma_map_bind) - vmw_ttm_unmap_dma(vmw_be); - - return 0; -} - - -static void vmw_ttm_destroy(struct ttm_tt *ttm) -{ - struct vmw_ttm_tt *vmw_be = - container_of(ttm, struct vmw_ttm_tt, dma_ttm.ttm); - - vmw_ttm_unmap_dma(vmw_be); - if (vmw_be->dev_priv->map_mode == vmw_dma_alloc_coherent) - ttm_dma_tt_fini(&vmw_be->dma_ttm); - else - ttm_tt_fini(ttm); - - if (vmw_be->mob) - vmw_mob_destroy(vmw_be->mob); - - kfree(vmw_be); -} - - -static int vmw_ttm_populate(struct ttm_tt *ttm, struct ttm_operation_ctx *ctx) -{ - struct vmw_ttm_tt *vmw_tt = - container_of(ttm, struct vmw_ttm_tt, dma_ttm.ttm); - struct vmw_private *dev_priv = vmw_tt->dev_priv; - struct ttm_mem_global *glob = vmw_mem_glob(dev_priv); - int ret; - - if (ttm->state != tt_unpopulated) - return 0; - - if (dev_priv->map_mode == vmw_dma_alloc_coherent) { - size_t size = - ttm_round_pot(ttm->num_pages * sizeof(dma_addr_t)); - ret = ttm_mem_global_alloc(glob, size, ctx); - if (unlikely(ret != 0)) - return ret; - - ret = ttm_dma_populate(&vmw_tt->dma_ttm, dev_priv->dev->dev, - ctx); - if (unlikely(ret != 0)) - ttm_mem_global_free(glob, size); - } else - ret = ttm_pool_populate(ttm, ctx); - - return ret; -} - -static void vmw_ttm_unpopulate(struct ttm_tt *ttm) -{ - struct vmw_ttm_tt *vmw_tt = container_of(ttm, struct vmw_ttm_tt, - dma_ttm.ttm); - struct vmw_private *dev_priv = vmw_tt->dev_priv; - struct ttm_mem_global *glob = vmw_mem_glob(dev_priv); - - - if (vmw_tt->mob) { - vmw_mob_destroy(vmw_tt->mob); - vmw_tt->mob = NULL; - } - - vmw_ttm_unmap_dma(vmw_tt); - if (dev_priv->map_mode == vmw_dma_alloc_coherent) { - size_t size = - ttm_round_pot(ttm->num_pages * sizeof(dma_addr_t)); - - ttm_dma_unpopulate(&vmw_tt->dma_ttm, dev_priv->dev->dev); - ttm_mem_global_free(glob, size); - } else - ttm_pool_unpopulate(ttm); -} - -static struct ttm_backend_func vmw_ttm_func = { - .bind = vmw_ttm_bind, - .unbind = vmw_ttm_unbind, - .destroy = vmw_ttm_destroy, -}; - -static struct ttm_tt *vmw_ttm_tt_create(struct ttm_buffer_object *bo, - uint32_t page_flags) -{ - struct vmw_ttm_tt *vmw_be; - int ret; - - vmw_be = kzalloc(sizeof(*vmw_be), GFP_KERNEL); - if (!vmw_be) - return NULL; - - vmw_be->dma_ttm.ttm.func = &vmw_ttm_func; - vmw_be->dev_priv = container_of(bo->bdev, struct vmw_private, bdev); - vmw_be->mob = NULL; - - if (vmw_be->dev_priv->map_mode == vmw_dma_alloc_coherent) - ret = ttm_dma_tt_init(&vmw_be->dma_ttm, bo, page_flags); - else - ret = ttm_tt_init(&vmw_be->dma_ttm.ttm, bo, page_flags); - if (unlikely(ret != 0)) - goto out_no_init; - - return &vmw_be->dma_ttm.ttm; -out_no_init: - kfree(vmw_be); - return NULL; -} - -static int vmw_invalidate_caches(struct ttm_bo_device *bdev, uint32_t flags) -{ - return 0; -} - -static int vmw_init_mem_type(struct ttm_bo_device *bdev, uint32_t type, - struct ttm_mem_type_manager *man) -{ - switch (type) { - case TTM_PL_SYSTEM: - /* System memory */ - - man->flags = TTM_MEMTYPE_FLAG_MAPPABLE; - man->available_caching = TTM_PL_FLAG_CACHED; - man->default_caching = TTM_PL_FLAG_CACHED; - break; - case TTM_PL_VRAM: - /* "On-card" video ram */ - man->func = &ttm_bo_manager_func; - man->gpu_offset = 0; - man->flags = TTM_MEMTYPE_FLAG_FIXED | TTM_MEMTYPE_FLAG_MAPPABLE; - man->available_caching = TTM_PL_FLAG_CACHED; - man->default_caching = TTM_PL_FLAG_CACHED; - break; - case VMW_PL_GMR: - case VMW_PL_MOB: - /* - * "Guest Memory Regions" is an aperture like feature with - * one slot per bo. There is an upper limit of the number of - * slots as well as the bo size. - */ - man->func = &vmw_gmrid_manager_func; - man->gpu_offset = 0; - man->flags = TTM_MEMTYPE_FLAG_CMA | TTM_MEMTYPE_FLAG_MAPPABLE; - man->available_caching = TTM_PL_FLAG_CACHED; - man->default_caching = TTM_PL_FLAG_CACHED; - break; - default: - DRM_ERROR("Unsupported memory type %u\n", (unsigned)type); - return -EINVAL; - } - return 0; -} - -static void vmw_evict_flags(struct ttm_buffer_object *bo, - struct ttm_placement *placement) -{ - *placement = vmw_sys_placement; -} - -static int vmw_verify_access(struct ttm_buffer_object *bo, struct file *filp) -{ - struct ttm_object_file *tfile = - vmw_fpriv((struct drm_file *)filp->private_data)->tfile; - - return vmw_user_dmabuf_verify_access(bo, tfile); -} - -static int vmw_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem) -{ - struct ttm_mem_type_manager *man = &bdev->man[mem->mem_type]; - struct vmw_private *dev_priv = container_of(bdev, struct vmw_private, bdev); - - mem->bus.addr = NULL; - mem->bus.is_iomem = false; - mem->bus.offset = 0; - mem->bus.size = mem->num_pages << PAGE_SHIFT; - mem->bus.base = 0; - if (!(man->flags & TTM_MEMTYPE_FLAG_MAPPABLE)) - return -EINVAL; - switch (mem->mem_type) { - case TTM_PL_SYSTEM: - case VMW_PL_GMR: - case VMW_PL_MOB: - return 0; - case TTM_PL_VRAM: - mem->bus.offset = mem->start << PAGE_SHIFT; - mem->bus.base = dev_priv->vram_start; - mem->bus.is_iomem = true; - break; - default: - return -EINVAL; - } - return 0; -} - -static void vmw_ttm_io_mem_free(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem) -{ -} - -static int vmw_ttm_fault_reserve_notify(struct ttm_buffer_object *bo) -{ - return 0; -} - -/** - * vmw_move_notify - TTM move_notify_callback - * - * @bo: The TTM buffer object about to move. - * @mem: The struct ttm_mem_reg indicating to what memory - * region the move is taking place. - * - * Calls move_notify for all subsystems needing it. - * (currently only resources). - */ -static void vmw_move_notify(struct ttm_buffer_object *bo, - bool evict, - struct ttm_mem_reg *mem) -{ - vmw_resource_move_notify(bo, mem); - vmw_query_move_notify(bo, mem); -} - - -/** - * vmw_swap_notify - TTM move_notify_callback - * - * @bo: The TTM buffer object about to be swapped out. - */ -static void vmw_swap_notify(struct ttm_buffer_object *bo) -{ - vmw_resource_swap_notify(bo); - (void) ttm_bo_wait(bo, false, false); -} - - -struct ttm_bo_driver vmw_bo_driver = { - .ttm_tt_create = &vmw_ttm_tt_create, - .ttm_tt_populate = &vmw_ttm_populate, - .ttm_tt_unpopulate = &vmw_ttm_unpopulate, - .invalidate_caches = vmw_invalidate_caches, - .init_mem_type = vmw_init_mem_type, - .eviction_valuable = ttm_bo_eviction_valuable, - .evict_flags = vmw_evict_flags, - .move = NULL, - .verify_access = vmw_verify_access, - .move_notify = vmw_move_notify, - .swap_notify = vmw_swap_notify, - .fault_reserve_notify = &vmw_ttm_fault_reserve_notify, - .io_mem_reserve = &vmw_ttm_io_mem_reserve, - .io_mem_free = &vmw_ttm_io_mem_free, -}; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_context.c b/drivers/gpu/drm/vmwgfx/vmwgfx_context.c index 3767ac335aca..ff8acc74786c 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_context.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_context.c @@ -38,7 +38,7 @@ struct vmw_user_context { struct vmw_cmdbuf_res_manager *man; struct vmw_resource *cotables[SVGA_COTABLE_DX10_MAX]; spinlock_t cotable_lock; - struct vmw_dma_buffer *dx_query_mob; + struct vmw_buffer_object *dx_query_mob; }; static void vmw_user_context_free(struct vmw_resource *res); @@ -900,7 +900,7 @@ vmw_context_binding_state(struct vmw_resource *ctx) * specified in the parameter. 0 otherwise. */ int vmw_context_bind_dx_query(struct vmw_resource *ctx_res, - struct vmw_dma_buffer *mob) + struct vmw_buffer_object *mob) { struct vmw_user_context *uctx = container_of(ctx_res, struct vmw_user_context, res); @@ -908,7 +908,7 @@ int vmw_context_bind_dx_query(struct vmw_resource *ctx_res, if (mob == NULL) { if (uctx->dx_query_mob) { uctx->dx_query_mob->dx_query_ctx = NULL; - vmw_dmabuf_unreference(&uctx->dx_query_mob); + vmw_bo_unreference(&uctx->dx_query_mob); uctx->dx_query_mob = NULL; } @@ -922,7 +922,7 @@ int vmw_context_bind_dx_query(struct vmw_resource *ctx_res, mob->dx_query_ctx = ctx_res; if (!uctx->dx_query_mob) - uctx->dx_query_mob = vmw_dmabuf_reference(mob); + uctx->dx_query_mob = vmw_bo_reference(mob); return 0; } @@ -932,7 +932,7 @@ int vmw_context_bind_dx_query(struct vmw_resource *ctx_res, * * @ctx_res: The context resource */ -struct vmw_dma_buffer * +struct vmw_buffer_object * vmw_context_get_dx_query_mob(struct vmw_resource *ctx_res) { struct vmw_user_context *uctx = diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c index cbf54ea7b4c0..1052cd3cb700 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c @@ -390,7 +390,7 @@ static int vmw_cotable_resize(struct vmw_resource *res, size_t new_size) struct ttm_operation_ctx ctx = { false, false }; struct vmw_private *dev_priv = res->dev_priv; struct vmw_cotable *vcotbl = vmw_cotable(res); - struct vmw_dma_buffer *buf, *old_buf = res->backup; + struct vmw_buffer_object *buf, *old_buf = res->backup; struct ttm_buffer_object *bo, *old_bo = &res->backup->base; size_t old_size = res->backup_size; size_t old_size_read_back = vcotbl->size_read_back; @@ -415,8 +415,8 @@ static int vmw_cotable_resize(struct vmw_resource *res, size_t new_size) if (!buf) return -ENOMEM; - ret = vmw_dmabuf_init(dev_priv, buf, new_size, &vmw_mob_ne_placement, - true, vmw_dmabuf_bo_free); + ret = vmw_bo_init(dev_priv, buf, new_size, &vmw_mob_ne_placement, + true, vmw_bo_bo_free); if (ret) { DRM_ERROR("Failed initializing new cotable MOB.\n"); return ret; @@ -482,7 +482,7 @@ static int vmw_cotable_resize(struct vmw_resource *res, size_t new_size) /* Let go of the old mob. */ list_del(&res->mob_head); list_add_tail(&res->mob_head, &buf->res_list); - vmw_dmabuf_unreference(&old_buf); + vmw_bo_unreference(&old_buf); res->id = vcotbl->type; return 0; @@ -491,7 +491,7 @@ out_map_new: ttm_bo_kunmap(&old_map); out_wait: ttm_bo_unreserve(bo); - vmw_dmabuf_unreference(&buf); + vmw_bo_unreference(&buf); return ret; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c deleted file mode 100644 index d59d9dd16ebc..000000000000 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c +++ /dev/null @@ -1,376 +0,0 @@ -/************************************************************************** - * - * Copyright © 2011-2015 VMware, Inc., Palo Alto, CA., USA - * All Rights Reserved. - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the - * "Software"), to deal in the Software without restriction, including - * without limitation the rights to use, copy, modify, merge, publish, - * distribute, sub license, and/or sell copies of the Software, and to - * permit persons to whom the Software is furnished to do so, subject to - * the following conditions: - * - * The above copyright notice and this permission notice (including the - * next paragraph) shall be included in all copies or substantial portions - * of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL - * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, - * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR - * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE - * USE OR OTHER DEALINGS IN THE SOFTWARE. - * - **************************************************************************/ - -#include - -#include -#include "vmwgfx_drv.h" - - -/** - * vmw_dmabuf_pin_in_placement - Validate a buffer to placement. - * - * @dev_priv: Driver private. - * @buf: DMA buffer to move. - * @placement: The placement to pin it. - * @interruptible: Use interruptible wait. - * - * Returns - * -ERESTARTSYS if interrupted by a signal. - */ -int vmw_dmabuf_pin_in_placement(struct vmw_private *dev_priv, - struct vmw_dma_buffer *buf, - struct ttm_placement *placement, - bool interruptible) -{ - struct ttm_operation_ctx ctx = {interruptible, false }; - struct ttm_buffer_object *bo = &buf->base; - int ret; - uint32_t new_flags; - - ret = ttm_write_lock(&dev_priv->reservation_sem, interruptible); - if (unlikely(ret != 0)) - return ret; - - vmw_execbuf_release_pinned_bo(dev_priv); - - ret = ttm_bo_reserve(bo, interruptible, false, NULL); - if (unlikely(ret != 0)) - goto err; - - if (buf->pin_count > 0) - ret = ttm_bo_mem_compat(placement, &bo->mem, - &new_flags) == true ? 0 : -EINVAL; - else - ret = ttm_bo_validate(bo, placement, &ctx); - - if (!ret) - vmw_bo_pin_reserved(buf, true); - - ttm_bo_unreserve(bo); - -err: - ttm_write_unlock(&dev_priv->reservation_sem); - return ret; -} - -/** - * vmw_dmabuf_pin_in_vram_or_gmr - Move a buffer to vram or gmr. - * - * This function takes the reservation_sem in write mode. - * Flushes and unpins the query bo to avoid failures. - * - * @dev_priv: Driver private. - * @buf: DMA buffer to move. - * @pin: Pin buffer if true. - * @interruptible: Use interruptible wait. - * - * Returns - * -ERESTARTSYS if interrupted by a signal. - */ -int vmw_dmabuf_pin_in_vram_or_gmr(struct vmw_private *dev_priv, - struct vmw_dma_buffer *buf, - bool interruptible) -{ - struct ttm_operation_ctx ctx = {interruptible, false }; - struct ttm_buffer_object *bo = &buf->base; - int ret; - uint32_t new_flags; - - ret = ttm_write_lock(&dev_priv->reservation_sem, interruptible); - if (unlikely(ret != 0)) - return ret; - - vmw_execbuf_release_pinned_bo(dev_priv); - - ret = ttm_bo_reserve(bo, interruptible, false, NULL); - if (unlikely(ret != 0)) - goto err; - - if (buf->pin_count > 0) { - ret = ttm_bo_mem_compat(&vmw_vram_gmr_placement, &bo->mem, - &new_flags) == true ? 0 : -EINVAL; - goto out_unreserve; - } - - ret = ttm_bo_validate(bo, &vmw_vram_gmr_placement, &ctx); - if (likely(ret == 0) || ret == -ERESTARTSYS) - goto out_unreserve; - - ret = ttm_bo_validate(bo, &vmw_vram_placement, &ctx); - -out_unreserve: - if (!ret) - vmw_bo_pin_reserved(buf, true); - - ttm_bo_unreserve(bo); -err: - ttm_write_unlock(&dev_priv->reservation_sem); - return ret; -} - -/** - * vmw_dmabuf_pin_in_vram - Move a buffer to vram. - * - * This function takes the reservation_sem in write mode. - * Flushes and unpins the query bo to avoid failures. - * - * @dev_priv: Driver private. - * @buf: DMA buffer to move. - * @interruptible: Use interruptible wait. - * - * Returns - * -ERESTARTSYS if interrupted by a signal. - */ -int vmw_dmabuf_pin_in_vram(struct vmw_private *dev_priv, - struct vmw_dma_buffer *buf, - bool interruptible) -{ - return vmw_dmabuf_pin_in_placement(dev_priv, buf, &vmw_vram_placement, - interruptible); -} - -/** - * vmw_dmabuf_pin_in_start_of_vram - Move a buffer to start of vram. - * - * This function takes the reservation_sem in write mode. - * Flushes and unpins the query bo to avoid failures. - * - * @dev_priv: Driver private. - * @buf: DMA buffer to pin. - * @interruptible: Use interruptible wait. - * - * Returns - * -ERESTARTSYS if interrupted by a signal. - */ -int vmw_dmabuf_pin_in_start_of_vram(struct vmw_private *dev_priv, - struct vmw_dma_buffer *buf, - bool interruptible) -{ - struct ttm_operation_ctx ctx = {interruptible, false }; - struct ttm_buffer_object *bo = &buf->base; - struct ttm_placement placement; - struct ttm_place place; - int ret = 0; - uint32_t new_flags; - - place = vmw_vram_placement.placement[0]; - place.lpfn = bo->num_pages; - placement.num_placement = 1; - placement.placement = &place; - placement.num_busy_placement = 1; - placement.busy_placement = &place; - - ret = ttm_write_lock(&dev_priv->reservation_sem, interruptible); - if (unlikely(ret != 0)) - return ret; - - vmw_execbuf_release_pinned_bo(dev_priv); - ret = ttm_bo_reserve(bo, interruptible, false, NULL); - if (unlikely(ret != 0)) - goto err_unlock; - - /* - * Is this buffer already in vram but not at the start of it? - * In that case, evict it first because TTM isn't good at handling - * that situation. - */ - if (bo->mem.mem_type == TTM_PL_VRAM && - bo->mem.start < bo->num_pages && - bo->mem.start > 0 && - buf->pin_count == 0) { - ctx.interruptible = false; - (void) ttm_bo_validate(bo, &vmw_sys_placement, &ctx); - } - - if (buf->pin_count > 0) - ret = ttm_bo_mem_compat(&placement, &bo->mem, - &new_flags) == true ? 0 : -EINVAL; - else - ret = ttm_bo_validate(bo, &placement, &ctx); - - /* For some reason we didn't end up at the start of vram */ - WARN_ON(ret == 0 && bo->offset != 0); - if (!ret) - vmw_bo_pin_reserved(buf, true); - - ttm_bo_unreserve(bo); -err_unlock: - ttm_write_unlock(&dev_priv->reservation_sem); - - return ret; -} - -/** - * vmw_dmabuf_unpin - Unpin the buffer given buffer, does not move the buffer. - * - * This function takes the reservation_sem in write mode. - * - * @dev_priv: Driver private. - * @buf: DMA buffer to unpin. - * @interruptible: Use interruptible wait. - * - * Returns - * -ERESTARTSYS if interrupted by a signal. - */ -int vmw_dmabuf_unpin(struct vmw_private *dev_priv, - struct vmw_dma_buffer *buf, - bool interruptible) -{ - struct ttm_buffer_object *bo = &buf->base; - int ret; - - ret = ttm_read_lock(&dev_priv->reservation_sem, interruptible); - if (unlikely(ret != 0)) - return ret; - - ret = ttm_bo_reserve(bo, interruptible, false, NULL); - if (unlikely(ret != 0)) - goto err; - - vmw_bo_pin_reserved(buf, false); - - ttm_bo_unreserve(bo); - -err: - ttm_read_unlock(&dev_priv->reservation_sem); - return ret; -} - -/** - * vmw_bo_get_guest_ptr - Get the guest ptr representing the current placement - * of a buffer. - * - * @bo: Pointer to a struct ttm_buffer_object. Must be pinned or reserved. - * @ptr: SVGAGuestPtr returning the result. - */ -void vmw_bo_get_guest_ptr(const struct ttm_buffer_object *bo, - SVGAGuestPtr *ptr) -{ - if (bo->mem.mem_type == TTM_PL_VRAM) { - ptr->gmrId = SVGA_GMR_FRAMEBUFFER; - ptr->offset = bo->offset; - } else { - ptr->gmrId = bo->mem.start; - ptr->offset = 0; - } -} - - -/** - * vmw_bo_pin_reserved - Pin or unpin a buffer object without moving it. - * - * @vbo: The buffer object. Must be reserved. - * @pin: Whether to pin or unpin. - * - */ -void vmw_bo_pin_reserved(struct vmw_dma_buffer *vbo, bool pin) -{ - struct ttm_operation_ctx ctx = { false, true }; - struct ttm_place pl; - struct ttm_placement placement; - struct ttm_buffer_object *bo = &vbo->base; - uint32_t old_mem_type = bo->mem.mem_type; - int ret; - - lockdep_assert_held(&bo->resv->lock.base); - - if (pin) { - if (vbo->pin_count++ > 0) - return; - } else { - WARN_ON(vbo->pin_count <= 0); - if (--vbo->pin_count > 0) - return; - } - - pl.fpfn = 0; - pl.lpfn = 0; - pl.flags = TTM_PL_FLAG_VRAM | VMW_PL_FLAG_GMR | VMW_PL_FLAG_MOB - | TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED; - if (pin) - pl.flags |= TTM_PL_FLAG_NO_EVICT; - - memset(&placement, 0, sizeof(placement)); - placement.num_placement = 1; - placement.placement = &pl; - - ret = ttm_bo_validate(bo, &placement, &ctx); - - BUG_ON(ret != 0 || bo->mem.mem_type != old_mem_type); -} - - -/* - * vmw_dma_buffer_unmap - Tear down a cached buffer object map. - * - * @vbo: The buffer object whose map we are tearing down. - * - * This function tears down a cached map set up using - * vmw_dma_buffer_map_and_cache(). - */ -void vmw_dma_buffer_unmap(struct vmw_dma_buffer *vbo) -{ - if (vbo->map.bo == NULL) - return; - - ttm_bo_kunmap(&vbo->map); -} - - -/* - * vmw_dma_buffer_map_and_cache - Map a buffer object and cache the map - * - * @vbo: The buffer object to map - * Return: A kernel virtual address or NULL if mapping failed. - * - * This function maps a buffer object into the kernel address space, or - * returns the virtual kernel address of an already existing map. The virtual - * address remains valid as long as the buffer object is pinned or reserved. - * The cached map is torn down on either - * 1) Buffer object move - * 2) Buffer object swapout - * 3) Buffer object destruction - * - */ -void *vmw_dma_buffer_map_and_cache(struct vmw_dma_buffer *vbo) -{ - struct ttm_buffer_object *bo = &vbo->base; - bool not_used; - void *virtual; - int ret; - - virtual = ttm_kmap_obj_virtual(&vbo->map, ¬_used); - if (virtual) - return virtual; - - ret = ttm_bo_kmap(bo, 0, bo->num_pages, &vbo->map); - if (ret) - DRM_ERROR("Buffer object map failed: %d.\n", ret); - - return ttm_kmap_obj_virtual(&vbo->map, ¬_used); -} diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 09cc721160c4..4f18304226bc 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -153,9 +153,9 @@ static const struct drm_ioctl_desc vmw_ioctls[] = { VMW_IOCTL_DEF(VMW_GET_PARAM, vmw_getparam_ioctl, DRM_AUTH | DRM_RENDER_ALLOW), - VMW_IOCTL_DEF(VMW_ALLOC_DMABUF, vmw_dmabuf_alloc_ioctl, + VMW_IOCTL_DEF(VMW_ALLOC_DMABUF, vmw_bo_alloc_ioctl, DRM_AUTH | DRM_RENDER_ALLOW), - VMW_IOCTL_DEF(VMW_UNREF_DMABUF, vmw_dmabuf_unref_ioctl, + VMW_IOCTL_DEF(VMW_UNREF_DMABUF, vmw_bo_unref_ioctl, DRM_RENDER_ALLOW), VMW_IOCTL_DEF(VMW_CURSOR_BYPASS, vmw_kms_cursor_bypass_ioctl, @@ -219,7 +219,7 @@ static const struct drm_ioctl_desc vmw_ioctls[] = { vmw_gb_surface_reference_ioctl, DRM_AUTH | DRM_RENDER_ALLOW), VMW_IOCTL_DEF(VMW_SYNCCPU, - vmw_user_dmabuf_synccpu_ioctl, + vmw_user_bo_synccpu_ioctl, DRM_RENDER_ALLOW), VMW_IOCTL_DEF(VMW_CREATE_EXTENDED_CONTEXT, vmw_extended_context_define_ioctl, @@ -321,7 +321,7 @@ static void vmw_print_capabilities(uint32_t capabilities) static int vmw_dummy_query_bo_create(struct vmw_private *dev_priv) { int ret; - struct vmw_dma_buffer *vbo; + struct vmw_buffer_object *vbo; struct ttm_bo_kmap_obj map; volatile SVGA3dQueryResult *result; bool dummy; @@ -335,9 +335,9 @@ static int vmw_dummy_query_bo_create(struct vmw_private *dev_priv) if (!vbo) return -ENOMEM; - ret = vmw_dmabuf_init(dev_priv, vbo, PAGE_SIZE, - &vmw_sys_ne_placement, false, - &vmw_dmabuf_bo_free); + ret = vmw_bo_init(dev_priv, vbo, PAGE_SIZE, + &vmw_sys_ne_placement, false, + &vmw_bo_bo_free); if (unlikely(ret != 0)) return ret; @@ -358,7 +358,7 @@ static int vmw_dummy_query_bo_create(struct vmw_private *dev_priv) if (unlikely(ret != 0)) { DRM_ERROR("Dummy query buffer map failed.\n"); - vmw_dmabuf_unreference(&vbo); + vmw_bo_unreference(&vbo); } else dev_priv->dummy_query_bo = vbo; @@ -460,7 +460,7 @@ static void vmw_release_device_early(struct vmw_private *dev_priv) BUG_ON(dev_priv->pinned_bo != NULL); - vmw_dmabuf_unreference(&dev_priv->dummy_query_bo); + vmw_bo_unreference(&dev_priv->dummy_query_bo); if (dev_priv->cman) vmw_cmdbuf_remove_pool(dev_priv->cman); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index 5fcbe1620d50..25c2f668ad6c 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -86,7 +86,7 @@ struct vmw_fpriv { bool gb_aware; }; -struct vmw_dma_buffer { +struct vmw_buffer_object { struct ttm_buffer_object base; struct list_head res_list; s32 pin_count; @@ -120,7 +120,7 @@ struct vmw_resource { unsigned long backup_size; bool res_dirty; /* Protected by backup buffer reserved */ bool backup_dirty; /* Protected by backup buffer reserved */ - struct vmw_dma_buffer *backup; + struct vmw_buffer_object *backup; unsigned long backup_offset; unsigned long pin_count; /* Protected by resource reserved */ const struct vmw_res_func *func; @@ -304,7 +304,7 @@ struct vmw_sw_context{ uint32_t cmd_bounce_size; struct list_head resource_list; struct list_head ctx_resource_list; /* For contexts and cotables */ - struct vmw_dma_buffer *cur_query_bo; + struct vmw_buffer_object *cur_query_bo; struct list_head res_relocations; uint32_t *buf_start; struct vmw_res_cache_entry res_cache[vmw_res_max]; @@ -315,7 +315,7 @@ struct vmw_sw_context{ bool staged_bindings_inuse; struct list_head staged_cmd_res; struct vmw_resource_val_node *dx_ctx_node; - struct vmw_dma_buffer *dx_query_mob; + struct vmw_buffer_object *dx_query_mob; struct vmw_resource *dx_query_ctx; struct vmw_cmdbuf_res_manager *man; }; @@ -513,8 +513,8 @@ struct vmw_private { * are protected by the cmdbuf mutex. */ - struct vmw_dma_buffer *dummy_query_bo; - struct vmw_dma_buffer *pinned_bo; + struct vmw_buffer_object *dummy_query_bo; + struct vmw_buffer_object *pinned_bo; uint32_t query_cid; uint32_t query_cid_valid; bool dummy_query_bo_pinned; @@ -623,43 +623,43 @@ extern int vmw_user_lookup_handle(struct vmw_private *dev_priv, struct ttm_object_file *tfile, uint32_t handle, struct vmw_surface **out_surf, - struct vmw_dma_buffer **out_buf); + struct vmw_buffer_object **out_buf); extern int vmw_user_resource_lookup_handle( struct vmw_private *dev_priv, struct ttm_object_file *tfile, uint32_t handle, const struct vmw_user_resource_conv *converter, struct vmw_resource **p_res); -extern void vmw_dmabuf_bo_free(struct ttm_buffer_object *bo); -extern int vmw_dmabuf_init(struct vmw_private *dev_priv, - struct vmw_dma_buffer *vmw_bo, - size_t size, struct ttm_placement *placement, - bool interuptable, - void (*bo_free) (struct ttm_buffer_object *bo)); -extern int vmw_user_dmabuf_verify_access(struct ttm_buffer_object *bo, - struct ttm_object_file *tfile); -extern int vmw_user_dmabuf_alloc(struct vmw_private *dev_priv, - struct ttm_object_file *tfile, - uint32_t size, - bool shareable, - uint32_t *handle, - struct vmw_dma_buffer **p_dma_buf, - struct ttm_base_object **p_base); -extern int vmw_user_dmabuf_reference(struct ttm_object_file *tfile, - struct vmw_dma_buffer *dma_buf, - uint32_t *handle); -extern int vmw_dmabuf_alloc_ioctl(struct drm_device *dev, void *data, - struct drm_file *file_priv); -extern int vmw_dmabuf_unref_ioctl(struct drm_device *dev, void *data, - struct drm_file *file_priv); -extern int vmw_user_dmabuf_synccpu_ioctl(struct drm_device *dev, void *data, - struct drm_file *file_priv); -extern uint32_t vmw_dmabuf_validate_node(struct ttm_buffer_object *bo, - uint32_t cur_validate_node); -extern void vmw_dmabuf_validate_clear(struct ttm_buffer_object *bo); -extern int vmw_user_dmabuf_lookup(struct ttm_object_file *tfile, - uint32_t id, struct vmw_dma_buffer **out, - struct ttm_base_object **base); +extern void vmw_bo_bo_free(struct ttm_buffer_object *bo); +extern int vmw_bo_init(struct vmw_private *dev_priv, + struct vmw_buffer_object *vmw_bo, + size_t size, struct ttm_placement *placement, + bool interuptable, + void (*bo_free)(struct ttm_buffer_object *bo)); +extern int vmw_user_bo_verify_access(struct ttm_buffer_object *bo, + struct ttm_object_file *tfile); +extern int vmw_user_bo_alloc(struct vmw_private *dev_priv, + struct ttm_object_file *tfile, + uint32_t size, + bool shareable, + uint32_t *handle, + struct vmw_buffer_object **p_dma_buf, + struct ttm_base_object **p_base); +extern int vmw_user_bo_reference(struct ttm_object_file *tfile, + struct vmw_buffer_object *dma_buf, + uint32_t *handle); +extern int vmw_bo_alloc_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_priv); +extern int vmw_bo_unref_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_priv); +extern int vmw_user_bo_synccpu_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_priv); +extern uint32_t vmw_bo_validate_node(struct ttm_buffer_object *bo, + uint32_t cur_validate_node); +extern void vmw_bo_validate_clear(struct ttm_buffer_object *bo); +extern int vmw_user_bo_lookup(struct ttm_object_file *tfile, + uint32_t id, struct vmw_buffer_object **out, + struct ttm_base_object **base); extern int vmw_stream_claim_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv); extern int vmw_stream_unref_ioctl(struct drm_device *dev, void *data, @@ -670,43 +670,43 @@ extern int vmw_user_stream_lookup(struct vmw_private *dev_priv, struct vmw_resource **out); extern void vmw_resource_unreserve(struct vmw_resource *res, bool switch_backup, - struct vmw_dma_buffer *new_backup, + struct vmw_buffer_object *new_backup, unsigned long new_backup_offset); extern void vmw_resource_move_notify(struct ttm_buffer_object *bo, struct ttm_mem_reg *mem); extern void vmw_query_move_notify(struct ttm_buffer_object *bo, struct ttm_mem_reg *mem); extern void vmw_resource_swap_notify(struct ttm_buffer_object *bo); -extern int vmw_query_readback_all(struct vmw_dma_buffer *dx_query_mob); +extern int vmw_query_readback_all(struct vmw_buffer_object *dx_query_mob); extern void vmw_fence_single_bo(struct ttm_buffer_object *bo, struct vmw_fence_obj *fence); extern void vmw_resource_evict_all(struct vmw_private *dev_priv); /** - * DMA buffer helper routines - vmwgfx_dmabuf.c + * Buffer object helper functions - vmwgfx_bo.c */ -extern int vmw_dmabuf_pin_in_placement(struct vmw_private *vmw_priv, - struct vmw_dma_buffer *bo, - struct ttm_placement *placement, +extern int vmw_bo_pin_in_placement(struct vmw_private *vmw_priv, + struct vmw_buffer_object *bo, + struct ttm_placement *placement, + bool interruptible); +extern int vmw_bo_pin_in_vram(struct vmw_private *dev_priv, + struct vmw_buffer_object *buf, + bool interruptible); +extern int vmw_bo_pin_in_vram_or_gmr(struct vmw_private *dev_priv, + struct vmw_buffer_object *buf, + bool interruptible); +extern int vmw_bo_pin_in_start_of_vram(struct vmw_private *vmw_priv, + struct vmw_buffer_object *bo, bool interruptible); -extern int vmw_dmabuf_pin_in_vram(struct vmw_private *dev_priv, - struct vmw_dma_buffer *buf, - bool interruptible); -extern int vmw_dmabuf_pin_in_vram_or_gmr(struct vmw_private *dev_priv, - struct vmw_dma_buffer *buf, - bool interruptible); -extern int vmw_dmabuf_pin_in_start_of_vram(struct vmw_private *vmw_priv, - struct vmw_dma_buffer *bo, - bool interruptible); -extern int vmw_dmabuf_unpin(struct vmw_private *vmw_priv, - struct vmw_dma_buffer *bo, - bool interruptible); +extern int vmw_bo_unpin(struct vmw_private *vmw_priv, + struct vmw_buffer_object *bo, + bool interruptible); extern void vmw_bo_get_guest_ptr(const struct ttm_buffer_object *buf, SVGAGuestPtr *ptr); -extern void vmw_bo_pin_reserved(struct vmw_dma_buffer *bo, bool pin); -extern void *vmw_dma_buffer_map_and_cache(struct vmw_dma_buffer *vbo); -extern void vmw_dma_buffer_unmap(struct vmw_dma_buffer *vbo); +extern void vmw_bo_pin_reserved(struct vmw_buffer_object *bo, bool pin); +extern void *vmw_buffer_object_map_and_cache(struct vmw_buffer_object *vbo); +extern void vmw_buffer_object_unmap(struct vmw_buffer_object *vbo); /** * Misc Ioctl functionality - vmwgfx_ioctl.c @@ -758,7 +758,7 @@ extern void vmw_ttm_global_release(struct vmw_private *dev_priv); extern int vmw_mmap(struct file *filp, struct vm_area_struct *vma); /** - * TTM buffer object driver - vmwgfx_buffer.c + * TTM buffer object driver - vmwgfx_ttm_buffer.c */ extern const size_t vmw_tt_size; @@ -1041,8 +1041,8 @@ vmw_context_binding_state(struct vmw_resource *ctx); extern void vmw_dx_context_scrub_cotables(struct vmw_resource *ctx, bool readback); extern int vmw_context_bind_dx_query(struct vmw_resource *ctx_res, - struct vmw_dma_buffer *mob); -extern struct vmw_dma_buffer * + struct vmw_buffer_object *mob); +extern struct vmw_buffer_object * vmw_context_get_dx_query_mob(struct vmw_resource *ctx_res); @@ -1243,9 +1243,9 @@ static inline struct vmw_surface *vmw_surface_reference(struct vmw_surface *srf) return srf; } -static inline void vmw_dmabuf_unreference(struct vmw_dma_buffer **buf) +static inline void vmw_bo_unreference(struct vmw_buffer_object **buf) { - struct vmw_dma_buffer *tmp_buf = *buf; + struct vmw_buffer_object *tmp_buf = *buf; *buf = NULL; if (tmp_buf != NULL) { @@ -1255,7 +1255,8 @@ static inline void vmw_dmabuf_unreference(struct vmw_dma_buffer **buf) } } -static inline struct vmw_dma_buffer *vmw_dmabuf_reference(struct vmw_dma_buffer *buf) +static inline struct vmw_buffer_object * +vmw_bo_reference(struct vmw_buffer_object *buf) { if (ttm_bo_reference(&buf->base)) return buf; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index c9d5cc237124..a8b194655c40 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -92,7 +92,7 @@ struct vmw_resource_val_node { struct list_head head; struct drm_hash_item hash; struct vmw_resource *res; - struct vmw_dma_buffer *new_backup; + struct vmw_buffer_object *new_backup; struct vmw_ctx_binding_state *staged_bindings; unsigned long new_backup_offset; u32 first_usage : 1; @@ -126,9 +126,9 @@ static int vmw_resource_context_res_add(struct vmw_private *dev_priv, static int vmw_translate_mob_ptr(struct vmw_private *dev_priv, struct vmw_sw_context *sw_context, SVGAMobId *id, - struct vmw_dma_buffer **vmw_bo_p); + struct vmw_buffer_object **vmw_bo_p); static int vmw_bo_to_validate_list(struct vmw_sw_context *sw_context, - struct vmw_dma_buffer *vbo, + struct vmw_buffer_object *vbo, bool validate_as_mob, uint32_t *p_val_node); /** @@ -185,7 +185,7 @@ static void vmw_resources_unreserve(struct vmw_sw_context *sw_context, } vmw_resource_unreserve(res, switch_backup, val->new_backup, val->new_backup_offset); - vmw_dmabuf_unreference(&val->new_backup); + vmw_bo_unreference(&val->new_backup); } } @@ -423,7 +423,7 @@ static int vmw_resource_context_res_add(struct vmw_private *dev_priv, } if (dev_priv->has_dx && vmw_res_type(ctx) == vmw_res_dx_context) { - struct vmw_dma_buffer *dx_query_mob; + struct vmw_buffer_object *dx_query_mob; dx_query_mob = vmw_context_get_dx_query_mob(ctx); if (dx_query_mob) @@ -544,7 +544,7 @@ static int vmw_cmd_ok(struct vmw_private *dev_priv, * submission is reached. */ static int vmw_bo_to_validate_list(struct vmw_sw_context *sw_context, - struct vmw_dma_buffer *vbo, + struct vmw_buffer_object *vbo, bool validate_as_mob, uint32_t *p_val_node) { @@ -616,7 +616,7 @@ static int vmw_resources_reserve(struct vmw_sw_context *sw_context) return ret; if (res->backup) { - struct vmw_dma_buffer *vbo = res->backup; + struct vmw_buffer_object *vbo = res->backup; ret = vmw_bo_to_validate_list (sw_context, vbo, @@ -628,7 +628,7 @@ static int vmw_resources_reserve(struct vmw_sw_context *sw_context) } if (sw_context->dx_query_mob) { - struct vmw_dma_buffer *expected_dx_query_mob; + struct vmw_buffer_object *expected_dx_query_mob; expected_dx_query_mob = vmw_context_get_dx_query_mob(sw_context->dx_query_ctx); @@ -657,7 +657,7 @@ static int vmw_resources_validate(struct vmw_sw_context *sw_context) list_for_each_entry(val, &sw_context->resource_list, head) { struct vmw_resource *res = val->res; - struct vmw_dma_buffer *backup = res->backup; + struct vmw_buffer_object *backup = res->backup; ret = vmw_resource_validate(res); if (unlikely(ret != 0)) { @@ -668,7 +668,7 @@ static int vmw_resources_validate(struct vmw_sw_context *sw_context) /* Check if the resource switched backup buffer */ if (backup && res->backup && (backup != res->backup)) { - struct vmw_dma_buffer *vbo = res->backup; + struct vmw_buffer_object *vbo = res->backup; ret = vmw_bo_to_validate_list (sw_context, vbo, @@ -821,7 +821,7 @@ out_no_reloc: static int vmw_rebind_all_dx_query(struct vmw_resource *ctx_res) { struct vmw_private *dev_priv = ctx_res->dev_priv; - struct vmw_dma_buffer *dx_query_mob; + struct vmw_buffer_object *dx_query_mob; struct { SVGA3dCmdHeader header; SVGA3dCmdDXBindAllQuery body; @@ -1152,7 +1152,7 @@ static int vmw_cmd_present_check(struct vmw_private *dev_priv, * command batch. */ static int vmw_query_bo_switch_prepare(struct vmw_private *dev_priv, - struct vmw_dma_buffer *new_query_bo, + struct vmw_buffer_object *new_query_bo, struct vmw_sw_context *sw_context) { struct vmw_res_cache_entry *ctx_entry = @@ -1234,7 +1234,7 @@ static void vmw_query_bo_switch_commit(struct vmw_private *dev_priv, if (dev_priv->pinned_bo != sw_context->cur_query_bo) { if (dev_priv->pinned_bo) { vmw_bo_pin_reserved(dev_priv->pinned_bo, false); - vmw_dmabuf_unreference(&dev_priv->pinned_bo); + vmw_bo_unreference(&dev_priv->pinned_bo); } if (!sw_context->needs_post_query_barrier) { @@ -1256,7 +1256,7 @@ static void vmw_query_bo_switch_commit(struct vmw_private *dev_priv, dev_priv->query_cid = sw_context->last_query_ctx->id; dev_priv->query_cid_valid = true; dev_priv->pinned_bo = - vmw_dmabuf_reference(sw_context->cur_query_bo); + vmw_bo_reference(sw_context->cur_query_bo); } } } @@ -1282,15 +1282,14 @@ static void vmw_query_bo_switch_commit(struct vmw_private *dev_priv, static int vmw_translate_mob_ptr(struct vmw_private *dev_priv, struct vmw_sw_context *sw_context, SVGAMobId *id, - struct vmw_dma_buffer **vmw_bo_p) + struct vmw_buffer_object **vmw_bo_p) { - struct vmw_dma_buffer *vmw_bo = NULL; + struct vmw_buffer_object *vmw_bo = NULL; uint32_t handle = *id; struct vmw_relocation *reloc; int ret; - ret = vmw_user_dmabuf_lookup(sw_context->fp->tfile, handle, &vmw_bo, - NULL); + ret = vmw_user_bo_lookup(sw_context->fp->tfile, handle, &vmw_bo, NULL); if (unlikely(ret != 0)) { DRM_ERROR("Could not find or use MOB buffer.\n"); ret = -EINVAL; @@ -1316,7 +1315,7 @@ static int vmw_translate_mob_ptr(struct vmw_private *dev_priv, return 0; out_no_reloc: - vmw_dmabuf_unreference(&vmw_bo); + vmw_bo_unreference(&vmw_bo); *vmw_bo_p = NULL; return ret; } @@ -1343,15 +1342,14 @@ out_no_reloc: static int vmw_translate_guest_ptr(struct vmw_private *dev_priv, struct vmw_sw_context *sw_context, SVGAGuestPtr *ptr, - struct vmw_dma_buffer **vmw_bo_p) + struct vmw_buffer_object **vmw_bo_p) { - struct vmw_dma_buffer *vmw_bo = NULL; + struct vmw_buffer_object *vmw_bo = NULL; uint32_t handle = ptr->gmrId; struct vmw_relocation *reloc; int ret; - ret = vmw_user_dmabuf_lookup(sw_context->fp->tfile, handle, &vmw_bo, - NULL); + ret = vmw_user_bo_lookup(sw_context->fp->tfile, handle, &vmw_bo, NULL); if (unlikely(ret != 0)) { DRM_ERROR("Could not find or use GMR region.\n"); ret = -EINVAL; @@ -1376,7 +1374,7 @@ static int vmw_translate_guest_ptr(struct vmw_private *dev_priv, return 0; out_no_reloc: - vmw_dmabuf_unreference(&vmw_bo); + vmw_bo_unreference(&vmw_bo); *vmw_bo_p = NULL; return ret; } @@ -1447,7 +1445,7 @@ static int vmw_cmd_dx_bind_query(struct vmw_private *dev_priv, SVGA3dCmdDXBindQuery q; } *cmd; - struct vmw_dma_buffer *vmw_bo; + struct vmw_buffer_object *vmw_bo; int ret; @@ -1466,7 +1464,7 @@ static int vmw_cmd_dx_bind_query(struct vmw_private *dev_priv, sw_context->dx_query_mob = vmw_bo; sw_context->dx_query_ctx = sw_context->dx_ctx_node->res; - vmw_dmabuf_unreference(&vmw_bo); + vmw_bo_unreference(&vmw_bo); return ret; } @@ -1549,7 +1547,7 @@ static int vmw_cmd_end_gb_query(struct vmw_private *dev_priv, struct vmw_sw_context *sw_context, SVGA3dCmdHeader *header) { - struct vmw_dma_buffer *vmw_bo; + struct vmw_buffer_object *vmw_bo; struct vmw_query_cmd { SVGA3dCmdHeader header; SVGA3dCmdEndGBQuery q; @@ -1569,7 +1567,7 @@ static int vmw_cmd_end_gb_query(struct vmw_private *dev_priv, ret = vmw_query_bo_switch_prepare(dev_priv, vmw_bo, sw_context); - vmw_dmabuf_unreference(&vmw_bo); + vmw_bo_unreference(&vmw_bo); return ret; } @@ -1584,7 +1582,7 @@ static int vmw_cmd_end_query(struct vmw_private *dev_priv, struct vmw_sw_context *sw_context, SVGA3dCmdHeader *header) { - struct vmw_dma_buffer *vmw_bo; + struct vmw_buffer_object *vmw_bo; struct vmw_query_cmd { SVGA3dCmdHeader header; SVGA3dCmdEndQuery q; @@ -1623,7 +1621,7 @@ static int vmw_cmd_end_query(struct vmw_private *dev_priv, ret = vmw_query_bo_switch_prepare(dev_priv, vmw_bo, sw_context); - vmw_dmabuf_unreference(&vmw_bo); + vmw_bo_unreference(&vmw_bo); return ret; } @@ -1638,7 +1636,7 @@ static int vmw_cmd_wait_gb_query(struct vmw_private *dev_priv, struct vmw_sw_context *sw_context, SVGA3dCmdHeader *header) { - struct vmw_dma_buffer *vmw_bo; + struct vmw_buffer_object *vmw_bo; struct vmw_query_cmd { SVGA3dCmdHeader header; SVGA3dCmdWaitForGBQuery q; @@ -1656,7 +1654,7 @@ static int vmw_cmd_wait_gb_query(struct vmw_private *dev_priv, if (unlikely(ret != 0)) return ret; - vmw_dmabuf_unreference(&vmw_bo); + vmw_bo_unreference(&vmw_bo); return 0; } @@ -1671,7 +1669,7 @@ static int vmw_cmd_wait_query(struct vmw_private *dev_priv, struct vmw_sw_context *sw_context, SVGA3dCmdHeader *header) { - struct vmw_dma_buffer *vmw_bo; + struct vmw_buffer_object *vmw_bo; struct vmw_query_cmd { SVGA3dCmdHeader header; SVGA3dCmdWaitForQuery q; @@ -1708,7 +1706,7 @@ static int vmw_cmd_wait_query(struct vmw_private *dev_priv, if (unlikely(ret != 0)) return ret; - vmw_dmabuf_unreference(&vmw_bo); + vmw_bo_unreference(&vmw_bo); return 0; } @@ -1716,7 +1714,7 @@ static int vmw_cmd_dma(struct vmw_private *dev_priv, struct vmw_sw_context *sw_context, SVGA3dCmdHeader *header) { - struct vmw_dma_buffer *vmw_bo = NULL; + struct vmw_buffer_object *vmw_bo = NULL; struct vmw_surface *srf = NULL; struct vmw_dma_cmd { SVGA3dCmdHeader header; @@ -1768,7 +1766,7 @@ static int vmw_cmd_dma(struct vmw_private *dev_priv, header); out_no_surface: - vmw_dmabuf_unreference(&vmw_bo); + vmw_bo_unreference(&vmw_bo); return ret; } @@ -1887,7 +1885,7 @@ static int vmw_cmd_check_define_gmrfb(struct vmw_private *dev_priv, struct vmw_sw_context *sw_context, void *buf) { - struct vmw_dma_buffer *vmw_bo; + struct vmw_buffer_object *vmw_bo; int ret; struct { @@ -1901,7 +1899,7 @@ static int vmw_cmd_check_define_gmrfb(struct vmw_private *dev_priv, if (unlikely(ret != 0)) return ret; - vmw_dmabuf_unreference(&vmw_bo); + vmw_bo_unreference(&vmw_bo); return ret; } @@ -1928,7 +1926,7 @@ static int vmw_cmd_res_switch_backup(struct vmw_private *dev_priv, uint32_t *buf_id, unsigned long backup_offset) { - struct vmw_dma_buffer *dma_buf; + struct vmw_buffer_object *dma_buf; int ret; ret = vmw_translate_mob_ptr(dev_priv, sw_context, buf_id, &dma_buf); @@ -1939,7 +1937,7 @@ static int vmw_cmd_res_switch_backup(struct vmw_private *dev_priv, if (val_node->first_usage) val_node->no_buffer_needed = true; - vmw_dmabuf_unreference(&val_node->new_backup); + vmw_bo_unreference(&val_node->new_backup); val_node->new_backup = dma_buf; val_node->new_backup_offset = backup_offset; @@ -3701,8 +3699,8 @@ int vmw_validate_single_buffer(struct vmw_private *dev_priv, bool interruptible, bool validate_as_mob) { - struct vmw_dma_buffer *vbo = container_of(bo, struct vmw_dma_buffer, - base); + struct vmw_buffer_object *vbo = + container_of(bo, struct vmw_buffer_object, base); struct ttm_operation_ctx ctx = { interruptible, true }; int ret; @@ -4423,7 +4421,7 @@ void __vmw_execbuf_release_pinned_bo(struct vmw_private *dev_priv, ttm_bo_unref(&query_val.bo); ttm_bo_unref(&pinned_val.bo); - vmw_dmabuf_unreference(&dev_priv->pinned_bo); + vmw_bo_unreference(&dev_priv->pinned_bo); out_unlock: return; @@ -4432,7 +4430,7 @@ out_no_emit: out_no_reserve: ttm_bo_unref(&query_val.bo); ttm_bo_unref(&pinned_val.bo); - vmw_dmabuf_unreference(&dev_priv->pinned_bo); + vmw_bo_unreference(&dev_priv->pinned_bo); } /** diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c index 9b7e0aca5f84..dcde4985c574 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c @@ -42,7 +42,7 @@ struct vmw_fb_par { void *vmalloc; struct mutex bo_mutex; - struct vmw_dma_buffer *vmw_bo; + struct vmw_buffer_object *vmw_bo; unsigned bo_size; struct drm_framebuffer *set_fb; struct drm_display_mode *set_mode; @@ -184,7 +184,7 @@ static void vmw_fb_dirty_flush(struct work_struct *work) struct drm_clip_rect clip; struct drm_framebuffer *cur_fb; u8 *src_ptr, *dst_ptr; - struct vmw_dma_buffer *vbo = par->vmw_bo; + struct vmw_buffer_object *vbo = par->vmw_bo; void *virtual; if (!READ_ONCE(par->dirty.active)) @@ -197,7 +197,7 @@ static void vmw_fb_dirty_flush(struct work_struct *work) (void) ttm_read_lock(&vmw_priv->reservation_sem, false); (void) ttm_bo_reserve(&vbo->base, false, false, NULL); - virtual = vmw_dma_buffer_map_and_cache(vbo); + virtual = vmw_buffer_object_map_and_cache(vbo); if (!virtual) goto out_unreserve; @@ -391,9 +391,9 @@ static void vmw_fb_imageblit(struct fb_info *info, const struct fb_image *image) */ static int vmw_fb_create_bo(struct vmw_private *vmw_priv, - size_t size, struct vmw_dma_buffer **out) + size_t size, struct vmw_buffer_object **out) { - struct vmw_dma_buffer *vmw_bo; + struct vmw_buffer_object *vmw_bo; int ret; (void) ttm_write_lock(&vmw_priv->reservation_sem, false); @@ -404,10 +404,10 @@ static int vmw_fb_create_bo(struct vmw_private *vmw_priv, goto err_unlock; } - ret = vmw_dmabuf_init(vmw_priv, vmw_bo, size, + ret = vmw_bo_init(vmw_priv, vmw_bo, size, &vmw_sys_placement, false, - &vmw_dmabuf_bo_free); + &vmw_bo_bo_free); if (unlikely(ret != 0)) goto err_unlock; /* init frees the buffer on failure */ @@ -491,7 +491,7 @@ static int vmw_fb_kms_detach(struct vmw_fb_par *par, } if (par->vmw_bo && detach_bo && unref_bo) - vmw_dmabuf_unreference(&par->vmw_bo); + vmw_bo_unreference(&par->vmw_bo); return 0; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c index c5e8eae0dbe2..5e0c8f775c92 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c @@ -377,8 +377,8 @@ int vmw_present_readback_ioctl(struct drm_device *dev, void *data, } vfb = vmw_framebuffer_to_vfb(fb); - if (!vfb->dmabuf) { - DRM_ERROR("Framebuffer not dmabuf backed.\n"); + if (!vfb->bo) { + DRM_ERROR("Framebuffer not buffer backed.\n"); ret = -EINVAL; goto out_no_ttm_lock; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index ef96ba7432ad..7a32be0cef14 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -85,10 +85,10 @@ static int vmw_cursor_update_image(struct vmw_private *dev_priv, return 0; } -static int vmw_cursor_update_dmabuf(struct vmw_private *dev_priv, - struct vmw_dma_buffer *dmabuf, - u32 width, u32 height, - u32 hotspotX, u32 hotspotY) +static int vmw_cursor_update_bo(struct vmw_private *dev_priv, + struct vmw_buffer_object *bo, + u32 width, u32 height, + u32 hotspotX, u32 hotspotY) { struct ttm_bo_kmap_obj map; unsigned long kmap_offset; @@ -100,13 +100,13 @@ static int vmw_cursor_update_dmabuf(struct vmw_private *dev_priv, kmap_offset = 0; kmap_num = (width*height*4 + PAGE_SIZE - 1) >> PAGE_SHIFT; - ret = ttm_bo_reserve(&dmabuf->base, true, false, NULL); + ret = ttm_bo_reserve(&bo->base, true, false, NULL); if (unlikely(ret != 0)) { DRM_ERROR("reserve failed\n"); return -EINVAL; } - ret = ttm_bo_kmap(&dmabuf->base, kmap_offset, kmap_num, &map); + ret = ttm_bo_kmap(&bo->base, kmap_offset, kmap_num, &map); if (unlikely(ret != 0)) goto err_unreserve; @@ -116,7 +116,7 @@ static int vmw_cursor_update_dmabuf(struct vmw_private *dev_priv, ttm_bo_kunmap(&map); err_unreserve: - ttm_bo_unreserve(&dmabuf->base); + ttm_bo_unreserve(&bo->base); return ret; } @@ -352,13 +352,13 @@ vmw_du_cursor_plane_prepare_fb(struct drm_plane *plane, if (vps->surf) vmw_surface_unreference(&vps->surf); - if (vps->dmabuf) - vmw_dmabuf_unreference(&vps->dmabuf); + if (vps->bo) + vmw_bo_unreference(&vps->bo); if (fb) { - if (vmw_framebuffer_to_vfb(fb)->dmabuf) { - vps->dmabuf = vmw_framebuffer_to_vfbd(fb)->buffer; - vmw_dmabuf_reference(vps->dmabuf); + if (vmw_framebuffer_to_vfb(fb)->bo) { + vps->bo = vmw_framebuffer_to_vfbd(fb)->buffer; + vmw_bo_reference(vps->bo); } else { vps->surf = vmw_framebuffer_to_vfbs(fb)->surface; vmw_surface_reference(vps->surf); @@ -390,7 +390,7 @@ vmw_du_cursor_plane_atomic_update(struct drm_plane *plane, } du->cursor_surface = vps->surf; - du->cursor_dmabuf = vps->dmabuf; + du->cursor_bo = vps->bo; if (vps->surf) { du->cursor_age = du->cursor_surface->snooper.age; @@ -399,11 +399,11 @@ vmw_du_cursor_plane_atomic_update(struct drm_plane *plane, vps->surf->snooper.image, 64, 64, hotspot_x, hotspot_y); - } else if (vps->dmabuf) { - ret = vmw_cursor_update_dmabuf(dev_priv, vps->dmabuf, - plane->state->crtc_w, - plane->state->crtc_h, - hotspot_x, hotspot_y); + } else if (vps->bo) { + ret = vmw_cursor_update_bo(dev_priv, vps->bo, + plane->state->crtc_w, + plane->state->crtc_h, + hotspot_x, hotspot_y); } else { vmw_cursor_update_position(dev_priv, false, 0, 0); return; @@ -519,7 +519,7 @@ int vmw_du_cursor_plane_atomic_check(struct drm_plane *plane, ret = -EINVAL; } - if (!vmw_framebuffer_to_vfb(fb)->dmabuf) + if (!vmw_framebuffer_to_vfb(fb)->bo) surface = vmw_framebuffer_to_vfbs(fb)->surface; if (surface && !surface->snooper.image) { @@ -687,8 +687,8 @@ vmw_du_plane_duplicate_state(struct drm_plane *plane) if (vps->surf) (void) vmw_surface_reference(vps->surf); - if (vps->dmabuf) - (void) vmw_dmabuf_reference(vps->dmabuf); + if (vps->bo) + (void) vmw_bo_reference(vps->bo); state = &vps->base; @@ -745,8 +745,8 @@ vmw_du_plane_destroy_state(struct drm_plane *plane, if (vps->surf) vmw_surface_unreference(&vps->surf); - if (vps->dmabuf) - vmw_dmabuf_unreference(&vps->dmabuf); + if (vps->bo) + vmw_bo_unreference(&vps->bo); drm_atomic_helper_plane_destroy_state(plane, state); } @@ -902,12 +902,12 @@ static int vmw_framebuffer_surface_dirty(struct drm_framebuffer *framebuffer, /** * vmw_kms_readback - Perform a readback from the screen system to - * a dma-buffer backed framebuffer. + * a buffer-object backed framebuffer. * * @dev_priv: Pointer to the device private structure. * @file_priv: Pointer to a struct drm_file identifying the caller. * Must be set to NULL if @user_fence_rep is NULL. - * @vfb: Pointer to the dma-buffer backed framebuffer. + * @vfb: Pointer to the buffer-object backed framebuffer. * @user_fence_rep: User-space provided structure for fence information. * Must be set to non-NULL if @file_priv is non-NULL. * @vclips: Array of clip rects. @@ -951,7 +951,7 @@ static int vmw_kms_new_framebuffer_surface(struct vmw_private *dev_priv, struct vmw_framebuffer **out, const struct drm_mode_fb_cmd2 *mode_cmd, - bool is_dmabuf_proxy) + bool is_bo_proxy) { struct drm_device *dev = dev_priv->dev; @@ -1019,7 +1019,7 @@ static int vmw_kms_new_framebuffer_surface(struct vmw_private *dev_priv, drm_helper_mode_fill_fb_struct(dev, &vfbs->base.base, mode_cmd); vfbs->surface = vmw_surface_reference(surface); vfbs->base.user_handle = mode_cmd->handles[0]; - vfbs->is_dmabuf_proxy = is_dmabuf_proxy; + vfbs->is_bo_proxy = is_bo_proxy; *out = &vfbs->base; @@ -1038,30 +1038,30 @@ out_err1: } /* - * Dmabuf framebuffer code + * Buffer-object framebuffer code */ -static void vmw_framebuffer_dmabuf_destroy(struct drm_framebuffer *framebuffer) +static void vmw_framebuffer_bo_destroy(struct drm_framebuffer *framebuffer) { - struct vmw_framebuffer_dmabuf *vfbd = + struct vmw_framebuffer_bo *vfbd = vmw_framebuffer_to_vfbd(framebuffer); drm_framebuffer_cleanup(framebuffer); - vmw_dmabuf_unreference(&vfbd->buffer); + vmw_bo_unreference(&vfbd->buffer); if (vfbd->base.user_obj) ttm_base_object_unref(&vfbd->base.user_obj); kfree(vfbd); } -static int vmw_framebuffer_dmabuf_dirty(struct drm_framebuffer *framebuffer, - struct drm_file *file_priv, - unsigned flags, unsigned color, - struct drm_clip_rect *clips, - unsigned num_clips) +static int vmw_framebuffer_bo_dirty(struct drm_framebuffer *framebuffer, + struct drm_file *file_priv, + unsigned int flags, unsigned int color, + struct drm_clip_rect *clips, + unsigned int num_clips) { struct vmw_private *dev_priv = vmw_priv(framebuffer->dev); - struct vmw_framebuffer_dmabuf *vfbd = + struct vmw_framebuffer_bo *vfbd = vmw_framebuffer_to_vfbd(framebuffer); struct drm_clip_rect norect; int ret, increment = 1; @@ -1092,13 +1092,13 @@ static int vmw_framebuffer_dmabuf_dirty(struct drm_framebuffer *framebuffer, true, true, NULL); break; case vmw_du_screen_object: - ret = vmw_kms_sou_do_dmabuf_dirty(dev_priv, &vfbd->base, - clips, NULL, num_clips, - increment, true, NULL, NULL); + ret = vmw_kms_sou_do_bo_dirty(dev_priv, &vfbd->base, + clips, NULL, num_clips, + increment, true, NULL, NULL); break; case vmw_du_legacy: - ret = vmw_kms_ldu_do_dmabuf_dirty(dev_priv, &vfbd->base, 0, 0, - clips, num_clips, increment); + ret = vmw_kms_ldu_do_bo_dirty(dev_priv, &vfbd->base, 0, 0, + clips, num_clips, increment); break; default: ret = -EINVAL; @@ -1114,23 +1114,23 @@ static int vmw_framebuffer_dmabuf_dirty(struct drm_framebuffer *framebuffer, return ret; } -static const struct drm_framebuffer_funcs vmw_framebuffer_dmabuf_funcs = { - .destroy = vmw_framebuffer_dmabuf_destroy, - .dirty = vmw_framebuffer_dmabuf_dirty, +static const struct drm_framebuffer_funcs vmw_framebuffer_bo_funcs = { + .destroy = vmw_framebuffer_bo_destroy, + .dirty = vmw_framebuffer_bo_dirty, }; /** - * Pin the dmabuffer in a location suitable for access by the + * Pin the bofer in a location suitable for access by the * display system. */ static int vmw_framebuffer_pin(struct vmw_framebuffer *vfb) { struct vmw_private *dev_priv = vmw_priv(vfb->base.dev); - struct vmw_dma_buffer *buf; + struct vmw_buffer_object *buf; struct ttm_placement *placement; int ret; - buf = vfb->dmabuf ? vmw_framebuffer_to_vfbd(&vfb->base)->buffer : + buf = vfb->bo ? vmw_framebuffer_to_vfbd(&vfb->base)->buffer : vmw_framebuffer_to_vfbs(&vfb->base)->surface->res.backup; if (!buf) @@ -1139,12 +1139,12 @@ static int vmw_framebuffer_pin(struct vmw_framebuffer *vfb) switch (dev_priv->active_display_unit) { case vmw_du_legacy: vmw_overlay_pause_all(dev_priv); - ret = vmw_dmabuf_pin_in_start_of_vram(dev_priv, buf, false); + ret = vmw_bo_pin_in_start_of_vram(dev_priv, buf, false); vmw_overlay_resume_all(dev_priv); break; case vmw_du_screen_object: case vmw_du_screen_target: - if (vfb->dmabuf) { + if (vfb->bo) { if (dev_priv->capabilities & SVGA_CAP_3D) { /* * Use surface DMA to get content to @@ -1160,8 +1160,7 @@ static int vmw_framebuffer_pin(struct vmw_framebuffer *vfb) placement = &vmw_mob_placement; } - return vmw_dmabuf_pin_in_placement(dev_priv, buf, placement, - false); + return vmw_bo_pin_in_placement(dev_priv, buf, placement, false); default: return -EINVAL; } @@ -1172,36 +1171,36 @@ static int vmw_framebuffer_pin(struct vmw_framebuffer *vfb) static int vmw_framebuffer_unpin(struct vmw_framebuffer *vfb) { struct vmw_private *dev_priv = vmw_priv(vfb->base.dev); - struct vmw_dma_buffer *buf; + struct vmw_buffer_object *buf; - buf = vfb->dmabuf ? vmw_framebuffer_to_vfbd(&vfb->base)->buffer : + buf = vfb->bo ? vmw_framebuffer_to_vfbd(&vfb->base)->buffer : vmw_framebuffer_to_vfbs(&vfb->base)->surface->res.backup; if (WARN_ON(!buf)) return 0; - return vmw_dmabuf_unpin(dev_priv, buf, false); + return vmw_bo_unpin(dev_priv, buf, false); } /** - * vmw_create_dmabuf_proxy - create a proxy surface for the DMA buf + * vmw_create_bo_proxy - create a proxy surface for the buffer object * * @dev: DRM device * @mode_cmd: parameters for the new surface - * @dmabuf_mob: MOB backing the DMA buf + * @bo_mob: MOB backing the buffer object * @srf_out: newly created surface * - * When the content FB is a DMA buf, we create a surface as a proxy to the + * When the content FB is a buffer object, we create a surface as a proxy to the * same buffer. This way we can do a surface copy rather than a surface DMA. * This is a more efficient approach * * RETURNS: * 0 on success, error code otherwise */ -static int vmw_create_dmabuf_proxy(struct drm_device *dev, - const struct drm_mode_fb_cmd2 *mode_cmd, - struct vmw_dma_buffer *dmabuf_mob, - struct vmw_surface **srf_out) +static int vmw_create_bo_proxy(struct drm_device *dev, + const struct drm_mode_fb_cmd2 *mode_cmd, + struct vmw_buffer_object *bo_mob, + struct vmw_surface **srf_out) { uint32_t format; struct drm_vmw_size content_base_size = {0}; @@ -1258,8 +1257,8 @@ static int vmw_create_dmabuf_proxy(struct drm_device *dev, /* Reserve and switch the backing mob. */ mutex_lock(&res->dev_priv->cmdbuf_mutex); (void) vmw_resource_reserve(res, false, true); - vmw_dmabuf_unreference(&res->backup); - res->backup = vmw_dmabuf_reference(dmabuf_mob); + vmw_bo_unreference(&res->backup); + res->backup = vmw_bo_reference(bo_mob); res->backup_offset = 0; vmw_resource_unreserve(res, false, NULL, 0); mutex_unlock(&res->dev_priv->cmdbuf_mutex); @@ -1269,21 +1268,21 @@ static int vmw_create_dmabuf_proxy(struct drm_device *dev, -static int vmw_kms_new_framebuffer_dmabuf(struct vmw_private *dev_priv, - struct vmw_dma_buffer *dmabuf, - struct vmw_framebuffer **out, - const struct drm_mode_fb_cmd2 - *mode_cmd) +static int vmw_kms_new_framebuffer_bo(struct vmw_private *dev_priv, + struct vmw_buffer_object *bo, + struct vmw_framebuffer **out, + const struct drm_mode_fb_cmd2 + *mode_cmd) { struct drm_device *dev = dev_priv->dev; - struct vmw_framebuffer_dmabuf *vfbd; + struct vmw_framebuffer_bo *vfbd; unsigned int requested_size; struct drm_format_name_buf format_name; int ret; requested_size = mode_cmd->height * mode_cmd->pitches[0]; - if (unlikely(requested_size > dmabuf->base.num_pages * PAGE_SIZE)) { + if (unlikely(requested_size > bo->base.num_pages * PAGE_SIZE)) { DRM_ERROR("Screen buffer object size is too small " "for requested mode.\n"); return -EINVAL; @@ -1312,20 +1311,20 @@ static int vmw_kms_new_framebuffer_dmabuf(struct vmw_private *dev_priv, } drm_helper_mode_fill_fb_struct(dev, &vfbd->base.base, mode_cmd); - vfbd->base.dmabuf = true; - vfbd->buffer = vmw_dmabuf_reference(dmabuf); + vfbd->base.bo = true; + vfbd->buffer = vmw_bo_reference(bo); vfbd->base.user_handle = mode_cmd->handles[0]; *out = &vfbd->base; ret = drm_framebuffer_init(dev, &vfbd->base.base, - &vmw_framebuffer_dmabuf_funcs); + &vmw_framebuffer_bo_funcs); if (ret) goto out_err2; return 0; out_err2: - vmw_dmabuf_unreference(&dmabuf); + vmw_bo_unreference(&bo); kfree(vfbd); out_err1: return ret; @@ -1354,57 +1353,57 @@ vmw_kms_srf_ok(struct vmw_private *dev_priv, uint32_t width, uint32_t height) * vmw_kms_new_framebuffer - Create a new framebuffer. * * @dev_priv: Pointer to device private struct. - * @dmabuf: Pointer to dma buffer to wrap the kms framebuffer around. - * Either @dmabuf or @surface must be NULL. + * @bo: Pointer to buffer object to wrap the kms framebuffer around. + * Either @bo or @surface must be NULL. * @surface: Pointer to a surface to wrap the kms framebuffer around. - * Either @dmabuf or @surface must be NULL. - * @only_2d: No presents will occur to this dma buffer based framebuffer. This - * Helps the code to do some important optimizations. + * Either @bo or @surface must be NULL. + * @only_2d: No presents will occur to this buffer object based framebuffer. + * This helps the code to do some important optimizations. * @mode_cmd: Frame-buffer metadata. */ struct vmw_framebuffer * vmw_kms_new_framebuffer(struct vmw_private *dev_priv, - struct vmw_dma_buffer *dmabuf, + struct vmw_buffer_object *bo, struct vmw_surface *surface, bool only_2d, const struct drm_mode_fb_cmd2 *mode_cmd) { struct vmw_framebuffer *vfb = NULL; - bool is_dmabuf_proxy = false; + bool is_bo_proxy = false; int ret; /* * We cannot use the SurfaceDMA command in an non-accelerated VM, - * therefore, wrap the DMA buf in a surface so we can use the + * therefore, wrap the buffer object in a surface so we can use the * SurfaceCopy command. */ if (vmw_kms_srf_ok(dev_priv, mode_cmd->width, mode_cmd->height) && - dmabuf && only_2d && + bo && only_2d && mode_cmd->width > 64 && /* Don't create a proxy for cursor */ dev_priv->active_display_unit == vmw_du_screen_target) { - ret = vmw_create_dmabuf_proxy(dev_priv->dev, mode_cmd, - dmabuf, &surface); + ret = vmw_create_bo_proxy(dev_priv->dev, mode_cmd, + bo, &surface); if (ret) return ERR_PTR(ret); - is_dmabuf_proxy = true; + is_bo_proxy = true; } /* Create the new framebuffer depending one what we have */ if (surface) { ret = vmw_kms_new_framebuffer_surface(dev_priv, surface, &vfb, mode_cmd, - is_dmabuf_proxy); + is_bo_proxy); /* - * vmw_create_dmabuf_proxy() adds a reference that is no longer + * vmw_create_bo_proxy() adds a reference that is no longer * needed */ - if (is_dmabuf_proxy) + if (is_bo_proxy) vmw_surface_unreference(&surface); - } else if (dmabuf) { - ret = vmw_kms_new_framebuffer_dmabuf(dev_priv, dmabuf, &vfb, - mode_cmd); + } else if (bo) { + ret = vmw_kms_new_framebuffer_bo(dev_priv, bo, &vfb, + mode_cmd); } else { BUG(); } @@ -1430,7 +1429,7 @@ static struct drm_framebuffer *vmw_kms_fb_create(struct drm_device *dev, struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile; struct vmw_framebuffer *vfb = NULL; struct vmw_surface *surface = NULL; - struct vmw_dma_buffer *bo = NULL; + struct vmw_buffer_object *bo = NULL; struct ttm_base_object *user_obj; int ret; @@ -1466,7 +1465,7 @@ static struct drm_framebuffer *vmw_kms_fb_create(struct drm_device *dev, * End conditioned code. */ - /* returns either a dmabuf or surface */ + /* returns either a bo or surface */ ret = vmw_user_lookup_handle(dev_priv, tfile, mode_cmd->handles[0], &surface, &bo); @@ -1494,7 +1493,7 @@ static struct drm_framebuffer *vmw_kms_fb_create(struct drm_device *dev, err_out: /* vmw_user_lookup_handle takes one ref so does new_fb */ if (bo) - vmw_dmabuf_unreference(&bo); + vmw_bo_unreference(&bo); if (surface) vmw_surface_unreference(&surface); @@ -2427,7 +2426,7 @@ int vmw_kms_helper_dirty(struct vmw_private *dev_priv, * interrupted by a signal. */ int vmw_kms_helper_buffer_prepare(struct vmw_private *dev_priv, - struct vmw_dma_buffer *buf, + struct vmw_buffer_object *buf, bool interruptible, bool validate_as_mob, bool for_cpu_blit) @@ -2459,7 +2458,7 @@ int vmw_kms_helper_buffer_prepare(struct vmw_private *dev_priv, * Helper to be used if an error forces the caller to undo the actions of * vmw_kms_helper_buffer_prepare. */ -void vmw_kms_helper_buffer_revert(struct vmw_dma_buffer *buf) +void vmw_kms_helper_buffer_revert(struct vmw_buffer_object *buf) { if (buf) ttm_bo_unreserve(&buf->base); @@ -2482,7 +2481,7 @@ void vmw_kms_helper_buffer_revert(struct vmw_dma_buffer *buf) */ void vmw_kms_helper_buffer_finish(struct vmw_private *dev_priv, struct drm_file *file_priv, - struct vmw_dma_buffer *buf, + struct vmw_buffer_object *buf, struct vmw_fence_obj **out_fence, struct drm_vmw_fence_rep __user * user_fence_rep) @@ -2522,7 +2521,7 @@ void vmw_kms_helper_resource_revert(struct vmw_validation_ctx *ctx) struct vmw_resource *res = ctx->res; vmw_kms_helper_buffer_revert(ctx->buf); - vmw_dmabuf_unreference(&ctx->buf); + vmw_bo_unreference(&ctx->buf); vmw_resource_unreserve(res, false, NULL, 0); mutex_unlock(&res->dev_priv->cmdbuf_mutex); } @@ -2567,7 +2566,7 @@ int vmw_kms_helper_resource_prepare(struct vmw_resource *res, if (ret) goto out_unreserve; - ctx->buf = vmw_dmabuf_reference(res->backup); + ctx->buf = vmw_bo_reference(res->backup); } ret = vmw_resource_validate(res); if (ret) @@ -2600,7 +2599,7 @@ void vmw_kms_helper_resource_finish(struct vmw_validation_ctx *ctx, vmw_kms_helper_buffer_finish(res->dev_priv, NULL, ctx->buf, out_fence, NULL); - vmw_dmabuf_unreference(&ctx->buf); + vmw_bo_unreference(&ctx->buf); vmw_resource_unreserve(res, false, NULL, 0); mutex_unlock(&res->dev_priv->cmdbuf_mutex); } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h index 6b7c012719f1..ff1caed38f94 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h @@ -90,7 +90,7 @@ struct vmw_kms_dirty { #define vmw_framebuffer_to_vfbs(x) \ container_of(x, struct vmw_framebuffer_surface, base.base) #define vmw_framebuffer_to_vfbd(x) \ - container_of(x, struct vmw_framebuffer_dmabuf, base.base) + container_of(x, struct vmw_framebuffer_bo, base.base) /** * Base class for framebuffers @@ -102,7 +102,7 @@ struct vmw_framebuffer { struct drm_framebuffer base; int (*pin)(struct vmw_framebuffer *fb); int (*unpin)(struct vmw_framebuffer *fb); - bool dmabuf; + bool bo; struct ttm_base_object *user_obj; uint32_t user_handle; }; @@ -117,15 +117,15 @@ struct vmw_clip_rect { struct vmw_framebuffer_surface { struct vmw_framebuffer base; struct vmw_surface *surface; - struct vmw_dma_buffer *buffer; + struct vmw_buffer_object *buffer; struct list_head head; - bool is_dmabuf_proxy; /* true if this is proxy surface for DMA buf */ + bool is_bo_proxy; /* true if this is proxy surface for DMA buf */ }; -struct vmw_framebuffer_dmabuf { +struct vmw_framebuffer_bo { struct vmw_framebuffer base; - struct vmw_dma_buffer *buffer; + struct vmw_buffer_object *buffer; }; @@ -161,18 +161,18 @@ struct vmw_crtc_state { * * @base DRM plane object * @surf Display surface for STDU - * @dmabuf display dmabuf for SOU + * @bo display bo for SOU * @content_fb_type Used by STDU. - * @dmabuf_size Size of the dmabuf, used by Screen Object Display Unit + * @bo_size Size of the bo, used by Screen Object Display Unit * @pinned pin count for STDU display surface */ struct vmw_plane_state { struct drm_plane_state base; struct vmw_surface *surf; - struct vmw_dma_buffer *dmabuf; + struct vmw_buffer_object *bo; int content_fb_type; - unsigned long dmabuf_size; + unsigned long bo_size; int pinned; @@ -209,7 +209,7 @@ struct vmw_display_unit { struct drm_plane cursor; struct vmw_surface *cursor_surface; - struct vmw_dma_buffer *cursor_dmabuf; + struct vmw_buffer_object *cursor_bo; size_t cursor_age; int cursor_x; @@ -243,7 +243,7 @@ struct vmw_display_unit { struct vmw_validation_ctx { struct vmw_resource *res; - struct vmw_dma_buffer *buf; + struct vmw_buffer_object *buf; }; #define vmw_crtc_to_du(x) \ @@ -291,14 +291,14 @@ int vmw_kms_helper_dirty(struct vmw_private *dev_priv, struct vmw_kms_dirty *dirty); int vmw_kms_helper_buffer_prepare(struct vmw_private *dev_priv, - struct vmw_dma_buffer *buf, + struct vmw_buffer_object *buf, bool interruptible, bool validate_as_mob, bool for_cpu_blit); -void vmw_kms_helper_buffer_revert(struct vmw_dma_buffer *buf); +void vmw_kms_helper_buffer_revert(struct vmw_buffer_object *buf); void vmw_kms_helper_buffer_finish(struct vmw_private *dev_priv, struct drm_file *file_priv, - struct vmw_dma_buffer *buf, + struct vmw_buffer_object *buf, struct vmw_fence_obj **out_fence, struct drm_vmw_fence_rep __user * user_fence_rep); @@ -316,7 +316,7 @@ int vmw_kms_readback(struct vmw_private *dev_priv, uint32_t num_clips); struct vmw_framebuffer * vmw_kms_new_framebuffer(struct vmw_private *dev_priv, - struct vmw_dma_buffer *dmabuf, + struct vmw_buffer_object *bo, struct vmw_surface *surface, bool only_2d, const struct drm_mode_fb_cmd2 *mode_cmd); @@ -384,11 +384,11 @@ void vmw_du_connector_destroy_state(struct drm_connector *connector, */ int vmw_kms_ldu_init_display(struct vmw_private *dev_priv); int vmw_kms_ldu_close_display(struct vmw_private *dev_priv); -int vmw_kms_ldu_do_dmabuf_dirty(struct vmw_private *dev_priv, - struct vmw_framebuffer *framebuffer, - unsigned flags, unsigned color, - struct drm_clip_rect *clips, - unsigned num_clips, int increment); +int vmw_kms_ldu_do_bo_dirty(struct vmw_private *dev_priv, + struct vmw_framebuffer *framebuffer, + unsigned int flags, unsigned int color, + struct drm_clip_rect *clips, + unsigned int num_clips, int increment); int vmw_kms_update_proxy(struct vmw_resource *res, const struct drm_clip_rect *clips, unsigned num_clips, @@ -408,14 +408,14 @@ int vmw_kms_sou_do_surface_dirty(struct vmw_private *dev_priv, unsigned num_clips, int inc, struct vmw_fence_obj **out_fence, struct drm_crtc *crtc); -int vmw_kms_sou_do_dmabuf_dirty(struct vmw_private *dev_priv, - struct vmw_framebuffer *framebuffer, - struct drm_clip_rect *clips, - struct drm_vmw_rect *vclips, - unsigned num_clips, int increment, - bool interruptible, - struct vmw_fence_obj **out_fence, - struct drm_crtc *crtc); +int vmw_kms_sou_do_bo_dirty(struct vmw_private *dev_priv, + struct vmw_framebuffer *framebuffer, + struct drm_clip_rect *clips, + struct drm_vmw_rect *vclips, + unsigned int num_clips, int increment, + bool interruptible, + struct vmw_fence_obj **out_fence, + struct drm_crtc *crtc); int vmw_kms_sou_readback(struct vmw_private *dev_priv, struct drm_file *file_priv, struct vmw_framebuffer *vfb, diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c index 4a5907e3f560..a2dd9a829219 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c @@ -547,11 +547,11 @@ int vmw_kms_ldu_close_display(struct vmw_private *dev_priv) } -int vmw_kms_ldu_do_dmabuf_dirty(struct vmw_private *dev_priv, - struct vmw_framebuffer *framebuffer, - unsigned flags, unsigned color, - struct drm_clip_rect *clips, - unsigned num_clips, int increment) +int vmw_kms_ldu_do_bo_dirty(struct vmw_private *dev_priv, + struct vmw_framebuffer *framebuffer, + unsigned int flags, unsigned int color, + struct drm_clip_rect *clips, + unsigned int num_clips, int increment) { size_t fifo_size; int i; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c b/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c index 222c9c2123a1..09420ef19ecb 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c @@ -38,7 +38,7 @@ #define VMW_OVERLAY_CAP_MASK (SVGA_FIFO_CAP_VIDEO | SVGA_FIFO_CAP_ESCAPE) struct vmw_stream { - struct vmw_dma_buffer *buf; + struct vmw_buffer_object *buf; bool claimed; bool paused; struct drm_vmw_control_stream_arg saved; @@ -94,7 +94,7 @@ static inline void fill_flush(struct vmw_escape_video_flush *cmd, * -ERESTARTSYS if interrupted by a signal. */ static int vmw_overlay_send_put(struct vmw_private *dev_priv, - struct vmw_dma_buffer *buf, + struct vmw_buffer_object *buf, struct drm_vmw_control_stream_arg *arg, bool interruptible) { @@ -225,16 +225,16 @@ static int vmw_overlay_send_stop(struct vmw_private *dev_priv, * used with GMRs instead of being locked to vram. */ static int vmw_overlay_move_buffer(struct vmw_private *dev_priv, - struct vmw_dma_buffer *buf, + struct vmw_buffer_object *buf, bool pin, bool inter) { if (!pin) - return vmw_dmabuf_unpin(dev_priv, buf, inter); + return vmw_bo_unpin(dev_priv, buf, inter); if (dev_priv->active_display_unit == vmw_du_legacy) - return vmw_dmabuf_pin_in_vram(dev_priv, buf, inter); + return vmw_bo_pin_in_vram(dev_priv, buf, inter); - return vmw_dmabuf_pin_in_vram_or_gmr(dev_priv, buf, inter); + return vmw_bo_pin_in_vram_or_gmr(dev_priv, buf, inter); } /** @@ -278,7 +278,7 @@ static int vmw_overlay_stop(struct vmw_private *dev_priv, } if (!pause) { - vmw_dmabuf_unreference(&stream->buf); + vmw_bo_unreference(&stream->buf); stream->paused = false; } else { stream->paused = true; @@ -297,7 +297,7 @@ static int vmw_overlay_stop(struct vmw_private *dev_priv, * -ERESTARTSYS if interrupted. */ static int vmw_overlay_update_stream(struct vmw_private *dev_priv, - struct vmw_dma_buffer *buf, + struct vmw_buffer_object *buf, struct drm_vmw_control_stream_arg *arg, bool interruptible) { @@ -347,7 +347,7 @@ static int vmw_overlay_update_stream(struct vmw_private *dev_priv, } if (stream->buf != buf) - stream->buf = vmw_dmabuf_reference(buf); + stream->buf = vmw_bo_reference(buf); stream->saved = *arg; /* stream is no longer stopped/paused */ stream->paused = false; @@ -466,7 +466,7 @@ int vmw_overlay_ioctl(struct drm_device *dev, void *data, struct vmw_overlay *overlay = dev_priv->overlay_priv; struct drm_vmw_control_stream_arg *arg = (struct drm_vmw_control_stream_arg *)data; - struct vmw_dma_buffer *buf; + struct vmw_buffer_object *buf; struct vmw_resource *res; int ret; @@ -484,13 +484,13 @@ int vmw_overlay_ioctl(struct drm_device *dev, void *data, goto out_unlock; } - ret = vmw_user_dmabuf_lookup(tfile, arg->handle, &buf, NULL); + ret = vmw_user_bo_lookup(tfile, arg->handle, &buf, NULL); if (ret) goto out_unlock; ret = vmw_overlay_update_stream(dev_priv, buf, arg, true); - vmw_dmabuf_unreference(&buf); + vmw_bo_unreference(&buf); out_unlock: mutex_unlock(&overlay->mutex); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c index 6b3a942b18df..5aaf9ac65cba 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c @@ -35,9 +35,9 @@ #define VMW_RES_EVICT_ERR_COUNT 10 -struct vmw_user_dma_buffer { +struct vmw_user_buffer_object { struct ttm_prime_object prime; - struct vmw_dma_buffer dma; + struct vmw_buffer_object vbo; }; struct vmw_bo_user_rep { @@ -45,17 +45,18 @@ struct vmw_bo_user_rep { uint64_t map_handle; }; -static inline struct vmw_dma_buffer * -vmw_dma_buffer(struct ttm_buffer_object *bo) +static inline struct vmw_buffer_object * +vmw_buffer_object(struct ttm_buffer_object *bo) { - return container_of(bo, struct vmw_dma_buffer, base); + return container_of(bo, struct vmw_buffer_object, base); } -static inline struct vmw_user_dma_buffer * -vmw_user_dma_buffer(struct ttm_buffer_object *bo) +static inline struct vmw_user_buffer_object * +vmw_user_buffer_object(struct ttm_buffer_object *bo) { - struct vmw_dma_buffer *vmw_bo = vmw_dma_buffer(bo); - return container_of(vmw_bo, struct vmw_user_dma_buffer, dma); + struct vmw_buffer_object *vmw_bo = vmw_buffer_object(bo); + + return container_of(vmw_bo, struct vmw_user_buffer_object, vbo); } struct vmw_resource *vmw_resource_reference(struct vmw_resource *res) @@ -116,7 +117,7 @@ static void vmw_resource_release(struct kref *kref) res->backup_dirty = false; list_del_init(&res->mob_head); ttm_bo_unreserve(bo); - vmw_dmabuf_unreference(&res->backup); + vmw_bo_unreference(&res->backup); } if (likely(res->hw_destroy != NULL)) { @@ -287,7 +288,7 @@ out_bad_resource: } /** - * Helper function that looks either a surface or dmabuf. + * Helper function that looks either a surface or bo. * * The pointer this pointed at by out_surf and out_buf needs to be null. */ @@ -295,7 +296,7 @@ int vmw_user_lookup_handle(struct vmw_private *dev_priv, struct ttm_object_file *tfile, uint32_t handle, struct vmw_surface **out_surf, - struct vmw_dma_buffer **out_buf) + struct vmw_buffer_object **out_buf) { struct vmw_resource *res; int ret; @@ -311,7 +312,7 @@ int vmw_user_lookup_handle(struct vmw_private *dev_priv, } *out_surf = NULL; - ret = vmw_user_dmabuf_lookup(tfile, handle, out_buf, NULL); + ret = vmw_user_bo_lookup(tfile, handle, out_buf, NULL); return ret; } @@ -320,14 +321,14 @@ int vmw_user_lookup_handle(struct vmw_private *dev_priv, */ /** - * vmw_dmabuf_acc_size - Calculate the pinned memory usage of buffers + * vmw_bo_acc_size - Calculate the pinned memory usage of buffers * * @dev_priv: Pointer to a struct vmw_private identifying the device. * @size: The requested buffer size. * @user: Whether this is an ordinary dma buffer or a user dma buffer. */ -static size_t vmw_dmabuf_acc_size(struct vmw_private *dev_priv, size_t size, - bool user) +static size_t vmw_bo_acc_size(struct vmw_private *dev_priv, size_t size, + bool user) { static size_t struct_size, user_struct_size; size_t num_pages = PAGE_ALIGN(size) >> PAGE_SHIFT; @@ -337,9 +338,9 @@ static size_t vmw_dmabuf_acc_size(struct vmw_private *dev_priv, size_t size, size_t backend_size = ttm_round_pot(vmw_tt_size); struct_size = backend_size + - ttm_round_pot(sizeof(struct vmw_dma_buffer)); + ttm_round_pot(sizeof(struct vmw_buffer_object)); user_struct_size = backend_size + - ttm_round_pot(sizeof(struct vmw_user_dma_buffer)); + ttm_round_pot(sizeof(struct vmw_user_buffer_object)); } if (dev_priv->map_mode == vmw_dma_alloc_coherent) @@ -350,36 +351,36 @@ static size_t vmw_dmabuf_acc_size(struct vmw_private *dev_priv, size_t size, page_array_size; } -void vmw_dmabuf_bo_free(struct ttm_buffer_object *bo) +void vmw_bo_bo_free(struct ttm_buffer_object *bo) { - struct vmw_dma_buffer *vmw_bo = vmw_dma_buffer(bo); + struct vmw_buffer_object *vmw_bo = vmw_buffer_object(bo); - vmw_dma_buffer_unmap(vmw_bo); + vmw_buffer_object_unmap(vmw_bo); kfree(vmw_bo); } -static void vmw_user_dmabuf_destroy(struct ttm_buffer_object *bo) +static void vmw_user_bo_destroy(struct ttm_buffer_object *bo) { - struct vmw_user_dma_buffer *vmw_user_bo = vmw_user_dma_buffer(bo); + struct vmw_user_buffer_object *vmw_user_bo = vmw_user_buffer_object(bo); - vmw_dma_buffer_unmap(&vmw_user_bo->dma); + vmw_buffer_object_unmap(&vmw_user_bo->vbo); ttm_prime_object_kfree(vmw_user_bo, prime); } -int vmw_dmabuf_init(struct vmw_private *dev_priv, - struct vmw_dma_buffer *vmw_bo, - size_t size, struct ttm_placement *placement, - bool interruptible, - void (*bo_free) (struct ttm_buffer_object *bo)) +int vmw_bo_init(struct vmw_private *dev_priv, + struct vmw_buffer_object *vmw_bo, + size_t size, struct ttm_placement *placement, + bool interruptible, + void (*bo_free)(struct ttm_buffer_object *bo)) { struct ttm_bo_device *bdev = &dev_priv->bdev; size_t acc_size; int ret; - bool user = (bo_free == &vmw_user_dmabuf_destroy); + bool user = (bo_free == &vmw_user_bo_destroy); - BUG_ON(!bo_free && (!user && (bo_free != vmw_dmabuf_bo_free))); + WARN_ON_ONCE(!bo_free && (!user && (bo_free != vmw_bo_bo_free))); - acc_size = vmw_dmabuf_acc_size(dev_priv, size, user); + acc_size = vmw_bo_acc_size(dev_priv, size, user); memset(vmw_bo, 0, sizeof(*vmw_bo)); INIT_LIST_HEAD(&vmw_bo->res_list); @@ -391,9 +392,9 @@ int vmw_dmabuf_init(struct vmw_private *dev_priv, return ret; } -static void vmw_user_dmabuf_release(struct ttm_base_object **p_base) +static void vmw_user_bo_release(struct ttm_base_object **p_base) { - struct vmw_user_dma_buffer *vmw_user_bo; + struct vmw_user_buffer_object *vmw_user_bo; struct ttm_base_object *base = *p_base; struct ttm_buffer_object *bo; @@ -402,21 +403,22 @@ static void vmw_user_dmabuf_release(struct ttm_base_object **p_base) if (unlikely(base == NULL)) return; - vmw_user_bo = container_of(base, struct vmw_user_dma_buffer, + vmw_user_bo = container_of(base, struct vmw_user_buffer_object, prime.base); - bo = &vmw_user_bo->dma.base; + bo = &vmw_user_bo->vbo.base; ttm_bo_unref(&bo); } -static void vmw_user_dmabuf_ref_obj_release(struct ttm_base_object *base, - enum ttm_ref_type ref_type) +static void vmw_user_bo_ref_obj_release(struct ttm_base_object *base, + enum ttm_ref_type ref_type) { - struct vmw_user_dma_buffer *user_bo; - user_bo = container_of(base, struct vmw_user_dma_buffer, prime.base); + struct vmw_user_buffer_object *user_bo; + + user_bo = container_of(base, struct vmw_user_buffer_object, prime.base); switch (ref_type) { case TTM_REF_SYNCCPU_WRITE: - ttm_bo_synccpu_write_release(&user_bo->dma.base); + ttm_bo_synccpu_write_release(&user_bo->vbo.base); break; default: BUG(); @@ -424,7 +426,7 @@ static void vmw_user_dmabuf_ref_obj_release(struct ttm_base_object *base, } /** - * vmw_user_dmabuf_alloc - Allocate a user dma buffer + * vmw_user_bo_alloc - Allocate a user dma buffer * * @dev_priv: Pointer to a struct device private. * @tfile: Pointer to a struct ttm_object_file on which to register the user @@ -432,18 +434,18 @@ static void vmw_user_dmabuf_ref_obj_release(struct ttm_base_object *base, * @size: Size of the dma buffer. * @shareable: Boolean whether the buffer is shareable with other open files. * @handle: Pointer to where the handle value should be assigned. - * @p_dma_buf: Pointer to where the refcounted struct vmw_dma_buffer pointer + * @p_vbo: Pointer to where the refcounted struct vmw_buffer_object pointer * should be assigned. */ -int vmw_user_dmabuf_alloc(struct vmw_private *dev_priv, - struct ttm_object_file *tfile, - uint32_t size, - bool shareable, - uint32_t *handle, - struct vmw_dma_buffer **p_dma_buf, - struct ttm_base_object **p_base) +int vmw_user_bo_alloc(struct vmw_private *dev_priv, + struct ttm_object_file *tfile, + uint32_t size, + bool shareable, + uint32_t *handle, + struct vmw_buffer_object **p_vbo, + struct ttm_base_object **p_base) { - struct vmw_user_dma_buffer *user_bo; + struct vmw_user_buffer_object *user_bo; struct ttm_buffer_object *tmp; int ret; @@ -453,28 +455,28 @@ int vmw_user_dmabuf_alloc(struct vmw_private *dev_priv, return -ENOMEM; } - ret = vmw_dmabuf_init(dev_priv, &user_bo->dma, size, - (dev_priv->has_mob) ? - &vmw_sys_placement : - &vmw_vram_sys_placement, true, - &vmw_user_dmabuf_destroy); + ret = vmw_bo_init(dev_priv, &user_bo->vbo, size, + (dev_priv->has_mob) ? + &vmw_sys_placement : + &vmw_vram_sys_placement, true, + &vmw_user_bo_destroy); if (unlikely(ret != 0)) return ret; - tmp = ttm_bo_reference(&user_bo->dma.base); + tmp = ttm_bo_reference(&user_bo->vbo.base); ret = ttm_prime_object_init(tfile, size, &user_bo->prime, shareable, ttm_buffer_type, - &vmw_user_dmabuf_release, - &vmw_user_dmabuf_ref_obj_release); + &vmw_user_bo_release, + &vmw_user_bo_ref_obj_release); if (unlikely(ret != 0)) { ttm_bo_unref(&tmp); goto out_no_base_object; } - *p_dma_buf = &user_bo->dma; + *p_vbo = &user_bo->vbo; if (p_base) { *p_base = &user_bo->prime.base; kref_get(&(*p_base)->refcount); @@ -486,21 +488,21 @@ out_no_base_object: } /** - * vmw_user_dmabuf_verify_access - verify access permissions on this + * vmw_user_bo_verify_access - verify access permissions on this * buffer object. * * @bo: Pointer to the buffer object being accessed * @tfile: Identifying the caller. */ -int vmw_user_dmabuf_verify_access(struct ttm_buffer_object *bo, +int vmw_user_bo_verify_access(struct ttm_buffer_object *bo, struct ttm_object_file *tfile) { - struct vmw_user_dma_buffer *vmw_user_bo; + struct vmw_user_buffer_object *vmw_user_bo; - if (unlikely(bo->destroy != vmw_user_dmabuf_destroy)) + if (unlikely(bo->destroy != vmw_user_bo_destroy)) return -EPERM; - vmw_user_bo = vmw_user_dma_buffer(bo); + vmw_user_bo = vmw_user_buffer_object(bo); /* Check that the caller has opened the object. */ if (likely(ttm_ref_object_exists(tfile, &vmw_user_bo->prime.base))) @@ -511,7 +513,7 @@ int vmw_user_dmabuf_verify_access(struct ttm_buffer_object *bo, } /** - * vmw_user_dmabuf_synccpu_grab - Grab a struct vmw_user_dma_buffer for cpu + * vmw_user_bo_synccpu_grab - Grab a struct vmw_user_buffer_object for cpu * access, idling previous GPU operations on the buffer and optionally * blocking it for further command submissions. * @@ -521,11 +523,11 @@ int vmw_user_dmabuf_verify_access(struct ttm_buffer_object *bo, * * A blocking grab will be automatically released when @tfile is closed. */ -static int vmw_user_dmabuf_synccpu_grab(struct vmw_user_dma_buffer *user_bo, +static int vmw_user_bo_synccpu_grab(struct vmw_user_buffer_object *user_bo, struct ttm_object_file *tfile, uint32_t flags) { - struct ttm_buffer_object *bo = &user_bo->dma.base; + struct ttm_buffer_object *bo = &user_bo->vbo.base; bool existed; int ret; @@ -550,20 +552,20 @@ static int vmw_user_dmabuf_synccpu_grab(struct vmw_user_dma_buffer *user_bo, ret = ttm_ref_object_add(tfile, &user_bo->prime.base, TTM_REF_SYNCCPU_WRITE, &existed, false); if (ret != 0 || existed) - ttm_bo_synccpu_write_release(&user_bo->dma.base); + ttm_bo_synccpu_write_release(&user_bo->vbo.base); return ret; } /** - * vmw_user_dmabuf_synccpu_release - Release a previous grab for CPU access, + * vmw_user_bo_synccpu_release - Release a previous grab for CPU access, * and unblock command submission on the buffer if blocked. * * @handle: Handle identifying the buffer object. * @tfile: Identifying the caller. * @flags: Flags indicating the type of release. */ -static int vmw_user_dmabuf_synccpu_release(uint32_t handle, +static int vmw_user_bo_synccpu_release(uint32_t handle, struct ttm_object_file *tfile, uint32_t flags) { @@ -575,7 +577,7 @@ static int vmw_user_dmabuf_synccpu_release(uint32_t handle, } /** - * vmw_user_dmabuf_synccpu_release - ioctl function implementing the synccpu + * vmw_user_bo_synccpu_release - ioctl function implementing the synccpu * functionality. * * @dev: Identifies the drm device. @@ -585,13 +587,13 @@ static int vmw_user_dmabuf_synccpu_release(uint32_t handle, * This function checks the ioctl arguments for validity and calls the * relevant synccpu functions. */ -int vmw_user_dmabuf_synccpu_ioctl(struct drm_device *dev, void *data, +int vmw_user_bo_synccpu_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) { struct drm_vmw_synccpu_arg *arg = (struct drm_vmw_synccpu_arg *) data; - struct vmw_dma_buffer *dma_buf; - struct vmw_user_dma_buffer *user_bo; + struct vmw_buffer_object *vbo; + struct vmw_user_buffer_object *user_bo; struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile; struct ttm_base_object *buffer_base; int ret; @@ -606,15 +608,15 @@ int vmw_user_dmabuf_synccpu_ioctl(struct drm_device *dev, void *data, switch (arg->op) { case drm_vmw_synccpu_grab: - ret = vmw_user_dmabuf_lookup(tfile, arg->handle, &dma_buf, + ret = vmw_user_bo_lookup(tfile, arg->handle, &vbo, &buffer_base); if (unlikely(ret != 0)) return ret; - user_bo = container_of(dma_buf, struct vmw_user_dma_buffer, - dma); - ret = vmw_user_dmabuf_synccpu_grab(user_bo, tfile, arg->flags); - vmw_dmabuf_unreference(&dma_buf); + user_bo = container_of(vbo, struct vmw_user_buffer_object, + vbo); + ret = vmw_user_bo_synccpu_grab(user_bo, tfile, arg->flags); + vmw_bo_unreference(&vbo); ttm_base_object_unref(&buffer_base); if (unlikely(ret != 0 && ret != -ERESTARTSYS && ret != -EBUSY)) { @@ -624,8 +626,8 @@ int vmw_user_dmabuf_synccpu_ioctl(struct drm_device *dev, void *data, } break; case drm_vmw_synccpu_release: - ret = vmw_user_dmabuf_synccpu_release(arg->handle, tfile, - arg->flags); + ret = vmw_user_bo_synccpu_release(arg->handle, tfile, + arg->flags); if (unlikely(ret != 0)) { DRM_ERROR("Failed synccpu release on handle 0x%08x.\n", (unsigned int) arg->handle); @@ -640,15 +642,15 @@ int vmw_user_dmabuf_synccpu_ioctl(struct drm_device *dev, void *data, return 0; } -int vmw_dmabuf_alloc_ioctl(struct drm_device *dev, void *data, - struct drm_file *file_priv) +int vmw_bo_alloc_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_priv) { struct vmw_private *dev_priv = vmw_priv(dev); union drm_vmw_alloc_dmabuf_arg *arg = (union drm_vmw_alloc_dmabuf_arg *)data; struct drm_vmw_alloc_dmabuf_req *req = &arg->req; struct drm_vmw_dmabuf_rep *rep = &arg->rep; - struct vmw_dma_buffer *dma_buf; + struct vmw_buffer_object *vbo; uint32_t handle; int ret; @@ -656,27 +658,27 @@ int vmw_dmabuf_alloc_ioctl(struct drm_device *dev, void *data, if (unlikely(ret != 0)) return ret; - ret = vmw_user_dmabuf_alloc(dev_priv, vmw_fpriv(file_priv)->tfile, - req->size, false, &handle, &dma_buf, - NULL); + ret = vmw_user_bo_alloc(dev_priv, vmw_fpriv(file_priv)->tfile, + req->size, false, &handle, &vbo, + NULL); if (unlikely(ret != 0)) - goto out_no_dmabuf; + goto out_no_bo; rep->handle = handle; - rep->map_handle = drm_vma_node_offset_addr(&dma_buf->base.vma_node); + rep->map_handle = drm_vma_node_offset_addr(&vbo->base.vma_node); rep->cur_gmr_id = handle; rep->cur_gmr_offset = 0; - vmw_dmabuf_unreference(&dma_buf); + vmw_bo_unreference(&vbo); -out_no_dmabuf: +out_no_bo: ttm_read_unlock(&dev_priv->reservation_sem); return ret; } -int vmw_dmabuf_unref_ioctl(struct drm_device *dev, void *data, - struct drm_file *file_priv) +int vmw_bo_unref_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_priv) { struct drm_vmw_unref_dmabuf_arg *arg = (struct drm_vmw_unref_dmabuf_arg *)data; @@ -686,11 +688,11 @@ int vmw_dmabuf_unref_ioctl(struct drm_device *dev, void *data, TTM_REF_USAGE); } -int vmw_user_dmabuf_lookup(struct ttm_object_file *tfile, - uint32_t handle, struct vmw_dma_buffer **out, +int vmw_user_bo_lookup(struct ttm_object_file *tfile, + uint32_t handle, struct vmw_buffer_object **out, struct ttm_base_object **p_base) { - struct vmw_user_dma_buffer *vmw_user_bo; + struct vmw_user_buffer_object *vmw_user_bo; struct ttm_base_object *base; base = ttm_base_object_lookup(tfile, handle); @@ -707,28 +709,28 @@ int vmw_user_dmabuf_lookup(struct ttm_object_file *tfile, return -EINVAL; } - vmw_user_bo = container_of(base, struct vmw_user_dma_buffer, + vmw_user_bo = container_of(base, struct vmw_user_buffer_object, prime.base); - (void)ttm_bo_reference(&vmw_user_bo->dma.base); + (void)ttm_bo_reference(&vmw_user_bo->vbo.base); if (p_base) *p_base = base; else ttm_base_object_unref(&base); - *out = &vmw_user_bo->dma; + *out = &vmw_user_bo->vbo; return 0; } -int vmw_user_dmabuf_reference(struct ttm_object_file *tfile, - struct vmw_dma_buffer *dma_buf, +int vmw_user_bo_reference(struct ttm_object_file *tfile, + struct vmw_buffer_object *vbo, uint32_t *handle) { - struct vmw_user_dma_buffer *user_bo; + struct vmw_user_buffer_object *user_bo; - if (dma_buf->base.destroy != vmw_user_dmabuf_destroy) + if (vbo->base.destroy != vmw_user_bo_destroy) return -EINVAL; - user_bo = container_of(dma_buf, struct vmw_user_dma_buffer, dma); + user_bo = container_of(vbo, struct vmw_user_buffer_object, vbo); *handle = user_bo->prime.base.hash.key; return ttm_ref_object_add(tfile, &user_bo->prime.base, @@ -743,7 +745,7 @@ int vmw_user_dmabuf_reference(struct ttm_object_file *tfile, * @args: Pointer to a struct drm_mode_create_dumb structure * * This is a driver callback for the core drm create_dumb functionality. - * Note that this is very similar to the vmw_dmabuf_alloc ioctl, except + * Note that this is very similar to the vmw_bo_alloc ioctl, except * that the arguments have a different format. */ int vmw_dumb_create(struct drm_file *file_priv, @@ -751,7 +753,7 @@ int vmw_dumb_create(struct drm_file *file_priv, struct drm_mode_create_dumb *args) { struct vmw_private *dev_priv = vmw_priv(dev); - struct vmw_dma_buffer *dma_buf; + struct vmw_buffer_object *vbo; int ret; args->pitch = args->width * ((args->bpp + 7) / 8); @@ -761,14 +763,14 @@ int vmw_dumb_create(struct drm_file *file_priv, if (unlikely(ret != 0)) return ret; - ret = vmw_user_dmabuf_alloc(dev_priv, vmw_fpriv(file_priv)->tfile, + ret = vmw_user_bo_alloc(dev_priv, vmw_fpriv(file_priv)->tfile, args->size, false, &args->handle, - &dma_buf, NULL); + &vbo, NULL); if (unlikely(ret != 0)) - goto out_no_dmabuf; + goto out_no_bo; - vmw_dmabuf_unreference(&dma_buf); -out_no_dmabuf: + vmw_bo_unreference(&vbo); +out_no_bo: ttm_read_unlock(&dev_priv->reservation_sem); return ret; } @@ -788,15 +790,15 @@ int vmw_dumb_map_offset(struct drm_file *file_priv, uint64_t *offset) { struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile; - struct vmw_dma_buffer *out_buf; + struct vmw_buffer_object *out_buf; int ret; - ret = vmw_user_dmabuf_lookup(tfile, handle, &out_buf, NULL); + ret = vmw_user_bo_lookup(tfile, handle, &out_buf, NULL); if (ret != 0) return -EINVAL; *offset = drm_vma_node_offset_addr(&out_buf->base.vma_node); - vmw_dmabuf_unreference(&out_buf); + vmw_bo_unreference(&out_buf); return 0; } @@ -829,7 +831,7 @@ static int vmw_resource_buf_alloc(struct vmw_resource *res, { unsigned long size = (res->backup_size + PAGE_SIZE - 1) & PAGE_MASK; - struct vmw_dma_buffer *backup; + struct vmw_buffer_object *backup; int ret; if (likely(res->backup)) { @@ -841,16 +843,16 @@ static int vmw_resource_buf_alloc(struct vmw_resource *res, if (unlikely(!backup)) return -ENOMEM; - ret = vmw_dmabuf_init(res->dev_priv, backup, res->backup_size, + ret = vmw_bo_init(res->dev_priv, backup, res->backup_size, res->func->backup_placement, interruptible, - &vmw_dmabuf_bo_free); + &vmw_bo_bo_free); if (unlikely(ret != 0)) - goto out_no_dmabuf; + goto out_no_bo; res->backup = backup; -out_no_dmabuf: +out_no_bo: return ret; } @@ -919,7 +921,7 @@ out_bind_failed: */ void vmw_resource_unreserve(struct vmw_resource *res, bool switch_backup, - struct vmw_dma_buffer *new_backup, + struct vmw_buffer_object *new_backup, unsigned long new_backup_offset) { struct vmw_private *dev_priv = res->dev_priv; @@ -931,11 +933,11 @@ void vmw_resource_unreserve(struct vmw_resource *res, if (res->backup) { lockdep_assert_held(&res->backup->base.resv->lock.base); list_del_init(&res->mob_head); - vmw_dmabuf_unreference(&res->backup); + vmw_bo_unreference(&res->backup); } if (new_backup) { - res->backup = vmw_dmabuf_reference(new_backup); + res->backup = vmw_bo_reference(new_backup); lockdep_assert_held(&new_backup->base.resv->lock.base); list_add_tail(&res->mob_head, &new_backup->res_list); } else { @@ -1007,7 +1009,7 @@ out_no_validate: out_no_reserve: ttm_bo_unref(&val_buf->bo); if (backup_dirty) - vmw_dmabuf_unreference(&res->backup); + vmw_bo_unreference(&res->backup); return ret; } @@ -1171,7 +1173,7 @@ int vmw_resource_validate(struct vmw_resource *res) goto out_no_validate; else if (!res->func->needs_backup && res->backup) { list_del_init(&res->mob_head); - vmw_dmabuf_unreference(&res->backup); + vmw_bo_unreference(&res->backup); } return 0; @@ -1230,22 +1232,22 @@ void vmw_fence_single_bo(struct ttm_buffer_object *bo, void vmw_resource_move_notify(struct ttm_buffer_object *bo, struct ttm_mem_reg *mem) { - struct vmw_dma_buffer *dma_buf; + struct vmw_buffer_object *vbo; if (mem == NULL) return; - if (bo->destroy != vmw_dmabuf_bo_free && - bo->destroy != vmw_user_dmabuf_destroy) + if (bo->destroy != vmw_bo_bo_free && + bo->destroy != vmw_user_bo_destroy) return; - dma_buf = container_of(bo, struct vmw_dma_buffer, base); + vbo = container_of(bo, struct vmw_buffer_object, base); /* * Kill any cached kernel maps before move. An optimization could * be to do this iff source or destination memory type is VRAM. */ - vmw_dma_buffer_unmap(dma_buf); + vmw_buffer_object_unmap(vbo); if (mem->mem_type != VMW_PL_MOB) { struct vmw_resource *res, *n; @@ -1254,7 +1256,7 @@ void vmw_resource_move_notify(struct ttm_buffer_object *bo, val_buf.bo = bo; val_buf.shared = false; - list_for_each_entry_safe(res, n, &dma_buf->res_list, mob_head) { + list_for_each_entry_safe(res, n, &vbo->res_list, mob_head) { if (unlikely(res->func->unbind == NULL)) continue; @@ -1277,12 +1279,12 @@ void vmw_resource_move_notify(struct ttm_buffer_object *bo, */ void vmw_resource_swap_notify(struct ttm_buffer_object *bo) { - if (bo->destroy != vmw_dmabuf_bo_free && - bo->destroy != vmw_user_dmabuf_destroy) + if (bo->destroy != vmw_bo_bo_free && + bo->destroy != vmw_user_bo_destroy) return; /* Kill any cached kernel maps before swapout */ - vmw_dma_buffer_unmap(vmw_dma_buffer(bo)); + vmw_buffer_object_unmap(vmw_buffer_object(bo)); } @@ -1294,7 +1296,7 @@ void vmw_resource_swap_notify(struct ttm_buffer_object *bo) * Read back cached states from the device if they exist. This function * assumings binding_mutex is held. */ -int vmw_query_readback_all(struct vmw_dma_buffer *dx_query_mob) +int vmw_query_readback_all(struct vmw_buffer_object *dx_query_mob) { struct vmw_resource *dx_query_ctx; struct vmw_private *dev_priv; @@ -1344,7 +1346,7 @@ int vmw_query_readback_all(struct vmw_dma_buffer *dx_query_mob) void vmw_query_move_notify(struct ttm_buffer_object *bo, struct ttm_mem_reg *mem) { - struct vmw_dma_buffer *dx_query_mob; + struct vmw_buffer_object *dx_query_mob; struct ttm_bo_device *bdev = bo->bdev; struct vmw_private *dev_priv; @@ -1353,7 +1355,7 @@ void vmw_query_move_notify(struct ttm_buffer_object *bo, mutex_lock(&dev_priv->binding_mutex); - dx_query_mob = container_of(bo, struct vmw_dma_buffer, base); + dx_query_mob = container_of(bo, struct vmw_buffer_object, base); if (mem == NULL || !dx_query_mob || !dx_query_mob->dx_query_ctx) { mutex_unlock(&dev_priv->binding_mutex); return; @@ -1481,7 +1483,7 @@ int vmw_resource_pin(struct vmw_resource *res, bool interruptible) goto out_no_reserve; if (res->pin_count == 0) { - struct vmw_dma_buffer *vbo = NULL; + struct vmw_buffer_object *vbo = NULL; if (res->backup) { vbo = res->backup; @@ -1539,7 +1541,7 @@ void vmw_resource_unpin(struct vmw_resource *res) WARN_ON(res->pin_count == 0); if (--res->pin_count == 0 && res->backup) { - struct vmw_dma_buffer *vbo = res->backup; + struct vmw_buffer_object *vbo = res->backup; (void) ttm_bo_reserve(&vbo->base, false, false, NULL); vmw_bo_pin_reserved(vbo, false); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c index 9798640cbfcd..74dfd4621b7e 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c @@ -66,7 +66,7 @@ struct vmw_kms_sou_readback_blit { SVGAFifoCmdBlitScreenToGMRFB body; }; -struct vmw_kms_sou_dmabuf_blit { +struct vmw_kms_sou_bo_blit { uint32 header; SVGAFifoCmdBlitGMRFBToScreen body; }; @@ -83,7 +83,7 @@ struct vmw_screen_object_unit { struct vmw_display_unit base; unsigned long buffer_size; /**< Size of allocated buffer */ - struct vmw_dma_buffer *buffer; /**< Backing store buffer */ + struct vmw_buffer_object *buffer; /**< Backing store buffer */ bool defined; }; @@ -240,8 +240,8 @@ static void vmw_sou_crtc_mode_set_nofb(struct drm_crtc *crtc) } if (vfb) { - sou->buffer = vps->dmabuf; - sou->buffer_size = vps->dmabuf_size; + sou->buffer = vps->bo; + sou->buffer_size = vps->bo_size; ret = vmw_sou_fifo_create(dev_priv, sou, crtc->x, crtc->y, &crtc->mode); @@ -408,10 +408,10 @@ vmw_sou_primary_plane_cleanup_fb(struct drm_plane *plane, struct drm_crtc *crtc = plane->state->crtc ? plane->state->crtc : old_state->crtc; - if (vps->dmabuf) - vmw_dmabuf_unpin(vmw_priv(crtc->dev), vps->dmabuf, false); - vmw_dmabuf_unreference(&vps->dmabuf); - vps->dmabuf_size = 0; + if (vps->bo) + vmw_bo_unpin(vmw_priv(crtc->dev), vps->bo, false); + vmw_bo_unreference(&vps->bo); + vps->bo_size = 0; vmw_du_plane_cleanup_fb(plane, old_state); } @@ -440,8 +440,8 @@ vmw_sou_primary_plane_prepare_fb(struct drm_plane *plane, if (!new_fb) { - vmw_dmabuf_unreference(&vps->dmabuf); - vps->dmabuf_size = 0; + vmw_bo_unreference(&vps->bo); + vps->bo_size = 0; return 0; } @@ -449,22 +449,22 @@ vmw_sou_primary_plane_prepare_fb(struct drm_plane *plane, size = new_state->crtc_w * new_state->crtc_h * 4; dev_priv = vmw_priv(crtc->dev); - if (vps->dmabuf) { - if (vps->dmabuf_size == size) { + if (vps->bo) { + if (vps->bo_size == size) { /* * Note that this might temporarily up the pin-count * to 2, until cleanup_fb() is called. */ - return vmw_dmabuf_pin_in_vram(dev_priv, vps->dmabuf, + return vmw_bo_pin_in_vram(dev_priv, vps->bo, true); } - vmw_dmabuf_unreference(&vps->dmabuf); - vps->dmabuf_size = 0; + vmw_bo_unreference(&vps->bo); + vps->bo_size = 0; } - vps->dmabuf = kzalloc(sizeof(*vps->dmabuf), GFP_KERNEL); - if (!vps->dmabuf) + vps->bo = kzalloc(sizeof(*vps->bo), GFP_KERNEL); + if (!vps->bo) return -ENOMEM; vmw_svga_enable(dev_priv); @@ -473,22 +473,22 @@ vmw_sou_primary_plane_prepare_fb(struct drm_plane *plane, * resume the overlays, this is preferred to failing to alloc. */ vmw_overlay_pause_all(dev_priv); - ret = vmw_dmabuf_init(dev_priv, vps->dmabuf, size, + ret = vmw_bo_init(dev_priv, vps->bo, size, &vmw_vram_ne_placement, - false, &vmw_dmabuf_bo_free); + false, &vmw_bo_bo_free); vmw_overlay_resume_all(dev_priv); if (ret) { - vps->dmabuf = NULL; /* vmw_dmabuf_init frees on error */ + vps->bo = NULL; /* vmw_bo_init frees on error */ return ret; } - vps->dmabuf_size = size; + vps->bo_size = size; /* * TTM already thinks the buffer is pinned, but make sure the * pin_count is upped. */ - return vmw_dmabuf_pin_in_vram(dev_priv, vps->dmabuf, true); + return vmw_bo_pin_in_vram(dev_priv, vps->bo, true); } @@ -512,10 +512,10 @@ vmw_sou_primary_plane_atomic_update(struct drm_plane *plane, vclips.w = crtc->mode.hdisplay; vclips.h = crtc->mode.vdisplay; - if (vfb->dmabuf) - ret = vmw_kms_sou_do_dmabuf_dirty(dev_priv, vfb, NULL, - &vclips, 1, 1, true, - &fence, crtc); + if (vfb->bo) + ret = vmw_kms_sou_do_bo_dirty(dev_priv, vfb, NULL, + &vclips, 1, 1, true, + &fence, crtc); else ret = vmw_kms_sou_do_surface_dirty(dev_priv, vfb, NULL, &vclips, NULL, 0, 0, @@ -775,11 +775,11 @@ int vmw_kms_sou_init_display(struct vmw_private *dev_priv) return 0; } -static int do_dmabuf_define_gmrfb(struct vmw_private *dev_priv, +static int do_bo_define_gmrfb(struct vmw_private *dev_priv, struct vmw_framebuffer *framebuffer) { - struct vmw_dma_buffer *buf = - container_of(framebuffer, struct vmw_framebuffer_dmabuf, + struct vmw_buffer_object *buf = + container_of(framebuffer, struct vmw_framebuffer_bo, base)->buffer; int depth = framebuffer->base.format->depth; struct { @@ -970,13 +970,13 @@ int vmw_kms_sou_do_surface_dirty(struct vmw_private *dev_priv, } /** - * vmw_sou_dmabuf_fifo_commit - Callback to submit a set of readback clips. + * vmw_sou_bo_fifo_commit - Callback to submit a set of readback clips. * * @dirty: The closure structure. * * Commits a previously built command buffer of readback clips. */ -static void vmw_sou_dmabuf_fifo_commit(struct vmw_kms_dirty *dirty) +static void vmw_sou_bo_fifo_commit(struct vmw_kms_dirty *dirty) { if (!dirty->num_hits) { vmw_fifo_commit(dirty->dev_priv, 0); @@ -984,20 +984,20 @@ static void vmw_sou_dmabuf_fifo_commit(struct vmw_kms_dirty *dirty) } vmw_fifo_commit(dirty->dev_priv, - sizeof(struct vmw_kms_sou_dmabuf_blit) * + sizeof(struct vmw_kms_sou_bo_blit) * dirty->num_hits); } /** - * vmw_sou_dmabuf_clip - Callback to encode a readback cliprect. + * vmw_sou_bo_clip - Callback to encode a readback cliprect. * * @dirty: The closure structure * * Encodes a BLIT_GMRFB_TO_SCREEN cliprect. */ -static void vmw_sou_dmabuf_clip(struct vmw_kms_dirty *dirty) +static void vmw_sou_bo_clip(struct vmw_kms_dirty *dirty) { - struct vmw_kms_sou_dmabuf_blit *blit = dirty->cmd; + struct vmw_kms_sou_bo_blit *blit = dirty->cmd; blit += dirty->num_hits; blit->header = SVGA_CMD_BLIT_GMRFB_TO_SCREEN; @@ -1012,10 +1012,10 @@ static void vmw_sou_dmabuf_clip(struct vmw_kms_dirty *dirty) } /** - * vmw_kms_do_dmabuf_dirty - Dirty part of a dma-buffer backed framebuffer + * vmw_kms_do_bo_dirty - Dirty part of a buffer-object backed framebuffer * * @dev_priv: Pointer to the device private structure. - * @framebuffer: Pointer to the dma-buffer backed framebuffer. + * @framebuffer: Pointer to the buffer-object backed framebuffer. * @clips: Array of clip rects. * @vclips: Alternate array of clip rects. Either @clips or @vclips must * be NULL. @@ -1025,12 +1025,12 @@ static void vmw_sou_dmabuf_clip(struct vmw_kms_dirty *dirty) * @out_fence: If non-NULL, will return a ref-counted pointer to a * struct vmw_fence_obj. The returned fence pointer may be NULL in which * case the device has already synchronized. - * @crtc: If crtc is passed, perform dmabuf dirty on that crtc only. + * @crtc: If crtc is passed, perform bo dirty on that crtc only. * * Returns 0 on success, negative error code on failure. -ERESTARTSYS if * interrupted. */ -int vmw_kms_sou_do_dmabuf_dirty(struct vmw_private *dev_priv, +int vmw_kms_sou_do_bo_dirty(struct vmw_private *dev_priv, struct vmw_framebuffer *framebuffer, struct drm_clip_rect *clips, struct drm_vmw_rect *vclips, @@ -1039,8 +1039,8 @@ int vmw_kms_sou_do_dmabuf_dirty(struct vmw_private *dev_priv, struct vmw_fence_obj **out_fence, struct drm_crtc *crtc) { - struct vmw_dma_buffer *buf = - container_of(framebuffer, struct vmw_framebuffer_dmabuf, + struct vmw_buffer_object *buf = + container_of(framebuffer, struct vmw_framebuffer_bo, base)->buffer; struct vmw_kms_dirty dirty; int ret; @@ -1050,14 +1050,14 @@ int vmw_kms_sou_do_dmabuf_dirty(struct vmw_private *dev_priv, if (ret) return ret; - ret = do_dmabuf_define_gmrfb(dev_priv, framebuffer); + ret = do_bo_define_gmrfb(dev_priv, framebuffer); if (unlikely(ret != 0)) goto out_revert; dirty.crtc = crtc; - dirty.fifo_commit = vmw_sou_dmabuf_fifo_commit; - dirty.clip = vmw_sou_dmabuf_clip; - dirty.fifo_reserve_size = sizeof(struct vmw_kms_sou_dmabuf_blit) * + dirty.fifo_commit = vmw_sou_bo_fifo_commit; + dirty.clip = vmw_sou_bo_clip; + dirty.fifo_reserve_size = sizeof(struct vmw_kms_sou_bo_blit) * num_clips; ret = vmw_kms_helper_dirty(dev_priv, framebuffer, clips, vclips, 0, 0, num_clips, increment, &dirty); @@ -1116,12 +1116,12 @@ static void vmw_sou_readback_clip(struct vmw_kms_dirty *dirty) /** * vmw_kms_sou_readback - Perform a readback from the screen object system to - * a dma-buffer backed framebuffer. + * a buffer-object backed framebuffer. * * @dev_priv: Pointer to the device private structure. * @file_priv: Pointer to a struct drm_file identifying the caller. * Must be set to NULL if @user_fence_rep is NULL. - * @vfb: Pointer to the dma-buffer backed framebuffer. + * @vfb: Pointer to the buffer-object backed framebuffer. * @user_fence_rep: User-space provided structure for fence information. * Must be set to non-NULL if @file_priv is non-NULL. * @vclips: Array of clip rects. @@ -1139,8 +1139,8 @@ int vmw_kms_sou_readback(struct vmw_private *dev_priv, uint32_t num_clips, struct drm_crtc *crtc) { - struct vmw_dma_buffer *buf = - container_of(vfb, struct vmw_framebuffer_dmabuf, base)->buffer; + struct vmw_buffer_object *buf = + container_of(vfb, struct vmw_framebuffer_bo, base)->buffer; struct vmw_kms_dirty dirty; int ret; @@ -1149,7 +1149,7 @@ int vmw_kms_sou_readback(struct vmw_private *dev_priv, if (ret) return ret; - ret = do_dmabuf_define_gmrfb(dev_priv, vfb); + ret = do_bo_define_gmrfb(dev_priv, vfb); if (unlikely(ret != 0)) goto out_revert; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c index 73b8e9a16368..f6c939f3ff5e 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c @@ -159,7 +159,7 @@ static int vmw_gb_shader_init(struct vmw_private *dev_priv, SVGA3dShaderType type, uint8_t num_input_sig, uint8_t num_output_sig, - struct vmw_dma_buffer *byte_code, + struct vmw_buffer_object *byte_code, void (*res_free) (struct vmw_resource *res)) { struct vmw_shader *shader = vmw_res_to_shader(res); @@ -178,7 +178,7 @@ static int vmw_gb_shader_init(struct vmw_private *dev_priv, res->backup_size = size; if (byte_code) { - res->backup = vmw_dmabuf_reference(byte_code); + res->backup = vmw_bo_reference(byte_code); res->backup_offset = offset; } shader->size = size; @@ -723,7 +723,7 @@ int vmw_shader_destroy_ioctl(struct drm_device *dev, void *data, } static int vmw_user_shader_alloc(struct vmw_private *dev_priv, - struct vmw_dma_buffer *buffer, + struct vmw_buffer_object *buffer, size_t shader_size, size_t offset, SVGA3dShaderType shader_type, @@ -801,7 +801,7 @@ out: static struct vmw_resource *vmw_shader_alloc(struct vmw_private *dev_priv, - struct vmw_dma_buffer *buffer, + struct vmw_buffer_object *buffer, size_t shader_size, size_t offset, SVGA3dShaderType shader_type) @@ -862,12 +862,12 @@ static int vmw_shader_define(struct drm_device *dev, struct drm_file *file_priv, { struct vmw_private *dev_priv = vmw_priv(dev); struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile; - struct vmw_dma_buffer *buffer = NULL; + struct vmw_buffer_object *buffer = NULL; SVGA3dShaderType shader_type; int ret; if (buffer_handle != SVGA3D_INVALID_ID) { - ret = vmw_user_dmabuf_lookup(tfile, buffer_handle, + ret = vmw_user_bo_lookup(tfile, buffer_handle, &buffer, NULL); if (unlikely(ret != 0)) { DRM_ERROR("Could not find buffer for shader " @@ -906,7 +906,7 @@ static int vmw_shader_define(struct drm_device *dev, struct drm_file *file_priv, ttm_read_unlock(&dev_priv->reservation_sem); out_bad_arg: - vmw_dmabuf_unreference(&buffer); + vmw_bo_unreference(&buffer); return ret; } @@ -983,7 +983,7 @@ int vmw_compat_shader_add(struct vmw_private *dev_priv, struct list_head *list) { struct ttm_operation_ctx ctx = { false, true }; - struct vmw_dma_buffer *buf; + struct vmw_buffer_object *buf; struct ttm_bo_kmap_obj map; bool is_iomem; int ret; @@ -997,8 +997,8 @@ int vmw_compat_shader_add(struct vmw_private *dev_priv, if (unlikely(!buf)) return -ENOMEM; - ret = vmw_dmabuf_init(dev_priv, buf, size, &vmw_sys_ne_placement, - true, vmw_dmabuf_bo_free); + ret = vmw_bo_init(dev_priv, buf, size, &vmw_sys_ne_placement, + true, vmw_bo_bo_free); if (unlikely(ret != 0)) goto out; @@ -1031,7 +1031,7 @@ int vmw_compat_shader_add(struct vmw_private *dev_priv, res, list); vmw_resource_unreference(&res); no_reserve: - vmw_dmabuf_unreference(&buf); + vmw_bo_unreference(&buf); out: return ret; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c index 152e96cb1c01..537df9034008 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c @@ -44,7 +44,7 @@ enum stdu_content_type { SAME_AS_DISPLAY = 0, SEPARATE_SURFACE, - SEPARATE_DMA + SEPARATE_BO }; /** @@ -58,7 +58,7 @@ enum stdu_content_type { * @bottom: Bottom side of bounding box. * @fb_left: Left side of the framebuffer/content bounding box * @fb_top: Top of the framebuffer/content bounding box - * @buf: DMA buffer when DMA-ing between buffer and screen targets. + * @buf: buffer object when DMA-ing between buffer and screen targets. * @sid: Surface ID when copying between surface and screen targets. */ struct vmw_stdu_dirty { @@ -68,7 +68,7 @@ struct vmw_stdu_dirty { s32 fb_left, fb_top; u32 pitch; union { - struct vmw_dma_buffer *buf; + struct vmw_buffer_object *buf; u32 sid; }; }; @@ -508,14 +508,14 @@ static int vmw_stdu_crtc_page_flip(struct drm_crtc *crtc, /** - * vmw_stdu_dmabuf_clip - Callback to encode a suface DMA command cliprect + * vmw_stdu_bo_clip - Callback to encode a suface DMA command cliprect * * @dirty: The closure structure. * * Encodes a surface DMA command cliprect and updates the bounding box * for the DMA. */ -static void vmw_stdu_dmabuf_clip(struct vmw_kms_dirty *dirty) +static void vmw_stdu_bo_clip(struct vmw_kms_dirty *dirty) { struct vmw_stdu_dirty *ddirty = container_of(dirty, struct vmw_stdu_dirty, base); @@ -543,14 +543,14 @@ static void vmw_stdu_dmabuf_clip(struct vmw_kms_dirty *dirty) } /** - * vmw_stdu_dmabuf_fifo_commit - Callback to fill in and submit a DMA command. + * vmw_stdu_bo_fifo_commit - Callback to fill in and submit a DMA command. * * @dirty: The closure structure. * * Fills in the missing fields in a DMA command, and optionally encodes * a screen target update command, depending on transfer direction. */ -static void vmw_stdu_dmabuf_fifo_commit(struct vmw_kms_dirty *dirty) +static void vmw_stdu_bo_fifo_commit(struct vmw_kms_dirty *dirty) { struct vmw_stdu_dirty *ddirty = container_of(dirty, struct vmw_stdu_dirty, base); @@ -594,13 +594,13 @@ static void vmw_stdu_dmabuf_fifo_commit(struct vmw_kms_dirty *dirty) /** - * vmw_stdu_dmabuf_cpu_clip - Callback to encode a CPU blit + * vmw_stdu_bo_cpu_clip - Callback to encode a CPU blit * * @dirty: The closure structure. * * This function calculates the bounding box for all the incoming clips. */ -static void vmw_stdu_dmabuf_cpu_clip(struct vmw_kms_dirty *dirty) +static void vmw_stdu_bo_cpu_clip(struct vmw_kms_dirty *dirty) { struct vmw_stdu_dirty *ddirty = container_of(dirty, struct vmw_stdu_dirty, base); @@ -624,14 +624,14 @@ static void vmw_stdu_dmabuf_cpu_clip(struct vmw_kms_dirty *dirty) /** - * vmw_stdu_dmabuf_cpu_commit - Callback to do a CPU blit from DMAbuf + * vmw_stdu_bo_cpu_commit - Callback to do a CPU blit from buffer object * * @dirty: The closure structure. * * For the special case when we cannot create a proxy surface in a * 2D VM, we have to do a CPU blit ourselves. */ -static void vmw_stdu_dmabuf_cpu_commit(struct vmw_kms_dirty *dirty) +static void vmw_stdu_bo_cpu_commit(struct vmw_kms_dirty *dirty) { struct vmw_stdu_dirty *ddirty = container_of(dirty, struct vmw_stdu_dirty, base); @@ -652,7 +652,7 @@ static void vmw_stdu_dmabuf_cpu_commit(struct vmw_kms_dirty *dirty) if (width == 0 || height == 0) return; - /* Assume we are blitting from Guest (dmabuf) to Host (display_srf) */ + /* Assume we are blitting from Guest (bo) to Host (display_srf) */ dst_pitch = stdu->display_srf->base_size.width * stdu->cpp; dst_bo = &stdu->display_srf->res.backup->base; dst_offset = ddirty->top * dst_pitch + ddirty->left * stdu->cpp; @@ -712,13 +712,13 @@ out_cleanup: } /** - * vmw_kms_stdu_dma - Perform a DMA transfer between a dma-buffer backed + * vmw_kms_stdu_dma - Perform a DMA transfer between a buffer-object backed * framebuffer and the screen target system. * * @dev_priv: Pointer to the device private structure. * @file_priv: Pointer to a struct drm-file identifying the caller. May be * set to NULL, but then @user_fence_rep must also be set to NULL. - * @vfb: Pointer to the dma-buffer backed framebuffer. + * @vfb: Pointer to the buffer-object backed framebuffer. * @clips: Array of clip rects. Either @clips or @vclips must be NULL. * @vclips: Alternate array of clip rects. Either @clips or @vclips must * be NULL. @@ -747,8 +747,8 @@ int vmw_kms_stdu_dma(struct vmw_private *dev_priv, bool interruptible, struct drm_crtc *crtc) { - struct vmw_dma_buffer *buf = - container_of(vfb, struct vmw_framebuffer_dmabuf, base)->buffer; + struct vmw_buffer_object *buf = + container_of(vfb, struct vmw_framebuffer_bo, base)->buffer; struct vmw_stdu_dirty ddirty; int ret; bool cpu_blit = !(dev_priv->capabilities & SVGA_CAP_3D); @@ -770,8 +770,8 @@ int vmw_kms_stdu_dma(struct vmw_private *dev_priv, ddirty.fb_left = ddirty.fb_top = S32_MAX; ddirty.pitch = vfb->base.pitches[0]; ddirty.buf = buf; - ddirty.base.fifo_commit = vmw_stdu_dmabuf_fifo_commit; - ddirty.base.clip = vmw_stdu_dmabuf_clip; + ddirty.base.fifo_commit = vmw_stdu_bo_fifo_commit; + ddirty.base.clip = vmw_stdu_bo_clip; ddirty.base.fifo_reserve_size = sizeof(struct vmw_stdu_dma) + num_clips * sizeof(SVGA3dCopyBox) + sizeof(SVGA3dCmdSurfaceDMASuffix); @@ -780,8 +780,8 @@ int vmw_kms_stdu_dma(struct vmw_private *dev_priv, if (cpu_blit) { - ddirty.base.fifo_commit = vmw_stdu_dmabuf_cpu_commit; - ddirty.base.clip = vmw_stdu_dmabuf_cpu_clip; + ddirty.base.fifo_commit = vmw_stdu_bo_cpu_commit; + ddirty.base.clip = vmw_stdu_bo_cpu_clip; ddirty.base.fifo_reserve_size = 0; } @@ -927,7 +927,7 @@ int vmw_kms_stdu_surface_dirty(struct vmw_private *dev_priv, if (ret) return ret; - if (vfbs->is_dmabuf_proxy) { + if (vfbs->is_bo_proxy) { ret = vmw_kms_update_proxy(srf, clips, num_clips, inc); if (ret) goto out_finish; @@ -1075,7 +1075,7 @@ vmw_stdu_primary_plane_cleanup_fb(struct drm_plane *plane, * @new_state: info on the new plane state, including the FB * * This function allocates a new display surface if the content is - * backed by a DMA. The display surface is pinned here, and it'll + * backed by a buffer object. The display surface is pinned here, and it'll * be unpinned in .cleanup_fb() * * Returns 0 on success @@ -1105,13 +1105,13 @@ vmw_stdu_primary_plane_prepare_fb(struct drm_plane *plane, } vfb = vmw_framebuffer_to_vfb(new_fb); - new_vfbs = (vfb->dmabuf) ? NULL : vmw_framebuffer_to_vfbs(new_fb); + new_vfbs = (vfb->bo) ? NULL : vmw_framebuffer_to_vfbs(new_fb); if (new_vfbs && new_vfbs->surface->base_size.width == hdisplay && new_vfbs->surface->base_size.height == vdisplay) new_content_type = SAME_AS_DISPLAY; - else if (vfb->dmabuf) - new_content_type = SEPARATE_DMA; + else if (vfb->bo) + new_content_type = SEPARATE_BO; else new_content_type = SEPARATE_SURFACE; @@ -1124,10 +1124,10 @@ vmw_stdu_primary_plane_prepare_fb(struct drm_plane *plane, display_base_size.depth = 1; /* - * If content buffer is a DMA buf, then we have to construct - * surface info + * If content buffer is a buffer object, then we have to + * construct surface info */ - if (new_content_type == SEPARATE_DMA) { + if (new_content_type == SEPARATE_BO) { switch (new_fb->format->cpp[0]*8) { case 32: @@ -1212,12 +1212,12 @@ vmw_stdu_primary_plane_prepare_fb(struct drm_plane *plane, vps->content_fb_type = new_content_type; /* - * This should only happen if the DMA buf is too large to create a + * This should only happen if the buffer object is too large to create a * proxy surface for. - * If we are a 2D VM with a DMA buffer then we have to use CPU blit + * If we are a 2D VM with a buffer object then we have to use CPU blit * so cache these mappings */ - if (vps->content_fb_type == SEPARATE_DMA && + if (vps->content_fb_type == SEPARATE_BO && !(dev_priv->capabilities & SVGA_CAP_3D)) vps->cpp = new_fb->pitches[0] / new_fb->width; @@ -1276,7 +1276,7 @@ vmw_stdu_primary_plane_atomic_update(struct drm_plane *plane, if (ret) DRM_ERROR("Failed to bind surface to STDU.\n"); - if (vfb->dmabuf) + if (vfb->bo) ret = vmw_kms_stdu_dma(dev_priv, NULL, vfb, NULL, NULL, &vclips, 1, 1, true, false, crtc); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c index b236c48bf265..2b2e8aa7114a 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c @@ -842,12 +842,12 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data, if (dev_priv->has_mob && req->shareable) { uint32_t backup_handle; - ret = vmw_user_dmabuf_alloc(dev_priv, tfile, - res->backup_size, - true, - &backup_handle, - &res->backup, - &user_srf->backup_base); + ret = vmw_user_bo_alloc(dev_priv, tfile, + res->backup_size, + true, + &backup_handle, + &res->backup, + &user_srf->backup_base); if (unlikely(ret != 0)) { vmw_resource_unreference(&res); goto out_unlock; @@ -1317,14 +1317,14 @@ int vmw_gb_surface_define_ioctl(struct drm_device *dev, void *data, if (req->buffer_handle != SVGA3D_INVALID_ID) { - ret = vmw_user_dmabuf_lookup(tfile, req->buffer_handle, - &res->backup, - &user_srf->backup_base); + ret = vmw_user_bo_lookup(tfile, req->buffer_handle, + &res->backup, + &user_srf->backup_base); if (ret == 0) { if (res->backup->base.num_pages * PAGE_SIZE < res->backup_size) { DRM_ERROR("Surface backup buffer is too small.\n"); - vmw_dmabuf_unreference(&res->backup); + vmw_bo_unreference(&res->backup); ret = -EINVAL; goto out_unlock; } else { @@ -1332,13 +1332,13 @@ int vmw_gb_surface_define_ioctl(struct drm_device *dev, void *data, } } } else if (req->drm_surface_flags & drm_vmw_surface_flag_create_buffer) - ret = vmw_user_dmabuf_alloc(dev_priv, tfile, - res->backup_size, - req->drm_surface_flags & - drm_vmw_surface_flag_shareable, - &backup_handle, - &res->backup, - &user_srf->backup_base); + ret = vmw_user_bo_alloc(dev_priv, tfile, + res->backup_size, + req->drm_surface_flags & + drm_vmw_surface_flag_shareable, + &backup_handle, + &res->backup, + &user_srf->backup_base); if (unlikely(ret != 0)) { vmw_resource_unreference(&res); @@ -1414,8 +1414,7 @@ int vmw_gb_surface_reference_ioctl(struct drm_device *dev, void *data, } mutex_lock(&dev_priv->cmdbuf_mutex); /* Protect res->backup */ - ret = vmw_user_dmabuf_reference(tfile, srf->res.backup, - &backup_handle); + ret = vmw_user_bo_reference(tfile, srf->res.backup, &backup_handle); mutex_unlock(&dev_priv->cmdbuf_mutex); if (unlikely(ret != 0)) { diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c new file mode 100644 index 000000000000..0931f43913b1 --- /dev/null +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c @@ -0,0 +1,887 @@ +/************************************************************************** + * + * Copyright © 2009-2015 VMware, Inc., Palo Alto, CA., USA + * All Rights Reserved. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the + * "Software"), to deal in the Software without restriction, including + * without limitation the rights to use, copy, modify, merge, publish, + * distribute, sub license, and/or sell copies of the Software, and to + * permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice (including the + * next paragraph) shall be included in all copies or substantial portions + * of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, + * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + * USE OR OTHER DEALINGS IN THE SOFTWARE. + * + **************************************************************************/ + +#include "vmwgfx_drv.h" +#include +#include +#include + +static const struct ttm_place vram_placement_flags = { + .fpfn = 0, + .lpfn = 0, + .flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED +}; + +static const struct ttm_place vram_ne_placement_flags = { + .fpfn = 0, + .lpfn = 0, + .flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED | TTM_PL_FLAG_NO_EVICT +}; + +static const struct ttm_place sys_placement_flags = { + .fpfn = 0, + .lpfn = 0, + .flags = TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED +}; + +static const struct ttm_place sys_ne_placement_flags = { + .fpfn = 0, + .lpfn = 0, + .flags = TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED | TTM_PL_FLAG_NO_EVICT +}; + +static const struct ttm_place gmr_placement_flags = { + .fpfn = 0, + .lpfn = 0, + .flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED +}; + +static const struct ttm_place gmr_ne_placement_flags = { + .fpfn = 0, + .lpfn = 0, + .flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED | TTM_PL_FLAG_NO_EVICT +}; + +static const struct ttm_place mob_placement_flags = { + .fpfn = 0, + .lpfn = 0, + .flags = VMW_PL_FLAG_MOB | TTM_PL_FLAG_CACHED +}; + +static const struct ttm_place mob_ne_placement_flags = { + .fpfn = 0, + .lpfn = 0, + .flags = VMW_PL_FLAG_MOB | TTM_PL_FLAG_CACHED | TTM_PL_FLAG_NO_EVICT +}; + +struct ttm_placement vmw_vram_placement = { + .num_placement = 1, + .placement = &vram_placement_flags, + .num_busy_placement = 1, + .busy_placement = &vram_placement_flags +}; + +static const struct ttm_place vram_gmr_placement_flags[] = { + { + .fpfn = 0, + .lpfn = 0, + .flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED + }, { + .fpfn = 0, + .lpfn = 0, + .flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED + } +}; + +static const struct ttm_place gmr_vram_placement_flags[] = { + { + .fpfn = 0, + .lpfn = 0, + .flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED + }, { + .fpfn = 0, + .lpfn = 0, + .flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED + } +}; + +struct ttm_placement vmw_vram_gmr_placement = { + .num_placement = 2, + .placement = vram_gmr_placement_flags, + .num_busy_placement = 1, + .busy_placement = &gmr_placement_flags +}; + +static const struct ttm_place vram_gmr_ne_placement_flags[] = { + { + .fpfn = 0, + .lpfn = 0, + .flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED | + TTM_PL_FLAG_NO_EVICT + }, { + .fpfn = 0, + .lpfn = 0, + .flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED | + TTM_PL_FLAG_NO_EVICT + } +}; + +struct ttm_placement vmw_vram_gmr_ne_placement = { + .num_placement = 2, + .placement = vram_gmr_ne_placement_flags, + .num_busy_placement = 1, + .busy_placement = &gmr_ne_placement_flags +}; + +struct ttm_placement vmw_vram_sys_placement = { + .num_placement = 1, + .placement = &vram_placement_flags, + .num_busy_placement = 1, + .busy_placement = &sys_placement_flags +}; + +struct ttm_placement vmw_vram_ne_placement = { + .num_placement = 1, + .placement = &vram_ne_placement_flags, + .num_busy_placement = 1, + .busy_placement = &vram_ne_placement_flags +}; + +struct ttm_placement vmw_sys_placement = { + .num_placement = 1, + .placement = &sys_placement_flags, + .num_busy_placement = 1, + .busy_placement = &sys_placement_flags +}; + +struct ttm_placement vmw_sys_ne_placement = { + .num_placement = 1, + .placement = &sys_ne_placement_flags, + .num_busy_placement = 1, + .busy_placement = &sys_ne_placement_flags +}; + +static const struct ttm_place evictable_placement_flags[] = { + { + .fpfn = 0, + .lpfn = 0, + .flags = TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED + }, { + .fpfn = 0, + .lpfn = 0, + .flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED + }, { + .fpfn = 0, + .lpfn = 0, + .flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED + }, { + .fpfn = 0, + .lpfn = 0, + .flags = VMW_PL_FLAG_MOB | TTM_PL_FLAG_CACHED + } +}; + +static const struct ttm_place nonfixed_placement_flags[] = { + { + .fpfn = 0, + .lpfn = 0, + .flags = TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED + }, { + .fpfn = 0, + .lpfn = 0, + .flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED + }, { + .fpfn = 0, + .lpfn = 0, + .flags = VMW_PL_FLAG_MOB | TTM_PL_FLAG_CACHED + } +}; + +struct ttm_placement vmw_evictable_placement = { + .num_placement = 4, + .placement = evictable_placement_flags, + .num_busy_placement = 1, + .busy_placement = &sys_placement_flags +}; + +struct ttm_placement vmw_srf_placement = { + .num_placement = 1, + .num_busy_placement = 2, + .placement = &gmr_placement_flags, + .busy_placement = gmr_vram_placement_flags +}; + +struct ttm_placement vmw_mob_placement = { + .num_placement = 1, + .num_busy_placement = 1, + .placement = &mob_placement_flags, + .busy_placement = &mob_placement_flags +}; + +struct ttm_placement vmw_mob_ne_placement = { + .num_placement = 1, + .num_busy_placement = 1, + .placement = &mob_ne_placement_flags, + .busy_placement = &mob_ne_placement_flags +}; + +struct ttm_placement vmw_nonfixed_placement = { + .num_placement = 3, + .placement = nonfixed_placement_flags, + .num_busy_placement = 1, + .busy_placement = &sys_placement_flags +}; + +struct vmw_ttm_tt { + struct ttm_dma_tt dma_ttm; + struct vmw_private *dev_priv; + int gmr_id; + struct vmw_mob *mob; + int mem_type; + struct sg_table sgt; + struct vmw_sg_table vsgt; + uint64_t sg_alloc_size; + bool mapped; +}; + +const size_t vmw_tt_size = sizeof(struct vmw_ttm_tt); + +/** + * Helper functions to advance a struct vmw_piter iterator. + * + * @viter: Pointer to the iterator. + * + * These functions return false if past the end of the list, + * true otherwise. Functions are selected depending on the current + * DMA mapping mode. + */ +static bool __vmw_piter_non_sg_next(struct vmw_piter *viter) +{ + return ++(viter->i) < viter->num_pages; +} + +static bool __vmw_piter_sg_next(struct vmw_piter *viter) +{ + return __sg_page_iter_next(&viter->iter); +} + + +/** + * Helper functions to return a pointer to the current page. + * + * @viter: Pointer to the iterator + * + * These functions return a pointer to the page currently + * pointed to by @viter. Functions are selected depending on the + * current mapping mode. + */ +static struct page *__vmw_piter_non_sg_page(struct vmw_piter *viter) +{ + return viter->pages[viter->i]; +} + +static struct page *__vmw_piter_sg_page(struct vmw_piter *viter) +{ + return sg_page_iter_page(&viter->iter); +} + + +/** + * Helper functions to return the DMA address of the current page. + * + * @viter: Pointer to the iterator + * + * These functions return the DMA address of the page currently + * pointed to by @viter. Functions are selected depending on the + * current mapping mode. + */ +static dma_addr_t __vmw_piter_phys_addr(struct vmw_piter *viter) +{ + return page_to_phys(viter->pages[viter->i]); +} + +static dma_addr_t __vmw_piter_dma_addr(struct vmw_piter *viter) +{ + return viter->addrs[viter->i]; +} + +static dma_addr_t __vmw_piter_sg_addr(struct vmw_piter *viter) +{ + return sg_page_iter_dma_address(&viter->iter); +} + + +/** + * vmw_piter_start - Initialize a struct vmw_piter. + * + * @viter: Pointer to the iterator to initialize + * @vsgt: Pointer to a struct vmw_sg_table to initialize from + * + * Note that we're following the convention of __sg_page_iter_start, so that + * the iterator doesn't point to a valid page after initialization; it has + * to be advanced one step first. + */ +void vmw_piter_start(struct vmw_piter *viter, const struct vmw_sg_table *vsgt, + unsigned long p_offset) +{ + viter->i = p_offset - 1; + viter->num_pages = vsgt->num_pages; + switch (vsgt->mode) { + case vmw_dma_phys: + viter->next = &__vmw_piter_non_sg_next; + viter->dma_address = &__vmw_piter_phys_addr; + viter->page = &__vmw_piter_non_sg_page; + viter->pages = vsgt->pages; + break; + case vmw_dma_alloc_coherent: + viter->next = &__vmw_piter_non_sg_next; + viter->dma_address = &__vmw_piter_dma_addr; + viter->page = &__vmw_piter_non_sg_page; + viter->addrs = vsgt->addrs; + viter->pages = vsgt->pages; + break; + case vmw_dma_map_populate: + case vmw_dma_map_bind: + viter->next = &__vmw_piter_sg_next; + viter->dma_address = &__vmw_piter_sg_addr; + viter->page = &__vmw_piter_sg_page; + __sg_page_iter_start(&viter->iter, vsgt->sgt->sgl, + vsgt->sgt->orig_nents, p_offset); + break; + default: + BUG(); + } +} + +/** + * vmw_ttm_unmap_from_dma - unmap device addresses previsouly mapped for + * TTM pages + * + * @vmw_tt: Pointer to a struct vmw_ttm_backend + * + * Used to free dma mappings previously mapped by vmw_ttm_map_for_dma. + */ +static void vmw_ttm_unmap_from_dma(struct vmw_ttm_tt *vmw_tt) +{ + struct device *dev = vmw_tt->dev_priv->dev->dev; + + dma_unmap_sg(dev, vmw_tt->sgt.sgl, vmw_tt->sgt.nents, + DMA_BIDIRECTIONAL); + vmw_tt->sgt.nents = vmw_tt->sgt.orig_nents; +} + +/** + * vmw_ttm_map_for_dma - map TTM pages to get device addresses + * + * @vmw_tt: Pointer to a struct vmw_ttm_backend + * + * This function is used to get device addresses from the kernel DMA layer. + * However, it's violating the DMA API in that when this operation has been + * performed, it's illegal for the CPU to write to the pages without first + * unmapping the DMA mappings, or calling dma_sync_sg_for_cpu(). It is + * therefore only legal to call this function if we know that the function + * dma_sync_sg_for_cpu() is a NOP, and dma_sync_sg_for_device() is at most + * a CPU write buffer flush. + */ +static int vmw_ttm_map_for_dma(struct vmw_ttm_tt *vmw_tt) +{ + struct device *dev = vmw_tt->dev_priv->dev->dev; + int ret; + + ret = dma_map_sg(dev, vmw_tt->sgt.sgl, vmw_tt->sgt.orig_nents, + DMA_BIDIRECTIONAL); + if (unlikely(ret == 0)) + return -ENOMEM; + + vmw_tt->sgt.nents = ret; + + return 0; +} + +/** + * vmw_ttm_map_dma - Make sure TTM pages are visible to the device + * + * @vmw_tt: Pointer to a struct vmw_ttm_tt + * + * Select the correct function for and make sure the TTM pages are + * visible to the device. Allocate storage for the device mappings. + * If a mapping has already been performed, indicated by the storage + * pointer being non NULL, the function returns success. + */ +static int vmw_ttm_map_dma(struct vmw_ttm_tt *vmw_tt) +{ + struct vmw_private *dev_priv = vmw_tt->dev_priv; + struct ttm_mem_global *glob = vmw_mem_glob(dev_priv); + struct vmw_sg_table *vsgt = &vmw_tt->vsgt; + struct ttm_operation_ctx ctx = { + .interruptible = true, + .no_wait_gpu = false + }; + struct vmw_piter iter; + dma_addr_t old; + int ret = 0; + static size_t sgl_size; + static size_t sgt_size; + + if (vmw_tt->mapped) + return 0; + + vsgt->mode = dev_priv->map_mode; + vsgt->pages = vmw_tt->dma_ttm.ttm.pages; + vsgt->num_pages = vmw_tt->dma_ttm.ttm.num_pages; + vsgt->addrs = vmw_tt->dma_ttm.dma_address; + vsgt->sgt = &vmw_tt->sgt; + + switch (dev_priv->map_mode) { + case vmw_dma_map_bind: + case vmw_dma_map_populate: + if (unlikely(!sgl_size)) { + sgl_size = ttm_round_pot(sizeof(struct scatterlist)); + sgt_size = ttm_round_pot(sizeof(struct sg_table)); + } + vmw_tt->sg_alloc_size = sgt_size + sgl_size * vsgt->num_pages; + ret = ttm_mem_global_alloc(glob, vmw_tt->sg_alloc_size, &ctx); + if (unlikely(ret != 0)) + return ret; + + ret = sg_alloc_table_from_pages(&vmw_tt->sgt, vsgt->pages, + vsgt->num_pages, 0, + (unsigned long) + vsgt->num_pages << PAGE_SHIFT, + GFP_KERNEL); + if (unlikely(ret != 0)) + goto out_sg_alloc_fail; + + if (vsgt->num_pages > vmw_tt->sgt.nents) { + uint64_t over_alloc = + sgl_size * (vsgt->num_pages - + vmw_tt->sgt.nents); + + ttm_mem_global_free(glob, over_alloc); + vmw_tt->sg_alloc_size -= over_alloc; + } + + ret = vmw_ttm_map_for_dma(vmw_tt); + if (unlikely(ret != 0)) + goto out_map_fail; + + break; + default: + break; + } + + old = ~((dma_addr_t) 0); + vmw_tt->vsgt.num_regions = 0; + for (vmw_piter_start(&iter, vsgt, 0); vmw_piter_next(&iter);) { + dma_addr_t cur = vmw_piter_dma_addr(&iter); + + if (cur != old + PAGE_SIZE) + vmw_tt->vsgt.num_regions++; + old = cur; + } + + vmw_tt->mapped = true; + return 0; + +out_map_fail: + sg_free_table(vmw_tt->vsgt.sgt); + vmw_tt->vsgt.sgt = NULL; +out_sg_alloc_fail: + ttm_mem_global_free(glob, vmw_tt->sg_alloc_size); + return ret; +} + +/** + * vmw_ttm_unmap_dma - Tear down any TTM page device mappings + * + * @vmw_tt: Pointer to a struct vmw_ttm_tt + * + * Tear down any previously set up device DMA mappings and free + * any storage space allocated for them. If there are no mappings set up, + * this function is a NOP. + */ +static void vmw_ttm_unmap_dma(struct vmw_ttm_tt *vmw_tt) +{ + struct vmw_private *dev_priv = vmw_tt->dev_priv; + + if (!vmw_tt->vsgt.sgt) + return; + + switch (dev_priv->map_mode) { + case vmw_dma_map_bind: + case vmw_dma_map_populate: + vmw_ttm_unmap_from_dma(vmw_tt); + sg_free_table(vmw_tt->vsgt.sgt); + vmw_tt->vsgt.sgt = NULL; + ttm_mem_global_free(vmw_mem_glob(dev_priv), + vmw_tt->sg_alloc_size); + break; + default: + break; + } + vmw_tt->mapped = false; +} + + +/** + * vmw_bo_map_dma - Make sure buffer object pages are visible to the device + * + * @bo: Pointer to a struct ttm_buffer_object + * + * Wrapper around vmw_ttm_map_dma, that takes a TTM buffer object pointer + * instead of a pointer to a struct vmw_ttm_backend as argument. + * Note that the buffer object must be either pinned or reserved before + * calling this function. + */ +int vmw_bo_map_dma(struct ttm_buffer_object *bo) +{ + struct vmw_ttm_tt *vmw_tt = + container_of(bo->ttm, struct vmw_ttm_tt, dma_ttm.ttm); + + return vmw_ttm_map_dma(vmw_tt); +} + + +/** + * vmw_bo_unmap_dma - Make sure buffer object pages are visible to the device + * + * @bo: Pointer to a struct ttm_buffer_object + * + * Wrapper around vmw_ttm_unmap_dma, that takes a TTM buffer object pointer + * instead of a pointer to a struct vmw_ttm_backend as argument. + */ +void vmw_bo_unmap_dma(struct ttm_buffer_object *bo) +{ + struct vmw_ttm_tt *vmw_tt = + container_of(bo->ttm, struct vmw_ttm_tt, dma_ttm.ttm); + + vmw_ttm_unmap_dma(vmw_tt); +} + + +/** + * vmw_bo_sg_table - Return a struct vmw_sg_table object for a + * TTM buffer object + * + * @bo: Pointer to a struct ttm_buffer_object + * + * Returns a pointer to a struct vmw_sg_table object. The object should + * not be freed after use. + * Note that for the device addresses to be valid, the buffer object must + * either be reserved or pinned. + */ +const struct vmw_sg_table *vmw_bo_sg_table(struct ttm_buffer_object *bo) +{ + struct vmw_ttm_tt *vmw_tt = + container_of(bo->ttm, struct vmw_ttm_tt, dma_ttm.ttm); + + return &vmw_tt->vsgt; +} + + +static int vmw_ttm_bind(struct ttm_tt *ttm, struct ttm_mem_reg *bo_mem) +{ + struct vmw_ttm_tt *vmw_be = + container_of(ttm, struct vmw_ttm_tt, dma_ttm.ttm); + int ret; + + ret = vmw_ttm_map_dma(vmw_be); + if (unlikely(ret != 0)) + return ret; + + vmw_be->gmr_id = bo_mem->start; + vmw_be->mem_type = bo_mem->mem_type; + + switch (bo_mem->mem_type) { + case VMW_PL_GMR: + return vmw_gmr_bind(vmw_be->dev_priv, &vmw_be->vsgt, + ttm->num_pages, vmw_be->gmr_id); + case VMW_PL_MOB: + if (unlikely(vmw_be->mob == NULL)) { + vmw_be->mob = + vmw_mob_create(ttm->num_pages); + if (unlikely(vmw_be->mob == NULL)) + return -ENOMEM; + } + + return vmw_mob_bind(vmw_be->dev_priv, vmw_be->mob, + &vmw_be->vsgt, ttm->num_pages, + vmw_be->gmr_id); + default: + BUG(); + } + return 0; +} + +static int vmw_ttm_unbind(struct ttm_tt *ttm) +{ + struct vmw_ttm_tt *vmw_be = + container_of(ttm, struct vmw_ttm_tt, dma_ttm.ttm); + + switch (vmw_be->mem_type) { + case VMW_PL_GMR: + vmw_gmr_unbind(vmw_be->dev_priv, vmw_be->gmr_id); + break; + case VMW_PL_MOB: + vmw_mob_unbind(vmw_be->dev_priv, vmw_be->mob); + break; + default: + BUG(); + } + + if (vmw_be->dev_priv->map_mode == vmw_dma_map_bind) + vmw_ttm_unmap_dma(vmw_be); + + return 0; +} + + +static void vmw_ttm_destroy(struct ttm_tt *ttm) +{ + struct vmw_ttm_tt *vmw_be = + container_of(ttm, struct vmw_ttm_tt, dma_ttm.ttm); + + vmw_ttm_unmap_dma(vmw_be); + if (vmw_be->dev_priv->map_mode == vmw_dma_alloc_coherent) + ttm_dma_tt_fini(&vmw_be->dma_ttm); + else + ttm_tt_fini(ttm); + + if (vmw_be->mob) + vmw_mob_destroy(vmw_be->mob); + + kfree(vmw_be); +} + + +static int vmw_ttm_populate(struct ttm_tt *ttm, struct ttm_operation_ctx *ctx) +{ + struct vmw_ttm_tt *vmw_tt = + container_of(ttm, struct vmw_ttm_tt, dma_ttm.ttm); + struct vmw_private *dev_priv = vmw_tt->dev_priv; + struct ttm_mem_global *glob = vmw_mem_glob(dev_priv); + int ret; + + if (ttm->state != tt_unpopulated) + return 0; + + if (dev_priv->map_mode == vmw_dma_alloc_coherent) { + size_t size = + ttm_round_pot(ttm->num_pages * sizeof(dma_addr_t)); + ret = ttm_mem_global_alloc(glob, size, ctx); + if (unlikely(ret != 0)) + return ret; + + ret = ttm_dma_populate(&vmw_tt->dma_ttm, dev_priv->dev->dev, + ctx); + if (unlikely(ret != 0)) + ttm_mem_global_free(glob, size); + } else + ret = ttm_pool_populate(ttm, ctx); + + return ret; +} + +static void vmw_ttm_unpopulate(struct ttm_tt *ttm) +{ + struct vmw_ttm_tt *vmw_tt = container_of(ttm, struct vmw_ttm_tt, + dma_ttm.ttm); + struct vmw_private *dev_priv = vmw_tt->dev_priv; + struct ttm_mem_global *glob = vmw_mem_glob(dev_priv); + + + if (vmw_tt->mob) { + vmw_mob_destroy(vmw_tt->mob); + vmw_tt->mob = NULL; + } + + vmw_ttm_unmap_dma(vmw_tt); + if (dev_priv->map_mode == vmw_dma_alloc_coherent) { + size_t size = + ttm_round_pot(ttm->num_pages * sizeof(dma_addr_t)); + + ttm_dma_unpopulate(&vmw_tt->dma_ttm, dev_priv->dev->dev); + ttm_mem_global_free(glob, size); + } else + ttm_pool_unpopulate(ttm); +} + +static struct ttm_backend_func vmw_ttm_func = { + .bind = vmw_ttm_bind, + .unbind = vmw_ttm_unbind, + .destroy = vmw_ttm_destroy, +}; + +static struct ttm_tt *vmw_ttm_tt_create(struct ttm_buffer_object *bo, + uint32_t page_flags) +{ + struct vmw_ttm_tt *vmw_be; + int ret; + + vmw_be = kzalloc(sizeof(*vmw_be), GFP_KERNEL); + if (!vmw_be) + return NULL; + + vmw_be->dma_ttm.ttm.func = &vmw_ttm_func; + vmw_be->dev_priv = container_of(bo->bdev, struct vmw_private, bdev); + vmw_be->mob = NULL; + + if (vmw_be->dev_priv->map_mode == vmw_dma_alloc_coherent) + ret = ttm_dma_tt_init(&vmw_be->dma_ttm, bo, page_flags); + else + ret = ttm_tt_init(&vmw_be->dma_ttm.ttm, bo, page_flags); + if (unlikely(ret != 0)) + goto out_no_init; + + return &vmw_be->dma_ttm.ttm; +out_no_init: + kfree(vmw_be); + return NULL; +} + +static int vmw_invalidate_caches(struct ttm_bo_device *bdev, uint32_t flags) +{ + return 0; +} + +static int vmw_init_mem_type(struct ttm_bo_device *bdev, uint32_t type, + struct ttm_mem_type_manager *man) +{ + switch (type) { + case TTM_PL_SYSTEM: + /* System memory */ + + man->flags = TTM_MEMTYPE_FLAG_MAPPABLE; + man->available_caching = TTM_PL_FLAG_CACHED; + man->default_caching = TTM_PL_FLAG_CACHED; + break; + case TTM_PL_VRAM: + /* "On-card" video ram */ + man->func = &ttm_bo_manager_func; + man->gpu_offset = 0; + man->flags = TTM_MEMTYPE_FLAG_FIXED | TTM_MEMTYPE_FLAG_MAPPABLE; + man->available_caching = TTM_PL_FLAG_CACHED; + man->default_caching = TTM_PL_FLAG_CACHED; + break; + case VMW_PL_GMR: + case VMW_PL_MOB: + /* + * "Guest Memory Regions" is an aperture like feature with + * one slot per bo. There is an upper limit of the number of + * slots as well as the bo size. + */ + man->func = &vmw_gmrid_manager_func; + man->gpu_offset = 0; + man->flags = TTM_MEMTYPE_FLAG_CMA | TTM_MEMTYPE_FLAG_MAPPABLE; + man->available_caching = TTM_PL_FLAG_CACHED; + man->default_caching = TTM_PL_FLAG_CACHED; + break; + default: + DRM_ERROR("Unsupported memory type %u\n", (unsigned)type); + return -EINVAL; + } + return 0; +} + +static void vmw_evict_flags(struct ttm_buffer_object *bo, + struct ttm_placement *placement) +{ + *placement = vmw_sys_placement; +} + +static int vmw_verify_access(struct ttm_buffer_object *bo, struct file *filp) +{ + struct ttm_object_file *tfile = + vmw_fpriv((struct drm_file *)filp->private_data)->tfile; + + return vmw_user_bo_verify_access(bo, tfile); +} + +static int vmw_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem) +{ + struct ttm_mem_type_manager *man = &bdev->man[mem->mem_type]; + struct vmw_private *dev_priv = container_of(bdev, struct vmw_private, bdev); + + mem->bus.addr = NULL; + mem->bus.is_iomem = false; + mem->bus.offset = 0; + mem->bus.size = mem->num_pages << PAGE_SHIFT; + mem->bus.base = 0; + if (!(man->flags & TTM_MEMTYPE_FLAG_MAPPABLE)) + return -EINVAL; + switch (mem->mem_type) { + case TTM_PL_SYSTEM: + case VMW_PL_GMR: + case VMW_PL_MOB: + return 0; + case TTM_PL_VRAM: + mem->bus.offset = mem->start << PAGE_SHIFT; + mem->bus.base = dev_priv->vram_start; + mem->bus.is_iomem = true; + break; + default: + return -EINVAL; + } + return 0; +} + +static void vmw_ttm_io_mem_free(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem) +{ +} + +static int vmw_ttm_fault_reserve_notify(struct ttm_buffer_object *bo) +{ + return 0; +} + +/** + * vmw_move_notify - TTM move_notify_callback + * + * @bo: The TTM buffer object about to move. + * @mem: The struct ttm_mem_reg indicating to what memory + * region the move is taking place. + * + * Calls move_notify for all subsystems needing it. + * (currently only resources). + */ +static void vmw_move_notify(struct ttm_buffer_object *bo, + bool evict, + struct ttm_mem_reg *mem) +{ + vmw_resource_move_notify(bo, mem); + vmw_query_move_notify(bo, mem); +} + + +/** + * vmw_swap_notify - TTM move_notify_callback + * + * @bo: The TTM buffer object about to be swapped out. + */ +static void vmw_swap_notify(struct ttm_buffer_object *bo) +{ + vmw_resource_swap_notify(bo); + (void) ttm_bo_wait(bo, false, false); +} + + +struct ttm_bo_driver vmw_bo_driver = { + .ttm_tt_create = &vmw_ttm_tt_create, + .ttm_tt_populate = &vmw_ttm_populate, + .ttm_tt_unpopulate = &vmw_ttm_unpopulate, + .invalidate_caches = vmw_invalidate_caches, + .init_mem_type = vmw_init_mem_type, + .eviction_valuable = ttm_bo_eviction_valuable, + .evict_flags = vmw_evict_flags, + .move = NULL, + .verify_access = vmw_verify_access, + .move_notify = vmw_move_notify, + .swap_notify = vmw_swap_notify, + .fault_reserve_notify = &vmw_ttm_fault_reserve_notify, + .io_mem_reserve = &vmw_ttm_io_mem_reserve, + .io_mem_free = &vmw_ttm_io_mem_free, +}; diff --git a/include/uapi/drm/vmwgfx_drm.h b/include/uapi/drm/vmwgfx_drm.h index 0bc784f5e0db..57115a5fe61a 100644 --- a/include/uapi/drm/vmwgfx_drm.h +++ b/include/uapi/drm/vmwgfx_drm.h @@ -40,6 +40,7 @@ extern "C" { #define DRM_VMW_GET_PARAM 0 #define DRM_VMW_ALLOC_DMABUF 1 +#define DRM_VMW_ALLOC_BO 1 #define DRM_VMW_UNREF_DMABUF 2 #define DRM_VMW_HANDLE_CLOSE 2 #define DRM_VMW_CURSOR_BYPASS 3 @@ -356,9 +357,9 @@ struct drm_vmw_fence_rep { /*************************************************************************/ /** - * DRM_VMW_ALLOC_DMABUF + * DRM_VMW_ALLOC_BO * - * Allocate a DMA buffer that is visible also to the host. + * Allocate a buffer object that is visible also to the host. * NOTE: The buffer is * identified by a handle and an offset, which are private to the guest, but * useable in the command stream. The guest kernel may translate these @@ -366,27 +367,28 @@ struct drm_vmw_fence_rep { * be zero at all times, or it may disappear from the interface before it is * fixed. * - * The DMA buffer may stay user-space mapped in the guest at all times, + * The buffer object may stay user-space mapped in the guest at all times, * and is thus suitable for sub-allocation. * - * DMA buffers are mapped using the mmap() syscall on the drm device. + * Buffer objects are mapped using the mmap() syscall on the drm device. */ /** - * struct drm_vmw_alloc_dmabuf_req + * struct drm_vmw_alloc_bo_req * * @size: Required minimum size of the buffer. * - * Input data to the DRM_VMW_ALLOC_DMABUF Ioctl. + * Input data to the DRM_VMW_ALLOC_BO Ioctl. */ -struct drm_vmw_alloc_dmabuf_req { +struct drm_vmw_alloc_bo_req { __u32 size; __u32 pad64; }; +#define drm_vmw_alloc_dmabuf_req drm_vmw_alloc_bo_req /** - * struct drm_vmw_dmabuf_rep + * struct drm_vmw_bo_rep * * @map_handle: Offset to use in the mmap() call used to map the buffer. * @handle: Handle unique to this buffer. Used for unreferencing. @@ -395,50 +397,32 @@ struct drm_vmw_alloc_dmabuf_req { * @cur_gmr_offset: Offset to use in the command stream when this buffer is * referenced. See note above. * - * Output data from the DRM_VMW_ALLOC_DMABUF Ioctl. + * Output data from the DRM_VMW_ALLOC_BO Ioctl. */ -struct drm_vmw_dmabuf_rep { +struct drm_vmw_bo_rep { __u64 map_handle; __u32 handle; __u32 cur_gmr_id; __u32 cur_gmr_offset; __u32 pad64; }; +#define drm_vmw_dmabuf_rep drm_vmw_bo_rep /** - * union drm_vmw_dmabuf_arg + * union drm_vmw_alloc_bo_arg * * @req: Input data as described above. * @rep: Output data as described above. * - * Argument to the DRM_VMW_ALLOC_DMABUF Ioctl. + * Argument to the DRM_VMW_ALLOC_BO Ioctl. */ -union drm_vmw_alloc_dmabuf_arg { - struct drm_vmw_alloc_dmabuf_req req; - struct drm_vmw_dmabuf_rep rep; -}; - -/*************************************************************************/ -/** - * DRM_VMW_UNREF_DMABUF - Free a DMA buffer. - * - */ - -/** - * struct drm_vmw_unref_dmabuf_arg - * - * @handle: Handle indicating what buffer to free. Obtained from the - * DRM_VMW_ALLOC_DMABUF Ioctl. - * - * Argument to the DRM_VMW_UNREF_DMABUF Ioctl. - */ - -struct drm_vmw_unref_dmabuf_arg { - __u32 handle; - __u32 pad64; +union drm_vmw_alloc_bo_arg { + struct drm_vmw_alloc_bo_req req; + struct drm_vmw_bo_rep rep; }; +#define drm_vmw_alloc_dmabuf_arg drm_vmw_alloc_bo_arg /*************************************************************************/ /** @@ -1103,9 +1087,8 @@ union drm_vmw_extended_context_arg { * DRM_VMW_HANDLE_CLOSE - Close a user-space handle and release its * underlying resource. * - * Note that this ioctl is overlaid on the DRM_VMW_UNREF_DMABUF Ioctl. - * The ioctl arguments therefore need to be identical in layout. - * + * Note that this ioctl is overlaid on the deprecated DRM_VMW_UNREF_DMABUF + * Ioctl. */ /** @@ -1119,7 +1102,7 @@ struct drm_vmw_handle_close_arg { __u32 handle; __u32 pad64; }; - +#define drm_vmw_unref_dmabuf_arg drm_vmw_handle_close_arg #if defined(__cplusplus) } -- cgit v1.2.3 From 63b8add24e1a99d7218c904f258623e7c07ce99e Mon Sep 17 00:00:00 2001 From: Elaine Zhang Date: Fri, 15 Jun 2018 10:16:49 +0800 Subject: clk: rockchip: add dt-binding header for px30 Add the dt-bindings header for the px30, that gets shared between the clock controller and the clock references in the dts. Add softreset ID for px30. Signed-off-by: Elaine Zhang Reviewed-by: Rob Herring Signed-off-by: Heiko Stuebner --- include/dt-bindings/clock/px30-cru.h | 389 +++++++++++++++++++++++++++++++++++ 1 file changed, 389 insertions(+) create mode 100644 include/dt-bindings/clock/px30-cru.h (limited to 'include') diff --git a/include/dt-bindings/clock/px30-cru.h b/include/dt-bindings/clock/px30-cru.h new file mode 100644 index 000000000000..00101479f7c4 --- /dev/null +++ b/include/dt-bindings/clock/px30-cru.h @@ -0,0 +1,389 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _DT_BINDINGS_CLK_ROCKCHIP_PX30_H +#define _DT_BINDINGS_CLK_ROCKCHIP_PX30_H + +/* core clocks */ +#define PLL_APLL 1 +#define PLL_DPLL 2 +#define PLL_CPLL 3 +#define PLL_NPLL 4 +#define APLL_BOOST_H 5 +#define APLL_BOOST_L 6 +#define ARMCLK 7 + +/* sclk gates (special clocks) */ +#define USB480M 14 +#define SCLK_PDM 15 +#define SCLK_I2S0_TX 16 +#define SCLK_I2S0_TX_OUT 17 +#define SCLK_I2S0_RX 18 +#define SCLK_I2S0_RX_OUT 19 +#define SCLK_I2S1 20 +#define SCLK_I2S1_OUT 21 +#define SCLK_I2S2 22 +#define SCLK_I2S2_OUT 23 +#define SCLK_UART1 24 +#define SCLK_UART2 25 +#define SCLK_UART3 26 +#define SCLK_UART4 27 +#define SCLK_UART5 28 +#define SCLK_I2C0 29 +#define SCLK_I2C1 30 +#define SCLK_I2C2 31 +#define SCLK_I2C3 32 +#define SCLK_I2C4 33 +#define SCLK_PWM0 34 +#define SCLK_PWM1 35 +#define SCLK_SPI0 36 +#define SCLK_SPI1 37 +#define SCLK_TIMER0 38 +#define SCLK_TIMER1 39 +#define SCLK_TIMER2 40 +#define SCLK_TIMER3 41 +#define SCLK_TIMER4 42 +#define SCLK_TIMER5 43 +#define SCLK_TSADC 44 +#define SCLK_SARADC 45 +#define SCLK_OTP 46 +#define SCLK_OTP_USR 47 +#define SCLK_CRYPTO 48 +#define SCLK_CRYPTO_APK 49 +#define SCLK_DDRC 50 +#define SCLK_ISP 51 +#define SCLK_CIF_OUT 52 +#define SCLK_RGA_CORE 53 +#define SCLK_VOPB_PWM 54 +#define SCLK_NANDC 55 +#define SCLK_SDIO 56 +#define SCLK_EMMC 57 +#define SCLK_SFC 58 +#define SCLK_SDMMC 59 +#define SCLK_OTG_ADP 60 +#define SCLK_GMAC_SRC 61 +#define SCLK_GMAC 62 +#define SCLK_GMAC_RX_TX 63 +#define SCLK_MAC_REF 64 +#define SCLK_MAC_REFOUT 65 +#define SCLK_MAC_OUT 66 +#define SCLK_SDMMC_DRV 67 +#define SCLK_SDMMC_SAMPLE 68 +#define SCLK_SDIO_DRV 69 +#define SCLK_SDIO_SAMPLE 70 +#define SCLK_EMMC_DRV 71 +#define SCLK_EMMC_SAMPLE 72 +#define SCLK_GPU 73 +#define SCLK_PVTM 74 +#define SCLK_CORE_VPU 75 +#define SCLK_GMAC_RMII 76 +#define SCLK_UART2_SRC 77 +#define SCLK_NANDC_DIV 78 +#define SCLK_NANDC_DIV50 79 +#define SCLK_SDIO_DIV 80 +#define SCLK_SDIO_DIV50 81 +#define SCLK_EMMC_DIV 82 +#define SCLK_EMMC_DIV50 83 +#define SCLK_DDRCLK 84 +#define SCLK_UART1_SRC 85 + +/* dclk gates */ +#define DCLK_VOPB 150 +#define DCLK_VOPL 151 + +/* aclk gates */ +#define ACLK_GPU 170 +#define ACLK_BUS_PRE 171 +#define ACLK_CRYPTO 172 +#define ACLK_VI_PRE 173 +#define ACLK_VO_PRE 174 +#define ACLK_VPU 175 +#define ACLK_PERI_PRE 176 +#define ACLK_GMAC 178 +#define ACLK_CIF 179 +#define ACLK_ISP 180 +#define ACLK_VOPB 181 +#define ACLK_VOPL 182 +#define ACLK_RGA 183 +#define ACLK_GIC 184 +#define ACLK_DCF 186 +#define ACLK_DMAC 187 +#define ACLK_BUS_SRC 188 +#define ACLK_PERI_SRC 189 + +/* hclk gates */ +#define HCLK_BUS_PRE 240 +#define HCLK_CRYPTO 241 +#define HCLK_VI_PRE 242 +#define HCLK_VO_PRE 243 +#define HCLK_VPU 244 +#define HCLK_PERI_PRE 245 +#define HCLK_MMC_NAND 246 +#define HCLK_SDMMC 247 +#define HCLK_USB 248 +#define HCLK_CIF 249 +#define HCLK_ISP 250 +#define HCLK_VOPB 251 +#define HCLK_VOPL 252 +#define HCLK_RGA 253 +#define HCLK_NANDC 254 +#define HCLK_SDIO 255 +#define HCLK_EMMC 256 +#define HCLK_SFC 257 +#define HCLK_OTG 258 +#define HCLK_HOST 259 +#define HCLK_HOST_ARB 260 +#define HCLK_PDM 261 +#define HCLK_I2S0 262 +#define HCLK_I2S1 263 +#define HCLK_I2S2 264 + +/* pclk gates */ +#define PCLK_BUS_PRE 320 +#define PCLK_DDR 321 +#define PCLK_VO_PRE 322 +#define PCLK_GMAC 323 +#define PCLK_MIPI_DSI 324 +#define PCLK_MIPIDSIPHY 325 +#define PCLK_MIPICSIPHY 326 +#define PCLK_USB_GRF 327 +#define PCLK_DCF 328 +#define PCLK_UART1 329 +#define PCLK_UART2 330 +#define PCLK_UART3 331 +#define PCLK_UART4 332 +#define PCLK_UART5 333 +#define PCLK_I2C0 334 +#define PCLK_I2C1 335 +#define PCLK_I2C2 336 +#define PCLK_I2C3 337 +#define PCLK_I2C4 338 +#define PCLK_PWM0 339 +#define PCLK_PWM1 340 +#define PCLK_SPI0 341 +#define PCLK_SPI1 342 +#define PCLK_SARADC 343 +#define PCLK_TSADC 344 +#define PCLK_TIMER 345 +#define PCLK_OTP_NS 346 +#define PCLK_WDT_NS 347 +#define PCLK_GPIO1 348 +#define PCLK_GPIO2 349 +#define PCLK_GPIO3 350 +#define PCLK_ISP 351 +#define PCLK_CIF 352 +#define PCLK_OTP_PHY 353 + +#define CLK_NR_CLKS (PCLK_OTP_PHY + 1) + +/* pmu-clocks indices */ + +#define PLL_GPLL 1 + +#define SCLK_RTC32K_PMU 4 +#define SCLK_WIFI_PMU 5 +#define SCLK_UART0_PMU 6 +#define SCLK_PVTM_PMU 7 +#define PCLK_PMU_PRE 8 +#define SCLK_REF24M_PMU 9 +#define SCLK_USBPHY_REF 10 +#define SCLK_MIPIDSIPHY_REF 11 + +#define XIN24M_DIV 12 + +#define PCLK_GPIO0_PMU 20 +#define PCLK_UART0_PMU 21 + +#define CLKPMU_NR_CLKS (PCLK_UART0_PMU + 1) + +/* soft-reset indices */ +#define SRST_CORE0_PO 0 +#define SRST_CORE1_PO 1 +#define SRST_CORE2_PO 2 +#define SRST_CORE3_PO 3 +#define SRST_CORE0 4 +#define SRST_CORE1 5 +#define SRST_CORE2 6 +#define SRST_CORE3 7 +#define SRST_CORE0_DBG 8 +#define SRST_CORE1_DBG 9 +#define SRST_CORE2_DBG 10 +#define SRST_CORE3_DBG 11 +#define SRST_TOPDBG 12 +#define SRST_CORE_NOC 13 +#define SRST_STRC_A 14 +#define SRST_L2C 15 + +#define SRST_DAP 16 +#define SRST_CORE_PVTM 17 +#define SRST_GPU 18 +#define SRST_GPU_NIU 19 +#define SRST_UPCTL2 20 +#define SRST_UPCTL2_A 21 +#define SRST_UPCTL2_P 22 +#define SRST_MSCH 23 +#define SRST_MSCH_P 24 +#define SRST_DDRMON_P 25 +#define SRST_DDRSTDBY_P 26 +#define SRST_DDRSTDBY 27 +#define SRST_DDRGRF_p 28 +#define SRST_AXI_SPLIT_A 29 +#define SRST_AXI_CMD_A 30 +#define SRST_AXI_CMD_P 31 + +#define SRST_DDRPHY 32 +#define SRST_DDRPHYDIV 33 +#define SRST_DDRPHY_P 34 +#define SRST_VPU_A 36 +#define SRST_VPU_NIU_A 37 +#define SRST_VPU_H 38 +#define SRST_VPU_NIU_H 39 +#define SRST_VI_NIU_A 40 +#define SRST_VI_NIU_H 41 +#define SRST_ISP_H 42 +#define SRST_ISP 43 +#define SRST_CIF_A 44 +#define SRST_CIF_H 45 +#define SRST_CIF_PCLKIN 46 +#define SRST_MIPICSIPHY_P 47 + +#define SRST_VO_NIU_A 48 +#define SRST_VO_NIU_H 49 +#define SRST_VO_NIU_P 50 +#define SRST_VOPB_A 51 +#define SRST_VOPB_H 52 +#define SRST_VOPB 53 +#define SRST_PWM_VOPB 54 +#define SRST_VOPL_A 55 +#define SRST_VOPL_H 56 +#define SRST_VOPL 57 +#define SRST_RGA_A 58 +#define SRST_RGA_H 59 +#define SRST_RGA 60 +#define SRST_MIPIDSI_HOST_P 61 +#define SRST_MIPIDSIPHY_P 62 +#define SRST_VPU_CORE 63 + +#define SRST_PERI_NIU_A 64 +#define SRST_USB_NIU_H 65 +#define SRST_USB2OTG_H 66 +#define SRST_USB2OTG 67 +#define SRST_USB2OTG_ADP 68 +#define SRST_USB2HOST_H 69 +#define SRST_USB2HOST_ARB_H 70 +#define SRST_USB2HOST_AUX_H 71 +#define SRST_USB2HOST_EHCI 72 +#define SRST_USB2HOST 73 +#define SRST_USBPHYPOR 74 +#define SRST_USBPHY_OTG_PORT 75 +#define SRST_USBPHY_HOST_PORT 76 +#define SRST_USBPHY_GRF 77 +#define SRST_CPU_BOOST_P 78 +#define SRST_CPU_BOOST 79 + +#define SRST_MMC_NAND_NIU_H 80 +#define SRST_SDIO_H 81 +#define SRST_EMMC_H 82 +#define SRST_SFC_H 83 +#define SRST_SFC 84 +#define SRST_SDCARD_NIU_H 85 +#define SRST_SDMMC_H 86 +#define SRST_NANDC_H 89 +#define SRST_NANDC 90 +#define SRST_GMAC_NIU_A 92 +#define SRST_GMAC_NIU_P 93 +#define SRST_GMAC_A 94 + +#define SRST_PMU_NIU_P 96 +#define SRST_PMU_SGRF_P 97 +#define SRST_PMU_GRF_P 98 +#define SRST_PMU 99 +#define SRST_PMU_MEM_P 100 +#define SRST_PMU_GPIO0_P 101 +#define SRST_PMU_UART0_P 102 +#define SRST_PMU_CRU_P 103 +#define SRST_PMU_PVTM 104 +#define SRST_PMU_UART 105 +#define SRST_PMU_NIU_H 106 +#define SRST_PMU_DDR_FAIL_SAVE 107 +#define SRST_PMU_CORE_PERF_A 108 +#define SRST_PMU_CORE_GRF_P 109 +#define SRST_PMU_GPU_PERF_A 110 +#define SRST_PMU_GPU_GRF_P 111 + +#define SRST_CRYPTO_NIU_A 112 +#define SRST_CRYPTO_NIU_H 113 +#define SRST_CRYPTO_A 114 +#define SRST_CRYPTO_H 115 +#define SRST_CRYPTO 116 +#define SRST_CRYPTO_APK 117 +#define SRST_BUS_NIU_H 120 +#define SRST_USB_NIU_P 121 +#define SRST_BUS_TOP_NIU_P 122 +#define SRST_INTMEM_A 123 +#define SRST_GIC_A 124 +#define SRST_ROM_H 126 +#define SRST_DCF_A 127 + +#define SRST_DCF_P 128 +#define SRST_PDM_H 129 +#define SRST_PDM 130 +#define SRST_I2S0_H 131 +#define SRST_I2S0_TX 132 +#define SRST_I2S1_H 133 +#define SRST_I2S1 134 +#define SRST_I2S2_H 135 +#define SRST_I2S2 136 +#define SRST_UART1_P 137 +#define SRST_UART1 138 +#define SRST_UART2_P 139 +#define SRST_UART2 140 +#define SRST_UART3_P 141 +#define SRST_UART3 142 +#define SRST_UART4_P 143 + +#define SRST_UART4 144 +#define SRST_UART5_P 145 +#define SRST_UART5 146 +#define SRST_I2C0_P 147 +#define SRST_I2C0 148 +#define SRST_I2C1_P 149 +#define SRST_I2C1 150 +#define SRST_I2C2_P 151 +#define SRST_I2C2 152 +#define SRST_I2C3_P 153 +#define SRST_I2C3 154 +#define SRST_PWM0_P 157 +#define SRST_PWM0 158 +#define SRST_PWM1_P 159 + +#define SRST_PWM1 160 +#define SRST_SPI0_P 161 +#define SRST_SPI0 162 +#define SRST_SPI1_P 163 +#define SRST_SPI1 164 +#define SRST_SARADC_P 165 +#define SRST_SARADC 166 +#define SRST_TSADC_P 167 +#define SRST_TSADC 168 +#define SRST_TIMER_P 169 +#define SRST_TIMER0 170 +#define SRST_TIMER1 171 +#define SRST_TIMER2 172 +#define SRST_TIMER3 173 +#define SRST_TIMER4 174 +#define SRST_TIMER5 175 + +#define SRST_OTP_NS_P 176 +#define SRST_OTP_NS_SBPI 177 +#define SRST_OTP_NS_USR 178 +#define SRST_OTP_PHY_P 179 +#define SRST_OTP_PHY 180 +#define SRST_WDT_NS_P 181 +#define SRST_GPIO1_P 182 +#define SRST_GPIO2_P 183 +#define SRST_GPIO3_P 184 +#define SRST_SGRF_P 185 +#define SRST_GRF_P 186 +#define SRST_I2S0_RX 191 + +#endif -- cgit v1.2.3 From 69b9e1e07d98b57b972df3c44647ca8795284d39 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 2 Jul 2018 18:21:11 +0800 Subject: ipv4: add __ip_queue_xmit() that supports tos param This patch introduces __ip_queue_xmit(), through which the callers can pass tos param into it without having to set inet->tos. For ipv6, ip6_xmit() already allows passing tclass parameter. It's needed when some transport protocol doesn't use inet->tos, like sctp's per transport dscp, which will be added in next patch. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/net/ip.h | 9 ++++++++- net/ipv4/ip_output.c | 9 +++++---- 2 files changed, 13 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/ip.h b/include/net/ip.h index 0d2281b4b27a..09da79d8ceea 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -148,7 +148,8 @@ void ip_send_check(struct iphdr *ip); int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb); int ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb); -int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl); +int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, + __u8 tos); void ip_init(void); int ip_append_data(struct sock *sk, struct flowi4 *fl4, int getfrag(void *from, char *to, int offset, int len, @@ -174,6 +175,12 @@ struct sk_buff *ip_make_skb(struct sock *sk, struct flowi4 *fl4, struct ipcm_cookie *ipc, struct rtable **rtp, struct inet_cork *cork, unsigned int flags); +static inline int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, + struct flowi *fl) +{ + return __ip_queue_xmit(sk, skb, fl, inet_sk(sk)->tos); +} + static inline struct sk_buff *ip_finish_skb(struct sock *sk, struct flowi4 *fl4) { return __ip_make_skb(sk, fl4, &sk->sk_write_queue, &inet_sk(sk)->cork.base); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index b3308e9d9762..188cc586e7ff 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -423,7 +423,8 @@ static void ip_copy_addrs(struct iphdr *iph, const struct flowi4 *fl4) } /* Note: skb->sk can be different from sk, in case of tunnels */ -int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl) +int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, + __u8 tos) { struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); @@ -462,7 +463,7 @@ int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl) inet->inet_dport, inet->inet_sport, sk->sk_protocol, - RT_CONN_FLAGS(sk), + RT_CONN_FLAGS_TOS(sk, tos), sk->sk_bound_dev_if); if (IS_ERR(rt)) goto no_route; @@ -478,7 +479,7 @@ packet_routed: skb_push(skb, sizeof(struct iphdr) + (inet_opt ? inet_opt->opt.optlen : 0)); skb_reset_network_header(skb); iph = ip_hdr(skb); - *((__be16 *)iph) = htons((4 << 12) | (5 << 8) | (inet->tos & 0xff)); + *((__be16 *)iph) = htons((4 << 12) | (5 << 8) | (tos & 0xff)); if (ip_dont_fragment(sk, &rt->dst) && !skb->ignore_df) iph->frag_off = htons(IP_DF); else @@ -511,7 +512,7 @@ no_route: kfree_skb(skb); return -EHOSTUNREACH; } -EXPORT_SYMBOL(ip_queue_xmit); +EXPORT_SYMBOL(__ip_queue_xmit); static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) { -- cgit v1.2.3 From 8a9c58d28d0f66569737a3295116710ed24573cd Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 2 Jul 2018 18:21:12 +0800 Subject: sctp: add support for dscp and flowlabel per transport Like some other per transport params, flowlabel and dscp are added in transport, asoc and sctp_sock. By default, transport sets its value from asoc's, and asoc does it from sctp_sock. flowlabel only works for ipv6 transport. Other than that they need to be passed down in sctp_xmit, flow4/6 also needs to set them before looking up route in get_dst. Note that it uses '& 0x100000' to check if flowlabel is set and '& 0x1' (tos 1st bit is unused) to check if dscp is set by users, so that they could be set to 0 by sockopt in next patch. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 7 +++++++ include/net/sctp/structs.h | 9 +++++++++ net/sctp/associola.c | 7 +++++++ net/sctp/ipv6.c | 11 +++++++++-- net/sctp/protocol.c | 16 ++++++++++++---- 5 files changed, 44 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index b36c76635f18..83d94341e003 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -801,4 +801,11 @@ struct sctp_strreset_resptsn { __be32 receivers_next_tsn; }; +enum { + SCTP_DSCP_SET_MASK = 0x1, + SCTP_DSCP_VAL_MASK = 0xfc, + SCTP_FLOWLABEL_SET_MASK = 0x100000, + SCTP_FLOWLABEL_VAL_MASK = 0xfffff +}; + #endif /* __LINUX_SCTP_H__ */ diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 701a51736fa5..ab869e0d8326 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -193,6 +193,9 @@ struct sctp_sock { /* This is the max_retrans value for new associations. */ __u16 pathmaxrxt; + __u32 flowlabel; + __u8 dscp; + /* The initial Path MTU to use for new associations. */ __u32 pathmtu; @@ -895,6 +898,9 @@ struct sctp_transport { */ __u16 pathmaxrxt; + __u32 flowlabel; + __u8 dscp; + /* This is the partially failed retrans value for the transport * and will be initialized from the assocs value. This can be changed * using the SCTP_PEER_ADDR_THLDS socket option @@ -1772,6 +1778,9 @@ struct sctp_association { */ __u16 pathmaxrxt; + __u32 flowlabel; + __u8 dscp; + /* Flag that path mtu update is pending */ __u8 pmtu_pending; diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 5d5a16204d50..16ecfbc95614 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -115,6 +115,9 @@ static struct sctp_association *sctp_association_init( /* Initialize path max retrans value. */ asoc->pathmaxrxt = sp->pathmaxrxt; + asoc->flowlabel = sp->flowlabel; + asoc->dscp = sp->dscp; + /* Initialize default path MTU. */ asoc->pathmtu = sp->pathmtu; @@ -647,6 +650,10 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc, peer->sackdelay = asoc->sackdelay; peer->sackfreq = asoc->sackfreq; + if (addr->sa.sa_family == AF_INET6) + peer->flowlabel = asoc->flowlabel; + peer->dscp = asoc->dscp; + /* Enable/disable heartbeat, SACK delay, and path MTU discovery * based on association setting. */ diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 0cd2e764f47f..38102bf7f13e 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -209,12 +209,17 @@ static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport) struct sock *sk = skb->sk; struct ipv6_pinfo *np = inet6_sk(sk); struct flowi6 *fl6 = &transport->fl.u.ip6; + __u8 tclass = np->tclass; int res; pr_debug("%s: skb:%p, len:%d, src:%pI6 dst:%pI6\n", __func__, skb, skb->len, &fl6->saddr, &fl6->daddr); - IP6_ECN_flow_xmit(sk, fl6->flowlabel); + if (transport->dscp & SCTP_DSCP_SET_MASK) + tclass = transport->dscp & SCTP_DSCP_VAL_MASK; + + if (INET_ECN_is_capable(tclass)) + IP6_ECN_flow_xmit(sk, fl6->flowlabel); if (!(transport->param_flags & SPP_PMTUD_ENABLE)) skb->ignore_df = 1; @@ -223,7 +228,7 @@ static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport) rcu_read_lock(); res = ip6_xmit(sk, skb, fl6, sk->sk_mark, rcu_dereference(np->opt), - np->tclass); + tclass); rcu_read_unlock(); return res; } @@ -254,6 +259,8 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, fl6->flowi6_oif = daddr->v6.sin6_scope_id; else if (asoc) fl6->flowi6_oif = asoc->base.sk->sk_bound_dev_if; + if (t->flowlabel & SCTP_FLOWLABEL_SET_MASK) + fl6->flowlabel = htonl(t->flowlabel & SCTP_FLOWLABEL_VAL_MASK); pr_debug("%s: dst=%pI6 ", __func__, &fl6->daddr); diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 67f73d3a1356..e948db29ab53 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -426,13 +426,16 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr, struct dst_entry *dst = NULL; union sctp_addr *daddr = &t->ipaddr; union sctp_addr dst_saddr; + __u8 tos = inet_sk(sk)->tos; + if (t->dscp & SCTP_DSCP_SET_MASK) + tos = t->dscp & SCTP_DSCP_VAL_MASK; memset(fl4, 0x0, sizeof(struct flowi4)); fl4->daddr = daddr->v4.sin_addr.s_addr; fl4->fl4_dport = daddr->v4.sin_port; fl4->flowi4_proto = IPPROTO_SCTP; if (asoc) { - fl4->flowi4_tos = RT_CONN_FLAGS(asoc->base.sk); + fl4->flowi4_tos = RT_CONN_FLAGS_TOS(asoc->base.sk, tos); fl4->flowi4_oif = asoc->base.sk->sk_bound_dev_if; fl4->fl4_sport = htons(asoc->base.bind_addr.port); } @@ -495,7 +498,7 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr, fl4->fl4_sport = laddr->a.v4.sin_port; flowi4_update_output(fl4, asoc->base.sk->sk_bound_dev_if, - RT_CONN_FLAGS(asoc->base.sk), + RT_CONN_FLAGS_TOS(asoc->base.sk, tos), daddr->v4.sin_addr.s_addr, laddr->a.v4.sin_addr.s_addr); @@ -971,16 +974,21 @@ static inline int sctp_v4_xmit(struct sk_buff *skb, struct sctp_transport *transport) { struct inet_sock *inet = inet_sk(skb->sk); + __u8 dscp = inet->tos; pr_debug("%s: skb:%p, len:%d, src:%pI4, dst:%pI4\n", __func__, skb, - skb->len, &transport->fl.u.ip4.saddr, &transport->fl.u.ip4.daddr); + skb->len, &transport->fl.u.ip4.saddr, + &transport->fl.u.ip4.daddr); + + if (transport->dscp & SCTP_DSCP_SET_MASK) + dscp = transport->dscp & SCTP_DSCP_VAL_MASK; inet->pmtudisc = transport->param_flags & SPP_PMTUD_ENABLE ? IP_PMTUDISC_DO : IP_PMTUDISC_DONT; SCTP_INC_STATS(sock_net(&inet->sk), SCTP_MIB_OUTSCTPPACKS); - return ip_queue_xmit(&inet->sk, skb, &transport->fl); + return __ip_queue_xmit(&inet->sk, skb, &transport->fl, dscp); } static struct sctp_af sctp_af_inet; -- cgit v1.2.3 From 0b0dce7a36fb9f1a9dd8245ea82d3a268c6943fe Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 2 Jul 2018 18:21:13 +0800 Subject: sctp: add spp_ipv6_flowlabel and spp_dscp for sctp_paddrparams spp_ipv6_flowlabel and spp_dscp are added in sctp_paddrparams in this patch so that users could set sctp_sock/asoc/transport dscp and flowlabel with spp_flags SPP_IPV6_FLOWLABEL or SPP_DSCP by SCTP_PEER_ADDR_PARAMS , as described section 8.1.12 in RFC6458. As said in last patch, it uses '| 0x100000' or '|0x1' to mark flowlabel or dscp is set, so that their values could be set to 0. Note that to guarantee that an old app built with old kernel headers could work on the newer kernel, the param's check in sctp_g/setsockopt_peer_addr_params() is also improved, which follows the way that sctp_g/setsockopt_delayed_ack() or some other sockopts' process that accept two types of params does. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/uapi/linux/sctp.h | 4 ++ net/sctp/socket.c | 177 ++++++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 175 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index c02986a284db..b479db5c71d9 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -763,6 +763,8 @@ enum sctp_spp_flags { SPP_SACKDELAY_DISABLE = 1<<6, /*Disable SACK*/ SPP_SACKDELAY = SPP_SACKDELAY_ENABLE | SPP_SACKDELAY_DISABLE, SPP_HB_TIME_IS_ZERO = 1<<7, /* Set HB delay to 0 */ + SPP_IPV6_FLOWLABEL = 1<<8, + SPP_DSCP = 1<<9, }; struct sctp_paddrparams { @@ -773,6 +775,8 @@ struct sctp_paddrparams { __u32 spp_pathmtu; __u32 spp_sackdelay; __u32 spp_flags; + __u32 spp_ipv6_flowlabel; + __u8 spp_dscp; } __attribute__((packed, aligned(4))); /* diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 0e4c8332771a..50b7ef975b42 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2393,6 +2393,8 @@ static int sctp_setsockopt_autoclose(struct sock *sk, char __user *optval, * uint32_t spp_pathmtu; * uint32_t spp_sackdelay; * uint32_t spp_flags; + * uint32_t spp_ipv6_flowlabel; + * uint8_t spp_dscp; * }; * * spp_assoc_id - (one-to-many style socket) This is filled in the @@ -2472,6 +2474,45 @@ static int sctp_setsockopt_autoclose(struct sock *sk, char __user *optval, * also that this field is mutually exclusive to * SPP_SACKDELAY_ENABLE, setting both will have undefined * results. + * + * SPP_IPV6_FLOWLABEL: Setting this flag enables the + * setting of the IPV6 flow label value. The value is + * contained in the spp_ipv6_flowlabel field. + * Upon retrieval, this flag will be set to indicate that + * the spp_ipv6_flowlabel field has a valid value returned. + * If a specific destination address is set (in the + * spp_address field), then the value returned is that of + * the address. If just an association is specified (and + * no address), then the association's default flow label + * is returned. If neither an association nor a destination + * is specified, then the socket's default flow label is + * returned. For non-IPv6 sockets, this flag will be left + * cleared. + * + * SPP_DSCP: Setting this flag enables the setting of the + * Differentiated Services Code Point (DSCP) value + * associated with either the association or a specific + * address. The value is obtained in the spp_dscp field. + * Upon retrieval, this flag will be set to indicate that + * the spp_dscp field has a valid value returned. If a + * specific destination address is set when called (in the + * spp_address field), then that specific destination + * address's DSCP value is returned. If just an association + * is specified, then the association's default DSCP is + * returned. If neither an association nor a destination is + * specified, then the socket's default DSCP is returned. + * + * spp_ipv6_flowlabel + * - This field is used in conjunction with the + * SPP_IPV6_FLOWLABEL flag and contains the IPv6 flow label. + * The 20 least significant bits are used for the flow + * label. This setting has precedence over any IPv6-layer + * setting. + * + * spp_dscp - This field is used in conjunction with the SPP_DSCP flag + * and contains the DSCP. The 6 most significant bits are + * used for the DSCP. This setting has precedence over any + * IPv4- or IPv6- layer setting. */ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params, struct sctp_transport *trans, @@ -2611,6 +2652,51 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params, } } + if (params->spp_flags & SPP_IPV6_FLOWLABEL) { + if (trans && trans->ipaddr.sa.sa_family == AF_INET6) { + trans->flowlabel = params->spp_ipv6_flowlabel & + SCTP_FLOWLABEL_VAL_MASK; + trans->flowlabel |= SCTP_FLOWLABEL_SET_MASK; + } else if (asoc) { + list_for_each_entry(trans, + &asoc->peer.transport_addr_list, + transports) { + if (trans->ipaddr.sa.sa_family != AF_INET6) + continue; + trans->flowlabel = params->spp_ipv6_flowlabel & + SCTP_FLOWLABEL_VAL_MASK; + trans->flowlabel |= SCTP_FLOWLABEL_SET_MASK; + } + asoc->flowlabel = params->spp_ipv6_flowlabel & + SCTP_FLOWLABEL_VAL_MASK; + asoc->flowlabel |= SCTP_FLOWLABEL_SET_MASK; + } else if (sctp_opt2sk(sp)->sk_family == AF_INET6) { + sp->flowlabel = params->spp_ipv6_flowlabel & + SCTP_FLOWLABEL_VAL_MASK; + sp->flowlabel |= SCTP_FLOWLABEL_SET_MASK; + } + } + + if (params->spp_flags & SPP_DSCP) { + if (trans) { + trans->dscp = params->spp_dscp & SCTP_DSCP_VAL_MASK; + trans->dscp |= SCTP_DSCP_SET_MASK; + } else if (asoc) { + list_for_each_entry(trans, + &asoc->peer.transport_addr_list, + transports) { + trans->dscp = params->spp_dscp & + SCTP_DSCP_VAL_MASK; + trans->dscp |= SCTP_DSCP_SET_MASK; + } + asoc->dscp = params->spp_dscp & SCTP_DSCP_VAL_MASK; + asoc->dscp |= SCTP_DSCP_SET_MASK; + } else { + sp->dscp = params->spp_dscp & SCTP_DSCP_VAL_MASK; + sp->dscp |= SCTP_DSCP_SET_MASK; + } + } + return 0; } @@ -2625,11 +2711,18 @@ static int sctp_setsockopt_peer_addr_params(struct sock *sk, int error; int hb_change, pmtud_change, sackdelay_change; - if (optlen != sizeof(struct sctp_paddrparams)) + if (optlen == sizeof(params)) { + if (copy_from_user(¶ms, optval, optlen)) + return -EFAULT; + } else if (optlen == ALIGN(offsetof(struct sctp_paddrparams, + spp_ipv6_flowlabel), 4)) { + if (copy_from_user(¶ms, optval, optlen)) + return -EFAULT; + if (params.spp_flags & (SPP_DSCP | SPP_IPV6_FLOWLABEL)) + return -EINVAL; + } else { return -EINVAL; - - if (copy_from_user(¶ms, optval, optlen)) - return -EFAULT; + } /* Validate flags and value parameters. */ hb_change = params.spp_flags & SPP_HB; @@ -5453,6 +5546,45 @@ out: * also that this field is mutually exclusive to * SPP_SACKDELAY_ENABLE, setting both will have undefined * results. + * + * SPP_IPV6_FLOWLABEL: Setting this flag enables the + * setting of the IPV6 flow label value. The value is + * contained in the spp_ipv6_flowlabel field. + * Upon retrieval, this flag will be set to indicate that + * the spp_ipv6_flowlabel field has a valid value returned. + * If a specific destination address is set (in the + * spp_address field), then the value returned is that of + * the address. If just an association is specified (and + * no address), then the association's default flow label + * is returned. If neither an association nor a destination + * is specified, then the socket's default flow label is + * returned. For non-IPv6 sockets, this flag will be left + * cleared. + * + * SPP_DSCP: Setting this flag enables the setting of the + * Differentiated Services Code Point (DSCP) value + * associated with either the association or a specific + * address. The value is obtained in the spp_dscp field. + * Upon retrieval, this flag will be set to indicate that + * the spp_dscp field has a valid value returned. If a + * specific destination address is set when called (in the + * spp_address field), then that specific destination + * address's DSCP value is returned. If just an association + * is specified, then the association's default DSCP is + * returned. If neither an association nor a destination is + * specified, then the socket's default DSCP is returned. + * + * spp_ipv6_flowlabel + * - This field is used in conjunction with the + * SPP_IPV6_FLOWLABEL flag and contains the IPv6 flow label. + * The 20 least significant bits are used for the flow + * label. This setting has precedence over any IPv6-layer + * setting. + * + * spp_dscp - This field is used in conjunction with the SPP_DSCP flag + * and contains the DSCP. The 6 most significant bits are + * used for the DSCP. This setting has precedence over any + * IPv4- or IPv6- layer setting. */ static int sctp_getsockopt_peer_addr_params(struct sock *sk, int len, char __user *optval, int __user *optlen) @@ -5462,9 +5594,15 @@ static int sctp_getsockopt_peer_addr_params(struct sock *sk, int len, struct sctp_association *asoc = NULL; struct sctp_sock *sp = sctp_sk(sk); - if (len < sizeof(struct sctp_paddrparams)) + if (len >= sizeof(params)) + len = sizeof(params); + else if (len >= ALIGN(offsetof(struct sctp_paddrparams, + spp_ipv6_flowlabel), 4)) + len = ALIGN(offsetof(struct sctp_paddrparams, + spp_ipv6_flowlabel), 4); + else return -EINVAL; - len = sizeof(struct sctp_paddrparams); + if (copy_from_user(¶ms, optval, len)) return -EFAULT; @@ -5499,6 +5637,15 @@ static int sctp_getsockopt_peer_addr_params(struct sock *sk, int len, /*draft-11 doesn't say what to return in spp_flags*/ params.spp_flags = trans->param_flags; + if (trans->flowlabel & SCTP_FLOWLABEL_SET_MASK) { + params.spp_ipv6_flowlabel = trans->flowlabel & + SCTP_FLOWLABEL_VAL_MASK; + params.spp_flags |= SPP_IPV6_FLOWLABEL; + } + if (trans->dscp & SCTP_DSCP_SET_MASK) { + params.spp_dscp = trans->dscp & SCTP_DSCP_VAL_MASK; + params.spp_flags |= SPP_DSCP; + } } else if (asoc) { /* Fetch association values. */ params.spp_hbinterval = jiffies_to_msecs(asoc->hbinterval); @@ -5508,6 +5655,15 @@ static int sctp_getsockopt_peer_addr_params(struct sock *sk, int len, /*draft-11 doesn't say what to return in spp_flags*/ params.spp_flags = asoc->param_flags; + if (asoc->flowlabel & SCTP_FLOWLABEL_SET_MASK) { + params.spp_ipv6_flowlabel = asoc->flowlabel & + SCTP_FLOWLABEL_VAL_MASK; + params.spp_flags |= SPP_IPV6_FLOWLABEL; + } + if (asoc->dscp & SCTP_DSCP_SET_MASK) { + params.spp_dscp = asoc->dscp & SCTP_DSCP_VAL_MASK; + params.spp_flags |= SPP_DSCP; + } } else { /* Fetch socket values. */ params.spp_hbinterval = sp->hbinterval; @@ -5517,6 +5673,15 @@ static int sctp_getsockopt_peer_addr_params(struct sock *sk, int len, /*draft-11 doesn't say what to return in spp_flags*/ params.spp_flags = sp->param_flags; + if (sp->flowlabel & SCTP_FLOWLABEL_SET_MASK) { + params.spp_ipv6_flowlabel = sp->flowlabel & + SCTP_FLOWLABEL_VAL_MASK; + params.spp_flags |= SPP_IPV6_FLOWLABEL; + } + if (sp->dscp & SCTP_DSCP_SET_MASK) { + params.spp_dscp = sp->dscp & SCTP_DSCP_VAL_MASK; + params.spp_flags |= SPP_DSCP; + } } if (copy_to_user(optval, ¶ms, len)) -- cgit v1.2.3 From f6ad8c1bcdf014272d08c55b9469536952a0a771 Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Mon, 2 Jul 2018 16:12:45 +0100 Subject: net: core: trivial netif_receive_skb_list() entry point Just calls netif_receive_skb() in a loop. Signed-off-by: Edward Cree Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + net/core/dev.c | 19 +++++++++++++++++++ 2 files changed, 20 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 64480a0f2c16..f67258f057ca 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3477,6 +3477,7 @@ int netif_rx(struct sk_buff *skb); int netif_rx_ni(struct sk_buff *skb); int netif_receive_skb(struct sk_buff *skb); int netif_receive_skb_core(struct sk_buff *skb); +void netif_receive_skb_list(struct list_head *head); gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb); void napi_gro_flush(struct napi_struct *napi, bool flush_old); struct sk_buff *napi_get_frags(struct napi_struct *napi); diff --git a/net/core/dev.c b/net/core/dev.c index 08d58e0debe5..85c456a4b551 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4906,6 +4906,25 @@ int netif_receive_skb(struct sk_buff *skb) } EXPORT_SYMBOL(netif_receive_skb); +/** + * netif_receive_skb_list - process many receive buffers from network + * @head: list of skbs to process. + * + * For now, just calls netif_receive_skb() in a loop, ignoring the + * return value. + * + * This function may only be called from softirq context and interrupts + * should be enabled. + */ +void netif_receive_skb_list(struct list_head *head) +{ + struct sk_buff *skb, *next; + + list_for_each_entry_safe(skb, next, head, list) + netif_receive_skb(skb); +} +EXPORT_SYMBOL(netif_receive_skb_list); + DEFINE_PER_CPU(struct work_struct, flush_works); /* Network device is going away, flush any packets still pending */ -- cgit v1.2.3 From 920572b73280a29e3a9f58807a8b90051b19ee60 Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Mon, 2 Jul 2018 16:13:11 +0100 Subject: net: core: unwrap skb list receive slightly further Signed-off-by: Edward Cree Signed-off-by: David S. Miller --- include/trace/events/net.h | 7 +++++++ net/core/dev.c | 4 +++- 2 files changed, 10 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/net.h b/include/trace/events/net.h index 9c886739246a..00aa72ce0e7c 100644 --- a/include/trace/events/net.h +++ b/include/trace/events/net.h @@ -223,6 +223,13 @@ DEFINE_EVENT(net_dev_rx_verbose_template, netif_receive_skb_entry, TP_ARGS(skb) ); +DEFINE_EVENT(net_dev_rx_verbose_template, netif_receive_skb_list_entry, + + TP_PROTO(const struct sk_buff *skb), + + TP_ARGS(skb) +); + DEFINE_EVENT(net_dev_rx_verbose_template, netif_rx_entry, TP_PROTO(const struct sk_buff *skb), diff --git a/net/core/dev.c b/net/core/dev.c index 85c456a4b551..308acfd48139 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4920,8 +4920,10 @@ void netif_receive_skb_list(struct list_head *head) { struct sk_buff *skb, *next; + list_for_each_entry(skb, head, list) + trace_netif_receive_skb_list_entry(skb); list_for_each_entry_safe(skb, next, head, list) - netif_receive_skb(skb); + netif_receive_skb_internal(skb); } EXPORT_SYMBOL(netif_receive_skb_list); -- cgit v1.2.3 From 4ce0017a373afaaa9ef17614d8fa4f6fde261d18 Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Mon, 2 Jul 2018 16:13:40 +0100 Subject: net: core: another layer of lists, around PF_MEMALLOC skb handling First example of a layer splitting the list (rather than merely taking individual packets off it). Involves new list.h function, list_cut_before(), like list_cut_position() but cuts on the other side of the given entry. Signed-off-by: Edward Cree Signed-off-by: David S. Miller --- include/linux/list.h | 30 ++++++++++++++++++++++++++++++ net/core/dev.c | 44 ++++++++++++++++++++++++++++++++++++-------- 2 files changed, 66 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/list.h b/include/linux/list.h index 4b129df4d46b..de04cc5ed536 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -285,6 +285,36 @@ static inline void list_cut_position(struct list_head *list, __list_cut_position(list, head, entry); } +/** + * list_cut_before - cut a list into two, before given entry + * @list: a new list to add all removed entries + * @head: a list with entries + * @entry: an entry within head, could be the head itself + * + * This helper moves the initial part of @head, up to but + * excluding @entry, from @head to @list. You should pass + * in @entry an element you know is on @head. @list should + * be an empty list or a list you do not care about losing + * its data. + * If @entry == @head, all entries on @head are moved to + * @list. + */ +static inline void list_cut_before(struct list_head *list, + struct list_head *head, + struct list_head *entry) +{ + if (head->next == entry) { + INIT_LIST_HEAD(list); + return; + } + list->next = head->next; + list->next->prev = list; + list->prev = entry->prev; + list->prev->next = list; + head->next = entry; + entry->prev = head; +} + static inline void __list_splice(const struct list_head *list, struct list_head *prev, struct list_head *next) diff --git a/net/core/dev.c b/net/core/dev.c index 1e87361df2ab..9aadef976e8c 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4784,6 +4784,14 @@ int netif_receive_skb_core(struct sk_buff *skb) } EXPORT_SYMBOL(netif_receive_skb_core); +static void __netif_receive_skb_list_core(struct list_head *head, bool pfmemalloc) +{ + struct sk_buff *skb, *next; + + list_for_each_entry_safe(skb, next, head, list) + __netif_receive_skb_core(skb, pfmemalloc); +} + static int __netif_receive_skb(struct sk_buff *skb) { int ret; @@ -4809,6 +4817,34 @@ static int __netif_receive_skb(struct sk_buff *skb) return ret; } +static void __netif_receive_skb_list(struct list_head *head) +{ + unsigned long noreclaim_flag = 0; + struct sk_buff *skb, *next; + bool pfmemalloc = false; /* Is current sublist PF_MEMALLOC? */ + + list_for_each_entry_safe(skb, next, head, list) { + if ((sk_memalloc_socks() && skb_pfmemalloc(skb)) != pfmemalloc) { + struct list_head sublist; + + /* Handle the previous sublist */ + list_cut_before(&sublist, head, &skb->list); + __netif_receive_skb_list_core(&sublist, pfmemalloc); + pfmemalloc = !pfmemalloc; + /* See comments in __netif_receive_skb */ + if (pfmemalloc) + noreclaim_flag = memalloc_noreclaim_save(); + else + memalloc_noreclaim_restore(noreclaim_flag); + } + } + /* Handle the remaining sublist */ + __netif_receive_skb_list_core(head, pfmemalloc); + /* Restore pflags */ + if (pfmemalloc) + memalloc_noreclaim_restore(noreclaim_flag); +} + static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp) { struct bpf_prog *old = rtnl_dereference(dev->xdp_prog); @@ -4843,14 +4879,6 @@ static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp) return ret; } -static void __netif_receive_skb_list(struct list_head *head) -{ - struct sk_buff *skb, *next; - - list_for_each_entry_safe(skb, next, head, list) - __netif_receive_skb(skb); -} - static int netif_receive_skb_internal(struct sk_buff *skb) { int ret; -- cgit v1.2.3 From 17266ee939849cb095ed7dd9edbec4162172226b Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Mon, 2 Jul 2018 16:14:12 +0100 Subject: net: ipv4: listified version of ip_rcv Also involved adding a way to run a netfilter hook over a list of packets. Rather than attempting to make netfilter know about lists (which would be a major project in itself) we just let it call the regular okfn (in this case ip_rcv_finish()) for any packets it steals, and have it give us back a list of packets it's synchronously accepted (which normally NF_HOOK would automatically call okfn() on, but we want to be able to potentially pass the list to a listified version of okfn().) The netfilter hooks themselves are indirect calls that still happen per- packet (see nf_hook_entry_hookfn()), but again, changing that can be left for future work. There is potential for out-of-order receives if the netfilter hook ends up synchronously stealing packets, as they will be processed before any accepts earlier in the list. However, it was already possible for an asynchronous accept to cause out-of-order receives, so presumably this is considered OK. Signed-off-by: Edward Cree Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +++ include/linux/netfilter.h | 22 +++++++++++++++ include/net/ip.h | 2 ++ net/core/dev.c | 8 +++--- net/ipv4/af_inet.c | 1 + net/ipv4/ip_input.c | 68 ++++++++++++++++++++++++++++++++++++++++++----- 6 files changed, 94 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f67258f057ca..c1ef749b6f9f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2297,6 +2297,9 @@ struct packet_type { struct net_device *, struct packet_type *, struct net_device *); + void (*list_func) (struct list_head *, + struct packet_type *, + struct net_device *); bool (*id_match)(struct packet_type *ptype, struct sock *sk); void *af_packet_priv; diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index dd2052f0efb7..5a5e0a2ab2a3 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -288,6 +288,20 @@ NF_HOOK(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct return ret; } +static inline void +NF_HOOK_LIST(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, + struct list_head *head, struct net_device *in, struct net_device *out, + int (*okfn)(struct net *, struct sock *, struct sk_buff *)) +{ + struct sk_buff *skb, *next; + + list_for_each_entry_safe(skb, next, head, list) { + int ret = nf_hook(pf, hook, net, sk, skb, in, out, okfn); + if (ret != 1) + list_del(&skb->list); + } +} + /* Call setsockopt() */ int nf_setsockopt(struct sock *sk, u_int8_t pf, int optval, char __user *opt, unsigned int len); @@ -369,6 +383,14 @@ NF_HOOK(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, return okfn(net, sk, skb); } +static inline void +NF_HOOK_LIST(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, + struct list_head *head, struct net_device *in, struct net_device *out, + int (*okfn)(struct net *, struct sock *, struct sk_buff *)) +{ + /* nothing to do */ +} + static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *indev, struct net_device *outdev, diff --git a/include/net/ip.h b/include/net/ip.h index 09da79d8ceea..99d1b835d2aa 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -138,6 +138,8 @@ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, struct ip_options_rcu *opt); int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); +void ip_list_rcv(struct list_head *head, struct packet_type *pt, + struct net_device *orig_dev); int ip_local_deliver(struct sk_buff *skb); int ip_mr_input(struct sk_buff *skb); int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb); diff --git a/net/core/dev.c b/net/core/dev.c index 1bc485bb0678..5e22719ce71d 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4806,9 +4806,11 @@ static inline void __netif_receive_skb_list_ptype(struct list_head *head, return; if (list_empty(head)) return; - - list_for_each_entry_safe(skb, next, head, list) - pt_prev->func(skb, skb->dev, pt_prev, orig_dev); + if (pt_prev->list_func != NULL) + pt_prev->list_func(head, pt_prev, orig_dev); + else + list_for_each_entry_safe(skb, next, head, list) + pt_prev->func(skb, skb->dev, pt_prev, orig_dev); } static void __netif_receive_skb_list_core(struct list_head *head, bool pfmemalloc) diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 9263a2c114e0..c716be13d58c 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1882,6 +1882,7 @@ fs_initcall(ipv4_offload_init); static struct packet_type ip_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_IP), .func = ip_rcv, + .list_func = ip_list_rcv, }; static int __init inet_init(void) diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 7582713dd18f..914240830bdf 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -408,10 +408,9 @@ drop_error: /* * Main IP Receive routine. */ -int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) +static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net) { const struct iphdr *iph; - struct net *net; u32 len; /* When the interface is in promisc. mode, drop all the crap @@ -421,7 +420,6 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, goto drop; - net = dev_net(dev); __IP_UPD_PO_STATS(net, IPSTATS_MIB_IN, skb->len); skb = skb_share_check(skb, GFP_ATOMIC); @@ -489,9 +487,7 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, /* Must drop socket now because of tproxy. */ skb_orphan(skb); - return NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, - net, NULL, skb, dev, NULL, - ip_rcv_finish); + return skb; csum_error: __IP_INC_STATS(net, IPSTATS_MIB_CSUMERRORS); @@ -500,5 +496,63 @@ inhdr_error: drop: kfree_skb(skb); out: - return NET_RX_DROP; + return NULL; +} + +/* + * IP receive entry point + */ +int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, + struct net_device *orig_dev) +{ + struct net *net = dev_net(dev); + + skb = ip_rcv_core(skb, net); + if (skb == NULL) + return NET_RX_DROP; + return NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, + net, NULL, skb, dev, NULL, + ip_rcv_finish); +} + +static void ip_sublist_rcv(struct list_head *head, struct net_device *dev, + struct net *net) +{ + struct sk_buff *skb, *next; + + NF_HOOK_LIST(NFPROTO_IPV4, NF_INET_PRE_ROUTING, net, NULL, + head, dev, NULL, ip_rcv_finish); + list_for_each_entry_safe(skb, next, head, list) + ip_rcv_finish(net, NULL, skb); +} + +/* Receive a list of IP packets */ +void ip_list_rcv(struct list_head *head, struct packet_type *pt, + struct net_device *orig_dev) +{ + struct net_device *curr_dev = NULL; + struct net *curr_net = NULL; + struct sk_buff *skb, *next; + struct list_head sublist; + + list_for_each_entry_safe(skb, next, head, list) { + struct net_device *dev = skb->dev; + struct net *net = dev_net(dev); + + skb = ip_rcv_core(skb, net); + if (skb == NULL) + continue; + + if (curr_dev != dev || curr_net != net) { + /* dispatch old sublist */ + list_cut_before(&sublist, head, &skb->list); + if (!list_empty(&sublist)) + ip_sublist_rcv(&sublist, dev, net); + /* start new sublist */ + curr_dev = dev; + curr_net = net; + } + } + /* dispatch final sublist */ + ip_sublist_rcv(head, curr_dev, curr_net); } -- cgit v1.2.3 From 421860b9d47053badce4b247576fa48df9ab4c48 Mon Sep 17 00:00:00 2001 From: Steve Longerbeam Date: Wed, 27 Jun 2018 14:39:43 -0400 Subject: media: v4l2-ctrls: Fix CID base conflict between MAX217X and IMX When the imx-media driver was initially merged, there was a conflict with 8d67ae25 ("media: v4l2-ctrls: Reserve controls for MAX217X") which was not fixed up correctly, resulting in V4L2_CID_USER_MAX217X_BASE and V4L2_CID_USER_IMX_BASE taking on the same value. Fix by assigning imx CID base the next available range at 0x10b0. Signed-off-by: Steve Longerbeam Acked-by: Sakari Ailus Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/v4l2-controls.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index 8d473c979b61..8a75ad7899f3 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -188,7 +188,7 @@ enum v4l2_colorfx { /* The base for the imx driver controls. * We reserve 16 controls for this driver. */ -#define V4L2_CID_USER_IMX_BASE (V4L2_CID_USER_BASE + 0x1090) +#define V4L2_CID_USER_IMX_BASE (V4L2_CID_USER_BASE + 0x10b0) /* MPEG-class control IDs */ /* The MPEG controls are applicable to all codec controls -- cgit v1.2.3 From e7e3728bd776d1d1450212ad266832f1003f833f Mon Sep 17 00:00:00 2001 From: Qiaobin Fu Date: Sun, 1 Jul 2018 15:16:27 -0400 Subject: net:sched: add action inheritdsfield to skbedit The new action inheritdsfield copies the field DS of IPv4 and IPv6 packets into skb->priority. This enables later classification of packets based on the DS field. v5: *Update the drop counter for TC_ACT_SHOT v4: *Not allow setting flags other than the expected ones. *Allow dumping the pure flags. v3: *Use optional flags, so that it won't break old versions of tc. *Allow users to set both SKBEDIT_F_PRIORITY and SKBEDIT_F_INHERITDSFIELD flags. v2: *Fix the style issue *Move the code from skbmod to skbedit Original idea by Jamal Hadi Salim Signed-off-by: Qiaobin Fu Reviewed-by: Michel Machado Acked-by: Jamal Hadi Salim Reviewed-by: Marcelo Ricardo Leitner Acked-by: Davide Caratti Signed-off-by: David S. Miller --- include/uapi/linux/tc_act/tc_skbedit.h | 2 ++ net/sched/act_skbedit.c | 41 ++++++++++++++++++++++++++++++++++ 2 files changed, 43 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/tc_act/tc_skbedit.h b/include/uapi/linux/tc_act/tc_skbedit.h index fbcfe27a4e6c..6de6071ebed6 100644 --- a/include/uapi/linux/tc_act/tc_skbedit.h +++ b/include/uapi/linux/tc_act/tc_skbedit.h @@ -30,6 +30,7 @@ #define SKBEDIT_F_MARK 0x4 #define SKBEDIT_F_PTYPE 0x8 #define SKBEDIT_F_MASK 0x10 +#define SKBEDIT_F_INHERITDSFIELD 0x20 struct tc_skbedit { tc_gen; @@ -45,6 +46,7 @@ enum { TCA_SKBEDIT_PAD, TCA_SKBEDIT_PTYPE, TCA_SKBEDIT_MASK, + TCA_SKBEDIT_FLAGS, __TCA_SKBEDIT_MAX }; #define TCA_SKBEDIT_MAX (__TCA_SKBEDIT_MAX - 1) diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 6138d1d71900..dfaf5d8028dd 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -23,6 +23,9 @@ #include #include #include +#include +#include +#include #include #include @@ -41,6 +44,25 @@ static int tcf_skbedit(struct sk_buff *skb, const struct tc_action *a, if (d->flags & SKBEDIT_F_PRIORITY) skb->priority = d->priority; + if (d->flags & SKBEDIT_F_INHERITDSFIELD) { + int wlen = skb_network_offset(skb); + + switch (tc_skb_protocol(skb)) { + case htons(ETH_P_IP): + wlen += sizeof(struct iphdr); + if (!pskb_may_pull(skb, wlen)) + goto err; + skb->priority = ipv4_get_dsfield(ip_hdr(skb)) >> 2; + break; + + case htons(ETH_P_IPV6): + wlen += sizeof(struct ipv6hdr); + if (!pskb_may_pull(skb, wlen)) + goto err; + skb->priority = ipv6_get_dsfield(ipv6_hdr(skb)) >> 2; + break; + } + } if (d->flags & SKBEDIT_F_QUEUE_MAPPING && skb->dev->real_num_tx_queues > d->queue_mapping) skb_set_queue_mapping(skb, d->queue_mapping); @@ -53,6 +75,11 @@ static int tcf_skbedit(struct sk_buff *skb, const struct tc_action *a, spin_unlock(&d->tcf_lock); return d->tcf_action; + +err: + d->tcf_qstats.drops++; + spin_unlock(&d->tcf_lock); + return TC_ACT_SHOT; } static const struct nla_policy skbedit_policy[TCA_SKBEDIT_MAX + 1] = { @@ -62,6 +89,7 @@ static const struct nla_policy skbedit_policy[TCA_SKBEDIT_MAX + 1] = { [TCA_SKBEDIT_MARK] = { .len = sizeof(u32) }, [TCA_SKBEDIT_PTYPE] = { .len = sizeof(u16) }, [TCA_SKBEDIT_MASK] = { .len = sizeof(u32) }, + [TCA_SKBEDIT_FLAGS] = { .len = sizeof(u64) }, }; static int tcf_skbedit_init(struct net *net, struct nlattr *nla, @@ -114,6 +142,13 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, mask = nla_data(tb[TCA_SKBEDIT_MASK]); } + if (tb[TCA_SKBEDIT_FLAGS] != NULL) { + u64 *pure_flags = nla_data(tb[TCA_SKBEDIT_FLAGS]); + + if (*pure_flags & SKBEDIT_F_INHERITDSFIELD) + flags |= SKBEDIT_F_INHERITDSFIELD; + } + parm = nla_data(tb[TCA_SKBEDIT_PARMS]); exists = tcf_idr_check(tn, parm->index, a, bind); @@ -178,6 +213,7 @@ static int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a, .action = d->tcf_action, }; struct tcf_t t; + u64 pure_flags = 0; if (nla_put(skb, TCA_SKBEDIT_PARMS, sizeof(opt), &opt)) goto nla_put_failure; @@ -196,6 +232,11 @@ static int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a, if ((d->flags & SKBEDIT_F_MASK) && nla_put_u32(skb, TCA_SKBEDIT_MASK, d->mask)) goto nla_put_failure; + if (d->flags & SKBEDIT_F_INHERITDSFIELD) + pure_flags |= SKBEDIT_F_INHERITDSFIELD; + if (pure_flags != 0 && + nla_put(skb, TCA_SKBEDIT_FLAGS, sizeof(pure_flags), &pure_flags)) + goto nla_put_failure; tcf_tm_dump(&t, &d->tcf_tm); if (nla_put_64bit(skb, TCA_SKBEDIT_TM, sizeof(t), &t, TCA_SKBEDIT_PAD)) -- cgit v1.2.3 From be2fff656322e82f215730839063c2c2ca73d14b Mon Sep 17 00:00:00 2001 From: Ezequiel Garcia Date: Mon, 2 Jul 2018 11:36:05 -0400 Subject: media: add helpers for memory-to-memory media controller A memory-to-memory pipeline device consists in three entities: two DMA engine and one video processing entities. The DMA engine entities are linked to a V4L interface. This commit add a new v4l2_m2m_{un}register_media_controller API to register this topology. For instance, a typical mem2mem device topology would look like this: Device topology - entity 1: source (1 pad, 1 link) type Node subtype V4L flags 0 pad0: Source -> "proc":1 [ENABLED,IMMUTABLE] - entity 3: proc (2 pads, 2 links) type Node subtype Unknown flags 0 pad0: Source -> "sink":0 [ENABLED,IMMUTABLE] pad1: Sink <- "source":0 [ENABLED,IMMUTABLE] - entity 6: sink (1 pad, 1 link) type Node subtype V4L flags 0 pad0: Sink <- "proc":0 [ENABLED,IMMUTABLE] [hans.verkuil@cisco.com: mark interface links as IMMUTABLE] Suggested-by: Laurent Pinchart Signed-off-by: Ezequiel Garcia Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/media/v4l2-core/v4l2-dev.c | 13 ++- drivers/media/v4l2-core/v4l2-mem2mem.c | 190 +++++++++++++++++++++++++++++++++ include/media/v4l2-mem2mem.h | 19 ++++ 3 files changed, 217 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/media/v4l2-core/v4l2-dev.c b/drivers/media/v4l2-core/v4l2-dev.c index 5f43f63fa700..69e775930fc4 100644 --- a/drivers/media/v4l2-core/v4l2-dev.c +++ b/drivers/media/v4l2-core/v4l2-dev.c @@ -202,7 +202,7 @@ static void v4l2_device_release(struct device *cd) mutex_unlock(&videodev_lock); #if defined(CONFIG_MEDIA_CONTROLLER) - if (v4l2_dev->mdev) { + if (v4l2_dev->mdev && vdev->vfl_dir != VFL_DIR_M2M) { /* Remove interfaces and interface links */ media_devnode_remove(vdev->intf_devnode); if (vdev->entity.function != MEDIA_ENT_F_UNKNOWN) @@ -733,19 +733,22 @@ static void determine_valid_ioctls(struct video_device *vdev) BASE_VIDIOC_PRIVATE); } -static int video_register_media_controller(struct video_device *vdev, int type) +static int video_register_media_controller(struct video_device *vdev) { #if defined(CONFIG_MEDIA_CONTROLLER) u32 intf_type; int ret; - if (!vdev->v4l2_dev->mdev) + /* Memory-to-memory devices are more complex and use + * their own function to register its mc entities. + */ + if (!vdev->v4l2_dev->mdev || vdev->vfl_dir == VFL_DIR_M2M) return 0; vdev->entity.obj_type = MEDIA_ENTITY_TYPE_VIDEO_DEVICE; vdev->entity.function = MEDIA_ENT_F_UNKNOWN; - switch (type) { + switch (vdev->vfl_type) { case VFL_TYPE_GRABBER: intf_type = MEDIA_INTF_T_V4L_VIDEO; vdev->entity.function = MEDIA_ENT_F_IO_V4L; @@ -994,7 +997,7 @@ int __video_register_device(struct video_device *vdev, v4l2_device_get(vdev->v4l2_dev); /* Part 5: Register the entity. */ - ret = video_register_media_controller(vdev, type); + ret = video_register_media_controller(vdev); /* Part 6: Activate this minor. The char device can now be used. */ set_bit(V4L2_FL_REGISTERED, &vdev->flags); diff --git a/drivers/media/v4l2-core/v4l2-mem2mem.c b/drivers/media/v4l2-core/v4l2-mem2mem.c index 5f9cd5b74cda..725da74d15d8 100644 --- a/drivers/media/v4l2-core/v4l2-mem2mem.c +++ b/drivers/media/v4l2-core/v4l2-mem2mem.c @@ -17,9 +17,11 @@ #include #include +#include #include #include #include +#include #include #include @@ -50,6 +52,17 @@ module_param(debug, bool, 0644); * offsets but for different queues */ #define DST_QUEUE_OFF_BASE (1 << 30) +enum v4l2_m2m_entity_type { + MEM2MEM_ENT_TYPE_SOURCE, + MEM2MEM_ENT_TYPE_SINK, + MEM2MEM_ENT_TYPE_PROC +}; + +static const char * const m2m_entity_name[] = { + "source", + "sink", + "proc" +}; /** * struct v4l2_m2m_dev - per-device context @@ -60,6 +73,15 @@ module_param(debug, bool, 0644); */ struct v4l2_m2m_dev { struct v4l2_m2m_ctx *curr_ctx; +#ifdef CONFIG_MEDIA_CONTROLLER + struct media_entity *source; + struct media_pad source_pad; + struct media_entity sink; + struct media_pad sink_pad; + struct media_entity proc; + struct media_pad proc_pads[2]; + struct media_intf_devnode *intf_devnode; +#endif struct list_head job_queue; spinlock_t job_spinlock; @@ -594,6 +616,174 @@ int v4l2_m2m_mmap(struct file *file, struct v4l2_m2m_ctx *m2m_ctx, } EXPORT_SYMBOL(v4l2_m2m_mmap); +#if defined(CONFIG_MEDIA_CONTROLLER) +void v4l2_m2m_unregister_media_controller(struct v4l2_m2m_dev *m2m_dev) +{ + media_remove_intf_links(&m2m_dev->intf_devnode->intf); + media_devnode_remove(m2m_dev->intf_devnode); + + media_entity_remove_links(m2m_dev->source); + media_entity_remove_links(&m2m_dev->sink); + media_entity_remove_links(&m2m_dev->proc); + media_device_unregister_entity(m2m_dev->source); + media_device_unregister_entity(&m2m_dev->sink); + media_device_unregister_entity(&m2m_dev->proc); + kfree(m2m_dev->source->name); + kfree(m2m_dev->sink.name); + kfree(m2m_dev->proc.name); +} +EXPORT_SYMBOL_GPL(v4l2_m2m_unregister_media_controller); + +static int v4l2_m2m_register_entity(struct media_device *mdev, + struct v4l2_m2m_dev *m2m_dev, enum v4l2_m2m_entity_type type, + struct video_device *vdev, int function) +{ + struct media_entity *entity; + struct media_pad *pads; + char *name; + unsigned int len; + int num_pads; + int ret; + + switch (type) { + case MEM2MEM_ENT_TYPE_SOURCE: + entity = m2m_dev->source; + pads = &m2m_dev->source_pad; + pads[0].flags = MEDIA_PAD_FL_SOURCE; + num_pads = 1; + break; + case MEM2MEM_ENT_TYPE_SINK: + entity = &m2m_dev->sink; + pads = &m2m_dev->sink_pad; + pads[0].flags = MEDIA_PAD_FL_SINK; + num_pads = 1; + break; + case MEM2MEM_ENT_TYPE_PROC: + entity = &m2m_dev->proc; + pads = m2m_dev->proc_pads; + pads[0].flags = MEDIA_PAD_FL_SINK; + pads[1].flags = MEDIA_PAD_FL_SOURCE; + num_pads = 2; + break; + default: + return -EINVAL; + } + + entity->obj_type = MEDIA_ENTITY_TYPE_BASE; + if (type != MEM2MEM_ENT_TYPE_PROC) { + entity->info.dev.major = VIDEO_MAJOR; + entity->info.dev.minor = vdev->minor; + } + len = strlen(vdev->name) + 2 + strlen(m2m_entity_name[type]); + name = kmalloc(len, GFP_KERNEL); + if (!name) + return -ENOMEM; + snprintf(name, len, "%s-%s", vdev->name, m2m_entity_name[type]); + entity->name = name; + entity->function = function; + + ret = media_entity_pads_init(entity, num_pads, pads); + if (ret) + return ret; + ret = media_device_register_entity(mdev, entity); + if (ret) + return ret; + + return 0; +} + +int v4l2_m2m_register_media_controller(struct v4l2_m2m_dev *m2m_dev, + struct video_device *vdev, int function) +{ + struct media_device *mdev = vdev->v4l2_dev->mdev; + struct media_link *link; + int ret; + + if (!mdev) + return 0; + + /* A memory-to-memory device consists in two + * DMA engine and one video processing entities. + * The DMA engine entities are linked to a V4L interface + */ + + /* Create the three entities with their pads */ + m2m_dev->source = &vdev->entity; + ret = v4l2_m2m_register_entity(mdev, m2m_dev, + MEM2MEM_ENT_TYPE_SOURCE, vdev, MEDIA_ENT_F_IO_V4L); + if (ret) + return ret; + ret = v4l2_m2m_register_entity(mdev, m2m_dev, + MEM2MEM_ENT_TYPE_PROC, vdev, function); + if (ret) + goto err_rel_entity0; + ret = v4l2_m2m_register_entity(mdev, m2m_dev, + MEM2MEM_ENT_TYPE_SINK, vdev, MEDIA_ENT_F_IO_V4L); + if (ret) + goto err_rel_entity1; + + /* Connect the three entities */ + ret = media_create_pad_link(m2m_dev->source, 0, &m2m_dev->proc, 1, + MEDIA_LNK_FL_IMMUTABLE | MEDIA_LNK_FL_ENABLED); + if (ret) + goto err_rel_entity2; + + ret = media_create_pad_link(&m2m_dev->proc, 0, &m2m_dev->sink, 0, + MEDIA_LNK_FL_IMMUTABLE | MEDIA_LNK_FL_ENABLED); + if (ret) + goto err_rm_links0; + + /* Create video interface */ + m2m_dev->intf_devnode = media_devnode_create(mdev, + MEDIA_INTF_T_V4L_VIDEO, 0, + VIDEO_MAJOR, vdev->minor); + if (!m2m_dev->intf_devnode) { + ret = -ENOMEM; + goto err_rm_links1; + } + + /* Connect the two DMA engines to the interface */ + link = media_create_intf_link(m2m_dev->source, + &m2m_dev->intf_devnode->intf, + MEDIA_LNK_FL_IMMUTABLE | MEDIA_LNK_FL_ENABLED); + if (!link) { + ret = -ENOMEM; + goto err_rm_devnode; + } + + link = media_create_intf_link(&m2m_dev->sink, + &m2m_dev->intf_devnode->intf, + MEDIA_LNK_FL_IMMUTABLE | MEDIA_LNK_FL_ENABLED); + if (!link) { + ret = -ENOMEM; + goto err_rm_intf_link; + } + return 0; + +err_rm_intf_link: + media_remove_intf_links(&m2m_dev->intf_devnode->intf); +err_rm_devnode: + media_devnode_remove(m2m_dev->intf_devnode); +err_rm_links1: + media_entity_remove_links(&m2m_dev->sink); +err_rm_links0: + media_entity_remove_links(&m2m_dev->proc); + media_entity_remove_links(m2m_dev->source); +err_rel_entity2: + media_device_unregister_entity(&m2m_dev->proc); + kfree(m2m_dev->proc.name); +err_rel_entity1: + media_device_unregister_entity(&m2m_dev->sink); + kfree(m2m_dev->sink.name); +err_rel_entity0: + media_device_unregister_entity(m2m_dev->source); + kfree(m2m_dev->source->name); + return ret; + return 0; +} +EXPORT_SYMBOL_GPL(v4l2_m2m_register_media_controller); +#endif + struct v4l2_m2m_dev *v4l2_m2m_init(const struct v4l2_m2m_ops *m2m_ops) { struct v4l2_m2m_dev *m2m_dev; diff --git a/include/media/v4l2-mem2mem.h b/include/media/v4l2-mem2mem.h index 8f4b208cfee7..af48b1eca025 100644 --- a/include/media/v4l2-mem2mem.h +++ b/include/media/v4l2-mem2mem.h @@ -47,6 +47,7 @@ struct v4l2_m2m_ops { void (*job_abort)(void *priv); }; +struct video_device; struct v4l2_m2m_dev; /** @@ -322,6 +323,24 @@ int v4l2_m2m_mmap(struct file *file, struct v4l2_m2m_ctx *m2m_ctx, */ struct v4l2_m2m_dev *v4l2_m2m_init(const struct v4l2_m2m_ops *m2m_ops); +#if defined(CONFIG_MEDIA_CONTROLLER) +void v4l2_m2m_unregister_media_controller(struct v4l2_m2m_dev *m2m_dev); +int v4l2_m2m_register_media_controller(struct v4l2_m2m_dev *m2m_dev, + struct video_device *vdev, int function); +#else +static inline void +v4l2_m2m_unregister_media_controller(struct v4l2_m2m_dev *m2m_dev) +{ +} + +static inline int +v4l2_m2m_register_media_controller(struct v4l2_m2m_dev *m2m_dev, + struct video_device *vdev, int function) +{ + return 0; +} +#endif + /** * v4l2_m2m_release() - cleans up and frees a m2m_dev structure * -- cgit v1.2.3 From 5520b9467a39d5ec9ce9cd8a9ed01f826b817524 Mon Sep 17 00:00:00 2001 From: Keiichi Watanabe Date: Mon, 18 Jun 2018 03:58:52 -0400 Subject: media: v4l2-ctrl: Change control for VP8 profile to menu control Add a menu control V4L2_CID_MPEG_VIDEO_VP8_PROFILE for VP8 profile and make V4L2_CID_MPEG_VIDEO_VPX_PROFILE an alias of it. This new control is used to select the desired profile for VP8 encoder and query for supported profiles by VP8 encoder/decoder. Though we have originally a control V4L2_CID_MPEG_VIDEO_VPX_PROFILE and its name contains 'VPX', it works only for VP8 because supported profiles usually differ between VP8 and VP9. In addition, this control cannot be used for querying since it is not a menu control but an integer control, which cannot return an arbitrary set of supported profiles. The new control V4L2_CID_MPEG_VIDEO_VP8_PROFILE is a menu control as with controls for other codec profiles. (e.g. H264) In addition, this patch also fixes the use of V4L2_CID_MPEG_VIDEO_VPX_PROFILE in drivers of Qualcomm's venus and Samsung's s5p-mfc. Signed-off-by: Keiichi Watanabe Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- Documentation/media/uapi/v4l/extended-controls.rst | 25 +++++++++++++++++++--- drivers/media/platform/qcom/venus/vdec_ctrls.c | 10 +++++---- drivers/media/platform/qcom/venus/venc.c | 4 ++-- drivers/media/platform/qcom/venus/venc_ctrls.c | 10 +++++---- drivers/media/platform/s5p-mfc/s5p_mfc_enc.c | 15 ++++++------- drivers/media/v4l2-core/v4l2-ctrls.c | 12 ++++++++++- include/uapi/linux/v4l2-controls.h | 11 +++++++++- 7 files changed, 64 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/Documentation/media/uapi/v4l/extended-controls.rst b/Documentation/media/uapi/v4l/extended-controls.rst index 03931f9b1285..01ef31a934b4 100644 --- a/Documentation/media/uapi/v4l/extended-controls.rst +++ b/Documentation/media/uapi/v4l/extended-controls.rst @@ -1955,9 +1955,28 @@ enum v4l2_vp8_golden_frame_sel - ``V4L2_CID_MPEG_VIDEO_VPX_P_FRAME_QP (integer)`` Quantization parameter for a P frame for VP8. -``V4L2_CID_MPEG_VIDEO_VPX_PROFILE (integer)`` - Select the desired profile for VPx encoder. Acceptable values are 0, - 1, 2 and 3 corresponding to encoder profiles 0, 1, 2 and 3. +.. _v4l2-mpeg-video-vp8-profile: + +``V4L2_CID_MPEG_VIDEO_VP8_PROFILE`` + (enum) + +enum v4l2_mpeg_video_vp8_profile - + This control allows selecting the profile for VP8 encoder. + This is also used to enumerate supported profiles by VP8 encoder or decoder. + Possible values are: + +.. flat-table:: + :header-rows: 0 + :stub-columns: 0 + + * - ``V4L2_MPEG_VIDEO_VP8_PROFILE_0`` + - Profile 0 + * - ``V4L2_MPEG_VIDEO_VP8_PROFILE_1`` + - Profile 1 + * - ``V4L2_MPEG_VIDEO_VP8_PROFILE_2`` + - Profile 2 + * - ``V4L2_MPEG_VIDEO_VP8_PROFILE_3`` + - Profile 3 High Efficiency Video Coding (HEVC/H.265) Control Reference diff --git a/drivers/media/platform/qcom/venus/vdec_ctrls.c b/drivers/media/platform/qcom/venus/vdec_ctrls.c index 032839bbc967..f4604b0cd57e 100644 --- a/drivers/media/platform/qcom/venus/vdec_ctrls.c +++ b/drivers/media/platform/qcom/venus/vdec_ctrls.c @@ -29,7 +29,7 @@ static int vdec_op_s_ctrl(struct v4l2_ctrl *ctrl) break; case V4L2_CID_MPEG_VIDEO_H264_PROFILE: case V4L2_CID_MPEG_VIDEO_MPEG4_PROFILE: - case V4L2_CID_MPEG_VIDEO_VPX_PROFILE: + case V4L2_CID_MPEG_VIDEO_VP8_PROFILE: ctr->profile = ctrl->val; break; case V4L2_CID_MPEG_VIDEO_H264_LEVEL: @@ -54,7 +54,7 @@ static int vdec_op_g_volatile_ctrl(struct v4l2_ctrl *ctrl) switch (ctrl->id) { case V4L2_CID_MPEG_VIDEO_H264_PROFILE: case V4L2_CID_MPEG_VIDEO_MPEG4_PROFILE: - case V4L2_CID_MPEG_VIDEO_VPX_PROFILE: + case V4L2_CID_MPEG_VIDEO_VP8_PROFILE: ret = hfi_session_get_property(inst, ptype, &hprop); if (!ret) ctr->profile = hprop.profile_level.profile; @@ -130,8 +130,10 @@ int vdec_ctrl_init(struct venus_inst *inst) if (ctrl) ctrl->flags |= V4L2_CTRL_FLAG_VOLATILE; - ctrl = v4l2_ctrl_new_std(&inst->ctrl_handler, &vdec_ctrl_ops, - V4L2_CID_MPEG_VIDEO_VPX_PROFILE, 0, 3, 1, 0); + ctrl = v4l2_ctrl_new_std_menu(&inst->ctrl_handler, &vdec_ctrl_ops, + V4L2_CID_MPEG_VIDEO_VP8_PROFILE, + V4L2_MPEG_VIDEO_VP8_PROFILE_3, + 0, V4L2_MPEG_VIDEO_VP8_PROFILE_0); if (ctrl) ctrl->flags |= V4L2_CTRL_FLAG_VOLATILE; diff --git a/drivers/media/platform/qcom/venus/venc.c b/drivers/media/platform/qcom/venus/venc.c index 11dafc7848c5..f7a87a3dbb46 100644 --- a/drivers/media/platform/qcom/venus/venc.c +++ b/drivers/media/platform/qcom/venus/venc.c @@ -223,7 +223,7 @@ static int venc_v4l2_to_hfi(int id, int value) case V4L2_MPEG_VIDEO_H264_ENTROPY_MODE_CABAC: return HFI_H264_ENTROPY_CABAC; } - case V4L2_CID_MPEG_VIDEO_VPX_PROFILE: + case V4L2_CID_MPEG_VIDEO_VP8_PROFILE: switch (value) { case 0: default: @@ -754,7 +754,7 @@ static int venc_set_properties(struct venus_inst *inst) level = venc_v4l2_to_hfi(V4L2_CID_MPEG_VIDEO_H264_LEVEL, ctr->level.h264); } else if (inst->fmt_cap->pixfmt == V4L2_PIX_FMT_VP8) { - profile = venc_v4l2_to_hfi(V4L2_CID_MPEG_VIDEO_VPX_PROFILE, + profile = venc_v4l2_to_hfi(V4L2_CID_MPEG_VIDEO_VP8_PROFILE, ctr->profile.vpx); level = 0; } else if (inst->fmt_cap->pixfmt == V4L2_PIX_FMT_MPEG4) { diff --git a/drivers/media/platform/qcom/venus/venc_ctrls.c b/drivers/media/platform/qcom/venus/venc_ctrls.c index 21e938a28662..459101728d26 100644 --- a/drivers/media/platform/qcom/venus/venc_ctrls.c +++ b/drivers/media/platform/qcom/venus/venc_ctrls.c @@ -101,7 +101,7 @@ static int venc_op_s_ctrl(struct v4l2_ctrl *ctrl) case V4L2_CID_MPEG_VIDEO_H264_PROFILE: ctr->profile.h264 = ctrl->val; break; - case V4L2_CID_MPEG_VIDEO_VPX_PROFILE: + case V4L2_CID_MPEG_VIDEO_VP8_PROFILE: ctr->profile.vpx = ctrl->val; break; case V4L2_CID_MPEG_VIDEO_MPEG4_LEVEL: @@ -248,6 +248,11 @@ int venc_ctrl_init(struct venus_inst *inst) V4L2_MPEG_VIDEO_MULTI_SICE_MODE_MAX_BYTES, 0, V4L2_MPEG_VIDEO_MULTI_SLICE_MODE_SINGLE); + v4l2_ctrl_new_std_menu(&inst->ctrl_handler, &venc_ctrl_ops, + V4L2_CID_MPEG_VIDEO_VP8_PROFILE, + V4L2_MPEG_VIDEO_VP8_PROFILE_3, + 0, V4L2_MPEG_VIDEO_VP8_PROFILE_0); + v4l2_ctrl_new_std(&inst->ctrl_handler, &venc_ctrl_ops, V4L2_CID_MPEG_VIDEO_BITRATE, BITRATE_MIN, BITRATE_MAX, BITRATE_STEP, BITRATE_DEFAULT); @@ -256,9 +261,6 @@ int venc_ctrl_init(struct venus_inst *inst) V4L2_CID_MPEG_VIDEO_BITRATE_PEAK, BITRATE_MIN, BITRATE_MAX, BITRATE_STEP, BITRATE_DEFAULT_PEAK); - v4l2_ctrl_new_std(&inst->ctrl_handler, &venc_ctrl_ops, - V4L2_CID_MPEG_VIDEO_VPX_PROFILE, 0, 3, 1, 0); - v4l2_ctrl_new_std(&inst->ctrl_handler, &venc_ctrl_ops, V4L2_CID_MPEG_VIDEO_H264_I_FRAME_QP, 1, 51, 1, 26); diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_enc.c b/drivers/media/platform/s5p-mfc/s5p_mfc_enc.c index 570f391f2cfd..3ad4f5073002 100644 --- a/drivers/media/platform/s5p-mfc/s5p_mfc_enc.c +++ b/drivers/media/platform/s5p-mfc/s5p_mfc_enc.c @@ -692,12 +692,12 @@ static struct mfc_control controls[] = { .default_value = 10, }, { - .id = V4L2_CID_MPEG_VIDEO_VPX_PROFILE, - .type = V4L2_CTRL_TYPE_INTEGER, - .minimum = 0, - .maximum = 3, - .step = 1, - .default_value = 0, + .id = V4L2_CID_MPEG_VIDEO_VP8_PROFILE, + .type = V4L2_CTRL_TYPE_MENU, + .minimum = V4L2_MPEG_VIDEO_VP8_PROFILE_0, + .maximum = V4L2_MPEG_VIDEO_VP8_PROFILE_3, + .default_value = V4L2_MPEG_VIDEO_VP8_PROFILE_0, + .menu_skip_mask = 0, }, { .id = V4L2_CID_MPEG_VIDEO_HEVC_I_FRAME_QP, @@ -2057,7 +2057,7 @@ static int s5p_mfc_enc_s_ctrl(struct v4l2_ctrl *ctrl) case V4L2_CID_MPEG_VIDEO_VPX_P_FRAME_QP: p->codec.vp8.rc_p_frame_qp = ctrl->val; break; - case V4L2_CID_MPEG_VIDEO_VPX_PROFILE: + case V4L2_CID_MPEG_VIDEO_VP8_PROFILE: p->codec.vp8.profile = ctrl->val; break; case V4L2_CID_MPEG_VIDEO_HEVC_I_FRAME_QP: @@ -2711,4 +2711,3 @@ void s5p_mfc_enc_init(struct s5p_mfc_ctx *ctx) f.fmt.pix_mp.pixelformat = DEF_DST_FMT_ENC; ctx->dst_fmt = find_format(&f, MFC_FMT_ENC); } - diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c index d1087573da34..4a182a70de36 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls.c +++ b/drivers/media/v4l2-core/v4l2-ctrls.c @@ -431,6 +431,13 @@ const char * const *v4l2_ctrl_get_menu(u32 id) "Use Previous Specific Frame", NULL, }; + static const char * const vp8_profile[] = { + "0", + "1", + "2", + "3", + NULL, + }; static const char * const flash_led_mode[] = { "Off", @@ -614,6 +621,8 @@ const char * const *v4l2_ctrl_get_menu(u32 id) return mpeg4_profile; case V4L2_CID_MPEG_VIDEO_VPX_GOLDEN_FRAME_SEL: return vpx_golden_frame_sel; + case V4L2_CID_MPEG_VIDEO_VP8_PROFILE: + return vp8_profile; case V4L2_CID_JPEG_CHROMA_SUBSAMPLING: return jpeg_chroma_subsampling; case V4L2_CID_DV_TX_MODE: @@ -839,7 +848,7 @@ const char *v4l2_ctrl_get_name(u32 id) case V4L2_CID_MPEG_VIDEO_VPX_MAX_QP: return "VPX Maximum QP Value"; case V4L2_CID_MPEG_VIDEO_VPX_I_FRAME_QP: return "VPX I-Frame QP Value"; case V4L2_CID_MPEG_VIDEO_VPX_P_FRAME_QP: return "VPX P-Frame QP Value"; - case V4L2_CID_MPEG_VIDEO_VPX_PROFILE: return "VPX Profile"; + case V4L2_CID_MPEG_VIDEO_VP8_PROFILE: return "VP8 Profile"; /* HEVC controls */ case V4L2_CID_MPEG_VIDEO_HEVC_I_FRAME_QP: return "HEVC I-Frame QP Value"; @@ -1180,6 +1189,7 @@ void v4l2_ctrl_fill(u32 id, const char **name, enum v4l2_ctrl_type *type, case V4L2_CID_DEINTERLACING_MODE: case V4L2_CID_TUNE_DEEMPHASIS: case V4L2_CID_MPEG_VIDEO_VPX_GOLDEN_FRAME_SEL: + case V4L2_CID_MPEG_VIDEO_VP8_PROFILE: case V4L2_CID_DETECT_MD_MODE: case V4L2_CID_MPEG_VIDEO_HEVC_PROFILE: case V4L2_CID_MPEG_VIDEO_HEVC_LEVEL: diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index 8a75ad7899f3..ab96795b2829 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -587,7 +587,16 @@ enum v4l2_vp8_golden_frame_sel { #define V4L2_CID_MPEG_VIDEO_VPX_MAX_QP (V4L2_CID_MPEG_BASE+508) #define V4L2_CID_MPEG_VIDEO_VPX_I_FRAME_QP (V4L2_CID_MPEG_BASE+509) #define V4L2_CID_MPEG_VIDEO_VPX_P_FRAME_QP (V4L2_CID_MPEG_BASE+510) -#define V4L2_CID_MPEG_VIDEO_VPX_PROFILE (V4L2_CID_MPEG_BASE+511) + +#define V4L2_CID_MPEG_VIDEO_VP8_PROFILE (V4L2_CID_MPEG_BASE+511) +enum v4l2_mpeg_video_vp8_profile { + V4L2_MPEG_VIDEO_VP8_PROFILE_0 = 0, + V4L2_MPEG_VIDEO_VP8_PROFILE_1 = 1, + V4L2_MPEG_VIDEO_VP8_PROFILE_2 = 2, + V4L2_MPEG_VIDEO_VP8_PROFILE_3 = 3, +}; +/* Deprecated alias for compatibility reasons. */ +#define V4L2_CID_MPEG_VIDEO_VPX_PROFILE V4L2_CID_MPEG_VIDEO_VP8_PROFILE /* CIDs for HEVC encoding. */ -- cgit v1.2.3 From 80b14dee2bea128928537d61c333f24cb8cbb62f Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Tue, 3 Jul 2018 15:42:48 -0700 Subject: net: Add a new socket option for a future transmit time. This patch introduces SO_TXTIME. User space enables this option in order to pass a desired future transmit time in a CMSG when calling sendmsg(2). The argument to this socket option is a 8-bytes long struct provided by the uapi header net_tstamp.h defined as: struct sock_txtime { clockid_t clockid; u32 flags; }; Note that new fields were added to struct sock by filling a 2-bytes hole found in the struct. For that reason, neither the struct size or number of cachelines were altered. Signed-off-by: Richard Cochran Signed-off-by: Jesus Sanchez-Palencia Signed-off-by: David S. Miller --- arch/alpha/include/uapi/asm/socket.h | 3 +++ arch/ia64/include/uapi/asm/socket.h | 3 +++ arch/mips/include/uapi/asm/socket.h | 3 +++ arch/parisc/include/uapi/asm/socket.h | 3 +++ arch/s390/include/uapi/asm/socket.h | 3 +++ arch/sparc/include/uapi/asm/socket.h | 3 +++ arch/xtensa/include/uapi/asm/socket.h | 3 +++ include/net/sock.h | 10 ++++++++++ include/uapi/asm-generic/socket.h | 3 +++ include/uapi/linux/net_tstamp.h | 15 +++++++++++++++ net/core/sock.c | 35 +++++++++++++++++++++++++++++++++++ 11 files changed, 84 insertions(+) (limited to 'include') diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index be14f16149d5..065fb372e355 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -112,4 +112,7 @@ #define SO_ZEROCOPY 60 +#define SO_TXTIME 61 +#define SCM_TXTIME SO_TXTIME + #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/ia64/include/uapi/asm/socket.h b/arch/ia64/include/uapi/asm/socket.h index 3efba40adc54..c872c4e6bafb 100644 --- a/arch/ia64/include/uapi/asm/socket.h +++ b/arch/ia64/include/uapi/asm/socket.h @@ -114,4 +114,7 @@ #define SO_ZEROCOPY 60 +#define SO_TXTIME 61 +#define SCM_TXTIME SO_TXTIME + #endif /* _ASM_IA64_SOCKET_H */ diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index 49c3d4795963..71370fb3ceef 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -123,4 +123,7 @@ #define SO_ZEROCOPY 60 +#define SO_TXTIME 61 +#define SCM_TXTIME SO_TXTIME + #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index 1d0fdc3b5d22..061b9cf2a779 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -104,4 +104,7 @@ #define SO_ZEROCOPY 0x4035 +#define SO_TXTIME 0x4036 +#define SCM_TXTIME SO_TXTIME + #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h index 3510c0fd06f4..39d901476ee5 100644 --- a/arch/s390/include/uapi/asm/socket.h +++ b/arch/s390/include/uapi/asm/socket.h @@ -111,4 +111,7 @@ #define SO_ZEROCOPY 60 +#define SO_TXTIME 61 +#define SCM_TXTIME SO_TXTIME + #endif /* _ASM_SOCKET_H */ diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index d58520c2e6ff..7ea35e5601b6 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -101,6 +101,9 @@ #define SO_ZEROCOPY 0x003e +#define SO_TXTIME 0x003f +#define SCM_TXTIME SO_TXTIME + /* Security levels - as per NRL IPv6 - don't actually do anything */ #define SO_SECURITY_AUTHENTICATION 0x5001 #define SO_SECURITY_ENCRYPTION_TRANSPORT 0x5002 diff --git a/arch/xtensa/include/uapi/asm/socket.h b/arch/xtensa/include/uapi/asm/socket.h index 75a07b8119a9..1de07a7f7680 100644 --- a/arch/xtensa/include/uapi/asm/socket.h +++ b/arch/xtensa/include/uapi/asm/socket.h @@ -116,4 +116,7 @@ #define SO_ZEROCOPY 60 +#define SO_TXTIME 61 +#define SCM_TXTIME SO_TXTIME + #endif /* _XTENSA_SOCKET_H */ diff --git a/include/net/sock.h b/include/net/sock.h index 2ed99bfa4595..68347b9821c6 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -319,6 +319,9 @@ struct sock_common { * @sk_destruct: called at sock freeing time, i.e. when all refcnt == 0 * @sk_reuseport_cb: reuseport group container * @sk_rcu: used during RCU grace period + * @sk_clockid: clockid used by time-based scheduling (SO_TXTIME) + * @sk_txtime_deadline_mode: set deadline mode for SO_TXTIME + * @sk_txtime_unused: unused txtime flags */ struct sock { /* @@ -475,6 +478,11 @@ struct sock { u8 sk_shutdown; u32 sk_tskey; atomic_t sk_zckey; + + u8 sk_clockid; + u8 sk_txtime_deadline_mode : 1, + sk_txtime_unused : 7; + struct socket *sk_socket; void *sk_user_data; #ifdef CONFIG_SECURITY @@ -790,6 +798,7 @@ enum sock_flags { SOCK_FILTER_LOCKED, /* Filter cannot be changed anymore */ SOCK_SELECT_ERR_QUEUE, /* Wake select on error queue */ SOCK_RCU_FREE, /* wait rcu grace period in sk_destruct() */ + SOCK_TXTIME, }; #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)) @@ -1585,6 +1594,7 @@ void sock_kzfree_s(struct sock *sk, void *mem, int size); void sk_send_sigurg(struct sock *sk); struct sockcm_cookie { + u64 transmit_time; u32 mark; u16 tsflags; }; diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index 0ae758c90e54..a12692e5f7a8 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -107,4 +107,7 @@ #define SO_ZEROCOPY 60 +#define SO_TXTIME 61 +#define SCM_TXTIME SO_TXTIME + #endif /* __ASM_GENERIC_SOCKET_H */ diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h index 4fe104b2411f..c9a77c353b98 100644 --- a/include/uapi/linux/net_tstamp.h +++ b/include/uapi/linux/net_tstamp.h @@ -141,4 +141,19 @@ struct scm_ts_pktinfo { __u32 reserved[2]; }; +/* + * SO_TXTIME gets a struct sock_txtime with flags being an integer bit + * field comprised of these values. + */ +enum txtime_flags { + SOF_TXTIME_DEADLINE_MODE = (1 << 0), + + SOF_TXTIME_FLAGS_MASK = (SOF_TXTIME_DEADLINE_MODE) +}; + +struct sock_txtime { + clockid_t clockid; /* reference clockid */ + u32 flags; /* flags defined by enum txtime_flags */ +}; + #endif /* _NET_TIMESTAMPING_H */ diff --git a/net/core/sock.c b/net/core/sock.c index 6429982eb976..fe64b839f1b2 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -91,6 +91,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include #include #include #include @@ -697,6 +698,7 @@ EXPORT_SYMBOL(sk_mc_loop); int sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen) { + struct sock_txtime sk_txtime; struct sock *sk = sock->sk; int val; int valbool; @@ -1070,6 +1072,24 @@ set_rcvbuf: } break; + case SO_TXTIME: + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) { + ret = -EPERM; + } else if (optlen != sizeof(struct sock_txtime)) { + ret = -EINVAL; + } else if (copy_from_user(&sk_txtime, optval, + sizeof(struct sock_txtime))) { + ret = -EFAULT; + } else if (sk_txtime.flags & ~SOF_TXTIME_FLAGS_MASK) { + ret = -EINVAL; + } else { + sock_valbool_flag(sk, SOCK_TXTIME, true); + sk->sk_clockid = sk_txtime.clockid; + sk->sk_txtime_deadline_mode = + !!(sk_txtime.flags & SOF_TXTIME_DEADLINE_MODE); + } + break; + default: ret = -ENOPROTOOPT; break; @@ -1115,6 +1135,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, u64 val64; struct linger ling; struct timeval tm; + struct sock_txtime txtime; } v; int lv = sizeof(int); @@ -1403,6 +1424,13 @@ int sock_getsockopt(struct socket *sock, int level, int optname, v.val = sock_flag(sk, SOCK_ZEROCOPY); break; + case SO_TXTIME: + lv = sizeof(v.txtime); + v.txtime.clockid = sk->sk_clockid; + v.txtime.flags |= sk->sk_txtime_deadline_mode ? + SOF_TXTIME_DEADLINE_MODE : 0; + break; + default: /* We implement the SO_SNDLOWAT etc to not be settable * (1003.1g 7). @@ -2137,6 +2165,13 @@ int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg, sockc->tsflags &= ~SOF_TIMESTAMPING_TX_RECORD_MASK; sockc->tsflags |= tsflags; break; + case SCM_TXTIME: + if (!sock_flag(sk, SOCK_TXTIME)) + return -EINVAL; + if (cmsg->cmsg_len != CMSG_LEN(sizeof(u64))) + return -EINVAL; + sockc->transmit_time = get_unaligned((u64 *)CMSG_DATA(cmsg)); + break; /* SCM_RIGHTS and SCM_CREDENTIALS are semantically in SOL_UNIX. */ case SCM_RIGHTS: case SCM_CREDENTIALS: -- cgit v1.2.3 From bc969a977880511057053642a81371196303ca01 Mon Sep 17 00:00:00 2001 From: Jesus Sanchez-Palencia Date: Tue, 3 Jul 2018 15:42:49 -0700 Subject: net: ipv4: Hook into time based transmission Add a transmit_time field to struct inet_cork, then copy the timestamp from the CMSG cookie at ip_setup_cork() so we can safely copy it into the skb later during __ip_make_skb(). For the raw fast path, just perform the copy at raw_send_hdrinc(). Signed-off-by: Richard Cochran Signed-off-by: Jesus Sanchez-Palencia Signed-off-by: David S. Miller --- include/net/inet_sock.h | 1 + net/ipv4/icmp.c | 2 ++ net/ipv4/ip_output.c | 3 +++ net/ipv4/ping.c | 1 + net/ipv4/raw.c | 2 ++ net/ipv4/udp.c | 1 + 6 files changed, 10 insertions(+) (limited to 'include') diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 83d5b3c2ac42..314be484c696 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -148,6 +148,7 @@ struct inet_cork { __s16 tos; char priority; __u16 gso_size; + u64 transmit_time; }; struct inet_cork_full { diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 1617604c9284..937239afd68d 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -437,6 +437,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) ipc.tx_flags = 0; ipc.ttl = 0; ipc.tos = -1; + ipc.sockc.transmit_time = 0; if (icmp_param->replyopts.opt.opt.optlen) { ipc.opt = &icmp_param->replyopts.opt; @@ -715,6 +716,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) ipc.tx_flags = 0; ipc.ttl = 0; ipc.tos = -1; + ipc.sockc.transmit_time = 0; rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos, mark, type, code, &icmp_param); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 188cc586e7ff..570e3ebc3974 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1154,6 +1154,7 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, cork->tos = ipc->tos; cork->priority = ipc->priority; cork->tx_flags = ipc->tx_flags; + cork->transmit_time = ipc->sockc.transmit_time; return 0; } @@ -1414,6 +1415,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk, skb->priority = (cork->tos != -1) ? cork->priority: sk->sk_priority; skb->mark = sk->sk_mark; + skb->tstamp = cork->transmit_time; /* * Steal rt from cork.dst to avoid a pair of atomic_inc/atomic_dec * on dst refcount @@ -1551,6 +1553,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, ipc.tx_flags = 0; ipc.ttl = 0; ipc.tos = -1; + ipc.sockc.transmit_time = 0; if (replyopts.opt.opt.optlen) { ipc.opt = &replyopts.opt; diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 2ed64bca54e3..b47492205507 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -746,6 +746,7 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ipc.tx_flags = 0; ipc.ttl = 0; ipc.tos = -1; + ipc.sockc.transmit_time = 0; if (msg->msg_controllen) { err = ip_cmsg_send(sk, msg, &ipc, false); diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index abb3c9490c55..446af7be2b55 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -381,6 +381,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; + skb->tstamp = sockc->transmit_time; skb_dst_set(skb, &rt->dst); *rtp = NULL; @@ -562,6 +563,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) } ipc.sockc.tsflags = sk->sk_tsflags; + ipc.sockc.transmit_time = 0; ipc.addr = inet->inet_saddr; ipc.opt = NULL; ipc.tx_flags = 0; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 24e116ddae79..5c76ba0666ec 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -930,6 +930,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ipc.tx_flags = 0; ipc.ttl = 0; ipc.tos = -1; + ipc.sockc.transmit_time = 0; getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag; -- cgit v1.2.3 From 860b642b9c33ea4a6ae2f416607b0b98a9d11bb0 Mon Sep 17 00:00:00 2001 From: Vinicius Costa Gomes Date: Tue, 3 Jul 2018 15:42:52 -0700 Subject: net/sched: Allow creating a Qdisc watchdog with other clocks This adds 'qdisc_watchdog_init_clockid()' that allows a clockid to be passed, this allows other time references to be used when scheduling the Qdisc to run. Signed-off-by: Vinicius Costa Gomes Signed-off-by: David S. Miller --- include/net/pkt_sched.h | 2 ++ net/sched/sch_api.c | 11 +++++++++-- 2 files changed, 11 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 815b92a23936..2466ea143d01 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -72,6 +72,8 @@ struct qdisc_watchdog { struct Qdisc *qdisc; }; +void qdisc_watchdog_init_clockid(struct qdisc_watchdog *wd, struct Qdisc *qdisc, + clockid_t clockid); void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc); void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires); diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 54eca685420f..98541c6399db 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -596,12 +596,19 @@ static enum hrtimer_restart qdisc_watchdog(struct hrtimer *timer) return HRTIMER_NORESTART; } -void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc) +void qdisc_watchdog_init_clockid(struct qdisc_watchdog *wd, struct Qdisc *qdisc, + clockid_t clockid) { - hrtimer_init(&wd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED); + hrtimer_init(&wd->timer, clockid, HRTIMER_MODE_ABS_PINNED); wd->timer.function = qdisc_watchdog; wd->qdisc = qdisc; } +EXPORT_SYMBOL(qdisc_watchdog_init_clockid); + +void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc) +{ + qdisc_watchdog_init_clockid(wd, qdisc, CLOCK_MONOTONIC); +} EXPORT_SYMBOL(qdisc_watchdog_init); void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires) -- cgit v1.2.3 From 25db26a91364db00f5a30da2fea8e9afe14a163c Mon Sep 17 00:00:00 2001 From: Vinicius Costa Gomes Date: Tue, 3 Jul 2018 15:42:53 -0700 Subject: net/sched: Introduce the ETF Qdisc The ETF (Earliest TxTime First) qdisc uses the information added earlier in this series (the socket option SO_TXTIME and the new role of sk_buff->tstamp) to schedule packets transmission based on absolute time. For some workloads, just bandwidth enforcement is not enough, and precise control of the transmission of packets is necessary. Example: $ tc qdisc replace dev enp2s0 parent root handle 100 mqprio num_tc 3 \ map 2 2 1 0 2 2 2 2 2 2 2 2 2 2 2 2 queues 1@0 1@1 2@2 hw 0 $ tc qdisc add dev enp2s0 parent 100:1 etf delta 100000 \ clockid CLOCK_TAI In this example, the Qdisc will provide SW best-effort for the control of the transmission time to the network adapter, the time stamp in the socket will be in reference to the clockid CLOCK_TAI and packets will leave the qdisc "delta" (100000) nanoseconds before its transmission time. The ETF qdisc will buffer packets sorted by their txtime. It will drop packets on enqueue() if their skbuff clockid does not match the clock reference of the Qdisc. Moreover, on dequeue(), a packet will be dropped if it expires while being enqueued. The qdisc also supports the SO_TXTIME deadline mode. For this mode, it will dequeue a packet as soon as possible and change the skb timestamp to 'now' during etf_dequeue(). Note that both the qdisc's and the SO_TXTIME ABIs allow for a clockid to be configured, but it's been decided that usage of CLOCK_TAI should be enforced until we decide to allow for other clockids to be used. The rationale here is that PTP times are usually in the TAI scale, thus no other clocks should be necessary. For now, the qdisc will return EINVAL if any clocks other than CLOCK_TAI are used. Signed-off-by: Jesus Sanchez-Palencia Signed-off-by: Vinicius Costa Gomes Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + include/uapi/linux/pkt_sched.h | 17 ++ net/sched/Kconfig | 11 ++ net/sched/Makefile | 1 + net/sched/sch_etf.c | 384 +++++++++++++++++++++++++++++++++++++++++ 5 files changed, 414 insertions(+) create mode 100644 net/sched/sch_etf.c (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c1ef749b6f9f..f06ee8f91e74 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -798,6 +798,7 @@ enum tc_setup_type { TC_SETUP_QDISC_RED, TC_SETUP_QDISC_PRIO, TC_SETUP_QDISC_MQ, + TC_SETUP_QDISC_ETF, }; /* These structures hold the attributes of bpf state that are being passed diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index bad3c03bcf43..d5e933ce1447 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -937,4 +937,21 @@ enum { #define TCA_CBS_MAX (__TCA_CBS_MAX - 1) + +/* ETF */ +struct tc_etf_qopt { + __s32 delta; + __s32 clockid; + __u32 flags; +#define TC_ETF_DEADLINE_MODE_ON BIT(0) +}; + +enum { + TCA_ETF_UNSPEC, + TCA_ETF_PARMS, + __TCA_ETF_MAX, +}; + +#define TCA_ETF_MAX (__TCA_ETF_MAX - 1) + #endif diff --git a/net/sched/Kconfig b/net/sched/Kconfig index a01169fb5325..fcc89706745b 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -183,6 +183,17 @@ config NET_SCH_CBS To compile this code as a module, choose M here: the module will be called sch_cbs. +config NET_SCH_ETF + tristate "Earliest TxTime First (ETF)" + help + Say Y here if you want to use the Earliest TxTime First (ETF) packet + scheduling algorithm. + + See the top of for more details. + + To compile this code as a module, choose M here: the + module will be called sch_etf. + config NET_SCH_GRED tristate "Generic Random Early Detection (GRED)" ---help--- diff --git a/net/sched/Makefile b/net/sched/Makefile index 8811d3804878..9a5a7077d217 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -54,6 +54,7 @@ obj-$(CONFIG_NET_SCH_FQ) += sch_fq.o obj-$(CONFIG_NET_SCH_HHF) += sch_hhf.o obj-$(CONFIG_NET_SCH_PIE) += sch_pie.o obj-$(CONFIG_NET_SCH_CBS) += sch_cbs.o +obj-$(CONFIG_NET_SCH_ETF) += sch_etf.o obj-$(CONFIG_NET_CLS_U32) += cls_u32.o obj-$(CONFIG_NET_CLS_ROUTE4) += cls_route.o diff --git a/net/sched/sch_etf.c b/net/sched/sch_etf.c new file mode 100644 index 000000000000..4b7f4903ac17 --- /dev/null +++ b/net/sched/sch_etf.c @@ -0,0 +1,384 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* net/sched/sch_etf.c Earliest TxTime First queueing discipline. + * + * Authors: Jesus Sanchez-Palencia + * Vinicius Costa Gomes + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define DEADLINE_MODE_IS_ON(x) ((x)->flags & TC_ETF_DEADLINE_MODE_ON) + +struct etf_sched_data { + bool deadline_mode; + int clockid; + int queue; + s32 delta; /* in ns */ + ktime_t last; /* The txtime of the last skb sent to the netdevice. */ + struct rb_root head; + struct qdisc_watchdog watchdog; + ktime_t (*get_time)(void); +}; + +static const struct nla_policy etf_policy[TCA_ETF_MAX + 1] = { + [TCA_ETF_PARMS] = { .len = sizeof(struct tc_etf_qopt) }, +}; + +static inline int validate_input_params(struct tc_etf_qopt *qopt, + struct netlink_ext_ack *extack) +{ + /* Check if params comply to the following rules: + * * Clockid and delta must be valid. + * + * * Dynamic clockids are not supported. + * + * * Delta must be a positive integer. + */ + if (qopt->clockid < 0) { + NL_SET_ERR_MSG(extack, "Dynamic clockids are not supported"); + return -ENOTSUPP; + } + + if (qopt->clockid != CLOCK_TAI) { + NL_SET_ERR_MSG(extack, "Invalid clockid. CLOCK_TAI must be used"); + return -EINVAL; + } + + if (qopt->delta < 0) { + NL_SET_ERR_MSG(extack, "Delta must be positive"); + return -EINVAL; + } + + return 0; +} + +static bool is_packet_valid(struct Qdisc *sch, struct sk_buff *nskb) +{ + struct etf_sched_data *q = qdisc_priv(sch); + ktime_t txtime = nskb->tstamp; + struct sock *sk = nskb->sk; + ktime_t now; + + if (!sk) + return false; + + if (!sock_flag(sk, SOCK_TXTIME)) + return false; + + /* We don't perform crosstimestamping. + * Drop if packet's clockid differs from qdisc's. + */ + if (sk->sk_clockid != q->clockid) + return false; + + if (sk->sk_txtime_deadline_mode != q->deadline_mode) + return false; + + now = q->get_time(); + if (ktime_before(txtime, now) || ktime_before(txtime, q->last)) + return false; + + return true; +} + +static struct sk_buff *etf_peek_timesortedlist(struct Qdisc *sch) +{ + struct etf_sched_data *q = qdisc_priv(sch); + struct rb_node *p; + + p = rb_first(&q->head); + if (!p) + return NULL; + + return rb_to_skb(p); +} + +static void reset_watchdog(struct Qdisc *sch) +{ + struct etf_sched_data *q = qdisc_priv(sch); + struct sk_buff *skb = etf_peek_timesortedlist(sch); + ktime_t next; + + if (!skb) + return; + + next = ktime_sub_ns(skb->tstamp, q->delta); + qdisc_watchdog_schedule_ns(&q->watchdog, ktime_to_ns(next)); +} + +static int etf_enqueue_timesortedlist(struct sk_buff *nskb, struct Qdisc *sch, + struct sk_buff **to_free) +{ + struct etf_sched_data *q = qdisc_priv(sch); + struct rb_node **p = &q->head.rb_node, *parent = NULL; + ktime_t txtime = nskb->tstamp; + + if (!is_packet_valid(sch, nskb)) + return qdisc_drop(nskb, sch, to_free); + + while (*p) { + struct sk_buff *skb; + + parent = *p; + skb = rb_to_skb(parent); + if (ktime_after(txtime, skb->tstamp)) + p = &parent->rb_right; + else + p = &parent->rb_left; + } + rb_link_node(&nskb->rbnode, parent, p); + rb_insert_color(&nskb->rbnode, &q->head); + + qdisc_qstats_backlog_inc(sch, nskb); + sch->q.qlen++; + + /* Now we may need to re-arm the qdisc watchdog for the next packet. */ + reset_watchdog(sch); + + return NET_XMIT_SUCCESS; +} + +static void timesortedlist_erase(struct Qdisc *sch, struct sk_buff *skb, + bool drop) +{ + struct etf_sched_data *q = qdisc_priv(sch); + + rb_erase(&skb->rbnode, &q->head); + + /* The rbnode field in the skb re-uses these fields, now that + * we are done with the rbnode, reset them. + */ + skb->next = NULL; + skb->prev = NULL; + skb->dev = qdisc_dev(sch); + + qdisc_qstats_backlog_dec(sch, skb); + + if (drop) { + struct sk_buff *to_free = NULL; + + qdisc_drop(skb, sch, &to_free); + kfree_skb_list(to_free); + qdisc_qstats_overlimit(sch); + } else { + qdisc_bstats_update(sch, skb); + + q->last = skb->tstamp; + } + + sch->q.qlen--; +} + +static struct sk_buff *etf_dequeue_timesortedlist(struct Qdisc *sch) +{ + struct etf_sched_data *q = qdisc_priv(sch); + struct sk_buff *skb; + ktime_t now, next; + + skb = etf_peek_timesortedlist(sch); + if (!skb) + return NULL; + + now = q->get_time(); + + /* Drop if packet has expired while in queue. */ + /* FIXME: Must return error on the socket's error queue */ + if (ktime_before(skb->tstamp, now)) { + timesortedlist_erase(sch, skb, true); + skb = NULL; + goto out; + } + + /* When in deadline mode, dequeue as soon as possible and change the + * txtime from deadline to (now + delta). + */ + if (q->deadline_mode) { + timesortedlist_erase(sch, skb, false); + skb->tstamp = now; + goto out; + } + + next = ktime_sub_ns(skb->tstamp, q->delta); + + /* Dequeue only if now is within the [txtime - delta, txtime] range. */ + if (ktime_after(now, next)) + timesortedlist_erase(sch, skb, false); + else + skb = NULL; + +out: + /* Now we may need to re-arm the qdisc watchdog for the next packet. */ + reset_watchdog(sch); + + return skb; +} + +static int etf_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + struct etf_sched_data *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct nlattr *tb[TCA_ETF_MAX + 1]; + struct tc_etf_qopt *qopt; + int err; + + if (!opt) { + NL_SET_ERR_MSG(extack, + "Missing ETF qdisc options which are mandatory"); + return -EINVAL; + } + + err = nla_parse_nested(tb, TCA_ETF_MAX, opt, etf_policy, extack); + if (err < 0) + return err; + + if (!tb[TCA_ETF_PARMS]) { + NL_SET_ERR_MSG(extack, "Missing mandatory ETF parameters"); + return -EINVAL; + } + + qopt = nla_data(tb[TCA_ETF_PARMS]); + + pr_debug("delta %d clockid %d deadline %s\n", + qopt->delta, qopt->clockid, + DEADLINE_MODE_IS_ON(qopt) ? "on" : "off"); + + err = validate_input_params(qopt, extack); + if (err < 0) + return err; + + q->queue = sch->dev_queue - netdev_get_tx_queue(dev, 0); + + /* Everything went OK, save the parameters used. */ + q->delta = qopt->delta; + q->clockid = qopt->clockid; + q->deadline_mode = DEADLINE_MODE_IS_ON(qopt); + + switch (q->clockid) { + case CLOCK_REALTIME: + q->get_time = ktime_get_real; + break; + case CLOCK_MONOTONIC: + q->get_time = ktime_get; + break; + case CLOCK_BOOTTIME: + q->get_time = ktime_get_boottime; + break; + case CLOCK_TAI: + q->get_time = ktime_get_clocktai; + break; + default: + NL_SET_ERR_MSG(extack, "Clockid is not supported"); + return -ENOTSUPP; + } + + qdisc_watchdog_init_clockid(&q->watchdog, sch, q->clockid); + + return 0; +} + +static void timesortedlist_clear(struct Qdisc *sch) +{ + struct etf_sched_data *q = qdisc_priv(sch); + struct rb_node *p = rb_first(&q->head); + + while (p) { + struct sk_buff *skb = rb_to_skb(p); + + p = rb_next(p); + + rb_erase(&skb->rbnode, &q->head); + rtnl_kfree_skbs(skb, skb); + sch->q.qlen--; + } +} + +static void etf_reset(struct Qdisc *sch) +{ + struct etf_sched_data *q = qdisc_priv(sch); + + /* Only cancel watchdog if it's been initialized. */ + if (q->watchdog.qdisc == sch) + qdisc_watchdog_cancel(&q->watchdog); + + /* No matter which mode we are on, it's safe to clear both lists. */ + timesortedlist_clear(sch); + __qdisc_reset_queue(&sch->q); + + sch->qstats.backlog = 0; + sch->q.qlen = 0; + + q->last = 0; +} + +static void etf_destroy(struct Qdisc *sch) +{ + struct etf_sched_data *q = qdisc_priv(sch); + + /* Only cancel watchdog if it's been initialized. */ + if (q->watchdog.qdisc == sch) + qdisc_watchdog_cancel(&q->watchdog); +} + +static int etf_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + struct etf_sched_data *q = qdisc_priv(sch); + struct tc_etf_qopt opt = { }; + struct nlattr *nest; + + nest = nla_nest_start(skb, TCA_OPTIONS); + if (!nest) + goto nla_put_failure; + + opt.delta = q->delta; + opt.clockid = q->clockid; + if (q->deadline_mode) + opt.flags |= TC_ETF_DEADLINE_MODE_ON; + + if (nla_put(skb, TCA_ETF_PARMS, sizeof(opt), &opt)) + goto nla_put_failure; + + return nla_nest_end(skb, nest); + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -1; +} + +static struct Qdisc_ops etf_qdisc_ops __read_mostly = { + .id = "etf", + .priv_size = sizeof(struct etf_sched_data), + .enqueue = etf_enqueue_timesortedlist, + .dequeue = etf_dequeue_timesortedlist, + .peek = etf_peek_timesortedlist, + .init = etf_init, + .reset = etf_reset, + .destroy = etf_destroy, + .dump = etf_dump, + .owner = THIS_MODULE, +}; + +static int __init etf_module_init(void) +{ + return register_qdisc(&etf_qdisc_ops); +} + +static void __exit etf_module_exit(void) +{ + unregister_qdisc(&etf_qdisc_ops); +} +module_init(etf_module_init) +module_exit(etf_module_exit) +MODULE_LICENSE("GPL"); -- cgit v1.2.3 From 88cab77162e86e0f6a2b7e4f859c1435c4e24feb Mon Sep 17 00:00:00 2001 From: Jesus Sanchez-Palencia Date: Tue, 3 Jul 2018 15:42:54 -0700 Subject: net/sched: Add HW offloading capability to ETF Add infra so etf qdisc supports HW offload of time-based transmission. For hw offload, the time sorted list is still used, so packets are dequeued always in order of txtime. Example: $ tc qdisc replace dev enp2s0 parent root handle 100 mqprio num_tc 3 \ map 2 2 1 0 2 2 2 2 2 2 2 2 2 2 2 2 queues 1@0 1@1 2@2 hw 0 $ tc qdisc add dev enp2s0 parent 100:1 etf offload delta 100000 \ clockid CLOCK_REALTIME In this example, the Qdisc will use HW offload for the control of the transmission time through the network adapter. The hrtimer used for packets scheduling inside the qdisc will use the clockid CLOCK_REALTIME as reference and packets leave the Qdisc "delta" (100000) nanoseconds before their transmission time. Because this will be using HW offload and since dynamic clocks are not supported by the hrtimer, the system clock and the PHC clock must be synchronized for this mode to behave as expected. Signed-off-by: Jesus Sanchez-Palencia Signed-off-by: David S. Miller --- include/net/pkt_sched.h | 5 +++ include/uapi/linux/pkt_sched.h | 1 + net/sched/sch_etf.c | 71 +++++++++++++++++++++++++++++++++++++++++- 3 files changed, 76 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 2466ea143d01..7dc769e5452b 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -155,4 +155,9 @@ struct tc_cbs_qopt_offload { s32 sendslope; }; +struct tc_etf_qopt_offload { + u8 enable; + s32 queue; +}; + #endif diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index d5e933ce1447..949118461009 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -944,6 +944,7 @@ struct tc_etf_qopt { __s32 clockid; __u32 flags; #define TC_ETF_DEADLINE_MODE_ON BIT(0) +#define TC_ETF_OFFLOAD_ON BIT(1) }; enum { diff --git a/net/sched/sch_etf.c b/net/sched/sch_etf.c index 4b7f4903ac17..932a136db568 100644 --- a/net/sched/sch_etf.c +++ b/net/sched/sch_etf.c @@ -20,8 +20,10 @@ #include #define DEADLINE_MODE_IS_ON(x) ((x)->flags & TC_ETF_DEADLINE_MODE_ON) +#define OFFLOAD_IS_ON(x) ((x)->flags & TC_ETF_OFFLOAD_ON) struct etf_sched_data { + bool offload; bool deadline_mode; int clockid; int queue; @@ -45,6 +47,9 @@ static inline int validate_input_params(struct tc_etf_qopt *qopt, * * Dynamic clockids are not supported. * * * Delta must be a positive integer. + * + * Also note that for the HW offload case, we must + * expect that system clocks have been synchronized to PHC. */ if (qopt->clockid < 0) { NL_SET_ERR_MSG(extack, "Dynamic clockids are not supported"); @@ -225,6 +230,56 @@ out: return skb; } +static void etf_disable_offload(struct net_device *dev, + struct etf_sched_data *q) +{ + struct tc_etf_qopt_offload etf = { }; + const struct net_device_ops *ops; + int err; + + if (!q->offload) + return; + + ops = dev->netdev_ops; + if (!ops->ndo_setup_tc) + return; + + etf.queue = q->queue; + etf.enable = 0; + + err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_ETF, &etf); + if (err < 0) + pr_warn("Couldn't disable ETF offload for queue %d\n", + etf.queue); +} + +static int etf_enable_offload(struct net_device *dev, struct etf_sched_data *q, + struct netlink_ext_ack *extack) +{ + const struct net_device_ops *ops = dev->netdev_ops; + struct tc_etf_qopt_offload etf = { }; + int err; + + if (q->offload) + return 0; + + if (!ops->ndo_setup_tc) { + NL_SET_ERR_MSG(extack, "Specified device does not support ETF offload"); + return -EOPNOTSUPP; + } + + etf.queue = q->queue; + etf.enable = 1; + + err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_ETF, &etf); + if (err < 0) { + NL_SET_ERR_MSG(extack, "Specified device failed to setup ETF hardware offload"); + return err; + } + + return 0; +} + static int etf_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { @@ -251,8 +306,9 @@ static int etf_init(struct Qdisc *sch, struct nlattr *opt, qopt = nla_data(tb[TCA_ETF_PARMS]); - pr_debug("delta %d clockid %d deadline %s\n", + pr_debug("delta %d clockid %d offload %s deadline %s\n", qopt->delta, qopt->clockid, + OFFLOAD_IS_ON(qopt) ? "on" : "off", DEADLINE_MODE_IS_ON(qopt) ? "on" : "off"); err = validate_input_params(qopt, extack); @@ -261,9 +317,16 @@ static int etf_init(struct Qdisc *sch, struct nlattr *opt, q->queue = sch->dev_queue - netdev_get_tx_queue(dev, 0); + if (OFFLOAD_IS_ON(qopt)) { + err = etf_enable_offload(dev, q, extack); + if (err < 0) + return err; + } + /* Everything went OK, save the parameters used. */ q->delta = qopt->delta; q->clockid = qopt->clockid; + q->offload = OFFLOAD_IS_ON(qopt); q->deadline_mode = DEADLINE_MODE_IS_ON(qopt); switch (q->clockid) { @@ -326,10 +389,13 @@ static void etf_reset(struct Qdisc *sch) static void etf_destroy(struct Qdisc *sch) { struct etf_sched_data *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); /* Only cancel watchdog if it's been initialized. */ if (q->watchdog.qdisc == sch) qdisc_watchdog_cancel(&q->watchdog); + + etf_disable_offload(dev, q); } static int etf_dump(struct Qdisc *sch, struct sk_buff *skb) @@ -344,6 +410,9 @@ static int etf_dump(struct Qdisc *sch, struct sk_buff *skb) opt.delta = q->delta; opt.clockid = q->clockid; + if (q->offload) + opt.flags |= TC_ETF_OFFLOAD_ON; + if (q->deadline_mode) opt.flags |= TC_ETF_DEADLINE_MODE_ON; -- cgit v1.2.3 From 4b15c7075352668d4467ced7594b676707d11cae Mon Sep 17 00:00:00 2001 From: Jesus Sanchez-Palencia Date: Tue, 3 Jul 2018 15:43:00 -0700 Subject: net/sched: Make etf report drops on error_queue Use the socket error queue for reporting dropped packets if the socket has enabled that feature through the SO_TXTIME API. Packets are dropped either on enqueue() if they aren't accepted by the qdisc or on dequeue() if the system misses their deadline. Those are reported as different errors so applications can react accordingly. Userspace can retrieve the errors through the socket error queue and the corresponding cmsg interfaces. A struct sock_extended_err* is used for returning the error data, and the packet's timestamp can be retrieved by adding both ee_data and ee_info fields as e.g.: ((__u64) serr->ee_data << 32) + serr->ee_info This feature is disabled by default and must be explicitly enabled by applications. Enabling it can bring some overhead for the Tx cycles of the application. Signed-off-by: Jesus Sanchez-Palencia Signed-off-by: David S. Miller --- include/net/sock.h | 3 ++- include/uapi/linux/errqueue.h | 4 ++++ include/uapi/linux/net_tstamp.h | 5 ++++- net/core/sock.c | 4 ++++ net/sched/sch_etf.c | 35 +++++++++++++++++++++++++++++++++-- 5 files changed, 47 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index 68347b9821c6..e0eac9ef44b5 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -481,7 +481,8 @@ struct sock { u8 sk_clockid; u8 sk_txtime_deadline_mode : 1, - sk_txtime_unused : 7; + sk_txtime_report_errors : 1, + sk_txtime_unused : 6; struct socket *sk_socket; void *sk_user_data; diff --git a/include/uapi/linux/errqueue.h b/include/uapi/linux/errqueue.h index dc64cfaf13da..c0151200f7d1 100644 --- a/include/uapi/linux/errqueue.h +++ b/include/uapi/linux/errqueue.h @@ -20,12 +20,16 @@ struct sock_extended_err { #define SO_EE_ORIGIN_ICMP6 3 #define SO_EE_ORIGIN_TXSTATUS 4 #define SO_EE_ORIGIN_ZEROCOPY 5 +#define SO_EE_ORIGIN_TXTIME 6 #define SO_EE_ORIGIN_TIMESTAMPING SO_EE_ORIGIN_TXSTATUS #define SO_EE_OFFENDER(ee) ((struct sockaddr*)((ee)+1)) #define SO_EE_CODE_ZEROCOPY_COPIED 1 +#define SO_EE_CODE_TXTIME_INVALID_PARAM 1 +#define SO_EE_CODE_TXTIME_MISSED 2 + /** * struct scm_timestamping - timestamps exposed through cmsg * diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h index c9a77c353b98..f8f4539f1135 100644 --- a/include/uapi/linux/net_tstamp.h +++ b/include/uapi/linux/net_tstamp.h @@ -147,8 +147,11 @@ struct scm_ts_pktinfo { */ enum txtime_flags { SOF_TXTIME_DEADLINE_MODE = (1 << 0), + SOF_TXTIME_REPORT_ERRORS = (1 << 1), - SOF_TXTIME_FLAGS_MASK = (SOF_TXTIME_DEADLINE_MODE) + SOF_TXTIME_FLAGS_LAST = SOF_TXTIME_REPORT_ERRORS, + SOF_TXTIME_FLAGS_MASK = (SOF_TXTIME_FLAGS_LAST - 1) | + SOF_TXTIME_FLAGS_LAST }; struct sock_txtime { diff --git a/net/core/sock.c b/net/core/sock.c index fe64b839f1b2..03fdea5b0f57 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1087,6 +1087,8 @@ set_rcvbuf: sk->sk_clockid = sk_txtime.clockid; sk->sk_txtime_deadline_mode = !!(sk_txtime.flags & SOF_TXTIME_DEADLINE_MODE); + sk->sk_txtime_report_errors = + !!(sk_txtime.flags & SOF_TXTIME_REPORT_ERRORS); } break; @@ -1429,6 +1431,8 @@ int sock_getsockopt(struct socket *sock, int level, int optname, v.txtime.clockid = sk->sk_clockid; v.txtime.flags |= sk->sk_txtime_deadline_mode ? SOF_TXTIME_DEADLINE_MODE : 0; + v.txtime.flags |= sk->sk_txtime_report_errors ? + SOF_TXTIME_REPORT_ERRORS : 0; break; default: diff --git a/net/sched/sch_etf.c b/net/sched/sch_etf.c index 932a136db568..1538d6fa8165 100644 --- a/net/sched/sch_etf.c +++ b/net/sched/sch_etf.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -123,6 +124,32 @@ static void reset_watchdog(struct Qdisc *sch) qdisc_watchdog_schedule_ns(&q->watchdog, ktime_to_ns(next)); } +static void report_sock_error(struct sk_buff *skb, u32 err, u8 code) +{ + struct sock_exterr_skb *serr; + struct sk_buff *clone; + ktime_t txtime = skb->tstamp; + + if (!skb->sk || !(skb->sk->sk_txtime_report_errors)) + return; + + clone = skb_clone(skb, GFP_ATOMIC); + if (!clone) + return; + + serr = SKB_EXT_ERR(clone); + serr->ee.ee_errno = err; + serr->ee.ee_origin = SO_EE_ORIGIN_TXTIME; + serr->ee.ee_type = 0; + serr->ee.ee_code = code; + serr->ee.ee_pad = 0; + serr->ee.ee_data = (txtime >> 32); /* high part of tstamp */ + serr->ee.ee_info = txtime; /* low part of tstamp */ + + if (sock_queue_err_skb(skb->sk, clone)) + kfree_skb(clone); +} + static int etf_enqueue_timesortedlist(struct sk_buff *nskb, struct Qdisc *sch, struct sk_buff **to_free) { @@ -130,8 +157,11 @@ static int etf_enqueue_timesortedlist(struct sk_buff *nskb, struct Qdisc *sch, struct rb_node **p = &q->head.rb_node, *parent = NULL; ktime_t txtime = nskb->tstamp; - if (!is_packet_valid(sch, nskb)) + if (!is_packet_valid(sch, nskb)) { + report_sock_error(nskb, EINVAL, + SO_EE_CODE_TXTIME_INVALID_PARAM); return qdisc_drop(nskb, sch, to_free); + } while (*p) { struct sk_buff *skb; @@ -174,6 +204,8 @@ static void timesortedlist_erase(struct Qdisc *sch, struct sk_buff *skb, if (drop) { struct sk_buff *to_free = NULL; + report_sock_error(skb, ECANCELED, SO_EE_CODE_TXTIME_MISSED); + qdisc_drop(skb, sch, &to_free); kfree_skb_list(to_free); qdisc_qstats_overlimit(sch); @@ -199,7 +231,6 @@ static struct sk_buff *etf_dequeue_timesortedlist(struct Qdisc *sch) now = q->get_time(); /* Drop if packet has expired while in queue. */ - /* FIXME: Must return error on the socket's error queue */ if (ktime_before(skb->tstamp, now)) { timesortedlist_erase(sch, skb, true); skb = NULL; -- cgit v1.2.3 From 2a75364d09b05f257f4cd1f718e06e0247eb1dd3 Mon Sep 17 00:00:00 2001 From: Keiichi Watanabe Date: Mon, 18 Jun 2018 03:58:53 -0400 Subject: media: v4l2-ctrl: Add control for VP9 profile Add a new control V4L2_CID_MPEG_VIDEO_VP9_PROFILE for VP9 profiles. This control allows selecting the desired profile for VP9 encoder and querying for supported profiles by VP9 encoder/decoder. Though this control is similar to V4L2_CID_MPEG_VIDEO_VP8_PROFILE, we need to separate this control from it because supported profiles usually differ between VP8 and VP9. Signed-off-by: Keiichi Watanabe Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- Documentation/media/uapi/v4l/extended-controls.rst | 23 ++++++++++++++++++++++ drivers/media/v4l2-core/v4l2-ctrls.c | 11 +++++++++++ include/uapi/linux/v4l2-controls.h | 7 +++++++ 3 files changed, 41 insertions(+) (limited to 'include') diff --git a/Documentation/media/uapi/v4l/extended-controls.rst b/Documentation/media/uapi/v4l/extended-controls.rst index 01ef31a934b4..9f7312bf3365 100644 --- a/Documentation/media/uapi/v4l/extended-controls.rst +++ b/Documentation/media/uapi/v4l/extended-controls.rst @@ -1978,6 +1978,29 @@ enum v4l2_mpeg_video_vp8_profile - * - ``V4L2_MPEG_VIDEO_VP8_PROFILE_3`` - Profile 3 +.. _v4l2-mpeg-video-vp9-profile: + +``V4L2_CID_MPEG_VIDEO_VP9_PROFILE`` + (enum) + +enum v4l2_mpeg_video_vp9_profile - + This control allows selecting the profile for VP9 encoder. + This is also used to enumerate supported profiles by VP9 encoder or decoder. + Possible values are: + +.. flat-table:: + :header-rows: 0 + :stub-columns: 0 + + * - ``V4L2_MPEG_VIDEO_VP9_PROFILE_0`` + - Profile 0 + * - ``V4L2_MPEG_VIDEO_VP9_PROFILE_1`` + - Profile 1 + * - ``V4L2_MPEG_VIDEO_VP9_PROFILE_2`` + - Profile 2 + * - ``V4L2_MPEG_VIDEO_VP9_PROFILE_3`` + - Profile 3 + High Efficiency Video Coding (HEVC/H.265) Control Reference ----------------------------------------------------------- diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c index 4a182a70de36..599c1cbff3b9 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls.c +++ b/drivers/media/v4l2-core/v4l2-ctrls.c @@ -438,6 +438,13 @@ const char * const *v4l2_ctrl_get_menu(u32 id) "3", NULL, }; + static const char * const vp9_profile[] = { + "0", + "1", + "2", + "3", + NULL, + }; static const char * const flash_led_mode[] = { "Off", @@ -623,6 +630,8 @@ const char * const *v4l2_ctrl_get_menu(u32 id) return vpx_golden_frame_sel; case V4L2_CID_MPEG_VIDEO_VP8_PROFILE: return vp8_profile; + case V4L2_CID_MPEG_VIDEO_VP9_PROFILE: + return vp9_profile; case V4L2_CID_JPEG_CHROMA_SUBSAMPLING: return jpeg_chroma_subsampling; case V4L2_CID_DV_TX_MODE: @@ -849,6 +858,7 @@ const char *v4l2_ctrl_get_name(u32 id) case V4L2_CID_MPEG_VIDEO_VPX_I_FRAME_QP: return "VPX I-Frame QP Value"; case V4L2_CID_MPEG_VIDEO_VPX_P_FRAME_QP: return "VPX P-Frame QP Value"; case V4L2_CID_MPEG_VIDEO_VP8_PROFILE: return "VP8 Profile"; + case V4L2_CID_MPEG_VIDEO_VP9_PROFILE: return "VP9 Profile"; /* HEVC controls */ case V4L2_CID_MPEG_VIDEO_HEVC_I_FRAME_QP: return "HEVC I-Frame QP Value"; @@ -1190,6 +1200,7 @@ void v4l2_ctrl_fill(u32 id, const char **name, enum v4l2_ctrl_type *type, case V4L2_CID_TUNE_DEEMPHASIS: case V4L2_CID_MPEG_VIDEO_VPX_GOLDEN_FRAME_SEL: case V4L2_CID_MPEG_VIDEO_VP8_PROFILE: + case V4L2_CID_MPEG_VIDEO_VP9_PROFILE: case V4L2_CID_DETECT_MD_MODE: case V4L2_CID_MPEG_VIDEO_HEVC_PROFILE: case V4L2_CID_MPEG_VIDEO_HEVC_LEVEL: diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index ab96795b2829..e4ee10ee917d 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -597,6 +597,13 @@ enum v4l2_mpeg_video_vp8_profile { }; /* Deprecated alias for compatibility reasons. */ #define V4L2_CID_MPEG_VIDEO_VPX_PROFILE V4L2_CID_MPEG_VIDEO_VP8_PROFILE +#define V4L2_CID_MPEG_VIDEO_VP9_PROFILE (V4L2_CID_MPEG_BASE+512) +enum v4l2_mpeg_video_vp9_profile { + V4L2_MPEG_VIDEO_VP9_PROFILE_0 = 0, + V4L2_MPEG_VIDEO_VP9_PROFILE_1 = 1, + V4L2_MPEG_VIDEO_VP9_PROFILE_2 = 2, + V4L2_MPEG_VIDEO_VP9_PROFILE_3 = 3, +}; /* CIDs for HEVC encoding. */ -- cgit v1.2.3 From b5cb15d9372abc9adc4e844c0c1bf594ca6a7695 Mon Sep 17 00:00:00 2001 From: Chris von Recklinghausen Date: Tue, 3 Jul 2018 15:43:08 -0400 Subject: usercopy: Allow boot cmdline disabling of hardening Enabling HARDENED_USERCOPY may cause measurable regressions in networking performance: up to 8% under UDP flood. I ran a small packet UDP flood using pktgen vs. a host b2b connected. On the receiver side the UDP packets are processed by a simple user space process that just reads and drops them: https://github.com/netoptimizer/network-testing/blob/master/src/udp_sink.c Not very useful from a functional PoV, but it helps to pin-point bottlenecks in the networking stack. When running a kernel with CONFIG_HARDENED_USERCOPY=y, I see a 5-8% regression in the receive tput, compared to the same kernel without this option enabled. With CONFIG_HARDENED_USERCOPY=y, perf shows ~6% of CPU time spent cumulatively in __check_object_size (~4%) and __virt_addr_valid (~2%). The call-chain is: __GI___libc_recvfrom entry_SYSCALL_64_after_hwframe do_syscall_64 __x64_sys_recvfrom __sys_recvfrom inet_recvmsg udp_recvmsg __check_object_size udp_recvmsg() actually calls copy_to_iter() (inlined) and the latters calls check_copy_size() (again, inlined). A generic distro may want to enable HARDENED_USERCOPY in their default kernel config, but at the same time, such distro may want to be able to avoid the performance penalties in with the default configuration and disable the stricter check on a per-boot basis. This change adds a boot parameter that conditionally disables HARDENED_USERCOPY via "hardened_usercopy=off". Signed-off-by: Chris von Recklinghausen Signed-off-by: Kees Cook --- Documentation/admin-guide/kernel-parameters.txt | 11 +++++++++++ include/linux/jump_label.h | 6 ++++++ mm/usercopy.c | 25 +++++++++++++++++++++++++ 3 files changed, 42 insertions(+) (limited to 'include') diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index efc7aa7a0670..560d4dc66f02 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -816,6 +816,17 @@ disable= [IPV6] See Documentation/networking/ipv6.txt. + hardened_usercopy= + [KNL] Under CONFIG_HARDENED_USERCOPY, whether + hardening is enabled for this boot. Hardened + usercopy checking is used to protect the kernel + from reading or writing beyond known memory + allocation boundaries as a proactive defense + against bounds-checking flaws in the kernel's + copy_to_user()/copy_from_user() interface. + on Perform hardened usercopy checks (default). + off Disable hardened usercopy checks. + disable_radix [PPC] Disable RADIX MMU mode on POWER9 diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index b46b541c67c4..1a0b6f17a5d6 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -299,12 +299,18 @@ struct static_key_false { #define DEFINE_STATIC_KEY_TRUE(name) \ struct static_key_true name = STATIC_KEY_TRUE_INIT +#define DEFINE_STATIC_KEY_TRUE_RO(name) \ + struct static_key_true name __ro_after_init = STATIC_KEY_TRUE_INIT + #define DECLARE_STATIC_KEY_TRUE(name) \ extern struct static_key_true name #define DEFINE_STATIC_KEY_FALSE(name) \ struct static_key_false name = STATIC_KEY_FALSE_INIT +#define DEFINE_STATIC_KEY_FALSE_RO(name) \ + struct static_key_false name __ro_after_init = STATIC_KEY_FALSE_INIT + #define DECLARE_STATIC_KEY_FALSE(name) \ extern struct static_key_false name diff --git a/mm/usercopy.c b/mm/usercopy.c index e9e9325f7638..852eb4e53f06 100644 --- a/mm/usercopy.c +++ b/mm/usercopy.c @@ -20,6 +20,8 @@ #include #include #include +#include +#include #include /* @@ -240,6 +242,8 @@ static inline void check_heap_object(const void *ptr, unsigned long n, } } +static DEFINE_STATIC_KEY_FALSE_RO(bypass_usercopy_checks); + /* * Validates that the given object is: * - not bogus address @@ -248,6 +252,9 @@ static inline void check_heap_object(const void *ptr, unsigned long n, */ void __check_object_size(const void *ptr, unsigned long n, bool to_user) { + if (static_branch_unlikely(&bypass_usercopy_checks)) + return; + /* Skip all tests if size is zero. */ if (!n) return; @@ -279,3 +286,21 @@ void __check_object_size(const void *ptr, unsigned long n, bool to_user) check_kernel_text_object((const unsigned long)ptr, n, to_user); } EXPORT_SYMBOL(__check_object_size); + +static bool enable_checks __initdata = true; + +static int __init parse_hardened_usercopy(char *str) +{ + return strtobool(str, &enable_checks); +} + +__setup("hardened_usercopy=", parse_hardened_usercopy); + +static int __init set_hardened_usercopy(void) +{ + if (enable_checks == false) + static_branch_enable(&bypass_usercopy_checks); + return 1; +} + +late_initcall(set_hardened_usercopy); -- cgit v1.2.3 From 785a19f9d1dd8a4ab2d0633be4656653bd3de1fc Mon Sep 17 00:00:00 2001 From: Chintan Pandya Date: Wed, 27 Jun 2018 08:13:47 -0600 Subject: ioremap: Update pgtable free interfaces with addr The following kernel panic was observed on ARM64 platform due to a stale TLB entry. 1. ioremap with 4K size, a valid pte page table is set. 2. iounmap it, its pte entry is set to 0. 3. ioremap the same address with 2M size, update its pmd entry with a new value. 4. CPU may hit an exception because the old pmd entry is still in TLB, which leads to a kernel panic. Commit b6bdb7517c3d ("mm/vmalloc: add interfaces to free unmapped page table") has addressed this panic by falling to pte mappings in the above case on ARM64. To support pmd mappings in all cases, TLB purge needs to be performed in this case on ARM64. Add a new arg, 'addr', to pud_free_pmd_page() and pmd_free_pte_page() so that TLB purge can be added later in seprate patches. [toshi.kani@hpe.com: merge changes, rewrite patch description] Fixes: 28ee90fe6048 ("x86/mm: implement free pmd/pte page interfaces") Signed-off-by: Chintan Pandya Signed-off-by: Toshi Kani Signed-off-by: Thomas Gleixner Cc: mhocko@suse.com Cc: akpm@linux-foundation.org Cc: hpa@zytor.com Cc: linux-mm@kvack.org Cc: linux-arm-kernel@lists.infradead.org Cc: Will Deacon Cc: Joerg Roedel Cc: stable@vger.kernel.org Cc: Andrew Morton Cc: Michal Hocko Cc: "H. Peter Anvin" Cc: Link: https://lkml.kernel.org/r/20180627141348.21777-3-toshi.kani@hpe.com --- arch/arm64/mm/mmu.c | 4 ++-- arch/x86/mm/pgtable.c | 12 +++++++----- include/asm-generic/pgtable.h | 8 ++++---- lib/ioremap.c | 4 ++-- 4 files changed, 15 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 493ff75670ff..8ae5d7ae4af3 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -977,12 +977,12 @@ int pmd_clear_huge(pmd_t *pmdp) return 1; } -int pud_free_pmd_page(pud_t *pud) +int pud_free_pmd_page(pud_t *pud, unsigned long addr) { return pud_none(*pud); } -int pmd_free_pte_page(pmd_t *pmd) +int pmd_free_pte_page(pmd_t *pmd, unsigned long addr) { return pmd_none(*pmd); } diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 1aeb7a5dbce5..fbd14e506758 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -723,11 +723,12 @@ int pmd_clear_huge(pmd_t *pmd) /** * pud_free_pmd_page - Clear pud entry and free pmd page. * @pud: Pointer to a PUD. + * @addr: Virtual address associated with pud. * * Context: The pud range has been unmaped and TLB purged. * Return: 1 if clearing the entry succeeded. 0 otherwise. */ -int pud_free_pmd_page(pud_t *pud) +int pud_free_pmd_page(pud_t *pud, unsigned long addr) { pmd_t *pmd; int i; @@ -738,7 +739,7 @@ int pud_free_pmd_page(pud_t *pud) pmd = (pmd_t *)pud_page_vaddr(*pud); for (i = 0; i < PTRS_PER_PMD; i++) - if (!pmd_free_pte_page(&pmd[i])) + if (!pmd_free_pte_page(&pmd[i], addr + (i * PMD_SIZE))) return 0; pud_clear(pud); @@ -750,11 +751,12 @@ int pud_free_pmd_page(pud_t *pud) /** * pmd_free_pte_page - Clear pmd entry and free pte page. * @pmd: Pointer to a PMD. + * @addr: Virtual address associated with pmd. * * Context: The pmd range has been unmaped and TLB purged. * Return: 1 if clearing the entry succeeded. 0 otherwise. */ -int pmd_free_pte_page(pmd_t *pmd) +int pmd_free_pte_page(pmd_t *pmd, unsigned long addr) { pte_t *pte; @@ -770,7 +772,7 @@ int pmd_free_pte_page(pmd_t *pmd) #else /* !CONFIG_X86_64 */ -int pud_free_pmd_page(pud_t *pud) +int pud_free_pmd_page(pud_t *pud, unsigned long addr) { return pud_none(*pud); } @@ -779,7 +781,7 @@ int pud_free_pmd_page(pud_t *pud) * Disable free page handling on x86-PAE. This assures that ioremap() * does not update sync'd pmd entries. See vmalloc_sync_one(). */ -int pmd_free_pte_page(pmd_t *pmd) +int pmd_free_pte_page(pmd_t *pmd, unsigned long addr) { return pmd_none(*pmd); } diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index f59639afaa39..b081794ba135 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -1019,8 +1019,8 @@ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot); int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot); int pud_clear_huge(pud_t *pud); int pmd_clear_huge(pmd_t *pmd); -int pud_free_pmd_page(pud_t *pud); -int pmd_free_pte_page(pmd_t *pmd); +int pud_free_pmd_page(pud_t *pud, unsigned long addr); +int pmd_free_pte_page(pmd_t *pmd, unsigned long addr); #else /* !CONFIG_HAVE_ARCH_HUGE_VMAP */ static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot) { @@ -1046,11 +1046,11 @@ static inline int pmd_clear_huge(pmd_t *pmd) { return 0; } -static inline int pud_free_pmd_page(pud_t *pud) +static inline int pud_free_pmd_page(pud_t *pud, unsigned long addr) { return 0; } -static inline int pmd_free_pte_page(pmd_t *pmd) +static inline int pmd_free_pte_page(pmd_t *pmd, unsigned long addr) { return 0; } diff --git a/lib/ioremap.c b/lib/ioremap.c index 54e5bbaa3200..517f5853ffed 100644 --- a/lib/ioremap.c +++ b/lib/ioremap.c @@ -92,7 +92,7 @@ static inline int ioremap_pmd_range(pud_t *pud, unsigned long addr, if (ioremap_pmd_enabled() && ((next - addr) == PMD_SIZE) && IS_ALIGNED(phys_addr + addr, PMD_SIZE) && - pmd_free_pte_page(pmd)) { + pmd_free_pte_page(pmd, addr)) { if (pmd_set_huge(pmd, phys_addr + addr, prot)) continue; } @@ -119,7 +119,7 @@ static inline int ioremap_pud_range(p4d_t *p4d, unsigned long addr, if (ioremap_pud_enabled() && ((next - addr) == PUD_SIZE) && IS_ALIGNED(phys_addr + addr, PUD_SIZE) && - pud_free_pmd_page(pud)) { + pud_free_pmd_page(pud, addr)) { if (pud_set_huge(pud, phys_addr + addr, prot)) continue; } -- cgit v1.2.3 From 6312fe77751f57d4fa2b28abeef84c6a95c28136 Mon Sep 17 00:00:00 2001 From: Li RongQing Date: Thu, 5 Jul 2018 14:34:32 +0800 Subject: net: limit each hash list length to MAX_GRO_SKBS After commit 07d78363dcff ("net: Convert NAPI gro list into a small hash table.")' there is 8 hash buckets, which allows more flows to be held for merging. but MAX_GRO_SKBS, the total held skb for merging, is 8 skb still, limit the hash table performance. keep MAX_GRO_SKBS as 8 skb, but limit each hash list length to 8 skb, not the total 8 skb Signed-off-by: Li RongQing Signed-off-by: David S. Miller --- include/linux/netdevice.h | 7 +++++- net/core/dev.c | 56 +++++++++++++++++++---------------------------- 2 files changed, 29 insertions(+), 34 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f06ee8f91e74..b683971e500d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -302,6 +302,11 @@ struct netdev_boot_setup { int __init netdev_boot_setup(char *str); +struct gro_list { + struct list_head list; + int count; +}; + /* * Structure for NAPI scheduling similar to tasklet but with weighting */ @@ -323,7 +328,7 @@ struct napi_struct { int poll_owner; #endif struct net_device *dev; - struct list_head gro_hash[GRO_HASH_BUCKETS]; + struct gro_list gro_hash[GRO_HASH_BUCKETS]; struct sk_buff *skb; struct hrtimer timer; struct list_head dev_list; diff --git a/net/core/dev.c b/net/core/dev.c index 7e6a2f66db5c..89825c1eccdc 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -149,7 +149,6 @@ #include "net-sysfs.h" -/* Instead of increasing this, you should create a hash table. */ #define MAX_GRO_SKBS 8 /* This should be increased if a protocol with a bigger head is added. */ @@ -5151,9 +5150,10 @@ out: return netif_receive_skb_internal(skb); } -static void __napi_gro_flush_chain(struct napi_struct *napi, struct list_head *head, +static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index, bool flush_old) { + struct list_head *head = &napi->gro_hash[index].list; struct sk_buff *skb, *p; list_for_each_entry_safe_reverse(skb, p, head, list) { @@ -5162,22 +5162,20 @@ static void __napi_gro_flush_chain(struct napi_struct *napi, struct list_head *h list_del_init(&skb->list); napi_gro_complete(skb); napi->gro_count--; + napi->gro_hash[index].count--; } } -/* napi->gro_hash contains packets ordered by age. +/* napi->gro_hash[].list contains packets ordered by age. * youngest packets at the head of it. * Complete skbs in reverse order to reduce latencies. */ void napi_gro_flush(struct napi_struct *napi, bool flush_old) { - int i; - - for (i = 0; i < GRO_HASH_BUCKETS; i++) { - struct list_head *head = &napi->gro_hash[i]; + u32 i; - __napi_gro_flush_chain(napi, head, flush_old); - } + for (i = 0; i < GRO_HASH_BUCKETS; i++) + __napi_gro_flush_chain(napi, i, flush_old); } EXPORT_SYMBOL(napi_gro_flush); @@ -5189,7 +5187,7 @@ static struct list_head *gro_list_prepare(struct napi_struct *napi, struct list_head *head; struct sk_buff *p; - head = &napi->gro_hash[hash & (GRO_HASH_BUCKETS - 1)]; + head = &napi->gro_hash[hash & (GRO_HASH_BUCKETS - 1)].list; list_for_each_entry(p, head, list) { unsigned long diffs; @@ -5257,27 +5255,13 @@ static void gro_pull_from_frag0(struct sk_buff *skb, int grow) } } -static void gro_flush_oldest(struct napi_struct *napi) +static void gro_flush_oldest(struct list_head *head) { - struct sk_buff *oldest = NULL; - unsigned long age = jiffies; - int i; - - for (i = 0; i < GRO_HASH_BUCKETS; i++) { - struct list_head *head = &napi->gro_hash[i]; - struct sk_buff *skb; - - if (list_empty(head)) - continue; + struct sk_buff *oldest; - skb = list_last_entry(head, struct sk_buff, list); - if (!oldest || time_before(NAPI_GRO_CB(skb)->age, age)) { - oldest = skb; - age = NAPI_GRO_CB(skb)->age; - } - } + oldest = list_last_entry(head, struct sk_buff, list); - /* We are called with napi->gro_count >= MAX_GRO_SKBS, so this is + /* We are called with head length >= MAX_GRO_SKBS, so this is * impossible. */ if (WARN_ON_ONCE(!oldest)) @@ -5292,6 +5276,7 @@ static void gro_flush_oldest(struct napi_struct *napi) static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { + u32 hash = skb_get_hash_raw(skb) & (GRO_HASH_BUCKETS - 1); struct list_head *head = &offload_base; struct packet_offload *ptype; __be16 type = skb->protocol; @@ -5358,6 +5343,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff list_del_init(&pp->list); napi_gro_complete(pp); napi->gro_count--; + napi->gro_hash[hash].count--; } if (same_flow) @@ -5366,10 +5352,11 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff if (NAPI_GRO_CB(skb)->flush) goto normal; - if (unlikely(napi->gro_count >= MAX_GRO_SKBS)) { - gro_flush_oldest(napi); + if (unlikely(napi->gro_hash[hash].count >= MAX_GRO_SKBS)) { + gro_flush_oldest(gro_head); } else { napi->gro_count++; + napi->gro_hash[hash].count++; } NAPI_GRO_CB(skb)->count = 1; NAPI_GRO_CB(skb)->age = jiffies; @@ -6006,8 +5993,10 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi, hrtimer_init(&napi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED); napi->timer.function = napi_watchdog; napi->gro_count = 0; - for (i = 0; i < GRO_HASH_BUCKETS; i++) - INIT_LIST_HEAD(&napi->gro_hash[i]); + for (i = 0; i < GRO_HASH_BUCKETS; i++) { + INIT_LIST_HEAD(&napi->gro_hash[i].list); + napi->gro_hash[i].count = 0; + } napi->skb = NULL; napi->poll = poll; if (weight > NAPI_POLL_WEIGHT) @@ -6047,8 +6036,9 @@ static void flush_gro_hash(struct napi_struct *napi) for (i = 0; i < GRO_HASH_BUCKETS; i++) { struct sk_buff *skb, *n; - list_for_each_entry_safe(skb, n, &napi->gro_hash[i], list) + list_for_each_entry_safe(skb, n, &napi->gro_hash[i].list, list) kfree_skb(skb); + napi->gro_hash[i].count = 0; } } -- cgit v1.2.3 From eabaef1896bc06319461a644e3aa139885454def Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Wed, 4 Jul 2018 14:30:28 +0300 Subject: devlink: Add devlink_param register and unregister Define configuration parameters data structure. Add functions to register and unregister the driver supported configuration parameters table. For each parameter registered, the driver should fill all the parameter's fields. In case the only supported configuration mode is "driverinit" the parameter's get()/set() functions are not required and should be set to NULL, for any other configuration mode, these functions are required and should be set by the driver. Signed-off-by: Moshe Shemesh Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/devlink.h | 85 +++++++++++++++++++++++++ include/uapi/linux/devlink.h | 10 +++ net/core/devlink.c | 148 +++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 243 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index e336ea9c73df..4a0687a1fb99 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -27,6 +27,7 @@ struct devlink { struct list_head sb_list; struct list_head dpipe_table_list; struct list_head resource_list; + struct list_head param_list; struct devlink_dpipe_headers *dpipe_headers; const struct devlink_ops *ops; struct device *dev; @@ -295,6 +296,68 @@ struct devlink_resource { #define DEVLINK_RESOURCE_ID_PARENT_TOP 0 +#define DEVLINK_PARAM_MAX_STRING_VALUE 32 +enum devlink_param_type { + DEVLINK_PARAM_TYPE_U8, + DEVLINK_PARAM_TYPE_U16, + DEVLINK_PARAM_TYPE_U32, + DEVLINK_PARAM_TYPE_STRING, + DEVLINK_PARAM_TYPE_BOOL, +}; + +union devlink_param_value { + u8 vu8; + u16 vu16; + u32 vu32; + const char *vstr; + bool vbool; +}; + +struct devlink_param_gset_ctx { + union devlink_param_value val; + enum devlink_param_cmode cmode; +}; + +/** + * struct devlink_param - devlink configuration parameter data + * @name: name of the parameter + * @generic: indicates if the parameter is generic or driver specific + * @type: parameter type + * @supported_cmodes: bitmap of supported configuration modes + * @get: get parameter value, used for runtime and permanent + * configuration modes + * @set: set parameter value, used for runtime and permanent + * configuration modes + * + * This struct should be used by the driver to fill the data for + * a parameter it registers. + */ +struct devlink_param { + u32 id; + const char *name; + bool generic; + enum devlink_param_type type; + unsigned long supported_cmodes; + int (*get)(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx); + int (*set)(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx); +}; + +struct devlink_param_item { + struct list_head list; + const struct devlink_param *param; + union devlink_param_value driverinit_value; + bool driverinit_value_valid; +}; + +enum devlink_param_generic_id { + + /* add new param generic ids above here*/ + __DEVLINK_PARAM_GENERIC_ID_MAX, + DEVLINK_PARAM_GENERIC_ID_MAX = __DEVLINK_PARAM_GENERIC_ID_MAX - 1, +}; + struct devlink_ops { int (*reload)(struct devlink *devlink, struct netlink_ext_ack *extack); int (*port_type_set)(struct devlink_port *devlink_port, @@ -430,6 +493,12 @@ void devlink_resource_occ_get_register(struct devlink *devlink, void *occ_get_priv); void devlink_resource_occ_get_unregister(struct devlink *devlink, u64 resource_id); +int devlink_params_register(struct devlink *devlink, + const struct devlink_param *params, + size_t params_count); +void devlink_params_unregister(struct devlink *devlink, + const struct devlink_param *params, + size_t params_count); #else @@ -622,6 +691,22 @@ devlink_resource_occ_get_unregister(struct devlink *devlink, { } +static inline int +devlink_params_register(struct devlink *devlink, + const struct devlink_param *params, + size_t params_count) +{ + return 0; +} + +static inline void +devlink_params_unregister(struct devlink *devlink, + const struct devlink_param *params, + size_t params_count) +{ + +} + #endif #endif /* _NET_DEVLINK_H_ */ diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 75cb5450c851..d814fa67c7b9 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -142,6 +142,16 @@ enum devlink_port_flavour { */ }; +enum devlink_param_cmode { + DEVLINK_PARAM_CMODE_RUNTIME, + DEVLINK_PARAM_CMODE_DRIVERINIT, + DEVLINK_PARAM_CMODE_PERMANENT, + + /* Add new configuration modes above */ + __DEVLINK_PARAM_CMODE_MAX, + DEVLINK_PARAM_CMODE_MAX = __DEVLINK_PARAM_CMODE_MAX - 1 +}; + enum devlink_attr { /* don't change the order or add anything between, this is ABI! */ DEVLINK_ATTR_UNSPEC, diff --git a/net/core/devlink.c b/net/core/devlink.c index 22099705cc41..41b1a5d1c992 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -2604,6 +2604,82 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) return devlink->ops->reload(devlink, info->extack); } +static const struct devlink_param devlink_param_generic[] = {}; + +static int devlink_param_generic_verify(const struct devlink_param *param) +{ + /* verify it match generic parameter by id and name */ + if (param->id > DEVLINK_PARAM_GENERIC_ID_MAX) + return -EINVAL; + if (strcmp(param->name, devlink_param_generic[param->id].name)) + return -ENOENT; + + WARN_ON(param->type != devlink_param_generic[param->id].type); + + return 0; +} + +static int devlink_param_driver_verify(const struct devlink_param *param) +{ + int i; + + if (param->id <= DEVLINK_PARAM_GENERIC_ID_MAX) + return -EINVAL; + /* verify no such name in generic params */ + for (i = 0; i <= DEVLINK_PARAM_GENERIC_ID_MAX; i++) + if (!strcmp(param->name, devlink_param_generic[i].name)) + return -EEXIST; + + return 0; +} + +static struct devlink_param_item * +devlink_param_find_by_name(struct list_head *param_list, + const char *param_name) +{ + struct devlink_param_item *param_item; + + list_for_each_entry(param_item, param_list, list) + if (!strcmp(param_item->param->name, param_name)) + return param_item; + return NULL; +} + +static int devlink_param_register_one(struct devlink *devlink, + const struct devlink_param *param) +{ + struct devlink_param_item *param_item; + + if (devlink_param_find_by_name(&devlink->param_list, + param->name)) + return -EEXIST; + + if (param->supported_cmodes == BIT(DEVLINK_PARAM_CMODE_DRIVERINIT)) + WARN_ON(param->get || param->set); + else + WARN_ON(!param->get || !param->set); + + param_item = kzalloc(sizeof(*param_item), GFP_KERNEL); + if (!param_item) + return -ENOMEM; + param_item->param = param; + + list_add_tail(¶m_item->list, &devlink->param_list); + return 0; +} + +static void devlink_param_unregister_one(struct devlink *devlink, + const struct devlink_param *param) +{ + struct devlink_param_item *param_item; + + param_item = devlink_param_find_by_name(&devlink->param_list, + param->name); + WARN_ON(!param_item); + list_del(¶m_item->list); + kfree(param_item); +} + static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING }, @@ -2845,6 +2921,7 @@ struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size) INIT_LIST_HEAD(&devlink->sb_list); INIT_LIST_HEAD_RCU(&devlink->dpipe_table_list); INIT_LIST_HEAD(&devlink->resource_list); + INIT_LIST_HEAD(&devlink->param_list); mutex_init(&devlink->lock); return devlink; } @@ -3434,6 +3511,77 @@ out: } EXPORT_SYMBOL_GPL(devlink_resource_occ_get_unregister); +/** + * devlink_params_register - register configuration parameters + * + * @devlink: devlink + * @params: configuration parameters array + * @params_count: number of parameters provided + * + * Register the configuration parameters supported by the driver. + */ +int devlink_params_register(struct devlink *devlink, + const struct devlink_param *params, + size_t params_count) +{ + const struct devlink_param *param = params; + int i; + int err; + + mutex_lock(&devlink->lock); + for (i = 0; i < params_count; i++, param++) { + if (!param || !param->name || !param->supported_cmodes) { + err = -EINVAL; + goto rollback; + } + if (param->generic) { + err = devlink_param_generic_verify(param); + if (err) + goto rollback; + } else { + err = devlink_param_driver_verify(param); + if (err) + goto rollback; + } + err = devlink_param_register_one(devlink, param); + if (err) + goto rollback; + } + + mutex_unlock(&devlink->lock); + return 0; + +rollback: + if (!i) + goto unlock; + for (param--; i > 0; i--, param--) + devlink_param_unregister_one(devlink, param); +unlock: + mutex_unlock(&devlink->lock); + return err; +} +EXPORT_SYMBOL_GPL(devlink_params_register); + +/** + * devlink_params_unregister - unregister configuration parameters + * @devlink: devlink + * @params: configuration parameters to unregister + * @params_count: number of parameters provided + */ +void devlink_params_unregister(struct devlink *devlink, + const struct devlink_param *params, + size_t params_count) +{ + const struct devlink_param *param = params; + int i; + + mutex_lock(&devlink->lock); + for (i = 0; i < params_count; i++, param++) + devlink_param_unregister_one(devlink, param); + mutex_unlock(&devlink->lock); +} +EXPORT_SYMBOL_GPL(devlink_params_unregister); + static int __init devlink_module_init(void) { return genl_register_family(&devlink_nl_family); -- cgit v1.2.3 From 45f05def5c44c806f094709f1c9b03dcecdd54f0 Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Wed, 4 Jul 2018 14:30:29 +0300 Subject: devlink: Add param get command Add param get command which gets data per parameter. Option to dump the parameters data per device. Signed-off-by: Moshe Shemesh Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/uapi/linux/devlink.h | 11 ++ net/core/devlink.c | 250 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 261 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index d814fa67c7b9..2ccfe84176bf 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -78,6 +78,8 @@ enum devlink_command { */ DEVLINK_CMD_RELOAD, + DEVLINK_CMD_PARAM_GET, /* can dump */ + /* add new commands above here */ __DEVLINK_CMD_MAX, DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1 @@ -248,6 +250,15 @@ enum devlink_attr { DEVLINK_ATTR_PORT_NUMBER, /* u32 */ DEVLINK_ATTR_PORT_SPLIT_SUBPORT_NUMBER, /* u32 */ + DEVLINK_ATTR_PARAM, /* nested */ + DEVLINK_ATTR_PARAM_NAME, /* string */ + DEVLINK_ATTR_PARAM_GENERIC, /* flag */ + DEVLINK_ATTR_PARAM_TYPE, /* u8 */ + DEVLINK_ATTR_PARAM_VALUES_LIST, /* nested */ + DEVLINK_ATTR_PARAM_VALUE, /* nested */ + DEVLINK_ATTR_PARAM_VALUE_DATA, /* dynamic */ + DEVLINK_ATTR_PARAM_VALUE_CMODE, /* u8 */ + /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, diff --git a/net/core/devlink.c b/net/core/devlink.c index 41b1a5d1c992..b22d41275f0b 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -2645,6 +2645,248 @@ devlink_param_find_by_name(struct list_head *param_list, return NULL; } +static bool +devlink_param_cmode_is_supported(const struct devlink_param *param, + enum devlink_param_cmode cmode) +{ + return test_bit(cmode, ¶m->supported_cmodes); +} + +static int devlink_param_get(struct devlink *devlink, + const struct devlink_param *param, + struct devlink_param_gset_ctx *ctx) +{ + if (!param->get) + return -EOPNOTSUPP; + return param->get(devlink, param->id, ctx); +} + +static int +devlink_param_type_to_nla_type(enum devlink_param_type param_type) +{ + switch (param_type) { + case DEVLINK_PARAM_TYPE_U8: + return NLA_U8; + case DEVLINK_PARAM_TYPE_U16: + return NLA_U16; + case DEVLINK_PARAM_TYPE_U32: + return NLA_U32; + case DEVLINK_PARAM_TYPE_STRING: + return NLA_STRING; + case DEVLINK_PARAM_TYPE_BOOL: + return NLA_FLAG; + default: + return -EINVAL; + } +} + +static int +devlink_nl_param_value_fill_one(struct sk_buff *msg, + enum devlink_param_type type, + enum devlink_param_cmode cmode, + union devlink_param_value val) +{ + struct nlattr *param_value_attr; + + param_value_attr = nla_nest_start(msg, DEVLINK_ATTR_PARAM_VALUE); + if (!param_value_attr) + goto nla_put_failure; + + if (nla_put_u8(msg, DEVLINK_ATTR_PARAM_VALUE_CMODE, cmode)) + goto value_nest_cancel; + + switch (type) { + case DEVLINK_PARAM_TYPE_U8: + if (nla_put_u8(msg, DEVLINK_ATTR_PARAM_VALUE_DATA, val.vu8)) + goto value_nest_cancel; + break; + case DEVLINK_PARAM_TYPE_U16: + if (nla_put_u16(msg, DEVLINK_ATTR_PARAM_VALUE_DATA, val.vu16)) + goto value_nest_cancel; + break; + case DEVLINK_PARAM_TYPE_U32: + if (nla_put_u32(msg, DEVLINK_ATTR_PARAM_VALUE_DATA, val.vu32)) + goto value_nest_cancel; + break; + case DEVLINK_PARAM_TYPE_STRING: + if (nla_put_string(msg, DEVLINK_ATTR_PARAM_VALUE_DATA, + val.vstr)) + goto value_nest_cancel; + break; + case DEVLINK_PARAM_TYPE_BOOL: + if (val.vbool && + nla_put_flag(msg, DEVLINK_ATTR_PARAM_VALUE_DATA)) + goto value_nest_cancel; + break; + } + + nla_nest_end(msg, param_value_attr); + return 0; + +value_nest_cancel: + nla_nest_cancel(msg, param_value_attr); +nla_put_failure: + return -EMSGSIZE; +} + +static int devlink_nl_param_fill(struct sk_buff *msg, struct devlink *devlink, + struct devlink_param_item *param_item, + enum devlink_command cmd, + u32 portid, u32 seq, int flags) +{ + union devlink_param_value param_value[DEVLINK_PARAM_CMODE_MAX + 1]; + const struct devlink_param *param = param_item->param; + struct devlink_param_gset_ctx ctx; + struct nlattr *param_values_list; + struct nlattr *param_attr; + int nla_type; + void *hdr; + int err; + int i; + + /* Get value from driver part to driverinit configuration mode */ + for (i = 0; i <= DEVLINK_PARAM_CMODE_MAX; i++) { + if (!devlink_param_cmode_is_supported(param, i)) + continue; + if (i == DEVLINK_PARAM_CMODE_DRIVERINIT) { + if (!param_item->driverinit_value_valid) + return -EOPNOTSUPP; + param_value[i] = param_item->driverinit_value; + } else { + ctx.cmode = i; + err = devlink_param_get(devlink, param, &ctx); + if (err) + return err; + param_value[i] = ctx.val; + } + } + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + if (devlink_nl_put_handle(msg, devlink)) + goto genlmsg_cancel; + param_attr = nla_nest_start(msg, DEVLINK_ATTR_PARAM); + if (!param_attr) + goto genlmsg_cancel; + if (nla_put_string(msg, DEVLINK_ATTR_PARAM_NAME, param->name)) + goto param_nest_cancel; + if (param->generic && nla_put_flag(msg, DEVLINK_ATTR_PARAM_GENERIC)) + goto param_nest_cancel; + + nla_type = devlink_param_type_to_nla_type(param->type); + if (nla_type < 0) + goto param_nest_cancel; + if (nla_put_u8(msg, DEVLINK_ATTR_PARAM_TYPE, nla_type)) + goto param_nest_cancel; + + param_values_list = nla_nest_start(msg, DEVLINK_ATTR_PARAM_VALUES_LIST); + if (!param_values_list) + goto param_nest_cancel; + + for (i = 0; i <= DEVLINK_PARAM_CMODE_MAX; i++) { + if (!devlink_param_cmode_is_supported(param, i)) + continue; + err = devlink_nl_param_value_fill_one(msg, param->type, + i, param_value[i]); + if (err) + goto values_list_nest_cancel; + } + + nla_nest_end(msg, param_values_list); + nla_nest_end(msg, param_attr); + genlmsg_end(msg, hdr); + return 0; + +values_list_nest_cancel: + nla_nest_end(msg, param_values_list); +param_nest_cancel: + nla_nest_cancel(msg, param_attr); +genlmsg_cancel: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static int devlink_nl_cmd_param_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + struct devlink_param_item *param_item; + struct devlink *devlink; + int start = cb->args[0]; + int idx = 0; + int err; + + mutex_lock(&devlink_mutex); + list_for_each_entry(devlink, &devlink_list, list) { + if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + continue; + mutex_lock(&devlink->lock); + list_for_each_entry(param_item, &devlink->param_list, list) { + if (idx < start) { + idx++; + continue; + } + err = devlink_nl_param_fill(msg, devlink, param_item, + DEVLINK_CMD_PARAM_GET, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI); + if (err) { + mutex_unlock(&devlink->lock); + goto out; + } + idx++; + } + mutex_unlock(&devlink->lock); + } +out: + mutex_unlock(&devlink_mutex); + + cb->args[0] = idx; + return msg->len; +} + +static struct devlink_param_item * +devlink_param_get_from_info(struct devlink *devlink, + struct genl_info *info) +{ + char *param_name; + + if (!info->attrs[DEVLINK_ATTR_PARAM_NAME]) + return NULL; + + param_name = nla_data(info->attrs[DEVLINK_ATTR_PARAM_NAME]); + return devlink_param_find_by_name(&devlink->param_list, param_name); +} + +static int devlink_nl_cmd_param_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_param_item *param_item; + struct sk_buff *msg; + int err; + + param_item = devlink_param_get_from_info(devlink, info); + if (!param_item) + return -EINVAL; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_param_fill(msg, devlink, param_item, + DEVLINK_CMD_PARAM_GET, + info->snd_portid, info->snd_seq, 0); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + static int devlink_param_register_one(struct devlink *devlink, const struct devlink_param *param) { @@ -2883,6 +3125,14 @@ static const struct genl_ops devlink_nl_ops[] = { .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK | DEVLINK_NL_FLAG_NO_LOCK, }, + { + .cmd = DEVLINK_CMD_PARAM_GET, + .doit = devlink_nl_cmd_param_get_doit, + .dumpit = devlink_nl_cmd_param_get_dumpit, + .policy = devlink_nl_policy, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + /* can be retrieved by unprivileged users */ + }, }; static struct genl_family devlink_nl_family __ro_after_init = { -- cgit v1.2.3 From e3b7ca18ad7b2f47ebd3b6e6ce58a42c6ec24746 Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Wed, 4 Jul 2018 14:30:30 +0300 Subject: devlink: Add param set command Add param set command to set value for a parameter. Value can be set to any of the supported configuration modes. Signed-off-by: Moshe Shemesh Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/devlink.h | 4 ++ include/uapi/linux/devlink.h | 1 + net/core/devlink.c | 134 +++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 139 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 4a0687a1fb99..88062752dcd7 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -328,6 +328,7 @@ struct devlink_param_gset_ctx { * configuration modes * @set: set parameter value, used for runtime and permanent * configuration modes + * @validate: validate input value is applicable (within value range, etc.) * * This struct should be used by the driver to fill the data for * a parameter it registers. @@ -342,6 +343,9 @@ struct devlink_param { struct devlink_param_gset_ctx *ctx); int (*set)(struct devlink *devlink, u32 id, struct devlink_param_gset_ctx *ctx); + int (*validate)(struct devlink *devlink, u32 id, + union devlink_param_value val, + struct netlink_ext_ack *extack); }; struct devlink_param_item { diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 2ccfe84176bf..ea0623e568f0 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -79,6 +79,7 @@ enum devlink_command { DEVLINK_CMD_RELOAD, DEVLINK_CMD_PARAM_GET, /* can dump */ + DEVLINK_CMD_PARAM_SET, /* add new commands above here */ __DEVLINK_CMD_MAX, diff --git a/net/core/devlink.c b/net/core/devlink.c index b22d41275f0b..0cd7a42dcec2 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -2661,6 +2661,15 @@ static int devlink_param_get(struct devlink *devlink, return param->get(devlink, param->id, ctx); } +static int devlink_param_set(struct devlink *devlink, + const struct devlink_param *param, + struct devlink_param_gset_ctx *ctx) +{ + if (!param->set) + return -EOPNOTSUPP; + return param->set(devlink, param->id, ctx); +} + static int devlink_param_type_to_nla_type(enum devlink_param_type param_type) { @@ -2847,6 +2856,69 @@ out: return msg->len; } +static int +devlink_param_type_get_from_info(struct genl_info *info, + enum devlink_param_type *param_type) +{ + if (!info->attrs[DEVLINK_ATTR_PARAM_TYPE]) + return -EINVAL; + + switch (nla_get_u8(info->attrs[DEVLINK_ATTR_PARAM_TYPE])) { + case NLA_U8: + *param_type = DEVLINK_PARAM_TYPE_U8; + break; + case NLA_U16: + *param_type = DEVLINK_PARAM_TYPE_U16; + break; + case NLA_U32: + *param_type = DEVLINK_PARAM_TYPE_U32; + break; + case NLA_STRING: + *param_type = DEVLINK_PARAM_TYPE_STRING; + break; + case NLA_FLAG: + *param_type = DEVLINK_PARAM_TYPE_BOOL; + break; + default: + return -EINVAL; + } + + return 0; +} + +static int +devlink_param_value_get_from_info(const struct devlink_param *param, + struct genl_info *info, + union devlink_param_value *value) +{ + if (param->type != DEVLINK_PARAM_TYPE_BOOL && + !info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]) + return -EINVAL; + + switch (param->type) { + case DEVLINK_PARAM_TYPE_U8: + value->vu8 = nla_get_u8(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]); + break; + case DEVLINK_PARAM_TYPE_U16: + value->vu16 = nla_get_u16(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]); + break; + case DEVLINK_PARAM_TYPE_U32: + value->vu32 = nla_get_u32(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]); + break; + case DEVLINK_PARAM_TYPE_STRING: + if (nla_len(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]) > + DEVLINK_PARAM_MAX_STRING_VALUE) + return -EINVAL; + value->vstr = nla_data(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]); + break; + case DEVLINK_PARAM_TYPE_BOOL: + value->vbool = info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA] ? + true : false; + break; + } + return 0; +} + static struct devlink_param_item * devlink_param_get_from_info(struct devlink *devlink, struct genl_info *info) @@ -2887,6 +2959,58 @@ static int devlink_nl_cmd_param_get_doit(struct sk_buff *skb, return genlmsg_reply(msg, info); } +static int devlink_nl_cmd_param_set_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + enum devlink_param_type param_type; + struct devlink_param_gset_ctx ctx; + enum devlink_param_cmode cmode; + struct devlink_param_item *param_item; + const struct devlink_param *param; + union devlink_param_value value; + int err = 0; + + param_item = devlink_param_get_from_info(devlink, info); + if (!param_item) + return -EINVAL; + param = param_item->param; + err = devlink_param_type_get_from_info(info, ¶m_type); + if (err) + return err; + if (param_type != param->type) + return -EINVAL; + err = devlink_param_value_get_from_info(param, info, &value); + if (err) + return err; + if (param->validate) { + err = param->validate(devlink, param->id, value, info->extack); + if (err) + return err; + } + + if (!info->attrs[DEVLINK_ATTR_PARAM_VALUE_CMODE]) + return -EINVAL; + cmode = nla_get_u8(info->attrs[DEVLINK_ATTR_PARAM_VALUE_CMODE]); + if (!devlink_param_cmode_is_supported(param, cmode)) + return -EOPNOTSUPP; + + if (cmode == DEVLINK_PARAM_CMODE_DRIVERINIT) { + param_item->driverinit_value = value; + param_item->driverinit_value_valid = true; + } else { + if (!param->set) + return -EOPNOTSUPP; + ctx.val = value; + ctx.cmode = cmode; + err = devlink_param_set(devlink, param, &ctx); + if (err) + return err; + } + + return 0; +} + static int devlink_param_register_one(struct devlink *devlink, const struct devlink_param *param) { @@ -2942,6 +3066,9 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED] = { .type = NLA_U8 }, [DEVLINK_ATTR_RESOURCE_ID] = { .type = NLA_U64}, [DEVLINK_ATTR_RESOURCE_SIZE] = { .type = NLA_U64}, + [DEVLINK_ATTR_PARAM_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_PARAM_TYPE] = { .type = NLA_U8 }, + [DEVLINK_ATTR_PARAM_VALUE_CMODE] = { .type = NLA_U8 }, }; static const struct genl_ops devlink_nl_ops[] = { @@ -3133,6 +3260,13 @@ static const struct genl_ops devlink_nl_ops[] = { .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, /* can be retrieved by unprivileged users */ }, + { + .cmd = DEVLINK_CMD_PARAM_SET, + .doit = devlink_nl_cmd_param_set_doit, + .policy = devlink_nl_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + }, }; static struct genl_family devlink_nl_family __ro_after_init = { -- cgit v1.2.3 From ec01aeb1803eaaf0d006e7b07b5ddb5e429c38a4 Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Wed, 4 Jul 2018 14:30:31 +0300 Subject: devlink: Add support for get/set driverinit value "driverinit" configuration mode value is held by devlink to enable the driver query the value after reload. Two additional functions added to help the driver get/set the value from/to devlink: devlink_param_driverinit_value_set() and devlink_param_driverinit_value_get(). Signed-off-by: Moshe Shemesh Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/devlink.h | 18 ++++++++++++ net/core/devlink.c | 77 +++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 95 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 88062752dcd7..3302e43b09a4 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -503,6 +503,10 @@ int devlink_params_register(struct devlink *devlink, void devlink_params_unregister(struct devlink *devlink, const struct devlink_param *params, size_t params_count); +int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id, + union devlink_param_value *init_val); +int devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id, + union devlink_param_value init_val); #else @@ -711,6 +715,20 @@ devlink_params_unregister(struct devlink *devlink, } +static inline int +devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id, + union devlink_param_value *init_val) +{ + return -EOPNOTSUPP; +} + +static inline int +devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id, + union devlink_param_value init_val) +{ + return -EOPNOTSUPP; +} + #endif #endif /* _NET_DEVLINK_H_ */ diff --git a/net/core/devlink.c b/net/core/devlink.c index 0cd7a42dcec2..3af08f4562b5 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -2645,6 +2645,17 @@ devlink_param_find_by_name(struct list_head *param_list, return NULL; } +static struct devlink_param_item * +devlink_param_find_by_id(struct list_head *param_list, u32 param_id) +{ + struct devlink_param_item *param_item; + + list_for_each_entry(param_item, param_list, list) + if (param_item->param->id == param_id) + return param_item; + return NULL; +} + static bool devlink_param_cmode_is_supported(const struct devlink_param *param, enum devlink_param_cmode cmode) @@ -3966,6 +3977,72 @@ void devlink_params_unregister(struct devlink *devlink, } EXPORT_SYMBOL_GPL(devlink_params_unregister); +/** + * devlink_param_driverinit_value_get - get configuration parameter + * value for driver initializing + * + * @devlink: devlink + * @param_id: parameter ID + * @init_val: value of parameter in driverinit configuration mode + * + * This function should be used by the driver to get driverinit + * configuration for initialization after reload command. + */ +int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id, + union devlink_param_value *init_val) +{ + struct devlink_param_item *param_item; + + if (!devlink->ops || !devlink->ops->reload) + return -EOPNOTSUPP; + + param_item = devlink_param_find_by_id(&devlink->param_list, param_id); + if (!param_item) + return -EINVAL; + + if (!param_item->driverinit_value_valid || + !devlink_param_cmode_is_supported(param_item->param, + DEVLINK_PARAM_CMODE_DRIVERINIT)) + return -EOPNOTSUPP; + + *init_val = param_item->driverinit_value; + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_param_driverinit_value_get); + +/** + * devlink_param_driverinit_value_set - set value of configuration + * parameter for driverinit + * configuration mode + * + * @devlink: devlink + * @param_id: parameter ID + * @init_val: value of parameter to set for driverinit configuration mode + * + * This function should be used by the driver to set driverinit + * configuration mode default value. + */ +int devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id, + union devlink_param_value init_val) +{ + struct devlink_param_item *param_item; + + param_item = devlink_param_find_by_id(&devlink->param_list, param_id); + if (!param_item) + return -EINVAL; + + if (!devlink_param_cmode_is_supported(param_item->param, + DEVLINK_PARAM_CMODE_DRIVERINIT)) + return -EOPNOTSUPP; + + param_item->driverinit_value = init_val; + param_item->driverinit_value_valid = true; + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_param_driverinit_value_set); + static int __init devlink_module_init(void) { return genl_register_family(&devlink_nl_family); -- cgit v1.2.3 From ea601e17098856ee059f35c2a75659e57df81f25 Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Wed, 4 Jul 2018 14:30:32 +0300 Subject: devlink: Add devlink notifications support for params Add devlink_param_notify() function to support devlink param notifications. Add notification call to devlink param set, register and unregister functions. Add devlink_param_value_changed() function to enable the driver notify devlink on value change. Driver should use this function after value was changed on any configuration mode part to driverinit. Signed-off-by: Moshe Shemesh Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/devlink.h | 7 +++++++ include/uapi/linux/devlink.h | 2 ++ net/core/devlink.c | 50 ++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 59 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 3302e43b09a4..792edaa996ba 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -507,6 +507,7 @@ int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id, union devlink_param_value *init_val); int devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id, union devlink_param_value init_val); +void devlink_param_value_changed(struct devlink *devlink, u32 param_id); #else @@ -729,6 +730,12 @@ devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id, return -EOPNOTSUPP; } +static inline void +devlink_param_value_changed(struct devlink *devlink, u32 param_id) +{ + return -EOPNOTSUPP; +} + #endif #endif /* _NET_DEVLINK_H_ */ diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index ea0623e568f0..68641fb56654 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -80,6 +80,8 @@ enum devlink_command { DEVLINK_CMD_PARAM_GET, /* can dump */ DEVLINK_CMD_PARAM_SET, + DEVLINK_CMD_PARAM_NEW, + DEVLINK_CMD_PARAM_DEL, /* add new commands above here */ __DEVLINK_CMD_MAX, diff --git a/net/core/devlink.c b/net/core/devlink.c index 3af08f4562b5..89d948fd4727 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -2828,6 +2828,28 @@ genlmsg_cancel: return -EMSGSIZE; } +static void devlink_param_notify(struct devlink *devlink, + struct devlink_param_item *param_item, + enum devlink_command cmd) +{ + struct sk_buff *msg; + int err; + + WARN_ON(cmd != DEVLINK_CMD_PARAM_NEW && cmd != DEVLINK_CMD_PARAM_DEL); + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + err = devlink_nl_param_fill(msg, devlink, param_item, cmd, 0, 0, 0); + if (err) { + nlmsg_free(msg); + return; + } + + genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), + msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); +} + static int devlink_nl_cmd_param_get_dumpit(struct sk_buff *msg, struct netlink_callback *cb) { @@ -3019,6 +3041,7 @@ static int devlink_nl_cmd_param_set_doit(struct sk_buff *skb, return err; } + devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_NEW); return 0; } @@ -3042,6 +3065,7 @@ static int devlink_param_register_one(struct devlink *devlink, param_item->param = param; list_add_tail(¶m_item->list, &devlink->param_list); + devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_NEW); return 0; } @@ -3053,6 +3077,7 @@ static void devlink_param_unregister_one(struct devlink *devlink, param_item = devlink_param_find_by_name(&devlink->param_list, param->name); WARN_ON(!param_item); + devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_DEL); list_del(¶m_item->list); kfree(param_item); } @@ -4039,10 +4064,35 @@ int devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id, param_item->driverinit_value = init_val; param_item->driverinit_value_valid = true; + devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_NEW); return 0; } EXPORT_SYMBOL_GPL(devlink_param_driverinit_value_set); +/** + * devlink_param_value_changed - notify devlink on a parameter's value + * change. Should be called by the driver + * right after the change. + * + * @devlink: devlink + * @param_id: parameter ID + * + * This function should be used by the driver to notify devlink on value + * change, excluding driverinit configuration mode. + * For driverinit configuration mode driver should use the function + * devlink_param_driverinit_value_set() instead. + */ +void devlink_param_value_changed(struct devlink *devlink, u32 param_id) +{ + struct devlink_param_item *param_item; + + param_item = devlink_param_find_by_id(&devlink->param_list, param_id); + WARN_ON(!param_item); + + devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_NEW); +} +EXPORT_SYMBOL_GPL(devlink_param_value_changed); + static int __init devlink_module_init(void) { return genl_register_family(&devlink_nl_family); -- cgit v1.2.3 From 036467c3990c75ec8ce97e517a864b52e184a1aa Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Wed, 4 Jul 2018 14:30:33 +0300 Subject: devlink: Add generic parameters internal_err_reset and max_macs Add 2 first generic parameters to devlink configuration parameters set: internal_err_reset - When set enables reset device on internal errors. max_macs - max number of MACs per ETH port. Signed-off-by: Moshe Shemesh Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/devlink.h | 31 +++++++++++++++++++++++++++++++ net/core/devlink.c | 14 +++++++++++++- 2 files changed, 44 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 792edaa996ba..a1c230d18911 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -356,12 +356,43 @@ struct devlink_param_item { }; enum devlink_param_generic_id { + DEVLINK_PARAM_GENERIC_ID_INT_ERR_RESET, + DEVLINK_PARAM_GENERIC_ID_MAX_MACS, /* add new param generic ids above here*/ __DEVLINK_PARAM_GENERIC_ID_MAX, DEVLINK_PARAM_GENERIC_ID_MAX = __DEVLINK_PARAM_GENERIC_ID_MAX - 1, }; +#define DEVLINK_PARAM_GENERIC_INT_ERR_RESET_NAME "internal_error_reset" +#define DEVLINK_PARAM_GENERIC_INT_ERR_RESET_TYPE DEVLINK_PARAM_TYPE_BOOL + +#define DEVLINK_PARAM_GENERIC_MAX_MACS_NAME "max_macs" +#define DEVLINK_PARAM_GENERIC_MAX_MACS_TYPE DEVLINK_PARAM_TYPE_U32 + +#define DEVLINK_PARAM_GENERIC(_id, _cmodes, _get, _set, _validate) \ +{ \ + .id = DEVLINK_PARAM_GENERIC_ID_##_id, \ + .name = DEVLINK_PARAM_GENERIC_##_id##_NAME, \ + .type = DEVLINK_PARAM_GENERIC_##_id##_TYPE, \ + .generic = true, \ + .supported_cmodes = _cmodes, \ + .get = _get, \ + .set = _set, \ + .validate = _validate, \ +} + +#define DEVLINK_PARAM_DRIVER(_id, _name, _type, _cmodes, _get, _set, _validate) \ +{ \ + .id = _id, \ + .name = _name, \ + .type = _type, \ + .supported_cmodes = _cmodes, \ + .get = _get, \ + .set = _set, \ + .validate = _validate, \ +} + struct devlink_ops { int (*reload)(struct devlink *devlink, struct netlink_ext_ack *extack); int (*port_type_set)(struct devlink_port *devlink_port, diff --git a/net/core/devlink.c b/net/core/devlink.c index 89d948fd4727..5bbd0aa7571a 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -2604,7 +2604,19 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) return devlink->ops->reload(devlink, info->extack); } -static const struct devlink_param devlink_param_generic[] = {}; +static const struct devlink_param devlink_param_generic[] = { + { + .id = DEVLINK_PARAM_GENERIC_ID_INT_ERR_RESET, + .name = DEVLINK_PARAM_GENERIC_INT_ERR_RESET_NAME, + .type = DEVLINK_PARAM_GENERIC_INT_ERR_RESET_TYPE, + }, + { + .id = DEVLINK_PARAM_GENERIC_ID_MAX_MACS, + .name = DEVLINK_PARAM_GENERIC_MAX_MACS_NAME, + .type = DEVLINK_PARAM_GENERIC_MAX_MACS_TYPE, + }, + +}; static int devlink_param_generic_verify(const struct devlink_param *param) { -- cgit v1.2.3 From f567bcdae2b052bab94be7903863cb9ab47c907c Mon Sep 17 00:00:00 2001 From: Vasundhara Volam Date: Wed, 4 Jul 2018 14:30:36 +0300 Subject: devlink: Add enable_sriov boolean generic parameter enable_sriov - Enables Single-Root Input/Output Virtualization(SR-IOV) characteristic of the device. Reviewed-by: Michael Chan Signed-off-by: Vasundhara Volam Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/devlink.h | 4 ++++ net/core/devlink.c | 6 +++++- 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index a1c230d18911..8ed571385626 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -358,6 +358,7 @@ struct devlink_param_item { enum devlink_param_generic_id { DEVLINK_PARAM_GENERIC_ID_INT_ERR_RESET, DEVLINK_PARAM_GENERIC_ID_MAX_MACS, + DEVLINK_PARAM_GENERIC_ID_ENABLE_SRIOV, /* add new param generic ids above here*/ __DEVLINK_PARAM_GENERIC_ID_MAX, @@ -370,6 +371,9 @@ enum devlink_param_generic_id { #define DEVLINK_PARAM_GENERIC_MAX_MACS_NAME "max_macs" #define DEVLINK_PARAM_GENERIC_MAX_MACS_TYPE DEVLINK_PARAM_TYPE_U32 +#define DEVLINK_PARAM_GENERIC_ENABLE_SRIOV_NAME "enable_sriov" +#define DEVLINK_PARAM_GENERIC_ENABLE_SRIOV_TYPE DEVLINK_PARAM_TYPE_BOOL + #define DEVLINK_PARAM_GENERIC(_id, _cmodes, _get, _set, _validate) \ { \ .id = DEVLINK_PARAM_GENERIC_ID_##_id, \ diff --git a/net/core/devlink.c b/net/core/devlink.c index 5bbd0aa7571a..470f3dbfecfe 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -2615,7 +2615,11 @@ static const struct devlink_param devlink_param_generic[] = { .name = DEVLINK_PARAM_GENERIC_MAX_MACS_NAME, .type = DEVLINK_PARAM_GENERIC_MAX_MACS_TYPE, }, - + { + .id = DEVLINK_PARAM_GENERIC_ID_ENABLE_SRIOV, + .name = DEVLINK_PARAM_GENERIC_ENABLE_SRIOV_NAME, + .type = DEVLINK_PARAM_GENERIC_ENABLE_SRIOV_TYPE, + }, }; static int devlink_param_generic_verify(const struct devlink_param *param) -- cgit v1.2.3 From 83aefbb887b59df0b3520965c3701e01deacfc52 Mon Sep 17 00:00:00 2001 From: Ville Syrjälä Date: Thu, 28 Jun 2018 16:13:09 +0300 Subject: drm: Add drm_connector_for_each_possible_encoder() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a convenience macro for iterating connector->encoder_ids[]. Isolates the users from the implementation details. Note that we don't seem to pass the file_priv down to drm_encoder_find() because encoders apparently don't get leased. No idea why drm_encoder_finc() even takes the file_priv actually. Also use ARRAY_SIZE() when populating the array to avoid spreading knowledge about the array size all over. v2: Hide the drm_encoder_find() in the macro, and rename the macro appropriately (Daniel) v3: Fix kernel docs (Daniel) Cc: Daniel Vetter Reviewed-by: Alex Deucher Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20180628131315.14156-4-ville.syrjala@linux.intel.com Reviewed-by: Daniel Vetter --- drivers/gpu/drm/drm_connector.c | 21 +++++++++------------ drivers/gpu/drm/drm_fb_helper.c | 11 ++--------- drivers/gpu/drm/drm_probe_helper.c | 10 +++------- include/drm/drm_connector.h | 13 +++++++++++++ 4 files changed, 27 insertions(+), 28 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c index b09b3a3e4024..7387c0377e51 100644 --- a/drivers/gpu/drm/drm_connector.c +++ b/drivers/gpu/drm/drm_connector.c @@ -321,7 +321,7 @@ int drm_mode_connector_attach_encoder(struct drm_connector *connector, if (WARN_ON(connector->encoder)) return -EINVAL; - for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) { + for (i = 0; i < ARRAY_SIZE(connector->encoder_ids); i++) { if (connector->encoder_ids[i] == 0) { connector->encoder_ids[i] = encoder->base.id; return 0; @@ -1706,22 +1706,19 @@ int drm_mode_getconnector(struct drm_device *dev, void *data, if (!connector) return -ENOENT; - for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) - if (connector->encoder_ids[i] != 0) - encoders_count++; + drm_connector_for_each_possible_encoder(connector, encoder, i) + encoders_count++; if ((out_resp->count_encoders >= encoders_count) && encoders_count) { copied = 0; encoder_ptr = (uint32_t __user *)(unsigned long)(out_resp->encoders_ptr); - for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) { - if (connector->encoder_ids[i] != 0) { - if (put_user(connector->encoder_ids[i], - encoder_ptr + copied)) { - ret = -EFAULT; - goto out; - } - copied++; + + drm_connector_for_each_possible_encoder(connector, encoder, i) { + if (put_user(encoder->base.id, encoder_ptr + copied)) { + ret = -EFAULT; + goto out; } + copied++; } } out_resp->count_encoders = encoders_count; diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index b37f06317d51..d697c1c4a067 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -2326,17 +2326,10 @@ retry: static bool connector_has_possible_crtc(struct drm_connector *connector, struct drm_crtc *crtc) { + struct drm_encoder *encoder; int i; - for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) { - struct drm_encoder *encoder; - - if (connector->encoder_ids[i] == 0) - break; - - encoder = drm_encoder_find(connector->dev, NULL, - connector->encoder_ids[i]); - + drm_connector_for_each_possible_encoder(connector, encoder, i) { if (encoder->possible_crtcs & drm_crtc_mask(crtc)) return true; } diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c index 527743394150..1a901fe9e23e 100644 --- a/drivers/gpu/drm/drm_probe_helper.c +++ b/drivers/gpu/drm/drm_probe_helper.c @@ -88,9 +88,9 @@ drm_mode_validate_pipeline(struct drm_display_mode *mode, struct drm_connector *connector) { struct drm_device *dev = connector->dev; - uint32_t *ids = connector->encoder_ids; enum drm_mode_status ret = MODE_OK; - unsigned int i; + struct drm_encoder *encoder; + int i; /* Step 1: Validate against connector */ ret = drm_connector_mode_valid(connector, mode); @@ -98,13 +98,9 @@ drm_mode_validate_pipeline(struct drm_display_mode *mode, return ret; /* Step 2: Validate against encoders and crtcs */ - for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) { - struct drm_encoder *encoder = drm_encoder_find(dev, NULL, ids[i]); + drm_connector_for_each_possible_encoder(connector, encoder, i) { struct drm_crtc *crtc; - if (!encoder) - continue; - ret = drm_encoder_mode_valid(encoder, mode); if (ret != MODE_OK) { /* No point in continuing for crtc check as this encoder diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h index bf0f0f0786d3..bd6f30cf0755 100644 --- a/include/drm/drm_connector.h +++ b/include/drm/drm_connector.h @@ -1199,4 +1199,17 @@ void drm_connector_list_iter_end(struct drm_connector_list_iter *iter); #define drm_for_each_connector_iter(connector, iter) \ while ((connector = drm_connector_list_iter_next(iter))) +/** + * drm_connector_for_each_possible_encoder - iterate connector's possible encoders + * @connector: &struct drm_connector pointer + * @encoder: &struct drm_encoder pointer used as cursor + * @__i: int iteration cursor, for macro-internal use + */ +#define drm_connector_for_each_possible_encoder(connector, encoder, __i) \ + for ((__i) = 0; (__i) < ARRAY_SIZE((connector)->encoder_ids) && \ + (connector)->encoder_ids[(__i)] != 0; (__i)++) \ + for_each_if((encoder) = \ + drm_encoder_find((connector)->dev, NULL, \ + (connector)->encoder_ids[(__i)])) \ + #endif -- cgit v1.2.3 From 38cb8d96933eb07231073efdcd24a6ffa43b23e6 Mon Sep 17 00:00:00 2001 From: Ville Syrjälä Date: Thu, 28 Jun 2018 16:13:13 +0300 Subject: drm: Add drm_connector_has_possible_encoder() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a small helper for checking whether a connector and encoder are associated with each other. Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20180628131315.14156-8-ville.syrjala@linux.intel.com Reviewed-by: Alex Deucher --- drivers/gpu/drm/drm_connector.c | 23 +++++++++++++++++++++++ include/drm/drm_connector.h | 3 +++ 2 files changed, 26 insertions(+) (limited to 'include') diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c index 7387c0377e51..5ada0640de5a 100644 --- a/drivers/gpu/drm/drm_connector.c +++ b/drivers/gpu/drm/drm_connector.c @@ -331,6 +331,29 @@ int drm_mode_connector_attach_encoder(struct drm_connector *connector, } EXPORT_SYMBOL(drm_mode_connector_attach_encoder); +/** + * drm_connector_has_possible_encoder - check if the connector and encoder are assosicated with each other + * @connector: the connector + * @encoder: the encoder + * + * Returns: + * True if @encoder is one of the possible encoders for @connector. + */ +bool drm_connector_has_possible_encoder(struct drm_connector *connector, + struct drm_encoder *encoder) +{ + struct drm_encoder *enc; + int i; + + drm_connector_for_each_possible_encoder(connector, enc, i) { + if (enc == encoder) + return true; + } + + return false; +} +EXPORT_SYMBOL(drm_connector_has_possible_encoder); + static void drm_mode_remove(struct drm_connector *connector, struct drm_display_mode *mode) { diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h index bd6f30cf0755..ad397dfc042b 100644 --- a/include/drm/drm_connector.h +++ b/include/drm/drm_connector.h @@ -1187,6 +1187,9 @@ struct drm_connector * drm_connector_list_iter_next(struct drm_connector_list_iter *iter); void drm_connector_list_iter_end(struct drm_connector_list_iter *iter); +bool drm_connector_has_possible_encoder(struct drm_connector *connector, + struct drm_encoder *encoder); + /** * drm_for_each_connector_iter - connector_list iterator macro * @connector: &struct drm_connector pointer used as cursor -- cgit v1.2.3 From 0380cf7dbaca75c524e34b30979f0806124fa8e6 Mon Sep 17 00:00:00 2001 From: pascal paillet Date: Thu, 5 Jul 2018 14:25:57 +0000 Subject: regulator: core: Change suspend_late to suspend Change suspend_late ops to suspend normal ops. The goal is to avoid requesting all the regulator drivers to be operational in suspend late phase. Signed-off-by: pascal paillet Signed-off-by: Mark Brown --- drivers/regulator/core.c | 26 +++++++++++++------------- include/linux/regulator/driver.h | 2 +- 2 files changed, 14 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 6ed568b96c0e..da9b0fed8330 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -4441,7 +4441,7 @@ void regulator_unregister(struct regulator_dev *rdev) EXPORT_SYMBOL_GPL(regulator_unregister); #ifdef CONFIG_SUSPEND -static int _regulator_suspend_late(struct device *dev, void *data) +static int _regulator_suspend(struct device *dev, void *data) { struct regulator_dev *rdev = dev_to_rdev(dev); suspend_state_t *state = data; @@ -4455,20 +4455,20 @@ static int _regulator_suspend_late(struct device *dev, void *data) } /** - * regulator_suspend_late - prepare regulators for system wide suspend + * regulator_suspend - prepare regulators for system wide suspend * @state: system suspend state * * Configure each regulator with it's suspend operating parameters for state. */ -static int regulator_suspend_late(struct device *dev) +static int regulator_suspend(struct device *dev) { suspend_state_t state = pm_suspend_target_state; return class_for_each_device(®ulator_class, NULL, &state, - _regulator_suspend_late); + _regulator_suspend); } -static int _regulator_resume_early(struct device *dev, void *data) +static int _regulator_resume(struct device *dev, void *data) { int ret = 0; struct regulator_dev *rdev = dev_to_rdev(dev); @@ -4481,35 +4481,35 @@ static int _regulator_resume_early(struct device *dev, void *data) regulator_lock(rdev); - if (rdev->desc->ops->resume_early && + if (rdev->desc->ops->resume && (rstate->enabled == ENABLE_IN_SUSPEND || rstate->enabled == DISABLE_IN_SUSPEND)) - ret = rdev->desc->ops->resume_early(rdev); + ret = rdev->desc->ops->resume(rdev); regulator_unlock(rdev); return ret; } -static int regulator_resume_early(struct device *dev) +static int regulator_resume(struct device *dev) { suspend_state_t state = pm_suspend_target_state; return class_for_each_device(®ulator_class, NULL, &state, - _regulator_resume_early); + _regulator_resume); } #else /* !CONFIG_SUSPEND */ -#define regulator_suspend_late NULL -#define regulator_resume_early NULL +#define regulator_suspend NULL +#define regulator_resume NULL #endif /* !CONFIG_SUSPEND */ #ifdef CONFIG_PM static const struct dev_pm_ops __maybe_unused regulator_pm_ops = { - .suspend_late = regulator_suspend_late, - .resume_early = regulator_resume_early, + .suspend = regulator_suspend, + .resume = regulator_resume, }; #endif diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index dea96ee39fdc..0fd8fbb74763 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -220,7 +220,7 @@ struct regulator_ops { /* set regulator suspend operating mode (defined in consumer.h) */ int (*set_suspend_mode) (struct regulator_dev *, unsigned int mode); - int (*resume_early)(struct regulator_dev *rdev); + int (*resume)(struct regulator_dev *rdev); int (*set_pull_down) (struct regulator_dev *); }; -- cgit v1.2.3 From d8842211b6f63d3f069df973d137de0a85964965 Mon Sep 17 00:00:00 2001 From: pascal paillet Date: Thu, 5 Jul 2018 14:25:56 +0000 Subject: driver core: Add device_link_remove function Device_link_remove uses the same arguments than device_link_add. The Goal is to avoid storing the link pointer. Signed-off-by: pascal paillet Acked-by: Greg Kroah-Hartman Signed-off-by: Mark Brown --- drivers/base/core.c | 30 ++++++++++++++++++++++++++++++ include/linux/device.h | 1 + 2 files changed, 31 insertions(+) (limited to 'include') diff --git a/drivers/base/core.c b/drivers/base/core.c index 36622b52e419..3b380b1f2768 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -365,6 +365,36 @@ void device_link_del(struct device_link *link) } EXPORT_SYMBOL_GPL(device_link_del); +/** + * device_link_remove - remove a link between two devices. + * @consumer: Consumer end of the link. + * @supplier: Supplier end of the link. + * + * The caller must ensure proper synchronization of this function with runtime + * PM. + */ +void device_link_remove(void *consumer, struct device *supplier) +{ + struct device_link *link; + + if (WARN_ON(consumer == supplier)) + return; + + device_links_write_lock(); + device_pm_lock(); + + list_for_each_entry(link, &supplier->links.consumers, s_node) { + if (link->consumer == consumer) { + kref_put(&link->kref, __device_link_del); + break; + } + } + + device_pm_unlock(); + device_links_write_unlock(); +} +EXPORT_SYMBOL_GPL(device_link_remove); + static void device_links_missing_supplier(struct device *dev) { struct device_link *link; diff --git a/include/linux/device.h b/include/linux/device.h index 055a69dbcd18..9c1c3b1d5e11 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1316,6 +1316,7 @@ extern const char *dev_driver_string(const struct device *dev); struct device_link *device_link_add(struct device *consumer, struct device *supplier, u32 flags); void device_link_del(struct device_link *link); +void device_link_remove(void *consumer, struct device *supplier); #ifdef CONFIG_PRINTK -- cgit v1.2.3 From 2282e125a406e09331c5a785e3df29035c99a607 Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Mon, 2 Jul 2018 22:05:21 +0200 Subject: leds: triggers: let struct led_trigger::activate() return an error code MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Given that activating a trigger can fail, let the callback return an indication. This prevents to have a trigger active according to the "trigger" sysfs attribute but not functional. All users are changed accordingly to return 0 for now. There is no intended change in behaviour. Signed-off-by: Uwe Kleine-König Acked-by: Pavel Machek Signed-off-by: Jacek Anaszewski --- drivers/leds/led-triggers.c | 24 +++++++++++++++++++++--- drivers/leds/trigger/ledtrig-activity.c | 8 +++++--- drivers/leds/trigger/ledtrig-backlight.c | 8 +++++--- drivers/leds/trigger/ledtrig-default-on.c | 3 ++- drivers/leds/trigger/ledtrig-gpio.c | 8 +++++--- drivers/leds/trigger/ledtrig-heartbeat.c | 8 +++++--- drivers/leds/trigger/ledtrig-netdev.c | 8 +++++--- drivers/leds/trigger/ledtrig-oneshot.c | 8 +++++--- drivers/leds/trigger/ledtrig-timer.c | 8 +++++--- drivers/leds/trigger/ledtrig-transient.c | 8 +++++--- drivers/tty/vt/keyboard.c | 4 +++- drivers/usb/core/ledtrig-usbport.c | 7 ++++--- include/linux/leds.h | 14 +++++++++----- net/bluetooth/leds.c | 6 ++++-- net/mac80211/led.c | 20 +++++++++++++++----- net/rfkill/core.c | 4 +++- 16 files changed, 101 insertions(+), 45 deletions(-) (limited to 'include') diff --git a/drivers/leds/led-triggers.c b/drivers/leds/led-triggers.c index 431123b048a2..a8786f4b3453 100644 --- a/drivers/leds/led-triggers.c +++ b/drivers/leds/led-triggers.c @@ -103,15 +103,16 @@ ssize_t led_trigger_show(struct device *dev, struct device_attribute *attr, EXPORT_SYMBOL_GPL(led_trigger_show); /* Caller must ensure led_cdev->trigger_lock held */ -void led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trig) +int led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trig) { unsigned long flags; char *event = NULL; char *envp[2]; const char *name; + int ret; if (!led_cdev->trigger && !trig) - return; + return 0; name = trig ? trig->name : "none"; event = kasprintf(GFP_KERNEL, "TRIGGER=%s", name); @@ -134,8 +135,14 @@ void led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trig) list_add_tail(&led_cdev->trig_list, &trig->led_cdevs); write_unlock_irqrestore(&trig->leddev_list_lock, flags); led_cdev->trigger = trig; + if (trig->activate) - trig->activate(led_cdev); + ret = trig->activate(led_cdev); + else + ret = 0; + + if (ret) + goto err_activate; } if (event) { @@ -146,6 +153,17 @@ void led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trig) "%s: Error sending uevent\n", __func__); kfree(event); } + + return 0; + +err_activate: + led_cdev->trigger = NULL; + write_lock_irqsave(&led_cdev->trigger->leddev_list_lock, flags); + list_del(&led_cdev->trig_list); + write_unlock_irqrestore(&led_cdev->trigger->leddev_list_lock, flags); + led_set_brightness(led_cdev, LED_OFF); + + return ret; } EXPORT_SYMBOL_GPL(led_trigger_set); diff --git a/drivers/leds/trigger/ledtrig-activity.c b/drivers/leds/trigger/ledtrig-activity.c index b39e1bb9a9ec..2fc065fb1754 100644 --- a/drivers/leds/trigger/ledtrig-activity.c +++ b/drivers/leds/trigger/ledtrig-activity.c @@ -178,20 +178,20 @@ static ssize_t led_invert_store(struct device *dev, static DEVICE_ATTR(invert, 0644, led_invert_show, led_invert_store); -static void activity_activate(struct led_classdev *led_cdev) +static int activity_activate(struct led_classdev *led_cdev) { struct activity_data *activity_data; int rc; activity_data = kzalloc(sizeof(*activity_data), GFP_KERNEL); if (!activity_data) - return; + return 0; led_cdev->trigger_data = activity_data; rc = device_create_file(led_cdev->dev, &dev_attr_invert); if (rc) { kfree(led_cdev->trigger_data); - return; + return 0; } activity_data->led_cdev = led_cdev; @@ -201,6 +201,8 @@ static void activity_activate(struct led_classdev *led_cdev) led_activity_function(&activity_data->timer); set_bit(LED_BLINK_SW, &led_cdev->work_flags); led_cdev->activated = true; + + return 0; } static void activity_deactivate(struct led_classdev *led_cdev) diff --git a/drivers/leds/trigger/ledtrig-backlight.c b/drivers/leds/trigger/ledtrig-backlight.c index 1ca1f1608f76..84512960d630 100644 --- a/drivers/leds/trigger/ledtrig-backlight.c +++ b/drivers/leds/trigger/ledtrig-backlight.c @@ -97,7 +97,7 @@ static ssize_t bl_trig_invert_store(struct device *dev, } static DEVICE_ATTR(inverted, 0644, bl_trig_invert_show, bl_trig_invert_store); -static void bl_trig_activate(struct led_classdev *led) +static int bl_trig_activate(struct led_classdev *led) { int ret; @@ -107,7 +107,7 @@ static void bl_trig_activate(struct led_classdev *led) led->trigger_data = n; if (!n) { dev_err(led->dev, "unable to allocate backlight trigger\n"); - return; + return 0; } ret = device_create_file(led->dev, &dev_attr_inverted); @@ -124,11 +124,13 @@ static void bl_trig_activate(struct led_classdev *led) dev_err(led->dev, "unable to register backlight trigger\n"); led->activated = true; - return; + return 0; err_invert: led->trigger_data = NULL; kfree(n); + + return 0; } static void bl_trig_deactivate(struct led_classdev *led) diff --git a/drivers/leds/trigger/ledtrig-default-on.c b/drivers/leds/trigger/ledtrig-default-on.c index 4ccea04b7a6b..2996fe672198 100644 --- a/drivers/leds/trigger/ledtrig-default-on.c +++ b/drivers/leds/trigger/ledtrig-default-on.c @@ -16,9 +16,10 @@ #include #include "../leds.h" -static void defon_trig_activate(struct led_classdev *led_cdev) +static int defon_trig_activate(struct led_classdev *led_cdev) { led_set_brightness_nosleep(led_cdev, led_cdev->max_brightness); + return 0; } static struct led_trigger defon_led_trigger = { diff --git a/drivers/leds/trigger/ledtrig-gpio.c b/drivers/leds/trigger/ledtrig-gpio.c index 93906a17a4b6..f5358c40d03f 100644 --- a/drivers/leds/trigger/ledtrig-gpio.c +++ b/drivers/leds/trigger/ledtrig-gpio.c @@ -162,14 +162,14 @@ static ssize_t gpio_trig_gpio_store(struct device *dev, } static DEVICE_ATTR(gpio, 0644, gpio_trig_gpio_show, gpio_trig_gpio_store); -static void gpio_trig_activate(struct led_classdev *led) +static int gpio_trig_activate(struct led_classdev *led) { struct gpio_trig_data *gpio_data; int ret; gpio_data = kzalloc(sizeof(*gpio_data), GFP_KERNEL); if (!gpio_data) - return; + return 0; ret = device_create_file(led->dev, &dev_attr_gpio); if (ret) @@ -187,7 +187,7 @@ static void gpio_trig_activate(struct led_classdev *led) led->trigger_data = gpio_data; led->activated = true; - return; + return 0; err_brightness: device_remove_file(led->dev, &dev_attr_inverted); @@ -197,6 +197,8 @@ err_inverted: err_gpio: kfree(gpio_data); + + return 0; } static void gpio_trig_deactivate(struct led_classdev *led) diff --git a/drivers/leds/trigger/ledtrig-heartbeat.c b/drivers/leds/trigger/ledtrig-heartbeat.c index 304b929edb8e..03a8dfce8fb9 100644 --- a/drivers/leds/trigger/ledtrig-heartbeat.c +++ b/drivers/leds/trigger/ledtrig-heartbeat.c @@ -121,21 +121,21 @@ static ssize_t led_invert_store(struct device *dev, static DEVICE_ATTR(invert, 0644, led_invert_show, led_invert_store); -static void heartbeat_trig_activate(struct led_classdev *led_cdev) +static int heartbeat_trig_activate(struct led_classdev *led_cdev) { struct heartbeat_trig_data *heartbeat_data; int rc; heartbeat_data = kzalloc(sizeof(*heartbeat_data), GFP_KERNEL); if (!heartbeat_data) - return; + return 0; led_cdev->trigger_data = heartbeat_data; heartbeat_data->led_cdev = led_cdev; rc = device_create_file(led_cdev->dev, &dev_attr_invert); if (rc) { kfree(led_cdev->trigger_data); - return; + return 0; } timer_setup(&heartbeat_data->timer, led_heartbeat_function, 0); @@ -145,6 +145,8 @@ static void heartbeat_trig_activate(struct led_classdev *led_cdev) led_heartbeat_function(&heartbeat_data->timer); set_bit(LED_BLINK_SW, &led_cdev->work_flags); led_cdev->activated = true; + + return 0; } static void heartbeat_trig_deactivate(struct led_classdev *led_cdev) diff --git a/drivers/leds/trigger/ledtrig-netdev.c b/drivers/leds/trigger/ledtrig-netdev.c index 6df4781a6308..bb05937255de 100644 --- a/drivers/leds/trigger/ledtrig-netdev.c +++ b/drivers/leds/trigger/ledtrig-netdev.c @@ -388,14 +388,14 @@ static void netdev_trig_work(struct work_struct *work) (atomic_read(&trigger_data->interval)*2)); } -static void netdev_trig_activate(struct led_classdev *led_cdev) +static int netdev_trig_activate(struct led_classdev *led_cdev) { struct led_netdev_data *trigger_data; int rc; trigger_data = kzalloc(sizeof(struct led_netdev_data), GFP_KERNEL); if (!trigger_data) - return; + return 0; spin_lock_init(&trigger_data->lock); @@ -432,7 +432,7 @@ static void netdev_trig_activate(struct led_classdev *led_cdev) rc = register_netdevice_notifier(&trigger_data->notifier); if (rc) goto err_out_interval; - return; + return 0; err_out_interval: device_remove_file(led_cdev->dev, &dev_attr_interval); @@ -447,6 +447,8 @@ err_out_device_name: err_out: led_cdev->trigger_data = NULL; kfree(trigger_data); + + return 0; } static void netdev_trig_deactivate(struct led_classdev *led_cdev) diff --git a/drivers/leds/trigger/ledtrig-oneshot.c b/drivers/leds/trigger/ledtrig-oneshot.c index b8ea9f0f1e19..7bbf92bd7f80 100644 --- a/drivers/leds/trigger/ledtrig-oneshot.c +++ b/drivers/leds/trigger/ledtrig-oneshot.c @@ -122,14 +122,14 @@ static DEVICE_ATTR(delay_off, 0644, led_delay_off_show, led_delay_off_store); static DEVICE_ATTR(invert, 0644, led_invert_show, led_invert_store); static DEVICE_ATTR(shot, 0200, NULL, led_shot); -static void oneshot_trig_activate(struct led_classdev *led_cdev) +static int oneshot_trig_activate(struct led_classdev *led_cdev) { struct oneshot_trig_data *oneshot_data; int rc; oneshot_data = kzalloc(sizeof(*oneshot_data), GFP_KERNEL); if (!oneshot_data) - return; + return 0; led_cdev->trigger_data = oneshot_data; @@ -151,7 +151,7 @@ static void oneshot_trig_activate(struct led_classdev *led_cdev) led_cdev->activated = true; - return; + return 0; err_out_invert: device_remove_file(led_cdev->dev, &dev_attr_invert); @@ -161,6 +161,8 @@ err_out_delayon: device_remove_file(led_cdev->dev, &dev_attr_delay_on); err_out_trig_data: kfree(led_cdev->trigger_data); + + return 0; } static void oneshot_trig_deactivate(struct led_classdev *led_cdev) diff --git a/drivers/leds/trigger/ledtrig-timer.c b/drivers/leds/trigger/ledtrig-timer.c index 10fc0966b0e3..527055d815ad 100644 --- a/drivers/leds/trigger/ledtrig-timer.c +++ b/drivers/leds/trigger/ledtrig-timer.c @@ -70,7 +70,7 @@ static ssize_t led_delay_off_store(struct device *dev, static DEVICE_ATTR(delay_on, 0644, led_delay_on_show, led_delay_on_store); static DEVICE_ATTR(delay_off, 0644, led_delay_off_show, led_delay_off_store); -static void timer_trig_activate(struct led_classdev *led_cdev) +static int timer_trig_activate(struct led_classdev *led_cdev) { int rc; @@ -78,7 +78,7 @@ static void timer_trig_activate(struct led_classdev *led_cdev) rc = device_create_file(led_cdev->dev, &dev_attr_delay_on); if (rc) - return; + return 0; rc = device_create_file(led_cdev->dev, &dev_attr_delay_off); if (rc) goto err_out_delayon; @@ -87,10 +87,12 @@ static void timer_trig_activate(struct led_classdev *led_cdev) &led_cdev->blink_delay_off); led_cdev->activated = true; - return; + return 0; err_out_delayon: device_remove_file(led_cdev->dev, &dev_attr_delay_on); + + return 0; } static void timer_trig_deactivate(struct led_classdev *led_cdev) diff --git a/drivers/leds/trigger/ledtrig-transient.c b/drivers/leds/trigger/ledtrig-transient.c index 9d1769073562..a55fc58179a9 100644 --- a/drivers/leds/trigger/ledtrig-transient.c +++ b/drivers/leds/trigger/ledtrig-transient.c @@ -152,7 +152,7 @@ static DEVICE_ATTR(duration, 0644, transient_duration_show, transient_duration_store); static DEVICE_ATTR(state, 0644, transient_state_show, transient_state_store); -static void transient_trig_activate(struct led_classdev *led_cdev) +static int transient_trig_activate(struct led_classdev *led_cdev) { int rc; struct transient_trig_data *tdata; @@ -161,7 +161,7 @@ static void transient_trig_activate(struct led_classdev *led_cdev) if (!tdata) { dev_err(led_cdev->dev, "unable to allocate transient trigger\n"); - return; + return 0; } led_cdev->trigger_data = tdata; tdata->led_cdev = led_cdev; @@ -181,7 +181,7 @@ static void transient_trig_activate(struct led_classdev *led_cdev) timer_setup(&tdata->timer, transient_timer_function, 0); led_cdev->activated = true; - return; + return 0; err_out_state: device_remove_file(led_cdev->dev, &dev_attr_duration); @@ -191,6 +191,8 @@ err_out: dev_err(led_cdev->dev, "unable to register transient trigger\n"); led_cdev->trigger_data = NULL; kfree(tdata); + + return 0; } static void transient_trig_deactivate(struct led_classdev *led_cdev) diff --git a/drivers/tty/vt/keyboard.c b/drivers/tty/vt/keyboard.c index d5b4a2b44ab8..de310621b8e7 100644 --- a/drivers/tty/vt/keyboard.c +++ b/drivers/tty/vt/keyboard.c @@ -959,7 +959,7 @@ struct kbd_led_trigger { unsigned int mask; }; -static void kbd_led_trigger_activate(struct led_classdev *cdev) +static int kbd_led_trigger_activate(struct led_classdev *cdev) { struct kbd_led_trigger *trigger = container_of(cdev->trigger, struct kbd_led_trigger, trigger); @@ -970,6 +970,8 @@ static void kbd_led_trigger_activate(struct led_classdev *cdev) ledstate & trigger->mask ? LED_FULL : LED_OFF); tasklet_enable(&keyboard_tasklet); + + return 0; } #define KBD_LED_TRIGGER(_led_bit, _name) { \ diff --git a/drivers/usb/core/ledtrig-usbport.c b/drivers/usb/core/ledtrig-usbport.c index d775ffea20c3..aa1d51458da7 100644 --- a/drivers/usb/core/ledtrig-usbport.c +++ b/drivers/usb/core/ledtrig-usbport.c @@ -298,14 +298,14 @@ static int usbport_trig_notify(struct notifier_block *nb, unsigned long action, return NOTIFY_DONE; } -static void usbport_trig_activate(struct led_classdev *led_cdev) +static int usbport_trig_activate(struct led_classdev *led_cdev) { struct usbport_trig_data *usbport_data; int err; usbport_data = kzalloc(sizeof(*usbport_data), GFP_KERNEL); if (!usbport_data) - return; + return 0; usbport_data->led_cdev = led_cdev; /* List of ports */ @@ -322,10 +322,11 @@ static void usbport_trig_activate(struct led_classdev *led_cdev) usb_register_notify(&usbport_data->nb); led_cdev->activated = true; - return; + return 0; err_free: kfree(usbport_data); + return 0; } static void usbport_trig_deactivate(struct led_classdev *led_cdev) diff --git a/include/linux/leds.h b/include/linux/leds.h index b7e82550e655..ba5baaaa43bf 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -253,7 +253,7 @@ static inline bool led_sysfs_is_disabled(struct led_classdev *led_cdev) struct led_trigger { /* Trigger Properties */ const char *name; - void (*activate)(struct led_classdev *led_cdev); + int (*activate)(struct led_classdev *led_cdev); void (*deactivate)(struct led_classdev *led_cdev); /* LEDs under control by this trigger (for simple triggers) */ @@ -288,8 +288,8 @@ extern void led_trigger_blink_oneshot(struct led_trigger *trigger, unsigned long *delay_off, int invert); extern void led_trigger_set_default(struct led_classdev *led_cdev); -extern void led_trigger_set(struct led_classdev *led_cdev, - struct led_trigger *trigger); +extern int led_trigger_set(struct led_classdev *led_cdev, + struct led_trigger *trigger); extern void led_trigger_remove(struct led_classdev *led_cdev); static inline void *led_get_trigger_data(struct led_classdev *led_cdev) @@ -334,8 +334,12 @@ static inline void led_trigger_blink_oneshot(struct led_trigger *trigger, unsigned long *delay_off, int invert) {} static inline void led_trigger_set_default(struct led_classdev *led_cdev) {} -static inline void led_trigger_set(struct led_classdev *led_cdev, - struct led_trigger *trigger) {} +static inline int led_trigger_set(struct led_classdev *led_cdev, + struct led_trigger *trigger) +{ + return 0; +} + static inline void led_trigger_remove(struct led_classdev *led_cdev) {} static inline void *led_get_trigger_data(struct led_classdev *led_cdev) { diff --git a/net/bluetooth/leds.c b/net/bluetooth/leds.c index cb670b5594eb..6d59a5023231 100644 --- a/net/bluetooth/leds.c +++ b/net/bluetooth/leds.c @@ -43,7 +43,7 @@ void hci_leds_update_powered(struct hci_dev *hdev, bool enabled) led_trigger_event(bt_power_led_trigger, enabled ? LED_FULL : LED_OFF); } -static void power_activate(struct led_classdev *led_cdev) +static int power_activate(struct led_classdev *led_cdev) { struct hci_basic_led_trigger *htrig; bool powered; @@ -52,10 +52,12 @@ static void power_activate(struct led_classdev *led_cdev) powered = test_bit(HCI_UP, &htrig->hdev->flags); led_trigger_event(led_cdev->trigger, powered ? LED_FULL : LED_OFF); + + return 0; } static struct led_trigger *led_allocate_basic(struct hci_dev *hdev, - void (*activate)(struct led_classdev *led_cdev), + int (*activate)(struct led_classdev *led_cdev), const char *name) { struct hci_basic_led_trigger *htrig; diff --git a/net/mac80211/led.c b/net/mac80211/led.c index ba0b507ea691..d6c66fc19716 100644 --- a/net/mac80211/led.c +++ b/net/mac80211/led.c @@ -52,13 +52,15 @@ void ieee80211_free_led_names(struct ieee80211_local *local) kfree(local->radio_led.name); } -static void ieee80211_tx_led_activate(struct led_classdev *led_cdev) +static int ieee80211_tx_led_activate(struct led_classdev *led_cdev) { struct ieee80211_local *local = container_of(led_cdev->trigger, struct ieee80211_local, tx_led); atomic_inc(&local->tx_led_active); + + return 0; } static void ieee80211_tx_led_deactivate(struct led_classdev *led_cdev) @@ -70,13 +72,15 @@ static void ieee80211_tx_led_deactivate(struct led_classdev *led_cdev) atomic_dec(&local->tx_led_active); } -static void ieee80211_rx_led_activate(struct led_classdev *led_cdev) +static int ieee80211_rx_led_activate(struct led_classdev *led_cdev) { struct ieee80211_local *local = container_of(led_cdev->trigger, struct ieee80211_local, rx_led); atomic_inc(&local->rx_led_active); + + return 0; } static void ieee80211_rx_led_deactivate(struct led_classdev *led_cdev) @@ -88,13 +92,15 @@ static void ieee80211_rx_led_deactivate(struct led_classdev *led_cdev) atomic_dec(&local->rx_led_active); } -static void ieee80211_assoc_led_activate(struct led_classdev *led_cdev) +static int ieee80211_assoc_led_activate(struct led_classdev *led_cdev) { struct ieee80211_local *local = container_of(led_cdev->trigger, struct ieee80211_local, assoc_led); atomic_inc(&local->assoc_led_active); + + return 0; } static void ieee80211_assoc_led_deactivate(struct led_classdev *led_cdev) @@ -106,13 +112,15 @@ static void ieee80211_assoc_led_deactivate(struct led_classdev *led_cdev) atomic_dec(&local->assoc_led_active); } -static void ieee80211_radio_led_activate(struct led_classdev *led_cdev) +static int ieee80211_radio_led_activate(struct led_classdev *led_cdev) { struct ieee80211_local *local = container_of(led_cdev->trigger, struct ieee80211_local, radio_led); atomic_inc(&local->radio_led_active); + + return 0; } static void ieee80211_radio_led_deactivate(struct led_classdev *led_cdev) @@ -124,13 +132,15 @@ static void ieee80211_radio_led_deactivate(struct led_classdev *led_cdev) atomic_dec(&local->radio_led_active); } -static void ieee80211_tpt_led_activate(struct led_classdev *led_cdev) +static int ieee80211_tpt_led_activate(struct led_classdev *led_cdev) { struct ieee80211_local *local = container_of(led_cdev->trigger, struct ieee80211_local, tpt_led); atomic_inc(&local->tpt_led_active); + + return 0; } static void ieee80211_tpt_led_deactivate(struct led_classdev *led_cdev) diff --git a/net/rfkill/core.c b/net/rfkill/core.c index a7a4e6ff9be2..1355f5ca8d22 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -141,13 +141,15 @@ static void rfkill_led_trigger_event(struct rfkill *rfkill) led_trigger_event(trigger, LED_FULL); } -static void rfkill_led_trigger_activate(struct led_classdev *led) +static int rfkill_led_trigger_activate(struct led_classdev *led) { struct rfkill *rfkill; rfkill = container_of(led->trigger, struct rfkill, led_trigger); rfkill_led_trigger_event(rfkill); + + return 0; } const char *rfkill_get_led_trigger_name(struct rfkill *rfkill) -- cgit v1.2.3 From a7e7a3156300a7e1982b03cc9cb8fb0c86434c49 Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Mon, 2 Jul 2018 22:05:22 +0200 Subject: leds: triggers: add device attribute support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit As many triggers use device attributes, add support for these in led_trigger_set which allows simplifying the drivers accordingly. Signed-off-by: Uwe Kleine-König Acked-by: Pavel Machek Signed-off-by: Jacek Anaszewski --- drivers/leds/led-triggers.c | 12 ++++++++++++ include/linux/leds.h | 11 +++++++++++ 2 files changed, 23 insertions(+) (limited to 'include') diff --git a/drivers/leds/led-triggers.c b/drivers/leds/led-triggers.c index a8786f4b3453..3f3e8728d82c 100644 --- a/drivers/leds/led-triggers.c +++ b/drivers/leds/led-triggers.c @@ -127,6 +127,7 @@ int led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trig) led_stop_software_blink(led_cdev); if (led_cdev->trigger->deactivate) led_cdev->trigger->deactivate(led_cdev); + device_remove_groups(led_cdev->dev, led_cdev->trigger->groups); led_cdev->trigger = NULL; led_set_brightness(led_cdev, LED_OFF); } @@ -143,6 +144,12 @@ int led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trig) if (ret) goto err_activate; + + ret = device_add_groups(led_cdev->dev, trig->groups); + if (ret) { + dev_err(led_cdev->dev, "Failed to add trigger attributes\n"); + goto err_add_groups; + } } if (event) { @@ -156,7 +163,12 @@ int led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trig) return 0; +err_add_groups: + + if (trig->deactivate) + trig->deactivate(led_cdev); err_activate: + led_cdev->trigger = NULL; write_lock_irqsave(&led_cdev->trigger->leddev_list_lock, flags); list_del(&led_cdev->trig_list); diff --git a/include/linux/leds.h b/include/linux/leds.h index ba5baaaa43bf..33484a5c7478 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -262,8 +262,19 @@ struct led_trigger { /* Link to next registered trigger */ struct list_head next_trig; + + const struct attribute_group **groups; }; +/* + * Currently the attributes in struct led_trigger::groups are added directly to + * the LED device. As this might change in the future, the following + * macros abstract getting the LED device and its trigger_data from the dev + * parameter passed to the attribute accessor functions. + */ +#define led_trigger_get_led(dev) ((struct led_classdev *)dev_get_drvdata((dev))) +#define led_trigger_get_drvdata(dev) (led_get_trigger_data(led_trigger_get_led(dev))) + ssize_t led_trigger_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count); ssize_t led_trigger_show(struct device *dev, struct device_attribute *attr, -- cgit v1.2.3 From a0b750768371e410d77b60bcf49c18bd45078d55 Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Mon, 2 Jul 2018 22:05:24 +0200 Subject: leds: triggers: define module_led_trigger helper MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This helps to simplify modules that provide a simple led_trigger. It's inspired by module_platform_driver, module_i2c_driver et al. Signed-off-by: Uwe Kleine-König Acked-by: Pavel Machek Signed-off-by: Jacek Anaszewski --- include/linux/leds.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/leds.h b/include/linux/leds.h index 33484a5c7478..a3ee10846a4b 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -326,6 +326,10 @@ static inline void *led_get_trigger_data(struct led_classdev *led_cdev) extern void led_trigger_rename_static(const char *name, struct led_trigger *trig); +#define module_led_trigger(__led_trigger) \ + module_driver(__led_trigger, led_trigger_register, \ + led_trigger_unregister) + #else /* Trigger has no members */ -- cgit v1.2.3 From 9acc560de2aac73ef99c54f0fdfb86b4684296b5 Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Mon, 2 Jul 2018 22:05:25 +0200 Subject: leds: triggers: new function led_set_trigger_data() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This is the natural counter part to the already existing led_get_trigger_data(). Signed-off-by: Uwe Kleine-König Acked-by: Pavel Machek Signed-off-by: Jacek Anaszewski --- include/linux/leds.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/leds.h b/include/linux/leds.h index a3ee10846a4b..834683d603f9 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -303,6 +303,12 @@ extern int led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trigger); extern void led_trigger_remove(struct led_classdev *led_cdev); +static inline void led_set_trigger_data(struct led_classdev *led_cdev, + void *trigger_data) +{ + led_cdev->trigger_data = trigger_data; +} + static inline void *led_get_trigger_data(struct led_classdev *led_cdev) { return led_cdev->trigger_data; @@ -356,6 +362,7 @@ static inline int led_trigger_set(struct led_classdev *led_cdev, } static inline void led_trigger_remove(struct led_classdev *led_cdev) {} +static inline void led_set_trigger_data(struct led_classdev *led_cdev) {} static inline void *led_get_trigger_data(struct led_classdev *led_cdev) { return NULL; -- cgit v1.2.3 From 180fc134d712a93a2bbc3d11ed657b5208e6f90f Mon Sep 17 00:00:00 2001 From: Andrey Grodzovsky Date: Tue, 5 Jun 2018 12:43:23 -0400 Subject: drm/scheduler: Rename cleanup functions v2. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Everything in the flush code path (i.e. waiting for SW queue to become empty) names with *_flush() and everything in the release code path names *_fini() This patch also effect the amdgpu and etnaviv drivers which use those functions. v2: Also pplay the change to vd3. Signed-off-by: Andrey Grodzovsky Suggested-by: Christian König Acked-by: Lucas Stach Reviewed-by: Christian König Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c | 8 ++++---- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c | 2 +- drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c | 2 +- drivers/gpu/drm/etnaviv/etnaviv_drv.c | 4 ++-- drivers/gpu/drm/scheduler/gpu_scheduler.c | 18 +++++++++--------- drivers/gpu/drm/v3d/v3d_drv.c | 2 +- include/drm/gpu_scheduler.h | 6 +++--- 11 files changed, 26 insertions(+), 26 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c index 64b3a1ed04dc..c0f06c02f2de 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c @@ -104,7 +104,7 @@ static int amdgpu_ctx_init(struct amdgpu_device *adev, failed: for (j = 0; j < i; j++) - drm_sched_entity_fini(&adev->rings[j]->sched, + drm_sched_entity_destroy(&adev->rings[j]->sched, &ctx->rings[j].entity); kfree(ctx->fences); ctx->fences = NULL; @@ -178,7 +178,7 @@ static void amdgpu_ctx_do_release(struct kref *ref) if (ctx->adev->rings[i] == &ctx->adev->gfx.kiq.ring) continue; - drm_sched_entity_fini(&ctx->adev->rings[i]->sched, + drm_sched_entity_destroy(&ctx->adev->rings[i]->sched, &ctx->rings[i].entity); } @@ -466,7 +466,7 @@ void amdgpu_ctx_mgr_entity_fini(struct amdgpu_ctx_mgr *mgr) if (ctx->adev->rings[i] == &ctx->adev->gfx.kiq.ring) continue; - max_wait = drm_sched_entity_do_release(&ctx->adev->rings[i]->sched, + max_wait = drm_sched_entity_flush(&ctx->adev->rings[i]->sched, &ctx->rings[i].entity, max_wait); } } @@ -492,7 +492,7 @@ void amdgpu_ctx_mgr_entity_cleanup(struct amdgpu_ctx_mgr *mgr) continue; if (kref_read(&ctx->refcount) == 1) - drm_sched_entity_cleanup(&ctx->adev->rings[i]->sched, + drm_sched_entity_fini(&ctx->adev->rings[i]->sched, &ctx->rings[i].entity); else DRM_ERROR("ctx %p is still alive\n", ctx); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 0c084d3d0865..0246cb87d9e4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -162,7 +162,7 @@ error_mem: static void amdgpu_ttm_global_fini(struct amdgpu_device *adev) { if (adev->mman.mem_global_referenced) { - drm_sched_entity_fini(adev->mman.entity.sched, + drm_sched_entity_destroy(adev->mman.entity.sched, &adev->mman.entity); mutex_destroy(&adev->mman.gtt_window_lock); drm_global_item_unref(&adev->mman.bo_global_ref.ref); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c index cc15d3230402..0b46ea1c6290 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c @@ -309,7 +309,7 @@ int amdgpu_uvd_sw_fini(struct amdgpu_device *adev) for (j = 0; j < adev->uvd.num_uvd_inst; ++j) { kfree(adev->uvd.inst[j].saved_bo); - drm_sched_entity_fini(&adev->uvd.inst[j].ring.sched, &adev->uvd.inst[j].entity); + drm_sched_entity_destroy(&adev->uvd.inst[j].ring.sched, &adev->uvd.inst[j].entity); amdgpu_bo_free_kernel(&adev->uvd.inst[j].vcpu_bo, &adev->uvd.inst[j].gpu_addr, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c index 23d960ec1cf2..b0dcdfd85f5b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c @@ -222,7 +222,7 @@ int amdgpu_vce_sw_fini(struct amdgpu_device *adev) if (adev->vce.vcpu_bo == NULL) return 0; - drm_sched_entity_fini(&adev->vce.ring[0].sched, &adev->vce.entity); + drm_sched_entity_destroy(&adev->vce.ring[0].sched, &adev->vce.entity); amdgpu_bo_free_kernel(&adev->vce.vcpu_bo, &adev->vce.gpu_addr, (void **)&adev->vce.cpu_addr); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 590db78b8c72..837066076ccf 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -2643,7 +2643,7 @@ error_free_root: vm->root.base.bo = NULL; error_free_sched_entity: - drm_sched_entity_fini(&ring->sched, &vm->entity); + drm_sched_entity_destroy(&ring->sched, &vm->entity); return r; } @@ -2780,7 +2780,7 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm) spin_unlock_irqrestore(&adev->vm_manager.pasid_lock, flags); } - drm_sched_entity_fini(vm->entity.sched, &vm->entity); + drm_sched_entity_destroy(vm->entity.sched, &vm->entity); if (!RB_EMPTY_ROOT(&vm->va.rb_root)) { dev_err(adev->dev, "still active bo inside vm\n"); diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c index bfddf97dd13e..1df1c6115341 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c @@ -470,7 +470,7 @@ static int uvd_v6_0_sw_fini(void *handle) return r; if (uvd_v6_0_enc_support(adev)) { - drm_sched_entity_fini(&adev->uvd.inst->ring_enc[0].sched, &adev->uvd.inst->entity_enc); + drm_sched_entity_destroy(&adev->uvd.inst->ring_enc[0].sched, &adev->uvd.inst->entity_enc); for (i = 0; i < adev->uvd.num_enc_rings; ++i) amdgpu_ring_fini(&adev->uvd.inst->ring_enc[i]); diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c index 57d32f21b3a6..ba244d3b74db 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c @@ -491,7 +491,7 @@ static int uvd_v7_0_sw_fini(void *handle) return r; for (j = 0; j < adev->uvd.num_uvd_inst; ++j) { - drm_sched_entity_fini(&adev->uvd.inst[j].ring_enc[0].sched, &adev->uvd.inst[j].entity_enc); + drm_sched_entity_destroy(&adev->uvd.inst[j].ring_enc[0].sched, &adev->uvd.inst[j].entity_enc); for (i = 0; i < adev->uvd.num_enc_rings; ++i) amdgpu_ring_fini(&adev->uvd.inst[j].ring_enc[i]); diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.c b/drivers/gpu/drm/etnaviv/etnaviv_drv.c index e5013a999147..45bfdf4cc107 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_drv.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.c @@ -78,8 +78,8 @@ static void etnaviv_postclose(struct drm_device *dev, struct drm_file *file) gpu->lastctx = NULL; mutex_unlock(&gpu->lock); - drm_sched_entity_fini(&gpu->sched, - &ctx->sched_entity[i]); + drm_sched_entity_destroy(&gpu->sched, + &ctx->sched_entity[i]); } } diff --git a/drivers/gpu/drm/scheduler/gpu_scheduler.c b/drivers/gpu/drm/scheduler/gpu_scheduler.c index 6a316701da73..7d2560699b84 100644 --- a/drivers/gpu/drm/scheduler/gpu_scheduler.c +++ b/drivers/gpu/drm/scheduler/gpu_scheduler.c @@ -256,7 +256,7 @@ static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f, /** - * drm_sched_entity_do_release - Destroy a context entity + * drm_sched_entity_flush - Flush a context entity * * @sched: scheduler instance * @entity: scheduler entity @@ -267,7 +267,7 @@ static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f, * * Returns the remaining time in jiffies left from the input timeout */ -long drm_sched_entity_do_release(struct drm_gpu_scheduler *sched, +long drm_sched_entity_flush(struct drm_gpu_scheduler *sched, struct drm_sched_entity *entity, long timeout) { long ret = timeout; @@ -294,7 +294,7 @@ long drm_sched_entity_do_release(struct drm_gpu_scheduler *sched, return ret; } -EXPORT_SYMBOL(drm_sched_entity_do_release); +EXPORT_SYMBOL(drm_sched_entity_flush); /** * drm_sched_entity_cleanup - Destroy a context entity @@ -306,7 +306,7 @@ EXPORT_SYMBOL(drm_sched_entity_do_release); * entity and signals all jobs with an error code if the process was killed. * */ -void drm_sched_entity_cleanup(struct drm_gpu_scheduler *sched, +void drm_sched_entity_fini(struct drm_gpu_scheduler *sched, struct drm_sched_entity *entity) { @@ -357,7 +357,7 @@ void drm_sched_entity_cleanup(struct drm_gpu_scheduler *sched, dma_fence_put(entity->last_scheduled); entity->last_scheduled = NULL; } -EXPORT_SYMBOL(drm_sched_entity_cleanup); +EXPORT_SYMBOL(drm_sched_entity_fini); /** * drm_sched_entity_fini - Destroy a context entity @@ -367,13 +367,13 @@ EXPORT_SYMBOL(drm_sched_entity_cleanup); * * Calls drm_sched_entity_do_release() and drm_sched_entity_cleanup() */ -void drm_sched_entity_fini(struct drm_gpu_scheduler *sched, +void drm_sched_entity_destroy(struct drm_gpu_scheduler *sched, struct drm_sched_entity *entity) { - drm_sched_entity_do_release(sched, entity, MAX_WAIT_SCHED_ENTITY_Q_EMPTY); - drm_sched_entity_cleanup(sched, entity); + drm_sched_entity_flush(sched, entity, MAX_WAIT_SCHED_ENTITY_Q_EMPTY); + drm_sched_entity_fini(sched, entity); } -EXPORT_SYMBOL(drm_sched_entity_fini); +EXPORT_SYMBOL(drm_sched_entity_destroy); static void drm_sched_entity_wakeup(struct dma_fence *f, struct dma_fence_cb *cb) { diff --git a/drivers/gpu/drm/v3d/v3d_drv.c b/drivers/gpu/drm/v3d/v3d_drv.c index cdb582043b4f..567f7d46d912 100644 --- a/drivers/gpu/drm/v3d/v3d_drv.c +++ b/drivers/gpu/drm/v3d/v3d_drv.c @@ -151,7 +151,7 @@ v3d_postclose(struct drm_device *dev, struct drm_file *file) enum v3d_queue q; for (q = 0; q < V3D_MAX_QUEUES; q++) { - drm_sched_entity_fini(&v3d->queue[q].sched, + drm_sched_entity_destroy(&v3d->queue[q].sched, &v3d_priv->sched_entity[q]); } diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index 7c2dfd6cc1af..4214ceb71c05 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -284,12 +284,12 @@ int drm_sched_entity_init(struct drm_gpu_scheduler *sched, struct drm_sched_entity *entity, struct drm_sched_rq *rq, atomic_t *guilty); -long drm_sched_entity_do_release(struct drm_gpu_scheduler *sched, +long drm_sched_entity_flush(struct drm_gpu_scheduler *sched, struct drm_sched_entity *entity, long timeout); -void drm_sched_entity_cleanup(struct drm_gpu_scheduler *sched, - struct drm_sched_entity *entity); void drm_sched_entity_fini(struct drm_gpu_scheduler *sched, struct drm_sched_entity *entity); +void drm_sched_entity_destroy(struct drm_gpu_scheduler *sched, + struct drm_sched_entity *entity); void drm_sched_entity_push_job(struct drm_sched_job *sched_job, struct drm_sched_entity *entity); void drm_sched_entity_set_rq(struct drm_sched_entity *entity, -- cgit v1.2.3 From 576c7218a1546e0153480b208b125509cec71470 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Mon, 25 Jun 2018 13:17:41 -0500 Subject: PCI: Export pcie_get_speed_cap and pcie_get_width_cap MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit So drivers can use them. This can be used to replace duplicate code in the drm subsystem. Acked-by: Christian König Acked-by: Bjorn Helgaas Signed-off-by: Alex Deucher --- drivers/pci/pci.c | 2 ++ include/linux/pci.h | 3 +++ 2 files changed, 5 insertions(+) (limited to 'include') diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 97acba712e4e..22adaf35b136 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -5222,6 +5222,7 @@ enum pci_bus_speed pcie_get_speed_cap(struct pci_dev *dev) return PCI_SPEED_UNKNOWN; } +EXPORT_SYMBOL(pcie_get_speed_cap); /** * pcie_get_width_cap - query for the PCI device's link width capability @@ -5240,6 +5241,7 @@ enum pcie_link_width pcie_get_width_cap(struct pci_dev *dev) return PCIE_LNK_WIDTH_UNKNOWN; } +EXPORT_SYMBOL(pcie_get_width_cap); /** * pcie_bandwidth_capable - calculate a PCI device's link bandwidth capability diff --git a/include/linux/pci.h b/include/linux/pci.h index 340029b2fb38..6e0c0803b241 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -261,6 +261,9 @@ enum pci_bus_speed { PCI_SPEED_UNKNOWN = 0xff, }; +enum pci_bus_speed pcie_get_speed_cap(struct pci_dev *dev); +enum pcie_link_width pcie_get_width_cap(struct pci_dev *dev); + struct pci_cap_saved_data { u16 cap_nr; bool cap_extended; -- cgit v1.2.3 From 289278cb7d32685ee75baf599857d7049c4b8030 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Mon, 25 Jun 2018 15:14:46 -0500 Subject: drm: drop drm_pcie_get_speed_cap_mask and drm_pcie_get_max_link_width MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit These functions duplicated functionality which was ultimately added to the pci core. All users of these functions have been ported to using the newly exposed pci functionality. These functions are no longer used, so drop them. Acked-by: Christian König Reviewed-by: Dave Airlie Signed-off-by: Alex Deucher --- drivers/gpu/drm/drm_pci.c | 58 ----------------------------------------------- include/drm/drm_pci.h | 7 ------ 2 files changed, 65 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_pci.c b/drivers/gpu/drm/drm_pci.c index 4db9c515b74f..896e42a34895 100644 --- a/drivers/gpu/drm/drm_pci.c +++ b/drivers/gpu/drm/drm_pci.c @@ -326,64 +326,6 @@ int drm_legacy_pci_init(struct drm_driver *driver, struct pci_driver *pdriver) } EXPORT_SYMBOL(drm_legacy_pci_init); -int drm_pcie_get_speed_cap_mask(struct drm_device *dev, u32 *mask) -{ - struct pci_dev *root; - u32 lnkcap, lnkcap2; - - *mask = 0; - if (!dev->pdev) - return -EINVAL; - - root = dev->pdev->bus->self; - - /* we've been informed via and serverworks don't make the cut */ - if (root->vendor == PCI_VENDOR_ID_VIA || - root->vendor == PCI_VENDOR_ID_SERVERWORKS) - return -EINVAL; - - pcie_capability_read_dword(root, PCI_EXP_LNKCAP, &lnkcap); - pcie_capability_read_dword(root, PCI_EXP_LNKCAP2, &lnkcap2); - - if (lnkcap2) { /* PCIe r3.0-compliant */ - if (lnkcap2 & PCI_EXP_LNKCAP2_SLS_2_5GB) - *mask |= DRM_PCIE_SPEED_25; - if (lnkcap2 & PCI_EXP_LNKCAP2_SLS_5_0GB) - *mask |= DRM_PCIE_SPEED_50; - if (lnkcap2 & PCI_EXP_LNKCAP2_SLS_8_0GB) - *mask |= DRM_PCIE_SPEED_80; - } else { /* pre-r3.0 */ - if (lnkcap & PCI_EXP_LNKCAP_SLS_2_5GB) - *mask |= DRM_PCIE_SPEED_25; - if (lnkcap & PCI_EXP_LNKCAP_SLS_5_0GB) - *mask |= (DRM_PCIE_SPEED_25 | DRM_PCIE_SPEED_50); - } - - DRM_INFO("probing gen 2 caps for device %x:%x = %x/%x\n", root->vendor, root->device, lnkcap, lnkcap2); - return 0; -} -EXPORT_SYMBOL(drm_pcie_get_speed_cap_mask); - -int drm_pcie_get_max_link_width(struct drm_device *dev, u32 *mlw) -{ - struct pci_dev *root; - u32 lnkcap; - - *mlw = 0; - if (!dev->pdev) - return -EINVAL; - - root = dev->pdev->bus->self; - - pcie_capability_read_dword(root, PCI_EXP_LNKCAP, &lnkcap); - - *mlw = (lnkcap & PCI_EXP_LNKCAP_MLW) >> 4; - - DRM_INFO("probing mlw for device %x:%x = %x\n", root->vendor, root->device, lnkcap); - return 0; -} -EXPORT_SYMBOL(drm_pcie_get_max_link_width); - #else void drm_pci_agp_destroy(struct drm_device *dev) {} diff --git a/include/drm/drm_pci.h b/include/drm/drm_pci.h index 674599025d7d..8181e9e7cf1d 100644 --- a/include/drm/drm_pci.h +++ b/include/drm/drm_pci.h @@ -58,11 +58,4 @@ static inline int drm_get_pci_dev(struct pci_dev *pdev, } #endif -#define DRM_PCIE_SPEED_25 1 -#define DRM_PCIE_SPEED_50 2 -#define DRM_PCIE_SPEED_80 4 - -int drm_pcie_get_speed_cap_mask(struct drm_device *dev, u32 *speed_mask); -int drm_pcie_get_max_link_width(struct drm_device *dev, u32 *mlw); - #endif /* _DRM_PCI_H_ */ -- cgit v1.2.3 From d8269e2cbf908f9d26aa5d3217236227dffd1d89 Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Thu, 5 Jul 2018 15:49:42 +0100 Subject: net: ipv6: listify ipv6_rcv() and ip6_rcv_finish() Essentially the same as the ipv4 equivalents. Signed-off-by: Edward Cree Signed-off-by: David S. Miller --- include/net/ipv6.h | 2 + net/ipv6/af_inet6.c | 1 + net/ipv6/ip6_input.c | 131 ++++++++++++++++++++++++++++++++++++++++++++------- 3 files changed, 118 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 16475c269749..b7843e0b16ee 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -922,6 +922,8 @@ static inline __be32 flowi6_get_flowlabel(const struct flowi6 *fl6) int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); +void ipv6_list_rcv(struct list_head *head, struct packet_type *pt, + struct net_device *orig_dev); int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 9ed0eae91758..c9535354149f 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -764,6 +764,7 @@ EXPORT_SYMBOL_GPL(ipv6_opt_accepted); static struct packet_type ipv6_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_IPV6), .func = ipv6_rcv, + .list_func = ipv6_list_rcv, }; static int __init ipv6_packet_init(void) diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index f08d34491ece..6242682be876 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -47,17 +47,11 @@ #include #include -int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) +static void ip6_rcv_finish_core(struct net *net, struct sock *sk, + struct sk_buff *skb) { void (*edemux)(struct sk_buff *skb); - /* if ingress device is enslaved to an L3 master device pass the - * skb to its handler for processing - */ - skb = l3mdev_ip6_rcv(skb); - if (!skb) - return NET_RX_SUCCESS; - if (net->ipv4.sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) { const struct inet6_protocol *ipprot; @@ -67,20 +61,73 @@ int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) } if (!skb_valid_dst(skb)) ip6_route_input(skb); +} + +int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) +{ + /* if ingress device is enslaved to an L3 master device pass the + * skb to its handler for processing + */ + skb = l3mdev_ip6_rcv(skb); + if (!skb) + return NET_RX_SUCCESS; + ip6_rcv_finish_core(net, sk, skb); return dst_input(skb); } -int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) +static void ip6_sublist_rcv_finish(struct list_head *head) +{ + struct sk_buff *skb, *next; + + list_for_each_entry_safe(skb, next, head, list) + dst_input(skb); +} + +static void ip6_list_rcv_finish(struct net *net, struct sock *sk, + struct list_head *head) +{ + struct dst_entry *curr_dst = NULL; + struct sk_buff *skb, *next; + struct list_head sublist; + + INIT_LIST_HEAD(&sublist); + list_for_each_entry_safe(skb, next, head, list) { + struct dst_entry *dst; + + list_del(&skb->list); + /* if ingress device is enslaved to an L3 master device pass the + * skb to its handler for processing + */ + skb = l3mdev_ip6_rcv(skb); + if (!skb) + continue; + ip6_rcv_finish_core(net, sk, skb); + dst = skb_dst(skb); + if (curr_dst != dst) { + /* dispatch old sublist */ + if (!list_empty(&sublist)) + ip6_sublist_rcv_finish(&sublist); + /* start new sublist */ + INIT_LIST_HEAD(&sublist); + curr_dst = dst; + } + list_add_tail(&skb->list, &sublist); + } + /* dispatch final sublist */ + ip6_sublist_rcv_finish(&sublist); +} + +static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev, + struct net *net) { const struct ipv6hdr *hdr; u32 pkt_len; struct inet6_dev *idev; - struct net *net = dev_net(skb->dev); if (skb->pkt_type == PACKET_OTHERHOST) { kfree_skb(skb); - return NET_RX_DROP; + return NULL; } rcu_read_lock(); @@ -196,7 +243,7 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt if (ipv6_parse_hopopts(skb) < 0) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); rcu_read_unlock(); - return NET_RX_DROP; + return NULL; } } @@ -205,15 +252,67 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt /* Must drop socket now because of tproxy. */ skb_orphan(skb); - return NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, - net, NULL, skb, dev, NULL, - ip6_rcv_finish); + return skb; err: __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); drop: rcu_read_unlock(); kfree_skb(skb); - return NET_RX_DROP; + return NULL; +} + +int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) +{ + struct net *net = dev_net(skb->dev); + + skb = ip6_rcv_core(skb, dev, net); + if (skb == NULL) + return NET_RX_DROP; + return NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, + net, NULL, skb, dev, NULL, + ip6_rcv_finish); +} + +static void ip6_sublist_rcv(struct list_head *head, struct net_device *dev, + struct net *net) +{ + NF_HOOK_LIST(NFPROTO_IPV6, NF_INET_PRE_ROUTING, net, NULL, + head, dev, NULL, ip6_rcv_finish); + ip6_list_rcv_finish(net, NULL, head); +} + +/* Receive a list of IPv6 packets */ +void ipv6_list_rcv(struct list_head *head, struct packet_type *pt, + struct net_device *orig_dev) +{ + struct net_device *curr_dev = NULL; + struct net *curr_net = NULL; + struct sk_buff *skb, *next; + struct list_head sublist; + + INIT_LIST_HEAD(&sublist); + list_for_each_entry_safe(skb, next, head, list) { + struct net_device *dev = skb->dev; + struct net *net = dev_net(dev); + + list_del(&skb->list); + skb = ip6_rcv_core(skb, dev, net); + if (skb == NULL) + continue; + + if (curr_dev != dev || curr_net != net) { + /* dispatch old sublist */ + if (!list_empty(&sublist)) + ip6_sublist_rcv(&sublist, curr_dev, curr_net); + /* start new sublist */ + INIT_LIST_HEAD(&sublist); + curr_dev = dev; + curr_net = net; + } + list_add_tail(&skb->list, &sublist); + } + /* dispatch final sublist */ + ip6_sublist_rcv(&sublist, curr_dev, curr_net); } /* -- cgit v1.2.3 From cfdb0c2d095ac5d7f09cac1317b7d0a9e8178134 Mon Sep 17 00:00:00 2001 From: Ankit Navik Date: Fri, 29 Jun 2018 12:12:50 +0530 Subject: Bluetooth: Store Resolv list size When the controller supports the Read LE Resolv List size feature, the maximum list size are read and now stored. Before patch: < HCI Command: LE Read White List... (0x08|0x000f) plen 0 #55 [hci0] 17.979791 > HCI Event: Command Complete (0x0e) plen 5 #56 [hci0] 17.980629 LE Read White List Size (0x08|0x000f) ncmd 1 Status: Success (0x00) Size: 25 < HCI Command: LE Clear White List (0x08|0x0010) plen 0 #57 [hci0] 17.980786 > HCI Event: Command Complete (0x0e) plen 4 #58 [hci0] 17.981627 LE Clear White List (0x08|0x0010) ncmd 1 Status: Success (0x00) < HCI Command: LE Read Maximum Dat.. (0x08|0x002f) plen 0 #59 [hci0] 17.981786 > HCI Event: Command Complete (0x0e) plen 12 #60 [hci0] 17.982636 LE Read Maximum Data Length (0x08|0x002f) ncmd 1 Status: Success (0x00) Max TX octets: 251 Max TX time: 17040 Max RX octets: 251 Max RX time: 17040 After patch: < HCI Command: LE Read White List... (0x08|0x000f) plen 0 #55 [hci0] 13.338168 > HCI Event: Command Complete (0x0e) plen 5 #56 [hci0] 13.338842 LE Read White List Size (0x08|0x000f) ncmd 1 Status: Success (0x00) Size: 25 < HCI Command: LE Clear White List (0x08|0x0010) plen 0 #57 [hci0] 13.339029 > HCI Event: Command Complete (0x0e) plen 4 #58 [hci0] 13.339939 LE Clear White List (0x08|0x0010) ncmd 1 Status: Success (0x00) < HCI Command: LE Read Resolving L.. (0x08|0x002a) plen 0 #59 [hci0] 13.340152 > HCI Event: Command Complete (0x0e) plen 5 #60 [hci0] 13.340952 LE Read Resolving List Size (0x08|0x002a) ncmd 1 Status: Success (0x00) Size: 25 < HCI Command: LE Read Maximum Dat.. (0x08|0x002f) plen 0 #61 [hci0] 13.341180 > HCI Event: Command Complete (0x0e) plen 12 #62 [hci0] 13.341898 LE Read Maximum Data Length (0x08|0x002f) ncmd 1 Status: Success (0x00) Max TX octets: 251 Max TX time: 17040 Max RX octets: 251 Max RX time: 17040 Signed-off-by: Ankit Navik Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci.h | 6 ++++++ include/net/bluetooth/hci_core.h | 2 ++ net/bluetooth/hci_core.c | 8 ++++++++ net/bluetooth/hci_debugfs.c | 19 +++++++++++++++++++ net/bluetooth/hci_event.c | 18 ++++++++++++++++++ 5 files changed, 53 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 1668211297a9..484f24c7a415 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -1490,6 +1490,12 @@ struct hci_cp_le_write_def_data_len { __le16 tx_time; } __packed; +#define HCI_OP_LE_READ_RESOLV_LIST_SIZE 0x202a +struct hci_rp_le_read_resolv_list_size { + __u8 status; + __u8 size; +} __packed; + #define HCI_OP_LE_READ_MAX_DATA_LEN 0x202f struct hci_rp_le_read_max_data_len { __u8 status; diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 893bbbb5d2fa..409f49bd8338 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -221,6 +221,7 @@ struct hci_dev { __u8 features[HCI_MAX_PAGES][8]; __u8 le_features[8]; __u8 le_white_list_size; + __u8 le_resolv_list_size; __u8 le_states[8]; __u8 commands[64]; __u8 hci_ver; @@ -367,6 +368,7 @@ struct hci_dev { struct list_head identity_resolving_keys; struct list_head remote_oob_data; struct list_head le_white_list; + struct list_head le_resolv_list; struct list_head le_conn_params; struct list_head pend_le_conns; struct list_head pend_le_reports; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index ee8ef1228263..036e14267d0a 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -714,6 +714,12 @@ static int hci_init3_req(struct hci_request *req, unsigned long opt) hci_req_add(req, HCI_OP_LE_CLEAR_WHITE_LIST, 0, NULL); } + if (hdev->commands[34] & 0x40) { + /* Read LE Resolving List Size */ + hci_req_add(req, HCI_OP_LE_READ_RESOLV_LIST_SIZE, + 0, NULL); + } + if (hdev->le_features[0] & HCI_LE_DATA_LEN_EXT) { /* Read LE Maximum Data Length */ hci_req_add(req, HCI_OP_LE_READ_MAX_DATA_LEN, 0, NULL); @@ -3017,6 +3023,7 @@ struct hci_dev *hci_alloc_dev(void) INIT_LIST_HEAD(&hdev->identity_resolving_keys); INIT_LIST_HEAD(&hdev->remote_oob_data); INIT_LIST_HEAD(&hdev->le_white_list); + INIT_LIST_HEAD(&hdev->le_resolv_list); INIT_LIST_HEAD(&hdev->le_conn_params); INIT_LIST_HEAD(&hdev->pend_le_conns); INIT_LIST_HEAD(&hdev->pend_le_reports); @@ -3218,6 +3225,7 @@ void hci_unregister_dev(struct hci_dev *hdev) hci_remote_oob_data_clear(hdev); hci_adv_instances_clear(hdev); hci_bdaddr_list_clear(&hdev->le_white_list); + hci_bdaddr_list_clear(&hdev->le_resolv_list); hci_conn_params_clear_all(hdev); hci_discovery_filter_clear(hdev); hci_dev_unlock(hdev); diff --git a/net/bluetooth/hci_debugfs.c b/net/bluetooth/hci_debugfs.c index 0d8ab5b3c177..51f5b1efc3a5 100644 --- a/net/bluetooth/hci_debugfs.c +++ b/net/bluetooth/hci_debugfs.c @@ -694,6 +694,21 @@ static int white_list_show(struct seq_file *f, void *ptr) DEFINE_SHOW_ATTRIBUTE(white_list); +static int resolv_list_show(struct seq_file *f, void *ptr) +{ + struct hci_dev *hdev = f->private; + struct bdaddr_list *b; + + hci_dev_lock(hdev); + list_for_each_entry(b, &hdev->le_resolv_list, list) + seq_printf(f, "%pMR (type %u)\n", &b->bdaddr, b->bdaddr_type); + hci_dev_unlock(hdev); + + return 0; +} + +DEFINE_SHOW_ATTRIBUTE(resolv_list); + static int identity_resolving_keys_show(struct seq_file *f, void *ptr) { struct hci_dev *hdev = f->private; @@ -955,6 +970,10 @@ void hci_debugfs_create_le(struct hci_dev *hdev) &hdev->le_white_list_size); debugfs_create_file("white_list", 0444, hdev->debugfs, hdev, &white_list_fops); + debugfs_create_u8("resolv_list_size", 0444, hdev->debugfs, + &hdev->le_resolv_list_size); + debugfs_create_file("resolv_list", 0444, hdev->debugfs, hdev, + &resolv_list_fops); debugfs_create_file("identity_resolving_keys", 0400, hdev->debugfs, hdev, &identity_resolving_keys_fops); debugfs_create_file("long_term_keys", 0400, hdev->debugfs, hdev, diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 235b5aaab23d..6ee69a79258f 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -221,6 +221,7 @@ static void hci_cc_reset(struct hci_dev *hdev, struct sk_buff *skb) hdev->ssp_debug_mode = 0; hci_bdaddr_list_clear(&hdev->le_white_list); + hci_bdaddr_list_clear(&hdev->le_resolv_list); } static void hci_cc_read_stored_link_key(struct hci_dev *hdev, @@ -1306,6 +1307,19 @@ static void hci_cc_le_write_def_data_len(struct hci_dev *hdev, hdev->le_def_tx_time = le16_to_cpu(sent->tx_time); } +static void hci_cc_le_read_resolv_list_size(struct hci_dev *hdev, + struct sk_buff *skb) +{ + struct hci_rp_le_read_resolv_list_size *rp = (void *) skb->data; + + BT_DBG("%s status 0x%2.2x size %u", hdev->name, rp->status, rp->size); + + if (rp->status) + return; + + hdev->le_resolv_list_size = rp->size; +} + static void hci_cc_le_read_max_data_len(struct hci_dev *hdev, struct sk_buff *skb) { @@ -3015,6 +3029,10 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb, hci_cc_le_write_def_data_len(hdev, skb); break; + case HCI_OP_LE_READ_RESOLV_LIST_SIZE: + hci_cc_le_read_resolv_list_size(hdev, skb); + break; + case HCI_OP_LE_READ_MAX_DATA_LEN: hci_cc_le_read_max_data_len(hdev, skb); break; -- cgit v1.2.3 From 545f2596b907f0747170c7cb71edc74cecf68c5c Mon Sep 17 00:00:00 2001 From: Ankit Navik Date: Fri, 29 Jun 2018 12:13:20 +0530 Subject: Bluetooth: Add HCI command for clear Resolv list Check for Resolv list supported by controller. So check the supported commmand first before issuing this command i.e.,HCI_OP_LE_CLEAR_RESOLV_LIST Before patch: < HCI Command: LE Read White List... (0x08|0x000f) plen 0 #55 [hci0] 13.338168 > HCI Event: Command Complete (0x0e) plen 5 #56 [hci0] 13.338842 LE Read White List Size (0x08|0x000f) ncmd 1 Status: Success (0x00) Size: 25 < HCI Command: LE Clear White List (0x08|0x0010) plen 0 #57 [hci0] 13.339029 > HCI Event: Command Complete (0x0e) plen 4 #58 [hci0] 13.339939 LE Clear White List (0x08|0x0010) ncmd 1 Status: Success (0x00) < HCI Command: LE Read Resolving L.. (0x08|0x002a) plen 0 #59 [hci0] 13.340152 > HCI Event: Command Complete (0x0e) plen 5 #60 [hci0] 13.340952 LE Read Resolving List Size (0x08|0x002a) ncmd 1 Status: Success (0x00) Size: 25 < HCI Command: LE Read Maximum Dat.. (0x08|0x002f) plen 0 #61 [hci0] 13.341180 > HCI Event: Command Complete (0x0e) plen 12 #62 [hci0] 13.341898 LE Read Maximum Data Length (0x08|0x002f) ncmd 1 Status: Success (0x00) Max TX octets: 251 Max TX time: 17040 Max RX octets: 251 Max RX time: 17040 After patch: < HCI Command: LE Read White List... (0x08|0x000f) plen 0 #55 [hci0] 28.919131 > HCI Event: Command Complete (0x0e) plen 5 #56 [hci0] 28.920016 LE Read White List Size (0x08|0x000f) ncmd 1 Status: Success (0x00) Size: 25 < HCI Command: LE Clear White List (0x08|0x0010) plen 0 #57 [hci0] 28.920164 > HCI Event: Command Complete (0x0e) plen 4 #58 [hci0] 28.920873 LE Clear White List (0x08|0x0010) ncmd 1 Status: Success (0x00) < HCI Command: LE Read Resolving L.. (0x08|0x002a) plen 0 #59 [hci0] 28.921109 > HCI Event: Command Complete (0x0e) plen 5 #60 [hci0] 28.922016 LE Read Resolving List Size (0x08|0x002a) ncmd 1 Status: Success (0x00) Size: 25 < HCI Command: LE Clear Resolving... (0x08|0x0029) plen 0 #61 [hci0] 28.922166 > HCI Event: Command Complete (0x0e) plen 4 #62 [hci0] 28.922872 LE Clear Resolving List (0x08|0x0029) ncmd 1 Status: Success (0x00) < HCI Command: LE Read Maximum Dat.. (0x08|0x002f) plen 0 #63 [hci0] 28.923117 > HCI Event: Command Complete (0x0e) plen 12 #64 [hci0] 28.924030 LE Read Maximum Data Length (0x08|0x002f) ncmd 1 Status: Success (0x00) Max TX octets: 251 Max TX time: 17040 Max RX octets: 251 Max RX time: 17040 Signed-off-by: Ankit Navik Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci.h | 2 ++ net/bluetooth/hci_core.c | 5 +++++ net/bluetooth/hci_event.c | 17 +++++++++++++++++ 3 files changed, 24 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 484f24c7a415..4af1a3a4d9b1 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -1490,6 +1490,8 @@ struct hci_cp_le_write_def_data_len { __le16 tx_time; } __packed; +#define HCI_OP_LE_CLEAR_RESOLV_LIST 0x2029 + #define HCI_OP_LE_READ_RESOLV_LIST_SIZE 0x202a struct hci_rp_le_read_resolv_list_size { __u8 status; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 036e14267d0a..ce2447d89ce1 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -720,6 +720,11 @@ static int hci_init3_req(struct hci_request *req, unsigned long opt) 0, NULL); } + if (hdev->commands[34] & 0x20) { + /* Clear LE Resolving List */ + hci_req_add(req, HCI_OP_LE_CLEAR_RESOLV_LIST, 0, NULL); + } + if (hdev->le_features[0] & HCI_LE_DATA_LEN_EXT) { /* Read LE Maximum Data Length */ hci_req_add(req, HCI_OP_LE_READ_MAX_DATA_LEN, 0, NULL); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 6ee69a79258f..562e7a854ed6 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -1307,6 +1307,19 @@ static void hci_cc_le_write_def_data_len(struct hci_dev *hdev, hdev->le_def_tx_time = le16_to_cpu(sent->tx_time); } +static void hci_cc_le_clear_resolv_list(struct hci_dev *hdev, + struct sk_buff *skb) +{ + __u8 status = *((__u8 *) skb->data); + + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + if (status) + return; + + hci_bdaddr_list_clear(&hdev->le_resolv_list); +} + static void hci_cc_le_read_resolv_list_size(struct hci_dev *hdev, struct sk_buff *skb) { @@ -3029,6 +3042,10 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb, hci_cc_le_write_def_data_len(hdev, skb); break; + case HCI_OP_LE_CLEAR_RESOLV_LIST: + hci_cc_le_clear_resolv_list(hdev, skb); + break; + case HCI_OP_LE_READ_RESOLV_LIST_SIZE: hci_cc_le_read_resolv_list_size(hdev, skb); break; -- cgit v1.2.3 From 1b0707a781eeaeeaacb464e18bb3f049b99b496b Mon Sep 17 00:00:00 2001 From: Corentin Labbe Date: Thu, 7 Jun 2018 19:50:38 +0000 Subject: Bluetooth: remove unused bt-nokia-h4p.h header Nothing in tree use this header which seems a remains of a staging driver. This patch remove it. Signed-off-by: Corentin Labbe Reviewed-by: Sebastian Reichel Signed-off-by: Marcel Holtmann --- include/linux/platform_data/bt-nokia-h4p.h | 38 ------------------------------ 1 file changed, 38 deletions(-) delete mode 100644 include/linux/platform_data/bt-nokia-h4p.h (limited to 'include') diff --git a/include/linux/platform_data/bt-nokia-h4p.h b/include/linux/platform_data/bt-nokia-h4p.h deleted file mode 100644 index 30d169dfadf3..000000000000 --- a/include/linux/platform_data/bt-nokia-h4p.h +++ /dev/null @@ -1,38 +0,0 @@ -/* - * This file is part of Nokia H4P bluetooth driver - * - * Copyright (C) 2010 Nokia Corporation. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * version 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA - * 02110-1301 USA - * - */ - - -/** - * struct hci_h4p_platform data - hci_h4p Platform data structure - */ -struct hci_h4p_platform_data { - int chip_type; - int bt_sysclk; - unsigned int bt_wakeup_gpio; - unsigned int host_wakeup_gpio; - unsigned int reset_gpio; - int reset_gpio_shared; - unsigned int uart_irq; - phys_addr_t uart_base; - const char *uart_iclk; - const char *uart_fclk; - void (*set_pm_limits)(struct device *dev, bool set); -}; -- cgit v1.2.3 From a012024571d98e2e4bf29a9168fb7ddc44b7ab86 Mon Sep 17 00:00:00 2001 From: Maarten Lankhorst Date: Wed, 18 Apr 2018 14:51:21 +0200 Subject: drm/crc: Only report a single overflow when a CRC fd is opened MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This reduces the amount of spam when you debug a CRC reading program. Signed-off-by: Maarten Lankhorst [mlankhorst: Change bool overflow to was_overflow (Ville)] Reviewed-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20180418125121.72081-1-maarten.lankhorst@linux.intel.com --- drivers/gpu/drm/drm_debugfs_crc.c | 9 ++++++++- include/drm/drm_debugfs_crc.h | 3 ++- 2 files changed, 10 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_debugfs_crc.c b/drivers/gpu/drm/drm_debugfs_crc.c index 9f8312137cad..99961192bf03 100644 --- a/drivers/gpu/drm/drm_debugfs_crc.c +++ b/drivers/gpu/drm/drm_debugfs_crc.c @@ -139,6 +139,7 @@ static int crtc_crc_data_count(struct drm_crtc_crc *crc) static void crtc_crc_cleanup(struct drm_crtc_crc *crc) { kfree(crc->entries); + crc->overflow = false; crc->entries = NULL; crc->head = 0; crc->tail = 0; @@ -391,8 +392,14 @@ int drm_crtc_add_crc_entry(struct drm_crtc *crtc, bool has_frame, tail = crc->tail; if (CIRC_SPACE(head, tail, DRM_CRC_ENTRIES_NR) < 1) { + bool was_overflow = crc->overflow; + + crc->overflow = true; spin_unlock(&crc->lock); - DRM_ERROR("Overflow of CRC buffer, userspace reads too slow.\n"); + + if (!was_overflow) + DRM_ERROR("Overflow of CRC buffer, userspace reads too slow.\n"); + return -ENOBUFS; } diff --git a/include/drm/drm_debugfs_crc.h b/include/drm/drm_debugfs_crc.h index 7d63b1d4adb9..b225eeb30d05 100644 --- a/include/drm/drm_debugfs_crc.h +++ b/include/drm/drm_debugfs_crc.h @@ -43,6 +43,7 @@ struct drm_crtc_crc_entry { * @lock: protects the fields in this struct * @source: name of the currently configured source of CRCs * @opened: whether userspace has opened the data file for reading + * @overflow: whether an overflow occured. * @entries: array of entries, with size of %DRM_CRC_ENTRIES_NR * @head: head of circular queue * @tail: tail of circular queue @@ -52,7 +53,7 @@ struct drm_crtc_crc_entry { struct drm_crtc_crc { spinlock_t lock; const char *source; - bool opened; + bool opened, overflow; struct drm_crtc_crc_entry *entries; int head, tail; size_t values_cnt; -- cgit v1.2.3 From d64c5cf8e89d124355924c513a42b16f0d7d3a03 Mon Sep 17 00:00:00 2001 From: Liam Girdwood Date: Fri, 6 Jul 2018 13:50:36 +0100 Subject: ALSA: pcm: Allow drivers to set R/W wait time. Currently ALSA core blocks userspace for about 10 seconds for PCM R/W IO. This needs to be configurable for modern hardware like DSPs where no pointer update in milliseconds can indicate terminal DSP errors. Add a substream variable to set the wait time in ms. This allows userspace and drivers to recover more quickly from terminal DSP errors. Signed-off-by: Liam Girdwood Signed-off-by: Takashi Iwai --- include/sound/pcm.h | 1 + sound/core/pcm_lib.c | 17 ++++++++++++----- 2 files changed, 13 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/sound/pcm.h b/include/sound/pcm.h index e054c583d3b3..fcdf358a25f0 100644 --- a/include/sound/pcm.h +++ b/include/sound/pcm.h @@ -462,6 +462,7 @@ struct snd_pcm_substream { /* -- timer section -- */ struct snd_timer *timer; /* timer */ unsigned timer_running: 1; /* time is running */ + long wait_time; /* time in ms for R/W to wait for avail */ /* -- next substream -- */ struct snd_pcm_substream *next; /* -- linked substreams -- */ diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c index c1d2e8e1fc6b..5736860f325b 100644 --- a/sound/core/pcm_lib.c +++ b/sound/core/pcm_lib.c @@ -1833,12 +1833,19 @@ static int wait_for_avail(struct snd_pcm_substream *substream, if (runtime->no_period_wakeup) wait_time = MAX_SCHEDULE_TIMEOUT; else { - wait_time = 10; - if (runtime->rate) { - long t = runtime->period_size * 2 / runtime->rate; - wait_time = max(t, wait_time); + /* use wait time from substream if available */ + if (substream->wait_time) { + wait_time = substream->wait_time; + } else { + wait_time = 10; + + if (runtime->rate) { + long t = runtime->period_size * 2 / + runtime->rate; + wait_time = max(t, wait_time); + } + wait_time = msecs_to_jiffies(wait_time * 1000); } - wait_time = msecs_to_jiffies(wait_time * 1000); } for (;;) { -- cgit v1.2.3 From 3b4c2511c004521efa89875512b5039a04d5e2e0 Mon Sep 17 00:00:00 2001 From: Neha Bhende Date: Mon, 18 Jun 2018 16:44:48 -0700 Subject: drm/vmwgfx: Add CAP2 support in vmwgfx The device exposes a new capability register. Add support for it. Signed-off-by: Neha Bhende Reviewed-by: Thomas Hellstrom Signed-off-by: Thomas Hellstrom --- drivers/gpu/drm/vmwgfx/vmwgfx_drv.c | 17 +++++++++++++++++ drivers/gpu/drm/vmwgfx/vmwgfx_drv.h | 1 + drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c | 3 +++ include/uapi/drm/vmwgfx_drm.h | 1 + 4 files changed, 22 insertions(+) (limited to 'include') diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 1128420de2c0..f2fad88e4c54 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -258,6 +258,15 @@ MODULE_PARM_DESC(assume_16bpp, "Assume 16-bpp when filtering modes"); module_param_named(assume_16bpp, vmw_assume_16bpp, int, 0600); +static void vmw_print_capabilities2(uint32_t capabilities2) +{ + DRM_INFO("Capabilities2:\n"); + if (capabilities2 & SVGA_CAP2_GROW_OTABLE) + DRM_INFO(" Grow oTable.\n"); + if (capabilities2 & SVGA_CAP2_INTRA_SURFACE_COPY) + DRM_INFO(" IntraSurface copy.\n"); +} + static void vmw_print_capabilities(uint32_t capabilities) { DRM_INFO("Capabilities:\n"); @@ -684,6 +693,12 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset) } dev_priv->capabilities = vmw_read(dev_priv, SVGA_REG_CAPABILITIES); + + if (dev_priv->capabilities & SVGA_CAP_CAP2_REGISTER) { + dev_priv->capabilities2 = vmw_read(dev_priv, SVGA_REG_CAP2); + } + + ret = vmw_dma_select_mode(dev_priv); if (unlikely(ret != 0)) { DRM_INFO("Restricting capabilities due to IOMMU setup.\n"); @@ -752,6 +767,8 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset) } vmw_print_capabilities(dev_priv->capabilities); + if (dev_priv->capabilities & SVGA_CAP_CAP2_REGISTER) + vmw_print_capabilities2(dev_priv->capabilities2); ret = vmw_dma_masks(dev_priv); if (unlikely(ret != 0)) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index a3a0826958a1..920365c0e9ab 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -386,6 +386,7 @@ struct vmw_private { uint32_t initial_height; u32 *mmio_virt; uint32_t capabilities; + uint32_t capabilities2; uint32_t max_gmr_ids; uint32_t max_gmr_pages; uint32_t max_mob_pages; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c index 6872c7ee8a08..ac6da0da2824 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c @@ -56,6 +56,9 @@ int vmw_getparam_ioctl(struct drm_device *dev, void *data, case DRM_VMW_PARAM_HW_CAPS: param->value = dev_priv->capabilities; break; + case DRM_VMW_PARAM_HW_CAPS2: + param->value = dev_priv->capabilities2; + break; case DRM_VMW_PARAM_FIFO_CAPS: param->value = dev_priv->fifo.capabilities; break; diff --git a/include/uapi/drm/vmwgfx_drm.h b/include/uapi/drm/vmwgfx_drm.h index 57115a5fe61a..84e81b38ca18 100644 --- a/include/uapi/drm/vmwgfx_drm.h +++ b/include/uapi/drm/vmwgfx_drm.h @@ -95,6 +95,7 @@ extern "C" { #define DRM_VMW_PARAM_MAX_MOB_SIZE 10 #define DRM_VMW_PARAM_SCREEN_TARGET 11 #define DRM_VMW_PARAM_DX 12 +#define DRM_VMW_PARAM_HW_CAPS2 13 /** * enum drm_vmw_handle_type - handle type for ref ioctls -- cgit v1.2.3 From 14b1c33e84295693c3b1a1d7c6ac82b3f384cd17 Mon Sep 17 00:00:00 2001 From: Deepak Rawat Date: Wed, 20 Jun 2018 14:48:35 -0700 Subject: drm/vmwgfx: Add new ioctl for GB surface create and reference New ioctls DRM_VMW_GB_SURFACE_CREATE_EXT and DRM_VMW_GB_SURFACE_REF_EXT are added which support 64-bit wide svga device surface flags, quality level and multisample pattern. Signed-off-by: Deepak Rawat Reviewed-by: Sinclair Yeh Reviewed-by: Brian Paul Reviewed-by: Thomas Hellstrom Reviewed-by: Charmaine Lee Signed-off-by: Thomas Hellstrom --- drivers/gpu/drm/vmwgfx/vmwgfx_drv.c | 12 + drivers/gpu/drm/vmwgfx/vmwgfx_drv.h | 8 + drivers/gpu/drm/vmwgfx/vmwgfx_kms.c | 20 +- drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c | 2 + drivers/gpu/drm/vmwgfx/vmwgfx_surface.c | 468 +++++++++++++++++++++----------- include/uapi/drm/vmwgfx_drm.h | 102 +++++++ 6 files changed, 437 insertions(+), 175 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 6cf81e19182f..59229111f303 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -137,6 +137,12 @@ #define DRM_IOCTL_VMW_CREATE_EXTENDED_CONTEXT \ DRM_IOWR(DRM_COMMAND_BASE + DRM_VMW_CREATE_EXTENDED_CONTEXT, \ struct drm_vmw_context_arg) +#define DRM_IOCTL_VMW_GB_SURFACE_CREATE_EXT \ + DRM_IOWR(DRM_COMMAND_BASE + DRM_VMW_GB_SURFACE_CREATE_EXT, \ + union drm_vmw_gb_surface_create_ext_arg) +#define DRM_IOCTL_VMW_GB_SURFACE_REF_EXT \ + DRM_IOWR(DRM_COMMAND_BASE + DRM_VMW_GB_SURFACE_REF_EXT, \ + union drm_vmw_gb_surface_reference_ext_arg) /** * The core DRM version of this macro doesn't account for @@ -224,6 +230,12 @@ static const struct drm_ioctl_desc vmw_ioctls[] = { VMW_IOCTL_DEF(VMW_CREATE_EXTENDED_CONTEXT, vmw_extended_context_define_ioctl, DRM_AUTH | DRM_RENDER_ALLOW), + VMW_IOCTL_DEF(VMW_GB_SURFACE_CREATE_EXT, + vmw_gb_surface_define_ext_ioctl, + DRM_AUTH | DRM_RENDER_ALLOW), + VMW_IOCTL_DEF(VMW_GB_SURFACE_REF_EXT, + vmw_gb_surface_reference_ext_ioctl, + DRM_AUTH | DRM_RENDER_ALLOW), }; static const struct pci_device_id vmw_pci_id_list[] = { diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index 7e5c93083036..59af14714797 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -1087,7 +1087,15 @@ int vmw_surface_gb_priv_define(struct drm_device *dev, uint32_t multisample_count, uint32_t array_size, struct drm_vmw_size size, + SVGA3dMSPattern multisample_pattern, + SVGA3dMSQualityLevel quality_level, struct vmw_surface **srf_out); +extern int vmw_gb_surface_define_ext_ioctl(struct drm_device *dev, + void *data, + struct drm_file *file_priv); +extern int vmw_gb_surface_reference_ext_ioctl(struct drm_device *dev, + void *data, + struct drm_file *file_priv); /* * Shader management - vmwgfx_shader.c diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index 0fb363458ab5..3201b0a51d10 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -1238,15 +1238,17 @@ static int vmw_create_bo_proxy(struct drm_device *dev, content_base_size.depth = 1; ret = vmw_surface_gb_priv_define(dev, - 0, /* kernel visible only */ - 0, /* flags */ - format, - true, /* can be a scanout buffer */ - 1, /* num of mip levels */ - 0, - 0, - content_base_size, - srf_out); + 0, /* kernel visible only */ + 0, /* flags */ + format, + true, /* can be a scanout buffer */ + 1, /* num of mip levels */ + 0, + 0, + content_base_size, + SVGA3D_MS_PATTERN_NONE, + SVGA3D_MS_QUALITY_NONE, + srf_out); if (ret) { DRM_ERROR("Failed to allocate proxy content buffer\n"); return ret; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c index 6630abf3a95c..f9872c9e60c4 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c @@ -1188,6 +1188,8 @@ vmw_stdu_primary_plane_prepare_fb(struct drm_plane *plane, content_srf.multisample_count, 0, display_base_size, + content_srf.multisample_pattern, + content_srf.quality_level, &vps->surf); if (ret != 0) { DRM_ERROR("Couldn't allocate STDU surface.\n"); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c index a5f93f62c7fa..1d4c010a0e48 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c @@ -33,6 +33,10 @@ #include "vmwgfx_binding.h" #include "device_include/svga3d_surfacedefs.h" +#define SVGA3D_FLAGS_64(upper32, lower32) (((uint64_t)upper32 << 32) | lower32) +#define SVGA3D_FLAGS_UPPER_32(svga3d_flags) (svga3d_flags >> 32) +#define SVGA3D_FLAGS_LOWER_32(svga3d_flags) \ + (svga3d_flags & ((uint64_t)U32_MAX)) /** * struct vmw_user_surface - User-space visible surface resource @@ -81,7 +85,16 @@ static int vmw_gb_surface_unbind(struct vmw_resource *res, bool readback, struct ttm_validate_buffer *val_buf); static int vmw_gb_surface_destroy(struct vmw_resource *res); - +static int +vmw_gb_surface_define_internal(struct drm_device *dev, + struct drm_vmw_gb_surface_create_ext_req *req, + struct drm_vmw_gb_surface_create_rep *rep, + struct drm_file *file_priv); +static int +vmw_gb_surface_reference_internal(struct drm_device *dev, + struct drm_vmw_surface_arg *req, + struct drm_vmw_gb_surface_ref_ext_rep *rep, + struct drm_file *file_priv); static const struct vmw_user_resource_conv user_surface_conv = { .object_type = VMW_RES_SURFACE, @@ -1289,193 +1302,55 @@ static int vmw_gb_surface_destroy(struct vmw_resource *res) /** * vmw_gb_surface_define_ioctl - Ioctl function implementing - * the user surface define functionality. + * the user surface define functionality. * - * @dev: Pointer to a struct drm_device. - * @data: Pointer to data copied from / to user-space. - * @file_priv: Pointer to a drm file private structure. + * @dev: Pointer to a struct drm_device. + * @data: Pointer to data copied from / to user-space. + * @file_priv: Pointer to a drm file private structure. */ int vmw_gb_surface_define_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) { - struct vmw_private *dev_priv = vmw_priv(dev); - struct vmw_user_surface *user_srf; - struct vmw_surface *srf; - struct vmw_resource *res; - struct vmw_resource *tmp; union drm_vmw_gb_surface_create_arg *arg = (union drm_vmw_gb_surface_create_arg *)data; - struct drm_vmw_gb_surface_create_req *req = &arg->req; struct drm_vmw_gb_surface_create_rep *rep = &arg->rep; - struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile; - int ret; - uint32_t size; - uint32_t backup_handle = 0; - - if (req->multisample_count != 0) - return -EINVAL; - - if (req->mip_levels > DRM_VMW_MAX_MIP_LEVELS) - return -EINVAL; - - if (unlikely(vmw_user_surface_size == 0)) - vmw_user_surface_size = ttm_round_pot(sizeof(*user_srf)) + - 128; - - size = vmw_user_surface_size + 128; - - /* Define a surface based on the parameters. */ - ret = vmw_surface_gb_priv_define(dev, - size, - (SVGA3dSurfaceAllFlags)req->svga3d_flags, - req->format, - req->drm_surface_flags & drm_vmw_surface_flag_scanout, - req->mip_levels, - req->multisample_count, - req->array_size, - req->base_size, - &srf); - if (unlikely(ret != 0)) - return ret; - - user_srf = container_of(srf, struct vmw_user_surface, srf); - if (drm_is_primary_client(file_priv)) - user_srf->master = drm_master_get(file_priv->master); - - ret = ttm_read_lock(&dev_priv->reservation_sem, true); - if (unlikely(ret != 0)) - return ret; - - res = &user_srf->srf.res; - - - if (req->buffer_handle != SVGA3D_INVALID_ID) { - ret = vmw_user_bo_lookup(tfile, req->buffer_handle, - &res->backup, - &user_srf->backup_base); - if (ret == 0) { - if (res->backup->base.num_pages * PAGE_SIZE < - res->backup_size) { - DRM_ERROR("Surface backup buffer is too small.\n"); - vmw_bo_unreference(&res->backup); - ret = -EINVAL; - goto out_unlock; - } else { - backup_handle = req->buffer_handle; - } - } - } else if (req->drm_surface_flags & drm_vmw_surface_flag_create_buffer) - ret = vmw_user_bo_alloc(dev_priv, tfile, - res->backup_size, - req->drm_surface_flags & - drm_vmw_surface_flag_shareable, - &backup_handle, - &res->backup, - &user_srf->backup_base); - - if (unlikely(ret != 0)) { - vmw_resource_unreference(&res); - goto out_unlock; - } - - tmp = vmw_resource_reference(res); - ret = ttm_prime_object_init(tfile, res->backup_size, &user_srf->prime, - req->drm_surface_flags & - drm_vmw_surface_flag_shareable, - VMW_RES_SURFACE, - &vmw_user_surface_base_release, NULL); - - if (unlikely(ret != 0)) { - vmw_resource_unreference(&tmp); - vmw_resource_unreference(&res); - goto out_unlock; - } - - rep->handle = user_srf->prime.base.hash.key; - rep->backup_size = res->backup_size; - if (res->backup) { - rep->buffer_map_handle = - drm_vma_node_offset_addr(&res->backup->base.vma_node); - rep->buffer_size = res->backup->base.num_pages * PAGE_SIZE; - rep->buffer_handle = backup_handle; - } else { - rep->buffer_map_handle = 0; - rep->buffer_size = 0; - rep->buffer_handle = SVGA3D_INVALID_ID; - } + struct drm_vmw_gb_surface_create_ext_req req_ext; - vmw_resource_unreference(&res); + req_ext.base = arg->req; + req_ext.version = drm_vmw_gb_surface_v1; + req_ext.svga3d_flags_upper_32_bits = 0; + req_ext.multisample_pattern = SVGA3D_MS_PATTERN_NONE; + req_ext.quality_level = SVGA3D_MS_QUALITY_NONE; + req_ext.must_be_zero = 0; -out_unlock: - ttm_read_unlock(&dev_priv->reservation_sem); - return ret; + return vmw_gb_surface_define_internal(dev, &req_ext, rep, file_priv); } /** * vmw_gb_surface_reference_ioctl - Ioctl function implementing - * the user surface reference functionality. + * the user surface reference functionality. * - * @dev: Pointer to a struct drm_device. - * @data: Pointer to data copied from / to user-space. - * @file_priv: Pointer to a drm file private structure. + * @dev: Pointer to a struct drm_device. + * @data: Pointer to data copied from / to user-space. + * @file_priv: Pointer to a drm file private structure. */ int vmw_gb_surface_reference_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) { - struct vmw_private *dev_priv = vmw_priv(dev); union drm_vmw_gb_surface_reference_arg *arg = (union drm_vmw_gb_surface_reference_arg *)data; struct drm_vmw_surface_arg *req = &arg->req; struct drm_vmw_gb_surface_ref_rep *rep = &arg->rep; - struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile; - struct vmw_surface *srf; - struct vmw_user_surface *user_srf; - struct ttm_base_object *base; - uint32_t backup_handle; - int ret = -EINVAL; + struct drm_vmw_gb_surface_ref_ext_rep rep_ext; + int ret; + + ret = vmw_gb_surface_reference_internal(dev, req, &rep_ext, file_priv); - ret = vmw_surface_handle_reference(dev_priv, file_priv, req->sid, - req->handle_type, &base); if (unlikely(ret != 0)) return ret; - user_srf = container_of(base, struct vmw_user_surface, prime.base); - srf = &user_srf->srf; - if (!srf->res.backup) { - DRM_ERROR("Shared GB surface is missing a backup buffer.\n"); - goto out_bad_resource; - } - - mutex_lock(&dev_priv->cmdbuf_mutex); /* Protect res->backup */ - ret = vmw_user_bo_reference(tfile, srf->res.backup, &backup_handle); - mutex_unlock(&dev_priv->cmdbuf_mutex); - - if (unlikely(ret != 0)) { - DRM_ERROR("Could not add a reference to a GB surface " - "backup buffer.\n"); - (void) ttm_ref_object_base_unref(tfile, base->hash.key, - TTM_REF_USAGE); - goto out_bad_resource; - } - - rep->creq.svga3d_flags = (uint32_t)srf->flags; - rep->creq.format = srf->format; - rep->creq.mip_levels = srf->mip_levels[0]; - rep->creq.drm_surface_flags = 0; - rep->creq.multisample_count = srf->multisample_count; - rep->creq.autogen_filter = srf->autogen_filter; - rep->creq.array_size = srf->array_size; - rep->creq.buffer_handle = backup_handle; - rep->creq.base_size = srf->base_size; - rep->crep.handle = user_srf->prime.base.hash.key; - rep->crep.backup_size = srf->res.backup_size; - rep->crep.buffer_handle = backup_handle; - rep->crep.buffer_map_handle = - drm_vma_node_offset_addr(&srf->res.backup->base.vma_node); - rep->crep.buffer_size = srf->res.backup->base.num_pages * PAGE_SIZE; - -out_bad_resource: - ttm_base_object_unref(&base); + rep->creq = rep_ext.creq.base; + rep->crep = rep_ext.crep; return ret; } @@ -1493,6 +1368,8 @@ out_bad_resource: * @multisample_count: * @array_size: Surface array size. * @size: width, heigh, depth of the surface requested + * @multisample_pattern: Multisampling pattern when msaa is supported + * @quality_level: Precision settings * @user_srf_out: allocated user_srf. Set to NULL on failure. * * GB surfaces allocated by this function will not have a user mode handle, and @@ -1509,6 +1386,8 @@ int vmw_surface_gb_priv_define(struct drm_device *dev, uint32_t multisample_count, uint32_t array_size, struct drm_vmw_size size, + SVGA3dMSPattern multisample_pattern, + SVGA3dMSQualityLevel quality_level, struct vmw_surface **srf_out) { struct vmw_private *dev_priv = vmw_priv(dev); @@ -1519,7 +1398,7 @@ int vmw_surface_gb_priv_define(struct drm_device *dev, }; struct vmw_surface *srf; int ret; - u32 num_layers; + u32 num_layers = 1; *srf_out = NULL; @@ -1594,15 +1473,13 @@ int vmw_surface_gb_priv_define(struct drm_device *dev, srf->autogen_filter = SVGA3D_TEX_FILTER_NONE; srf->array_size = array_size; srf->multisample_count = multisample_count; - srf->multisample_pattern = SVGA3D_MS_PATTERN_NONE; - srf->quality_level = SVGA3D_MS_QUALITY_NONE; + srf->multisample_pattern = multisample_pattern; + srf->quality_level = quality_level; if (array_size) num_layers = array_size; else if (svga3d_flags & SVGA3D_SURFACE_CUBEMAP) num_layers = SVGA3D_MAX_SURFACE_FACES; - else - num_layers = 1; srf->res.backup_size = svga3dsurface_get_serialized_size(srf->format, @@ -1633,3 +1510,262 @@ out_unlock: ttm_read_unlock(&dev_priv->reservation_sem); return ret; } + +/** + * vmw_gb_surface_define_ext_ioctl - Ioctl function implementing + * the user surface define functionality. + * + * @dev: Pointer to a struct drm_device. + * @data: Pointer to data copied from / to user-space. + * @file_priv: Pointer to a drm file private structure. + */ +int vmw_gb_surface_define_ext_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_priv) +{ + union drm_vmw_gb_surface_create_ext_arg *arg = + (union drm_vmw_gb_surface_create_ext_arg *)data; + struct drm_vmw_gb_surface_create_ext_req *req = &arg->req; + struct drm_vmw_gb_surface_create_rep *rep = &arg->rep; + + return vmw_gb_surface_define_internal(dev, req, rep, file_priv); +} + +/** + * vmw_gb_surface_reference_ext_ioctl - Ioctl function implementing + * the user surface reference functionality. + * + * @dev: Pointer to a struct drm_device. + * @data: Pointer to data copied from / to user-space. + * @file_priv: Pointer to a drm file private structure. + */ +int vmw_gb_surface_reference_ext_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_priv) +{ + union drm_vmw_gb_surface_reference_ext_arg *arg = + (union drm_vmw_gb_surface_reference_ext_arg *)data; + struct drm_vmw_surface_arg *req = &arg->req; + struct drm_vmw_gb_surface_ref_ext_rep *rep = &arg->rep; + + return vmw_gb_surface_reference_internal(dev, req, rep, file_priv); +} + +/** + * vmw_gb_surface_define_internal - Ioctl function implementing + * the user surface define functionality. + * + * @dev: Pointer to a struct drm_device. + * @req: Request argument from user-space. + * @rep: Response argument to user-space. + * @file_priv: Pointer to a drm file private structure. + */ +static int +vmw_gb_surface_define_internal(struct drm_device *dev, + struct drm_vmw_gb_surface_create_ext_req *req, + struct drm_vmw_gb_surface_create_rep *rep, + struct drm_file *file_priv) +{ + struct vmw_private *dev_priv = vmw_priv(dev); + struct vmw_user_surface *user_srf; + struct vmw_surface *srf; + struct vmw_resource *res; + struct vmw_resource *tmp; + struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile; + int ret; + uint32_t size; + uint32_t backup_handle = 0; + SVGA3dSurfaceAllFlags svga3d_flags_64 = + SVGA3D_FLAGS_64(req->svga3d_flags_upper_32_bits, + req->base.svga3d_flags); + + if (!dev_priv->has_sm4_1) { + /* + * If SM4_1 is not support then cannot send 64-bit flag to + * device. + */ + if (req->svga3d_flags_upper_32_bits != 0) + return -EINVAL; + + if (req->base.multisample_count != 0) + return -EINVAL; + + if (req->multisample_pattern != SVGA3D_MS_PATTERN_NONE) + return -EINVAL; + + if (req->quality_level != SVGA3D_MS_QUALITY_NONE) + return -EINVAL; + } + + if (req->base.mip_levels > DRM_VMW_MAX_MIP_LEVELS) + return -EINVAL; + + if (unlikely(vmw_user_surface_size == 0)) + vmw_user_surface_size = ttm_round_pot(sizeof(*user_srf)) + + 128; + + size = vmw_user_surface_size + 128; + + /* Define a surface based on the parameters. */ + ret = vmw_surface_gb_priv_define(dev, + size, + svga3d_flags_64, + req->base.format, + req->base.drm_surface_flags & + drm_vmw_surface_flag_scanout, + req->base.mip_levels, + req->base.multisample_count, + req->base.array_size, + req->base.base_size, + req->multisample_pattern, + req->quality_level, + &srf); + if (unlikely(ret != 0)) + return ret; + + user_srf = container_of(srf, struct vmw_user_surface, srf); + if (drm_is_primary_client(file_priv)) + user_srf->master = drm_master_get(file_priv->master); + + ret = ttm_read_lock(&dev_priv->reservation_sem, true); + if (unlikely(ret != 0)) + return ret; + + res = &user_srf->srf.res; + + if (req->base.buffer_handle != SVGA3D_INVALID_ID) { + ret = vmw_user_bo_lookup(tfile, req->base.buffer_handle, + &res->backup, + &user_srf->backup_base); + if (ret == 0) { + if (res->backup->base.num_pages * PAGE_SIZE < + res->backup_size) { + DRM_ERROR("Surface backup buffer too small.\n"); + vmw_bo_unreference(&res->backup); + ret = -EINVAL; + goto out_unlock; + } else { + backup_handle = req->base.buffer_handle; + } + } + } else if (req->base.drm_surface_flags & + drm_vmw_surface_flag_create_buffer) + ret = vmw_user_bo_alloc(dev_priv, tfile, + res->backup_size, + req->base.drm_surface_flags & + drm_vmw_surface_flag_shareable, + &backup_handle, + &res->backup, + &user_srf->backup_base); + + if (unlikely(ret != 0)) { + vmw_resource_unreference(&res); + goto out_unlock; + } + + tmp = vmw_resource_reference(res); + ret = ttm_prime_object_init(tfile, res->backup_size, &user_srf->prime, + req->base.drm_surface_flags & + drm_vmw_surface_flag_shareable, + VMW_RES_SURFACE, + &vmw_user_surface_base_release, NULL); + + if (unlikely(ret != 0)) { + vmw_resource_unreference(&tmp); + vmw_resource_unreference(&res); + goto out_unlock; + } + + rep->handle = user_srf->prime.base.hash.key; + rep->backup_size = res->backup_size; + if (res->backup) { + rep->buffer_map_handle = + drm_vma_node_offset_addr(&res->backup->base.vma_node); + rep->buffer_size = res->backup->base.num_pages * PAGE_SIZE; + rep->buffer_handle = backup_handle; + } else { + rep->buffer_map_handle = 0; + rep->buffer_size = 0; + rep->buffer_handle = SVGA3D_INVALID_ID; + } + + vmw_resource_unreference(&res); + +out_unlock: + ttm_read_unlock(&dev_priv->reservation_sem); + return ret; +} + +/** + * vmw_gb_surface_reference_internal - Ioctl function implementing + * the user surface reference functionality. + * + * @dev: Pointer to a struct drm_device. + * @req: Pointer to user-space request surface arg. + * @rep: Pointer to response to user-space. + * @file_priv: Pointer to a drm file private structure. + */ +static int +vmw_gb_surface_reference_internal(struct drm_device *dev, + struct drm_vmw_surface_arg *req, + struct drm_vmw_gb_surface_ref_ext_rep *rep, + struct drm_file *file_priv) +{ + struct vmw_private *dev_priv = vmw_priv(dev); + struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile; + struct vmw_surface *srf; + struct vmw_user_surface *user_srf; + struct ttm_base_object *base; + uint32_t backup_handle; + int ret = -EINVAL; + + ret = vmw_surface_handle_reference(dev_priv, file_priv, req->sid, + req->handle_type, &base); + if (unlikely(ret != 0)) + return ret; + + user_srf = container_of(base, struct vmw_user_surface, prime.base); + srf = &user_srf->srf; + if (!srf->res.backup) { + DRM_ERROR("Shared GB surface is missing a backup buffer.\n"); + goto out_bad_resource; + } + + mutex_lock(&dev_priv->cmdbuf_mutex); /* Protect res->backup */ + ret = vmw_user_bo_reference(tfile, srf->res.backup, &backup_handle); + mutex_unlock(&dev_priv->cmdbuf_mutex); + + if (unlikely(ret != 0)) { + DRM_ERROR("Could not add a reference to a GB surface " + "backup buffer.\n"); + (void) ttm_ref_object_base_unref(tfile, base->hash.key, + TTM_REF_USAGE); + goto out_bad_resource; + } + + rep->creq.base.svga3d_flags = SVGA3D_FLAGS_LOWER_32(srf->flags); + rep->creq.base.format = srf->format; + rep->creq.base.mip_levels = srf->mip_levels[0]; + rep->creq.base.drm_surface_flags = 0; + rep->creq.base.multisample_count = srf->multisample_count; + rep->creq.base.autogen_filter = srf->autogen_filter; + rep->creq.base.array_size = srf->array_size; + rep->creq.base.buffer_handle = backup_handle; + rep->creq.base.base_size = srf->base_size; + rep->crep.handle = user_srf->prime.base.hash.key; + rep->crep.backup_size = srf->res.backup_size; + rep->crep.buffer_handle = backup_handle; + rep->crep.buffer_map_handle = + drm_vma_node_offset_addr(&srf->res.backup->base.vma_node); + rep->crep.buffer_size = srf->res.backup->base.num_pages * PAGE_SIZE; + + rep->creq.version = drm_vmw_gb_surface_v1; + rep->creq.svga3d_flags_upper_32_bits = + SVGA3D_FLAGS_UPPER_32(srf->flags); + rep->creq.multisample_pattern = srf->multisample_pattern; + rep->creq.quality_level = srf->quality_level; + rep->creq.must_be_zero = 0; + +out_bad_resource: + ttm_base_object_unref(&base); + + return ret; +} diff --git a/include/uapi/drm/vmwgfx_drm.h b/include/uapi/drm/vmwgfx_drm.h index 84e81b38ca18..68ff37d4c035 100644 --- a/include/uapi/drm/vmwgfx_drm.h +++ b/include/uapi/drm/vmwgfx_drm.h @@ -69,6 +69,8 @@ extern "C" { #define DRM_VMW_GB_SURFACE_REF 24 #define DRM_VMW_SYNCCPU 25 #define DRM_VMW_CREATE_EXTENDED_CONTEXT 26 +#define DRM_VMW_GB_SURFACE_CREATE_EXT 27 +#define DRM_VMW_GB_SURFACE_REF_EXT 28 /*************************************************************************/ /** @@ -1105,6 +1107,106 @@ struct drm_vmw_handle_close_arg { }; #define drm_vmw_unref_dmabuf_arg drm_vmw_handle_close_arg +/*************************************************************************/ +/** + * DRM_VMW_GB_SURFACE_CREATE_EXT - Create a host guest-backed surface. + * + * Allocates a surface handle and queues a create surface command + * for the host on the first use of the surface. The surface ID can + * be used as the surface ID in commands referencing the surface. + * + * This new command extends DRM_VMW_GB_SURFACE_CREATE by adding version + * parameter and 64 bit svga flag. + */ + +/** + * enum drm_vmw_surface_version + * + * @drm_vmw_surface_gb_v1: Corresponds to current gb surface format with + * svga3d surface flags split into 2, upper half and lower half. + */ +enum drm_vmw_surface_version { + drm_vmw_gb_surface_v1 +}; + +/** + * struct drm_vmw_gb_surface_create_ext_req + * + * @base: Surface create parameters. + * @version: Version of surface create ioctl. + * @svga3d_flags_upper_32_bits: Upper 32 bits of svga3d flags. + * @multisample_pattern: Multisampling pattern when msaa is supported. + * @quality_level: Precision settings for each sample. + * @must_be_zero: Reserved for future usage. + * + * Input argument to the DRM_VMW_GB_SURFACE_CREATE_EXT Ioctl. + * Part of output argument for the DRM_VMW_GB_SURFACE_REF_EXT Ioctl. + */ +struct drm_vmw_gb_surface_create_ext_req { + struct drm_vmw_gb_surface_create_req base; + enum drm_vmw_surface_version version; + uint32_t svga3d_flags_upper_32_bits; + SVGA3dMSPattern multisample_pattern; + SVGA3dMSQualityLevel quality_level; + uint64_t must_be_zero; +}; + +/** + * union drm_vmw_gb_surface_create_ext_arg + * + * @req: Input argument as described above. + * @rep: Output argument as described above. + * + * Argument to the DRM_VMW_GB_SURFACE_CREATE_EXT ioctl. + */ +union drm_vmw_gb_surface_create_ext_arg { + struct drm_vmw_gb_surface_create_rep rep; + struct drm_vmw_gb_surface_create_ext_req req; +}; + +/*************************************************************************/ +/** + * DRM_VMW_GB_SURFACE_REF_EXT - Reference a host surface. + * + * Puts a reference on a host surface with a given handle, as previously + * returned by the DRM_VMW_GB_SURFACE_CREATE_EXT ioctl. + * A reference will make sure the surface isn't destroyed while we hold + * it and will allow the calling client to use the surface handle in + * the command stream. + * + * On successful return, the Ioctl returns the surface information given + * to and returned from the DRM_VMW_GB_SURFACE_CREATE_EXT ioctl. + */ + +/** + * struct drm_vmw_gb_surface_ref_ext_rep + * + * @creq: The data used as input when the surface was created, as described + * above at "struct drm_vmw_gb_surface_create_ext_req" + * @crep: Additional data output when the surface was created, as described + * above at "struct drm_vmw_gb_surface_create_rep" + * + * Output Argument to the DRM_VMW_GB_SURFACE_REF_EXT ioctl. + */ +struct drm_vmw_gb_surface_ref_ext_rep { + struct drm_vmw_gb_surface_create_ext_req creq; + struct drm_vmw_gb_surface_create_rep crep; +}; + +/** + * union drm_vmw_gb_surface_reference_ext_arg + * + * @req: Input data as described above at "struct drm_vmw_surface_arg" + * @rep: Output data as described above at + * "struct drm_vmw_gb_surface_ref_ext_rep" + * + * Argument to the DRM_VMW_GB_SURFACE_REF Ioctl. + */ +union drm_vmw_gb_surface_reference_ext_arg { + struct drm_vmw_gb_surface_ref_ext_rep rep; + struct drm_vmw_surface_arg req; +}; + #if defined(__cplusplus) } #endif -- cgit v1.2.3 From 9b07b287aa3ef49695bfad59c1870cd942f579a8 Mon Sep 17 00:00:00 2001 From: Deepak Rawat Date: Wed, 20 Jun 2018 15:09:43 -0700 Subject: drm/vmwgfx: Expose SM4_1 param to user space A new param DRM_VMW_PARAM_SM4_1, is added for user space to determine availability of SM4.1. Minor version bump for SM4.1. Signed-off-by: Deepak Rawat Reviewed-by: Sinclair Yeh Reviewed-by: Brian Paul Reviewed-by: Thomas Hellstrom Signed-off-by: Thomas Hellstrom --- drivers/gpu/drm/vmwgfx/vmwgfx_drv.h | 6 +++--- drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c | 3 +++ include/uapi/drm/vmwgfx_drm.h | 4 ++++ 3 files changed, 10 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index a67b54e4fd50..f1b803d34c59 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -43,10 +43,10 @@ #include #define VMWGFX_DRIVER_NAME "vmwgfx" -#define VMWGFX_DRIVER_DATE "20180322" +#define VMWGFX_DRIVER_DATE "20180704" #define VMWGFX_DRIVER_MAJOR 2 -#define VMWGFX_DRIVER_MINOR 14 -#define VMWGFX_DRIVER_PATCHLEVEL 1 +#define VMWGFX_DRIVER_MINOR 15 +#define VMWGFX_DRIVER_PATCHLEVEL 0 #define VMWGFX_FILE_PAGE_OFFSET 0x00100000 #define VMWGFX_FIFO_STATIC_SIZE (1024*1024) #define VMWGFX_MAX_RELOCATIONS 2048 diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c index ac6da0da2824..e825192ca30e 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c @@ -116,6 +116,9 @@ int vmw_getparam_ioctl(struct drm_device *dev, void *data, case DRM_VMW_PARAM_DX: param->value = dev_priv->has_dx; break; + case DRM_VMW_PARAM_SM4_1: + param->value = dev_priv->has_sm4_1; + break; default: return -EINVAL; } diff --git a/include/uapi/drm/vmwgfx_drm.h b/include/uapi/drm/vmwgfx_drm.h index 68ff37d4c035..399f58317cff 100644 --- a/include/uapi/drm/vmwgfx_drm.h +++ b/include/uapi/drm/vmwgfx_drm.h @@ -82,6 +82,9 @@ extern "C" { * * DRM_VMW_PARAM_OVERLAY_IOCTL: * Does the driver support the overlay ioctl. + * + * DRM_VMW_PARAM_SM4_1 + * SM4_1 support is enabled. */ #define DRM_VMW_PARAM_NUM_STREAMS 0 @@ -98,6 +101,7 @@ extern "C" { #define DRM_VMW_PARAM_SCREEN_TARGET 11 #define DRM_VMW_PARAM_DX 12 #define DRM_VMW_PARAM_HW_CAPS2 13 +#define DRM_VMW_PARAM_SM4_1 14 /** * enum drm_vmw_handle_type - handle type for ref ioctls -- cgit v1.2.3 From 18df02fb79cb20ba4de1e02e1df41ba83f8b9bec Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Sun, 17 Jun 2018 14:05:34 +0200 Subject: dts: clk: add devicetree bindings for MAX9485 This patch adds the devicetree bindings for MAX9485, a programmable audio clock generator. Signed-off-by: Daniel Mack Reviewed-by: Rob Herring Signed-off-by: Stephen Boyd --- .../devicetree/bindings/clock/maxim,max9485.txt | 59 ++++++++++++++++++++++ include/dt-bindings/clock/maxim,max9485.h | 18 +++++++ 2 files changed, 77 insertions(+) create mode 100644 Documentation/devicetree/bindings/clock/maxim,max9485.txt create mode 100644 include/dt-bindings/clock/maxim,max9485.h (limited to 'include') diff --git a/Documentation/devicetree/bindings/clock/maxim,max9485.txt b/Documentation/devicetree/bindings/clock/maxim,max9485.txt new file mode 100644 index 000000000000..61bec1100a94 --- /dev/null +++ b/Documentation/devicetree/bindings/clock/maxim,max9485.txt @@ -0,0 +1,59 @@ +Devicetree bindings for Maxim MAX9485 Programmable Audio Clock Generator + +This device exposes 4 clocks in total: + +- MAX9485_MCLKOUT: A gated, buffered output of the input clock of 27 MHz +- MAX9485_CLKOUT: A PLL that can be configured to 16 different discrete + frequencies +- MAX9485_CLKOUT[1,2]: Two gated outputs for MAX9485_CLKOUT + +MAX9485_CLKOUT[1,2] are children of MAX9485_CLKOUT which upchain all rate set +requests. + +Required properties: +- compatible: "maxim,max9485" +- clocks: Input clock, must provice 27.000 MHz +- clock-names: Must be set to "xclk" +- #clock-cells: From common clock binding; shall be set to 1 + +Optional properties: +- reset-gpios: GPIO descriptor connected to the #RESET input pin +- vdd-supply: A regulator node for Vdd +- clock-output-names: Name of output clocks, as defined in common clock + bindings + +If not explicitly set, the output names are "mclkout", "clkout", "clkout1" +and "clkout2". + +Clocks are defined as preprocessor macros in the dt-binding header. + +Example: + + #include + + xo-27mhz: xo-27mhz { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <27000000>; + }; + + &i2c0 { + max9485: audio-clock@63 { + reg = <0x63>; + compatible = "maxim,max9485"; + clock-names = "xclk"; + clocks = <&xo-27mhz>; + reset-gpios = <&gpio 1 GPIO_ACTIVE_HIGH>; + vdd-supply = <&3v3-reg>; + #clock-cells = <1>; + }; + }; + + // Clock consumer node + + foo@0 { + compatible = "bar,foo"; + /* ... */ + clock-names = "foo-input-clk"; + clocks = <&max9485 MAX9485_CLKOUT1>; + }; diff --git a/include/dt-bindings/clock/maxim,max9485.h b/include/dt-bindings/clock/maxim,max9485.h new file mode 100644 index 000000000000..185b09ce1869 --- /dev/null +++ b/include/dt-bindings/clock/maxim,max9485.h @@ -0,0 +1,18 @@ +/* + * Copyright (C) 2018 Daniel Mack + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#ifndef __DT_BINDINGS_MAX9485_CLK_H +#define __DT_BINDINGS_MAX9485_CLK_H + +#define MAX9485_MCLKOUT 0 +#define MAX9485_CLKOUT 1 +#define MAX9485_CLKOUT1 2 +#define MAX9485_CLKOUT2 3 + +#endif /* __DT_BINDINGS_MAX9485_CLK_H */ -- cgit v1.2.3 From a2344b9e3a8c5c2064306b0d99b0e9a6c4813c08 Mon Sep 17 00:00:00 2001 From: Jaganath Kanakkassery Date: Fri, 6 Jul 2018 17:05:28 +0530 Subject: Bluetooth: Use extended scanning if controller supports This implements Set extended scan param and set extended scan enable commands and use it for start LE scan based on controller support. The new features added in these commands are setting of new PHY for scanning and setting of scan duration. Both features are disabled for now, meaning only 1M PHY is set and scan duration is set to 0 which means that scanning will be done untill scan disable is called. < HCI Command: LE Set Extended Scan Parameters (0x08|0x0041) plen 8 Own address type: Random (0x01) Filter policy: Accept all advertisement (0x00) PHYs: 0x01 Entry 0: LE 1M Type: Active (0x01) Interval: 11.250 msec (0x0012) Window: 11.250 msec (0x0012) > HCI Event: Command Complete (0x0e) plen 4 LE Set Extended Scan Parameters (0x08|0x0041) ncmd 1 Status: Success (0x00) < HCI Command: LE Set Extended Scan Enable (0x08|0x0042) plen 6 Extended scan: Enabled (0x01) Filter duplicates: Enabled (0x01) Duration: 0 msec (0x0000) Period: 0.00 sec (0x0000) > HCI Event: Command Complete (0x0e) plen 4 LE Set Extended Scan Enable (0x08|0x0042) ncmd 2 Status: Success (0x00) Signed-off-by: Jaganath Kanakkassery Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci.h | 24 +++++++++ include/net/bluetooth/hci_core.h | 4 ++ net/bluetooth/hci_event.c | 51 ++++++++++++++++++ net/bluetooth/hci_request.c | 110 ++++++++++++++++++++++++++++++--------- 4 files changed, 164 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 4af1a3a4d9b1..8c2868f439e7 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -1514,6 +1514,30 @@ struct hci_cp_le_set_default_phy { __u8 rx_phys; } __packed; +#define HCI_OP_LE_SET_EXT_SCAN_PARAMS 0x2041 +struct hci_cp_le_set_ext_scan_params { + __u8 own_addr_type; + __u8 filter_policy; + __u8 scanning_phys; + __u8 data[0]; +} __packed; + +#define LE_SCAN_PHY_1M 0x01 + +struct hci_cp_le_scan_phy_params { + __u8 type; + __le16 interval; + __le16 window; +} __packed; + +#define HCI_OP_LE_SET_EXT_SCAN_ENABLE 0x2042 +struct hci_cp_le_set_ext_scan_enable { + __u8 enable; + __u8 filter_dup; + __le16 duration; + __le16 period; +} __packed; + /* ---- HCI Events ---- */ #define HCI_EV_INQUIRY_COMPLETE 0x01 diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 409f49bd8338..cc0bde74dd45 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1158,6 +1158,10 @@ void hci_conn_del_sysfs(struct hci_conn *conn); #define bredr_sc_enabled(dev) (lmp_sc_capable(dev) && \ hci_dev_test_flag(dev, HCI_SC_ENABLED)) +/* Use ext scanning if set ext scan param and ext scan enable is supported */ +#define use_ext_scan(dev) (((dev)->commands[37] & 0x20) && \ + ((dev)->commands[37] & 0x40)) + /* ----- HCI protocols ----- */ #define HCI_PROTO_DEFER 0x01 diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 9ec07cd4ab13..15afad005d72 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -1098,6 +1098,31 @@ static void hci_cc_le_set_scan_param(struct hci_dev *hdev, struct sk_buff *skb) hci_dev_unlock(hdev); } +static void hci_cc_le_set_ext_scan_param(struct hci_dev *hdev, + struct sk_buff *skb) +{ + struct hci_cp_le_set_ext_scan_params *cp; + __u8 status = *((__u8 *) skb->data); + struct hci_cp_le_scan_phy_params *phy_param; + + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + if (status) + return; + + cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_EXT_SCAN_PARAMS); + if (!cp) + return; + + phy_param = (void *)cp->data; + + hci_dev_lock(hdev); + + hdev->le_scan_type = phy_param->type; + + hci_dev_unlock(hdev); +} + static bool has_pending_adv_report(struct hci_dev *hdev) { struct discovery_state *d = &hdev->discovery; @@ -1202,6 +1227,24 @@ static void hci_cc_le_set_scan_enable(struct hci_dev *hdev, le_set_scan_enable_complete(hdev, cp->enable); } +static void hci_cc_le_set_ext_scan_enable(struct hci_dev *hdev, + struct sk_buff *skb) +{ + struct hci_cp_le_set_ext_scan_enable *cp; + __u8 status = *((__u8 *) skb->data); + + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + if (status) + return; + + cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_EXT_SCAN_ENABLE); + if (!cp) + return; + + le_set_scan_enable_complete(hdev, cp->enable); +} + static void hci_cc_le_read_white_list_size(struct hci_dev *hdev, struct sk_buff *skb) { @@ -3079,6 +3122,14 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb, hci_cc_write_ssp_debug_mode(hdev, skb); break; + case HCI_OP_LE_SET_EXT_SCAN_PARAMS: + hci_cc_le_set_ext_scan_param(hdev, skb); + break; + + case HCI_OP_LE_SET_EXT_SCAN_ENABLE: + hci_cc_le_set_ext_scan_enable(hdev, skb); + break; + default: BT_DBG("%s opcode 0x%4.4x", hdev->name, *opcode); break; diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index 76dcc3f14cea..faf7c711234c 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -647,11 +647,22 @@ void __hci_req_update_eir(struct hci_request *req) void hci_req_add_le_scan_disable(struct hci_request *req) { - struct hci_cp_le_set_scan_enable cp; + struct hci_dev *hdev = req->hdev; - memset(&cp, 0, sizeof(cp)); - cp.enable = LE_SCAN_DISABLE; - hci_req_add(req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(cp), &cp); + if (use_ext_scan(hdev)) { + struct hci_cp_le_set_ext_scan_enable cp; + + memset(&cp, 0, sizeof(cp)); + cp.enable = LE_SCAN_DISABLE; + hci_req_add(req, HCI_OP_LE_SET_EXT_SCAN_ENABLE, sizeof(cp), + &cp); + } else { + struct hci_cp_le_set_scan_enable cp; + + memset(&cp, 0, sizeof(cp)); + cp.enable = LE_SCAN_DISABLE; + hci_req_add(req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(cp), &cp); + } } static void add_to_white_list(struct hci_request *req, @@ -770,23 +781,60 @@ static bool scan_use_rpa(struct hci_dev *hdev) static void hci_req_start_scan(struct hci_request *req, u8 type, u16 interval, u16 window, u8 own_addr_type, u8 filter_policy) { - struct hci_cp_le_set_scan_param param_cp; - struct hci_cp_le_set_scan_enable enable_cp; - - memset(¶m_cp, 0, sizeof(param_cp)); - param_cp.type = type; - param_cp.interval = cpu_to_le16(interval); - param_cp.window = cpu_to_le16(window); - param_cp.own_address_type = own_addr_type; - param_cp.filter_policy = filter_policy; - hci_req_add(req, HCI_OP_LE_SET_SCAN_PARAM, sizeof(param_cp), - ¶m_cp); + struct hci_dev *hdev = req->hdev; - memset(&enable_cp, 0, sizeof(enable_cp)); - enable_cp.enable = LE_SCAN_ENABLE; - enable_cp.filter_dup = LE_SCAN_FILTER_DUP_ENABLE; - hci_req_add(req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(enable_cp), - &enable_cp); + /* Use ext scanning if set ext scan param and ext scan enable is + * supported + */ + if (use_ext_scan(hdev)) { + struct hci_cp_le_set_ext_scan_params *ext_param_cp; + struct hci_cp_le_set_ext_scan_enable ext_enable_cp; + struct hci_cp_le_scan_phy_params *phy_params; + /* Ony single PHY (1M) is supported as of now */ + u8 data[sizeof(*ext_param_cp) + sizeof(*phy_params) * 1]; + + ext_param_cp = (void *)data; + phy_params = (void *)ext_param_cp->data; + + memset(ext_param_cp, 0, sizeof(*ext_param_cp)); + ext_param_cp->own_addr_type = own_addr_type; + ext_param_cp->filter_policy = filter_policy; + ext_param_cp->scanning_phys = LE_SCAN_PHY_1M; + + memset(phy_params, 0, sizeof(*phy_params)); + phy_params->type = type; + phy_params->interval = cpu_to_le16(interval); + phy_params->window = cpu_to_le16(window); + + hci_req_add(req, HCI_OP_LE_SET_EXT_SCAN_PARAMS, + sizeof(*ext_param_cp) + sizeof(*phy_params), + ext_param_cp); + + memset(&ext_enable_cp, 0, sizeof(ext_enable_cp)); + ext_enable_cp.enable = LE_SCAN_ENABLE; + ext_enable_cp.filter_dup = LE_SCAN_FILTER_DUP_ENABLE; + + hci_req_add(req, HCI_OP_LE_SET_EXT_SCAN_ENABLE, + sizeof(ext_enable_cp), &ext_enable_cp); + } else { + struct hci_cp_le_set_scan_param param_cp; + struct hci_cp_le_set_scan_enable enable_cp; + + memset(¶m_cp, 0, sizeof(param_cp)); + param_cp.type = type; + param_cp.interval = cpu_to_le16(interval); + param_cp.window = cpu_to_le16(window); + param_cp.own_address_type = own_addr_type; + param_cp.filter_policy = filter_policy; + hci_req_add(req, HCI_OP_LE_SET_SCAN_PARAM, sizeof(param_cp), + ¶m_cp); + + memset(&enable_cp, 0, sizeof(enable_cp)); + enable_cp.enable = LE_SCAN_ENABLE; + enable_cp.filter_dup = LE_SCAN_FILTER_DUP_ENABLE; + hci_req_add(req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(enable_cp), + &enable_cp); + } } void hci_req_add_le_passive_scan(struct hci_request *req) @@ -1948,7 +1996,6 @@ discov_stopped: static int le_scan_restart(struct hci_request *req, unsigned long opt) { struct hci_dev *hdev = req->hdev; - struct hci_cp_le_set_scan_enable cp; /* If controller is not scanning we are done. */ if (!hci_dev_test_flag(hdev, HCI_LE_SCAN)) @@ -1956,10 +2003,23 @@ static int le_scan_restart(struct hci_request *req, unsigned long opt) hci_req_add_le_scan_disable(req); - memset(&cp, 0, sizeof(cp)); - cp.enable = LE_SCAN_ENABLE; - cp.filter_dup = LE_SCAN_FILTER_DUP_ENABLE; - hci_req_add(req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(cp), &cp); + if (use_ext_scan(hdev)) { + struct hci_cp_le_set_ext_scan_enable ext_enable_cp; + + memset(&ext_enable_cp, 0, sizeof(ext_enable_cp)); + ext_enable_cp.enable = LE_SCAN_ENABLE; + ext_enable_cp.filter_dup = LE_SCAN_FILTER_DUP_ENABLE; + + hci_req_add(req, HCI_OP_LE_SET_EXT_SCAN_ENABLE, + sizeof(ext_enable_cp), &ext_enable_cp); + } else { + struct hci_cp_le_set_scan_enable cp; + + memset(&cp, 0, sizeof(cp)); + cp.enable = LE_SCAN_ENABLE; + cp.filter_dup = LE_SCAN_FILTER_DUP_ENABLE; + hci_req_add(req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(cp), &cp); + } return 0; } -- cgit v1.2.3 From c215e9397b00b3045a668120ed7dbd89f2866e74 Mon Sep 17 00:00:00 2001 From: Jaganath Kanakkassery Date: Fri, 6 Jul 2018 17:05:29 +0530 Subject: Bluetooth: Process extended ADV report event This patch enables Extended ADV report event if extended scanning is supported in the controller and process the same. The new features are not handled and for now its as good as legacy ADV report. > HCI Event: LE Meta Event (0x3e) plen 53 LE Extended Advertising Report (0x0d) Num reports: 1 Entry 0 Event type: 0x0013 Props: 0x0013 Connectable Scannable Use legacy advertising PDUs Data status: Complete Legacy PDU Type: ADV_IND (0x0013) Address type: Random (0x01) Address: DB:7E:2E:1A:85:E8 (Static) Primary PHY: LE 1M Secondary PHY: LE 1M SID: 0x00 TX power: 0 dBm RSSI: -90 dBm (0xa6) Periodic advertising invteral: 0.00 msec (0x0000) Direct address type: Public (0x00) Direct address: 00:00:00:00:00:00 (OUI 00-00-00) Data length: 0x1b 0f 09 44 65 73 69 67 6e 65 72 20 4d 6f 75 73 65 ..Designer Mouse 03 19 c2 03 02 01 05 03 03 12 18 ........... Signed-off-by: Jaganath Kanakkassery Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci.h | 26 +++++++++++++++++++++++ net/bluetooth/hci_core.c | 9 ++++++++ net/bluetooth/hci_event.c | 52 +++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 87 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 8c2868f439e7..0ec51eb14810 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -1925,6 +1925,15 @@ struct hci_ev_le_conn_complete { #define LE_ADV_SCAN_IND 0x02 #define LE_ADV_NONCONN_IND 0x03 #define LE_ADV_SCAN_RSP 0x04 +#define LE_ADV_INVALID 0x05 + +/* Legacy event types in extended adv report */ +#define LE_LEGACY_ADV_IND 0x0013 +#define LE_LEGACY_ADV_DIRECT_IND 0x0015 +#define LE_LEGACY_ADV_SCAN_IND 0x0012 +#define LE_LEGACY_NONCONN_IND 0x0010 +#define LE_LEGACY_SCAN_RSP_ADV 0x001b +#define LE_LEGACY_SCAN_RSP_ADV_SCAN 0x001a #define ADDR_LE_DEV_PUBLIC 0x00 #define ADDR_LE_DEV_RANDOM 0x01 @@ -1989,6 +1998,23 @@ struct hci_ev_le_direct_adv_info { __s8 rssi; } __packed; +#define HCI_EV_LE_EXT_ADV_REPORT 0x0d +struct hci_ev_le_ext_adv_report { + __le16 evt_type; + __u8 bdaddr_type; + bdaddr_t bdaddr; + __u8 primary_phy; + __u8 secondary_phy; + __u8 sid; + __u8 tx_power; + __s8 rssi; + __le16 interval; + __u8 direct_addr_type; + bdaddr_t direct_addr; + __u8 length; + __u8 data[0]; +} __packed; + /* Internal events generated by Bluetooth stack */ #define HCI_EV_STACK_INTERNAL 0xfd struct hci_ev_stack_internal { diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index ce2447d89ce1..e3ec2d782762 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -695,6 +695,15 @@ static int hci_init3_req(struct hci_request *req, unsigned long opt) if (hdev->commands[35] & (0x20 | 0x40)) events[1] |= 0x08; /* LE PHY Update Complete */ + /* If the controller supports LE Set Extended Scan Parameters + * and LE Set Extended Scan Enable commands, enable the + * corresponding event. + */ + if (use_ext_scan(hdev)) + events[1] |= 0x10; /* LE Extended Advertising + * Report + */ + hci_req_add(req, HCI_OP_LE_SET_EVENT_MASK, sizeof(events), events); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 15afad005d72..6c6fd4f55f23 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -5048,6 +5048,54 @@ static void hci_le_adv_report_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_dev_unlock(hdev); } +static u8 convert_legacy_evt_type(u16 evt_type) +{ + switch (evt_type) { + case LE_LEGACY_ADV_IND: + return LE_ADV_IND; + case LE_LEGACY_ADV_DIRECT_IND: + return LE_ADV_DIRECT_IND; + case LE_LEGACY_ADV_SCAN_IND: + return LE_ADV_SCAN_IND; + case LE_LEGACY_NONCONN_IND: + return LE_ADV_NONCONN_IND; + case LE_LEGACY_SCAN_RSP_ADV: + case LE_LEGACY_SCAN_RSP_ADV_SCAN: + return LE_ADV_SCAN_RSP; + } + + BT_ERR_RATELIMITED("Unknown advertising packet type: 0x%02x", + evt_type); + + return LE_ADV_INVALID; +} + +static void hci_le_ext_adv_report_evt(struct hci_dev *hdev, struct sk_buff *skb) +{ + u8 num_reports = skb->data[0]; + void *ptr = &skb->data[1]; + + hci_dev_lock(hdev); + + while (num_reports--) { + struct hci_ev_le_ext_adv_report *ev = ptr; + u8 legacy_evt_type; + u16 evt_type; + + evt_type = __le16_to_cpu(ev->evt_type); + legacy_evt_type = convert_legacy_evt_type(evt_type); + if (legacy_evt_type != LE_ADV_INVALID) { + process_adv_report(hdev, legacy_evt_type, &ev->bdaddr, + ev->bdaddr_type, NULL, 0, ev->rssi, + ev->data, ev->length); + } + + ptr += sizeof(*ev) + ev->length + 1; + } + + hci_dev_unlock(hdev); +} + static void hci_le_remote_feat_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) { @@ -5280,6 +5328,10 @@ static void hci_le_meta_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_le_direct_adv_report_evt(hdev, skb); break; + case HCI_EV_LE_EXT_ADV_REPORT: + hci_le_ext_adv_report_evt(hdev, skb); + break; + default: break; } -- cgit v1.2.3 From fc20654389364a55eeab837244b24f8da75009f6 Mon Sep 17 00:00:00 2001 From: Robert Jarzmik Date: Wed, 27 Jun 2018 21:41:23 +0200 Subject: clk: pxa: export 32kHz PLL This clock is especially used by the RTC driver, so export it so that devicetree users can use it. Signed-off-by: Robert Jarzmik Signed-off-by: Stephen Boyd --- drivers/clk/pxa/clk-pxa25x.c | 6 ++++-- drivers/clk/pxa/clk-pxa27x.c | 7 ++++--- drivers/clk/pxa/clk-pxa3xx.c | 7 ++++--- include/dt-bindings/clock/pxa-clock.h | 3 ++- 4 files changed, 14 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/drivers/clk/pxa/clk-pxa25x.c b/drivers/clk/pxa/clk-pxa25x.c index 6416c1f8e632..e88f8e01fe3a 100644 --- a/drivers/clk/pxa/clk-pxa25x.c +++ b/drivers/clk/pxa/clk-pxa25x.c @@ -292,8 +292,10 @@ static void __init pxa25x_register_plls(void) { clk_register_fixed_rate(NULL, "osc_3_6864mhz", NULL, CLK_GET_RATE_NOCACHE, 3686400); - clk_register_fixed_rate(NULL, "osc_32_768khz", NULL, - CLK_GET_RATE_NOCACHE, 32768); + clkdev_pxa_register(CLK_OSC32k768, "osc_32_768khz", NULL, + clk_register_fixed_rate(NULL, "osc_32_768khz", NULL, + CLK_GET_RATE_NOCACHE, + 32768)); clk_register_fixed_rate(NULL, "clk_dummy", NULL, 0, 0); clk_register_fixed_factor(NULL, "ppll_95_85mhz", "osc_3_6864mhz", 0, 26, 1); diff --git a/drivers/clk/pxa/clk-pxa27x.c b/drivers/clk/pxa/clk-pxa27x.c index 25a30194d27a..d40b63e7bbce 100644 --- a/drivers/clk/pxa/clk-pxa27x.c +++ b/drivers/clk/pxa/clk-pxa27x.c @@ -314,9 +314,10 @@ static void __init pxa27x_register_plls(void) clk_register_fixed_rate(NULL, "osc_13mhz", NULL, CLK_GET_RATE_NOCACHE, 13 * MHz); - clk_register_fixed_rate(NULL, "osc_32_768khz", NULL, - CLK_GET_RATE_NOCACHE, - 32768 * KHz); + clkdev_pxa_register(CLK_OSC32k768, "osc_32_768khz", NULL, + clk_register_fixed_rate(NULL, "osc_32_768khz", NULL, + CLK_GET_RATE_NOCACHE, + 32768 * KHz)); clk_register_fixed_rate(NULL, "clk_dummy", NULL, 0, 0); clk_register_fixed_factor(NULL, "ppll_312mhz", "osc_13mhz", 0, 24, 1); } diff --git a/drivers/clk/pxa/clk-pxa3xx.c b/drivers/clk/pxa/clk-pxa3xx.c index 2d126df2bccd..7aa120c3bd08 100644 --- a/drivers/clk/pxa/clk-pxa3xx.c +++ b/drivers/clk/pxa/clk-pxa3xx.c @@ -286,9 +286,10 @@ static void __init pxa3xx_register_plls(void) clk_register_fixed_rate(NULL, "osc_13mhz", NULL, CLK_GET_RATE_NOCACHE, 13 * MHz); - clk_register_fixed_rate(NULL, "osc_32_768khz", NULL, - CLK_GET_RATE_NOCACHE, - 32768); + clkdev_pxa_register(CLK_OSC32k768, "osc_32_768khz", NULL, + clk_register_fixed_rate(NULL, "osc_32_768khz", NULL, + CLK_GET_RATE_NOCACHE, + 32768)); clk_register_fixed_rate(NULL, "ring_osc_120mhz", NULL, CLK_GET_RATE_NOCACHE, 120 * MHz); diff --git a/include/dt-bindings/clock/pxa-clock.h b/include/dt-bindings/clock/pxa-clock.h index e65803b1dc7e..0b0fd2b01538 100644 --- a/include/dt-bindings/clock/pxa-clock.h +++ b/include/dt-bindings/clock/pxa-clock.h @@ -72,6 +72,7 @@ #define CLK_USIM 58 #define CLK_USIM1 59 #define CLK_USMI0 60 -#define CLK_MAX 61 +#define CLK_OSC32k768 61 +#define CLK_MAX 62 #endif -- cgit v1.2.3 From 4d94f95d30c8fbfe86068e9abed110974d697cf5 Mon Sep 17 00:00:00 2001 From: Jaganath Kanakkassery Date: Fri, 6 Jul 2018 22:50:32 +0200 Subject: Bluetooth: Use extended LE Connection if supported This implements extended LE craete connection and enhanced LE conn complete event if the controller supports. For now it is as good as legacy LE connection and event as no new features in the extended connection is handled. < HCI Command: LE Extended Create Connection (0x08|0x0043) plen 26 Filter policy: White list is not used (0x00) Own address type: Public (0x00) Peer address type: Random (0x01) Peer address: DB:7E:2E:1D:85:E8 (Static) Initiating PHYs: 0x01 Entry 0: LE 1M Scan interval: 60.000 msec (0x0060) Scan window: 60.000 msec (0x0060) Min connection interval: 50.00 msec (0x0028) Max connection interval: 70.00 msec (0x0038) Connection latency: 0 (0x0000) Supervision timeout: 420 msec (0x002a) Min connection length: 0.000 msec (0x0000) Max connection length: 0.000 msec (0x0000) > HCI Event: Command Status (0x0f) plen 4 LE Extended Create Connection (0x08|0x0043) ncmd 2 Status: Success (0x00) > HCI Event: LE Meta Event (0x3e) plen 31 LE Enhanced Connection Complete (0x0a) Status: Success (0x00) Handle: 3585 Role: Master (0x00) Peer address type: Random (0x01) Peer address: DB:7E:2E:1D:85:E8 (Static) Local resolvable private address: 00:00:00:00:00:00 (Non-Resolvable) Peer resolvable private address: 00:00:00:00:00:00 (Non-Resolvable) Connection interval: 67.50 msec (0x0036) Connection latency: 0 (0x0000) Supervision timeout: 420 msec (0x002a) Master clock accuracy: 0x00 @ MGMT Event: Device Connected (0x000b) plen 40 LE Address: DB:7E:2E:1D:85:E8 (Static) Flags: 0x00000000 Data length: 27 Name (complete): Designer Mouse Appearance: Mouse (0x03c2) Flags: 0x05 LE Limited Discoverable Mode BR/EDR Not Supported 16-bit Service UUIDs (complete): 1 entry Human Interface Device (0x1812) Signed-off-by: Jaganath Kanakkassery Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci.h | 36 ++++++++++++++++++++ include/net/bluetooth/hci_core.h | 2 ++ net/bluetooth/hci_conn.c | 72 ++++++++++++++++++++++++++++++---------- net/bluetooth/hci_core.c | 8 +++++ net/bluetooth/hci_event.c | 47 ++++++++++++++++++++++++++ 5 files changed, 147 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 0ec51eb14810..73e48be5bbb3 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -1538,6 +1538,27 @@ struct hci_cp_le_set_ext_scan_enable { __le16 period; } __packed; +#define HCI_OP_LE_EXT_CREATE_CONN 0x2043 +struct hci_cp_le_ext_create_conn { + __u8 filter_policy; + __u8 own_addr_type; + __u8 peer_addr_type; + bdaddr_t peer_addr; + __u8 phys; + __u8 data[0]; +} __packed; + +struct hci_cp_le_ext_conn_param { + __le16 scan_interval; + __le16 scan_window; + __le16 conn_interval_min; + __le16 conn_interval_max; + __le16 conn_latency; + __le16 supervision_timeout; + __le16 min_ce_len; + __le16 max_ce_len; +} __packed; + /* ---- HCI Events ---- */ #define HCI_EV_INQUIRY_COMPLETE 0x01 @@ -2015,6 +2036,21 @@ struct hci_ev_le_ext_adv_report { __u8 data[0]; } __packed; +#define HCI_EV_LE_ENHANCED_CONN_COMPLETE 0x0a +struct hci_ev_le_enh_conn_complete { + __u8 status; + __le16 handle; + __u8 role; + __u8 bdaddr_type; + bdaddr_t bdaddr; + bdaddr_t local_rpa; + bdaddr_t peer_rpa; + __le16 interval; + __le16 latency; + __le16 supervision_timeout; + __u8 clk_accurancy; +} __packed; + /* Internal events generated by Bluetooth stack */ #define HCI_EV_STACK_INTERNAL 0xfd struct hci_ev_stack_internal { diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index cc0bde74dd45..a74453571264 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1161,6 +1161,8 @@ void hci_conn_del_sysfs(struct hci_conn *conn); /* Use ext scanning if set ext scan param and ext scan enable is supported */ #define use_ext_scan(dev) (((dev)->commands[37] & 0x20) && \ ((dev)->commands[37] & 0x40)) +/* Use ext create connection if command is supported */ +#define use_ext_conn(dev) ((dev)->commands[37] & 0x80) /* ----- HCI protocols ----- */ #define HCI_PROTO_DEFER 0x01 diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 45ff5dc124cc..cc967ca67962 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -752,7 +752,6 @@ static void hci_req_add_le_create_conn(struct hci_request *req, struct hci_conn *conn, bdaddr_t *direct_rpa) { - struct hci_cp_le_create_conn cp; struct hci_dev *hdev = conn->hdev; u8 own_addr_type; @@ -775,25 +774,62 @@ static void hci_req_add_le_create_conn(struct hci_request *req, return; } - memset(&cp, 0, sizeof(cp)); + if (use_ext_conn(hdev)) { + struct hci_cp_le_ext_create_conn *cp; + struct hci_cp_le_ext_conn_param *p; + /* As of now only LE 1M is supported */ + u8 data[sizeof(*cp) + sizeof(*p) * 1]; - /* Set window to be the same value as the interval to enable - * continuous scanning. - */ - cp.scan_interval = cpu_to_le16(hdev->le_scan_interval); - cp.scan_window = cp.scan_interval; + cp = (void *) data; + p = (void *) cp->data; - bacpy(&cp.peer_addr, &conn->dst); - cp.peer_addr_type = conn->dst_type; - cp.own_address_type = own_addr_type; - cp.conn_interval_min = cpu_to_le16(conn->le_conn_min_interval); - cp.conn_interval_max = cpu_to_le16(conn->le_conn_max_interval); - cp.conn_latency = cpu_to_le16(conn->le_conn_latency); - cp.supervision_timeout = cpu_to_le16(conn->le_supv_timeout); - cp.min_ce_len = cpu_to_le16(0x0000); - cp.max_ce_len = cpu_to_le16(0x0000); - - hci_req_add(req, HCI_OP_LE_CREATE_CONN, sizeof(cp), &cp); + memset(cp, 0, sizeof(*cp)); + + bacpy(&cp->peer_addr, &conn->dst); + cp->peer_addr_type = conn->dst_type; + cp->own_addr_type = own_addr_type; + cp->phys = LE_SCAN_PHY_1M; + + memset(p, 0, sizeof(*p)); + + /* Set window to be the same value as the interval to enable + * continuous scanning. + */ + + p->scan_interval = cpu_to_le16(hdev->le_scan_interval); + p->scan_window = p->scan_interval; + p->conn_interval_min = cpu_to_le16(conn->le_conn_min_interval); + p->conn_interval_max = cpu_to_le16(conn->le_conn_max_interval); + p->conn_latency = cpu_to_le16(conn->le_conn_latency); + p->supervision_timeout = cpu_to_le16(conn->le_supv_timeout); + p->min_ce_len = cpu_to_le16(0x0000); + p->max_ce_len = cpu_to_le16(0x0000); + + hci_req_add(req, HCI_OP_LE_EXT_CREATE_CONN, sizeof(data), data); + + } else { + struct hci_cp_le_create_conn cp; + + memset(&cp, 0, sizeof(cp)); + + /* Set window to be the same value as the interval to enable + * continuous scanning. + */ + cp.scan_interval = cpu_to_le16(hdev->le_scan_interval); + cp.scan_window = cp.scan_interval; + + bacpy(&cp.peer_addr, &conn->dst); + cp.peer_addr_type = conn->dst_type; + cp.own_address_type = own_addr_type; + cp.conn_interval_min = cpu_to_le16(conn->le_conn_min_interval); + cp.conn_interval_max = cpu_to_le16(conn->le_conn_max_interval); + cp.conn_latency = cpu_to_le16(conn->le_conn_latency); + cp.supervision_timeout = cpu_to_le16(conn->le_supv_timeout); + cp.min_ce_len = cpu_to_le16(0x0000); + cp.max_ce_len = cpu_to_le16(0x0000); + + hci_req_add(req, HCI_OP_LE_CREATE_CONN, sizeof(cp), &cp); + } conn->state = BT_CONNECT; clear_bit(HCI_CONN_SCANNING, &conn->flags); diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index e3ec2d782762..f5c21004186c 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -704,6 +704,14 @@ static int hci_init3_req(struct hci_request *req, unsigned long opt) * Report */ + /* If the controller supports the LE Extended Create Connection + * command, enable the corresponding event. + */ + if (use_ext_conn(hdev)) + events[1] |= 0x02; /* LE Enhanced Connection + * Complete + */ + hci_req_add(req, HCI_OP_LE_SET_EVENT_MASK, sizeof(events), events); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 14e42e157de9..68192152c23b 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -2031,6 +2031,31 @@ static void hci_cs_le_create_conn(struct hci_dev *hdev, u8 status) hci_dev_unlock(hdev); } +static void hci_cs_le_ext_create_conn(struct hci_dev *hdev, u8 status) +{ + struct hci_cp_le_ext_create_conn *cp; + + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + /* All connection failure handling is taken care of by the + * hci_le_conn_failed function which is triggered by the HCI + * request completion callbacks used for connecting. + */ + if (status) + return; + + cp = hci_sent_cmd_data(hdev, HCI_OP_LE_EXT_CREATE_CONN); + if (!cp) + return; + + hci_dev_lock(hdev); + + cs_le_create_conn(hdev, &cp->peer_addr, cp->peer_addr_type, + cp->own_addr_type, cp->filter_policy); + + hci_dev_unlock(hdev); +} + static void hci_cs_le_read_remote_features(struct hci_dev *hdev, u8 status) { struct hci_cp_le_read_remote_features *cp; @@ -3233,6 +3258,10 @@ static void hci_cmd_status_evt(struct hci_dev *hdev, struct sk_buff *skb, hci_cs_le_start_enc(hdev, ev->status); break; + case HCI_OP_LE_EXT_CREATE_CONN: + hci_cs_le_ext_create_conn(hdev, ev->status); + break; + default: BT_DBG("%s opcode 0x%4.4x", hdev->name, *opcode); break; @@ -4733,6 +4762,20 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) le16_to_cpu(ev->supervision_timeout)); } +static void hci_le_enh_conn_complete_evt(struct hci_dev *hdev, + struct sk_buff *skb) +{ + struct hci_ev_le_enh_conn_complete *ev = (void *) skb->data; + + BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); + + le_conn_complete_evt(hdev, ev->status, &ev->bdaddr, ev->bdaddr_type, + ev->role, le16_to_cpu(ev->handle), + le16_to_cpu(ev->interval), + le16_to_cpu(ev->latency), + le16_to_cpu(ev->supervision_timeout)); +} + static void hci_le_conn_update_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) { @@ -5352,6 +5395,10 @@ static void hci_le_meta_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_le_ext_adv_report_evt(hdev, skb); break; + case HCI_EV_LE_ENHANCED_CONN_COMPLETE: + hci_le_enh_conn_complete_evt(hdev, skb); + break; + default: break; } -- cgit v1.2.3 From cd88259a7215e0737f8ef2c2842f41922ae87d8d Mon Sep 17 00:00:00 2001 From: Lei YU Date: Tue, 26 Jun 2018 09:55:25 +0800 Subject: clk: aspeed: Fix SDCLK name The SDCLK was named SDCLKCLK, and no one has used this yet. Fix it. Signed-off-by: Lei YU Acked-by: Rob Herring Signed-off-by: Stephen Boyd --- drivers/clk/clk-aspeed.c | 2 +- include/dt-bindings/clock/aspeed-clock.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/clk/clk-aspeed.c b/drivers/clk/clk-aspeed.c index 38b366b00c57..f49c6842c604 100644 --- a/drivers/clk/clk-aspeed.c +++ b/drivers/clk/clk-aspeed.c @@ -109,7 +109,7 @@ static const struct aspeed_gate_data aspeed_gates[] = { [ASPEED_CLK_GATE_RSACLK] = { 24, -1, "rsaclk-gate", NULL, 0 }, /* RSA */ [ASPEED_CLK_GATE_UART3CLK] = { 25, -1, "uart3clk-gate", "uart", 0 }, /* UART3 */ [ASPEED_CLK_GATE_UART4CLK] = { 26, -1, "uart4clk-gate", "uart", 0 }, /* UART4 */ - [ASPEED_CLK_GATE_SDCLKCLK] = { 27, 16, "sdclk-gate", NULL, 0 }, /* SDIO/SD */ + [ASPEED_CLK_GATE_SDCLK] = { 27, 16, "sdclk-gate", NULL, 0 }, /* SDIO/SD */ [ASPEED_CLK_GATE_LHCCLK] = { 28, -1, "lhclk-gate", "lhclk", 0 }, /* LPC master/LPC+ */ }; diff --git a/include/dt-bindings/clock/aspeed-clock.h b/include/dt-bindings/clock/aspeed-clock.h index 44761849fcbe..f43738607d77 100644 --- a/include/dt-bindings/clock/aspeed-clock.h +++ b/include/dt-bindings/clock/aspeed-clock.h @@ -25,7 +25,7 @@ #define ASPEED_CLK_GATE_RSACLK 19 #define ASPEED_CLK_GATE_UART3CLK 20 #define ASPEED_CLK_GATE_UART4CLK 21 -#define ASPEED_CLK_GATE_SDCLKCLK 22 +#define ASPEED_CLK_GATE_SDCLK 22 #define ASPEED_CLK_GATE_LHCCLK 23 #define ASPEED_CLK_HPLL 24 #define ASPEED_CLK_AHB 25 -- cgit v1.2.3 From 9d8108f9f3cb996a9677223fcd1feeb1f3e05566 Mon Sep 17 00:00:00 2001 From: Anson Huang Date: Fri, 22 Jun 2018 14:32:33 +0800 Subject: clk: imx6sll: add GPIO LPCGs According to Reference Manual Rev.0, 06/2017, there are GPIO LPCGs defined in CCM CCGRs, add them into clock tree. Signed-off-by: Anson Huang Reviewed-by: Fabio Estevam Acked-by: Rob Herring Signed-off-by: Stephen Boyd --- drivers/clk/imx/clk-imx6sll.c | 6 ++++++ include/dt-bindings/clock/imx6sll-clock.h | 9 ++++++++- 2 files changed, 14 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/clk/imx/clk-imx6sll.c b/drivers/clk/imx/clk-imx6sll.c index 3651c77fbabe..627064597af9 100644 --- a/drivers/clk/imx/clk-imx6sll.c +++ b/drivers/clk/imx/clk-imx6sll.c @@ -253,6 +253,7 @@ static void __init imx6sll_clocks_init(struct device_node *ccm_node) clks[IMX6SLL_CLK_DCP] = imx_clk_gate2("dcp", "ahb", base + 0x68, 10); clks[IMX6SLL_CLK_UART2_IPG] = imx_clk_gate2("uart2_ipg", "ipg", base + 0x68, 28); clks[IMX6SLL_CLK_UART2_SERIAL] = imx_clk_gate2("uart2_serial", "uart_podf", base + 0x68, 28); + clks[IMX6SLL_CLK_GPIO2] = imx_clk_gate2("gpio2", "ipg", base + 0x68, 30); /* CCGR1 */ clks[IMX6SLL_CLK_ECSPI1] = imx_clk_gate2("ecspi1", "ecspi_podf", base + 0x6c, 0); @@ -267,13 +268,17 @@ static void __init imx6sll_clocks_init(struct device_node *ccm_node) clks[IMX6SLL_CLK_GPT_SERIAL] = imx_clk_gate2("gpt1_serial", "perclk", base + 0x6c, 22); clks[IMX6SLL_CLK_UART4_IPG] = imx_clk_gate2("uart4_ipg", "ipg", base + 0x6c, 24); clks[IMX6SLL_CLK_UART4_SERIAL] = imx_clk_gate2("uart4_serail", "uart_podf", base + 0x6c, 24); + clks[IMX6SLL_CLK_GPIO1] = imx_clk_gate2("gpio1", "ipg", base + 0x6c, 26); + clks[IMX6SLL_CLK_GPIO5] = imx_clk_gate2("gpio5", "ipg", base + 0x6c, 30); /* CCGR2 */ + clks[IMX6SLL_CLK_GPIO6] = imx_clk_gate2("gpio6", "ipg", base + 0x70, 0); clks[IMX6SLL_CLK_CSI] = imx_clk_gate2("csi", "axi", base + 0x70, 2); clks[IMX6SLL_CLK_I2C1] = imx_clk_gate2("i2c1", "perclk", base + 0x70, 6); clks[IMX6SLL_CLK_I2C2] = imx_clk_gate2("i2c2", "perclk", base + 0x70, 8); clks[IMX6SLL_CLK_I2C3] = imx_clk_gate2("i2c3", "perclk", base + 0x70, 10); clks[IMX6SLL_CLK_OCOTP] = imx_clk_gate2("ocotp", "ipg", base + 0x70, 12); + clks[IMX6SLL_CLK_GPIO3] = imx_clk_gate2("gpio3", "ipg", base + 0x70, 26); clks[IMX6SLL_CLK_LCDIF_APB] = imx_clk_gate2("lcdif_apb", "axi", base + 0x70, 28); clks[IMX6SLL_CLK_PXP] = imx_clk_gate2("pxp", "axi", base + 0x70, 30); @@ -283,6 +288,7 @@ static void __init imx6sll_clocks_init(struct device_node *ccm_node) clks[IMX6SLL_CLK_EPDC_AXI] = imx_clk_gate2("epdc_aclk", "axi", base + 0x74, 4); clks[IMX6SLL_CLK_EPDC_PIX] = imx_clk_gate2("epdc_pix", "epdc_podf", base + 0x74, 4); clks[IMX6SLL_CLK_LCDIF_PIX] = imx_clk_gate2("lcdif_pix", "lcdif_podf", base + 0x74, 10); + clks[IMX6SLL_CLK_GPIO4] = imx_clk_gate2("gpio4", "ipg", base + 0x74, 12); clks[IMX6SLL_CLK_WDOG1] = imx_clk_gate2("wdog1", "ipg", base + 0x74, 16); clks[IMX6SLL_CLK_MMDC_P0_FAST] = imx_clk_gate_flags("mmdc_p0_fast", "mmdc_podf", base + 0x74, 20, CLK_IS_CRITICAL); clks[IMX6SLL_CLK_MMDC_P0_IPG] = imx_clk_gate2_flags("mmdc_p0_ipg", "ipg", base + 0x74, 24, CLK_IS_CRITICAL); diff --git a/include/dt-bindings/clock/imx6sll-clock.h b/include/dt-bindings/clock/imx6sll-clock.h index 151111e68f4f..1036475f997d 100644 --- a/include/dt-bindings/clock/imx6sll-clock.h +++ b/include/dt-bindings/clock/imx6sll-clock.h @@ -197,6 +197,13 @@ #define IMX6SLL_CLK_EXTERN_AUDIO_PODF 171 #define IMX6SLL_CLK_EXTERN_AUDIO 172 -#define IMX6SLL_CLK_END 173 +#define IMX6SLL_CLK_GPIO1 173 +#define IMX6SLL_CLK_GPIO2 174 +#define IMX6SLL_CLK_GPIO3 175 +#define IMX6SLL_CLK_GPIO4 176 +#define IMX6SLL_CLK_GPIO5 177 +#define IMX6SLL_CLK_GPIO6 178 + +#define IMX6SLL_CLK_END 179 #endif /* __DT_BINDINGS_CLOCK_IMX6SLL_H */ -- cgit v1.2.3 From 06ae48269d1e0324d806fca30fe77112f4a4a14a Mon Sep 17 00:00:00 2001 From: Jiong Wang Date: Fri, 6 Jul 2018 15:13:18 -0700 Subject: lib: reciprocal_div: implement the improved algorithm on the paper mentioned The new added "reciprocal_value_adv" implements the advanced version of the algorithm described in Figure 4.2 of the paper except when "divisor > (1U << 31)" whose ceil(log2(d)) result will be 32 which then requires u128 divide on host. The exception case could be easily handled before calling "reciprocal_value_adv". The advanced version requires more complex calculation to get the reciprocal multiplier and other control variables, but then could reduce the required emulation operations. It makes no sense to use this advanced version for host divide emulation, those extra complexities for calculating multiplier etc could completely waive our saving on emulation operations. However, it makes sense to use it for JIT divide code generation (for example eBPF JIT backends) for which we are willing to trade performance of JITed code with that of host. As shown by the following pseudo code, the required emulation operations could go down from 6 (the basic version) to 3 or 4. To use the result of "reciprocal_value_adv", suppose we want to calculate n/d, the C-style pseudo code will be the following, it could be easily changed to real code generation for other JIT targets. struct reciprocal_value_adv rvalue; u8 pre_shift, exp; // handle exception case. if (d >= (1U << 31)) { result = n >= d; return; } rvalue = reciprocal_value_adv(d, 32) exp = rvalue.exp; if (rvalue.is_wide_m && !(d & 1)) { // floor(log2(d & (2^32 -d))) pre_shift = fls(d & -d) - 1; rvalue = reciprocal_value_adv(d >> pre_shift, 32 - pre_shift); } else { pre_shift = 0; } // code generation starts. if (imm == 1U << exp) { result = n >> exp; } else if (rvalue.is_wide_m) { // pre_shift must be zero when reached here. t = (n * rvalue.m) >> 32; result = n - t; result >>= 1; result += t; result >>= rvalue.sh - 1; } else { if (pre_shift) result = n >> pre_shift; result = ((u64)result * rvalue.m) >> 32; result >>= rvalue.sh; } Signed-off-by: Jiong Wang Reviewed-by: Jakub Kicinski Signed-off-by: Daniel Borkmann --- include/linux/reciprocal_div.h | 68 ++++++++++++++++++++++++++++++++++++++++++ lib/reciprocal_div.c | 41 +++++++++++++++++++++++++ 2 files changed, 109 insertions(+) (limited to 'include') diff --git a/include/linux/reciprocal_div.h b/include/linux/reciprocal_div.h index e031e9f2f9d8..585ce89c0f33 100644 --- a/include/linux/reciprocal_div.h +++ b/include/linux/reciprocal_div.h @@ -25,6 +25,9 @@ struct reciprocal_value { u8 sh1, sh2; }; +/* "reciprocal_value" and "reciprocal_divide" together implement the basic + * version of the algorithm described in Figure 4.1 of the paper. + */ struct reciprocal_value reciprocal_value(u32 d); static inline u32 reciprocal_divide(u32 a, struct reciprocal_value R) @@ -33,4 +36,69 @@ static inline u32 reciprocal_divide(u32 a, struct reciprocal_value R) return (t + ((a - t) >> R.sh1)) >> R.sh2; } +struct reciprocal_value_adv { + u32 m; + u8 sh, exp; + bool is_wide_m; +}; + +/* "reciprocal_value_adv" implements the advanced version of the algorithm + * described in Figure 4.2 of the paper except when "divisor > (1U << 31)" whose + * ceil(log2(d)) result will be 32 which then requires u128 divide on host. The + * exception case could be easily handled before calling "reciprocal_value_adv". + * + * The advanced version requires more complex calculation to get the reciprocal + * multiplier and other control variables, but then could reduce the required + * emulation operations. + * + * It makes no sense to use this advanced version for host divide emulation, + * those extra complexities for calculating multiplier etc could completely + * waive our saving on emulation operations. + * + * However, it makes sense to use it for JIT divide code generation for which + * we are willing to trade performance of JITed code with that of host. As shown + * by the following pseudo code, the required emulation operations could go down + * from 6 (the basic version) to 3 or 4. + * + * To use the result of "reciprocal_value_adv", suppose we want to calculate + * n/d, the pseudo C code will be: + * + * struct reciprocal_value_adv rvalue; + * u8 pre_shift, exp; + * + * // handle exception case. + * if (d >= (1U << 31)) { + * result = n >= d; + * return; + * } + * + * rvalue = reciprocal_value_adv(d, 32) + * exp = rvalue.exp; + * if (rvalue.is_wide_m && !(d & 1)) { + * // floor(log2(d & (2^32 -d))) + * pre_shift = fls(d & -d) - 1; + * rvalue = reciprocal_value_adv(d >> pre_shift, 32 - pre_shift); + * } else { + * pre_shift = 0; + * } + * + * // code generation starts. + * if (imm == 1U << exp) { + * result = n >> exp; + * } else if (rvalue.is_wide_m) { + * // pre_shift must be zero when reached here. + * t = (n * rvalue.m) >> 32; + * result = n - t; + * result >>= 1; + * result += t; + * result >>= rvalue.sh - 1; + * } else { + * if (pre_shift) + * result = n >> pre_shift; + * result = ((u64)result * rvalue.m) >> 32; + * result >>= rvalue.sh; + * } + */ +struct reciprocal_value_adv reciprocal_value_adv(u32 d, u8 prec); + #endif /* _LINUX_RECIPROCAL_DIV_H */ diff --git a/lib/reciprocal_div.c b/lib/reciprocal_div.c index fcb4ce682c6f..bf043258fa00 100644 --- a/lib/reciprocal_div.c +++ b/lib/reciprocal_div.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#include #include #include #include @@ -26,3 +27,43 @@ struct reciprocal_value reciprocal_value(u32 d) return R; } EXPORT_SYMBOL(reciprocal_value); + +struct reciprocal_value_adv reciprocal_value_adv(u32 d, u8 prec) +{ + struct reciprocal_value_adv R; + u32 l, post_shift; + u64 mhigh, mlow; + + /* ceil(log2(d)) */ + l = fls(d - 1); + /* NOTE: mlow/mhigh could overflow u64 when l == 32. This case needs to + * be handled before calling "reciprocal_value_adv", please see the + * comment at include/linux/reciprocal_div.h. + */ + WARN(l == 32, + "ceil(log2(0x%08x)) == 32, %s doesn't support such divisor", + d, __func__); + post_shift = l; + mlow = 1ULL << (32 + l); + do_div(mlow, d); + mhigh = (1ULL << (32 + l)) + (1ULL << (32 + l - prec)); + do_div(mhigh, d); + + for (; post_shift > 0; post_shift--) { + u64 lo = mlow >> 1, hi = mhigh >> 1; + + if (lo >= hi) + break; + + mlow = lo; + mhigh = hi; + } + + R.m = (u32)mhigh; + R.sh = post_shift; + R.exp = l; + R.is_wide_m = mhigh > U32_MAX; + + return R; +} +EXPORT_SYMBOL(reciprocal_value_adv); -- cgit v1.2.3 From 6c79d12e945e85556674a04cde13657a5d7943da Mon Sep 17 00:00:00 2001 From: Taniya Das Date: Sat, 23 Jun 2018 19:49:26 +0530 Subject: dt-bindings: clock: Introduce QCOM Display clock bindings Add device tree bindings for display clock controller for Qualcomm Technology Inc's SDM845 SoCs. Signed-off-by: Taniya Das Reviewed-by: Rob Herring Signed-off-by: Stephen Boyd --- .../devicetree/bindings/clock/qcom,dispcc.txt | 19 +++++++++ include/dt-bindings/clock/qcom,dispcc-sdm845.h | 45 ++++++++++++++++++++++ 2 files changed, 64 insertions(+) create mode 100644 Documentation/devicetree/bindings/clock/qcom,dispcc.txt create mode 100644 include/dt-bindings/clock/qcom,dispcc-sdm845.h (limited to 'include') diff --git a/Documentation/devicetree/bindings/clock/qcom,dispcc.txt b/Documentation/devicetree/bindings/clock/qcom,dispcc.txt new file mode 100644 index 000000000000..d639e18d0b85 --- /dev/null +++ b/Documentation/devicetree/bindings/clock/qcom,dispcc.txt @@ -0,0 +1,19 @@ +Qualcomm Technologies, Inc. Display Clock Controller Binding +------------------------------------------------------------ + +Required properties : + +- compatible : shall contain "qcom,sdm845-dispcc" +- reg : shall contain base register location and length. +- #clock-cells : from common clock binding, shall contain 1. +- #reset-cells : from common reset binding, shall contain 1. +- #power-domain-cells : from generic power domain binding, shall contain 1. + +Example: + dispcc: clock-controller@af00000 { + compatible = "qcom,sdm845-dispcc"; + reg = <0xaf00000 0x100000>; + #clock-cells = <1>; + #reset-cells = <1>; + #power-domain-cells = <1>; + }; diff --git a/include/dt-bindings/clock/qcom,dispcc-sdm845.h b/include/dt-bindings/clock/qcom,dispcc-sdm845.h new file mode 100644 index 000000000000..11eed4bc9646 --- /dev/null +++ b/include/dt-bindings/clock/qcom,dispcc-sdm845.h @@ -0,0 +1,45 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2018, The Linux Foundation. All rights reserved. + */ + +#ifndef _DT_BINDINGS_CLK_SDM_DISP_CC_SDM845_H +#define _DT_BINDINGS_CLK_SDM_DISP_CC_SDM845_H + +/* DISP_CC clock registers */ +#define DISP_CC_MDSS_AHB_CLK 0 +#define DISP_CC_MDSS_AXI_CLK 1 +#define DISP_CC_MDSS_BYTE0_CLK 2 +#define DISP_CC_MDSS_BYTE0_CLK_SRC 3 +#define DISP_CC_MDSS_BYTE0_INTF_CLK 4 +#define DISP_CC_MDSS_BYTE1_CLK 5 +#define DISP_CC_MDSS_BYTE1_CLK_SRC 6 +#define DISP_CC_MDSS_BYTE1_INTF_CLK 7 +#define DISP_CC_MDSS_ESC0_CLK 8 +#define DISP_CC_MDSS_ESC0_CLK_SRC 9 +#define DISP_CC_MDSS_ESC1_CLK 10 +#define DISP_CC_MDSS_ESC1_CLK_SRC 11 +#define DISP_CC_MDSS_MDP_CLK 12 +#define DISP_CC_MDSS_MDP_CLK_SRC 13 +#define DISP_CC_MDSS_MDP_LUT_CLK 14 +#define DISP_CC_MDSS_PCLK0_CLK 15 +#define DISP_CC_MDSS_PCLK0_CLK_SRC 16 +#define DISP_CC_MDSS_PCLK1_CLK 17 +#define DISP_CC_MDSS_PCLK1_CLK_SRC 18 +#define DISP_CC_MDSS_ROT_CLK 19 +#define DISP_CC_MDSS_ROT_CLK_SRC 20 +#define DISP_CC_MDSS_RSCC_AHB_CLK 21 +#define DISP_CC_MDSS_RSCC_VSYNC_CLK 22 +#define DISP_CC_MDSS_VSYNC_CLK 23 +#define DISP_CC_MDSS_VSYNC_CLK_SRC 24 +#define DISP_CC_PLL0 25 +#define DISP_CC_MDSS_BYTE0_DIV_CLK_SRC 26 +#define DISP_CC_MDSS_BYTE1_DIV_CLK_SRC 27 + +/* DISP_CC Reset */ +#define DISP_CC_MDSS_RSCC_BCR 0 + +/* DISP_CC GDSCR */ +#define MDSS_GDSC 0 + +#endif -- cgit v1.2.3 From 351782067b6be81879b0af0daf7bd3acbb32d986 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Fri, 6 Jul 2018 10:12:54 -0400 Subject: ipv4: ipcm_cookie initializers Initialize the cookie in one location to reduce code duplication and avoid bugs from inconsistent initialization, such as that fixed in commit 9887cba19978 ("ip: limit use of gso_size to udp"). Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/net/ip.h | 15 +++++++++++++++ net/ipv4/icmp.c | 11 ++--------- net/ipv4/ip_output.c | 6 +----- net/ipv4/ping.c | 9 +-------- net/ipv4/raw.c | 9 +-------- net/ipv4/udp.c | 10 +--------- 6 files changed, 21 insertions(+), 39 deletions(-) (limited to 'include') diff --git a/include/net/ip.h b/include/net/ip.h index 99d1b835d2aa..6db23bf1e5eb 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -79,6 +79,21 @@ struct ipcm_cookie { __u16 gso_size; }; +static inline void ipcm_init(struct ipcm_cookie *ipcm) +{ + *ipcm = (struct ipcm_cookie) { .tos = -1 }; +} + +static inline void ipcm_init_sk(struct ipcm_cookie *ipcm, + const struct inet_sock *inet) +{ + ipcm_init(ipcm); + + ipcm->sockc.tsflags = inet->sk.sk_tsflags; + ipcm->oif = inet->sk.sk_bound_dev_if; + ipcm->addr = inet->inet_saddr; +} + #define IPCB(skb) ((struct inet_skb_parm*)((skb)->cb)) #define PKTINFO_SKB_CB(skb) ((struct in_pktinfo *)((skb)->cb)) diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 937239afd68d..695979b7ef6d 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -429,15 +429,11 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) icmp_param->data.icmph.checksum = 0; + ipcm_init(&ipc); inet->tos = ip_hdr(skb)->tos; sk->sk_mark = mark; daddr = ipc.addr = ip_hdr(skb)->saddr; saddr = fib_compute_spec_dst(skb); - ipc.opt = NULL; - ipc.tx_flags = 0; - ipc.ttl = 0; - ipc.tos = -1; - ipc.sockc.transmit_time = 0; if (icmp_param->replyopts.opt.opt.optlen) { ipc.opt = &icmp_param->replyopts.opt; @@ -711,12 +707,9 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) icmp_param.offset = skb_network_offset(skb_in); inet_sk(sk)->tos = tos; sk->sk_mark = mark; + ipcm_init(&ipc); ipc.addr = iph->saddr; ipc.opt = &icmp_param.replyopts.opt; - ipc.tx_flags = 0; - ipc.ttl = 0; - ipc.tos = -1; - ipc.sockc.transmit_time = 0; rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos, mark, type, code, &icmp_param); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 570e3ebc3974..81d0e4a77ec5 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1548,12 +1548,8 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, if (__ip_options_echo(net, &replyopts.opt.opt, skb, sopt)) return; + ipcm_init(&ipc); ipc.addr = daddr; - ipc.opt = NULL; - ipc.tx_flags = 0; - ipc.ttl = 0; - ipc.tos = -1; - ipc.sockc.transmit_time = 0; if (replyopts.opt.opt.optlen) { ipc.opt = &replyopts.opt; diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index b47492205507..6f17fc8ebbdb 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -739,14 +739,7 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) /* no remote port */ } - ipc.sockc.tsflags = sk->sk_tsflags; - ipc.addr = inet->inet_saddr; - ipc.opt = NULL; - ipc.oif = sk->sk_bound_dev_if; - ipc.tx_flags = 0; - ipc.ttl = 0; - ipc.tos = -1; - ipc.sockc.transmit_time = 0; + ipcm_init_sk(&ipc, inet); if (msg->msg_controllen) { err = ip_cmsg_send(sk, msg, &ipc, false); diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 446af7be2b55..cf142909389c 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -562,14 +562,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) daddr = inet->inet_daddr; } - ipc.sockc.tsflags = sk->sk_tsflags; - ipc.sockc.transmit_time = 0; - ipc.addr = inet->inet_saddr; - ipc.opt = NULL; - ipc.tx_flags = 0; - ipc.ttl = 0; - ipc.tos = -1; - ipc.oif = sk->sk_bound_dev_if; + ipcm_init_sk(&ipc, inet); if (msg->msg_controllen) { err = ip_cmsg_send(sk, msg, &ipc, false); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 5c76ba0666ec..87f3a0b77864 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -926,12 +926,6 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (msg->msg_flags & MSG_OOB) /* Mirror BSD error message compatibility */ return -EOPNOTSUPP; - ipc.opt = NULL; - ipc.tx_flags = 0; - ipc.ttl = 0; - ipc.tos = -1; - ipc.sockc.transmit_time = 0; - getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag; fl4 = &inet->cork.fl.u.ip4; @@ -978,9 +972,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) connected = 1; } - ipc.sockc.tsflags = sk->sk_tsflags; - ipc.addr = inet->inet_saddr; - ipc.oif = sk->sk_bound_dev_if; + ipcm_init_sk(&ipc, inet); ipc.gso_size = up->gso_size; if (msg->msg_controllen) { -- cgit v1.2.3 From b515430ac9c25d5192cf498af3c6be6c4f51caad Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Fri, 6 Jul 2018 10:12:55 -0400 Subject: ipv6: ipcm6_cookie initializer Initialize the cookie in one location to reduce code duplication and avoid bugs from inconsistent initialization, such as that fixed in commit 9887cba19978 ("ip: limit use of gso_size to udp"). Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/net/ipv6.h | 19 +++++++++++++++++++ net/ipv6/icmp.c | 7 ++----- net/ipv6/ping.c | 4 +--- net/ipv6/raw.c | 5 +---- net/ipv6/udp.c | 4 +--- net/l2tp/l2tp_ip6.c | 4 +--- 6 files changed, 25 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index b7843e0b16ee..6cb247f54d4c 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -301,6 +301,25 @@ struct ipcm6_cookie { __u16 gso_size; }; +static inline void ipcm6_init(struct ipcm6_cookie *ipc6) +{ + *ipc6 = (struct ipcm6_cookie) { + .hlimit = -1, + .tclass = -1, + .dontfrag = -1, + }; +} + +static inline void ipcm6_init_sk(struct ipcm6_cookie *ipc6, + const struct ipv6_pinfo *np) +{ + *ipc6 = (struct ipcm6_cookie) { + .hlimit = -1, + .tclass = np->tclass, + .dontfrag = np->dontfrag, + }; +} + static inline struct ipv6_txoptions *txopt_get(const struct ipv6_pinfo *np) { struct ipv6_txoptions *opt; diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index be491bf6ab6e..d99fed67cd10 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -545,7 +545,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, else if (!fl6.flowi6_oif) fl6.flowi6_oif = np->ucast_oif; - ipc6.tclass = np->tclass; + ipcm6_init_sk(&ipc6, np); fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); dst = icmpv6_route_lookup(net, skb, sk, &fl6); @@ -553,8 +553,6 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, goto out; ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); - ipc6.dontfrag = np->dontfrag; - ipc6.opt = NULL; msg.skb = skb; msg.offset = skb_network_offset(skb); @@ -726,10 +724,9 @@ static void icmpv6_echo_reply(struct sk_buff *skb) msg.offset = 0; msg.type = ICMPV6_ECHO_REPLY; + ipcm6_init_sk(&ipc6, np); ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); ipc6.tclass = ipv6_get_dsfield(ipv6_hdr(skb)); - ipc6.dontfrag = np->dontfrag; - ipc6.opt = NULL; if (ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr), diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index 96f56bf49a30..717e7c1fba29 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -119,7 +119,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) fl6.fl6_icmp_code = user_icmph.icmp6_code; security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); - ipc6.tclass = np->tclass; + ipcm6_init_sk(&ipc6, np); fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); dst = ip6_sk_dst_lookup_flow(sk, &fl6, daddr, false); @@ -142,8 +142,6 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) pfh.family = AF_INET6; ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); - ipc6.dontfrag = np->dontfrag; - ipc6.opt = NULL; lock_sock(sk); err = ip6_append_data(sk, ping_getfrag, &pfh, len, diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 5737c50f16eb..5f40670271ee 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -791,10 +791,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) fl6.flowi6_mark = sk->sk_mark; fl6.flowi6_uid = sk->sk_uid; - ipc6.hlimit = -1; - ipc6.tclass = -1; - ipc6.dontfrag = -1; - ipc6.opt = NULL; + ipcm6_init(&ipc6); if (sin6) { if (addr_len < SIN6_LEN_RFC2133) diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index ac6fc6728903..940115da9843 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1143,9 +1143,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) int (*getfrag)(void *, char *, int, int, int, struct sk_buff *); struct sockcm_cookie sockc; - ipc6.hlimit = -1; - ipc6.tclass = -1; - ipc6.dontfrag = -1; + ipcm6_init(&ipc6); ipc6.gso_size = up->gso_size; sockc.tsflags = sk->sk_tsflags; sockc.transmit_time = 0; diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 957369192ca1..38f80691f4ab 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -525,9 +525,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) fl6.flowi6_mark = sk->sk_mark; fl6.flowi6_uid = sk->sk_uid; - ipc6.hlimit = -1; - ipc6.tclass = -1; - ipc6.dontfrag = -1; + ipcm6_init(&ipc6); if (lsa) { if (addr_len < SIN6_LEN_RFC2133) -- cgit v1.2.3 From 657a0667025e77cc17f8a38b93e60a2bc24d830c Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Fri, 6 Jul 2018 10:12:56 -0400 Subject: sock: sockc cookie initializer Initialize the cookie in one location to reduce code duplication and avoid bugs from inconsistent initialization, such as that fixed in commit 9887cba19978 ("ip: limit use of gso_size to udp"). Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/net/sock.h | 6 ++++++ net/ipv4/tcp.c | 2 +- net/packet/af_packet.c | 9 +++------ 3 files changed, 10 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index e0eac9ef44b5..83b747538bd0 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1600,6 +1600,12 @@ struct sockcm_cookie { u16 tsflags; }; +static inline void sockcm_init(struct sockcm_cookie *sockc, + const struct sock *sk) +{ + *sockc = (struct sockcm_cookie) { .tsflags = sk->sk_tsflags }; +} + int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg, struct sockcm_cookie *sockc); int sock_cmsg_send(struct sock *sk, struct msghdr *msg, diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index bf461fa77ed6..850dc8f15afc 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1241,7 +1241,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) /* 'common' sending to sendq */ } - sockc.tsflags = sk->sk_tsflags; + sockcm_init(&sockc, sk); if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); if (unlikely(err)) { diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 3428f7739ae9..47931ebfaef3 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1951,8 +1951,7 @@ retry: goto out_unlock; } - sockc.transmit_time = 0; - sockc.tsflags = sk->sk_tsflags; + sockcm_init(&sockc, sk); if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); if (unlikely(err)) @@ -2636,8 +2635,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) if (unlikely(!(dev->flags & IFF_UP))) goto out_put; - sockc.transmit_time = 0; - sockc.tsflags = po->sk.sk_tsflags; + sockcm_init(&sockc, &po->sk); if (msg->msg_controllen) { err = sock_cmsg_send(&po->sk, msg, &sockc); if (unlikely(err)) @@ -2833,8 +2831,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) if (unlikely(!(dev->flags & IFF_UP))) goto out_unlock; - sockc.transmit_time = 0; - sockc.tsflags = sk->sk_tsflags; + sockcm_init(&sockc, sk); sockc.mark = sk->sk_mark; if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); -- cgit v1.2.3 From 5fdaa88dfefa87ee1ea92750e99950dca182ea41 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Fri, 6 Jul 2018 10:12:57 -0400 Subject: ipv6: fold sockcm_cookie into ipcm6_cookie ipcm_cookie includes sockcm_cookie. Do the same for ipcm6_cookie. This reduces the number of arguments that need to be passed around, applies ipcm6_init to all cookie fields at once and reduces code differentiation between ipv4 and ipv6. Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/net/ipv6.h | 7 +++---- include/net/transp_v6.h | 3 +-- net/ipv6/datagram.c | 4 ++-- net/ipv6/icmp.c | 7 ++----- net/ipv6/ip6_flowlabel.c | 3 +-- net/ipv6/ip6_output.c | 24 ++++++++++-------------- net/ipv6/ipv6_sockglue.c | 3 +-- net/ipv6/ping.c | 3 +-- net/ipv6/raw.c | 10 ++++------ net/ipv6/udp.c | 10 ++++------ net/l2tp/l2tp_ip6.c | 6 ++---- 11 files changed, 31 insertions(+), 49 deletions(-) (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 6cb247f54d4c..aa6fd11a887c 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -294,6 +294,7 @@ struct ipv6_fl_socklist { }; struct ipcm6_cookie { + struct sockcm_cookie sockc; __s16 hlimit; __s16 tclass; __s8 dontfrag; @@ -959,8 +960,7 @@ int ip6_append_data(struct sock *sk, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, struct ipcm6_cookie *ipc6, struct flowi6 *fl6, - struct rt6_info *rt, unsigned int flags, - const struct sockcm_cookie *sockc); + struct rt6_info *rt, unsigned int flags); int ip6_push_pending_frames(struct sock *sk); @@ -977,8 +977,7 @@ struct sk_buff *ip6_make_skb(struct sock *sk, void *from, int length, int transhdrlen, struct ipcm6_cookie *ipc6, struct flowi6 *fl6, struct rt6_info *rt, unsigned int flags, - struct inet_cork_full *cork, - const struct sockcm_cookie *sockc); + struct inet_cork_full *cork); static inline struct sk_buff *ip6_finish_skb(struct sock *sk) { diff --git a/include/net/transp_v6.h b/include/net/transp_v6.h index f6a3543e5247..a8f6020f1196 100644 --- a/include/net/transp_v6.h +++ b/include/net/transp_v6.h @@ -42,8 +42,7 @@ void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb); int ip6_datagram_send_ctl(struct net *net, struct sock *sk, struct msghdr *msg, - struct flowi6 *fl6, struct ipcm6_cookie *ipc6, - struct sockcm_cookie *sockc); + struct flowi6 *fl6, struct ipcm6_cookie *ipc6); void __ip6_dgram_sock_seq_show(struct seq_file *seq, struct sock *sp, __u16 srcp, __u16 destp, int rqueue, int bucket); diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 2ee08b6a86a4..201306b9b5ea 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -736,7 +736,7 @@ EXPORT_SYMBOL_GPL(ip6_datagram_recv_ctl); int ip6_datagram_send_ctl(struct net *net, struct sock *sk, struct msghdr *msg, struct flowi6 *fl6, - struct ipcm6_cookie *ipc6, struct sockcm_cookie *sockc) + struct ipcm6_cookie *ipc6) { struct in6_pktinfo *src_info; struct cmsghdr *cmsg; @@ -755,7 +755,7 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk, } if (cmsg->cmsg_level == SOL_SOCKET) { - err = __sock_cmsg_send(sk, msg, cmsg, sockc); + err = __sock_cmsg_send(sk, msg, cmsg, &ipc6->sockc); if (err) return err; continue; diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index d99fed67cd10..24611c8b0562 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -430,7 +430,6 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, struct icmp6hdr tmp_hdr; struct flowi6 fl6; struct icmpv6_msg msg; - struct sockcm_cookie sockc_unused = {0}; struct ipcm6_cookie ipc6; int iif = 0; int addr_type = 0; @@ -573,7 +572,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, len + sizeof(struct icmp6hdr), sizeof(struct icmp6hdr), &ipc6, &fl6, (struct rt6_info *)dst, - MSG_DONTWAIT, &sockc_unused)) { + MSG_DONTWAIT)) { ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS); ip6_flush_pending_frames(sk); } else { @@ -677,7 +676,6 @@ static void icmpv6_echo_reply(struct sk_buff *skb) struct dst_entry *dst; struct ipcm6_cookie ipc6; u32 mark = IP6_REPLY_MARK(net, skb->mark); - struct sockcm_cookie sockc_unused = {0}; saddr = &ipv6_hdr(skb)->daddr; @@ -731,8 +729,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb) if (ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr), sizeof(struct icmp6hdr), &ipc6, &fl6, - (struct rt6_info *)dst, MSG_DONTWAIT, - &sockc_unused)) { + (struct rt6_info *)dst, MSG_DONTWAIT)) { __ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS); ip6_flush_pending_frames(sk); } else { diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 3eee7637bdfe..cb54a8a3c273 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -373,7 +373,6 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq, if (olen > 0) { struct msghdr msg; struct flowi6 flowi6; - struct sockcm_cookie sockc_junk; struct ipcm6_cookie ipc6; err = -ENOMEM; @@ -392,7 +391,7 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq, memset(&flowi6, 0, sizeof(flowi6)); ipc6.opt = fl->opt; - err = ip6_datagram_send_ctl(net, sk, &msg, &flowi6, &ipc6, &sockc_junk); + err = ip6_datagram_send_ctl(net, sk, &msg, &flowi6, &ipc6); if (err) goto done; err = -EINVAL; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index f48af7e62f12..1a3bf6437cb9 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1158,8 +1158,7 @@ static void ip6_append_data_mtu(unsigned int *mtu, static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork, struct inet6_cork *v6_cork, struct ipcm6_cookie *ipc6, - struct rt6_info *rt, struct flowi6 *fl6, - const struct sockcm_cookie *sockc) + struct rt6_info *rt, struct flowi6 *fl6) { struct ipv6_pinfo *np = inet6_sk(sk); unsigned int mtu; @@ -1227,7 +1226,7 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork, cork->base.flags |= IPCORK_ALLFRAG; cork->base.length = 0; - cork->base.transmit_time = sockc->transmit_time; + cork->base.transmit_time = ipc6->sockc.transmit_time; return 0; } @@ -1241,8 +1240,7 @@ static int __ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, - unsigned int flags, struct ipcm6_cookie *ipc6, - const struct sockcm_cookie *sockc) + unsigned int flags, struct ipcm6_cookie *ipc6) { struct sk_buff *skb, *skb_prev = NULL; unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu, pmtu; @@ -1321,7 +1319,7 @@ emsgsize: csummode = CHECKSUM_PARTIAL; if (sk->sk_type == SOCK_DGRAM || sk->sk_type == SOCK_RAW) { - sock_tx_timestamp(sk, sockc->tsflags, &tx_flags); + sock_tx_timestamp(sk, ipc6->sockc.tsflags, &tx_flags); if (tx_flags & SKBTX_ANY_SW_TSTAMP && sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) tskey = sk->sk_tskey++; @@ -1563,8 +1561,7 @@ int ip6_append_data(struct sock *sk, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, struct ipcm6_cookie *ipc6, struct flowi6 *fl6, - struct rt6_info *rt, unsigned int flags, - const struct sockcm_cookie *sockc) + struct rt6_info *rt, unsigned int flags) { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); @@ -1578,7 +1575,7 @@ int ip6_append_data(struct sock *sk, * setup for corking */ err = ip6_setup_cork(sk, &inet->cork, &np->cork, - ipc6, rt, fl6, sockc); + ipc6, rt, fl6); if (err) return err; @@ -1592,7 +1589,7 @@ int ip6_append_data(struct sock *sk, return __ip6_append_data(sk, fl6, &sk->sk_write_queue, &inet->cork.base, &np->cork, sk_page_frag(sk), getfrag, - from, length, transhdrlen, flags, ipc6, sockc); + from, length, transhdrlen, flags, ipc6); } EXPORT_SYMBOL_GPL(ip6_append_data); @@ -1752,8 +1749,7 @@ struct sk_buff *ip6_make_skb(struct sock *sk, void *from, int length, int transhdrlen, struct ipcm6_cookie *ipc6, struct flowi6 *fl6, struct rt6_info *rt, unsigned int flags, - struct inet_cork_full *cork, - const struct sockcm_cookie *sockc) + struct inet_cork_full *cork) { struct inet6_cork v6_cork; struct sk_buff_head queue; @@ -1770,7 +1766,7 @@ struct sk_buff *ip6_make_skb(struct sock *sk, cork->base.opt = NULL; cork->base.dst = NULL; v6_cork.opt = NULL; - err = ip6_setup_cork(sk, cork, &v6_cork, ipc6, rt, fl6, sockc); + err = ip6_setup_cork(sk, cork, &v6_cork, ipc6, rt, fl6); if (err) { ip6_cork_release(cork, &v6_cork); return ERR_PTR(err); @@ -1781,7 +1777,7 @@ struct sk_buff *ip6_make_skb(struct sock *sk, err = __ip6_append_data(sk, fl6, &queue, &cork->base, &v6_cork, ¤t->task_frag, getfrag, from, length + exthdrlen, transhdrlen + exthdrlen, - flags, ipc6, sockc); + flags, ipc6); if (err) { __ip6_flush_pending_frames(sk, &queue, cork, &v6_cork); return ERR_PTR(err); diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 4d780c7f0130..fabe3ba1bddc 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -489,7 +489,6 @@ sticky_done: struct ipv6_txoptions *opt = NULL; struct msghdr msg; struct flowi6 fl6; - struct sockcm_cookie sockc_junk; struct ipcm6_cookie ipc6; memset(&fl6, 0, sizeof(fl6)); @@ -522,7 +521,7 @@ sticky_done: msg.msg_control = (void *)(opt+1); ipc6.opt = opt; - retv = ip6_datagram_send_ctl(net, sk, &msg, &fl6, &ipc6, &sockc_junk); + retv = ip6_datagram_send_ctl(net, sk, &msg, &fl6, &ipc6); if (retv) goto done; update: diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index 717e7c1fba29..4c04bccc7417 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -62,7 +62,6 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) struct dst_entry *dst; struct rt6_info *rt; struct pingfakehdr pfh; - struct sockcm_cookie junk = {0}; struct ipcm6_cookie ipc6; pr_debug("ping_v6_sendmsg(sk=%p,sk->num=%u)\n", inet, inet->inet_num); @@ -146,7 +145,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) lock_sock(sk); err = ip6_append_data(sk, ping_getfrag, &pfh, len, 0, &ipc6, &fl6, rt, - MSG_DONTWAIT, &junk); + MSG_DONTWAIT); if (err) { ICMP6_INC_STATS(sock_net(sk), rt->rt6i_idev, diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 5f40670271ee..413d98bf24f4 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -767,7 +767,6 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) struct dst_entry *dst = NULL; struct raw6_frag_vec rfv; struct flowi6 fl6; - struct sockcm_cookie sockc; struct ipcm6_cookie ipc6; int addr_len = msg->msg_namelen; u16 proto; @@ -792,6 +791,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) fl6.flowi6_uid = sk->sk_uid; ipcm6_init(&ipc6); + ipc6.sockc.tsflags = sk->sk_tsflags; if (sin6) { if (addr_len < SIN6_LEN_RFC2133) @@ -845,15 +845,13 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (fl6.flowi6_oif == 0) fl6.flowi6_oif = sk->sk_bound_dev_if; - sockc.tsflags = sk->sk_tsflags; - sockc.transmit_time = 0; if (msg->msg_controllen) { opt = &opt_space; memset(opt, 0, sizeof(struct ipv6_txoptions)); opt->tot_len = sizeof(struct ipv6_txoptions); ipc6.opt = opt; - err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, &ipc6, &sockc); + err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, &ipc6); if (err < 0) { fl6_sock_release(flowlabel); return err; @@ -921,13 +919,13 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) back_from_confirm: if (inet->hdrincl) err = rawv6_send_hdrinc(sk, msg, len, &fl6, &dst, - msg->msg_flags, &sockc); + msg->msg_flags, &ipc6.sockc); else { ipc6.opt = opt; lock_sock(sk); err = ip6_append_data(sk, raw6_getfrag, &rfv, len, 0, &ipc6, &fl6, (struct rt6_info *)dst, - msg->msg_flags, &sockc); + msg->msg_flags); if (err) ip6_flush_pending_frames(sk); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 940115da9843..f6b96956a8ed 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1141,12 +1141,10 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) int err; int is_udplite = IS_UDPLITE(sk); int (*getfrag)(void *, char *, int, int, int, struct sk_buff *); - struct sockcm_cookie sockc; ipcm6_init(&ipc6); ipc6.gso_size = up->gso_size; - sockc.tsflags = sk->sk_tsflags; - sockc.transmit_time = 0; + ipc6.sockc.tsflags = sk->sk_tsflags; /* destination address check */ if (sin6) { @@ -1281,7 +1279,7 @@ do_udp_sendmsg: err = udp_cmsg_send(sk, msg, &ipc6.gso_size); if (err > 0) err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, - &ipc6, &sockc); + &ipc6); if (err < 0) { fl6_sock_release(flowlabel); return err; @@ -1375,7 +1373,7 @@ back_from_confirm: skb = ip6_make_skb(sk, getfrag, msg, ulen, sizeof(struct udphdr), &ipc6, &fl6, (struct rt6_info *)dst, - msg->msg_flags, &cork, &sockc); + msg->msg_flags, &cork); err = PTR_ERR(skb); if (!IS_ERR_OR_NULL(skb)) err = udp_v6_send_skb(skb, &fl6, &cork.base); @@ -1401,7 +1399,7 @@ do_append_data: up->len += ulen; err = ip6_append_data(sk, getfrag, msg, ulen, sizeof(struct udphdr), &ipc6, &fl6, (struct rt6_info *)dst, - corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags, &sockc); + corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags); if (err) udp_v6_flush_pending_frames(sk); else if (!corkreq) diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 38f80691f4ab..672e5b753738 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -500,7 +500,6 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) struct ip6_flowlabel *flowlabel = NULL; struct dst_entry *dst = NULL; struct flowi6 fl6; - struct sockcm_cookie sockc_unused = {0}; struct ipcm6_cookie ipc6; int addr_len = msg->msg_namelen; int transhdrlen = 4; /* zero session-id */ @@ -573,8 +572,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) opt->tot_len = sizeof(struct ipv6_txoptions); ipc6.opt = opt; - err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, &ipc6, - &sockc_unused); + err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, &ipc6); if (err < 0) { fl6_sock_release(flowlabel); return err; @@ -639,7 +637,7 @@ back_from_confirm: err = ip6_append_data(sk, ip_generic_getfrag, msg, ulen, transhdrlen, &ipc6, &fl6, (struct rt6_info *)dst, - msg->msg_flags, &sockc_unused); + msg->msg_flags); if (err) ip6_flush_pending_frames(sk); else if (!(msg->msg_flags & MSG_MORE)) -- cgit v1.2.3 From 678ca42d688534adfc780b150abefaaac7c86687 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Fri, 6 Jul 2018 10:12:58 -0400 Subject: ip: remove tx_flags from ipcm_cookie and use same logic for v4 and v6 skb_shinfo(skb)->tx_flags is derived from sk->sk_tsflags, possibly after modification by __sock_cmsg_send, by calling sock_tx_timestamp. The IPv4 and IPv6 paths do this conversion differently. In IPv4, the individual protocols that support tx timestamps call this function and store the result in ipc.tx_flags. In IPv6, sock_tx_timestamp is called in __ip6_append_data. There is no need to store both tx_flags and ts_flags in the cookie as one is derived from the other. Convert when setting up the cork and remove the redundant field. This is similar to IPv6, only have the conversion happen only once per datagram, in ip(6)_setup_cork. Also change __ip6_append_data to match __ip_append_data. Only update tskey if timestamping is enabled with OPT_ID. The SOCK_.. test is redundant: only valid protocols can have non-zero cork->tx_flags. After this change the IPv4 and IPv6 logic is the same. Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/net/ip.h | 1 - net/ipv4/ip_output.c | 3 ++- net/ipv4/ping.c | 2 -- net/ipv4/raw.c | 2 -- net/ipv4/udp.c | 2 -- net/ipv6/ip6_output.c | 18 ++++++++---------- 6 files changed, 10 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/net/ip.h b/include/net/ip.h index 6db23bf1e5eb..e44b1a44f67a 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -72,7 +72,6 @@ struct ipcm_cookie { __be32 addr; int oif; struct ip_options_rcu *opt; - __u8 tx_flags; __u8 ttl; __s16 tos; char priority; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 81d0e4a77ec5..e14c774cc092 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1153,8 +1153,9 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, cork->ttl = ipc->ttl; cork->tos = ipc->tos; cork->priority = ipc->priority; - cork->tx_flags = ipc->tx_flags; cork->transmit_time = ipc->sockc.transmit_time; + cork->tx_flags = 0; + sock_tx_timestamp(sk, ipc->sockc.tsflags, &cork->tx_flags); return 0; } diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 6f17fc8ebbdb..b54c964ad925 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -763,8 +763,6 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) rcu_read_unlock(); } - sock_tx_timestamp(sk, ipc.sockc.tsflags, &ipc.tx_flags); - saddr = ipc.addr; ipc.addr = faddr = daddr; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index cf142909389c..33df4d76db2d 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -665,8 +665,6 @@ back_from_confirm: &rt, msg->msg_flags, &ipc.sockc); else { - sock_tx_timestamp(sk, ipc.sockc.tsflags, &ipc.tx_flags); - if (!ipc.addr) ipc.addr = fl4.daddr; lock_sock(sk); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 87f3a0b77864..060e841dde40 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1020,8 +1020,6 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) saddr = ipc.addr; ipc.addr = faddr = daddr; - sock_tx_timestamp(sk, ipc.sockc.tsflags, &ipc.tx_flags); - if (ipc.opt && ipc.opt->opt.srr) { if (!daddr) { err = -EINVAL; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 1a3bf6437cb9..ff4b28a600ab 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1221,6 +1221,8 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork, cork->base.fragsize = mtu; cork->base.gso_size = sk->sk_type == SOCK_DGRAM && sk->sk_protocol == IPPROTO_UDP ? ipc6->gso_size : 0; + cork->base.tx_flags = 0; + sock_tx_timestamp(sk, ipc6->sockc.tsflags, &cork->base.tx_flags); if (dst_allfrag(xfrm_dst_path(&rt->dst))) cork->base.flags |= IPCORK_ALLFRAG; @@ -1250,7 +1252,6 @@ static int __ip6_append_data(struct sock *sk, int copy; int err; int offset = 0; - __u8 tx_flags = 0; u32 tskey = 0; struct rt6_info *rt = (struct rt6_info *)cork->dst; struct ipv6_txoptions *opt = v6_cork->opt; @@ -1269,6 +1270,10 @@ static int __ip6_append_data(struct sock *sk, mtu = cork->gso_size ? IP6_MAX_MTU : cork->fragsize; orig_mtu = mtu; + if (cork->tx_flags & SKBTX_ANY_SW_TSTAMP && + sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) + tskey = sk->sk_tskey++; + hh_len = LL_RESERVED_SPACE(rt->dst.dev); fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len + @@ -1318,13 +1323,6 @@ emsgsize: rt->dst.dev->features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM)) csummode = CHECKSUM_PARTIAL; - if (sk->sk_type == SOCK_DGRAM || sk->sk_type == SOCK_RAW) { - sock_tx_timestamp(sk, ipc6->sockc.tsflags, &tx_flags); - if (tx_flags & SKBTX_ANY_SW_TSTAMP && - sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) - tskey = sk->sk_tskey++; - } - /* * Let's try using as much space as possible. * Use MTU if total length of the message fits into the MTU. @@ -1443,8 +1441,8 @@ alloc_new_skb: dst_exthdrlen); /* Only the initial fragment is time stamped */ - skb_shinfo(skb)->tx_flags = tx_flags; - tx_flags = 0; + skb_shinfo(skb)->tx_flags = cork->tx_flags; + cork->tx_flags = 0; skb_shinfo(skb)->tskey = tskey; tskey = 0; -- cgit v1.2.3 From b82c1f8f78b4d273d1bcefe3e805eff61e879a68 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 3 Jul 2018 09:50:15 +0200 Subject: drm/atomic: Avoid connector to writeback_connector casts Use container_of() instead of type casting so that it keeps working even if base is moved inside the drm_writeback_connector struct. Signed-off-by: Boris Brezillon Reviewed-by: Liviu Dudau Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20180703075022.15138-2-boris.brezillon@bootlin.com --- drivers/gpu/drm/drm_atomic.c | 4 +++- include/drm/drm_writeback.h | 6 ++++++ 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c index e6062c779aaf..3eb061e11e2e 100644 --- a/drivers/gpu/drm/drm_atomic.c +++ b/drivers/gpu/drm/drm_atomic.c @@ -2428,6 +2428,7 @@ static int prepare_signaling(struct drm_device *dev, } for_each_new_connector_in_state(state, conn, conn_state, i) { + struct drm_writeback_connector *wb_conn; struct drm_writeback_job *job; struct drm_out_fence_state *f; struct dma_fence *fence; @@ -2451,7 +2452,8 @@ static int prepare_signaling(struct drm_device *dev, f[*num_fences].out_fence_ptr = fence_ptr; *fence_state = f; - fence = drm_writeback_get_out_fence((struct drm_writeback_connector *)conn); + wb_conn = drm_connector_to_writeback(conn); + fence = drm_writeback_get_out_fence(wb_conn); if (!fence) return -ENOMEM; diff --git a/include/drm/drm_writeback.h b/include/drm/drm_writeback.h index a10fe556dfd4..23df9d463003 100644 --- a/include/drm/drm_writeback.h +++ b/include/drm/drm_writeback.h @@ -110,6 +110,12 @@ struct drm_writeback_job { struct dma_fence *out_fence; }; +static inline struct drm_writeback_connector * +drm_connector_to_writeback(struct drm_connector *connector) +{ + return container_of(connector, struct drm_writeback_connector, base); +} + int drm_writeback_connector_init(struct drm_device *dev, struct drm_writeback_connector *wb_connector, const struct drm_connector_funcs *con_funcs, -- cgit v1.2.3 From 425132fdb169c2a2772190ff56e0e8eea37ff716 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 3 Jul 2018 09:50:16 +0200 Subject: drm/connector: Pass a drm_connector_state to ->atomic_commit() Other atomic hooks are passed state objects, let's change this one to be consistent. Signed-off-by: Boris Brezillon Acked-by: Liviu Dudau Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20180703075022.15138-3-boris.brezillon@bootlin.com --- drivers/gpu/drm/drm_atomic_helper.c | 2 +- include/drm/drm_modeset_helper_vtables.h | 4 +++- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index 7787e0e6bbc6..47e84aa7b6e2 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -1187,7 +1187,7 @@ static void drm_atomic_helper_commit_writebacks(struct drm_device *dev, if (new_conn_state->writeback_job && new_conn_state->writeback_job->fb) { WARN_ON(connector->connector_type != DRM_MODE_CONNECTOR_WRITEBACK); - funcs->atomic_commit(connector, new_conn_state->writeback_job); + funcs->atomic_commit(connector, new_conn_state); } } } diff --git a/include/drm/drm_modeset_helper_vtables.h b/include/drm/drm_modeset_helper_vtables.h index 3b289773297c..fb841f44949c 100644 --- a/include/drm/drm_modeset_helper_vtables.h +++ b/include/drm/drm_modeset_helper_vtables.h @@ -980,11 +980,13 @@ struct drm_connector_helper_funcs { * * This hook is to be used by drivers implementing writeback connectors * that need a point when to commit the writeback job to the hardware. + * The writeback_job to commit is available in + * &drm_connector_state.writeback_job. * * This callback is used by the atomic modeset helpers. */ void (*atomic_commit)(struct drm_connector *connector, - struct drm_writeback_job *writeback_job); + struct drm_connector_state *state); }; /** -- cgit v1.2.3 From 814bde99ee809c172a409829889d1bafc3e4bcf7 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 3 Jul 2018 09:50:17 +0200 Subject: drm/connector: Make ->atomic_commit() optional Not all writeback connector implementations might want to commit things from the connector driver. Some, like the malidp driver, commit things from their main commit_tail() function, and would rather not have to implement a dummy hook for drm_connector_helper_funcs.atomic_commit(). Make this function optional and reflect this fact in the doc. Signed-off-by: Boris Brezillon Acked-by: Liviu Dudau Link: https://patchwork.freedesktop.org/patch/msgid/20180703075022.15138-4-boris.brezillon@bootlin.com --- drivers/gpu/drm/drm_atomic_helper.c | 2 ++ include/drm/drm_modeset_helper_vtables.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index 47e84aa7b6e2..bab8051690bb 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -1184,6 +1184,8 @@ static void drm_atomic_helper_commit_writebacks(struct drm_device *dev, const struct drm_connector_helper_funcs *funcs; funcs = connector->helper_private; + if (!funcs->atomic_commit) + continue; if (new_conn_state->writeback_job && new_conn_state->writeback_job->fb) { WARN_ON(connector->connector_type != DRM_MODE_CONNECTOR_WRITEBACK); diff --git a/include/drm/drm_modeset_helper_vtables.h b/include/drm/drm_modeset_helper_vtables.h index fb841f44949c..d0eb76c4b309 100644 --- a/include/drm/drm_modeset_helper_vtables.h +++ b/include/drm/drm_modeset_helper_vtables.h @@ -983,6 +983,8 @@ struct drm_connector_helper_funcs { * The writeback_job to commit is available in * &drm_connector_state.writeback_job. * + * This hook is optional. + * * This callback is used by the atomic modeset helpers. */ void (*atomic_commit)(struct drm_connector *connector, -- cgit v1.2.3 From b25c60af7a8773694a505cdb0d2e67807243217d Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 3 Jul 2018 09:50:19 +0200 Subject: drm/crtc: Add a generic infrastructure to fake VBLANK events In some cases CRTCs are active but are not able to generating events, at least not at every frame at it's expected to. This is typically the case when the CRTC is feeding a writeback connector that has no job queued. In this situation the CRTC is usually stopped until a new job is queued, and this can lead to timeouts when part of the pipeline is updated but no new jobs are queued to the active writeback connector. In order to solve that, we add a ->no_vblank flag to drm_crtc_state and ask the CRTC drivers to set it to true when they know they're not able to generate VBLANK events. The core drm_atomic_helper_fake_vblank() helper can then be used to fake VBLANKs at commit time. Signed-off-by: Boris Brezillon Reviewed-by: Liviu Dudau Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20180703075022.15138-6-boris.brezillon@bootlin.com --- drivers/gpu/drm/drm_atomic_helper.c | 39 +++++++++++++++++++++++++++++++++++++ include/drm/drm_atomic_helper.h | 1 + include/drm/drm_crtc.h | 23 ++++++++++++++++++++++ 3 files changed, 63 insertions(+) (limited to 'include') diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index bab8051690bb..c31f670b1283 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -2053,6 +2053,45 @@ void drm_atomic_helper_wait_for_dependencies(struct drm_atomic_state *old_state) } EXPORT_SYMBOL(drm_atomic_helper_wait_for_dependencies); +/** + * drm_atomic_helper_fake_vblank - fake VBLANK events if needed + * @old_state: atomic state object with old state structures + * + * This function walks all CRTCs and fake VBLANK events on those with + * &drm_crtc_state.no_vblank set to true and &drm_crtc_state.event != NULL. + * The primary use of this function is writeback connectors working in oneshot + * mode and faking VBLANK events. In this case they only fake the VBLANK event + * when a job is queued, and any change to the pipeline that does not touch the + * connector is leading to timeouts when calling + * drm_atomic_helper_wait_for_vblanks() or + * drm_atomic_helper_wait_for_flip_done(). + * + * This is part of the atomic helper support for nonblocking commits, see + * drm_atomic_helper_setup_commit() for an overview. + */ +void drm_atomic_helper_fake_vblank(struct drm_atomic_state *old_state) +{ + struct drm_crtc_state *new_crtc_state; + struct drm_crtc *crtc; + int i; + + for_each_new_crtc_in_state(old_state, crtc, new_crtc_state, i) { + unsigned long flags; + + if (!new_crtc_state->no_vblank) + continue; + + spin_lock_irqsave(&old_state->dev->event_lock, flags); + if (new_crtc_state->event) { + drm_crtc_send_vblank_event(crtc, + new_crtc_state->event); + new_crtc_state->event = NULL; + } + spin_unlock_irqrestore(&old_state->dev->event_lock, flags); + } +} +EXPORT_SYMBOL(drm_atomic_helper_fake_vblank); + /** * drm_atomic_helper_commit_hw_done - setup possible nonblocking commit * @old_state: atomic state object with old state structures diff --git a/include/drm/drm_atomic_helper.h b/include/drm/drm_atomic_helper.h index 26aaba58d6ce..99e2a5297c69 100644 --- a/include/drm/drm_atomic_helper.h +++ b/include/drm/drm_atomic_helper.h @@ -100,6 +100,7 @@ int __must_check drm_atomic_helper_swap_state(struct drm_atomic_state *state, int drm_atomic_helper_setup_commit(struct drm_atomic_state *state, bool nonblock); void drm_atomic_helper_wait_for_dependencies(struct drm_atomic_state *state); +void drm_atomic_helper_fake_vblank(struct drm_atomic_state *state); void drm_atomic_helper_commit_hw_done(struct drm_atomic_state *state); void drm_atomic_helper_commit_cleanup_done(struct drm_atomic_state *state); diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h index 23eddbccab10..17f4f93340b8 100644 --- a/include/drm/drm_crtc.h +++ b/include/drm/drm_crtc.h @@ -119,6 +119,29 @@ struct drm_crtc_state { bool zpos_changed : 1; bool color_mgmt_changed : 1; + /** + * @no_vblank: + * + * Reflects the ability of a CRTC to send VBLANK events. This state + * usually depends on the pipeline configuration, and the main usuage + * is CRTCs feeding a writeback connector operating in oneshot mode. + * In this case the VBLANK event is only generated when a job is queued + * to the writeback connector, and we want the core to fake VBLANK + * events when this part of the pipeline hasn't changed but others had + * or when the CRTC and connectors are being disabled. + * + * __drm_atomic_helper_crtc_duplicate_state() will not reset the value + * from the current state, the CRTC driver is then responsible for + * updating this field when needed. + * + * Note that the combination of &drm_crtc_state.event == NULL and + * &drm_crtc_state.no_blank == true is valid and usually used when the + * writeback connector attached to the CRTC has a new job queued. In + * this case the driver will send the VBLANK event on its own when the + * writeback job is complete. + */ + bool no_vblank : 1; + /* attached planes bitmask: * WARNING: transitional helpers do not maintain plane_mask so * drivers not converted over to atomic helpers should not rely -- cgit v1.2.3 From 22dd149167359981ea6f4afde04026fb78747ddc Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 6 Jul 2018 14:58:51 +0200 Subject: devlink: fix incorrect return statement A newly added dummy helper function tries to return a failure from a "void" function: In file included from include/net/dsa.h:24, from arch/arm/plat-orion/common.c:21: include/net/devlink.h: In function 'devlink_param_value_changed': include/net/devlink.h:771:9: error: 'return' with a value, in function returning void [-Werror] return -EOPNOTSUPP; This fixes it by removing the bogus statement. Fixes: ea601e170988 ("devlink: Add devlink notifications support for params") Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- include/net/devlink.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 8ed571385626..f67c29cede15 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -768,7 +768,6 @@ devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id, static inline void devlink_param_value_changed(struct devlink *devlink, u32 param_id) { - return -EOPNOTSUPP; } #endif -- cgit v1.2.3 From 2064c3d4c02026572d4975177f28a58052f0a8b7 Mon Sep 17 00:00:00 2001 From: Jianbo Liu Date: Fri, 6 Jul 2018 05:38:12 +0000 Subject: net/flow_dissector: Save vlan ethertype from headers Change vlan dissector key to save vlan tpid to support both 802.1Q and 802.1AD ethertype. Signed-off-by: Jianbo Liu Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/flow_dissector.h | 2 +- net/core/flow_dissector.c | 2 ++ 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index adc24df56b90..8f899688a965 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -47,7 +47,7 @@ struct flow_dissector_key_tags { struct flow_dissector_key_vlan { u16 vlan_id:12, vlan_priority:3; - u16 padding; + __be16 vlan_tpid; }; struct flow_dissector_key_mpls { diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 53f96e4f7bf5..18cb99b50cba 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -751,6 +751,7 @@ proto_again: const struct vlan_hdr *vlan; struct vlan_hdr _vlan; bool vlan_tag_present = skb && skb_vlan_tag_present(skb); + __be16 saved_vlan_tpid = proto; if (vlan_tag_present) proto = skb->protocol; @@ -789,6 +790,7 @@ proto_again: (ntohs(vlan->h_vlan_TCI) & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; } + key_vlan->vlan_tpid = saved_vlan_tpid; } fdret = FLOW_DISSECT_RET_PROTO_AGAIN; -- cgit v1.2.3 From 24c590e3b0f9eebe603ebe3d516990306d385f46 Mon Sep 17 00:00:00 2001 From: Jianbo Liu Date: Fri, 6 Jul 2018 05:38:14 +0000 Subject: net/flow_dissector: Add support for QinQ dissection Dissect the QinQ packets to get both outer and inner vlan information, then store to the extended flow keys. Signed-off-by: Jianbo Liu Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/flow_dissector.h | 2 ++ net/core/flow_dissector.c | 32 +++++++++++++++++--------------- 2 files changed, 19 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index 8f899688a965..c64406717eee 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -206,6 +206,7 @@ enum flow_dissector_key_id { FLOW_DISSECTOR_KEY_MPLS, /* struct flow_dissector_key_mpls */ FLOW_DISSECTOR_KEY_TCP, /* struct flow_dissector_key_tcp */ FLOW_DISSECTOR_KEY_IP, /* struct flow_dissector_key_ip */ + FLOW_DISSECTOR_KEY_CVLAN, /* struct flow_dissector_key_flow_vlan */ FLOW_DISSECTOR_KEY_MAX, }; @@ -237,6 +238,7 @@ struct flow_keys { struct flow_dissector_key_basic basic; struct flow_dissector_key_tags tags; struct flow_dissector_key_vlan vlan; + struct flow_dissector_key_vlan cvlan; struct flow_dissector_key_keyid keyid; struct flow_dissector_key_ports ports; struct flow_dissector_key_addrs addrs; diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 18cb99b50cba..b555fc229e96 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -589,7 +589,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector_key_tags *key_tags; struct flow_dissector_key_vlan *key_vlan; enum flow_dissect_ret fdret; - bool skip_vlan = false; + enum flow_dissector_key_id dissector_vlan = FLOW_DISSECTOR_KEY_MAX; int num_hdrs = 0; u8 ip_proto = 0; bool ret; @@ -748,15 +748,14 @@ proto_again: } case htons(ETH_P_8021AD): case htons(ETH_P_8021Q): { - const struct vlan_hdr *vlan; + const struct vlan_hdr *vlan = NULL; struct vlan_hdr _vlan; - bool vlan_tag_present = skb && skb_vlan_tag_present(skb); __be16 saved_vlan_tpid = proto; - if (vlan_tag_present) + if (dissector_vlan == FLOW_DISSECTOR_KEY_MAX && + skb && skb_vlan_tag_present(skb)) { proto = skb->protocol; - - if (!vlan_tag_present || eth_type_vlan(skb->protocol)) { + } else { vlan = __skb_header_pointer(skb, nhoff, sizeof(_vlan), data, hlen, &_vlan); if (!vlan) { @@ -766,20 +765,23 @@ proto_again: proto = vlan->h_vlan_encapsulated_proto; nhoff += sizeof(*vlan); - if (skip_vlan) { - fdret = FLOW_DISSECT_RET_PROTO_AGAIN; - break; - } } - skip_vlan = true; - if (dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_VLAN)) { + if (dissector_vlan == FLOW_DISSECTOR_KEY_MAX) { + dissector_vlan = FLOW_DISSECTOR_KEY_VLAN; + } else if (dissector_vlan == FLOW_DISSECTOR_KEY_VLAN) { + dissector_vlan = FLOW_DISSECTOR_KEY_CVLAN; + } else { + fdret = FLOW_DISSECT_RET_PROTO_AGAIN; + break; + } + + if (dissector_uses_key(flow_dissector, dissector_vlan)) { key_vlan = skb_flow_dissector_target(flow_dissector, - FLOW_DISSECTOR_KEY_VLAN, + dissector_vlan, target_container); - if (vlan_tag_present) { + if (!vlan) { key_vlan->vlan_id = skb_vlan_tag_get_id(skb); key_vlan->vlan_priority = (skb_vlan_tag_get_prio(skb) >> VLAN_PRIO_SHIFT); -- cgit v1.2.3 From d64efd0926ba4f32e657e615a4f4a6170d5cc0fa Mon Sep 17 00:00:00 2001 From: Jianbo Liu Date: Fri, 6 Jul 2018 05:38:16 +0000 Subject: net/sched: flower: Add supprt for matching on QinQ vlan headers As support dissecting of QinQ inner and outer vlan headers, user can add rules to match on QinQ vlan headers. Signed-off-by: Jianbo Liu Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/uapi/linux/pkt_cls.h | 4 +++ net/sched/cls_flower.c | 65 ++++++++++++++++++++++++++++++++++---------- 2 files changed, 55 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 84e4c1d0f874..c4262d911596 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -469,6 +469,10 @@ enum { TCA_FLOWER_KEY_IP_TTL, /* u8 */ TCA_FLOWER_KEY_IP_TTL_MASK, /* u8 */ + TCA_FLOWER_KEY_CVLAN_ID, /* be16 */ + TCA_FLOWER_KEY_CVLAN_PRIO, /* u8 */ + TCA_FLOWER_KEY_CVLAN_ETH_TYPE, /* be16 */ + __TCA_FLOWER_MAX, }; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index e93b13d2cb81..487a152a852c 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -35,6 +35,7 @@ struct fl_flow_key { struct flow_dissector_key_basic basic; struct flow_dissector_key_eth_addrs eth; struct flow_dissector_key_vlan vlan; + struct flow_dissector_key_vlan cvlan; union { struct flow_dissector_key_ipv4_addrs ipv4; struct flow_dissector_key_ipv6_addrs ipv6; @@ -449,6 +450,9 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { [TCA_FLOWER_KEY_IP_TOS_MASK] = { .type = NLA_U8 }, [TCA_FLOWER_KEY_IP_TTL] = { .type = NLA_U8 }, [TCA_FLOWER_KEY_IP_TTL_MASK] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_CVLAN_ID] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_CVLAN_PRIO] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_CVLAN_ETH_TYPE] = { .type = NLA_U16 }, }; static void fl_set_key_val(struct nlattr **tb, @@ -501,19 +505,20 @@ static int fl_set_key_mpls(struct nlattr **tb, static void fl_set_key_vlan(struct nlattr **tb, __be16 ethertype, + int vlan_id_key, int vlan_prio_key, struct flow_dissector_key_vlan *key_val, struct flow_dissector_key_vlan *key_mask) { #define VLAN_PRIORITY_MASK 0x7 - if (tb[TCA_FLOWER_KEY_VLAN_ID]) { + if (tb[vlan_id_key]) { key_val->vlan_id = - nla_get_u16(tb[TCA_FLOWER_KEY_VLAN_ID]) & VLAN_VID_MASK; + nla_get_u16(tb[vlan_id_key]) & VLAN_VID_MASK; key_mask->vlan_id = VLAN_VID_MASK; } - if (tb[TCA_FLOWER_KEY_VLAN_PRIO]) { + if (tb[vlan_prio_key]) { key_val->vlan_priority = - nla_get_u8(tb[TCA_FLOWER_KEY_VLAN_PRIO]) & + nla_get_u8(tb[vlan_prio_key]) & VLAN_PRIORITY_MASK; key_mask->vlan_priority = VLAN_PRIORITY_MASK; } @@ -596,11 +601,25 @@ static int fl_set_key(struct net *net, struct nlattr **tb, ethertype = nla_get_be16(tb[TCA_FLOWER_KEY_ETH_TYPE]); if (eth_type_vlan(ethertype)) { - fl_set_key_vlan(tb, ethertype, &key->vlan, &mask->vlan); - fl_set_key_val(tb, &key->basic.n_proto, - TCA_FLOWER_KEY_VLAN_ETH_TYPE, - &mask->basic.n_proto, TCA_FLOWER_UNSPEC, - sizeof(key->basic.n_proto)); + fl_set_key_vlan(tb, ethertype, TCA_FLOWER_KEY_VLAN_ID, + TCA_FLOWER_KEY_VLAN_PRIO, &key->vlan, + &mask->vlan); + + ethertype = nla_get_be16(tb[TCA_FLOWER_KEY_VLAN_ETH_TYPE]); + if (eth_type_vlan(ethertype)) { + fl_set_key_vlan(tb, ethertype, + TCA_FLOWER_KEY_CVLAN_ID, + TCA_FLOWER_KEY_CVLAN_PRIO, + &key->cvlan, &mask->cvlan); + fl_set_key_val(tb, &key->basic.n_proto, + TCA_FLOWER_KEY_CVLAN_ETH_TYPE, + &mask->basic.n_proto, + TCA_FLOWER_UNSPEC, + sizeof(key->basic.n_proto)); + } else { + key->basic.n_proto = ethertype; + mask->basic.n_proto = cpu_to_be16(~0); + } } else { key->basic.n_proto = ethertype; mask->basic.n_proto = cpu_to_be16(~0); @@ -825,6 +844,8 @@ static void fl_init_dissector(struct fl_flow_mask *mask) FLOW_DISSECTOR_KEY_MPLS, mpls); FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, FLOW_DISSECTOR_KEY_VLAN, vlan); + FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, + FLOW_DISSECTOR_KEY_CVLAN, cvlan); FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, FLOW_DISSECTOR_KEY_ENC_KEYID, enc_key_id); FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, @@ -1201,6 +1222,7 @@ static int fl_dump_key_ip(struct sk_buff *skb, } static int fl_dump_key_vlan(struct sk_buff *skb, + int vlan_id_key, int vlan_prio_key, struct flow_dissector_key_vlan *vlan_key, struct flow_dissector_key_vlan *vlan_mask) { @@ -1209,13 +1231,13 @@ static int fl_dump_key_vlan(struct sk_buff *skb, if (!memchr_inv(vlan_mask, 0, sizeof(*vlan_mask))) return 0; if (vlan_mask->vlan_id) { - err = nla_put_u16(skb, TCA_FLOWER_KEY_VLAN_ID, + err = nla_put_u16(skb, vlan_id_key, vlan_key->vlan_id); if (err) return err; } if (vlan_mask->vlan_priority) { - err = nla_put_u8(skb, TCA_FLOWER_KEY_VLAN_PRIO, + err = nla_put_u8(skb, vlan_prio_key, vlan_key->vlan_priority); if (err) return err; @@ -1310,13 +1332,28 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh, if (fl_dump_key_mpls(skb, &key->mpls, &mask->mpls)) goto nla_put_failure; - if (fl_dump_key_vlan(skb, &key->vlan, &mask->vlan)) + if (fl_dump_key_vlan(skb, TCA_FLOWER_KEY_VLAN_ID, + TCA_FLOWER_KEY_VLAN_PRIO, &key->vlan, &mask->vlan)) goto nla_put_failure; - if (mask->vlan.vlan_tpid && - nla_put_be16(skb, TCA_FLOWER_KEY_VLAN_ETH_TYPE, key->basic.n_proto)) + if (fl_dump_key_vlan(skb, TCA_FLOWER_KEY_CVLAN_ID, + TCA_FLOWER_KEY_CVLAN_PRIO, + &key->cvlan, &mask->cvlan) || + (mask->cvlan.vlan_tpid && + nla_put_u16(skb, TCA_FLOWER_KEY_VLAN_ETH_TYPE, + key->cvlan.vlan_tpid))) goto nla_put_failure; + if (mask->cvlan.vlan_tpid) { + if (nla_put_be16(skb, TCA_FLOWER_KEY_CVLAN_ETH_TYPE, + key->basic.n_proto)) + goto nla_put_failure; + } else if (mask->vlan.vlan_tpid) { + if (nla_put_be16(skb, TCA_FLOWER_KEY_VLAN_ETH_TYPE, + key->basic.n_proto)) + goto nla_put_failure; + } + if ((key->basic.n_proto == htons(ETH_P_IP) || key->basic.n_proto == htons(ETH_P_IPV6)) && (fl_dump_key_val(skb, &key->basic.ip_proto, TCA_FLOWER_KEY_IP_PROTO, -- cgit v1.2.3 From b233504033dbd65740e59681820ccfd0a2a8ec53 Mon Sep 17 00:00:00 2001 From: Yifeng Sun Date: Mon, 2 Jul 2018 08:18:03 -0700 Subject: openvswitch: kernel datapath clone action Add 'clone' action to kernel datapath by using existing functions. When actions within clone don't modify the current flow, the flow key is not cloned before executing clone actions. This is a follow up patch for this incomplete work: https://patchwork.ozlabs.org/patch/722096/ v1 -> v2: Refactor as advised by reviewer. Signed-off-by: Yifeng Sun Signed-off-by: Andy Zhou Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- include/linux/openvswitch.h | 5 +++ include/uapi/linux/openvswitch.h | 3 ++ net/openvswitch/actions.c | 33 ++++++++++++++++++ net/openvswitch/flow_netlink.c | 73 ++++++++++++++++++++++++++++++++++++++++ 4 files changed, 114 insertions(+) (limited to 'include') diff --git a/include/linux/openvswitch.h b/include/linux/openvswitch.h index e6b240b6196c..379affc63e24 100644 --- a/include/linux/openvswitch.h +++ b/include/linux/openvswitch.h @@ -21,4 +21,9 @@ #include +#define OVS_CLONE_ATTR_EXEC 0 /* Specify an u32 value. When nonzero, + * actions in clone will not change flow + * keys. False otherwise. + */ + #endif /* _LINUX_OPENVSWITCH_H */ diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 863aabaa5cc9..dbe0cbe4f1b7 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -840,6 +840,8 @@ struct ovs_action_push_eth { * @OVS_ACTION_ATTR_POP_NSH: pop the outermost NSH header off the packet. * @OVS_ACTION_ATTR_METER: Run packet through a meter, which may drop the * packet, or modify the packet (e.g., change the DSCP field). + * @OVS_ACTION_ATTR_CLONE: make a copy of the packet and execute a list of + * actions without affecting the original packet and key. * * Only a single header can be set with a single %OVS_ACTION_ATTR_SET. Not all * fields within a header are modifiable, e.g. the IPv4 protocol and fragment @@ -873,6 +875,7 @@ enum ovs_action_attr { OVS_ACTION_ATTR_PUSH_NSH, /* Nested OVS_NSH_KEY_ATTR_*. */ OVS_ACTION_ATTR_POP_NSH, /* No argument. */ OVS_ACTION_ATTR_METER, /* u32 meter ID. */ + OVS_ACTION_ATTR_CLONE, /* Nested OVS_CLONE_ATTR_*. */ __OVS_ACTION_ATTR_MAX, /* Nothing past this will be accepted * from userspace. */ diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 30a5df27116e..85ae53d8fd09 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -1057,6 +1057,28 @@ static int sample(struct datapath *dp, struct sk_buff *skb, clone_flow_key); } +/* When 'last' is true, clone() should always consume the 'skb'. + * Otherwise, clone() should keep 'skb' intact regardless what + * actions are executed within clone(). + */ +static int clone(struct datapath *dp, struct sk_buff *skb, + struct sw_flow_key *key, const struct nlattr *attr, + bool last) +{ + struct nlattr *actions; + struct nlattr *clone_arg; + int rem = nla_len(attr); + bool dont_clone_flow_key; + + /* The first action is always 'OVS_CLONE_ATTR_ARG'. */ + clone_arg = nla_data(attr); + dont_clone_flow_key = nla_get_u32(clone_arg); + actions = nla_next(clone_arg, &rem); + + return clone_execute(dp, skb, key, 0, actions, rem, last, + !dont_clone_flow_key); +} + static void execute_hash(struct sk_buff *skb, struct sw_flow_key *key, const struct nlattr *attr) { @@ -1336,6 +1358,17 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, consume_skb(skb); return 0; } + break; + + case OVS_ACTION_ATTR_CLONE: { + bool last = nla_is_last(a, rem); + + err = clone(dp, skb, key, a, last); + if (last) + return err; + + break; + } } if (unlikely(err)) { diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 391c4073a6dc..a70097ecf33c 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -2460,6 +2460,40 @@ static int validate_and_copy_sample(struct net *net, const struct nlattr *attr, return 0; } +static int validate_and_copy_clone(struct net *net, + const struct nlattr *attr, + const struct sw_flow_key *key, + struct sw_flow_actions **sfa, + __be16 eth_type, __be16 vlan_tci, + bool log, bool last) +{ + int start, err; + u32 exec; + + if (nla_len(attr) && nla_len(attr) < NLA_HDRLEN) + return -EINVAL; + + start = add_nested_action_start(sfa, OVS_ACTION_ATTR_CLONE, log); + if (start < 0) + return start; + + exec = last || !actions_may_change_flow(attr); + + err = ovs_nla_add_action(sfa, OVS_CLONE_ATTR_EXEC, &exec, + sizeof(exec), log); + if (err) + return err; + + err = __ovs_nla_copy_actions(net, attr, key, sfa, + eth_type, vlan_tci, log); + if (err) + return err; + + add_nested_action_end(*sfa, start); + + return 0; +} + void ovs_match_init(struct sw_flow_match *match, struct sw_flow_key *key, bool reset_key, @@ -2849,6 +2883,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, [OVS_ACTION_ATTR_PUSH_NSH] = (u32)-1, [OVS_ACTION_ATTR_POP_NSH] = 0, [OVS_ACTION_ATTR_METER] = sizeof(u32), + [OVS_ACTION_ATTR_CLONE] = (u32)-1, }; const struct ovs_action_push_vlan *vlan; int type = nla_type(a); @@ -3038,6 +3073,18 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, /* Non-existent meters are simply ignored. */ break; + case OVS_ACTION_ATTR_CLONE: { + bool last = nla_is_last(a, rem); + + err = validate_and_copy_clone(net, a, key, sfa, + eth_type, vlan_tci, + log, last); + if (err) + return err; + skip_copy = true; + break; + } + default: OVS_NLERR(log, "Unknown Action type %d", type); return -EINVAL; @@ -3116,6 +3163,26 @@ out: return err; } +static int clone_action_to_attr(const struct nlattr *attr, + struct sk_buff *skb) +{ + struct nlattr *start; + int err = 0, rem = nla_len(attr); + + start = nla_nest_start(skb, OVS_ACTION_ATTR_CLONE); + if (!start) + return -EMSGSIZE; + + err = ovs_nla_put_actions(nla_data(attr), rem, skb); + + if (err) + nla_nest_cancel(skb, start); + else + nla_nest_end(skb, start); + + return err; +} + static int set_action_to_attr(const struct nlattr *a, struct sk_buff *skb) { const struct nlattr *ovs_key = nla_data(a); @@ -3204,6 +3271,12 @@ int ovs_nla_put_actions(const struct nlattr *attr, int len, struct sk_buff *skb) return err; break; + case OVS_ACTION_ATTR_CLONE: + err = clone_action_to_attr(a, skb); + if (err) + return err; + break; + default: if (nla_put(skb, type, nla_len(a), nla_data(a))) return -EMSGSIZE; -- cgit v1.2.3 From eec94fdb04806790c7b7e6ea347820064cc6d467 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Thu, 5 Jul 2018 17:24:23 +0300 Subject: net: sched: use rcu for action cookie update Implement functions to atomically update and free action cookie using rcu mechanism. Reviewed-by: Marcelo Ricardo Leitner Signed-off-by: Vlad Buslov Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/act_api.h | 2 +- include/net/pkt_cls.h | 1 + net/sched/act_api.c | 44 ++++++++++++++++++++++++++++++-------------- 3 files changed, 32 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/net/act_api.h b/include/net/act_api.h index 5ff11adbe2a6..ffc3ef321776 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -37,7 +37,7 @@ struct tc_action { spinlock_t tcfa_lock; struct gnet_stats_basic_cpu __percpu *cpu_bstats; struct gnet_stats_queue __percpu *cpu_qstats; - struct tc_cookie *act_cookie; + struct tc_cookie __rcu *act_cookie; struct tcf_chain *goto_chain; }; #define tcf_index common.tcfa_index diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 6641584b27f1..2081e4219f81 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -781,6 +781,7 @@ struct tc_mqprio_qopt_offload { struct tc_cookie { u8 *data; u32 len; + struct rcu_head rcu; }; struct tc_qopt_offload_stats { diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 3f4cf930f809..02670c7489e3 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -55,6 +55,24 @@ static void tcf_action_goto_chain_exec(const struct tc_action *a, res->goto_tp = rcu_dereference_bh(chain->filter_chain); } +static void tcf_free_cookie_rcu(struct rcu_head *p) +{ + struct tc_cookie *cookie = container_of(p, struct tc_cookie, rcu); + + kfree(cookie->data); + kfree(cookie); +} + +static void tcf_set_action_cookie(struct tc_cookie __rcu **old_cookie, + struct tc_cookie *new_cookie) +{ + struct tc_cookie *old; + + old = xchg(old_cookie, new_cookie); + if (old) + call_rcu(&old->rcu, tcf_free_cookie_rcu); +} + /* XXX: For standalone actions, we don't need a RCU grace period either, because * actions are always connected to filters and filters are already destroyed in * RCU callbacks, so after a RCU grace period actions are already disconnected @@ -65,10 +83,7 @@ static void free_tcf(struct tc_action *p) free_percpu(p->cpu_bstats); free_percpu(p->cpu_qstats); - if (p->act_cookie) { - kfree(p->act_cookie->data); - kfree(p->act_cookie); - } + tcf_set_action_cookie(&p->act_cookie, NULL); if (p->goto_chain) tcf_action_goto_chain_fini(p); @@ -567,16 +582,22 @@ tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind, int ref) int err = -EINVAL; unsigned char *b = skb_tail_pointer(skb); struct nlattr *nest; + struct tc_cookie *cookie; if (nla_put_string(skb, TCA_KIND, a->ops->kind)) goto nla_put_failure; if (tcf_action_copy_stats(skb, a, 0)) goto nla_put_failure; - if (a->act_cookie) { - if (nla_put(skb, TCA_ACT_COOKIE, a->act_cookie->len, - a->act_cookie->data)) + + rcu_read_lock(); + cookie = rcu_dereference(a->act_cookie); + if (cookie) { + if (nla_put(skb, TCA_ACT_COOKIE, cookie->len, cookie->data)) { + rcu_read_unlock(); goto nla_put_failure; + } } + rcu_read_unlock(); nest = nla_nest_start(skb, TCA_OPTIONS); if (nest == NULL) @@ -719,13 +740,8 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, if (err < 0) goto err_mod; - if (name == NULL && tb[TCA_ACT_COOKIE]) { - if (a->act_cookie) { - kfree(a->act_cookie->data); - kfree(a->act_cookie); - } - a->act_cookie = cookie; - } + if (!name && tb[TCA_ACT_COOKIE]) + tcf_set_action_cookie(&a->act_cookie, cookie); /* module count goes up only when brand new policy is created * if it exists and is only bound to in a_o->init() then -- cgit v1.2.3 From 036bb44327f50273e85ee4a2c9b56eebce1c0838 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Thu, 5 Jul 2018 17:24:24 +0300 Subject: net: sched: change type of reference and bind counters Change type of action reference counter to refcount_t. Change type of action bind counter to atomic_t. This type is used to allow decrementing bind counter without testing for 0 result. Reviewed-by: Marcelo Ricardo Leitner Signed-off-by: Vlad Buslov Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/act_api.h | 5 +++-- net/sched/act_api.c | 32 ++++++++++++++++++++++---------- net/sched/act_bpf.c | 4 ++-- net/sched/act_connmark.c | 4 ++-- net/sched/act_csum.c | 4 ++-- net/sched/act_gact.c | 4 ++-- net/sched/act_ife.c | 4 ++-- net/sched/act_ipt.c | 4 ++-- net/sched/act_mirred.c | 4 ++-- net/sched/act_nat.c | 4 ++-- net/sched/act_pedit.c | 4 ++-- net/sched/act_police.c | 4 ++-- net/sched/act_sample.c | 4 ++-- net/sched/act_simple.c | 4 ++-- net/sched/act_skbedit.c | 4 ++-- net/sched/act_skbmod.c | 4 ++-- net/sched/act_tunnel_key.c | 4 ++-- net/sched/act_vlan.c | 4 ++-- 18 files changed, 57 insertions(+), 44 deletions(-) (limited to 'include') diff --git a/include/net/act_api.h b/include/net/act_api.h index ffc3ef321776..2759226527a2 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -6,6 +6,7 @@ * Public action API for classifiers/qdiscs */ +#include #include #include #include @@ -26,8 +27,8 @@ struct tc_action { struct tcf_idrinfo *idrinfo; u32 tcfa_index; - int tcfa_refcnt; - int tcfa_bindcnt; + refcount_t tcfa_refcnt; + atomic_t tcfa_bindcnt; u32 tcfa_capab; int tcfa_action; struct tcf_t tcfa_tm; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 02670c7489e3..4f064ecab882 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -105,14 +105,26 @@ int __tcf_idr_release(struct tc_action *p, bool bind, bool strict) ASSERT_RTNL(); + /* Release with strict==1 and bind==0 is only called through act API + * interface (classifiers always bind). Only case when action with + * positive reference count and zero bind count can exist is when it was + * also created with act API (unbinding last classifier will destroy the + * action if it was created by classifier). So only case when bind count + * can be changed after initial check is when unbound action is + * destroyed by act API while classifier binds to action with same id + * concurrently. This result either creation of new action(same behavior + * as before), or reusing existing action if concurrent process + * increments reference count before action is deleted. Both scenarios + * are acceptable. + */ if (p) { if (bind) - p->tcfa_bindcnt--; - else if (strict && p->tcfa_bindcnt > 0) + atomic_dec(&p->tcfa_bindcnt); + else if (strict && atomic_read(&p->tcfa_bindcnt) > 0) return -EPERM; - p->tcfa_refcnt--; - if (p->tcfa_bindcnt <= 0 && p->tcfa_refcnt <= 0) { + if (atomic_read(&p->tcfa_bindcnt) <= 0 && + refcount_dec_and_test(&p->tcfa_refcnt)) { if (p->ops->cleanup) p->ops->cleanup(p); tcf_idr_remove(p->idrinfo, p); @@ -304,8 +316,8 @@ bool tcf_idr_check(struct tc_action_net *tn, u32 index, struct tc_action **a, if (index && p) { if (bind) - p->tcfa_bindcnt++; - p->tcfa_refcnt++; + atomic_inc(&p->tcfa_bindcnt); + refcount_inc(&p->tcfa_refcnt); *a = p; return true; } @@ -324,9 +336,9 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est, if (unlikely(!p)) return -ENOMEM; - p->tcfa_refcnt = 1; + refcount_set(&p->tcfa_refcnt, 1); if (bind) - p->tcfa_bindcnt = 1; + atomic_set(&p->tcfa_bindcnt, 1); if (cpustats) { p->cpu_bstats = netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu); @@ -782,7 +794,7 @@ static void cleanup_a(struct list_head *actions, int ovr) return; list_for_each_entry(a, actions, list) - a->tcfa_refcnt--; + refcount_dec(&a->tcfa_refcnt); } int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, @@ -810,7 +822,7 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, act->order = i; sz += tcf_action_fill_size(act); if (ovr) - act->tcfa_refcnt++; + refcount_inc(&act->tcfa_refcnt); list_add_tail(&act->list, actions); } diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index 18089c02e557..15a2a53cbde1 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -141,8 +141,8 @@ static int tcf_bpf_dump(struct sk_buff *skb, struct tc_action *act, struct tcf_bpf *prog = to_bpf(act); struct tc_act_bpf opt = { .index = prog->tcf_index, - .refcnt = prog->tcf_refcnt - ref, - .bindcnt = prog->tcf_bindcnt - bind, + .refcnt = refcount_read(&prog->tcf_refcnt) - ref, + .bindcnt = atomic_read(&prog->tcf_bindcnt) - bind, .action = prog->tcf_action, }; struct tcf_t tm; diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index e4b880fa51fe..188865034f9a 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -154,8 +154,8 @@ static inline int tcf_connmark_dump(struct sk_buff *skb, struct tc_action *a, struct tc_connmark opt = { .index = ci->tcf_index, - .refcnt = ci->tcf_refcnt - ref, - .bindcnt = ci->tcf_bindcnt - bind, + .refcnt = refcount_read(&ci->tcf_refcnt) - ref, + .bindcnt = atomic_read(&ci->tcf_bindcnt) - bind, .action = ci->tcf_action, .zone = ci->zone, }; diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 526a8e491626..da865f7b390a 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -597,8 +597,8 @@ static int tcf_csum_dump(struct sk_buff *skb, struct tc_action *a, int bind, struct tcf_csum_params *params; struct tc_csum opt = { .index = p->tcf_index, - .refcnt = p->tcf_refcnt - ref, - .bindcnt = p->tcf_bindcnt - bind, + .refcnt = refcount_read(&p->tcf_refcnt) - ref, + .bindcnt = atomic_read(&p->tcf_bindcnt) - bind, }; struct tcf_t t; diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index 4dc4f153cad8..ca83debd5a70 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -169,8 +169,8 @@ static int tcf_gact_dump(struct sk_buff *skb, struct tc_action *a, struct tcf_gact *gact = to_gact(a); struct tc_gact opt = { .index = gact->tcf_index, - .refcnt = gact->tcf_refcnt - ref, - .bindcnt = gact->tcf_bindcnt - bind, + .refcnt = refcount_read(&gact->tcf_refcnt) - ref, + .bindcnt = atomic_read(&gact->tcf_bindcnt) - bind, .action = gact->tcf_action, }; struct tcf_t t; diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 20d7d36b2fc9..3536a23f46b5 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -596,8 +596,8 @@ static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind, struct tcf_ife_params *p = rtnl_dereference(ife->params); struct tc_ife opt = { .index = ife->tcf_index, - .refcnt = ife->tcf_refcnt - ref, - .bindcnt = ife->tcf_bindcnt - bind, + .refcnt = refcount_read(&ife->tcf_refcnt) - ref, + .bindcnt = atomic_read(&ife->tcf_bindcnt) - bind, .action = ife->tcf_action, .flags = p->flags, }; diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 14c312d7908f..7bce88dc11c9 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -280,8 +280,8 @@ static int tcf_ipt_dump(struct sk_buff *skb, struct tc_action *a, int bind, if (unlikely(!t)) goto nla_put_failure; - c.bindcnt = ipt->tcf_bindcnt - bind; - c.refcnt = ipt->tcf_refcnt - ref; + c.bindcnt = atomic_read(&ipt->tcf_bindcnt) - bind; + c.refcnt = refcount_read(&ipt->tcf_refcnt) - ref; strcpy(t->u.user.name, ipt->tcfi_t->u.kernel.target->name); if (nla_put(skb, TCA_IPT_TARG, ipt->tcfi_t->u.user.target_size, t) || diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index fd34015331ab..82a8bdd67c47 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -250,8 +250,8 @@ static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind, struct tc_mirred opt = { .index = m->tcf_index, .action = m->tcf_action, - .refcnt = m->tcf_refcnt - ref, - .bindcnt = m->tcf_bindcnt - bind, + .refcnt = refcount_read(&m->tcf_refcnt) - ref, + .bindcnt = atomic_read(&m->tcf_bindcnt) - bind, .eaction = m->tcfm_eaction, .ifindex = dev ? dev->ifindex : 0, }; diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 4b5848b6c252..457c2ae3de46 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -257,8 +257,8 @@ static int tcf_nat_dump(struct sk_buff *skb, struct tc_action *a, .index = p->tcf_index, .action = p->tcf_action, - .refcnt = p->tcf_refcnt - ref, - .bindcnt = p->tcf_bindcnt - bind, + .refcnt = refcount_read(&p->tcf_refcnt) - ref, + .bindcnt = atomic_read(&p->tcf_bindcnt) - bind, }; struct tcf_t t; diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index e43aef28fdac..889690e0ec39 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -409,8 +409,8 @@ static int tcf_pedit_dump(struct sk_buff *skb, struct tc_action *a, opt->nkeys = p->tcfp_nkeys; opt->flags = p->tcfp_flags; opt->action = p->tcf_action; - opt->refcnt = p->tcf_refcnt - ref; - opt->bindcnt = p->tcf_bindcnt - bind; + opt->refcnt = refcount_read(&p->tcf_refcnt) - ref; + opt->bindcnt = atomic_read(&p->tcf_bindcnt) - bind; if (p->tcfp_keys_ex) { tcf_pedit_key_ex_dump(skb, p->tcfp_keys_ex, p->tcfp_nkeys); diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 4e72bc2a0dfb..a789b8060968 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -274,8 +274,8 @@ static int tcf_act_police_dump(struct sk_buff *skb, struct tc_action *a, .action = police->tcf_action, .mtu = police->tcfp_mtu, .burst = PSCHED_NS2TICKS(police->tcfp_burst), - .refcnt = police->tcf_refcnt - ref, - .bindcnt = police->tcf_bindcnt - bind, + .refcnt = refcount_read(&police->tcf_refcnt) - ref, + .bindcnt = atomic_read(&police->tcf_bindcnt) - bind, }; struct tcf_t t; diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 5db358497c9e..4a46978db092 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -173,8 +173,8 @@ static int tcf_sample_dump(struct sk_buff *skb, struct tc_action *a, struct tc_sample opt = { .index = s->tcf_index, .action = s->tcf_action, - .refcnt = s->tcf_refcnt - ref, - .bindcnt = s->tcf_bindcnt - bind, + .refcnt = refcount_read(&s->tcf_refcnt) - ref, + .bindcnt = atomic_read(&s->tcf_bindcnt) - bind, }; struct tcf_t t; diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index 98c4afe7c15b..c3a761097b01 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -145,8 +145,8 @@ static int tcf_simp_dump(struct sk_buff *skb, struct tc_action *a, struct tcf_defact *d = to_defact(a); struct tc_defact opt = { .index = d->tcf_index, - .refcnt = d->tcf_refcnt - ref, - .bindcnt = d->tcf_bindcnt - bind, + .refcnt = refcount_read(&d->tcf_refcnt) - ref, + .bindcnt = atomic_read(&d->tcf_bindcnt) - bind, .action = d->tcf_action, }; struct tcf_t t; diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index dfaf5d8028dd..cfd20d3d2ca9 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -208,8 +208,8 @@ static int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a, struct tcf_skbedit *d = to_skbedit(a); struct tc_skbedit opt = { .index = d->tcf_index, - .refcnt = d->tcf_refcnt - ref, - .bindcnt = d->tcf_bindcnt - bind, + .refcnt = refcount_read(&d->tcf_refcnt) - ref, + .bindcnt = atomic_read(&d->tcf_bindcnt) - bind, .action = d->tcf_action, }; struct tcf_t t; diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index ad050d7d4b46..ff90d720eda3 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -205,8 +205,8 @@ static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a, struct tcf_skbmod_params *p = rtnl_dereference(d->skbmod_p); struct tc_skbmod opt = { .index = d->tcf_index, - .refcnt = d->tcf_refcnt - ref, - .bindcnt = d->tcf_bindcnt - bind, + .refcnt = refcount_read(&d->tcf_refcnt) - ref, + .bindcnt = atomic_read(&d->tcf_bindcnt) - bind, .action = d->tcf_action, }; struct tcf_t t; diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index ea203e386a92..2354f07eba15 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -474,8 +474,8 @@ static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a, struct tcf_tunnel_key_params *params; struct tc_tunnel_key opt = { .index = t->tcf_index, - .refcnt = t->tcf_refcnt - ref, - .bindcnt = t->tcf_bindcnt - bind, + .refcnt = refcount_read(&t->tcf_refcnt) - ref, + .bindcnt = atomic_read(&t->tcf_bindcnt) - bind, }; struct tcf_t tm; diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index 1fb39e1f9d07..799e3deb44ac 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -239,8 +239,8 @@ static int tcf_vlan_dump(struct sk_buff *skb, struct tc_action *a, struct tcf_vlan_params *p = rtnl_dereference(v->vlan_p); struct tc_vlan opt = { .index = v->tcf_index, - .refcnt = v->tcf_refcnt - ref, - .bindcnt = v->tcf_bindcnt - bind, + .refcnt = refcount_read(&v->tcf_refcnt) - ref, + .bindcnt = atomic_read(&v->tcf_bindcnt) - bind, .action = v->tcf_action, .v_action = p->tcfv_action, }; -- cgit v1.2.3 From 789871bb2a0381425b106d2a995bde1460d35a34 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Thu, 5 Jul 2018 17:24:25 +0300 Subject: net: sched: implement unlocked action init API Add additional 'rtnl_held' argument to act API init functions. It is required to implement actions that need to release rtnl lock before loading kernel module and reacquire if afterwards. Reviewed-by: Marcelo Ricardo Leitner Signed-off-by: Vlad Buslov Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/act_api.h | 6 ++++-- net/sched/act_api.c | 18 +++++++++++------- net/sched/act_bpf.c | 3 ++- net/sched/act_connmark.c | 2 +- net/sched/act_csum.c | 3 ++- net/sched/act_gact.c | 3 ++- net/sched/act_ife.c | 3 ++- net/sched/act_ipt.c | 6 ++++-- net/sched/act_mirred.c | 5 +++-- net/sched/act_nat.c | 2 +- net/sched/act_pedit.c | 3 ++- net/sched/act_police.c | 2 +- net/sched/act_sample.c | 3 ++- net/sched/act_simple.c | 3 ++- net/sched/act_skbedit.c | 3 ++- net/sched/act_skbmod.c | 3 ++- net/sched/act_tunnel_key.c | 3 ++- net/sched/act_vlan.c | 3 ++- net/sched/cls_api.c | 5 +++-- 19 files changed, 50 insertions(+), 29 deletions(-) (limited to 'include') diff --git a/include/net/act_api.h b/include/net/act_api.h index 2759226527a2..27823f4e24c4 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -92,7 +92,8 @@ struct tc_action_ops { struct netlink_ext_ack *extack); int (*init)(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **act, int ovr, - int bind, struct netlink_ext_ack *extack); + int bind, bool rtnl_held, + struct netlink_ext_ack *extack); int (*walk)(struct net *, struct sk_buff *, struct netlink_callback *, int, const struct tc_action_ops *, @@ -168,10 +169,11 @@ int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions, int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, struct nlattr *est, char *name, int ovr, int bind, struct list_head *actions, size_t *attr_size, - struct netlink_ext_ack *extack); + bool rtnl_held, struct netlink_ext_ack *extack); struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, struct nlattr *nla, struct nlattr *est, char *name, int ovr, int bind, + bool rtnl_held, struct netlink_ext_ack *extack); int tcf_action_dump(struct sk_buff *skb, struct list_head *, int, int); int tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int, int); diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 4f064ecab882..256b0c93916c 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -671,6 +671,7 @@ static struct tc_cookie *nla_memdup_cookie(struct nlattr **tb) struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, struct nlattr *nla, struct nlattr *est, char *name, int ovr, int bind, + bool rtnl_held, struct netlink_ext_ack *extack) { struct tc_action *a; @@ -721,9 +722,11 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, a_o = tc_lookup_action_n(act_name); if (a_o == NULL) { #ifdef CONFIG_MODULES - rtnl_unlock(); + if (rtnl_held) + rtnl_unlock(); request_module("act_%s", act_name); - rtnl_lock(); + if (rtnl_held) + rtnl_lock(); a_o = tc_lookup_action_n(act_name); @@ -746,9 +749,10 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, /* backward compatibility for policer */ if (name == NULL) err = a_o->init(net, tb[TCA_ACT_OPTIONS], est, &a, ovr, bind, - extack); + rtnl_held, extack); else - err = a_o->init(net, nla, est, &a, ovr, bind, extack); + err = a_o->init(net, nla, est, &a, ovr, bind, rtnl_held, + extack); if (err < 0) goto err_mod; @@ -800,7 +804,7 @@ static void cleanup_a(struct list_head *actions, int ovr) int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, struct nlattr *est, char *name, int ovr, int bind, struct list_head *actions, size_t *attr_size, - struct netlink_ext_ack *extack) + bool rtnl_held, struct netlink_ext_ack *extack) { struct nlattr *tb[TCA_ACT_MAX_PRIO + 1]; struct tc_action *act; @@ -814,7 +818,7 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) { act = tcf_action_init_1(net, tp, tb[i], est, name, ovr, bind, - extack); + rtnl_held, extack); if (IS_ERR(act)) { err = PTR_ERR(act); goto err; @@ -1173,7 +1177,7 @@ static int tcf_action_add(struct net *net, struct nlattr *nla, LIST_HEAD(actions); ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, &actions, - &attr_size, extack); + &attr_size, true, extack); if (ret) return ret; diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index 15a2a53cbde1..8ebf40a3506c 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -276,7 +276,8 @@ static void tcf_bpf_prog_fill_cfg(const struct tcf_bpf *prog, static int tcf_bpf_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **act, - int replace, int bind, struct netlink_ext_ack *extack) + int replace, int bind, bool rtnl_held, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, bpf_net_id); struct nlattr *tb[TCA_ACT_BPF_MAX + 1]; diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 188865034f9a..e3787aa0025a 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -96,7 +96,7 @@ static const struct nla_policy connmark_policy[TCA_CONNMARK_MAX + 1] = { static int tcf_connmark_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind, + int ovr, int bind, bool rtnl_held, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, connmark_net_id); diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index da865f7b390a..334261943f9f 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -46,7 +46,8 @@ static struct tc_action_ops act_csum_ops; static int tcf_csum_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, - int bind, struct netlink_ext_ack *extack) + int bind, bool rtnl_held, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, csum_net_id); struct tcf_csum_params *params_old, *params_new; diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index ca83debd5a70..b4dfb2b4addc 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -56,7 +56,8 @@ static const struct nla_policy gact_policy[TCA_GACT_MAX + 1] = { static int tcf_gact_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind, struct netlink_ext_ack *extack) + int ovr, int bind, bool rtnl_held, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, gact_net_id); struct nlattr *tb[TCA_GACT_MAX + 1]; diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 3536a23f46b5..576ffbba61c3 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -448,7 +448,8 @@ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb, static int tcf_ife_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind, struct netlink_ext_ack *extack) + int ovr, int bind, bool rtnl_held, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, ife_net_id); struct nlattr *tb[TCA_IFE_MAX + 1]; diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 7bce88dc11c9..9c21663a86a6 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -196,7 +196,8 @@ err1: static int tcf_ipt_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, - int bind, struct netlink_ext_ack *extack) + int bind, bool rtnl_held, + struct netlink_ext_ack *extack) { return __tcf_ipt_init(net, ipt_net_id, nla, est, a, &act_ipt_ops, ovr, bind); @@ -204,7 +205,8 @@ static int tcf_ipt_init(struct net *net, struct nlattr *nla, static int tcf_xt_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, - int bind, struct netlink_ext_ack *extack) + int bind, bool unlocked, + struct netlink_ext_ack *extack) { return __tcf_ipt_init(net, xt_net_id, nla, est, a, &act_xt_ops, ovr, bind); diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 82a8bdd67c47..5434f08f2eb7 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -68,8 +68,9 @@ static unsigned int mirred_net_id; static struct tc_action_ops act_mirred_ops; static int tcf_mirred_init(struct net *net, struct nlattr *nla, - struct nlattr *est, struct tc_action **a, int ovr, - int bind, struct netlink_ext_ack *extack) + struct nlattr *est, struct tc_action **a, + int ovr, int bind, bool rtnl_held, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, mirred_net_id); struct nlattr *tb[TCA_MIRRED_MAX + 1]; diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 457c2ae3de46..e6487ad1e4a8 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -38,7 +38,7 @@ static const struct nla_policy nat_policy[TCA_NAT_MAX + 1] = { static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind, - struct netlink_ext_ack *extack) + bool rtnl_held, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, nat_net_id); struct nlattr *tb[TCA_NAT_MAX + 1]; diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 889690e0ec39..f7965f35585b 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -132,7 +132,8 @@ static int tcf_pedit_key_ex_dump(struct sk_buff *skb, static int tcf_pedit_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind, struct netlink_ext_ack *extack) + int ovr, int bind, bool rtnl_held, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, pedit_net_id); struct nlattr *tb[TCA_PEDIT_MAX + 1]; diff --git a/net/sched/act_police.c b/net/sched/act_police.c index a789b8060968..0e1c2fb0ebea 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -75,7 +75,7 @@ static const struct nla_policy police_policy[TCA_POLICE_MAX + 1] = { static int tcf_act_police_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind, + int ovr, int bind, bool rtnl_held, struct netlink_ext_ack *extack) { int ret = 0, err; diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 4a46978db092..316fc645595d 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -37,7 +37,8 @@ static const struct nla_policy sample_policy[TCA_SAMPLE_MAX + 1] = { static int tcf_sample_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, - int bind, struct netlink_ext_ack *extack) + int bind, bool rtnl_held, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, sample_net_id); struct nlattr *tb[TCA_SAMPLE_MAX + 1]; diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index c3a761097b01..dc591cc87f4a 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -79,7 +79,8 @@ static const struct nla_policy simple_policy[TCA_DEF_MAX + 1] = { static int tcf_simp_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind, struct netlink_ext_ack *extack) + int ovr, int bind, bool rtnl_held, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, simp_net_id); struct nlattr *tb[TCA_DEF_MAX + 1]; diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index cfd20d3d2ca9..c4ae4bd830aa 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -94,7 +94,8 @@ static const struct nla_policy skbedit_policy[TCA_SKBEDIT_MAX + 1] = { static int tcf_skbedit_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind, struct netlink_ext_ack *extack) + int ovr, int bind, bool rtnl_held, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, skbedit_net_id); struct nlattr *tb[TCA_SKBEDIT_MAX + 1]; diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index ff90d720eda3..026d6f58eda1 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -84,7 +84,8 @@ static const struct nla_policy skbmod_policy[TCA_SKBMOD_MAX + 1] = { static int tcf_skbmod_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind, struct netlink_ext_ack *extack) + int ovr, int bind, bool rtnl_held, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, skbmod_net_id); struct nlattr *tb[TCA_SKBMOD_MAX + 1]; diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 2354f07eba15..15ea5ce0f9ed 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -201,7 +201,8 @@ static const struct nla_policy tunnel_key_policy[TCA_TUNNEL_KEY_MAX + 1] = { static int tunnel_key_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind, struct netlink_ext_ack *extack) + int ovr, int bind, bool rtnl_held, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, tunnel_key_net_id); struct nlattr *tb[TCA_TUNNEL_KEY_MAX + 1]; diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index 799e3deb44ac..c61775250722 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -109,7 +109,8 @@ static const struct nla_policy vlan_policy[TCA_VLAN_MAX + 1] = { static int tcf_vlan_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind, struct netlink_ext_ack *extack) + int ovr, int bind, bool rtnl_held, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, vlan_net_id); struct nlattr *tb[TCA_VLAN_MAX + 1]; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index bbf8dda96b0e..ebc2b9dd783f 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1632,7 +1632,7 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, if (exts->police && tb[exts->police]) { act = tcf_action_init_1(net, tp, tb[exts->police], rate_tlv, "police", ovr, - TCA_ACT_BIND, extack); + TCA_ACT_BIND, true, extack); if (IS_ERR(act)) return PTR_ERR(act); @@ -1645,7 +1645,8 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, err = tcf_action_init(net, tp, tb[exts->action], rate_tlv, NULL, ovr, TCA_ACT_BIND, - &actions, &attr_size, extack); + &actions, &attr_size, true, + extack); if (err) return err; list_for_each_entry(act, &actions, list) -- cgit v1.2.3 From 2a2ea349704fffade9526d5122299edbbfd122ca Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Thu, 5 Jul 2018 17:24:27 +0300 Subject: net: sched: implement action API that deletes action by index Implement new action API function that atomically finds and deletes action from idr by index. Intended to be used by lockless actions that do not rely on rtnl lock. Reviewed-by: Marcelo Ricardo Leitner Signed-off-by: Vlad Buslov Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/act_api.h | 1 + net/sched/act_api.c | 39 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 40 insertions(+) (limited to 'include') diff --git a/include/net/act_api.h b/include/net/act_api.h index 27823f4e24c4..a8eaae67c264 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -153,6 +153,7 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est, int bind, bool cpustats); void tcf_idr_insert(struct tc_action_net *tn, struct tc_action *a); +int tcf_idr_delete_index(struct tc_action_net *tn, u32 index); int __tcf_idr_release(struct tc_action *a, bool bind, bool strict); static inline int tcf_idr_release(struct tc_action *a, bool bind) diff --git a/net/sched/act_api.c b/net/sched/act_api.c index aa304d36fee0..0f31f09946ab 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -319,6 +319,45 @@ bool tcf_idr_check(struct tc_action_net *tn, u32 index, struct tc_action **a, } EXPORT_SYMBOL(tcf_idr_check); +int tcf_idr_delete_index(struct tc_action_net *tn, u32 index) +{ + struct tcf_idrinfo *idrinfo = tn->idrinfo; + struct tc_action *p; + int ret = 0; + + spin_lock(&idrinfo->lock); + p = idr_find(&idrinfo->action_idr, index); + if (!p) { + spin_unlock(&idrinfo->lock); + return -ENOENT; + } + + if (!atomic_read(&p->tcfa_bindcnt)) { + if (refcount_dec_and_test(&p->tcfa_refcnt)) { + struct module *owner = p->ops->owner; + + WARN_ON(p != idr_remove(&idrinfo->action_idr, + p->tcfa_index)); + spin_unlock(&idrinfo->lock); + + if (p->ops->cleanup) + p->ops->cleanup(p); + + gen_kill_estimator(&p->tcfa_rate_est); + free_tcf(p); + module_put(owner); + return 0; + } + ret = 0; + } else { + ret = -EPERM; + } + + spin_unlock(&idrinfo->lock); + return ret; +} +EXPORT_SYMBOL(tcf_idr_delete_index); + int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est, struct tc_action **a, const struct tc_action_ops *ops, int bind, bool cpustats) -- cgit v1.2.3 From b409074e6693bcdaa7abbee2a035f22a9eabda53 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Thu, 5 Jul 2018 17:24:28 +0300 Subject: net: sched: add 'delete' function to action ops Extend action ops with 'delete' function. Each action type to implements its own delete function that doesn't depend on rtnl lock. Implement delete function that is required to delete actions without holding rtnl lock. Use action API function that atomically deletes action only if it is still in action idr. This implementation prevents concurrent threads from deleting same action twice. Reviewed-by: Marcelo Ricardo Leitner Signed-off-by: Vlad Buslov Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/act_api.h | 1 + net/sched/act_bpf.c | 8 ++++++++ net/sched/act_connmark.c | 8 ++++++++ net/sched/act_csum.c | 8 ++++++++ net/sched/act_gact.c | 8 ++++++++ net/sched/act_ife.c | 8 ++++++++ net/sched/act_ipt.c | 16 ++++++++++++++++ net/sched/act_mirred.c | 8 ++++++++ net/sched/act_nat.c | 8 ++++++++ net/sched/act_pedit.c | 8 ++++++++ net/sched/act_police.c | 8 ++++++++ net/sched/act_sample.c | 8 ++++++++ net/sched/act_simple.c | 8 ++++++++ net/sched/act_skbedit.c | 8 ++++++++ net/sched/act_skbmod.c | 8 ++++++++ net/sched/act_tunnel_key.c | 8 ++++++++ net/sched/act_vlan.c | 8 ++++++++ 17 files changed, 137 insertions(+) (limited to 'include') diff --git a/include/net/act_api.h b/include/net/act_api.h index a8eaae67c264..b9ed2b8256a5 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -101,6 +101,7 @@ struct tc_action_ops { void (*stats_update)(struct tc_action *, u64, u32, u64); size_t (*get_fill_size)(const struct tc_action *act); struct net_device *(*get_dev)(const struct tc_action *a); + int (*delete)(struct net *net, u32 index); }; struct tc_action_net { diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index 8ebf40a3506c..7941dd66ff83 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -388,6 +388,13 @@ static int tcf_bpf_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } +static int tcf_bpf_delete(struct net *net, u32 index) +{ + struct tc_action_net *tn = net_generic(net, bpf_net_id); + + return tcf_idr_delete_index(tn, index); +} + static struct tc_action_ops act_bpf_ops __read_mostly = { .kind = "bpf", .type = TCA_ACT_BPF, @@ -398,6 +405,7 @@ static struct tc_action_ops act_bpf_ops __read_mostly = { .init = tcf_bpf_init, .walk = tcf_bpf_walker, .lookup = tcf_bpf_search, + .delete = tcf_bpf_delete, .size = sizeof(struct tcf_bpf), }; diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index e3787aa0025a..143c2d3de723 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -193,6 +193,13 @@ static int tcf_connmark_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } +static int tcf_connmark_delete(struct net *net, u32 index) +{ + struct tc_action_net *tn = net_generic(net, connmark_net_id); + + return tcf_idr_delete_index(tn, index); +} + static struct tc_action_ops act_connmark_ops = { .kind = "connmark", .type = TCA_ACT_CONNMARK, @@ -202,6 +209,7 @@ static struct tc_action_ops act_connmark_ops = { .init = tcf_connmark_init, .walk = tcf_connmark_walker, .lookup = tcf_connmark_search, + .delete = tcf_connmark_delete, .size = sizeof(struct tcf_connmark_info), }; diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 334261943f9f..3768539340e0 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -654,6 +654,13 @@ static size_t tcf_csum_get_fill_size(const struct tc_action *act) return nla_total_size(sizeof(struct tc_csum)); } +static int tcf_csum_delete(struct net *net, u32 index) +{ + struct tc_action_net *tn = net_generic(net, csum_net_id); + + return tcf_idr_delete_index(tn, index); +} + static struct tc_action_ops act_csum_ops = { .kind = "csum", .type = TCA_ACT_CSUM, @@ -665,6 +672,7 @@ static struct tc_action_ops act_csum_ops = { .walk = tcf_csum_walker, .lookup = tcf_csum_search, .get_fill_size = tcf_csum_get_fill_size, + .delete = tcf_csum_delete, .size = sizeof(struct tcf_csum), }; diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index b4dfb2b4addc..a431a711f0dd 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -231,6 +231,13 @@ static size_t tcf_gact_get_fill_size(const struct tc_action *act) return sz; } +static int tcf_gact_delete(struct net *net, u32 index) +{ + struct tc_action_net *tn = net_generic(net, gact_net_id); + + return tcf_idr_delete_index(tn, index); +} + static struct tc_action_ops act_gact_ops = { .kind = "gact", .type = TCA_ACT_GACT, @@ -242,6 +249,7 @@ static struct tc_action_ops act_gact_ops = { .walk = tcf_gact_walker, .lookup = tcf_gact_search, .get_fill_size = tcf_gact_get_fill_size, + .delete = tcf_gact_delete, .size = sizeof(struct tcf_gact), }; diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 576ffbba61c3..89a761395c94 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -844,6 +844,13 @@ static int tcf_ife_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } +static int tcf_ife_delete(struct net *net, u32 index) +{ + struct tc_action_net *tn = net_generic(net, ife_net_id); + + return tcf_idr_delete_index(tn, index); +} + static struct tc_action_ops act_ife_ops = { .kind = "ife", .type = TCA_ACT_IFE, @@ -854,6 +861,7 @@ static struct tc_action_ops act_ife_ops = { .init = tcf_ife_init, .walk = tcf_ife_walker, .lookup = tcf_ife_search, + .delete = tcf_ife_delete, .size = sizeof(struct tcf_ife_info), }; diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 9c21663a86a6..6c234411c771 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -324,6 +324,13 @@ static int tcf_ipt_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } +static int tcf_ipt_delete(struct net *net, u32 index) +{ + struct tc_action_net *tn = net_generic(net, ipt_net_id); + + return tcf_idr_delete_index(tn, index); +} + static struct tc_action_ops act_ipt_ops = { .kind = "ipt", .type = TCA_ACT_IPT, @@ -334,6 +341,7 @@ static struct tc_action_ops act_ipt_ops = { .init = tcf_ipt_init, .walk = tcf_ipt_walker, .lookup = tcf_ipt_search, + .delete = tcf_ipt_delete, .size = sizeof(struct tcf_ipt), }; @@ -374,6 +382,13 @@ static int tcf_xt_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } +static int tcf_xt_delete(struct net *net, u32 index) +{ + struct tc_action_net *tn = net_generic(net, xt_net_id); + + return tcf_idr_delete_index(tn, index); +} + static struct tc_action_ops act_xt_ops = { .kind = "xt", .type = TCA_ACT_XT, @@ -384,6 +399,7 @@ static struct tc_action_ops act_xt_ops = { .init = tcf_xt_init, .walk = tcf_xt_walker, .lookup = tcf_xt_search, + .delete = tcf_xt_delete, .size = sizeof(struct tcf_ipt), }; diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 5434f08f2eb7..3d8300bce7e4 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -322,6 +322,13 @@ static struct net_device *tcf_mirred_get_dev(const struct tc_action *a) return rtnl_dereference(m->tcfm_dev); } +static int tcf_mirred_delete(struct net *net, u32 index) +{ + struct tc_action_net *tn = net_generic(net, mirred_net_id); + + return tcf_idr_delete_index(tn, index); +} + static struct tc_action_ops act_mirred_ops = { .kind = "mirred", .type = TCA_ACT_MIRRED, @@ -335,6 +342,7 @@ static struct tc_action_ops act_mirred_ops = { .lookup = tcf_mirred_search, .size = sizeof(struct tcf_mirred), .get_dev = tcf_mirred_get_dev, + .delete = tcf_mirred_delete, }; static __net_init int mirred_init_net(struct net *net) diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index e6487ad1e4a8..9eb27c89dc46 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -294,6 +294,13 @@ static int tcf_nat_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } +static int tcf_nat_delete(struct net *net, u32 index) +{ + struct tc_action_net *tn = net_generic(net, nat_net_id); + + return tcf_idr_delete_index(tn, index); +} + static struct tc_action_ops act_nat_ops = { .kind = "nat", .type = TCA_ACT_NAT, @@ -303,6 +310,7 @@ static struct tc_action_ops act_nat_ops = { .init = tcf_nat_init, .walk = tcf_nat_walker, .lookup = tcf_nat_search, + .delete = tcf_nat_delete, .size = sizeof(struct tcf_nat), }; diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index f7965f35585b..45871052840f 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -454,6 +454,13 @@ static int tcf_pedit_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } +static int tcf_pedit_delete(struct net *net, u32 index) +{ + struct tc_action_net *tn = net_generic(net, pedit_net_id); + + return tcf_idr_delete_index(tn, index); +} + static struct tc_action_ops act_pedit_ops = { .kind = "pedit", .type = TCA_ACT_PEDIT, @@ -464,6 +471,7 @@ static struct tc_action_ops act_pedit_ops = { .init = tcf_pedit_init, .walk = tcf_pedit_walker, .lookup = tcf_pedit_search, + .delete = tcf_pedit_delete, .size = sizeof(struct tcf_pedit), }; diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 0e1c2fb0ebea..c955fb0d4f3f 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -314,6 +314,13 @@ static int tcf_police_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } +static int tcf_police_delete(struct net *net, u32 index) +{ + struct tc_action_net *tn = net_generic(net, police_net_id); + + return tcf_idr_delete_index(tn, index); +} + MODULE_AUTHOR("Alexey Kuznetsov"); MODULE_DESCRIPTION("Policing actions"); MODULE_LICENSE("GPL"); @@ -327,6 +334,7 @@ static struct tc_action_ops act_police_ops = { .init = tcf_act_police_init, .walk = tcf_act_police_walker, .lookup = tcf_police_search, + .delete = tcf_police_delete, .size = sizeof(struct tcf_police), }; diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 316fc645595d..6f79d2afcba2 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -220,6 +220,13 @@ static int tcf_sample_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } +static int tcf_sample_delete(struct net *net, u32 index) +{ + struct tc_action_net *tn = net_generic(net, sample_net_id); + + return tcf_idr_delete_index(tn, index); +} + static struct tc_action_ops act_sample_ops = { .kind = "sample", .type = TCA_ACT_SAMPLE, @@ -230,6 +237,7 @@ static struct tc_action_ops act_sample_ops = { .cleanup = tcf_sample_cleanup, .walk = tcf_sample_walker, .lookup = tcf_sample_search, + .delete = tcf_sample_delete, .size = sizeof(struct tcf_sample), }; diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index dc591cc87f4a..446c750f3d3c 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -184,6 +184,13 @@ static int tcf_simp_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } +static int tcf_simp_delete(struct net *net, u32 index) +{ + struct tc_action_net *tn = net_generic(net, simp_net_id); + + return tcf_idr_delete_index(tn, index); +} + static struct tc_action_ops act_simp_ops = { .kind = "simple", .type = TCA_ACT_SIMP, @@ -194,6 +201,7 @@ static struct tc_action_ops act_simp_ops = { .init = tcf_simp_init, .walk = tcf_simp_walker, .lookup = tcf_simp_search, + .delete = tcf_simp_delete, .size = sizeof(struct tcf_defact), }; diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index c4ae4bd830aa..b3eaa120c7f4 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -267,6 +267,13 @@ static int tcf_skbedit_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } +static int tcf_skbedit_delete(struct net *net, u32 index) +{ + struct tc_action_net *tn = net_generic(net, skbedit_net_id); + + return tcf_idr_delete_index(tn, index); +} + static struct tc_action_ops act_skbedit_ops = { .kind = "skbedit", .type = TCA_ACT_SKBEDIT, @@ -276,6 +283,7 @@ static struct tc_action_ops act_skbedit_ops = { .init = tcf_skbedit_init, .walk = tcf_skbedit_walker, .lookup = tcf_skbedit_search, + .delete = tcf_skbedit_delete, .size = sizeof(struct tcf_skbedit), }; diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index 026d6f58eda1..30be3f767495 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -253,6 +253,13 @@ static int tcf_skbmod_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } +static int tcf_skbmod_delete(struct net *net, u32 index) +{ + struct tc_action_net *tn = net_generic(net, skbmod_net_id); + + return tcf_idr_delete_index(tn, index); +} + static struct tc_action_ops act_skbmod_ops = { .kind = "skbmod", .type = TCA_ACT_SKBMOD, @@ -263,6 +270,7 @@ static struct tc_action_ops act_skbmod_ops = { .cleanup = tcf_skbmod_cleanup, .walk = tcf_skbmod_walker, .lookup = tcf_skbmod_search, + .delete = tcf_skbmod_delete, .size = sizeof(struct tcf_skbmod), }; diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 15ea5ce0f9ed..655ed0b3fc67 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -534,6 +534,13 @@ static int tunnel_key_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } +static int tunnel_key_delete(struct net *net, u32 index) +{ + struct tc_action_net *tn = net_generic(net, tunnel_key_net_id); + + return tcf_idr_delete_index(tn, index); +} + static struct tc_action_ops act_tunnel_key_ops = { .kind = "tunnel_key", .type = TCA_ACT_TUNNEL_KEY, @@ -544,6 +551,7 @@ static struct tc_action_ops act_tunnel_key_ops = { .cleanup = tunnel_key_release, .walk = tunnel_key_walker, .lookup = tunnel_key_search, + .delete = tunnel_key_delete, .size = sizeof(struct tcf_tunnel_key), }; diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index c61775250722..e334d2751784 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -287,6 +287,13 @@ static int tcf_vlan_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } +static int tcf_vlan_delete(struct net *net, u32 index) +{ + struct tc_action_net *tn = net_generic(net, vlan_net_id); + + return tcf_idr_delete_index(tn, index); +} + static struct tc_action_ops act_vlan_ops = { .kind = "vlan", .type = TCA_ACT_VLAN, @@ -297,6 +304,7 @@ static struct tc_action_ops act_vlan_ops = { .cleanup = tcf_vlan_cleanup, .walk = tcf_vlan_walker, .lookup = tcf_vlan_search, + .delete = tcf_vlan_delete, .size = sizeof(struct tcf_vlan), }; -- cgit v1.2.3 From 0190c1d452a91c38a3462abdd81752be1b9006a8 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Thu, 5 Jul 2018 17:24:32 +0300 Subject: net: sched: atomically check-allocate action Implement function that atomically checks if action exists and either takes reference to it, or allocates idr slot for action index to prevent concurrent allocations of actions with same index. Use EBUSY error pointer to indicate that idr slot is reserved. Implement cleanup helper function that removes temporary error pointer from idr. (in case of error between idr allocation and insertion of newly created action to specified index) Refactor all action init functions to insert new action to idr using this API. Reviewed-by: Marcelo Ricardo Leitner Signed-off-by: Vlad Buslov Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/act_api.h | 3 ++ net/sched/act_api.c | 92 ++++++++++++++++++++++++++++++++++++---------- net/sched/act_bpf.c | 11 ++++-- net/sched/act_connmark.c | 10 +++-- net/sched/act_csum.c | 11 ++++-- net/sched/act_gact.c | 11 ++++-- net/sched/act_ife.c | 6 ++- net/sched/act_ipt.c | 13 ++++++- net/sched/act_mirred.c | 16 ++++++-- net/sched/act_nat.c | 11 ++++-- net/sched/act_pedit.c | 12 ++++-- net/sched/act_police.c | 9 ++++- net/sched/act_sample.c | 11 ++++-- net/sched/act_simple.c | 11 +++++- net/sched/act_skbedit.c | 11 +++++- net/sched/act_skbmod.c | 11 +++++- net/sched/act_tunnel_key.c | 9 ++++- net/sched/act_vlan.c | 17 ++++++++- 18 files changed, 216 insertions(+), 59 deletions(-) (limited to 'include') diff --git a/include/net/act_api.h b/include/net/act_api.h index b9ed2b8256a5..8090de2edab7 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -154,6 +154,9 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est, int bind, bool cpustats); void tcf_idr_insert(struct tc_action_net *tn, struct tc_action *a); +void tcf_idr_cleanup(struct tc_action_net *tn, u32 index); +int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index, + struct tc_action **a, int bind); int tcf_idr_delete_index(struct tc_action_net *tn, u32 index); int __tcf_idr_release(struct tc_action *a, bool bind, bool strict); diff --git a/net/sched/act_api.c b/net/sched/act_api.c index eefe8c2fe667..9511502e1cbb 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -303,7 +303,9 @@ static bool __tcf_idr_check(struct tc_action_net *tn, u32 index, spin_lock(&idrinfo->lock); p = idr_find(&idrinfo->action_idr, index); - if (p) { + if (IS_ERR(p)) { + p = NULL; + } else if (p) { refcount_inc(&p->tcfa_refcnt); if (bind) atomic_inc(&p->tcfa_bindcnt); @@ -371,7 +373,6 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est, { struct tc_action *p = kzalloc(ops->size, GFP_KERNEL); struct tcf_idrinfo *idrinfo = tn->idrinfo; - struct idr *idr = &idrinfo->action_idr; int err = -ENOMEM; if (unlikely(!p)) @@ -389,20 +390,6 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est, goto err2; } spin_lock_init(&p->tcfa_lock); - idr_preload(GFP_KERNEL); - spin_lock(&idrinfo->lock); - /* user doesn't specify an index */ - if (!index) { - index = 1; - err = idr_alloc_u32(idr, NULL, &index, UINT_MAX, GFP_ATOMIC); - } else { - err = idr_alloc_u32(idr, NULL, &index, index, GFP_ATOMIC); - } - spin_unlock(&idrinfo->lock); - idr_preload_end(); - if (err) - goto err3; - p->tcfa_index = index; p->tcfa_tm.install = jiffies; p->tcfa_tm.lastuse = jiffies; @@ -412,7 +399,7 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est, &p->tcfa_rate_est, &p->tcfa_lock, NULL, est); if (err) - goto err4; + goto err3; } p->idrinfo = idrinfo; @@ -420,8 +407,6 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est, INIT_LIST_HEAD(&p->list); *a = p; return 0; -err4: - idr_remove(idr, index); err3: free_percpu(p->cpu_qstats); err2: @@ -437,11 +422,78 @@ void tcf_idr_insert(struct tc_action_net *tn, struct tc_action *a) struct tcf_idrinfo *idrinfo = tn->idrinfo; spin_lock(&idrinfo->lock); - idr_replace(&idrinfo->action_idr, a, a->tcfa_index); + /* Replace ERR_PTR(-EBUSY) allocated by tcf_idr_check_alloc */ + WARN_ON(!IS_ERR(idr_replace(&idrinfo->action_idr, a, a->tcfa_index))); spin_unlock(&idrinfo->lock); } EXPORT_SYMBOL(tcf_idr_insert); +/* Cleanup idr index that was allocated but not initialized. */ + +void tcf_idr_cleanup(struct tc_action_net *tn, u32 index) +{ + struct tcf_idrinfo *idrinfo = tn->idrinfo; + + spin_lock(&idrinfo->lock); + /* Remove ERR_PTR(-EBUSY) allocated by tcf_idr_check_alloc */ + WARN_ON(!IS_ERR(idr_remove(&idrinfo->action_idr, index))); + spin_unlock(&idrinfo->lock); +} +EXPORT_SYMBOL(tcf_idr_cleanup); + +/* Check if action with specified index exists. If actions is found, increments + * its reference and bind counters, and return 1. Otherwise insert temporary + * error pointer (to prevent concurrent users from inserting actions with same + * index) and return 0. + */ + +int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index, + struct tc_action **a, int bind) +{ + struct tcf_idrinfo *idrinfo = tn->idrinfo; + struct tc_action *p; + int ret; + +again: + spin_lock(&idrinfo->lock); + if (*index) { + p = idr_find(&idrinfo->action_idr, *index); + if (IS_ERR(p)) { + /* This means that another process allocated + * index but did not assign the pointer yet. + */ + spin_unlock(&idrinfo->lock); + goto again; + } + + if (p) { + refcount_inc(&p->tcfa_refcnt); + if (bind) + atomic_inc(&p->tcfa_bindcnt); + *a = p; + ret = 1; + } else { + *a = NULL; + ret = idr_alloc_u32(&idrinfo->action_idr, NULL, index, + *index, GFP_ATOMIC); + if (!ret) + idr_replace(&idrinfo->action_idr, + ERR_PTR(-EBUSY), *index); + } + } else { + *index = 1; + *a = NULL; + ret = idr_alloc_u32(&idrinfo->action_idr, NULL, index, + UINT_MAX, GFP_ATOMIC); + if (!ret) + idr_replace(&idrinfo->action_idr, ERR_PTR(-EBUSY), + *index); + } + spin_unlock(&idrinfo->lock); + return ret; +} +EXPORT_SYMBOL(tcf_idr_check_alloc); + void tcf_idrinfo_destroy(const struct tc_action_ops *ops, struct tcf_idrinfo *idrinfo) { diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index d3f4ac6f2c4b..06f743d8ed41 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -299,14 +299,17 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, parm = nla_data(tb[TCA_ACT_BPF_PARMS]); - if (!tcf_idr_check(tn, parm->index, act, bind)) { + ret = tcf_idr_check_alloc(tn, &parm->index, act, bind); + if (!ret) { ret = tcf_idr_create(tn, parm->index, est, act, &act_bpf_ops, bind, true); - if (ret < 0) + if (ret < 0) { + tcf_idr_cleanup(tn, parm->index); return ret; + } res = ACT_P_CREATED; - } else { + } else if (ret > 0) { /* Don't override defaults. */ if (bind) return 0; @@ -315,6 +318,8 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, tcf_idr_release(*act, bind); return -EEXIST; } + } else { + return ret; } is_bpf = tb[TCA_ACT_BPF_OPS_LEN] && tb[TCA_ACT_BPF_OPS]; diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 701e90244eff..1e31f0e448e2 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -118,11 +118,14 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla, parm = nla_data(tb[TCA_CONNMARK_PARMS]); - if (!tcf_idr_check(tn, parm->index, a, bind)) { + ret = tcf_idr_check_alloc(tn, &parm->index, a, bind); + if (!ret) { ret = tcf_idr_create(tn, parm->index, est, a, &act_connmark_ops, bind, false); - if (ret) + if (ret) { + tcf_idr_cleanup(tn, parm->index); return ret; + } ci = to_connmark(*a); ci->tcf_action = parm->action; @@ -131,7 +134,7 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla, tcf_idr_insert(tn, *a); ret = ACT_P_CREATED; - } else { + } else if (ret > 0) { ci = to_connmark(*a); if (bind) return 0; @@ -142,6 +145,7 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla, /* replacing action and zone */ ci->tcf_action = parm->action; ci->zone = parm->zone; + ret = 0; } return ret; diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 5dbee136b0a1..bd232d3bd022 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -67,19 +67,24 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla, return -EINVAL; parm = nla_data(tb[TCA_CSUM_PARMS]); - if (!tcf_idr_check(tn, parm->index, a, bind)) { + err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + if (!err) { ret = tcf_idr_create(tn, parm->index, est, a, &act_csum_ops, bind, true); - if (ret) + if (ret) { + tcf_idr_cleanup(tn, parm->index); return ret; + } ret = ACT_P_CREATED; - } else { + } else if (err > 0) { if (bind)/* dont override defaults */ return 0; if (!ovr) { tcf_idr_release(*a, bind); return -EEXIST; } + } else { + return err; } p = to_tcf_csum(*a); diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index 11c4de3f344e..661b72b9147d 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -91,19 +91,24 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, } #endif - if (!tcf_idr_check(tn, parm->index, a, bind)) { + err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + if (!err) { ret = tcf_idr_create(tn, parm->index, est, a, &act_gact_ops, bind, true); - if (ret) + if (ret) { + tcf_idr_cleanup(tn, parm->index); return ret; + } ret = ACT_P_CREATED; - } else { + } else if (err > 0) { if (bind)/* dont override defaults */ return 0; if (!ovr) { tcf_idr_release(*a, bind); return -EEXIST; } + } else { + return err; } gact = to_gact(*a); diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index acea3feae762..a3eef00cd711 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -484,7 +484,10 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, if (!p) return -ENOMEM; - exists = tcf_idr_check(tn, parm->index, a, bind); + err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + if (err < 0) + return err; + exists = err; if (exists && bind) { kfree(p); return 0; @@ -494,6 +497,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, ret = tcf_idr_create(tn, parm->index, est, a, &act_ife_ops, bind, true); if (ret) { + tcf_idr_cleanup(tn, parm->index); kfree(p); return ret; } diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 85e85dfba401..0dc787a57798 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -119,13 +119,18 @@ static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla, if (tb[TCA_IPT_INDEX] != NULL) index = nla_get_u32(tb[TCA_IPT_INDEX]); - exists = tcf_idr_check(tn, index, a, bind); + err = tcf_idr_check_alloc(tn, &index, a, bind); + if (err < 0) + return err; + exists = err; if (exists && bind) return 0; if (tb[TCA_IPT_HOOK] == NULL || tb[TCA_IPT_TARG] == NULL) { if (exists) tcf_idr_release(*a, bind); + else + tcf_idr_cleanup(tn, index); return -EINVAL; } @@ -133,14 +138,18 @@ static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla, if (nla_len(tb[TCA_IPT_TARG]) < td->u.target_size) { if (exists) tcf_idr_release(*a, bind); + else + tcf_idr_cleanup(tn, index); return -EINVAL; } if (!exists) { ret = tcf_idr_create(tn, index, est, a, ops, bind, false); - if (ret) + if (ret) { + tcf_idr_cleanup(tn, index); return ret; + } ret = ACT_P_CREATED; } else { if (bind)/* dont override defaults */ diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index e08aed06d7f8..6afd89a36c69 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -79,7 +79,7 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, struct tcf_mirred *m; struct net_device *dev; bool exists = false; - int ret; + int ret, err; if (!nla) { NL_SET_ERR_MSG_MOD(extack, "Mirred requires attributes to be passed"); @@ -94,7 +94,10 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, } parm = nla_data(tb[TCA_MIRRED_PARMS]); - exists = tcf_idr_check(tn, parm->index, a, bind); + err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + if (err < 0) + return err; + exists = err; if (exists && bind) return 0; @@ -107,6 +110,8 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, default: if (exists) tcf_idr_release(*a, bind); + else + tcf_idr_cleanup(tn, parm->index); NL_SET_ERR_MSG_MOD(extack, "Unknown mirred option"); return -EINVAL; } @@ -115,6 +120,8 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, if (dev == NULL) { if (exists) tcf_idr_release(*a, bind); + else + tcf_idr_cleanup(tn, parm->index); return -ENODEV; } mac_header_xmit = dev_is_mac_header_xmit(dev); @@ -124,13 +131,16 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, if (!exists) { if (!dev) { + tcf_idr_cleanup(tn, parm->index); NL_SET_ERR_MSG_MOD(extack, "Specified device does not exist"); return -EINVAL; } ret = tcf_idr_create(tn, parm->index, est, a, &act_mirred_ops, bind, true); - if (ret) + if (ret) { + tcf_idr_cleanup(tn, parm->index); return ret; + } ret = ACT_P_CREATED; } else if (!ovr) { tcf_idr_release(*a, bind); diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 1f91e8e66c0f..4dd9188a72fd 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -57,19 +57,24 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, return -EINVAL; parm = nla_data(tb[TCA_NAT_PARMS]); - if (!tcf_idr_check(tn, parm->index, a, bind)) { + err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + if (!err) { ret = tcf_idr_create(tn, parm->index, est, a, &act_nat_ops, bind, false); - if (ret) + if (ret) { + tcf_idr_cleanup(tn, parm->index); return ret; + } ret = ACT_P_CREATED; - } else { + } else if (err > 0) { if (bind) return 0; if (!ovr) { tcf_idr_release(*a, bind); return -EEXIST; } + } else { + return err; } p = to_tcf_nat(*a); diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 3a0e2f762f4e..cc8ffcd1ddb5 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -173,16 +173,20 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, if (IS_ERR(keys_ex)) return PTR_ERR(keys_ex); - if (!tcf_idr_check(tn, parm->index, a, bind)) { + err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + if (!err) { if (!parm->nkeys) { + tcf_idr_cleanup(tn, parm->index); NL_SET_ERR_MSG_MOD(extack, "Pedit requires keys to be passed"); ret = -EINVAL; goto out_free; } ret = tcf_idr_create(tn, parm->index, est, a, &act_pedit_ops, bind, false); - if (ret) + if (ret) { + tcf_idr_cleanup(tn, parm->index); goto out_free; + } p = to_pedit(*a); keys = kmalloc(ksize, GFP_KERNEL); if (!keys) { @@ -191,7 +195,7 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, goto out_free; } ret = ACT_P_CREATED; - } else { + } else if (err > 0) { if (bind) goto out_free; if (!ovr) { @@ -207,6 +211,8 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, goto out_free; } } + } else { + return err; } spin_lock_bh(&p->tcf_lock); diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 99335cca739e..1f3192ea8df7 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -101,15 +101,20 @@ static int tcf_act_police_init(struct net *net, struct nlattr *nla, return -EINVAL; parm = nla_data(tb[TCA_POLICE_TBF]); - exists = tcf_idr_check(tn, parm->index, a, bind); + err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + if (err < 0) + return err; + exists = err; if (exists && bind) return 0; if (!exists) { ret = tcf_idr_create(tn, parm->index, NULL, a, &act_police_ops, bind, false); - if (ret) + if (ret) { + tcf_idr_cleanup(tn, parm->index); return ret; + } ret = ACT_P_CREATED; } else if (!ovr) { tcf_idr_release(*a, bind); diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index a8582e1347db..3079e7be5bde 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -46,7 +46,7 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, struct tc_sample *parm; struct tcf_sample *s; bool exists = false; - int ret; + int ret, err; if (!nla) return -EINVAL; @@ -59,15 +59,20 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, parm = nla_data(tb[TCA_SAMPLE_PARMS]); - exists = tcf_idr_check(tn, parm->index, a, bind); + err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + if (err < 0) + return err; + exists = err; if (exists && bind) return 0; if (!exists) { ret = tcf_idr_create(tn, parm->index, est, a, &act_sample_ops, bind, false); - if (ret) + if (ret) { + tcf_idr_cleanup(tn, parm->index); return ret; + } ret = ACT_P_CREATED; } else if (!ovr) { tcf_idr_release(*a, bind); diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index 2da47c682a30..aa51152e0066 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -100,21 +100,28 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, return -EINVAL; parm = nla_data(tb[TCA_DEF_PARMS]); - exists = tcf_idr_check(tn, parm->index, a, bind); + err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + if (err < 0) + return err; + exists = err; if (exists && bind) return 0; if (tb[TCA_DEF_DATA] == NULL) { if (exists) tcf_idr_release(*a, bind); + else + tcf_idr_cleanup(tn, parm->index); return -EINVAL; } if (!exists) { ret = tcf_idr_create(tn, parm->index, est, a, &act_simp_ops, bind, false); - if (ret) + if (ret) { + tcf_idr_cleanup(tn, parm->index); return ret; + } d = to_defact(*a); ret = alloc_defdata(d, tb[TCA_DEF_DATA]); diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 4616a2c1821f..86521a74ecdd 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -152,21 +152,28 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, parm = nla_data(tb[TCA_SKBEDIT_PARMS]); - exists = tcf_idr_check(tn, parm->index, a, bind); + err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + if (err < 0) + return err; + exists = err; if (exists && bind) return 0; if (!flags) { if (exists) tcf_idr_release(*a, bind); + else + tcf_idr_cleanup(tn, parm->index); return -EINVAL; } if (!exists) { ret = tcf_idr_create(tn, parm->index, est, a, &act_skbedit_ops, bind, false); - if (ret) + if (ret) { + tcf_idr_cleanup(tn, parm->index); return ret; + } d = to_skbedit(*a); ret = ACT_P_CREATED; diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index e844381af066..cdc6bacfb190 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -128,21 +128,28 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla, if (parm->flags & SKBMOD_F_SWAPMAC) lflags = SKBMOD_F_SWAPMAC; - exists = tcf_idr_check(tn, parm->index, a, bind); + err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + if (err < 0) + return err; + exists = err; if (exists && bind) return 0; if (!lflags) { if (exists) tcf_idr_release(*a, bind); + else + tcf_idr_cleanup(tn, parm->index); return -EINVAL; } if (!exists) { ret = tcf_idr_create(tn, parm->index, est, a, &act_skbmod_ops, bind, true); - if (ret) + if (ret) { + tcf_idr_cleanup(tn, parm->index); return ret; + } ret = ACT_P_CREATED; } else if (!ovr) { diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index ab5bf5c13f87..3ec585d58762 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -237,7 +237,10 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, } parm = nla_data(tb[TCA_TUNNEL_KEY_PARMS]); - exists = tcf_idr_check(tn, parm->index, a, bind); + err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + if (err < 0) + return err; + exists = err; if (exists && bind) return 0; @@ -325,7 +328,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, &act_tunnel_key_ops, bind, true); if (ret) { NL_SET_ERR_MSG(extack, "Cannot create TC IDR"); - return ret; + goto err_out; } ret = ACT_P_CREATED; @@ -364,6 +367,8 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, err_out: if (exists) tcf_idr_release(*a, bind); + else + tcf_idr_cleanup(tn, parm->index); return ret; } diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index 9b600faaccbb..ad37f308175a 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -134,7 +134,10 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, if (!tb[TCA_VLAN_PARMS]) return -EINVAL; parm = nla_data(tb[TCA_VLAN_PARMS]); - exists = tcf_idr_check(tn, parm->index, a, bind); + err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + if (err < 0) + return err; + exists = err; if (exists && bind) return 0; @@ -146,12 +149,16 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, if (!tb[TCA_VLAN_PUSH_VLAN_ID]) { if (exists) tcf_idr_release(*a, bind); + else + tcf_idr_cleanup(tn, parm->index); return -EINVAL; } push_vid = nla_get_u16(tb[TCA_VLAN_PUSH_VLAN_ID]); if (push_vid >= VLAN_VID_MASK) { if (exists) tcf_idr_release(*a, bind); + else + tcf_idr_cleanup(tn, parm->index); return -ERANGE; } @@ -164,6 +171,8 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, default: if (exists) tcf_idr_release(*a, bind); + else + tcf_idr_cleanup(tn, parm->index); return -EPROTONOSUPPORT; } } else { @@ -176,6 +185,8 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, default: if (exists) tcf_idr_release(*a, bind); + else + tcf_idr_cleanup(tn, parm->index); return -EINVAL; } action = parm->v_action; @@ -183,8 +194,10 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, if (!exists) { ret = tcf_idr_create(tn, parm->index, est, a, &act_vlan_ops, bind, true); - if (ret) + if (ret) { + tcf_idr_cleanup(tn, parm->index); return ret; + } ret = ACT_P_CREATED; } else if (!ovr) { -- cgit v1.2.3 From 90b73b77d08ec395311411b545c756ca710aae59 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Thu, 5 Jul 2018 17:24:33 +0300 Subject: net: sched: change action API to use array of pointers to actions Act API used linked list to pass set of actions to functions. It is intrusive data structure that stores list nodes inside action structure itself, which means it is not safe to modify such list concurrently. However, action API doesn't use any linked list specific operations on this set of actions, so it can be safely refactored into plain pointer array. Refactor action API to use array of pointers to tc_actions instead of linked list. Change argument 'actions' type of exported action init, destroy and dump functions. Acked-by: Jiri Pirko Signed-off-by: Vlad Buslov Signed-off-by: David S. Miller --- include/net/act_api.h | 7 ++-- net/sched/act_api.c | 89 +++++++++++++++++++++++++++++---------------------- net/sched/cls_api.c | 21 ++++-------- 3 files changed, 60 insertions(+), 57 deletions(-) (limited to 'include') diff --git a/include/net/act_api.h b/include/net/act_api.h index 8090de2edab7..683ce41053d9 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -168,19 +168,20 @@ static inline int tcf_idr_release(struct tc_action *a, bool bind) int tcf_register_action(struct tc_action_ops *a, struct pernet_operations *ops); int tcf_unregister_action(struct tc_action_ops *a, struct pernet_operations *ops); -int tcf_action_destroy(struct list_head *actions, int bind); +int tcf_action_destroy(struct tc_action *actions[], int bind); int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions, int nr_actions, struct tcf_result *res); int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, struct nlattr *est, char *name, int ovr, int bind, - struct list_head *actions, size_t *attr_size, + struct tc_action *actions[], size_t *attr_size, bool rtnl_held, struct netlink_ext_ack *extack); struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, struct nlattr *nla, struct nlattr *est, char *name, int ovr, int bind, bool rtnl_held, struct netlink_ext_ack *extack); -int tcf_action_dump(struct sk_buff *skb, struct list_head *, int, int); +int tcf_action_dump(struct sk_buff *skb, struct tc_action *actions[], int bind, + int ref); int tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int, int); int tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int, int); int tcf_action_copy_stats(struct sk_buff *, struct tc_action *, int); diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 9511502e1cbb..bf1c35f3deb6 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -657,13 +657,15 @@ repeat: } EXPORT_SYMBOL(tcf_action_exec); -int tcf_action_destroy(struct list_head *actions, int bind) +int tcf_action_destroy(struct tc_action *actions[], int bind) { const struct tc_action_ops *ops; - struct tc_action *a, *tmp; - int ret = 0; + struct tc_action *a; + int ret = 0, i; - list_for_each_entry_safe(a, tmp, actions, list) { + for (i = 0; i < TCA_ACT_MAX_PRIO && actions[i]; i++) { + a = actions[i]; + actions[i] = NULL; ops = a->ops; ret = __tcf_idr_release(a, bind, true); if (ret == ACT_P_DELETED) @@ -679,11 +681,12 @@ static int tcf_action_put(struct tc_action *p) return __tcf_action_put(p, false); } -static void tcf_action_put_lst(struct list_head *actions) +static void tcf_action_put_many(struct tc_action *actions[]) { - struct tc_action *a, *tmp; + int i; - list_for_each_entry_safe(a, tmp, actions, list) { + for (i = 0; i < TCA_ACT_MAX_PRIO && actions[i]; i++) { + struct tc_action *a = actions[i]; const struct tc_action_ops *ops = a->ops; if (tcf_action_put(a)) @@ -735,14 +738,15 @@ nla_put_failure: } EXPORT_SYMBOL(tcf_action_dump_1); -int tcf_action_dump(struct sk_buff *skb, struct list_head *actions, +int tcf_action_dump(struct sk_buff *skb, struct tc_action *actions[], int bind, int ref) { struct tc_action *a; - int err = -EINVAL; + int err = -EINVAL, i; struct nlattr *nest; - list_for_each_entry(a, actions, list) { + for (i = 0; i < TCA_ACT_MAX_PRIO && actions[i]; i++) { + a = actions[i]; nest = nla_nest_start(skb, a->order); if (nest == NULL) goto nla_put_failure; @@ -878,10 +882,9 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, if (TC_ACT_EXT_CMP(a->tcfa_action, TC_ACT_GOTO_CHAIN)) { err = tcf_action_goto_chain_init(a, tp); if (err) { - LIST_HEAD(actions); + struct tc_action *actions[] = { a, NULL }; - list_add_tail(&a->list, &actions); - tcf_action_destroy(&actions, bind); + tcf_action_destroy(actions, bind); NL_SET_ERR_MSG(extack, "Failed to init TC action chain"); return ERR_PTR(err); } @@ -899,9 +902,11 @@ err_out: return ERR_PTR(err); } +/* Returns numbers of initialized actions or negative error. */ + int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, struct nlattr *est, char *name, int ovr, int bind, - struct list_head *actions, size_t *attr_size, + struct tc_action *actions[], size_t *attr_size, bool rtnl_held, struct netlink_ext_ack *extack) { struct nlattr *tb[TCA_ACT_MAX_PRIO + 1]; @@ -923,11 +928,12 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, } act->order = i; sz += tcf_action_fill_size(act); - list_add_tail(&act->list, actions); + /* Start from index 0 */ + actions[i - 1] = act; } *attr_size = tcf_action_full_attrs_size(sz); - return 0; + return i - 1; err: tcf_action_destroy(actions, bind); @@ -978,7 +984,7 @@ errout: return -1; } -static int tca_get_fill(struct sk_buff *skb, struct list_head *actions, +static int tca_get_fill(struct sk_buff *skb, struct tc_action *actions[], u32 portid, u32 seq, u16 flags, int event, int bind, int ref) { @@ -1014,7 +1020,7 @@ out_nlmsg_trim: static int tcf_get_notify(struct net *net, u32 portid, struct nlmsghdr *n, - struct list_head *actions, int event, + struct tc_action *actions[], int event, struct netlink_ext_ack *extack) { struct sk_buff *skb; @@ -1150,14 +1156,14 @@ err_out: return err; } -static int tcf_action_delete(struct net *net, struct list_head *actions, - struct netlink_ext_ack *extack) +static int tcf_action_delete(struct net *net, struct tc_action *actions[], + int *acts_deleted, struct netlink_ext_ack *extack) { - struct tc_action *a, *tmp; u32 act_index; - int ret; + int ret, i; - list_for_each_entry_safe(a, tmp, actions, list) { + for (i = 0; i < TCA_ACT_MAX_PRIO && actions[i]; i++) { + struct tc_action *a = actions[i]; const struct tc_action_ops *ops = a->ops; /* Actions can be deleted concurrently so we must save their @@ -1165,23 +1171,26 @@ static int tcf_action_delete(struct net *net, struct list_head *actions, */ act_index = a->tcfa_index; - list_del(&a->list); if (tcf_action_put(a)) { /* last reference, action was deleted concurrently */ module_put(ops->owner); } else { /* now do the delete */ ret = ops->delete(net, act_index); - if (ret < 0) + if (ret < 0) { + *acts_deleted = i + 1; return ret; + } } } + *acts_deleted = i; return 0; } static int -tcf_del_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions, - u32 portid, size_t attr_size, struct netlink_ext_ack *extack) +tcf_del_notify(struct net *net, struct nlmsghdr *n, struct tc_action *actions[], + int *acts_deleted, u32 portid, size_t attr_size, + struct netlink_ext_ack *extack) { int ret; struct sk_buff *skb; @@ -1199,7 +1208,7 @@ tcf_del_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions, } /* now do the delete */ - ret = tcf_action_delete(net, actions, extack); + ret = tcf_action_delete(net, actions, acts_deleted, extack); if (ret < 0) { NL_SET_ERR_MSG(extack, "Failed to delete TC action"); kfree_skb(skb); @@ -1221,7 +1230,8 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, struct nlattr *tb[TCA_ACT_MAX_PRIO + 1]; struct tc_action *act; size_t attr_size = 0; - LIST_HEAD(actions); + struct tc_action *actions[TCA_ACT_MAX_PRIO + 1] = {}; + int acts_deleted = 0; ret = nla_parse_nested(tb, TCA_ACT_MAX_PRIO, nla, NULL, extack); if (ret < 0) @@ -1243,26 +1253,27 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, } act->order = i; attr_size += tcf_action_fill_size(act); - list_add_tail(&act->list, &actions); + actions[i - 1] = act; } attr_size = tcf_action_full_attrs_size(attr_size); if (event == RTM_GETACTION) - ret = tcf_get_notify(net, portid, n, &actions, event, extack); + ret = tcf_get_notify(net, portid, n, actions, event, extack); else { /* delete */ - ret = tcf_del_notify(net, n, &actions, portid, attr_size, extack); + ret = tcf_del_notify(net, n, actions, &acts_deleted, portid, + attr_size, extack); if (ret) goto err; return ret; } err: - tcf_action_put_lst(&actions); + tcf_action_put_many(&actions[acts_deleted]); return ret; } static int -tcf_add_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions, +tcf_add_notify(struct net *net, struct nlmsghdr *n, struct tc_action *actions[], u32 portid, size_t attr_size, struct netlink_ext_ack *extack) { struct sk_buff *skb; @@ -1293,15 +1304,15 @@ static int tcf_action_add(struct net *net, struct nlattr *nla, { size_t attr_size = 0; int ret = 0; - LIST_HEAD(actions); + struct tc_action *actions[TCA_ACT_MAX_PRIO] = {}; - ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, &actions, + ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, actions, &attr_size, true, extack); - if (ret) + if (ret < 0) return ret; - ret = tcf_add_notify(net, n, &actions, portid, attr_size, extack); + ret = tcf_add_notify(net, n, actions, portid, attr_size, extack); if (ovr) - tcf_action_put_lst(&actions); + tcf_action_put_many(actions); return ret; } diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 9041f0e43e9a..73d9967c3739 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1609,10 +1609,7 @@ out: void tcf_exts_destroy(struct tcf_exts *exts) { #ifdef CONFIG_NET_CLS_ACT - LIST_HEAD(actions); - - tcf_exts_to_list(exts, &actions); - tcf_action_destroy(&actions, TCA_ACT_UNBIND); + tcf_action_destroy(exts->actions, TCA_ACT_UNBIND); kfree(exts->actions); exts->nr_actions = 0; #endif @@ -1639,18 +1636,15 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, exts->actions[0] = act; exts->nr_actions = 1; } else if (exts->action && tb[exts->action]) { - LIST_HEAD(actions); - int err, i = 0; + int err; err = tcf_action_init(net, tp, tb[exts->action], rate_tlv, NULL, ovr, TCA_ACT_BIND, - &actions, &attr_size, true, + exts->actions, &attr_size, true, extack); - if (err) + if (err < 0) return err; - list_for_each_entry(act, &actions, list) - exts->actions[i++] = act; - exts->nr_actions = i; + exts->nr_actions = err; } exts->net = net; } @@ -1699,14 +1693,11 @@ int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts) * tc data even if iproute2 was newer - jhs */ if (exts->type != TCA_OLD_COMPAT) { - LIST_HEAD(actions); - nest = nla_nest_start(skb, exts->action); if (nest == NULL) goto nla_put_failure; - tcf_exts_to_list(exts, &actions); - if (tcf_action_dump(skb, &actions, 0, 0) < 0) + if (tcf_action_dump(skb, exts->actions, 0, 0) < 0) goto nla_put_failure; nla_nest_end(skb, nest); } else if (exts->police) { -- cgit v1.2.3 From e3fe0ae129622b78e710e75ecbf7aca7af5dda47 Mon Sep 17 00:00:00 2001 From: Stephan Mueller Date: Wed, 27 Jun 2018 08:15:31 +0200 Subject: crypto: dh - add public key verification test According to SP800-56A section 5.6.2.1, the public key to be processed for the DH operation shall be checked for appropriateness. The check shall covers the full verification test in case the domain parameter Q is provided as defined in SP800-56A section 5.6.2.3.1. If Q is not provided, the partial check according to SP800-56A section 5.6.2.3.2 is performed. The full verification test requires the presence of the domain parameter Q. Thus, the patch adds the support to handle Q. It is permissible to not provide the Q value as part of the domain parameters. This implies that the interface is still backwards-compatible where so far only P and G are to be provided. However, if Q is provided, it is imported. Without the test, the NIST ACVP testing fails. After adding this check, the NIST ACVP testing passes. Testing without providing the Q domain parameter has been performed to verify the interface has not changed. Signed-off-by: Stephan Mueller Signed-off-by: Herbert Xu --- crypto/dh.c | 66 ++++++++++++++++++++++++++++++++++++++++++++++++++--- crypto/dh_helper.c | 15 +++++++++--- include/crypto/dh.h | 4 ++++ 3 files changed, 79 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/crypto/dh.c b/crypto/dh.c index 5659fe7f446d..8f79269db2b7 100644 --- a/crypto/dh.c +++ b/crypto/dh.c @@ -16,14 +16,16 @@ #include struct dh_ctx { - MPI p; - MPI g; - MPI xa; + MPI p; /* Value is guaranteed to be set. */ + MPI q; /* Value is optional. */ + MPI g; /* Value is guaranteed to be set. */ + MPI xa; /* Value is guaranteed to be set. */ }; static void dh_clear_ctx(struct dh_ctx *ctx) { mpi_free(ctx->p); + mpi_free(ctx->q); mpi_free(ctx->g); mpi_free(ctx->xa); memset(ctx, 0, sizeof(*ctx)); @@ -60,6 +62,12 @@ static int dh_set_params(struct dh_ctx *ctx, struct dh *params) if (!ctx->p) return -EINVAL; + if (params->q && params->q_size) { + ctx->q = mpi_read_raw_data(params->q, params->q_size); + if (!ctx->q) + return -EINVAL; + } + ctx->g = mpi_read_raw_data(params->g, params->g_size); if (!ctx->g) return -EINVAL; @@ -93,6 +101,55 @@ err_clear_ctx: return -EINVAL; } +/* + * SP800-56A public key verification: + * + * * If Q is provided as part of the domain paramenters, a full validation + * according to SP800-56A section 5.6.2.3.1 is performed. + * + * * If Q is not provided, a partial validation according to SP800-56A section + * 5.6.2.3.2 is performed. + */ +static int dh_is_pubkey_valid(struct dh_ctx *ctx, MPI y) +{ + if (unlikely(!ctx->p)) + return -EINVAL; + + /* + * Step 1: Verify that 2 <= y <= p - 2. + * + * The upper limit check is actually y < p instead of y < p - 1 + * as the mpi_sub_ui function is yet missing. + */ + if (mpi_cmp_ui(y, 1) < 1 || mpi_cmp(y, ctx->p) >= 0) + return -EINVAL; + + /* Step 2: Verify that 1 = y^q mod p */ + if (ctx->q) { + MPI val = mpi_alloc(0); + int ret; + + if (!val) + return -ENOMEM; + + ret = mpi_powm(val, y, ctx->q, ctx->p); + + if (ret) { + mpi_free(val); + return ret; + } + + ret = mpi_cmp_ui(val, 1); + + mpi_free(val); + + if (ret != 0) + return -EINVAL; + } + + return 0; +} + static int dh_compute_value(struct kpp_request *req) { struct crypto_kpp *tfm = crypto_kpp_reqtfm(req); @@ -115,6 +172,9 @@ static int dh_compute_value(struct kpp_request *req) ret = -EINVAL; goto err_free_val; } + ret = dh_is_pubkey_valid(ctx, base); + if (ret) + goto err_free_val; } else { base = ctx->g; } diff --git a/crypto/dh_helper.c b/crypto/dh_helper.c index 24fdb2ecaa85..a7de3d9ce5ac 100644 --- a/crypto/dh_helper.c +++ b/crypto/dh_helper.c @@ -30,7 +30,7 @@ static inline const u8 *dh_unpack_data(void *dst, const void *src, size_t size) static inline unsigned int dh_data_size(const struct dh *p) { - return p->key_size + p->p_size + p->g_size; + return p->key_size + p->p_size + p->q_size + p->g_size; } unsigned int crypto_dh_key_len(const struct dh *p) @@ -56,9 +56,11 @@ int crypto_dh_encode_key(char *buf, unsigned int len, const struct dh *params) ptr = dh_pack_data(ptr, &secret, sizeof(secret)); ptr = dh_pack_data(ptr, ¶ms->key_size, sizeof(params->key_size)); ptr = dh_pack_data(ptr, ¶ms->p_size, sizeof(params->p_size)); + ptr = dh_pack_data(ptr, ¶ms->q_size, sizeof(params->q_size)); ptr = dh_pack_data(ptr, ¶ms->g_size, sizeof(params->g_size)); ptr = dh_pack_data(ptr, params->key, params->key_size); ptr = dh_pack_data(ptr, params->p, params->p_size); + ptr = dh_pack_data(ptr, params->q, params->q_size); dh_pack_data(ptr, params->g, params->g_size); return 0; @@ -79,6 +81,7 @@ int crypto_dh_decode_key(const char *buf, unsigned int len, struct dh *params) ptr = dh_unpack_data(¶ms->key_size, ptr, sizeof(params->key_size)); ptr = dh_unpack_data(¶ms->p_size, ptr, sizeof(params->p_size)); + ptr = dh_unpack_data(¶ms->q_size, ptr, sizeof(params->q_size)); ptr = dh_unpack_data(¶ms->g_size, ptr, sizeof(params->g_size)); if (secret.len != crypto_dh_key_len(params)) return -EINVAL; @@ -88,7 +91,7 @@ int crypto_dh_decode_key(const char *buf, unsigned int len, struct dh *params) * some drivers assume otherwise. */ if (params->key_size > params->p_size || - params->g_size > params->p_size) + params->g_size > params->p_size || params->q_size > params->p_size) return -EINVAL; /* Don't allocate memory. Set pointers to data within @@ -96,7 +99,9 @@ int crypto_dh_decode_key(const char *buf, unsigned int len, struct dh *params) */ params->key = (void *)ptr; params->p = (void *)(ptr + params->key_size); - params->g = (void *)(ptr + params->key_size + params->p_size); + params->q = (void *)(ptr + params->key_size + params->p_size); + params->g = (void *)(ptr + params->key_size + params->p_size + + params->q_size); /* * Don't permit 'p' to be 0. It's not a prime number, and it's subject @@ -106,6 +111,10 @@ int crypto_dh_decode_key(const char *buf, unsigned int len, struct dh *params) if (memchr_inv(params->p, 0, params->p_size) == NULL) return -EINVAL; + /* It is permissible to not provide Q. */ + if (params->q_size == 0) + params->q = NULL; + return 0; } EXPORT_SYMBOL_GPL(crypto_dh_decode_key); diff --git a/include/crypto/dh.h b/include/crypto/dh.h index 71e1bb24d79f..7e0dad94cb2b 100644 --- a/include/crypto/dh.h +++ b/include/crypto/dh.h @@ -29,17 +29,21 @@ * * @key: Private DH key * @p: Diffie-Hellman parameter P + * @q: Diffie-Hellman parameter Q * @g: Diffie-Hellman generator G * @key_size: Size of the private DH key * @p_size: Size of DH parameter P + * @q_size: Size of DH parameter Q * @g_size: Size of DH generator G */ struct dh { void *key; void *p; + void *q; void *g; unsigned int key_size; unsigned int p_size; + unsigned int q_size; unsigned int g_size; }; -- cgit v1.2.3 From 69448867abcb231afaa7891ff9d9fd04b2b94a0d Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 5 Jul 2018 09:25:43 +0300 Subject: fs: shave 8 bytes off of struct inode Here is a link to Linus' reply to Jan's concern about making i_blkbibts byte addressable: https://marc.info/?l=linux-fsdevel&m=152882624707975&w=2 Here is a link to an lkp.org report about potential performance improvement in some workload, which could(?) be related to packing i_blkbits closer to i_bytes/i_lock: https://marc.info/?l=linux-fsdevel&m=153077048108198&w=2 Changes since v1: - Add links to relevant discussions Signed-off-by: Amir Goldstein Signed-off-by: Al Viro --- include/linux/fs.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index f140c11d35dd..9b00676f5d9d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -275,6 +275,7 @@ struct writeback_control; /* * Write life time hint values. + * Stored in struct inode as u8. */ enum rw_hint { WRITE_LIFE_NOT_SET = 0, @@ -609,8 +610,8 @@ struct inode { struct timespec64 i_ctime; spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */ unsigned short i_bytes; - unsigned int i_blkbits; - enum rw_hint i_write_hint; + u8 i_blkbits; + u8 i_write_hint; blkcnt_t i_blocks; #ifdef __NEED_I_SIZE_ORDERED -- cgit v1.2.3 From e74770fb6823c6fde49c3f2b38e3a2e68ae46682 Mon Sep 17 00:00:00 2001 From: Bob Moore Date: Fri, 29 Jun 2018 11:28:13 -0700 Subject: ACPICA: Update version to 20180629 Version 20180629. Signed-off-by: Bob Moore Signed-off-by: Erik Schmauss Signed-off-by: Rafael J. Wysocki --- include/acpi/acpixf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index 48d84f0d9547..88072c92ace2 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -12,7 +12,7 @@ /* Current ACPICA subsystem version in YYYYMMDD format */ -#define ACPI_CA_VERSION 0x20180531 +#define ACPI_CA_VERSION 0x20180629 #include #include -- cgit v1.2.3 From 5d6be70add65e3f236642ab0029e356261617cd0 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Fri, 29 Jun 2018 13:04:31 +0200 Subject: PM / Domains: Introduce option to attach a device by name to genpd For the multiple PM domain case, let's introduce a new function called genpd_dev_pm_attach_by_name(). This allows a device to be associated with its PM domain through genpd, by using a name based lookup. Note that, genpd_dev_pm_attach_by_name() shall only be called by the driver core / PM core, similar to how the existing dev_pm_domain_attach_by_id() makes use of genpd_dev_pm_attach_by_id(). However, this is implemented by following changes on top. Signed-off-by: Ulf Hansson Tested-by: Rajendra Nayak Reviewed-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/base/power/domain.c | 24 ++++++++++++++++++++++++ include/linux/pm_domain.h | 8 ++++++++ 2 files changed, 32 insertions(+) (limited to 'include') diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index 9e8484189034..79bdca70a81a 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -2374,6 +2374,30 @@ struct device *genpd_dev_pm_attach_by_id(struct device *dev, } EXPORT_SYMBOL_GPL(genpd_dev_pm_attach_by_id); +/** + * genpd_dev_pm_attach_by_name - Associate a device with one of its PM domains. + * @dev: The device used to lookup the PM domain. + * @name: The name of the PM domain. + * + * Parse device's OF node to find a PM domain specifier using the + * power-domain-names DT property. For further description see + * genpd_dev_pm_attach_by_id(). + */ +struct device *genpd_dev_pm_attach_by_name(struct device *dev, char *name) +{ + int index; + + if (!dev->of_node) + return NULL; + + index = of_property_match_string(dev->of_node, "power-domain-names", + name); + if (index < 0) + return NULL; + + return genpd_dev_pm_attach_by_id(dev, index); +} + static const struct of_device_id idle_state_match[] = { { .compatible = "domain-idle-state", }, { } diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index cb8d84090cfb..03e14a38462d 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -239,6 +239,8 @@ unsigned int of_genpd_opp_to_performance_state(struct device *dev, int genpd_dev_pm_attach(struct device *dev); struct device *genpd_dev_pm_attach_by_id(struct device *dev, unsigned int index); +struct device *genpd_dev_pm_attach_by_name(struct device *dev, + char *name); #else /* !CONFIG_PM_GENERIC_DOMAINS_OF */ static inline int of_genpd_add_provider_simple(struct device_node *np, struct generic_pm_domain *genpd) @@ -290,6 +292,12 @@ static inline struct device *genpd_dev_pm_attach_by_id(struct device *dev, return NULL; } +static inline struct device *genpd_dev_pm_attach_by_name(struct device *dev, + char *name) +{ + return NULL; +} + static inline struct generic_pm_domain *of_genpd_remove_last(struct device_node *np) { -- cgit v1.2.3 From 27dceb81f445c58b1d10d27d26eaf4ac2e9e0b00 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Fri, 29 Jun 2018 13:04:32 +0200 Subject: PM / Domains: Introduce dev_pm_domain_attach_by_name() For the multiple PM domain case, let's introduce a new API called dev_pm_domain_attach_by_name(). This allows a consumer driver to associate its device with one of its PM domains, by using a name based lookup. Do note that, currently it's only genpd that supports multiple PM domains per device, but dev_pm_domain_attach_by_name() can easily by extended to cover other PM domain types, if/when needed. Signed-off-by: Ulf Hansson Tested-by: Rajendra Nayak Reviewed-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/base/power/common.c | 17 +++++++++++++++++ include/linux/pm_domain.h | 7 +++++++ 2 files changed, 24 insertions(+) (limited to 'include') diff --git a/drivers/base/power/common.c b/drivers/base/power/common.c index df41b4780b3b..b413951c6abc 100644 --- a/drivers/base/power/common.c +++ b/drivers/base/power/common.c @@ -152,6 +152,23 @@ struct device *dev_pm_domain_attach_by_id(struct device *dev, } EXPORT_SYMBOL_GPL(dev_pm_domain_attach_by_id); +/** + * dev_pm_domain_attach_by_name - Associate a device with one of its PM domains. + * @dev: The device used to lookup the PM domain. + * @name: The name of the PM domain. + * + * For a detailed function description, see dev_pm_domain_attach_by_id(). + */ +struct device *dev_pm_domain_attach_by_name(struct device *dev, + char *name) +{ + if (dev->pm_domain) + return ERR_PTR(-EEXIST); + + return genpd_dev_pm_attach_by_name(dev, name); +} +EXPORT_SYMBOL_GPL(dev_pm_domain_attach_by_name); + /** * dev_pm_domain_detach - Detach a device from its PM domain. * @dev: Device to detach. diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 03e14a38462d..776c546d581a 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -309,6 +309,8 @@ struct generic_pm_domain *of_genpd_remove_last(struct device_node *np) int dev_pm_domain_attach(struct device *dev, bool power_on); struct device *dev_pm_domain_attach_by_id(struct device *dev, unsigned int index); +struct device *dev_pm_domain_attach_by_name(struct device *dev, + char *name); void dev_pm_domain_detach(struct device *dev, bool power_off); void dev_pm_domain_set(struct device *dev, struct dev_pm_domain *pd); #else @@ -321,6 +323,11 @@ static inline struct device *dev_pm_domain_attach_by_id(struct device *dev, { return NULL; } +static inline struct device *dev_pm_domain_attach_by_name(struct device *dev, + char *name) +{ + return NULL; +} static inline void dev_pm_domain_detach(struct device *dev, bool power_off) {} static inline void dev_pm_domain_set(struct device *dev, struct dev_pm_domain *pd) {} -- cgit v1.2.3 From e88728f46cfbb59cc7e7acf1d230c05ec093764e Mon Sep 17 00:00:00 2001 From: Vivek Gautam Date: Wed, 27 Jun 2018 18:20:55 +0530 Subject: driver core: Rename flag AUTOREMOVE to AUTOREMOVE_CONSUMER Now that we want to add another flag to autoremove the device link on supplier unbind, it's fair to rename the existing flag from DL_FLAG_AUTOREMOVE to DL_FLAG_AUTOREMOVE_CONSUMER so that we can add similar flag for supplier later. And, while we are touching device.h, fix a doc build warning. Signed-off-by: Vivek Gautam Reviewed-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- Documentation/driver-api/device_link.rst | 8 ++++---- drivers/base/core.c | 15 ++++++++------- drivers/gpu/drm/tegra/dc.c | 2 +- drivers/gpu/ipu-v3/ipu-pre.c | 3 ++- drivers/gpu/ipu-v3/ipu-prg.c | 3 ++- drivers/soc/imx/gpc.c | 2 +- include/linux/device.h | 12 ++++++------ 7 files changed, 24 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/Documentation/driver-api/device_link.rst b/Documentation/driver-api/device_link.rst index 70e328e16aad..a005b904a264 100644 --- a/Documentation/driver-api/device_link.rst +++ b/Documentation/driver-api/device_link.rst @@ -81,10 +81,10 @@ integration is desired. Two other flags are specifically targeted at use cases where the device link is added from the consumer's ``->probe`` callback: ``DL_FLAG_RPM_ACTIVE`` can be specified to runtime resume the supplier upon addition of the -device link. ``DL_FLAG_AUTOREMOVE`` causes the device link to be automatically -purged when the consumer fails to probe or later unbinds. This obviates -the need to explicitly delete the link in the ``->remove`` callback or in -the error path of the ``->probe`` callback. +device link. ``DL_FLAG_AUTOREMOVE_CONSUMER`` causes the device link to be +automatically purged when the consumer fails to probe or later unbinds. +This obviates the need to explicitly delete the link in the ``->remove`` +callback or in the error path of the ``->probe`` callback. Limitations =========== diff --git a/drivers/base/core.c b/drivers/base/core.c index df3e1a44707a..14c1e3151e08 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -178,10 +178,10 @@ void device_pm_move_to_tail(struct device *dev) * of the link. If DL_FLAG_PM_RUNTIME is not set, DL_FLAG_RPM_ACTIVE will be * ignored. * - * If the DL_FLAG_AUTOREMOVE is set, the link will be removed automatically - * when the consumer device driver unbinds from it. The combination of both - * DL_FLAG_AUTOREMOVE and DL_FLAG_STATELESS set is invalid and will cause NULL - * to be returned. + * If the DL_FLAG_AUTOREMOVE_CONSUMER is set, the link will be removed + * automatically when the consumer device driver unbinds from it. + * The combination of both DL_FLAG_AUTOREMOVE_CONSUMER and DL_FLAG_STATELESS + * set is invalid and will cause NULL to be returned. * * A side effect of the link creation is re-ordering of dpm_list and the * devices_kset list by moving the consumer device and all devices depending @@ -198,7 +198,8 @@ struct device_link *device_link_add(struct device *consumer, struct device_link *link; if (!consumer || !supplier || - ((flags & DL_FLAG_STATELESS) && (flags & DL_FLAG_AUTOREMOVE))) + ((flags & DL_FLAG_STATELESS) && + (flags & DL_FLAG_AUTOREMOVE_CONSUMER))) return NULL; device_links_write_lock(); @@ -479,7 +480,7 @@ static void __device_links_no_driver(struct device *dev) if (link->flags & DL_FLAG_STATELESS) continue; - if (link->flags & DL_FLAG_AUTOREMOVE) + if (link->flags & DL_FLAG_AUTOREMOVE_CONSUMER) kref_put(&link->kref, __device_link_del); else if (link->status != DL_STATE_SUPPLIER_UNBIND) WRITE_ONCE(link->status, DL_STATE_AVAILABLE); @@ -515,7 +516,7 @@ void device_links_driver_cleanup(struct device *dev) if (link->flags & DL_FLAG_STATELESS) continue; - WARN_ON(link->flags & DL_FLAG_AUTOREMOVE); + WARN_ON(link->flags & DL_FLAG_AUTOREMOVE_CONSUMER); WARN_ON(link->status != DL_STATE_SUPPLIER_UNBIND); WRITE_ONCE(link->status, DL_STATE_DORMANT); } diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c index c3afe7b2237e..965088afcfad 100644 --- a/drivers/gpu/drm/tegra/dc.c +++ b/drivers/gpu/drm/tegra/dc.c @@ -2312,7 +2312,7 @@ static int tegra_dc_couple(struct tegra_dc *dc) * POWER_CONTROL registers during CRTC enabling. */ if (dc->soc->coupled_pm && dc->pipe == 1) { - u32 flags = DL_FLAG_PM_RUNTIME | DL_FLAG_AUTOREMOVE; + u32 flags = DL_FLAG_PM_RUNTIME | DL_FLAG_AUTOREMOVE_CONSUMER; struct device_link *link; struct device *partner; diff --git a/drivers/gpu/ipu-v3/ipu-pre.c b/drivers/gpu/ipu-v3/ipu-pre.c index 0f70e8847540..2f8db9d62551 100644 --- a/drivers/gpu/ipu-v3/ipu-pre.c +++ b/drivers/gpu/ipu-v3/ipu-pre.c @@ -128,7 +128,8 @@ ipu_pre_lookup_by_phandle(struct device *dev, const char *name, int index) list_for_each_entry(pre, &ipu_pre_list, list) { if (pre_node == pre->dev->of_node) { mutex_unlock(&ipu_pre_list_mutex); - device_link_add(dev, pre->dev, DL_FLAG_AUTOREMOVE); + device_link_add(dev, pre->dev, + DL_FLAG_AUTOREMOVE_CONSUMER); of_node_put(pre_node); return pre; } diff --git a/drivers/gpu/ipu-v3/ipu-prg.c b/drivers/gpu/ipu-v3/ipu-prg.c index 83f9dd934a5d..38a3a9764e49 100644 --- a/drivers/gpu/ipu-v3/ipu-prg.c +++ b/drivers/gpu/ipu-v3/ipu-prg.c @@ -100,7 +100,8 @@ ipu_prg_lookup_by_phandle(struct device *dev, const char *name, int ipu_id) list_for_each_entry(prg, &ipu_prg_list, list) { if (prg_node == prg->dev->of_node) { mutex_unlock(&ipu_prg_list_mutex); - device_link_add(dev, prg->dev, DL_FLAG_AUTOREMOVE); + device_link_add(dev, prg->dev, + DL_FLAG_AUTOREMOVE_CONSUMER); prg->id = ipu_id; of_node_put(prg_node); return prg; diff --git a/drivers/soc/imx/gpc.c b/drivers/soc/imx/gpc.c index 32f0748fd067..aa9e65bc965e 100644 --- a/drivers/soc/imx/gpc.c +++ b/drivers/soc/imx/gpc.c @@ -202,7 +202,7 @@ static int imx_pgc_power_domain_probe(struct platform_device *pdev) goto genpd_err; } - device_link_add(dev, dev->parent, DL_FLAG_AUTOREMOVE); + device_link_add(dev, dev->parent, DL_FLAG_AUTOREMOVE_CONSUMER); return 0; diff --git a/include/linux/device.h b/include/linux/device.h index 055a69dbcd18..3929805cdd59 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -90,7 +90,7 @@ extern void bus_remove_file(struct bus_type *, struct bus_attribute *); * @num_vf: Called to find out how many virtual functions a device on this * bus supports. * @dma_configure: Called to setup DMA configuration on a device on - this bus. + * this bus. * @pm: Power management operations of this bus, callback the specific * device driver's pm-ops. * @iommu_ops: IOMMU specific operations for this bus, used to attach IOMMU @@ -784,14 +784,14 @@ enum device_link_state { * Device link flags. * * STATELESS: The core won't track the presence of supplier/consumer drivers. - * AUTOREMOVE: Remove this link automatically on consumer driver unbind. + * AUTOREMOVE_CONSUMER: Remove the link automatically on consumer driver unbind. * PM_RUNTIME: If set, the runtime PM framework will use this link. * RPM_ACTIVE: Run pm_runtime_get_sync() on the supplier during link creation. */ -#define DL_FLAG_STATELESS BIT(0) -#define DL_FLAG_AUTOREMOVE BIT(1) -#define DL_FLAG_PM_RUNTIME BIT(2) -#define DL_FLAG_RPM_ACTIVE BIT(3) +#define DL_FLAG_STATELESS BIT(0) +#define DL_FLAG_AUTOREMOVE_CONSUMER BIT(1) +#define DL_FLAG_PM_RUNTIME BIT(2) +#define DL_FLAG_RPM_ACTIVE BIT(3) /** * struct device_link - Device link representation. -- cgit v1.2.3 From 1689cac5b32a6db6f812e8063ea418a7cf023d03 Mon Sep 17 00:00:00 2001 From: Vivek Gautam Date: Wed, 27 Jun 2018 18:20:56 +0530 Subject: driver core: Add flag to autoremove device link on supplier unbind Add a flag to autoremove the device links on supplier driver unbind. This obviates the need to explicitly delete the link in the remove path. We remove these links only when the supplier's link to its consumers has gone to DL_STATE_SUPPLIER_UNBIND state. Signed-off-by: Vivek Gautam Suggested-by: Lukas Wunner Reviewed-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- Documentation/driver-api/device_link.rst | 4 ++++ drivers/base/core.c | 10 ++++++++++ include/linux/device.h | 2 ++ 3 files changed, 16 insertions(+) (limited to 'include') diff --git a/Documentation/driver-api/device_link.rst b/Documentation/driver-api/device_link.rst index a005b904a264..d6763272e747 100644 --- a/Documentation/driver-api/device_link.rst +++ b/Documentation/driver-api/device_link.rst @@ -86,6 +86,10 @@ automatically purged when the consumer fails to probe or later unbinds. This obviates the need to explicitly delete the link in the ``->remove`` callback or in the error path of the ``->probe`` callback. +Similarly, when the device link is added from supplier's ``->probe`` callback, +``DL_FLAG_AUTOREMOVE_SUPPLIER`` causes the device link to be automatically +purged when the supplier fails to probe or later unbinds. + Limitations =========== diff --git a/drivers/base/core.c b/drivers/base/core.c index 14c1e3151e08..e721218bf352 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -518,6 +518,16 @@ void device_links_driver_cleanup(struct device *dev) WARN_ON(link->flags & DL_FLAG_AUTOREMOVE_CONSUMER); WARN_ON(link->status != DL_STATE_SUPPLIER_UNBIND); + + /* + * autoremove the links between this @dev and its consumer + * devices that are not active, i.e. where the link state + * has moved to DL_STATE_SUPPLIER_UNBIND. + */ + if (link->status == DL_STATE_SUPPLIER_UNBIND && + link->flags & DL_FLAG_AUTOREMOVE_SUPPLIER) + kref_put(&link->kref, __device_link_del); + WRITE_ONCE(link->status, DL_STATE_DORMANT); } diff --git a/include/linux/device.h b/include/linux/device.h index 3929805cdd59..e80920452b49 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -787,11 +787,13 @@ enum device_link_state { * AUTOREMOVE_CONSUMER: Remove the link automatically on consumer driver unbind. * PM_RUNTIME: If set, the runtime PM framework will use this link. * RPM_ACTIVE: Run pm_runtime_get_sync() on the supplier during link creation. + * AUTOREMOVE_SUPPLIER: Remove the link automatically on supplier driver unbind. */ #define DL_FLAG_STATELESS BIT(0) #define DL_FLAG_AUTOREMOVE_CONSUMER BIT(1) #define DL_FLAG_PM_RUNTIME BIT(2) #define DL_FLAG_RPM_ACTIVE BIT(3) +#define DL_FLAG_AUTOREMOVE_SUPPLIER BIT(4) /** * struct device_link - Device link representation. -- cgit v1.2.3 From 63f3fb8d7ccb813e0a1f2ceedb9a3ebe2685b620 Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Mon, 2 Jul 2018 15:59:37 -0700 Subject: pinctrl: Document pin_config_group_get() return codes like pin_config_get() The pinconf_generic_dump_one() function makes the assumption that pin_config_group_get() should return -EINVAL and -ENOTSUPP just like pin_config_get() does. Document that so it's more obvious. Signed-off-by: Douglas Anderson Signed-off-by: Linus Walleij --- include/linux/pinctrl/pinconf.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/pinctrl/pinconf.h b/include/linux/pinctrl/pinconf.h index 09eb80f2574a..8dd85d302b90 100644 --- a/include/linux/pinctrl/pinconf.h +++ b/include/linux/pinctrl/pinconf.h @@ -28,7 +28,8 @@ struct seq_file; * is not available on this controller this should return -ENOTSUPP * and if it is available but disabled it should return -EINVAL * @pin_config_set: configure an individual pin - * @pin_config_group_get: get configurations for an entire pin group + * @pin_config_group_get: get configurations for an entire pin group; should + * return -ENOTSUPP and -EINVAL using the same rules as pin_config_get. * @pin_config_group_set: configure all pins in a group * @pin_config_dbg_parse_modify: optional debugfs to modify a pin configuration * @pin_config_dbg_show: optional debugfs display hook that will provide -- cgit v1.2.3 From de3c1e71d412d7e254e3eebeb82e260fb8513566 Mon Sep 17 00:00:00 2001 From: Jerome Brunet Date: Wed, 4 Jul 2018 18:54:57 +0200 Subject: clk: meson: expose GEN_CLK clkid Expose GEN_CLK clock id Signed-off-by: Jerome Brunet --- include/dt-bindings/clock/axg-clkc.h | 1 + include/dt-bindings/clock/gxbb-clkc.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/clock/axg-clkc.h b/include/dt-bindings/clock/axg-clkc.h index 70371228b7e0..fd1f938c38d1 100644 --- a/include/dt-bindings/clock/axg-clkc.h +++ b/include/dt-bindings/clock/axg-clkc.h @@ -71,5 +71,6 @@ #define CLKID_PCIE_CML_EN0 79 #define CLKID_PCIE_CML_EN1 80 #define CLKID_MIPI_ENABLE 81 +#define CLKID_GEN_CLK 84 #endif /* __AXG_CLKC_H */ diff --git a/include/dt-bindings/clock/gxbb-clkc.h b/include/dt-bindings/clock/gxbb-clkc.h index 7a892be90549..3979d48c025f 100644 --- a/include/dt-bindings/clock/gxbb-clkc.h +++ b/include/dt-bindings/clock/gxbb-clkc.h @@ -127,5 +127,6 @@ #define CLKID_VAPB 140 #define CLKID_VDEC_1 153 #define CLKID_VDEC_HEVC 156 +#define CLKID_GEN_CLK 159 #endif /* __GXBB_CLKC_H */ -- cgit v1.2.3 From 03fc7f9c99c1e7ae2925d459e8487f1a6f199f79 Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Wed, 27 Jun 2018 16:20:28 +0200 Subject: printk/nmi: Prevent deadlock when accessing the main log buffer in NMI The commit 719f6a7040f1bdaf96 ("printk: Use the main logbuf in NMI when logbuf_lock is available") brought back the possible deadlocks in printk() and NMI. The check of logbuf_lock is done only in printk_nmi_enter() to prevent mixed output. But another CPU might take the lock later, enter NMI, and: + Both NMIs might be serialized by yet another lock, for example, the one in nmi_cpu_backtrace(). + The other CPU might get stopped in NMI, see smp_send_stop() in panic(). The only safe solution is to use trylock when storing the message into the main log-buffer. It might cause reordering when some lines go to the main lock buffer directly and others are delayed via the per-CPU buffer. It means that it is not useful in general. This patch replaces the problematic NMI deferred context with NMI direct context. It can be used to mark a code that might produce many messages in NMI and the risk of losing them is more critical than problems with eventual reordering. The context is then used when dumping trace buffers on oops. It was the primary motivation for the original fix. Also the reordering is even smaller issue there because some traces have their own time stamps. Finally, nmi_cpu_backtrace() need not longer be serialized because it will always us the per-CPU buffers again. Fixes: 719f6a7040f1bdaf96 ("printk: Use the main logbuf in NMI when logbuf_lock is available") Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/20180627142028.11259-1-pmladek@suse.com To: Steven Rostedt Cc: Peter Zijlstra Cc: Tetsuo Handa Cc: Sergey Senozhatsky Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org Acked-by: Sergey Senozhatsky Signed-off-by: Petr Mladek --- include/linux/printk.h | 4 ++++ kernel/printk/internal.h | 9 ++++++- kernel/printk/printk_safe.c | 58 +++++++++++++++++++++++++++++---------------- kernel/trace/trace.c | 4 +++- lib/nmi_backtrace.c | 3 --- 5 files changed, 52 insertions(+), 26 deletions(-) (limited to 'include') diff --git a/include/linux/printk.h b/include/linux/printk.h index 6d7e800affd8..3ede9f46a494 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -148,9 +148,13 @@ void early_printk(const char *s, ...) { } #ifdef CONFIG_PRINTK_NMI extern void printk_nmi_enter(void); extern void printk_nmi_exit(void); +extern void printk_nmi_direct_enter(void); +extern void printk_nmi_direct_exit(void); #else static inline void printk_nmi_enter(void) { } static inline void printk_nmi_exit(void) { } +static inline void printk_nmi_direct_enter(void) { } +static inline void printk_nmi_direct_exit(void) { } #endif /* PRINTK_NMI */ #ifdef CONFIG_PRINTK diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h index 2a7d04049af4..0f1898820cba 100644 --- a/kernel/printk/internal.h +++ b/kernel/printk/internal.h @@ -19,11 +19,16 @@ #ifdef CONFIG_PRINTK #define PRINTK_SAFE_CONTEXT_MASK 0x3fffffff -#define PRINTK_NMI_DEFERRED_CONTEXT_MASK 0x40000000 +#define PRINTK_NMI_DIRECT_CONTEXT_MASK 0x40000000 #define PRINTK_NMI_CONTEXT_MASK 0x80000000 extern raw_spinlock_t logbuf_lock; +__printf(5, 0) +int vprintk_store(int facility, int level, + const char *dict, size_t dictlen, + const char *fmt, va_list args); + __printf(1, 0) int vprintk_default(const char *fmt, va_list args); __printf(1, 0) int vprintk_deferred(const char *fmt, va_list args); __printf(1, 0) int vprintk_func(const char *fmt, va_list args); @@ -54,6 +59,8 @@ void __printk_safe_exit(void); local_irq_enable(); \ } while (0) +void defer_console_output(void); + #else __printf(1, 0) int vprintk_func(const char *fmt, va_list args) { return 0; } diff --git a/kernel/printk/printk_safe.c b/kernel/printk/printk_safe.c index d7d091309054..a0a74c533e4b 100644 --- a/kernel/printk/printk_safe.c +++ b/kernel/printk/printk_safe.c @@ -308,24 +308,33 @@ static __printf(1, 0) int vprintk_nmi(const char *fmt, va_list args) void printk_nmi_enter(void) { - /* - * The size of the extra per-CPU buffer is limited. Use it only when - * the main one is locked. If this CPU is not in the safe context, - * the lock must be taken on another CPU and we could wait for it. - */ - if ((this_cpu_read(printk_context) & PRINTK_SAFE_CONTEXT_MASK) && - raw_spin_is_locked(&logbuf_lock)) { - this_cpu_or(printk_context, PRINTK_NMI_CONTEXT_MASK); - } else { - this_cpu_or(printk_context, PRINTK_NMI_DEFERRED_CONTEXT_MASK); - } + this_cpu_or(printk_context, PRINTK_NMI_CONTEXT_MASK); } void printk_nmi_exit(void) { - this_cpu_and(printk_context, - ~(PRINTK_NMI_CONTEXT_MASK | - PRINTK_NMI_DEFERRED_CONTEXT_MASK)); + this_cpu_and(printk_context, ~PRINTK_NMI_CONTEXT_MASK); +} + +/* + * Marks a code that might produce many messages in NMI context + * and the risk of losing them is more critical than eventual + * reordering. + * + * It has effect only when called in NMI context. Then printk() + * will try to store the messages into the main logbuf directly + * and use the per-CPU buffers only as a fallback when the lock + * is not available. + */ +void printk_nmi_direct_enter(void) +{ + if (this_cpu_read(printk_context) & PRINTK_NMI_CONTEXT_MASK) + this_cpu_or(printk_context, PRINTK_NMI_DIRECT_CONTEXT_MASK); +} + +void printk_nmi_direct_exit(void) +{ + this_cpu_and(printk_context, ~PRINTK_NMI_DIRECT_CONTEXT_MASK); } #else @@ -363,6 +372,20 @@ void __printk_safe_exit(void) __printf(1, 0) int vprintk_func(const char *fmt, va_list args) { + /* + * Try to use the main logbuf even in NMI. But avoid calling console + * drivers that might have their own locks. + */ + if ((this_cpu_read(printk_context) & PRINTK_NMI_DIRECT_CONTEXT_MASK) && + raw_spin_trylock(&logbuf_lock)) { + int len; + + len = vprintk_store(0, LOGLEVEL_DEFAULT, NULL, 0, fmt, args); + raw_spin_unlock(&logbuf_lock); + defer_console_output(); + return len; + } + /* Use extra buffer in NMI when logbuf_lock is taken or in safe mode. */ if (this_cpu_read(printk_context) & PRINTK_NMI_CONTEXT_MASK) return vprintk_nmi(fmt, args); @@ -371,13 +394,6 @@ __printf(1, 0) int vprintk_func(const char *fmt, va_list args) if (this_cpu_read(printk_context) & PRINTK_SAFE_CONTEXT_MASK) return vprintk_safe(fmt, args); - /* - * Use the main logbuf when logbuf_lock is available in NMI. - * But avoid calling console drivers that might have their own locks. - */ - if (this_cpu_read(printk_context) & PRINTK_NMI_DEFERRED_CONTEXT_MASK) - return vprintk_deferred(fmt, args); - /* No obstacles. */ return vprintk_default(fmt, args); } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index bcd93031d042..f106ad12f72f 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -8265,6 +8265,7 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) tracing_off(); local_irq_save(flags); + printk_nmi_direct_enter(); /* Simulate the iterator */ trace_init_global_iter(&iter); @@ -8344,7 +8345,8 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) for_each_tracing_cpu(cpu) { atomic_dec(&per_cpu_ptr(iter.trace_buffer->data, cpu)->disabled); } - atomic_dec(&dump_running); + atomic_dec(&dump_running); + printk_nmi_direct_exit(); local_irq_restore(flags); } EXPORT_SYMBOL_GPL(ftrace_dump); diff --git a/lib/nmi_backtrace.c b/lib/nmi_backtrace.c index 61a6b5aab07e..15ca78e1c7d4 100644 --- a/lib/nmi_backtrace.c +++ b/lib/nmi_backtrace.c @@ -87,11 +87,9 @@ void nmi_trigger_cpumask_backtrace(const cpumask_t *mask, bool nmi_cpu_backtrace(struct pt_regs *regs) { - static arch_spinlock_t lock = __ARCH_SPIN_LOCK_UNLOCKED; int cpu = smp_processor_id(); if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) { - arch_spin_lock(&lock); if (regs && cpu_in_idle(instruction_pointer(regs))) { pr_warn("NMI backtrace for cpu %d skipped: idling at %pS\n", cpu, (void *)instruction_pointer(regs)); @@ -102,7 +100,6 @@ bool nmi_cpu_backtrace(struct pt_regs *regs) else dump_stack(); } - arch_spin_unlock(&lock); cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask)); return true; } -- cgit v1.2.3 From b3e7e7d2d668de0102264302a4d10dd9d4438a42 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Fri, 15 Jun 2018 14:55:18 -0700 Subject: include/uapi/linux/blkzoned.h: Remove a superfluous __packed directive Using the __packed directive for a structure that does not need it is wrong because it makes gcc generate suboptimal code on some architectures. Hence remove the __packed directive from the blk_zone_report structure definition. See also http://digitalvampire.org/blog/index.php/2006/07/31/why-you-shouldnt-use-__attribute__packed/. Signed-off-by: Bart Van Assche Reviewed-by: Damien Le Moal Cc: Matias Bjorling Cc: Christoph Hellwig Signed-off-by: Jens Axboe --- include/uapi/linux/blkzoned.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/blkzoned.h b/include/uapi/linux/blkzoned.h index e3c70fe6bf0f..ff5a5db8906a 100644 --- a/include/uapi/linux/blkzoned.h +++ b/include/uapi/linux/blkzoned.h @@ -117,7 +117,7 @@ struct blk_zone_report { __u32 nr_zones; __u8 reserved[4]; struct blk_zone zones[0]; -} __packed; +}; /** * struct blk_zone_range - BLKRESETZONE ioctl request -- cgit v1.2.3 From 6b1d83d274486615cc341e410467a98fd9c27c0a Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Fri, 15 Jun 2018 14:55:19 -0700 Subject: block: Remove bdev_nr_zones() Remove this function since it has no callers. This function was introduced in commit 6cc77e9cb080 ("block: introduce zoned block devices zone write locking"). Signed-off-by: Bart Van Assche Reviewed-by: Damien Le Moal Cc: Christoph Hellwig Cc: Matias Bjorling Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 79226ca8f80f..49a400afb146 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1639,15 +1639,6 @@ static inline unsigned int bdev_zone_sectors(struct block_device *bdev) return 0; } -static inline unsigned int bdev_nr_zones(struct block_device *bdev) -{ - struct request_queue *q = bdev_get_queue(bdev); - - if (q) - return blk_queue_nr_zones(q); - return 0; -} - static inline int queue_dma_alignment(struct request_queue *q) { return q ? q->dma_alignment : 511; -- cgit v1.2.3 From 7c8542b7982264226cf94102950343185869b584 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Fri, 15 Jun 2018 14:55:20 -0700 Subject: block: Inline blk_queue_nr_zones() Since the implementation of blk_queue_nr_zones() is trivial and since it only has a single caller, inline this function. Signed-off-by: Bart Van Assche Reviewed-by: Damien Le Moal Cc: Matias Bjorling Cc: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-mq-debugfs.c | 2 +- include/linux/blkdev.h | 5 ----- 2 files changed, 1 insertion(+), 6 deletions(-) (limited to 'include') diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 1c4532e92938..26e1f8e425a8 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -214,7 +214,7 @@ static int queue_zone_wlock_show(void *data, struct seq_file *m) if (!q->seq_zones_wlock) return 0; - for (i = 0; i < blk_queue_nr_zones(q); i++) + for (i = 0; i < q->nr_zones; i++) if (test_bit(i, q->seq_zones_wlock)) seq_printf(m, "%u\n", i); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 49a400afb146..905daa7c647e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -800,11 +800,6 @@ static inline unsigned int blk_queue_zone_sectors(struct request_queue *q) return blk_queue_is_zoned(q) ? q->limits.chunk_sectors : 0; } -static inline unsigned int blk_queue_nr_zones(struct request_queue *q) -{ - return q->nr_zones; -} - static inline unsigned int blk_queue_zone_no(struct request_queue *q, sector_t sector) { -- cgit v1.2.3 From 6a5ac9846508ad7d1d23881d9d5add35f2e6ae71 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Fri, 15 Jun 2018 14:55:21 -0700 Subject: block: Make struct request_queue smaller for CONFIG_BLK_DEV_ZONED=n Exclude zoned block device members from struct request_queue for CONFIG_BLK_DEV_ZONED == n. Avoid breaking the build by only building the code that uses these struct request_queue members if CONFIG_BLK_DEV_ZONED != n. Signed-off-by: Bart Van Assche Reviewed-by: Damien Le Moal Cc: Matias Bjorling Cc: Christoph Hellwig Signed-off-by: Jens Axboe --- block/Kconfig | 4 ++++ block/Makefile | 1 + block/blk-mq-debugfs-zoned.c | 24 ++++++++++++++++++++++++ block/blk-mq-debugfs.c | 15 --------------- block/blk-mq-debugfs.h | 9 +++++++++ include/linux/blkdev.h | 6 ++++++ 6 files changed, 44 insertions(+), 15 deletions(-) create mode 100644 block/blk-mq-debugfs-zoned.c (limited to 'include') diff --git a/block/Kconfig b/block/Kconfig index eb50fd4977c2..dfe7bc770fc9 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -177,6 +177,10 @@ config BLK_DEBUG_FS Unless you are building a kernel for a tiny system, you should say Y here. +config BLK_DEBUG_FS_ZONED + bool + default BLK_DEBUG_FS && BLK_DEV_ZONED + config BLK_SED_OPAL bool "Logic for interfacing with Opal enabled SEDs" ---help--- diff --git a/block/Makefile b/block/Makefile index 6a56303b9925..a8f94cdb75c3 100644 --- a/block/Makefile +++ b/block/Makefile @@ -34,4 +34,5 @@ obj-$(CONFIG_BLK_MQ_RDMA) += blk-mq-rdma.o obj-$(CONFIG_BLK_DEV_ZONED) += blk-zoned.o obj-$(CONFIG_BLK_WBT) += blk-wbt.o obj-$(CONFIG_BLK_DEBUG_FS) += blk-mq-debugfs.o +obj-$(CONFIG_BLK_DEBUG_FS_ZONED)+= blk-mq-debugfs-zoned.o obj-$(CONFIG_BLK_SED_OPAL) += sed-opal.o diff --git a/block/blk-mq-debugfs-zoned.c b/block/blk-mq-debugfs-zoned.c new file mode 100644 index 000000000000..fb2c82c351e4 --- /dev/null +++ b/block/blk-mq-debugfs-zoned.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2017 Western Digital Corporation or its affiliates. + * + * This file is released under the GPL. + */ + +#include +#include "blk-mq-debugfs.h" + +int queue_zone_wlock_show(void *data, struct seq_file *m) +{ + struct request_queue *q = data; + unsigned int i; + + if (!q->seq_zones_wlock) + return 0; + + for (i = 0; i < q->nr_zones; i++) + if (test_bit(i, q->seq_zones_wlock)) + seq_printf(m, "%u\n", i); + + return 0; +} diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 26e1f8e425a8..7efe268e4447 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -206,21 +206,6 @@ static ssize_t queue_write_hint_store(void *data, const char __user *buf, return count; } -static int queue_zone_wlock_show(void *data, struct seq_file *m) -{ - struct request_queue *q = data; - unsigned int i; - - if (!q->seq_zones_wlock) - return 0; - - for (i = 0; i < q->nr_zones; i++) - if (test_bit(i, q->seq_zones_wlock)) - seq_printf(m, "%u\n", i); - - return 0; -} - static const struct blk_mq_debugfs_attr blk_mq_debugfs_queue_attrs[] = { { "poll_stat", 0400, queue_poll_stat_show }, { "requeue_list", 0400, .seq_ops = &queue_requeue_list_seq_ops }, diff --git a/block/blk-mq-debugfs.h b/block/blk-mq-debugfs.h index b9d366e57097..a9160be12be0 100644 --- a/block/blk-mq-debugfs.h +++ b/block/blk-mq-debugfs.h @@ -80,4 +80,13 @@ static inline void blk_mq_debugfs_unregister_sched_hctx(struct blk_mq_hw_ctx *hc } #endif +#ifdef CONFIG_BLK_DEBUG_FS_ZONED +int queue_zone_wlock_show(void *data, struct seq_file *m); +#else +static inline int queue_zone_wlock_show(void *data, struct seq_file *m) +{ + return 0; +} +#endif + #endif diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 905daa7c647e..ca5a8b046894 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -592,6 +592,7 @@ struct request_queue { struct queue_limits limits; +#ifdef CONFIG_BLK_DEV_ZONED /* * Zoned block device information for request dispatch control. * nr_zones is the total number of zones of the device. This is always @@ -612,6 +613,7 @@ struct request_queue { unsigned int nr_zones; unsigned long *seq_zones_bitmap; unsigned long *seq_zones_wlock; +#endif /* CONFIG_BLK_DEV_ZONED */ /* * sg stuff @@ -800,6 +802,7 @@ static inline unsigned int blk_queue_zone_sectors(struct request_queue *q) return blk_queue_is_zoned(q) ? q->limits.chunk_sectors : 0; } +#ifdef CONFIG_BLK_DEV_ZONED static inline unsigned int blk_queue_zone_no(struct request_queue *q, sector_t sector) { @@ -815,6 +818,7 @@ static inline bool blk_queue_zone_is_seq(struct request_queue *q, return false; return test_bit(blk_queue_zone_no(q, sector), q->seq_zones_bitmap); } +#endif /* CONFIG_BLK_DEV_ZONED */ static inline bool rq_is_sync(struct request *rq) { @@ -1065,6 +1069,7 @@ static inline unsigned int blk_rq_cur_sectors(const struct request *rq) return blk_rq_cur_bytes(rq) >> SECTOR_SHIFT; } +#ifdef CONFIG_BLK_DEV_ZONED static inline unsigned int blk_rq_zone_no(struct request *rq) { return blk_queue_zone_no(rq->q, blk_rq_pos(rq)); @@ -1074,6 +1079,7 @@ static inline unsigned int blk_rq_zone_is_seq(struct request *rq) { return blk_queue_zone_is_seq(rq->q, blk_rq_pos(rq)); } +#endif /* CONFIG_BLK_DEV_ZONED */ /* * Some commands like WRITE SAME have a payload or data transfer size which -- cgit v1.2.3 From 5815839b3ca16bb1d45939270871169f6803a121 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Mon, 25 Jun 2018 19:31:47 +0800 Subject: blk-mq: introduce new lock for protecting hctx->dispatch_wait Now hctx->lock is only acquired when adding hctx->dispatch_wait to one wait queue, but not held when removing it from the wait queue. IO hang can be observed easily if SCHED RESTART is disabled, that means now RESTART exits just for fixing the issue in blk_mq_mark_tag_wait(). This patch fixes the issue by introducing hctx->dispatch_wait_lock and holding it for removing hctx->dispatch_wait in blk_mq_dispatch_wake(), since we need to avoid acquiring hctx->lock in irq context. Fixes: eb619fdb2d4cb8b3d3419 ("blk-mq: fix issue with shared tag queue re-running") Cc: Christoph Hellwig Cc: Omar Sandoval Cc: Bart Van Assche Tested-by: Andrew Jones Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- block/blk-mq.c | 26 +++++++++++++++++--------- include/linux/blk-mq.h | 1 + 2 files changed, 18 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/block/blk-mq.c b/block/blk-mq.c index 9eee896a3592..df84281f6af6 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -998,7 +998,10 @@ static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode, hctx = container_of(wait, struct blk_mq_hw_ctx, dispatch_wait); + spin_lock(&hctx->dispatch_wait_lock); list_del_init(&wait->entry); + spin_unlock(&hctx->dispatch_wait_lock); + blk_mq_run_hw_queue(hctx, true); return 1; } @@ -1012,7 +1015,7 @@ static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode, static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx, struct request *rq) { - struct sbq_wait_state *ws; + struct wait_queue_head *wq; wait_queue_entry_t *wait; bool ret; @@ -1035,14 +1038,18 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx, if (!list_empty_careful(&wait->entry)) return false; - spin_lock(&hctx->lock); + wq = &bt_wait_ptr(&hctx->tags->bitmap_tags, hctx)->wait; + + spin_lock_irq(&wq->lock); + spin_lock(&hctx->dispatch_wait_lock); if (!list_empty(&wait->entry)) { - spin_unlock(&hctx->lock); + spin_unlock(&hctx->dispatch_wait_lock); + spin_unlock_irq(&wq->lock); return false; } - ws = bt_wait_ptr(&hctx->tags->bitmap_tags, hctx); - add_wait_queue(&ws->wait, wait); + wait->flags &= ~WQ_FLAG_EXCLUSIVE; + __add_wait_queue(wq, wait); /* * It's possible that a tag was freed in the window between the @@ -1051,7 +1058,8 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx, */ ret = blk_mq_get_driver_tag(rq); if (!ret) { - spin_unlock(&hctx->lock); + spin_unlock(&hctx->dispatch_wait_lock); + spin_unlock_irq(&wq->lock); return false; } @@ -1059,10 +1067,9 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx, * We got a tag, remove ourselves from the wait queue to ensure * someone else gets the wakeup. */ - spin_lock_irq(&ws->wait.lock); list_del_init(&wait->entry); - spin_unlock_irq(&ws->wait.lock); - spin_unlock(&hctx->lock); + spin_unlock(&hctx->dispatch_wait_lock); + spin_unlock_irq(&wq->lock); return true; } @@ -2142,6 +2149,7 @@ static int blk_mq_init_hctx(struct request_queue *q, hctx->nr_ctx = 0; + spin_lock_init(&hctx->dispatch_wait_lock); init_waitqueue_func_entry(&hctx->dispatch_wait, blk_mq_dispatch_wake); INIT_LIST_HEAD(&hctx->dispatch_wait.entry); diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index e3147eb74222..ea690254dab7 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -39,6 +39,7 @@ struct blk_mq_hw_ctx { struct blk_mq_ctx **ctxs; unsigned int nr_ctx; + spinlock_t dispatch_wait_lock; wait_queue_entry_t dispatch_wait; atomic_t wait_index; -- cgit v1.2.3 From 97889f9ac24f8d2fc8e703ea7f80c162bab10d4d Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Mon, 25 Jun 2018 19:31:48 +0800 Subject: blk-mq: remove synchronize_rcu() from blk_mq_del_queue_tag_set() We have to remove synchronize_rcu() from blk_queue_cleanup(), otherwise long delay can be caused during lun probe. For removing it, we have to avoid to iterate the set->tag_list in IO path, eg, blk_mq_sched_restart(). This patch reverts 5b79413946d (Revert "blk-mq: don't handle TAG_SHARED in restart"). Given we have fixed enough IO hang issue, and there isn't any reason to restart all queues in one tags any more, see the following reasons: 1) blk-mq core can deal with shared-tags case well via blk_mq_get_driver_tag(), which can wake up queues waiting for driver tag. 2) SCSI is a bit special because it may return BLK_STS_RESOURCE if queue, target or host is ready, but SCSI built-in restart can cover all these well, see scsi_end_request(), queue will be rerun after any request initiated from this host/target is completed. In my test on scsi_debug(8 luns), this patch may improve IOPS by 20% ~ 30% when running I/O on these 8 luns concurrently. Fixes: 705cda97ee3a ("blk-mq: Make it safe to use RCU to iterate over blk_mq_tag_set.tag_list") Cc: Omar Sandoval Cc: Bart Van Assche Cc: Christoph Hellwig Cc: Martin K. Petersen Cc: linux-scsi@vger.kernel.org Reported-by: Andrew Jones Tested-by: Andrew Jones Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- block/blk-mq-sched.c | 85 +++----------------------------------------------- block/blk-mq.c | 10 ++---- include/linux/blkdev.h | 2 -- 3 files changed, 7 insertions(+), 90 deletions(-) (limited to 'include') diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index 56c493c6cd90..4e027f6108ae 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -59,29 +59,16 @@ static void blk_mq_sched_mark_restart_hctx(struct blk_mq_hw_ctx *hctx) if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state)) return; - if (hctx->flags & BLK_MQ_F_TAG_SHARED) { - struct request_queue *q = hctx->queue; - - if (!test_and_set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state)) - atomic_inc(&q->shared_hctx_restart); - } else - set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state); + set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state); } -static bool blk_mq_sched_restart_hctx(struct blk_mq_hw_ctx *hctx) +void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx) { if (!test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state)) - return false; - - if (hctx->flags & BLK_MQ_F_TAG_SHARED) { - struct request_queue *q = hctx->queue; - - if (test_and_clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state)) - atomic_dec(&q->shared_hctx_restart); - } else - clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state); + return; + clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state); - return blk_mq_run_hw_queue(hctx, true); + blk_mq_run_hw_queue(hctx, true); } /* @@ -380,68 +367,6 @@ static bool blk_mq_sched_bypass_insert(struct blk_mq_hw_ctx *hctx, return false; } -/** - * list_for_each_entry_rcu_rr - iterate in a round-robin fashion over rcu list - * @pos: loop cursor. - * @skip: the list element that will not be examined. Iteration starts at - * @skip->next. - * @head: head of the list to examine. This list must have at least one - * element, namely @skip. - * @member: name of the list_head structure within typeof(*pos). - */ -#define list_for_each_entry_rcu_rr(pos, skip, head, member) \ - for ((pos) = (skip); \ - (pos = (pos)->member.next != (head) ? list_entry_rcu( \ - (pos)->member.next, typeof(*pos), member) : \ - list_entry_rcu((pos)->member.next->next, typeof(*pos), member)), \ - (pos) != (skip); ) - -/* - * Called after a driver tag has been freed to check whether a hctx needs to - * be restarted. Restarts @hctx if its tag set is not shared. Restarts hardware - * queues in a round-robin fashion if the tag set of @hctx is shared with other - * hardware queues. - */ -void blk_mq_sched_restart(struct blk_mq_hw_ctx *const hctx) -{ - struct blk_mq_tags *const tags = hctx->tags; - struct blk_mq_tag_set *const set = hctx->queue->tag_set; - struct request_queue *const queue = hctx->queue, *q; - struct blk_mq_hw_ctx *hctx2; - unsigned int i, j; - - if (set->flags & BLK_MQ_F_TAG_SHARED) { - /* - * If this is 0, then we know that no hardware queues - * have RESTART marked. We're done. - */ - if (!atomic_read(&queue->shared_hctx_restart)) - return; - - rcu_read_lock(); - list_for_each_entry_rcu_rr(q, queue, &set->tag_list, - tag_set_list) { - queue_for_each_hw_ctx(q, hctx2, i) - if (hctx2->tags == tags && - blk_mq_sched_restart_hctx(hctx2)) - goto done; - } - j = hctx->queue_num + 1; - for (i = 0; i < queue->nr_hw_queues; i++, j++) { - if (j == queue->nr_hw_queues) - j = 0; - hctx2 = queue->queue_hw_ctx[j]; - if (hctx2->tags == tags && - blk_mq_sched_restart_hctx(hctx2)) - break; - } -done: - rcu_read_unlock(); - } else { - blk_mq_sched_restart_hctx(hctx); - } -} - void blk_mq_sched_insert_request(struct request *rq, bool at_head, bool run_queue, bool async) { diff --git a/block/blk-mq.c b/block/blk-mq.c index df84281f6af6..7c6ff13171ef 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2335,15 +2335,10 @@ static void queue_set_hctx_shared(struct request_queue *q, bool shared) int i; queue_for_each_hw_ctx(q, hctx, i) { - if (shared) { - if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state)) - atomic_inc(&q->shared_hctx_restart); + if (shared) hctx->flags |= BLK_MQ_F_TAG_SHARED; - } else { - if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state)) - atomic_dec(&q->shared_hctx_restart); + else hctx->flags &= ~BLK_MQ_F_TAG_SHARED; - } } } @@ -2374,7 +2369,6 @@ static void blk_mq_del_queue_tag_set(struct request_queue *q) blk_mq_update_tag_set_depth(set, false); } mutex_unlock(&set->tag_list_lock); - synchronize_rcu(); INIT_LIST_HEAD(&q->tag_set_list); } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index ca5a8b046894..9d05646d5059 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -442,8 +442,6 @@ struct request_queue { int nr_rqs[2]; /* # allocated [a]sync rqs */ int nr_rqs_elvpriv; /* # allocated rqs w/ elvpriv */ - atomic_t shared_hctx_restart; - struct blk_queue_stats *stats; struct rq_wb *rq_wb; -- cgit v1.2.3 From 6e768717304bdbe8d2897ca8298f6b58863fdc41 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Tue, 3 Jul 2018 09:03:16 -0600 Subject: blk-mq: dequeue request one by one from sw queue if hctx is busy It won't be efficient to dequeue request one by one from sw queue, but we have to do that when queue is busy for better merge performance. This patch takes the Exponential Weighted Moving Average(EWMA) to figure out if queue is busy, then only dequeue request one by one from sw queue when queue is busy. Fixes: b347689ffbca ("blk-mq-sched: improve dispatching from sw queue") Cc: Kashyap Desai Cc: Laurence Oberman Cc: Omar Sandoval Cc: Christoph Hellwig Cc: Bart Van Assche Cc: Hannes Reinecke Reported-by: Kashyap Desai Tested-by: Kashyap Desai Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- block/blk-mq-debugfs.c | 9 +++++++++ block/blk-mq-sched.c | 11 ++--------- block/blk-mq.c | 33 ++++++++++++++++++++++++++++++++- include/linux/blk-mq.h | 3 ++- 4 files changed, 45 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 7efe268e4447..cb1e6cf7ac48 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -622,6 +622,14 @@ static int hctx_active_show(void *data, struct seq_file *m) return 0; } +static int hctx_dispatch_busy_show(void *data, struct seq_file *m) +{ + struct blk_mq_hw_ctx *hctx = data; + + seq_printf(m, "%u\n", hctx->dispatch_busy); + return 0; +} + static void *ctx_rq_list_start(struct seq_file *m, loff_t *pos) __acquires(&ctx->lock) { @@ -783,6 +791,7 @@ static const struct blk_mq_debugfs_attr blk_mq_debugfs_hctx_attrs[] = { {"queued", 0600, hctx_queued_show, hctx_queued_write}, {"run", 0600, hctx_run_show, hctx_run_write}, {"active", 0400, hctx_active_show}, + {"dispatch_busy", 0400, hctx_dispatch_busy_show}, {}, }; diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index f3b4b5ceb4d1..fdc129e64cc4 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -206,15 +206,8 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx) } } else if (has_sched_dispatch) { blk_mq_do_dispatch_sched(hctx); - } else if (q->mq_ops->get_budget) { - /* - * If we need to get budget before queuing request, we - * dequeue request one by one from sw queue for avoiding - * to mess up I/O merge when dispatch runs out of resource. - * - * TODO: get more budgets, and dequeue more requests in - * one time. - */ + } else if (hctx->dispatch_busy) { + /* dequeue request one by one from sw queue if queue is busy */ blk_mq_do_dispatch_ctx(hctx); } else { blk_mq_flush_busy_ctxs(hctx, &rq_list); diff --git a/block/blk-mq.c b/block/blk-mq.c index 795ba859b16b..850fdd02c385 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1074,6 +1074,35 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx, return true; } +#define BLK_MQ_DISPATCH_BUSY_EWMA_WEIGHT 8 +#define BLK_MQ_DISPATCH_BUSY_EWMA_FACTOR 4 +/* + * Update dispatch busy with the Exponential Weighted Moving Average(EWMA): + * - EWMA is one simple way to compute running average value + * - weight(7/8 and 1/8) is applied so that it can decrease exponentially + * - take 4 as factor for avoiding to get too small(0) result, and this + * factor doesn't matter because EWMA decreases exponentially + */ +static void blk_mq_update_dispatch_busy(struct blk_mq_hw_ctx *hctx, bool busy) +{ + unsigned int ewma; + + if (hctx->queue->elevator) + return; + + ewma = hctx->dispatch_busy; + + if (!ewma && !busy) + return; + + ewma *= BLK_MQ_DISPATCH_BUSY_EWMA_WEIGHT - 1; + if (busy) + ewma += 1 << BLK_MQ_DISPATCH_BUSY_EWMA_FACTOR; + ewma /= BLK_MQ_DISPATCH_BUSY_EWMA_WEIGHT; + + hctx->dispatch_busy = ewma; +} + #define BLK_MQ_RESOURCE_DELAY 3 /* ms units */ /* @@ -1210,8 +1239,10 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list, else if (needs_restart && (ret == BLK_STS_RESOURCE)) blk_mq_delay_run_hw_queue(hctx, BLK_MQ_RESOURCE_DELAY); + blk_mq_update_dispatch_busy(hctx, true); return false; - } + } else + blk_mq_update_dispatch_busy(hctx, false); /* * If the host/device is unable to accept more work, inform the diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index ea690254dab7..d710e92874cc 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -35,9 +35,10 @@ struct blk_mq_hw_ctx { struct sbitmap ctx_map; struct blk_mq_ctx *dispatch_from; + unsigned int dispatch_busy; - struct blk_mq_ctx **ctxs; unsigned int nr_ctx; + struct blk_mq_ctx **ctxs; spinlock_t dispatch_wait_lock; wait_queue_entry_t dispatch_wait; -- cgit v1.2.3 From 08e18eab0c579ad84399c1899c11899734854eb2 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 3 Jul 2018 11:14:50 -0400 Subject: block: add bi_blkg to the bio for cgroups Currently io.low uses a bi_cg_private to stash its private data for the blkg, however other blkcg policies may want to use this as well. Since we can get the private data out of the blkg, move this to bi_blkg in the bio and make it generic, then we can use bio_associate_blkg() to attach the blkg to the bio. Theoretically we could simply replace the bi_css with this since we can get to all the same information from the blkg, however you have to lookup the blkg, so for example wbc_init_bio() would have to lookup and possibly allocate the blkg for the css it was trying to attach to the bio. This could be problematic and result in us either not attaching the css at all to the bio, or falling back to the root blkcg if we are unable to allocate the corresponding blkg. So for now do this, and in the future if possible we could just replace the bi_css with bi_blkg and update the helpers to do the correct translation. Signed-off-by: Josef Bacik Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- block/bio.c | 23 +++++++++++++++++++++++ block/blk-throttle.c | 21 +++++++-------------- include/linux/bio.h | 1 + include/linux/blk_types.h | 2 +- 4 files changed, 32 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/block/bio.c b/block/bio.c index 67eff5eddc49..044571538574 100644 --- a/block/bio.c +++ b/block/bio.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include "blk.h" @@ -2036,6 +2037,24 @@ int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css) } EXPORT_SYMBOL_GPL(bio_associate_blkcg); +/** + * bio_associate_blkg - associate a bio with the specified blkg + * @bio: target bio + * @blkg: the blkg to associate + * + * Associate @bio with the blkg specified by @blkg. This is the queue specific + * blkcg information associated with the @bio, a reference will be taken on the + * @blkg and will be freed when the bio is freed. + */ +int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg) +{ + if (unlikely(bio->bi_blkg)) + return -EBUSY; + blkg_get(blkg); + bio->bi_blkg = blkg; + return 0; +} + /** * bio_disassociate_task - undo bio_associate_current() * @bio: target bio @@ -2050,6 +2069,10 @@ void bio_disassociate_task(struct bio *bio) css_put(bio->bi_css); bio->bi_css = NULL; } + if (bio->bi_blkg) { + blkg_put(bio->bi_blkg); + bio->bi_blkg = NULL; + } } /** diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 63bb261811dd..caaabbe8a7a5 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -2134,12 +2134,8 @@ static inline void throtl_update_latency_buckets(struct throtl_data *td) static void blk_throtl_assoc_bio(struct throtl_grp *tg, struct bio *bio) { #ifdef CONFIG_BLK_DEV_THROTTLING_LOW - if (bio->bi_css) { - if (bio->bi_cg_private) - blkg_put(tg_to_blkg(bio->bi_cg_private)); - bio->bi_cg_private = tg; - blkg_get(tg_to_blkg(tg)); - } + if (bio->bi_css) + bio_associate_blkg(bio, tg_to_blkg(tg)); bio_issue_init(&bio->bi_issue, bio_sectors(bio)); #endif } @@ -2287,6 +2283,7 @@ void blk_throtl_stat_add(struct request *rq, u64 time_ns) void blk_throtl_bio_endio(struct bio *bio) { + struct blkcg_gq *blkg; struct throtl_grp *tg; u64 finish_time_ns; unsigned long finish_time; @@ -2294,20 +2291,18 @@ void blk_throtl_bio_endio(struct bio *bio) unsigned long lat; int rw = bio_data_dir(bio); - tg = bio->bi_cg_private; - if (!tg) + blkg = bio->bi_blkg; + if (!blkg) return; - bio->bi_cg_private = NULL; + tg = blkg_to_tg(blkg); finish_time_ns = ktime_get_ns(); tg->last_finish_time = finish_time_ns >> 10; start_time = bio_issue_time(&bio->bi_issue) >> 10; finish_time = __bio_issue_time(finish_time_ns) >> 10; - if (!start_time || finish_time <= start_time) { - blkg_put(tg_to_blkg(tg)); + if (!start_time || finish_time <= start_time) return; - } lat = finish_time - start_time; /* this is only for bio based driver */ @@ -2336,8 +2331,6 @@ void blk_throtl_bio_endio(struct bio *bio) tg->bio_cnt /= 2; tg->bad_bio_cnt /= 2; } - - blkg_put(tg_to_blkg(tg)); } #endif diff --git a/include/linux/bio.h b/include/linux/bio.h index f08f5fe7bd08..a279ba384da9 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -555,6 +555,7 @@ do { \ #ifdef CONFIG_BLK_CGROUP int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css); +int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg); void bio_disassociate_task(struct bio *bio); void bio_clone_blkcg_association(struct bio *dst, struct bio *src); #else /* CONFIG_BLK_CGROUP */ diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 3c4f390aea4b..3364d42ebe08 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -179,8 +179,8 @@ struct bio { */ struct io_context *bi_ioc; struct cgroup_subsys_state *bi_css; + struct blkcg_gq *bi_blkg; #ifdef CONFIG_BLK_DEV_THROTTLING_LOW - void *bi_cg_private; struct bio_issue bi_issue; #endif #endif -- cgit v1.2.3 From c7c98fd37653955d3a17dd4f1fa67aba070096a9 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 3 Jul 2018 11:14:51 -0400 Subject: block: introduce bio_issue_as_root_blkg Instead of forcing all file systems to get the right context on their bio's, simply check for REQ_META to see if we need to issue as the root blkg. We don't want to force all bio's to have the root blkg associated with them if REQ_META is set, as some controllers (blk-iolatency) need to know who the originating cgroup is so it can backcharge them for the work they are doing. This helper will make sure that the controllers do the proper thing wrt the IO priority and backcharging. Signed-off-by: Josef Bacik Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 6c666fd7de3c..69aa71dc0c04 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -238,6 +238,22 @@ static inline struct blkcg *bio_blkcg(struct bio *bio) return css_to_blkcg(task_css(current, io_cgrp_id)); } +/** + * bio_issue_as_root_blkg - see if this bio needs to be issued as root blkg + * @return: true if this bio needs to be submitted with the root blkg context. + * + * In order to avoid priority inversions we sometimes need to issue a bio as if + * it were attached to the root blkg, and then backcharge to the actual owning + * blkg. The idea is we do bio_blkcg() to look up the actual context for the + * bio and attach the appropriate blkg to the bio. Then we call this helper and + * if it is true run with the root blkg for that queue and then do any + * backcharging to the originating cgroup once the io is complete. + */ +static inline bool bio_issue_as_root_blkg(struct bio *bio) +{ + return (bio->bi_opf & REQ_META); +} + /** * blkcg_parent - get the parent of a blkcg * @blkcg: blkcg of interest -- cgit v1.2.3 From 903d23f0a354f226fa78f1c1c34b60aaf992e812 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 3 Jul 2018 11:14:52 -0400 Subject: blk-cgroup: allow controllers to output their own stats blk-iolatency has a few stats that it would like to print out, and instead of adding a bunch of crap to the generic code just provide a helper so that controllers can add stuff to the stat line if they want to. Hide it behind a boot option since it changes the output of io.stat from normal, and these stats are only interesting to developers. Signed-off-by: Josef Bacik Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- block/blk-cgroup.c | 47 +++++++++++++++++++++++++++++++++++++++++++--- include/linux/blk-cgroup.h | 3 +++ 2 files changed, 47 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index eb85cb87c40f..7dc6f05cc44b 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -50,6 +50,8 @@ static struct blkcg_policy *blkcg_policy[BLKCG_MAX_POLS]; static LIST_HEAD(all_blkcgs); /* protected by blkcg_pol_mutex */ +static bool blkcg_debug_stats = false; + static bool blkcg_policy_enabled(struct request_queue *q, const struct blkcg_policy *pol) { @@ -954,13 +956,25 @@ static int blkcg_print_stat(struct seq_file *sf, void *v) hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) { const char *dname; + char *buf; struct blkg_rwstat rwstat; u64 rbytes, wbytes, rios, wios; + size_t size = seq_get_buf(sf, &buf), off = 0; + int i; + bool has_stats = false; dname = blkg_dev_name(blkg); if (!dname) continue; + /* + * Hooray string manipulation, count is the size written NOT + * INCLUDING THE \0, so size is now count+1 less than what we + * had before, but we want to start writing the next bit from + * the \0 so we only add count to buf. + */ + off += scnprintf(buf+off, size-off, "%s ", dname); + spin_lock_irq(blkg->q->queue_lock); rwstat = blkg_rwstat_recursive_sum(blkg, NULL, @@ -975,9 +989,33 @@ static int blkcg_print_stat(struct seq_file *sf, void *v) spin_unlock_irq(blkg->q->queue_lock); - if (rbytes || wbytes || rios || wios) - seq_printf(sf, "%s rbytes=%llu wbytes=%llu rios=%llu wios=%llu\n", - dname, rbytes, wbytes, rios, wios); + if (rbytes || wbytes || rios || wios) { + has_stats = true; + off += scnprintf(buf+off, size-off, + "rbytes=%llu wbytes=%llu rios=%llu wios=%llu", + rbytes, wbytes, rios, wios); + } + + if (!blkcg_debug_stats) + goto next; + + for (i = 0; i < BLKCG_MAX_POLS; i++) { + struct blkcg_policy *pol = blkcg_policy[i]; + size_t written; + + if (!blkg->pd[i] || !pol->pd_stat_fn) + continue; + + written = pol->pd_stat_fn(blkg->pd[i], buf+off, size-off); + if (written) + has_stats = true; + off += written; + } +next: + if (has_stats) { + off += scnprintf(buf+off, size-off, "\n"); + seq_commit(sf, off); + } } rcu_read_unlock(); @@ -1547,3 +1585,6 @@ out_unlock: mutex_unlock(&blkcg_pol_register_mutex); } EXPORT_SYMBOL_GPL(blkcg_policy_unregister); + +module_param(blkcg_debug_stats, bool, 0644); +MODULE_PARM_DESC(blkcg_debug_stats, "True if you want debug stats, false if not"); diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 69aa71dc0c04..b41292726c0f 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -148,6 +148,8 @@ typedef void (blkcg_pol_online_pd_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_offline_pd_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_free_pd_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_reset_pd_stats_fn)(struct blkg_policy_data *pd); +typedef size_t (blkcg_pol_stat_pd_fn)(struct blkg_policy_data *pd, char *buf, + size_t size); struct blkcg_policy { int plid; @@ -167,6 +169,7 @@ struct blkcg_policy { blkcg_pol_offline_pd_fn *pd_offline_fn; blkcg_pol_free_pd_fn *pd_free_fn; blkcg_pol_reset_pd_stats_fn *pd_reset_stats_fn; + blkcg_pol_stat_pd_fn *pd_stat_fn; }; extern struct blkcg blkcg_root; -- cgit v1.2.3 From 0d1e0c7cd5909d6c6aa0957179318e13fcca971a Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 3 Jul 2018 11:14:53 -0400 Subject: blk: introduce REQ_SWAP Just like REQ_META, it's important to know the IO coming down is swap in order to guard against potential IO priority inversion issues with cgroups. Add REQ_SWAP and use it for all swap IO, and add it to our bio_issue_as_root_blkg helper. Signed-off-by: Josef Bacik Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 2 +- include/linux/blk_types.h | 3 ++- mm/page_io.c | 2 +- 3 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index b41292726c0f..a8f9ba8f33a4 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -254,7 +254,7 @@ static inline struct blkcg *bio_blkcg(struct bio *bio) */ static inline bool bio_issue_as_root_blkg(struct bio *bio) { - return (bio->bi_opf & REQ_META); + return (bio->bi_opf & (REQ_META | REQ_SWAP)) != 0; } /** diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 3364d42ebe08..0ffc34c5cc83 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -329,7 +329,7 @@ enum req_flag_bits { /* for driver use */ __REQ_DRV, - + __REQ_SWAP, /* swapping request. */ __REQ_NR_BITS, /* stops here */ }; @@ -351,6 +351,7 @@ enum req_flag_bits { #define REQ_NOUNMAP (1ULL << __REQ_NOUNMAP) #define REQ_DRV (1ULL << __REQ_DRV) +#define REQ_SWAP (1ULL << __REQ_SWAP) #define REQ_FAILFAST_MASK \ (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER) diff --git a/mm/page_io.c b/mm/page_io.c index b41cf9644585..a552cb37e220 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -338,7 +338,7 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc, ret = -ENOMEM; goto out; } - bio->bi_opf = REQ_OP_WRITE | wbc_to_write_flags(wbc); + bio->bi_opf = REQ_OP_WRITE | REQ_SWAP | wbc_to_write_flags(wbc); count_swpout_vm_event(page); set_page_writeback(page); unlock_page(page); -- cgit v1.2.3 From 0d3bd88d54f513723602b361dccfc71639f50779 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 3 Jul 2018 11:14:54 -0400 Subject: swap,blkcg: issue swap io with the appropriate context For backcharging we need to know who the page belongs to when swapping it out. We don't worry about things that do ->rw_page (zram etc) at the moment, we're only worried about pages that actually go to a block device. Signed-off-by: Tejun Heo Signed-off-by: Josef Bacik Acked-by: Johannes Weiner Acked-by: Andrew Morton Signed-off-by: Jens Axboe --- block/bio.c | 24 ++++++++++++++++++++++++ include/linux/bio.h | 7 +++++++ mm/page_io.c | 1 + 3 files changed, 32 insertions(+) (limited to 'include') diff --git a/block/bio.c b/block/bio.c index 044571538574..5f84f5c3887b 100644 --- a/block/bio.c +++ b/block/bio.c @@ -2015,6 +2015,30 @@ EXPORT_SYMBOL(bioset_init_from_src); #ifdef CONFIG_BLK_CGROUP +#ifdef CONFIG_MEMCG +/** + * bio_associate_blkcg_from_page - associate a bio with the page's blkcg + * @bio: target bio + * @page: the page to lookup the blkcg from + * + * Associate @bio with the blkcg from @page's owning memcg. This works like + * every other associate function wrt references. + */ +int bio_associate_blkcg_from_page(struct bio *bio, struct page *page) +{ + struct cgroup_subsys_state *blkcg_css; + + if (unlikely(bio->bi_css)) + return -EBUSY; + if (!page->mem_cgroup) + return 0; + blkcg_css = cgroup_get_e_css(page->mem_cgroup->css.cgroup, + &io_cgrp_subsys); + bio->bi_css = blkcg_css; + return 0; +} +#endif /* CONFIG_MEMCG */ + /** * bio_associate_blkcg - associate a bio with the specified blkcg * @bio: target bio diff --git a/include/linux/bio.h b/include/linux/bio.h index a279ba384da9..a00dfff51aa5 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -553,6 +553,13 @@ do { \ #define bio_dev(bio) \ disk_devt((bio)->bi_disk) +#if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) +int bio_associate_blkcg_from_page(struct bio *bio, struct page *page); +#else +static inline int bio_associate_blkcg_from_page(struct bio *bio, + struct page *page) { return 0; } +#endif + #ifdef CONFIG_BLK_CGROUP int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css); int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg); diff --git a/mm/page_io.c b/mm/page_io.c index a552cb37e220..aafd19ec1db4 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -339,6 +339,7 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc, goto out; } bio->bi_opf = REQ_OP_WRITE | REQ_SWAP | wbc_to_write_flags(wbc); + bio_associate_blkcg_from_page(bio, page); count_swpout_vm_event(page); set_page_writeback(page); unlock_page(page); -- cgit v1.2.3 From d09d8df3a29403693d9d20cc34ed101f2c558e2b Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 3 Jul 2018 11:14:55 -0400 Subject: blkcg: add generic throttling mechanism Since IO can be issued from literally anywhere it's almost impossible to do throttling without having some sort of adverse effect somewhere else in the system because of locking or other dependencies. The best way to solve this is to do the throttling when we know we aren't holding any other kernel resources. Do this by tracking throttling in a per-blkg basis, and if we require throttling flag the task that it needs to check before it returns to user space and possibly sleep there. This is to address the case where a process is doing work that is generating IO that can't be throttled, whether that is directly with a lot of REQ_META IO, or indirectly by allocating so much memory that it is swamping the disk with REQ_SWAP. We can't use task_add_work as we don't want to induce a memory allocation in the IO path, so simply saving the request queue in the task and flagging it to do the notify_resume thing achieves the same result without the overhead of a memory allocation. Signed-off-by: Josef Bacik Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- block/blk-cgroup.c | 220 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/blk-cgroup.h | 99 ++++++++++++++++++++ include/linux/cgroup-defs.h | 3 + include/linux/sched.h | 8 ++ include/linux/tracehook.h | 2 + 5 files changed, 332 insertions(+) (limited to 'include') diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 7dc6f05cc44b..d3310ec96c2a 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -27,6 +27,7 @@ #include #include #include +#include #include "blk.h" #define MAX_KEY_LEN 100 @@ -999,6 +1000,14 @@ static int blkcg_print_stat(struct seq_file *sf, void *v) if (!blkcg_debug_stats) goto next; + if (atomic_read(&blkg->use_delay)) { + has_stats = true; + off += scnprintf(buf+off, size-off, + " use_delay=%d delay_nsec=%llu", + atomic_read(&blkg->use_delay), + (unsigned long long)atomic64_read(&blkg->delay_nsec)); + } + for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; size_t written; @@ -1326,6 +1335,13 @@ static void blkcg_bind(struct cgroup_subsys_state *root_css) mutex_unlock(&blkcg_pol_mutex); } +static void blkcg_exit(struct task_struct *tsk) +{ + if (tsk->throttle_queue) + blk_put_queue(tsk->throttle_queue); + tsk->throttle_queue = NULL; +} + struct cgroup_subsys io_cgrp_subsys = { .css_alloc = blkcg_css_alloc, .css_offline = blkcg_css_offline, @@ -1335,6 +1351,7 @@ struct cgroup_subsys io_cgrp_subsys = { .dfl_cftypes = blkcg_files, .legacy_cftypes = blkcg_legacy_files, .legacy_name = "blkio", + .exit = blkcg_exit, #ifdef CONFIG_MEMCG /* * This ensures that, if available, memcg is automatically enabled @@ -1586,5 +1603,208 @@ out_unlock: } EXPORT_SYMBOL_GPL(blkcg_policy_unregister); +/* + * Scale the accumulated delay based on how long it has been since we updated + * the delay. We only call this when we are adding delay, in case it's been a + * while since we added delay, and when we are checking to see if we need to + * delay a task, to account for any delays that may have occurred. + */ +static void blkcg_scale_delay(struct blkcg_gq *blkg, u64 now) +{ + u64 old = atomic64_read(&blkg->delay_start); + + /* + * We only want to scale down every second. The idea here is that we + * want to delay people for min(delay_nsec, NSEC_PER_SEC) in a certain + * time window. We only want to throttle tasks for recent delay that + * has occurred, in 1 second time windows since that's the maximum + * things can be throttled. We save the current delay window in + * blkg->last_delay so we know what amount is still left to be charged + * to the blkg from this point onward. blkg->last_use keeps track of + * the use_delay counter. The idea is if we're unthrottling the blkg we + * are ok with whatever is happening now, and we can take away more of + * the accumulated delay as we've already throttled enough that + * everybody is happy with their IO latencies. + */ + if (time_before64(old + NSEC_PER_SEC, now) && + atomic64_cmpxchg(&blkg->delay_start, old, now) == old) { + u64 cur = atomic64_read(&blkg->delay_nsec); + u64 sub = min_t(u64, blkg->last_delay, now - old); + int cur_use = atomic_read(&blkg->use_delay); + + /* + * We've been unthrottled, subtract a larger chunk of our + * accumulated delay. + */ + if (cur_use < blkg->last_use) + sub = max_t(u64, sub, blkg->last_delay >> 1); + + /* + * This shouldn't happen, but handle it anyway. Our delay_nsec + * should only ever be growing except here where we subtract out + * min(last_delay, 1 second), but lord knows bugs happen and I'd + * rather not end up with negative numbers. + */ + if (unlikely(cur < sub)) { + atomic64_set(&blkg->delay_nsec, 0); + blkg->last_delay = 0; + } else { + atomic64_sub(sub, &blkg->delay_nsec); + blkg->last_delay = cur - sub; + } + blkg->last_use = cur_use; + } +} + +/* + * This is called when we want to actually walk up the hierarchy and check to + * see if we need to throttle, and then actually throttle if there is some + * accumulated delay. This should only be called upon return to user space so + * we're not holding some lock that would induce a priority inversion. + */ +static void blkcg_maybe_throttle_blkg(struct blkcg_gq *blkg, bool use_memdelay) +{ + u64 now = ktime_to_ns(ktime_get()); + u64 exp; + u64 delay_nsec = 0; + int tok; + + while (blkg->parent) { + if (atomic_read(&blkg->use_delay)) { + blkcg_scale_delay(blkg, now); + delay_nsec = max_t(u64, delay_nsec, + atomic64_read(&blkg->delay_nsec)); + } + blkg = blkg->parent; + } + + if (!delay_nsec) + return; + + /* + * Let's not sleep for all eternity if we've amassed a huge delay. + * Swapping or metadata IO can accumulate 10's of seconds worth of + * delay, and we want userspace to be able to do _something_ so cap the + * delays at 1 second. If there's 10's of seconds worth of delay then + * the tasks will be delayed for 1 second for every syscall. + */ + delay_nsec = min_t(u64, delay_nsec, 250 * NSEC_PER_MSEC); + + /* + * TODO: the use_memdelay flag is going to be for the upcoming psi stuff + * that hasn't landed upstream yet. Once that stuff is in place we need + * to do a psi_memstall_enter/leave if memdelay is set. + */ + + exp = ktime_add_ns(now, delay_nsec); + tok = io_schedule_prepare(); + do { + __set_current_state(TASK_KILLABLE); + if (!schedule_hrtimeout(&exp, HRTIMER_MODE_ABS)) + break; + } while (!fatal_signal_pending(current)); + io_schedule_finish(tok); +} + +/** + * blkcg_maybe_throttle_current - throttle the current task if it has been marked + * + * This is only called if we've been marked with set_notify_resume(). Obviously + * we can be set_notify_resume() for reasons other than blkcg throttling, so we + * check to see if current->throttle_queue is set and if not this doesn't do + * anything. This should only ever be called by the resume code, it's not meant + * to be called by people willy-nilly as it will actually do the work to + * throttle the task if it is setup for throttling. + */ +void blkcg_maybe_throttle_current(void) +{ + struct request_queue *q = current->throttle_queue; + struct cgroup_subsys_state *css; + struct blkcg *blkcg; + struct blkcg_gq *blkg; + bool use_memdelay = current->use_memdelay; + + if (!q) + return; + + current->throttle_queue = NULL; + current->use_memdelay = false; + + rcu_read_lock(); + css = kthread_blkcg(); + if (css) + blkcg = css_to_blkcg(css); + else + blkcg = css_to_blkcg(task_css(current, io_cgrp_id)); + + if (!blkcg) + goto out; + blkg = blkg_lookup(blkcg, q); + if (!blkg) + goto out; + blkg = blkg_try_get(blkg); + if (!blkg) + goto out; + rcu_read_unlock(); + blk_put_queue(q); + + blkcg_maybe_throttle_blkg(blkg, use_memdelay); + blkg_put(blkg); + return; +out: + rcu_read_unlock(); + blk_put_queue(q); +} +EXPORT_SYMBOL_GPL(blkcg_maybe_throttle_current); + +/** + * blkcg_schedule_throttle - this task needs to check for throttling + * @q - the request queue IO was submitted on + * @use_memdelay - do we charge this to memory delay for PSI + * + * This is called by the IO controller when we know there's delay accumulated + * for the blkg for this task. We do not pass the blkg because there are places + * we call this that may not have that information, the swapping code for + * instance will only have a request_queue at that point. This set's the + * notify_resume for the task to check and see if it requires throttling before + * returning to user space. + * + * We will only schedule once per syscall. You can call this over and over + * again and it will only do the check once upon return to user space, and only + * throttle once. If the task needs to be throttled again it'll need to be + * re-set at the next time we see the task. + */ +void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay) +{ + if (unlikely(current->flags & PF_KTHREAD)) + return; + + if (!blk_get_queue(q)) + return; + + if (current->throttle_queue) + blk_put_queue(current->throttle_queue); + current->throttle_queue = q; + if (use_memdelay) + current->use_memdelay = use_memdelay; + set_notify_resume(current); +} +EXPORT_SYMBOL_GPL(blkcg_schedule_throttle); + +/** + * blkcg_add_delay - add delay to this blkg + * @now - the current time in nanoseconds + * @delta - how many nanoseconds of delay to add + * + * Charge @delta to the blkg's current delay accumulation. This is used to + * throttle tasks if an IO controller thinks we need more throttling. + */ +void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta) +{ + blkcg_scale_delay(blkg, now); + atomic64_add(delta, &blkg->delay_nsec); +} +EXPORT_SYMBOL_GPL(blkcg_add_delay); + module_param(blkcg_debug_stats, bool, 0644); MODULE_PARM_DESC(blkcg_debug_stats, "True if you want debug stats, false if not"); diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index a8f9ba8f33a4..de57de4831d5 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -136,6 +136,12 @@ struct blkcg_gq { struct blkg_policy_data *pd[BLKCG_MAX_POLS]; struct rcu_head rcu_head; + + atomic_t use_delay; + atomic64_t delay_nsec; + atomic64_t delay_start; + u64 last_delay; + int last_use; }; typedef struct blkcg_policy_data *(blkcg_pol_alloc_cpd_fn)(gfp_t gfp); @@ -241,6 +247,26 @@ static inline struct blkcg *bio_blkcg(struct bio *bio) return css_to_blkcg(task_css(current, io_cgrp_id)); } +static inline bool blk_cgroup_congested(void) +{ + struct cgroup_subsys_state *css; + bool ret = false; + + rcu_read_lock(); + css = kthread_blkcg(); + if (!css) + css = task_css(current, io_cgrp_id); + while (css) { + if (atomic_read(&css->cgroup->congestion_count)) { + ret = true; + break; + } + css = css->parent; + } + rcu_read_unlock(); + return ret; +} + /** * bio_issue_as_root_blkg - see if this bio needs to be issued as root blkg * @return: true if this bio needs to be submitted with the root blkg context. @@ -374,6 +400,21 @@ static inline void blkg_get(struct blkcg_gq *blkg) atomic_inc(&blkg->refcnt); } +/** + * blkg_try_get - try and get a blkg reference + * @blkg: blkg to get + * + * This is for use when doing an RCU lookup of the blkg. We may be in the midst + * of freeing this blkg, so we can only use it if the refcnt is not zero. + */ +static inline struct blkcg_gq *blkg_try_get(struct blkcg_gq *blkg) +{ + if (atomic_inc_not_zero(&blkg->refcnt)) + return blkg; + return NULL; +} + + void __blkg_release_rcu(struct rcu_head *rcu); /** @@ -734,6 +775,59 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, return !throtl; } +static inline void blkcg_use_delay(struct blkcg_gq *blkg) +{ + if (atomic_add_return(1, &blkg->use_delay) == 1) + atomic_inc(&blkg->blkcg->css.cgroup->congestion_count); +} + +static inline int blkcg_unuse_delay(struct blkcg_gq *blkg) +{ + int old = atomic_read(&blkg->use_delay); + + if (old == 0) + return 0; + + /* + * We do this song and dance because we can race with somebody else + * adding or removing delay. If we just did an atomic_dec we'd end up + * negative and we'd already be in trouble. We need to subtract 1 and + * then check to see if we were the last delay so we can drop the + * congestion count on the cgroup. + */ + while (old) { + int cur = atomic_cmpxchg(&blkg->use_delay, old, old - 1); + if (cur == old) + break; + old = cur; + } + + if (old == 0) + return 0; + if (old == 1) + atomic_dec(&blkg->blkcg->css.cgroup->congestion_count); + return 1; +} + +static inline void blkcg_clear_delay(struct blkcg_gq *blkg) +{ + int old = atomic_read(&blkg->use_delay); + if (!old) + return; + /* We only want 1 person clearing the congestion count for this blkg. */ + while (old) { + int cur = atomic_cmpxchg(&blkg->use_delay, old, 0); + if (cur == old) { + atomic_dec(&blkg->blkcg->css.cgroup->congestion_count); + break; + } + old = cur; + } +} + +void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta); +void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay); +void blkcg_maybe_throttle_current(void); #else /* CONFIG_BLK_CGROUP */ struct blkcg { @@ -753,8 +847,13 @@ struct blkcg_policy { #define blkcg_root_css ((struct cgroup_subsys_state *)ERR_PTR(-EINVAL)) +static inline void blkcg_maybe_throttle_current(void) { } +static inline bool blk_cgroup_congested(void) { return false; } + #ifdef CONFIG_BLOCK +static inline void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay) { } + static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; } static inline int blkcg_init_queue(struct request_queue *q) { return 0; } static inline void blkcg_drain_queue(struct request_queue *q) { } diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index c0e68f903011..ff20b677fb9f 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -438,6 +438,9 @@ struct cgroup { /* used to store eBPF programs */ struct cgroup_bpf bpf; + /* If there is block congestion on this cgroup. */ + atomic_t congestion_count; + /* ids of the ancestors at each level including self */ int ancestor_ids[]; }; diff --git a/include/linux/sched.h b/include/linux/sched.h index 43731fe51c97..c2e993de67ec 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -734,6 +734,10 @@ struct task_struct { /* disallow userland-initiated cgroup migration */ unsigned no_cgroup_migration:1; #endif +#ifdef CONFIG_BLK_CGROUP + /* to be used once the psi infrastructure lands upstream. */ + unsigned use_memdelay:1; +#endif unsigned long atomic_flags; /* Flags requiring atomic access. */ @@ -1151,6 +1155,10 @@ struct task_struct { unsigned int memcg_nr_pages_over_high; #endif +#ifdef CONFIG_BLK_CGROUP + struct request_queue *throttle_queue; +#endif + #ifdef CONFIG_UPROBES struct uprobe_task *utask; #endif diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 4a8841963c2e..05589a3e37f4 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -51,6 +51,7 @@ #include #include #include +#include struct linux_binprm; /* @@ -192,6 +193,7 @@ static inline void tracehook_notify_resume(struct pt_regs *regs) task_work_run(); mem_cgroup_handle_over_high(); + blkcg_maybe_throttle_current(); } #endif /* */ -- cgit v1.2.3 From 2cf855837b89d92996cf264713f3bed2bf9b0b4f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 3 Jul 2018 11:14:56 -0400 Subject: memcontrol: schedule throttling if we are congested Memory allocations can induce swapping via kswapd or direct reclaim. If we are having IO done for us by kswapd and don't actually go into direct reclaim we may never get scheduled for throttling. So instead check to see if our cgroup is congested, and if so schedule the throttling. Before we return to user space the throttling stuff will only throttle if we actually required it. Signed-off-by: Tejun Heo Signed-off-by: Josef Bacik Acked-by: Johannes Weiner Acked-by: Andrew Morton Signed-off-by: Jens Axboe --- include/linux/memcontrol.h | 13 +++++++++++++ include/linux/swap.h | 11 ++++++++++- mm/huge_memory.c | 6 +++--- mm/memcontrol.c | 13 +++++++++++++ mm/memory.c | 11 ++++++----- mm/shmem.c | 10 +++++----- mm/swapfile.c | 31 +++++++++++++++++++++++++++++++ 7 files changed, 81 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 6c6fb116e925..680d3395fc83 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -317,6 +317,9 @@ enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root, int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, struct mem_cgroup **memcgp, bool compound); +int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm, + gfp_t gfp_mask, struct mem_cgroup **memcgp, + bool compound); void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, bool lrucare, bool compound); void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg, @@ -789,6 +792,16 @@ static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, return 0; } +static inline int mem_cgroup_try_charge_delay(struct page *page, + struct mm_struct *mm, + gfp_t gfp_mask, + struct mem_cgroup **memcgp, + bool compound) +{ + *memcgp = NULL; + return 0; +} + static inline void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, bool lrucare, bool compound) diff --git a/include/linux/swap.h b/include/linux/swap.h index c063443d8638..1a8bd05a335e 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -629,7 +629,6 @@ static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg) return memcg->swappiness; } - #else static inline int mem_cgroup_swappiness(struct mem_cgroup *mem) { @@ -637,6 +636,16 @@ static inline int mem_cgroup_swappiness(struct mem_cgroup *mem) } #endif +#if defined(CONFIG_SWAP) && defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) +extern void mem_cgroup_throttle_swaprate(struct mem_cgroup *memcg, int node, + gfp_t gfp_mask); +#else +static inline void mem_cgroup_throttle_swaprate(struct mem_cgroup *memcg, + int node, gfp_t gfp_mask) +{ +} +#endif + #ifdef CONFIG_MEMCG_SWAP extern void mem_cgroup_swapout(struct page *page, swp_entry_t entry); extern int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 1cd7c1a57a14..b87d5b151db2 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -552,7 +552,7 @@ static int __do_huge_pmd_anonymous_page(struct vm_fault *vmf, struct page *page, VM_BUG_ON_PAGE(!PageCompound(page), page); - if (mem_cgroup_try_charge(page, vma->vm_mm, gfp, &memcg, true)) { + if (mem_cgroup_try_charge_delay(page, vma->vm_mm, gfp, &memcg, true)) { put_page(page); count_vm_event(THP_FAULT_FALLBACK); return VM_FAULT_FALLBACK; @@ -1142,7 +1142,7 @@ static int do_huge_pmd_wp_page_fallback(struct vm_fault *vmf, pmd_t orig_pmd, pages[i] = alloc_page_vma_node(GFP_HIGHUSER_MOVABLE, vma, vmf->address, page_to_nid(page)); if (unlikely(!pages[i] || - mem_cgroup_try_charge(pages[i], vma->vm_mm, + mem_cgroup_try_charge_delay(pages[i], vma->vm_mm, GFP_KERNEL, &memcg, false))) { if (pages[i]) put_page(pages[i]); @@ -1312,7 +1312,7 @@ alloc: goto out; } - if (unlikely(mem_cgroup_try_charge(new_page, vma->vm_mm, + if (unlikely(mem_cgroup_try_charge_delay(new_page, vma->vm_mm, huge_gfp, &memcg, true))) { put_page(new_page); split_huge_pmd(vma, vmf->pmd, vmf->address); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index e6f0d5ef320a..64bd28d35388 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5593,6 +5593,19 @@ out: return ret; } +int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm, + gfp_t gfp_mask, struct mem_cgroup **memcgp, + bool compound) +{ + struct mem_cgroup *memcg; + int ret; + + ret = mem_cgroup_try_charge(page, mm, gfp_mask, memcgp, compound); + memcg = *memcgp; + mem_cgroup_throttle_swaprate(memcg, page_to_nid(page), gfp_mask); + return ret; +} + /** * mem_cgroup_commit_charge - commit a page charge * @page: page to charge diff --git a/mm/memory.c b/mm/memory.c index 7206a634270b..dfe80c574282 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2503,7 +2503,7 @@ static int wp_page_copy(struct vm_fault *vmf) cow_user_page(new_page, old_page, vmf->address, vma); } - if (mem_cgroup_try_charge(new_page, mm, GFP_KERNEL, &memcg, false)) + if (mem_cgroup_try_charge_delay(new_page, mm, GFP_KERNEL, &memcg, false)) goto oom_free_new; __SetPageUptodate(new_page); @@ -3003,8 +3003,8 @@ int do_swap_page(struct vm_fault *vmf) goto out_page; } - if (mem_cgroup_try_charge(page, vma->vm_mm, GFP_KERNEL, - &memcg, false)) { + if (mem_cgroup_try_charge_delay(page, vma->vm_mm, GFP_KERNEL, + &memcg, false)) { ret = VM_FAULT_OOM; goto out_page; } @@ -3165,7 +3165,8 @@ static int do_anonymous_page(struct vm_fault *vmf) if (!page) goto oom; - if (mem_cgroup_try_charge(page, vma->vm_mm, GFP_KERNEL, &memcg, false)) + if (mem_cgroup_try_charge_delay(page, vma->vm_mm, GFP_KERNEL, &memcg, + false)) goto oom_free_page; /* @@ -3661,7 +3662,7 @@ static int do_cow_fault(struct vm_fault *vmf) if (!vmf->cow_page) return VM_FAULT_OOM; - if (mem_cgroup_try_charge(vmf->cow_page, vma->vm_mm, GFP_KERNEL, + if (mem_cgroup_try_charge_delay(vmf->cow_page, vma->vm_mm, GFP_KERNEL, &vmf->memcg, false)) { put_page(vmf->cow_page); return VM_FAULT_OOM; diff --git a/mm/shmem.c b/mm/shmem.c index 2cab84403055..6206ca3510cf 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1239,8 +1239,8 @@ int shmem_unuse(swp_entry_t swap, struct page *page) * the shmem_swaplist_mutex which might hold up shmem_writepage(). * Charged back to the user (not to caller) when swap account is used. */ - error = mem_cgroup_try_charge(page, current->mm, GFP_KERNEL, &memcg, - false); + error = mem_cgroup_try_charge_delay(page, current->mm, GFP_KERNEL, + &memcg, false); if (error) goto out; /* No radix_tree_preload: swap entry keeps a place for page in tree */ @@ -1712,7 +1712,7 @@ repeat: goto failed; } - error = mem_cgroup_try_charge(page, charge_mm, gfp, &memcg, + error = mem_cgroup_try_charge_delay(page, charge_mm, gfp, &memcg, false); if (!error) { error = shmem_add_to_page_cache(page, mapping, index, @@ -1818,7 +1818,7 @@ alloc_nohuge: page = shmem_alloc_and_acct_page(gfp, inode, if (sgp == SGP_WRITE) __SetPageReferenced(page); - error = mem_cgroup_try_charge(page, charge_mm, gfp, &memcg, + error = mem_cgroup_try_charge_delay(page, charge_mm, gfp, &memcg, PageTransHuge(page)); if (error) goto unacct; @@ -2291,7 +2291,7 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, __SetPageSwapBacked(page); __SetPageUptodate(page); - ret = mem_cgroup_try_charge(page, dst_mm, gfp, &memcg, false); + ret = mem_cgroup_try_charge_delay(page, dst_mm, gfp, &memcg, false); if (ret) goto out_release; diff --git a/mm/swapfile.c b/mm/swapfile.c index 2cc2972eedaf..db4ec8ae1c8c 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -3731,6 +3731,37 @@ static void free_swap_count_continuations(struct swap_info_struct *si) } } +#if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) +void mem_cgroup_throttle_swaprate(struct mem_cgroup *memcg, int node, + gfp_t gfp_mask) +{ + struct swap_info_struct *si, *next; + if (!(gfp_mask & __GFP_IO) || !memcg) + return; + + if (!blk_cgroup_congested()) + return; + + /* + * We've already scheduled a throttle, avoid taking the global swap + * lock. + */ + if (current->throttle_queue) + return; + + spin_lock(&swap_avail_lock); + plist_for_each_entry_safe(si, next, &swap_avail_heads[node], + avail_lists[node]) { + if (si->bdev) { + blkcg_schedule_throttle(bdev_get_queue(si->bdev), + true); + break; + } + } + spin_unlock(&swap_avail_lock); +} +#endif + static int __init swapfile_init(void) { int nid; -- cgit v1.2.3 From a79050434b45959f397042080fd1d70ffa9bd9df Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 3 Jul 2018 09:32:35 -0600 Subject: blk-rq-qos: refactor out common elements of blk-wbt blkcg-qos is going to do essentially what wbt does, only on a cgroup basis. Break out the common code that will be shared between blkcg-qos and wbt into blk-rq-qos.* so they can both utilize the same infrastructure. Signed-off-by: Josef Bacik Signed-off-by: Jens Axboe --- block/Makefile | 2 +- block/blk-core.c | 12 +- block/blk-mq.c | 12 +- block/blk-rq-qos.c | 178 +++++++++++++++++++++++++++ block/blk-rq-qos.h | 106 ++++++++++++++++ block/blk-settings.c | 4 +- block/blk-sysfs.c | 22 ++-- block/blk-wbt.c | 326 ++++++++++++++++++++++--------------------------- block/blk-wbt.h | 63 ++++------ include/linux/blkdev.h | 4 +- 10 files changed, 478 insertions(+), 251 deletions(-) create mode 100644 block/blk-rq-qos.c create mode 100644 block/blk-rq-qos.h (limited to 'include') diff --git a/block/Makefile b/block/Makefile index a8f94cdb75c3..57d0f47ab05f 100644 --- a/block/Makefile +++ b/block/Makefile @@ -9,7 +9,7 @@ obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-tag.o blk-sysfs.o \ blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \ blk-mq-sysfs.o blk-mq-cpumap.o blk-mq-sched.o ioctl.o \ genhd.o partition-generic.o ioprio.o \ - badblocks.o partitions/ + badblocks.o partitions/ blk-rq-qos.o obj-$(CONFIG_BOUNCE) += bounce.o obj-$(CONFIG_BLK_SCSI_REQUEST) += scsi_ioctl.o diff --git a/block/blk-core.c b/block/blk-core.c index 2ff8e131a892..b33a73bcf2d0 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1645,7 +1645,7 @@ void blk_requeue_request(struct request_queue *q, struct request *rq) blk_delete_timer(rq); blk_clear_rq_complete(rq); trace_block_rq_requeue(q, rq); - wbt_requeue(q->rq_wb, rq); + rq_qos_requeue(q, rq); if (rq->rq_flags & RQF_QUEUED) blk_queue_end_tag(q, rq); @@ -1752,7 +1752,7 @@ void __blk_put_request(struct request_queue *q, struct request *req) /* this is a bio leak */ WARN_ON(req->bio != NULL); - wbt_done(q->rq_wb, req); + rq_qos_done(q, req); /* * Request may not have originated from ll_rw_blk. if not, @@ -2044,7 +2044,7 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio) } get_rq: - wb_acct = wbt_wait(q->rq_wb, bio, q->queue_lock); + wb_acct = rq_qos_throttle(q, bio, q->queue_lock); /* * Grab a free request. This is might sleep but can not fail. @@ -2054,7 +2054,7 @@ get_rq: req = get_request(q, bio->bi_opf, bio, 0, GFP_NOIO); if (IS_ERR(req)) { blk_queue_exit(q); - __wbt_done(q->rq_wb, wb_acct); + rq_qos_cleanup(q, wb_acct); if (PTR_ERR(req) == -ENOMEM) bio->bi_status = BLK_STS_RESOURCE; else @@ -2983,7 +2983,7 @@ void blk_start_request(struct request *req) req->throtl_size = blk_rq_sectors(req); #endif req->rq_flags |= RQF_STATS; - wbt_issue(req->q->rq_wb, req); + rq_qos_issue(req->q, req); } BUG_ON(blk_rq_is_complete(req)); @@ -3207,7 +3207,7 @@ void blk_finish_request(struct request *req, blk_status_t error) blk_account_io_done(req, now); if (req->end_io) { - wbt_done(req->q->rq_wb, req); + rq_qos_done(q, req); req->end_io(req, error); } else { if (blk_bidi_rq(req)) diff --git a/block/blk-mq.c b/block/blk-mq.c index 850fdd02c385..ea2a226457fa 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -504,7 +504,7 @@ void blk_mq_free_request(struct request *rq) if (unlikely(laptop_mode && !blk_rq_is_passthrough(rq))) laptop_io_completion(q->backing_dev_info); - wbt_done(q->rq_wb, rq); + rq_qos_done(q, rq); if (blk_rq_rl(rq)) blk_put_rl(blk_rq_rl(rq)); @@ -527,7 +527,7 @@ inline void __blk_mq_end_request(struct request *rq, blk_status_t error) blk_account_io_done(rq, now); if (rq->end_io) { - wbt_done(rq->q->rq_wb, rq); + rq_qos_done(rq->q, rq); rq->end_io(rq, error); } else { if (unlikely(blk_bidi_rq(rq))) @@ -641,7 +641,7 @@ void blk_mq_start_request(struct request *rq) rq->throtl_size = blk_rq_sectors(rq); #endif rq->rq_flags |= RQF_STATS; - wbt_issue(q->rq_wb, rq); + rq_qos_issue(q, rq); } WARN_ON_ONCE(blk_mq_rq_state(rq) != MQ_RQ_IDLE); @@ -667,7 +667,7 @@ static void __blk_mq_requeue_request(struct request *rq) blk_mq_put_driver_tag(rq); trace_block_rq_requeue(q, rq); - wbt_requeue(q->rq_wb, rq); + rq_qos_requeue(q, rq); if (blk_mq_request_started(rq)) { WRITE_ONCE(rq->state, MQ_RQ_IDLE); @@ -1806,13 +1806,13 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) if (blk_mq_sched_bio_merge(q, bio)) return BLK_QC_T_NONE; - wb_acct = wbt_wait(q->rq_wb, bio, NULL); + wb_acct = rq_qos_throttle(q, bio, NULL); trace_block_getrq(q, bio, bio->bi_opf); rq = blk_mq_get_request(q, bio, bio->bi_opf, &data); if (unlikely(!rq)) { - __wbt_done(q->rq_wb, wb_acct); + rq_qos_cleanup(q, wb_acct); if (bio->bi_opf & REQ_NOWAIT) bio_wouldblock_error(bio); return BLK_QC_T_NONE; diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c new file mode 100644 index 000000000000..d2f2af8aa10c --- /dev/null +++ b/block/blk-rq-qos.c @@ -0,0 +1,178 @@ +#include "blk-rq-qos.h" + +#include "blk-wbt.h" + +/* + * Increment 'v', if 'v' is below 'below'. Returns true if we succeeded, + * false if 'v' + 1 would be bigger than 'below'. + */ +static bool atomic_inc_below(atomic_t *v, int below) +{ + int cur = atomic_read(v); + + for (;;) { + int old; + + if (cur >= below) + return false; + old = atomic_cmpxchg(v, cur, cur + 1); + if (old == cur) + break; + cur = old; + } + + return true; +} + +bool rq_wait_inc_below(struct rq_wait *rq_wait, int limit) +{ + return atomic_inc_below(&rq_wait->inflight, limit); +} + +void rq_qos_cleanup(struct request_queue *q, enum wbt_flags wb_acct) +{ + struct rq_qos *rqos; + + for (rqos = q->rq_qos; rqos; rqos = rqos->next) { + if (rqos->ops->cleanup) + rqos->ops->cleanup(rqos, wb_acct); + } +} + +void rq_qos_done(struct request_queue *q, struct request *rq) +{ + struct rq_qos *rqos; + + for (rqos = q->rq_qos; rqos; rqos = rqos->next) { + if (rqos->ops->done) + rqos->ops->done(rqos, rq); + } +} + +void rq_qos_issue(struct request_queue *q, struct request *rq) +{ + struct rq_qos *rqos; + + for(rqos = q->rq_qos; rqos; rqos = rqos->next) { + if (rqos->ops->issue) + rqos->ops->issue(rqos, rq); + } +} + +void rq_qos_requeue(struct request_queue *q, struct request *rq) +{ + struct rq_qos *rqos; + + for(rqos = q->rq_qos; rqos; rqos = rqos->next) { + if (rqos->ops->requeue) + rqos->ops->requeue(rqos, rq); + } +} + +enum wbt_flags rq_qos_throttle(struct request_queue *q, struct bio *bio, + spinlock_t *lock) +{ + struct rq_qos *rqos; + enum wbt_flags flags = 0; + + for(rqos = q->rq_qos; rqos; rqos = rqos->next) { + if (rqos->ops->throttle) + flags |= rqos->ops->throttle(rqos, bio, lock); + } + return flags; +} + +/* + * Return true, if we can't increase the depth further by scaling + */ +bool rq_depth_calc_max_depth(struct rq_depth *rqd) +{ + unsigned int depth; + bool ret = false; + + /* + * For QD=1 devices, this is a special case. It's important for those + * to have one request ready when one completes, so force a depth of + * 2 for those devices. On the backend, it'll be a depth of 1 anyway, + * since the device can't have more than that in flight. If we're + * scaling down, then keep a setting of 1/1/1. + */ + if (rqd->queue_depth == 1) { + if (rqd->scale_step > 0) + rqd->max_depth = 1; + else { + rqd->max_depth = 2; + ret = true; + } + } else { + /* + * scale_step == 0 is our default state. If we have suffered + * latency spikes, step will be > 0, and we shrink the + * allowed write depths. If step is < 0, we're only doing + * writes, and we allow a temporarily higher depth to + * increase performance. + */ + depth = min_t(unsigned int, rqd->default_depth, + rqd->queue_depth); + if (rqd->scale_step > 0) + depth = 1 + ((depth - 1) >> min(31, rqd->scale_step)); + else if (rqd->scale_step < 0) { + unsigned int maxd = 3 * rqd->queue_depth / 4; + + depth = 1 + ((depth - 1) << -rqd->scale_step); + if (depth > maxd) { + depth = maxd; + ret = true; + } + } + + rqd->max_depth = depth; + } + + return ret; +} + +void rq_depth_scale_up(struct rq_depth *rqd) +{ + /* + * Hit max in previous round, stop here + */ + if (rqd->scaled_max) + return; + + rqd->scale_step--; + + rqd->scaled_max = rq_depth_calc_max_depth(rqd); +} + +/* + * Scale rwb down. If 'hard_throttle' is set, do it quicker, since we + * had a latency violation. + */ +void rq_depth_scale_down(struct rq_depth *rqd, bool hard_throttle) +{ + /* + * Stop scaling down when we've hit the limit. This also prevents + * ->scale_step from going to crazy values, if the device can't + * keep up. + */ + if (rqd->max_depth == 1) + return; + + if (rqd->scale_step < 0 && hard_throttle) + rqd->scale_step = 0; + else + rqd->scale_step++; + + rqd->scaled_max = false; + rq_depth_calc_max_depth(rqd); +} + +void rq_qos_exit(struct request_queue *q) +{ + while (q->rq_qos) { + struct rq_qos *rqos = q->rq_qos; + q->rq_qos = rqos->next; + rqos->ops->exit(rqos); + } +} diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h new file mode 100644 index 000000000000..f9a39bd6ece3 --- /dev/null +++ b/block/blk-rq-qos.h @@ -0,0 +1,106 @@ +#ifndef RQ_QOS_H +#define RQ_QOS_H + +#include +#include +#include +#include +#include + +enum rq_qos_id { + RQ_QOS_WBT, + RQ_QOS_CGROUP, +}; + +struct rq_wait { + wait_queue_head_t wait; + atomic_t inflight; +}; + +struct rq_qos { + struct rq_qos_ops *ops; + struct request_queue *q; + enum rq_qos_id id; + struct rq_qos *next; +}; + +struct rq_qos_ops { + enum wbt_flags (*throttle)(struct rq_qos *, struct bio *, + spinlock_t *); + void (*issue)(struct rq_qos *, struct request *); + void (*requeue)(struct rq_qos *, struct request *); + void (*done)(struct rq_qos *, struct request *); + void (*cleanup)(struct rq_qos *, enum wbt_flags); + void (*exit)(struct rq_qos *); +}; + +struct rq_depth { + unsigned int max_depth; + + int scale_step; + bool scaled_max; + + unsigned int queue_depth; + unsigned int default_depth; +}; + +static inline struct rq_qos *rq_qos_id(struct request_queue *q, + enum rq_qos_id id) +{ + struct rq_qos *rqos; + for (rqos = q->rq_qos; rqos; rqos = rqos->next) { + if (rqos->id == id) + break; + } + return rqos; +} + +static inline struct rq_qos *wbt_rq_qos(struct request_queue *q) +{ + return rq_qos_id(q, RQ_QOS_WBT); +} + +static inline struct rq_qos *blkcg_rq_qos(struct request_queue *q) +{ + return rq_qos_id(q, RQ_QOS_CGROUP); +} + +static inline void rq_wait_init(struct rq_wait *rq_wait) +{ + atomic_set(&rq_wait->inflight, 0); + init_waitqueue_head(&rq_wait->wait); +} + +static inline void rq_qos_add(struct request_queue *q, struct rq_qos *rqos) +{ + rqos->next = q->rq_qos; + q->rq_qos = rqos; +} + +static inline void rq_qos_del(struct request_queue *q, struct rq_qos *rqos) +{ + struct rq_qos *cur, *prev = NULL; + for (cur = q->rq_qos; cur; cur = cur->next) { + if (cur == rqos) { + if (prev) + prev->next = rqos->next; + else + q->rq_qos = cur; + break; + } + prev = cur; + } +} + +bool rq_wait_inc_below(struct rq_wait *rq_wait, int limit); +void rq_depth_scale_up(struct rq_depth *rqd); +void rq_depth_scale_down(struct rq_depth *rqd, bool hard_throttle); +bool rq_depth_calc_max_depth(struct rq_depth *rqd); + +void rq_qos_cleanup(struct request_queue *, enum wbt_flags); +void rq_qos_done(struct request_queue *, struct request *); +void rq_qos_issue(struct request_queue *, struct request *); +void rq_qos_requeue(struct request_queue *, struct request *); +enum wbt_flags rq_qos_throttle(struct request_queue *, struct bio *, spinlock_t *); +void rq_qos_exit(struct request_queue *); +#endif diff --git a/block/blk-settings.c b/block/blk-settings.c index d1de71124656..053de87d1fda 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -875,7 +875,7 @@ EXPORT_SYMBOL_GPL(blk_queue_flush_queueable); void blk_set_queue_depth(struct request_queue *q, unsigned int depth) { q->queue_depth = depth; - wbt_set_queue_depth(q->rq_wb, depth); + wbt_set_queue_depth(q, depth); } EXPORT_SYMBOL(blk_set_queue_depth); @@ -900,7 +900,7 @@ void blk_queue_write_cache(struct request_queue *q, bool wc, bool fua) queue_flag_clear(QUEUE_FLAG_FUA, q); spin_unlock_irq(q->queue_lock); - wbt_set_write_cache(q->rq_wb, test_bit(QUEUE_FLAG_WC, &q->queue_flags)); + wbt_set_write_cache(q, test_bit(QUEUE_FLAG_WC, &q->queue_flags)); } EXPORT_SYMBOL_GPL(blk_queue_write_cache); diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 94987b1f69e1..49c29a5d06bb 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -422,16 +422,16 @@ static ssize_t queue_poll_store(struct request_queue *q, const char *page, static ssize_t queue_wb_lat_show(struct request_queue *q, char *page) { - if (!q->rq_wb) + if (!wbt_rq_qos(q)) return -EINVAL; - return sprintf(page, "%llu\n", div_u64(q->rq_wb->min_lat_nsec, 1000)); + return sprintf(page, "%llu\n", div_u64(wbt_get_min_lat(q), 1000)); } static ssize_t queue_wb_lat_store(struct request_queue *q, const char *page, size_t count) { - struct rq_wb *rwb; + struct rq_qos *rqos; ssize_t ret; s64 val; @@ -441,23 +441,21 @@ static ssize_t queue_wb_lat_store(struct request_queue *q, const char *page, if (val < -1) return -EINVAL; - rwb = q->rq_wb; - if (!rwb) { + rqos = wbt_rq_qos(q); + if (!rqos) { ret = wbt_init(q); if (ret) return ret; } - rwb = q->rq_wb; if (val == -1) - rwb->min_lat_nsec = wbt_default_latency_nsec(q); + val = wbt_default_latency_nsec(q); else if (val >= 0) - rwb->min_lat_nsec = val * 1000ULL; + val *= 1000ULL; - if (rwb->enable_state == WBT_STATE_ON_DEFAULT) - rwb->enable_state = WBT_STATE_ON_MANUAL; + wbt_set_min_lat(q, val); - wbt_update_limits(rwb); + wbt_update_limits(q); return count; } @@ -964,7 +962,7 @@ void blk_unregister_queue(struct gendisk *disk) kobject_del(&q->kobj); blk_trace_remove_sysfs(disk_to_dev(disk)); - wbt_exit(q); + rq_qos_exit(q); mutex_lock(&q->sysfs_lock); if (q->request_fn || (q->mq_ops && q->elevator)) diff --git a/block/blk-wbt.c b/block/blk-wbt.c index 4f89b28fa652..6fe20fb823e4 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -25,6 +25,7 @@ #include #include "blk-wbt.h" +#include "blk-rq-qos.h" #define CREATE_TRACE_POINTS #include @@ -78,28 +79,6 @@ static inline bool rwb_enabled(struct rq_wb *rwb) return rwb && rwb->wb_normal != 0; } -/* - * Increment 'v', if 'v' is below 'below'. Returns true if we succeeded, - * false if 'v' + 1 would be bigger than 'below'. - */ -static bool atomic_inc_below(atomic_t *v, int below) -{ - int cur = atomic_read(v); - - for (;;) { - int old; - - if (cur >= below) - return false; - old = atomic_cmpxchg(v, cur, cur + 1); - if (old == cur) - break; - cur = old; - } - - return true; -} - static void wb_timestamp(struct rq_wb *rwb, unsigned long *var) { if (rwb_enabled(rwb)) { @@ -116,7 +95,7 @@ static void wb_timestamp(struct rq_wb *rwb, unsigned long *var) */ static bool wb_recent_wait(struct rq_wb *rwb) { - struct bdi_writeback *wb = &rwb->queue->backing_dev_info->wb; + struct bdi_writeback *wb = &rwb->rqos.q->backing_dev_info->wb; return time_before(jiffies, wb->dirty_sleep + HZ); } @@ -144,8 +123,9 @@ static void rwb_wake_all(struct rq_wb *rwb) } } -void __wbt_done(struct rq_wb *rwb, enum wbt_flags wb_acct) +static void __wbt_done(struct rq_qos *rqos, enum wbt_flags wb_acct) { + struct rq_wb *rwb = RQWB(rqos); struct rq_wait *rqw; int inflight, limit; @@ -194,10 +174,9 @@ void __wbt_done(struct rq_wb *rwb, enum wbt_flags wb_acct) * Called on completion of a request. Note that it's also called when * a request is merged, when the request gets freed. */ -void wbt_done(struct rq_wb *rwb, struct request *rq) +static void wbt_done(struct rq_qos *rqos, struct request *rq) { - if (!rwb) - return; + struct rq_wb *rwb = RQWB(rqos); if (!wbt_is_tracked(rq)) { if (rwb->sync_cookie == rq) { @@ -209,72 +188,11 @@ void wbt_done(struct rq_wb *rwb, struct request *rq) wb_timestamp(rwb, &rwb->last_comp); } else { WARN_ON_ONCE(rq == rwb->sync_cookie); - __wbt_done(rwb, wbt_flags(rq)); + __wbt_done(rqos, wbt_flags(rq)); } wbt_clear_state(rq); } -/* - * Return true, if we can't increase the depth further by scaling - */ -static bool calc_wb_limits(struct rq_wb *rwb) -{ - unsigned int depth; - bool ret = false; - - if (!rwb->min_lat_nsec) { - rwb->wb_max = rwb->wb_normal = rwb->wb_background = 0; - return false; - } - - /* - * For QD=1 devices, this is a special case. It's important for those - * to have one request ready when one completes, so force a depth of - * 2 for those devices. On the backend, it'll be a depth of 1 anyway, - * since the device can't have more than that in flight. If we're - * scaling down, then keep a setting of 1/1/1. - */ - if (rwb->queue_depth == 1) { - if (rwb->scale_step > 0) - rwb->wb_max = rwb->wb_normal = 1; - else { - rwb->wb_max = rwb->wb_normal = 2; - ret = true; - } - rwb->wb_background = 1; - } else { - /* - * scale_step == 0 is our default state. If we have suffered - * latency spikes, step will be > 0, and we shrink the - * allowed write depths. If step is < 0, we're only doing - * writes, and we allow a temporarily higher depth to - * increase performance. - */ - depth = min_t(unsigned int, RWB_DEF_DEPTH, rwb->queue_depth); - if (rwb->scale_step > 0) - depth = 1 + ((depth - 1) >> min(31, rwb->scale_step)); - else if (rwb->scale_step < 0) { - unsigned int maxd = 3 * rwb->queue_depth / 4; - - depth = 1 + ((depth - 1) << -rwb->scale_step); - if (depth > maxd) { - depth = maxd; - ret = true; - } - } - - /* - * Set our max/normal/bg queue depths based on how far - * we have scaled down (->scale_step). - */ - rwb->wb_max = depth; - rwb->wb_normal = (rwb->wb_max + 1) / 2; - rwb->wb_background = (rwb->wb_max + 3) / 4; - } - - return ret; -} - static inline bool stat_sample_valid(struct blk_rq_stat *stat) { /* @@ -307,7 +225,8 @@ enum { static int latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat) { - struct backing_dev_info *bdi = rwb->queue->backing_dev_info; + struct backing_dev_info *bdi = rwb->rqos.q->backing_dev_info; + struct rq_depth *rqd = &rwb->rq_depth; u64 thislat; /* @@ -351,7 +270,7 @@ static int latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat) return LAT_EXCEEDED; } - if (rwb->scale_step) + if (rqd->scale_step) trace_wbt_stat(bdi, stat); return LAT_OK; @@ -359,58 +278,48 @@ static int latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat) static void rwb_trace_step(struct rq_wb *rwb, const char *msg) { - struct backing_dev_info *bdi = rwb->queue->backing_dev_info; + struct backing_dev_info *bdi = rwb->rqos.q->backing_dev_info; + struct rq_depth *rqd = &rwb->rq_depth; - trace_wbt_step(bdi, msg, rwb->scale_step, rwb->cur_win_nsec, - rwb->wb_background, rwb->wb_normal, rwb->wb_max); + trace_wbt_step(bdi, msg, rqd->scale_step, rwb->cur_win_nsec, + rwb->wb_background, rwb->wb_normal, rqd->max_depth); } -static void scale_up(struct rq_wb *rwb) +static void calc_wb_limits(struct rq_wb *rwb) { - /* - * Hit max in previous round, stop here - */ - if (rwb->scaled_max) - return; + if (rwb->min_lat_nsec == 0) { + rwb->wb_normal = rwb->wb_background = 0; + } else if (rwb->rq_depth.max_depth <= 2) { + rwb->wb_normal = rwb->rq_depth.max_depth; + rwb->wb_background = 1; + } else { + rwb->wb_normal = (rwb->rq_depth.max_depth + 1) / 2; + rwb->wb_background = (rwb->rq_depth.max_depth + 3) / 4; + } +} - rwb->scale_step--; +static void scale_up(struct rq_wb *rwb) +{ + rq_depth_scale_up(&rwb->rq_depth); + calc_wb_limits(rwb); rwb->unknown_cnt = 0; - - rwb->scaled_max = calc_wb_limits(rwb); - - rwb_wake_all(rwb); - - rwb_trace_step(rwb, "step up"); + rwb_trace_step(rwb, "scale up"); } -/* - * Scale rwb down. If 'hard_throttle' is set, do it quicker, since we - * had a latency violation. - */ static void scale_down(struct rq_wb *rwb, bool hard_throttle) { - /* - * Stop scaling down when we've hit the limit. This also prevents - * ->scale_step from going to crazy values, if the device can't - * keep up. - */ - if (rwb->wb_max == 1) - return; - - if (rwb->scale_step < 0 && hard_throttle) - rwb->scale_step = 0; - else - rwb->scale_step++; - - rwb->scaled_max = false; - rwb->unknown_cnt = 0; + rq_depth_scale_down(&rwb->rq_depth, hard_throttle); calc_wb_limits(rwb); - rwb_trace_step(rwb, "step down"); + rwb->unknown_cnt = 0; + rwb_wake_all(rwb); + rwb_trace_step(rwb, "scale down"); } static void rwb_arm_timer(struct rq_wb *rwb) { - if (rwb->scale_step > 0) { + struct rq_depth *rqd = &rwb->rq_depth; + + if (rqd->scale_step > 0) { /* * We should speed this up, using some variant of a fast * integer inverse square root calculation. Since we only do @@ -418,7 +327,7 @@ static void rwb_arm_timer(struct rq_wb *rwb) * though. */ rwb->cur_win_nsec = div_u64(rwb->win_nsec << 4, - int_sqrt((rwb->scale_step + 1) << 8)); + int_sqrt((rqd->scale_step + 1) << 8)); } else { /* * For step < 0, we don't want to increase/decrease the @@ -433,12 +342,13 @@ static void rwb_arm_timer(struct rq_wb *rwb) static void wb_timer_fn(struct blk_stat_callback *cb) { struct rq_wb *rwb = cb->data; + struct rq_depth *rqd = &rwb->rq_depth; unsigned int inflight = wbt_inflight(rwb); int status; status = latency_exceeded(rwb, cb->stat); - trace_wbt_timer(rwb->queue->backing_dev_info, status, rwb->scale_step, + trace_wbt_timer(rwb->rqos.q->backing_dev_info, status, rqd->scale_step, inflight); /* @@ -469,9 +379,9 @@ static void wb_timer_fn(struct blk_stat_callback *cb) * currently don't have a valid read/write sample. For that * case, slowly return to center state (step == 0). */ - if (rwb->scale_step > 0) + if (rqd->scale_step > 0) scale_up(rwb); - else if (rwb->scale_step < 0) + else if (rqd->scale_step < 0) scale_down(rwb, false); break; default: @@ -481,19 +391,50 @@ static void wb_timer_fn(struct blk_stat_callback *cb) /* * Re-arm timer, if we have IO in flight */ - if (rwb->scale_step || inflight) + if (rqd->scale_step || inflight) rwb_arm_timer(rwb); } -void wbt_update_limits(struct rq_wb *rwb) +static void __wbt_update_limits(struct rq_wb *rwb) { - rwb->scale_step = 0; - rwb->scaled_max = false; + struct rq_depth *rqd = &rwb->rq_depth; + + rqd->scale_step = 0; + rqd->scaled_max = false; + + rq_depth_calc_max_depth(rqd); calc_wb_limits(rwb); rwb_wake_all(rwb); } +void wbt_update_limits(struct request_queue *q) +{ + struct rq_qos *rqos = wbt_rq_qos(q); + if (!rqos) + return; + __wbt_update_limits(RQWB(rqos)); +} + +u64 wbt_get_min_lat(struct request_queue *q) +{ + struct rq_qos *rqos = wbt_rq_qos(q); + if (!rqos) + return 0; + return RQWB(rqos)->min_lat_nsec; +} + +void wbt_set_min_lat(struct request_queue *q, u64 val) +{ + struct rq_qos *rqos = wbt_rq_qos(q); + if (!rqos) + return; + RQWB(rqos)->min_lat_nsec = val; + RQWB(rqos)->enable_state = WBT_STATE_ON_MANUAL; + __wbt_update_limits(RQWB(rqos)); +} + + static bool close_io(struct rq_wb *rwb) { const unsigned long now = jiffies; @@ -520,7 +461,7 @@ static inline unsigned int get_limit(struct rq_wb *rwb, unsigned long rw) * IO for a bit. */ if ((rw & REQ_HIPRIO) || wb_recent_wait(rwb) || current_is_kswapd()) - limit = rwb->wb_max; + limit = rwb->rq_depth.max_depth; else if ((rw & REQ_BACKGROUND) || close_io(rwb)) { /* * If less than 100ms since we completed unrelated IO, @@ -554,7 +495,7 @@ static inline bool may_queue(struct rq_wb *rwb, struct rq_wait *rqw, rqw->wait.head.next != &wait->entry) return false; - return atomic_inc_below(&rqw->inflight, get_limit(rwb, rw)); + return rq_wait_inc_below(rqw, get_limit(rwb, rw)); } /* @@ -614,8 +555,10 @@ static inline bool wbt_should_throttle(struct rq_wb *rwb, struct bio *bio) * in an irq held spinlock, if it holds one when calling this function. * If we do sleep, we'll release and re-grab it. */ -enum wbt_flags wbt_wait(struct rq_wb *rwb, struct bio *bio, spinlock_t *lock) +static enum wbt_flags wbt_wait(struct rq_qos *rqos, struct bio *bio, + spinlock_t *lock) { + struct rq_wb *rwb = RQWB(rqos); enum wbt_flags ret = 0; if (!rwb_enabled(rwb)) @@ -643,8 +586,10 @@ enum wbt_flags wbt_wait(struct rq_wb *rwb, struct bio *bio, spinlock_t *lock) return ret | WBT_TRACKED; } -void wbt_issue(struct rq_wb *rwb, struct request *rq) +void wbt_issue(struct rq_qos *rqos, struct request *rq) { + struct rq_wb *rwb = RQWB(rqos); + if (!rwb_enabled(rwb)) return; @@ -661,8 +606,9 @@ void wbt_issue(struct rq_wb *rwb, struct request *rq) } } -void wbt_requeue(struct rq_wb *rwb, struct request *rq) +void wbt_requeue(struct rq_qos *rqos, struct request *rq) { + struct rq_wb *rwb = RQWB(rqos); if (!rwb_enabled(rwb)) return; if (rq == rwb->sync_cookie) { @@ -671,39 +617,30 @@ void wbt_requeue(struct rq_wb *rwb, struct request *rq) } } -void wbt_set_queue_depth(struct rq_wb *rwb, unsigned int depth) +void wbt_set_queue_depth(struct request_queue *q, unsigned int depth) { - if (rwb) { - rwb->queue_depth = depth; - wbt_update_limits(rwb); + struct rq_qos *rqos = wbt_rq_qos(q); + if (rqos) { + RQWB(rqos)->rq_depth.queue_depth = depth; + __wbt_update_limits(RQWB(rqos)); } } -void wbt_set_write_cache(struct rq_wb *rwb, bool write_cache_on) -{ - if (rwb) - rwb->wc = write_cache_on; -} - -/* - * Disable wbt, if enabled by default. - */ -void wbt_disable_default(struct request_queue *q) +void wbt_set_write_cache(struct request_queue *q, bool write_cache_on) { - struct rq_wb *rwb = q->rq_wb; - - if (rwb && rwb->enable_state == WBT_STATE_ON_DEFAULT) - wbt_exit(q); + struct rq_qos *rqos = wbt_rq_qos(q); + if (rqos) + RQWB(rqos)->wc = write_cache_on; } -EXPORT_SYMBOL_GPL(wbt_disable_default); /* * Enable wbt if defaults are configured that way */ void wbt_enable_default(struct request_queue *q) { + struct rq_qos *rqos = wbt_rq_qos(q); /* Throttling already enabled? */ - if (q->rq_wb) + if (rqos) return; /* Queue not registered? Maybe shutting down... */ @@ -741,6 +678,41 @@ static int wbt_data_dir(const struct request *rq) return -1; } +static void wbt_exit(struct rq_qos *rqos) +{ + struct rq_wb *rwb = RQWB(rqos); + struct request_queue *q = rqos->q; + + blk_stat_remove_callback(q, rwb->cb); + blk_stat_free_callback(rwb->cb); + kfree(rwb); +} + +/* + * Disable wbt, if enabled by default. + */ +void wbt_disable_default(struct request_queue *q) +{ + struct rq_qos *rqos = wbt_rq_qos(q); + struct rq_wb *rwb; + if (!rqos) + return; + rwb = RQWB(rqos); + if (rwb->enable_state == WBT_STATE_ON_DEFAULT) + rwb->wb_normal = 0; +} +EXPORT_SYMBOL_GPL(wbt_disable_default); + + +static struct rq_qos_ops wbt_rqos_ops = { + .throttle = wbt_wait, + .issue = wbt_issue, + .requeue = wbt_requeue, + .done = wbt_done, + .cleanup = __wbt_done, + .exit = wbt_exit, +}; + int wbt_init(struct request_queue *q) { struct rq_wb *rwb; @@ -756,39 +728,29 @@ int wbt_init(struct request_queue *q) return -ENOMEM; } - for (i = 0; i < WBT_NUM_RWQ; i++) { - atomic_set(&rwb->rq_wait[i].inflight, 0); - init_waitqueue_head(&rwb->rq_wait[i].wait); - } + for (i = 0; i < WBT_NUM_RWQ; i++) + rq_wait_init(&rwb->rq_wait[i]); + rwb->rqos.id = RQ_QOS_WBT; + rwb->rqos.ops = &wbt_rqos_ops; + rwb->rqos.q = q; rwb->last_comp = rwb->last_issue = jiffies; - rwb->queue = q; rwb->win_nsec = RWB_WINDOW_NSEC; rwb->enable_state = WBT_STATE_ON_DEFAULT; - wbt_update_limits(rwb); + rwb->wc = 1; + rwb->rq_depth.default_depth = RWB_DEF_DEPTH; + __wbt_update_limits(rwb); /* * Assign rwb and add the stats callback. */ - q->rq_wb = rwb; + rq_qos_add(q, &rwb->rqos); blk_stat_add_callback(q, rwb->cb); rwb->min_lat_nsec = wbt_default_latency_nsec(q); - wbt_set_queue_depth(rwb, blk_queue_depth(q)); - wbt_set_write_cache(rwb, test_bit(QUEUE_FLAG_WC, &q->queue_flags)); + wbt_set_queue_depth(q, blk_queue_depth(q)); + wbt_set_write_cache(q, test_bit(QUEUE_FLAG_WC, &q->queue_flags)); return 0; } - -void wbt_exit(struct request_queue *q) -{ - struct rq_wb *rwb = q->rq_wb; - - if (rwb) { - blk_stat_remove_callback(q, rwb->cb); - blk_stat_free_callback(rwb->cb); - q->rq_wb = NULL; - kfree(rwb); - } -} diff --git a/block/blk-wbt.h b/block/blk-wbt.h index 300df531d0a6..53b20a58c0a2 100644 --- a/block/blk-wbt.h +++ b/block/blk-wbt.h @@ -9,6 +9,7 @@ #include #include "blk-stat.h" +#include "blk-rq-qos.h" enum wbt_flags { WBT_TRACKED = 1, /* write, tracked for throttling */ @@ -35,20 +36,12 @@ enum { WBT_STATE_ON_MANUAL = 2, }; -struct rq_wait { - wait_queue_head_t wait; - atomic_t inflight; -}; - struct rq_wb { /* * Settings that govern how we throttle */ unsigned int wb_background; /* background writeback */ unsigned int wb_normal; /* normal writeback */ - unsigned int wb_max; /* max throughput writeback */ - int scale_step; - bool scaled_max; short enable_state; /* WBT_STATE_* */ @@ -67,15 +60,20 @@ struct rq_wb { void *sync_cookie; unsigned int wc; - unsigned int queue_depth; unsigned long last_issue; /* last non-throttled issue */ unsigned long last_comp; /* last non-throttled comp */ unsigned long min_lat_nsec; - struct request_queue *queue; + struct rq_qos rqos; struct rq_wait rq_wait[WBT_NUM_RWQ]; + struct rq_depth rq_depth; }; +static inline struct rq_wb *RQWB(struct rq_qos *rqos) +{ + return container_of(rqos, struct rq_wb, rqos); +} + static inline unsigned int wbt_inflight(struct rq_wb *rwb) { unsigned int i, ret = 0; @@ -86,6 +84,7 @@ static inline unsigned int wbt_inflight(struct rq_wb *rwb) return ret; } + #ifdef CONFIG_BLK_WBT static inline void wbt_track(struct request *rq, enum wbt_flags flags) @@ -93,19 +92,16 @@ static inline void wbt_track(struct request *rq, enum wbt_flags flags) rq->wbt_flags |= flags; } -void __wbt_done(struct rq_wb *, enum wbt_flags); -void wbt_done(struct rq_wb *, struct request *); -enum wbt_flags wbt_wait(struct rq_wb *, struct bio *, spinlock_t *); int wbt_init(struct request_queue *); -void wbt_exit(struct request_queue *); -void wbt_update_limits(struct rq_wb *); -void wbt_requeue(struct rq_wb *, struct request *); -void wbt_issue(struct rq_wb *, struct request *); +void wbt_update_limits(struct request_queue *); void wbt_disable_default(struct request_queue *); void wbt_enable_default(struct request_queue *); -void wbt_set_queue_depth(struct rq_wb *, unsigned int); -void wbt_set_write_cache(struct rq_wb *, bool); +u64 wbt_get_min_lat(struct request_queue *q); +void wbt_set_min_lat(struct request_queue *q, u64 val); + +void wbt_set_queue_depth(struct request_queue *, unsigned int); +void wbt_set_write_cache(struct request_queue *, bool); u64 wbt_default_latency_nsec(struct request_queue *); @@ -114,43 +110,30 @@ u64 wbt_default_latency_nsec(struct request_queue *); static inline void wbt_track(struct request *rq, enum wbt_flags flags) { } -static inline void __wbt_done(struct rq_wb *rwb, enum wbt_flags flags) -{ -} -static inline void wbt_done(struct rq_wb *rwb, struct request *rq) -{ -} -static inline enum wbt_flags wbt_wait(struct rq_wb *rwb, struct bio *bio, - spinlock_t *lock) -{ - return 0; -} static inline int wbt_init(struct request_queue *q) { return -EINVAL; } -static inline void wbt_exit(struct request_queue *q) -{ -} -static inline void wbt_update_limits(struct rq_wb *rwb) +static inline void wbt_update_limits(struct request_queue *q) { } -static inline void wbt_requeue(struct rq_wb *rwb, struct request *rq) +static inline void wbt_disable_default(struct request_queue *q) { } -static inline void wbt_issue(struct rq_wb *rwb, struct request *rq) +static inline void wbt_enable_default(struct request_queue *q) { } -static inline void wbt_disable_default(struct request_queue *q) +static inline void wbt_set_queue_depth(struct request_queue *q, unsigned int depth) { } -static inline void wbt_enable_default(struct request_queue *q) +static inline void wbt_set_write_cache(struct request_queue *q, bool wc) { } -static inline void wbt_set_queue_depth(struct rq_wb *rwb, unsigned int depth) +static inline u64 wbt_get_min_lat(struct request_queue *q) { + return 0; } -static inline void wbt_set_write_cache(struct rq_wb *rwb, bool wc) +static inline void wbt_set_min_lat(struct request_queue *q, u64 val) { } static inline u64 wbt_default_latency_nsec(struct request_queue *q) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 9d05646d5059..137759862f07 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -42,7 +42,7 @@ struct bsg_job; struct blkcg_gq; struct blk_flush_queue; struct pr_ops; -struct rq_wb; +struct rq_qos; struct blk_queue_stats; struct blk_stat_callback; @@ -443,7 +443,7 @@ struct request_queue { int nr_rqs_elvpriv; /* # allocated rqs w/ elvpriv */ struct blk_queue_stats *stats; - struct rq_wb *rq_wb; + struct rq_qos *rq_qos; /* * If blkcg is not used, @q->root_rl serves all requests. If blkcg -- cgit v1.2.3 From d70675121546c35feaceebf7ed9caed8716640f3 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 3 Jul 2018 11:15:01 -0400 Subject: block: introduce blk-iolatency io controller Current IO controllers for the block layer are less than ideal for our use case. The io.max controller is great at hard limiting, but it is not work conserving. This patch introduces io.latency. You provide a latency target for your group and we monitor the io in short windows to make sure we are not exceeding those latency targets. This makes use of the rq-qos infrastructure and works much like the wbt stuff. There are a few differences from wbt - It's bio based, so the latency covers the whole block layer in addition to the actual io. - We will throttle all IO types that comes in here if we need to. - We use the mean latency over the 100ms window. This is because writes can be particularly fast, which could give us a false sense of the impact of other workloads on our protected workload. - By default there's no throttling, we set the queue_depth to INT_MAX so that we can have as many outstanding bio's as we're allowed to. Only at throttle time do we pay attention to the actual queue depth. - We backcharge cgroups for root cg issued IO and induce artificial delays in order to deal with cases like metadata only or swap heavy workloads. In testing this has worked out relatively well. Protected workloads will throttle noisy workloads down to 1 io at time if they are doing normal IO on their own, or induce up to a 1 second delay per syscall if they are doing a lot of root issued IO (metadata/swap IO). Our testing has revolved mostly around our production web servers where we have hhvm (the web server application) in a protected group and everything else in another group. We see slightly higher requests per second (RPS) on the test tier vs the control tier, and much more stable RPS across all machines in the test tier vs the control tier. Another test we run is a slow memory allocator in the unprotected group. Before this would eventually push us into swap and cause the whole box to die and not recover at all. With these patches we see slight RPS drops (usually 10-15%) before the memory consumer is properly killed and things recover within seconds. Signed-off-by: Josef Bacik Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- block/Kconfig | 12 + block/Makefile | 1 + block/blk-cgroup.c | 8 + block/blk-iolatency.c | 930 ++++++++++++++++++++++++++++++++++++++++++++++ block/blk.h | 6 + include/linux/blk_types.h | 2 - 6 files changed, 957 insertions(+), 2 deletions(-) create mode 100644 block/blk-iolatency.c (limited to 'include') diff --git a/block/Kconfig b/block/Kconfig index dfe7bc770fc9..1f2469a0123c 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -149,6 +149,18 @@ config BLK_WBT dynamically on an algorithm loosely based on CoDel, factoring in the realtime performance of the disk. +config BLK_CGROUP_IOLATENCY + bool "Enable support for latency based cgroup IO protection" + depends on BLK_CGROUP=y + default n + ---help--- + Enabling this option enables the .latency interface for IO throttling. + The IO controller will attempt to maintain average IO latencies below + the configured latency target, throttling anybody with a higher latency + target than the victimized group. + + Note, this is an experimental interface and could be changed someday. + config BLK_WBT_SQ bool "Single queue writeback throttling" default n diff --git a/block/Makefile b/block/Makefile index 57d0f47ab05f..572b33f32c07 100644 --- a/block/Makefile +++ b/block/Makefile @@ -17,6 +17,7 @@ obj-$(CONFIG_BLK_DEV_BSG) += bsg.o obj-$(CONFIG_BLK_DEV_BSGLIB) += bsg-lib.o obj-$(CONFIG_BLK_CGROUP) += blk-cgroup.o obj-$(CONFIG_BLK_DEV_THROTTLING) += blk-throttle.o +obj-$(CONFIG_BLK_CGROUP_IOLATENCY) += blk-iolatency.o obj-$(CONFIG_IOSCHED_NOOP) += noop-iosched.o obj-$(CONFIG_IOSCHED_DEADLINE) += deadline-iosched.o obj-$(CONFIG_IOSCHED_CFQ) += cfq-iosched.o diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index d3310ec96c2a..7e2c19ce1a08 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1238,6 +1238,14 @@ int blkcg_init_queue(struct request_queue *q) if (preloaded) radix_tree_preload_end(); + ret = blk_iolatency_init(q); + if (ret) { + spin_lock_irq(q->queue_lock); + blkg_destroy_all(q); + spin_unlock_irq(q->queue_lock); + return ret; + } + ret = blk_throtl_init(q); if (ret) { spin_lock_irq(q->queue_lock); diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c new file mode 100644 index 000000000000..a35a1f580337 --- /dev/null +++ b/block/blk-iolatency.c @@ -0,0 +1,930 @@ +/* + * Block rq-qos base io controller + * + * This works similar to wbt with a few exceptions + * + * - It's bio based, so the latency covers the whole block layer in addition to + * the actual io. + * - We will throttle all IO that comes in here if we need to. + * - We use the mean latency over the 100ms window. This is because writes can + * be particularly fast, which could give us a false sense of the impact of + * other workloads on our protected workload. + * - By default there's no throttling, we set the queue_depth to INT_MAX so that + * we can have as many outstanding bio's as we're allowed to. Only at + * throttle time do we pay attention to the actual queue depth. + * + * The hierarchy works like the cpu controller does, we track the latency at + * every configured node, and each configured node has it's own independent + * queue depth. This means that we only care about our latency targets at the + * peer level. Some group at the bottom of the hierarchy isn't going to affect + * a group at the end of some other path if we're only configred at leaf level. + * + * Consider the following + * + * root blkg + * / \ + * fast (target=5ms) slow (target=10ms) + * / \ / \ + * a b normal(15ms) unloved + * + * "a" and "b" have no target, but their combined io under "fast" cannot exceed + * an average latency of 5ms. If it does then we will throttle the "slow" + * group. In the case of "normal", if it exceeds its 15ms target, we will + * throttle "unloved", but nobody else. + * + * In this example "fast", "slow", and "normal" will be the only groups actually + * accounting their io latencies. We have to walk up the heirarchy to the root + * on every submit and complete so we can do the appropriate stat recording and + * adjust the queue depth of ourselves if needed. + * + * There are 2 ways we throttle IO. + * + * 1) Queue depth throttling. As we throttle down we will adjust the maximum + * number of IO's we're allowed to have in flight. This starts at (u64)-1 down + * to 1. If the group is only ever submitting IO for itself then this is the + * only way we throttle. + * + * 2) Induced delay throttling. This is for the case that a group is generating + * IO that has to be issued by the root cg to avoid priority inversion. So think + * REQ_META or REQ_SWAP. If we are already at qd == 1 and we're getting a lot + * of work done for us on behalf of the root cg and are being asked to scale + * down more then we induce a latency at userspace return. We accumulate the + * total amount of time we need to be punished by doing + * + * total_time += min_lat_nsec - actual_io_completion + * + * and then at throttle time will do + * + * throttle_time = min(total_time, NSEC_PER_SEC) + * + * This induced delay will throttle back the activity that is generating the + * root cg issued io's, wethere that's some metadata intensive operation or the + * group is using so much memory that it is pushing us into swap. + * + * Copyright (C) 2018 Josef Bacik + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include "blk-rq-qos.h" +#include "blk-stat.h" + +#define DEFAULT_SCALE_COOKIE 1000000U + +static struct blkcg_policy blkcg_policy_iolatency; +struct iolatency_grp; + +struct blk_iolatency { + struct rq_qos rqos; + struct timer_list timer; + atomic_t enabled; +}; + +static inline struct blk_iolatency *BLKIOLATENCY(struct rq_qos *rqos) +{ + return container_of(rqos, struct blk_iolatency, rqos); +} + +static inline bool blk_iolatency_enabled(struct blk_iolatency *blkiolat) +{ + return atomic_read(&blkiolat->enabled) > 0; +} + +struct child_latency_info { + spinlock_t lock; + + /* Last time we adjusted the scale of everybody. */ + u64 last_scale_event; + + /* The latency that we missed. */ + u64 scale_lat; + + /* Total io's from all of our children for the last summation. */ + u64 nr_samples; + + /* The guy who actually changed the latency numbers. */ + struct iolatency_grp *scale_grp; + + /* Cookie to tell if we need to scale up or down. */ + atomic_t scale_cookie; +}; + +struct iolatency_grp { + struct blkg_policy_data pd; + struct blk_rq_stat __percpu *stats; + struct blk_iolatency *blkiolat; + struct rq_depth rq_depth; + struct rq_wait rq_wait; + atomic64_t window_start; + atomic_t scale_cookie; + u64 min_lat_nsec; + u64 cur_win_nsec; + + /* total running average of our io latency. */ + u64 total_lat_avg; + u64 total_lat_nr; + + /* Our current number of IO's for the last summation. */ + u64 nr_samples; + + struct child_latency_info child_lat; +}; + +static inline struct iolatency_grp *pd_to_lat(struct blkg_policy_data *pd) +{ + return pd ? container_of(pd, struct iolatency_grp, pd) : NULL; +} + +static inline struct iolatency_grp *blkg_to_lat(struct blkcg_gq *blkg) +{ + return pd_to_lat(blkg_to_pd(blkg, &blkcg_policy_iolatency)); +} + +static inline struct blkcg_gq *lat_to_blkg(struct iolatency_grp *iolat) +{ + return pd_to_blkg(&iolat->pd); +} + +static inline bool iolatency_may_queue(struct iolatency_grp *iolat, + wait_queue_entry_t *wait, + bool first_block) +{ + struct rq_wait *rqw = &iolat->rq_wait; + + if (first_block && waitqueue_active(&rqw->wait) && + rqw->wait.head.next != &wait->entry) + return false; + return rq_wait_inc_below(rqw, iolat->rq_depth.max_depth); +} + +static void __blkcg_iolatency_throttle(struct rq_qos *rqos, + struct iolatency_grp *iolat, + spinlock_t *lock, bool issue_as_root, + bool use_memdelay) + __releases(lock) + __acquires(lock) +{ + struct rq_wait *rqw = &iolat->rq_wait; + unsigned use_delay = atomic_read(&lat_to_blkg(iolat)->use_delay); + DEFINE_WAIT(wait); + bool first_block = true; + + if (use_delay) + blkcg_schedule_throttle(rqos->q, use_memdelay); + + /* + * To avoid priority inversions we want to just take a slot if we are + * issuing as root. If we're being killed off there's no point in + * delaying things, we may have been killed by OOM so throttling may + * make recovery take even longer, so just let the IO's through so the + * task can go away. + */ + if (issue_as_root || fatal_signal_pending(current)) { + atomic_inc(&rqw->inflight); + return; + } + + if (iolatency_may_queue(iolat, &wait, first_block)) + return; + + do { + prepare_to_wait_exclusive(&rqw->wait, &wait, + TASK_UNINTERRUPTIBLE); + + if (iolatency_may_queue(iolat, &wait, first_block)) + break; + first_block = false; + + if (lock) { + spin_unlock_irq(lock); + io_schedule(); + spin_lock_irq(lock); + } else { + io_schedule(); + } + } while (1); + + finish_wait(&rqw->wait, &wait); +} + +#define SCALE_DOWN_FACTOR 2 +#define SCALE_UP_FACTOR 4 + +static inline unsigned long scale_amount(unsigned long qd, bool up) +{ + return max(up ? qd >> SCALE_UP_FACTOR : qd >> SCALE_DOWN_FACTOR, 1UL); +} + +/* + * We scale the qd down faster than we scale up, so we need to use this helper + * to adjust the scale_cookie accordingly so we don't prematurely get + * scale_cookie at DEFAULT_SCALE_COOKIE and unthrottle too much. + * + * Each group has their own local copy of the last scale cookie they saw, so if + * the global scale cookie goes up or down they know which way they need to go + * based on their last knowledge of it. + */ +static void scale_cookie_change(struct blk_iolatency *blkiolat, + struct child_latency_info *lat_info, + bool up) +{ + unsigned long qd = blk_queue_depth(blkiolat->rqos.q); + unsigned long scale = scale_amount(qd, up); + unsigned long old = atomic_read(&lat_info->scale_cookie); + unsigned long max_scale = qd << 1; + unsigned long diff = 0; + + if (old < DEFAULT_SCALE_COOKIE) + diff = DEFAULT_SCALE_COOKIE - old; + + if (up) { + if (scale + old > DEFAULT_SCALE_COOKIE) + atomic_set(&lat_info->scale_cookie, + DEFAULT_SCALE_COOKIE); + else if (diff > qd) + atomic_inc(&lat_info->scale_cookie); + else + atomic_add(scale, &lat_info->scale_cookie); + } else { + /* + * We don't want to dig a hole so deep that it takes us hours to + * dig out of it. Just enough that we don't throttle/unthrottle + * with jagged workloads but can still unthrottle once pressure + * has sufficiently dissipated. + */ + if (diff > qd) { + if (diff < max_scale) + atomic_dec(&lat_info->scale_cookie); + } else { + atomic_sub(scale, &lat_info->scale_cookie); + } + } +} + +/* + * Change the queue depth of the iolatency_grp. We add/subtract 1/16th of the + * queue depth at a time so we don't get wild swings and hopefully dial in to + * fairer distribution of the overall queue depth. + */ +static void scale_change(struct iolatency_grp *iolat, bool up) +{ + unsigned long qd = blk_queue_depth(iolat->blkiolat->rqos.q); + unsigned long scale = scale_amount(qd, up); + unsigned long old = iolat->rq_depth.max_depth; + bool changed = false; + + if (old > qd) + old = qd; + + if (up) { + if (old == 1 && blkcg_unuse_delay(lat_to_blkg(iolat))) + return; + + if (old < qd) { + changed = true; + old += scale; + old = min(old, qd); + iolat->rq_depth.max_depth = old; + wake_up_all(&iolat->rq_wait.wait); + } + } else if (old > 1) { + old >>= 1; + changed = true; + iolat->rq_depth.max_depth = max(old, 1UL); + } +} + +/* Check our parent and see if the scale cookie has changed. */ +static void check_scale_change(struct iolatency_grp *iolat) +{ + struct iolatency_grp *parent; + struct child_latency_info *lat_info; + unsigned int cur_cookie; + unsigned int our_cookie = atomic_read(&iolat->scale_cookie); + u64 scale_lat; + unsigned int old; + int direction = 0; + + if (lat_to_blkg(iolat)->parent == NULL) + return; + + parent = blkg_to_lat(lat_to_blkg(iolat)->parent); + if (!parent) + return; + + lat_info = &parent->child_lat; + cur_cookie = atomic_read(&lat_info->scale_cookie); + scale_lat = READ_ONCE(lat_info->scale_lat); + + if (cur_cookie < our_cookie) + direction = -1; + else if (cur_cookie > our_cookie) + direction = 1; + else + return; + + old = atomic_cmpxchg(&iolat->scale_cookie, our_cookie, cur_cookie); + + /* Somebody beat us to the punch, just bail. */ + if (old != our_cookie) + return; + + if (direction < 0 && iolat->min_lat_nsec) { + u64 samples_thresh; + + if (!scale_lat || iolat->min_lat_nsec <= scale_lat) + return; + + /* + * Sometimes high priority groups are their own worst enemy, so + * instead of taking it out on some poor other group that did 5% + * or less of the IO's for the last summation just skip this + * scale down event. + */ + samples_thresh = lat_info->nr_samples * 5; + samples_thresh = div64_u64(samples_thresh, 100); + if (iolat->nr_samples <= samples_thresh) + return; + } + + /* We're as low as we can go. */ + if (iolat->rq_depth.max_depth == 1 && direction < 0) { + blkcg_use_delay(lat_to_blkg(iolat)); + return; + } + + /* We're back to the default cookie, unthrottle all the things. */ + if (cur_cookie == DEFAULT_SCALE_COOKIE) { + blkcg_clear_delay(lat_to_blkg(iolat)); + iolat->rq_depth.max_depth = INT_MAX; + wake_up_all(&iolat->rq_wait.wait); + return; + } + + scale_change(iolat, direction > 0); +} + +static void blkcg_iolatency_throttle(struct rq_qos *rqos, struct bio *bio, + spinlock_t *lock) +{ + struct blk_iolatency *blkiolat = BLKIOLATENCY(rqos); + struct blkcg *blkcg; + struct blkcg_gq *blkg; + struct request_queue *q = rqos->q; + bool issue_as_root = bio_issue_as_root_blkg(bio); + + if (!blk_iolatency_enabled(blkiolat)) + return; + + rcu_read_lock(); + blkcg = bio_blkcg(bio); + bio_associate_blkcg(bio, &blkcg->css); + blkg = blkg_lookup(blkcg, q); + if (unlikely(!blkg)) { + if (!lock) + spin_lock_irq(q->queue_lock); + blkg = blkg_lookup_create(blkcg, q); + if (IS_ERR(blkg)) + blkg = NULL; + if (!lock) + spin_unlock_irq(q->queue_lock); + } + if (!blkg) + goto out; + + bio_issue_init(&bio->bi_issue, bio_sectors(bio)); + bio_associate_blkg(bio, blkg); +out: + rcu_read_unlock(); + while (blkg && blkg->parent) { + struct iolatency_grp *iolat = blkg_to_lat(blkg); + if (!iolat) { + blkg = blkg->parent; + continue; + } + + check_scale_change(iolat); + __blkcg_iolatency_throttle(rqos, iolat, lock, issue_as_root, + (bio->bi_opf & REQ_SWAP) == REQ_SWAP); + blkg = blkg->parent; + } + if (!timer_pending(&blkiolat->timer)) + mod_timer(&blkiolat->timer, jiffies + HZ); +} + +static void iolatency_record_time(struct iolatency_grp *iolat, + struct bio_issue *issue, u64 now, + bool issue_as_root) +{ + struct blk_rq_stat *rq_stat; + u64 start = bio_issue_time(issue); + u64 req_time; + + if (now <= start) + return; + + req_time = now - start; + + /* + * We don't want to count issue_as_root bio's in the cgroups latency + * statistics as it could skew the numbers downwards. + */ + if (unlikely(issue_as_root && iolat->rq_depth.max_depth != (u64)-1)) { + u64 sub = iolat->min_lat_nsec; + if (req_time < sub) + blkcg_add_delay(lat_to_blkg(iolat), now, sub - req_time); + return; + } + + rq_stat = get_cpu_ptr(iolat->stats); + blk_rq_stat_add(rq_stat, req_time); + put_cpu_ptr(rq_stat); +} + +#define BLKIOLATENCY_MIN_ADJUST_TIME (500 * NSEC_PER_MSEC) +#define BLKIOLATENCY_MIN_GOOD_SAMPLES 5 + +static void iolatency_check_latencies(struct iolatency_grp *iolat, u64 now) +{ + struct blkcg_gq *blkg = lat_to_blkg(iolat); + struct iolatency_grp *parent; + struct child_latency_info *lat_info; + struct blk_rq_stat stat; + unsigned long flags; + int cpu; + + blk_rq_stat_init(&stat); + preempt_disable(); + for_each_online_cpu(cpu) { + struct blk_rq_stat *s; + s = per_cpu_ptr(iolat->stats, cpu); + blk_rq_stat_sum(&stat, s); + blk_rq_stat_init(s); + } + preempt_enable(); + + /* + * Our average exceeded our window, scale up our window so we are more + * accurate, but not more than the global timer. + */ + if (stat.mean > iolat->cur_win_nsec) { + iolat->cur_win_nsec <<= 1; + iolat->cur_win_nsec = + max_t(u64, iolat->cur_win_nsec, NSEC_PER_SEC); + } + + parent = blkg_to_lat(blkg->parent); + if (!parent) + return; + + lat_info = &parent->child_lat; + + iolat->total_lat_avg = + div64_u64((iolat->total_lat_avg * iolat->total_lat_nr) + + stat.mean, iolat->total_lat_nr + 1); + + iolat->total_lat_nr++; + + /* Everything is ok and we don't need to adjust the scale. */ + if (stat.mean <= iolat->min_lat_nsec && + atomic_read(&lat_info->scale_cookie) == DEFAULT_SCALE_COOKIE) + return; + + /* Somebody beat us to the punch, just bail. */ + spin_lock_irqsave(&lat_info->lock, flags); + lat_info->nr_samples -= iolat->nr_samples; + lat_info->nr_samples += stat.nr_samples; + iolat->nr_samples = stat.nr_samples; + + if ((lat_info->last_scale_event >= now || + now - lat_info->last_scale_event < BLKIOLATENCY_MIN_ADJUST_TIME) && + lat_info->scale_lat <= iolat->min_lat_nsec) + goto out; + + if (stat.mean <= iolat->min_lat_nsec && + stat.nr_samples >= BLKIOLATENCY_MIN_GOOD_SAMPLES) { + if (lat_info->scale_grp == iolat) { + lat_info->last_scale_event = now; + scale_cookie_change(iolat->blkiolat, lat_info, true); + } + } else if (stat.mean > iolat->min_lat_nsec) { + lat_info->last_scale_event = now; + if (!lat_info->scale_grp || + lat_info->scale_lat > iolat->min_lat_nsec) { + WRITE_ONCE(lat_info->scale_lat, iolat->min_lat_nsec); + lat_info->scale_grp = iolat; + } + scale_cookie_change(iolat->blkiolat, lat_info, false); + } +out: + spin_unlock_irqrestore(&lat_info->lock, flags); +} + +static void blkcg_iolatency_done_bio(struct rq_qos *rqos, struct bio *bio) +{ + struct blkcg_gq *blkg; + struct rq_wait *rqw; + struct iolatency_grp *iolat; + u64 window_start; + u64 now = ktime_to_ns(ktime_get()); + bool issue_as_root = bio_issue_as_root_blkg(bio); + bool enabled = false; + + blkg = bio->bi_blkg; + if (!blkg) + return; + + iolat = blkg_to_lat(bio->bi_blkg); + if (!iolat) + return; + + enabled = blk_iolatency_enabled(iolat->blkiolat); + while (blkg && blkg->parent) { + iolat = blkg_to_lat(blkg); + if (!iolat) { + blkg = blkg->parent; + continue; + } + rqw = &iolat->rq_wait; + + atomic_dec(&rqw->inflight); + if (!enabled || iolat->min_lat_nsec == 0) + goto next; + iolatency_record_time(iolat, &bio->bi_issue, now, + issue_as_root); + window_start = atomic64_read(&iolat->window_start); + if (now > window_start && + (now - window_start) >= iolat->cur_win_nsec) { + if (atomic64_cmpxchg(&iolat->window_start, + window_start, now) == window_start) + iolatency_check_latencies(iolat, now); + } +next: + wake_up(&rqw->wait); + blkg = blkg->parent; + } +} + +static void blkcg_iolatency_cleanup(struct rq_qos *rqos, struct bio *bio) +{ + struct blkcg_gq *blkg; + + blkg = bio->bi_blkg; + while (blkg && blkg->parent) { + struct rq_wait *rqw; + struct iolatency_grp *iolat; + + iolat = blkg_to_lat(blkg); + if (!iolat) + goto next; + + rqw = &iolat->rq_wait; + atomic_dec(&rqw->inflight); + wake_up(&rqw->wait); +next: + blkg = blkg->parent; + } +} + +static void blkcg_iolatency_exit(struct rq_qos *rqos) +{ + struct blk_iolatency *blkiolat = BLKIOLATENCY(rqos); + + del_timer_sync(&blkiolat->timer); + blkcg_deactivate_policy(rqos->q, &blkcg_policy_iolatency); + kfree(blkiolat); +} + +static struct rq_qos_ops blkcg_iolatency_ops = { + .throttle = blkcg_iolatency_throttle, + .cleanup = blkcg_iolatency_cleanup, + .done_bio = blkcg_iolatency_done_bio, + .exit = blkcg_iolatency_exit, +}; + +static void blkiolatency_timer_fn(struct timer_list *t) +{ + struct blk_iolatency *blkiolat = from_timer(blkiolat, t, timer); + struct blkcg_gq *blkg; + struct cgroup_subsys_state *pos_css; + u64 now = ktime_to_ns(ktime_get()); + + rcu_read_lock(); + blkg_for_each_descendant_pre(blkg, pos_css, + blkiolat->rqos.q->root_blkg) { + struct iolatency_grp *iolat; + struct child_latency_info *lat_info; + unsigned long flags; + u64 cookie; + + /* + * We could be exiting, don't access the pd unless we have a + * ref on the blkg. + */ + if (!blkg_try_get(blkg)) + continue; + + iolat = blkg_to_lat(blkg); + if (!iolat) + continue; + + lat_info = &iolat->child_lat; + cookie = atomic_read(&lat_info->scale_cookie); + + if (cookie >= DEFAULT_SCALE_COOKIE) + goto next; + + spin_lock_irqsave(&lat_info->lock, flags); + if (lat_info->last_scale_event >= now) + goto next_lock; + + /* + * We scaled down but don't have a scale_grp, scale up and carry + * on. + */ + if (lat_info->scale_grp == NULL) { + scale_cookie_change(iolat->blkiolat, lat_info, true); + goto next_lock; + } + + /* + * It's been 5 seconds since our last scale event, clear the + * scale grp in case the group that needed the scale down isn't + * doing any IO currently. + */ + if (now - lat_info->last_scale_event >= + ((u64)NSEC_PER_SEC * 5)) + lat_info->scale_grp = NULL; +next_lock: + spin_unlock_irqrestore(&lat_info->lock, flags); +next: + blkg_put(blkg); + } + rcu_read_unlock(); +} + +int blk_iolatency_init(struct request_queue *q) +{ + struct blk_iolatency *blkiolat; + struct rq_qos *rqos; + int ret; + + blkiolat = kzalloc(sizeof(*blkiolat), GFP_KERNEL); + if (!blkiolat) + return -ENOMEM; + + rqos = &blkiolat->rqos; + rqos->id = RQ_QOS_CGROUP; + rqos->ops = &blkcg_iolatency_ops; + rqos->q = q; + + rq_qos_add(q, rqos); + + ret = blkcg_activate_policy(q, &blkcg_policy_iolatency); + if (ret) { + rq_qos_del(q, rqos); + kfree(blkiolat); + return ret; + } + + timer_setup(&blkiolat->timer, blkiolatency_timer_fn, 0); + + return 0; +} + +static void iolatency_set_min_lat_nsec(struct blkcg_gq *blkg, u64 val) +{ + struct iolatency_grp *iolat = blkg_to_lat(blkg); + struct blk_iolatency *blkiolat = iolat->blkiolat; + u64 oldval = iolat->min_lat_nsec; + + iolat->min_lat_nsec = val; + iolat->cur_win_nsec = max_t(u64, val << 4, 100 * NSEC_PER_MSEC); + iolat->cur_win_nsec = min_t(u64, iolat->cur_win_nsec, NSEC_PER_SEC); + + if (!oldval && val) + atomic_inc(&blkiolat->enabled); + if (oldval && !val) + atomic_dec(&blkiolat->enabled); +} + +static void iolatency_clear_scaling(struct blkcg_gq *blkg) +{ + if (blkg->parent) { + struct iolatency_grp *iolat = blkg_to_lat(blkg->parent); + struct child_latency_info *lat_info; + if (!iolat) + return; + + lat_info = &iolat->child_lat; + spin_lock(&lat_info->lock); + atomic_set(&lat_info->scale_cookie, DEFAULT_SCALE_COOKIE); + lat_info->last_scale_event = 0; + lat_info->scale_grp = NULL; + lat_info->scale_lat = 0; + spin_unlock(&lat_info->lock); + } +} + +static ssize_t iolatency_set_limit(struct kernfs_open_file *of, char *buf, + size_t nbytes, loff_t off) +{ + struct blkcg *blkcg = css_to_blkcg(of_css(of)); + struct blkcg_gq *blkg; + struct blk_iolatency *blkiolat; + struct blkg_conf_ctx ctx; + struct iolatency_grp *iolat; + char *p, *tok; + u64 lat_val = 0; + u64 oldval; + int ret; + + ret = blkg_conf_prep(blkcg, &blkcg_policy_iolatency, buf, &ctx); + if (ret) + return ret; + + iolat = blkg_to_lat(ctx.blkg); + blkiolat = iolat->blkiolat; + p = ctx.body; + + ret = -EINVAL; + while ((tok = strsep(&p, " "))) { + char key[16]; + char val[21]; /* 18446744073709551616 */ + + if (sscanf(tok, "%15[^=]=%20s", key, val) != 2) + goto out; + + if (!strcmp(key, "target")) { + u64 v; + + if (!strcmp(val, "max")) + lat_val = 0; + else if (sscanf(val, "%llu", &v) == 1) + lat_val = v * NSEC_PER_USEC; + else + goto out; + } else { + goto out; + } + } + + /* Walk up the tree to see if our new val is lower than it should be. */ + blkg = ctx.blkg; + oldval = iolat->min_lat_nsec; + + iolatency_set_min_lat_nsec(blkg, lat_val); + if (oldval != iolat->min_lat_nsec) { + iolatency_clear_scaling(blkg); + } + + ret = 0; +out: + blkg_conf_finish(&ctx); + return ret ?: nbytes; +} + +static u64 iolatency_prfill_limit(struct seq_file *sf, + struct blkg_policy_data *pd, int off) +{ + struct iolatency_grp *iolat = pd_to_lat(pd); + const char *dname = blkg_dev_name(pd->blkg); + + if (!dname || !iolat->min_lat_nsec) + return 0; + seq_printf(sf, "%s target=%llu\n", + dname, + (unsigned long long)iolat->min_lat_nsec / NSEC_PER_USEC); + return 0; +} + +static int iolatency_print_limit(struct seq_file *sf, void *v) +{ + blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), + iolatency_prfill_limit, + &blkcg_policy_iolatency, seq_cft(sf)->private, false); + return 0; +} + +static size_t iolatency_pd_stat(struct blkg_policy_data *pd, char *buf, + size_t size) +{ + struct iolatency_grp *iolat = pd_to_lat(pd); + unsigned long long avg_lat = div64_u64(iolat->total_lat_avg, NSEC_PER_USEC); + + if (iolat->rq_depth.max_depth == (u64)-1) + return scnprintf(buf, size, " depth=max avg_lat=%llu", + avg_lat); + + return scnprintf(buf, size, " depth=%u avg_lat=%llu", + iolat->rq_depth.max_depth, avg_lat); +} + + +static struct blkg_policy_data *iolatency_pd_alloc(gfp_t gfp, int node) +{ + struct iolatency_grp *iolat; + + iolat = kzalloc_node(sizeof(*iolat), gfp, node); + if (!iolat) + return NULL; + iolat->stats = __alloc_percpu_gfp(sizeof(struct blk_rq_stat), + __alignof__(struct blk_rq_stat), gfp); + if (!iolat->stats) { + kfree(iolat); + return NULL; + } + return &iolat->pd; +} + +static void iolatency_pd_init(struct blkg_policy_data *pd) +{ + struct iolatency_grp *iolat = pd_to_lat(pd); + struct blkcg_gq *blkg = lat_to_blkg(iolat); + struct rq_qos *rqos = blkcg_rq_qos(blkg->q); + struct blk_iolatency *blkiolat = BLKIOLATENCY(rqos); + u64 now = ktime_to_ns(ktime_get()); + int cpu; + + for_each_possible_cpu(cpu) { + struct blk_rq_stat *stat; + stat = per_cpu_ptr(iolat->stats, cpu); + blk_rq_stat_init(stat); + } + + rq_wait_init(&iolat->rq_wait); + spin_lock_init(&iolat->child_lat.lock); + iolat->rq_depth.queue_depth = blk_queue_depth(blkg->q); + iolat->rq_depth.max_depth = INT_MAX; + iolat->rq_depth.default_depth = iolat->rq_depth.queue_depth; + iolat->blkiolat = blkiolat; + iolat->cur_win_nsec = 100 * NSEC_PER_MSEC; + atomic64_set(&iolat->window_start, now); + + /* + * We init things in list order, so the pd for the parent may not be + * init'ed yet for whatever reason. + */ + if (blkg->parent && blkg_to_pd(blkg->parent, &blkcg_policy_iolatency)) { + struct iolatency_grp *parent = blkg_to_lat(blkg->parent); + atomic_set(&iolat->scale_cookie, + atomic_read(&parent->child_lat.scale_cookie)); + } else { + atomic_set(&iolat->scale_cookie, DEFAULT_SCALE_COOKIE); + } + + atomic_set(&iolat->child_lat.scale_cookie, DEFAULT_SCALE_COOKIE); +} + +static void iolatency_pd_offline(struct blkg_policy_data *pd) +{ + struct iolatency_grp *iolat = pd_to_lat(pd); + struct blkcg_gq *blkg = lat_to_blkg(iolat); + + iolatency_set_min_lat_nsec(blkg, 0); + iolatency_clear_scaling(blkg); +} + +static void iolatency_pd_free(struct blkg_policy_data *pd) +{ + struct iolatency_grp *iolat = pd_to_lat(pd); + free_percpu(iolat->stats); + kfree(iolat); +} + +static struct cftype iolatency_files[] = { + { + .name = "latency", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = iolatency_print_limit, + .write = iolatency_set_limit, + }, + {} +}; + +static struct blkcg_policy blkcg_policy_iolatency = { + .dfl_cftypes = iolatency_files, + .pd_alloc_fn = iolatency_pd_alloc, + .pd_init_fn = iolatency_pd_init, + .pd_offline_fn = iolatency_pd_offline, + .pd_free_fn = iolatency_pd_free, + .pd_stat_fn = iolatency_pd_stat, +}; + +static int __init iolatency_init(void) +{ + return blkcg_policy_register(&blkcg_policy_iolatency); +} + +static void __exit iolatency_exit(void) +{ + return blkcg_policy_unregister(&blkcg_policy_iolatency); +} + +module_init(iolatency_init); +module_exit(iolatency_exit); diff --git a/block/blk.h b/block/blk.h index 8d23aea96ce9..69b14cd2bb22 100644 --- a/block/blk.h +++ b/block/blk.h @@ -412,4 +412,10 @@ static inline void blk_queue_bounce(struct request_queue *q, struct bio **bio) extern void blk_drain_queue(struct request_queue *q); +#ifdef CONFIG_BLK_CGROUP_IOLATENCY +extern int blk_iolatency_init(struct request_queue *q); +#else +static inline int blk_iolatency_init(struct request_queue *q) { return 0; } +#endif + #endif /* BLK_INTERNAL_H */ diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 0ffc34c5cc83..e13449a379a1 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -180,9 +180,7 @@ struct bio { struct io_context *bi_ioc; struct cgroup_subsys_state *bi_css; struct blkcg_gq *bi_blkg; -#ifdef CONFIG_BLK_DEV_THROTTLING_LOW struct bio_issue bi_issue; -#endif #endif union { #if defined(CONFIG_BLK_DEV_INTEGRITY) -- cgit v1.2.3 From ffcfe25bb50f27395e15fa999f1a7eb769f55360 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 9 Jul 2018 12:19:38 -0400 Subject: net: Add support for subordinate device traffic classes This patch is meant to provide the basic tools needed to allow us to create subordinate device traffic classes. The general idea here is to allow subdividing the queues of a device into queue groups accessible through an upper device such as a macvlan. The idea here is to enforce the idea that an upper device has to be a single queue device, ideally with IFF_NO_QUQUE set. With that being the case we can pretty much guarantee that the tc_to_txq mappings and XPS maps for the upper device are unused. As such we could reuse those in order to support subdividing the lower device and distributing those queues between the subordinate devices. In order to distinguish between a regular set of traffic classes and if a device is carrying subordinate traffic classes I changed num_tc from a u8 to a s16 value and use the negative values to represent the subordinate pool values. So starting at -1 and running to -32768 we can encode those as pool values, and the existing values of 0 to 15 can be maintained. Signed-off-by: Alexander Duyck Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- include/linux/netdevice.h | 16 ++++++++- net/core/dev.c | 89 +++++++++++++++++++++++++++++++++++++++++++++++ net/core/net-sysfs.c | 21 ++++++++++- 3 files changed, 124 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b683971e500d..b1ff77276bc4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -575,6 +575,9 @@ struct netdev_queue { * (/sys/class/net/DEV/Q/trans_timeout) */ unsigned long trans_timeout; + + /* Subordinate device that the queue has been assigned to */ + struct net_device *sb_dev; /* * write-mostly part */ @@ -1991,7 +1994,7 @@ struct net_device { #ifdef CONFIG_DCB const struct dcbnl_rtnl_ops *dcbnl_ops; #endif - u8 num_tc; + s16 num_tc; struct netdev_tc_txq tc_to_txq[TC_MAX_QUEUE]; u8 prio_tc_map[TC_BITMASK + 1]; @@ -2045,6 +2048,17 @@ int netdev_get_num_tc(struct net_device *dev) return dev->num_tc; } +void netdev_unbind_sb_channel(struct net_device *dev, + struct net_device *sb_dev); +int netdev_bind_sb_channel_queue(struct net_device *dev, + struct net_device *sb_dev, + u8 tc, u16 count, u16 offset); +int netdev_set_sb_channel(struct net_device *dev, u16 channel); +static inline int netdev_get_sb_channel(struct net_device *dev) +{ + return max_t(int, -dev->num_tc, 0); +} + static inline struct netdev_queue *netdev_get_tx_queue(const struct net_device *dev, unsigned int index) diff --git a/net/core/dev.c b/net/core/dev.c index 89825c1eccdc..cc1d6bba017a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2067,11 +2067,13 @@ int netdev_txq_to_tc(struct net_device *dev, unsigned int txq) struct netdev_tc_txq *tc = &dev->tc_to_txq[0]; int i; + /* walk through the TCs and see if it falls into any of them */ for (i = 0; i < TC_MAX_QUEUE; i++, tc++) { if ((txq - tc->offset) < tc->count) return i; } + /* didn't find it, just return -1 to indicate no match */ return -1; } @@ -2260,7 +2262,14 @@ int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask, unsigned int nr_ids; if (dev->num_tc) { + /* Do not allow XPS on subordinate device directly */ num_tc = dev->num_tc; + if (num_tc < 0) + return -EINVAL; + + /* If queue belongs to subordinate dev use its map */ + dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev; + tc = netdev_txq_to_tc(dev, index); if (tc < 0) return -EINVAL; @@ -2448,11 +2457,25 @@ int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, EXPORT_SYMBOL(netif_set_xps_queue); #endif +static void netdev_unbind_all_sb_channels(struct net_device *dev) +{ + struct netdev_queue *txq = &dev->_tx[dev->num_tx_queues]; + + /* Unbind any subordinate channels */ + while (txq-- != &dev->_tx[0]) { + if (txq->sb_dev) + netdev_unbind_sb_channel(dev, txq->sb_dev); + } +} + void netdev_reset_tc(struct net_device *dev) { #ifdef CONFIG_XPS netif_reset_xps_queues_gt(dev, 0); #endif + netdev_unbind_all_sb_channels(dev); + + /* Reset TC configuration of device */ dev->num_tc = 0; memset(dev->tc_to_txq, 0, sizeof(dev->tc_to_txq)); memset(dev->prio_tc_map, 0, sizeof(dev->prio_tc_map)); @@ -2481,11 +2504,77 @@ int netdev_set_num_tc(struct net_device *dev, u8 num_tc) #ifdef CONFIG_XPS netif_reset_xps_queues_gt(dev, 0); #endif + netdev_unbind_all_sb_channels(dev); + dev->num_tc = num_tc; return 0; } EXPORT_SYMBOL(netdev_set_num_tc); +void netdev_unbind_sb_channel(struct net_device *dev, + struct net_device *sb_dev) +{ + struct netdev_queue *txq = &dev->_tx[dev->num_tx_queues]; + +#ifdef CONFIG_XPS + netif_reset_xps_queues_gt(sb_dev, 0); +#endif + memset(sb_dev->tc_to_txq, 0, sizeof(sb_dev->tc_to_txq)); + memset(sb_dev->prio_tc_map, 0, sizeof(sb_dev->prio_tc_map)); + + while (txq-- != &dev->_tx[0]) { + if (txq->sb_dev == sb_dev) + txq->sb_dev = NULL; + } +} +EXPORT_SYMBOL(netdev_unbind_sb_channel); + +int netdev_bind_sb_channel_queue(struct net_device *dev, + struct net_device *sb_dev, + u8 tc, u16 count, u16 offset) +{ + /* Make certain the sb_dev and dev are already configured */ + if (sb_dev->num_tc >= 0 || tc >= dev->num_tc) + return -EINVAL; + + /* We cannot hand out queues we don't have */ + if ((offset + count) > dev->real_num_tx_queues) + return -EINVAL; + + /* Record the mapping */ + sb_dev->tc_to_txq[tc].count = count; + sb_dev->tc_to_txq[tc].offset = offset; + + /* Provide a way for Tx queue to find the tc_to_txq map or + * XPS map for itself. + */ + while (count--) + netdev_get_tx_queue(dev, count + offset)->sb_dev = sb_dev; + + return 0; +} +EXPORT_SYMBOL(netdev_bind_sb_channel_queue); + +int netdev_set_sb_channel(struct net_device *dev, u16 channel) +{ + /* Do not use a multiqueue device to represent a subordinate channel */ + if (netif_is_multiqueue(dev)) + return -ENODEV; + + /* We allow channels 1 - 32767 to be used for subordinate channels. + * Channel 0 is meant to be "native" mode and used only to represent + * the main root device. We allow writing 0 to reset the device back + * to normal mode after being used as a subordinate channel. + */ + if (channel > S16_MAX) + return -EINVAL; + + dev->num_tc = -channel; + + return 0; +} +EXPORT_SYMBOL(netdev_set_sb_channel); + /* * Routine to help set real_num_tx_queues. To avoid skbs mapped to queues * greater than real_num_tx_queues stale skbs on the qdisc must be flushed. diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index dce3ae0fbca2..ffa1d18f2c2c 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -1054,11 +1054,23 @@ static ssize_t traffic_class_show(struct netdev_queue *queue, return -ENOENT; index = get_netdev_queue_index(queue); + + /* If queue belongs to subordinate dev use its TC mapping */ + dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev; + tc = netdev_txq_to_tc(dev, index); if (tc < 0) return -EINVAL; - return sprintf(buf, "%u\n", tc); + /* We can report the traffic class one of two ways: + * Subordinate device traffic classes are reported with the traffic + * class first, and then the subordinate class so for example TC0 on + * subordinate device 2 will be reported as "0-2". If the queue + * belongs to the root device it will be reported with just the + * traffic class, so just "0" for TC 0 for example. + */ + return dev->num_tc < 0 ? sprintf(buf, "%u%d\n", tc, dev->num_tc) : + sprintf(buf, "%u\n", tc); } #ifdef CONFIG_XPS @@ -1225,7 +1237,14 @@ static ssize_t xps_cpus_show(struct netdev_queue *queue, index = get_netdev_queue_index(queue); if (dev->num_tc) { + /* Do not allow XPS on subordinate device directly */ num_tc = dev->num_tc; + if (num_tc < 0) + return -EINVAL; + + /* If queue belongs to subordinate dev use its map */ + dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev; + tc = netdev_txq_to_tc(dev, index); if (tc < 0) return -EINVAL; -- cgit v1.2.3 From eadec877ce9ca46a94e9036b5a44e7941d4fc501 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 9 Jul 2018 12:19:48 -0400 Subject: net: Add support for subordinate traffic classes to netdev_pick_tx This change makes it so that we can support the concept of subordinate device traffic classes to the core networking code. In doing this we can start pulling out the driver specific bits needed to support selecting a queue based on an upper device. The solution at is currently stands is only partially implemented. I have the start of some XPS bits in here, but I would still need to allow for configuration of the XPS maps on the queues reserved for the subordinate devices. For now I am using the reference to the sb_dev XPS map as just a way to skip the lookup of the lower device XPS map for now as that would result in the wrong queue being picked. Signed-off-by: Alexander Duyck Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 19 +++------ drivers/net/macvlan.c | 10 +---- include/linux/netdevice.h | 4 +- net/core/dev.c | 58 ++++++++++++++++----------- 4 files changed, 45 insertions(+), 46 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 80225af2acb1..abb176df2e7f 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -8208,20 +8208,17 @@ static void ixgbe_atr(struct ixgbe_ring *ring, input, common, ring->queue_index); } +#ifdef IXGBE_FCOE static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb, void *accel_priv, select_queue_fallback_t fallback) { - struct ixgbe_fwd_adapter *fwd_adapter = accel_priv; -#ifdef IXGBE_FCOE struct ixgbe_adapter *adapter; struct ixgbe_ring_feature *f; -#endif int txq; - if (fwd_adapter) { - u8 tc = netdev_get_num_tc(dev) ? - netdev_get_prio_tc_map(dev, skb->priority) : 0; - struct net_device *vdev = fwd_adapter->netdev; + if (accel_priv) { + u8 tc = netdev_get_prio_tc_map(dev, skb->priority); + struct net_device *vdev = accel_priv; txq = vdev->tc_to_txq[tc].offset; txq += reciprocal_scale(skb_get_hash(skb), @@ -8230,8 +8227,6 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb, return txq; } -#ifdef IXGBE_FCOE - /* * only execute the code below if protocol is FCoE * or FIP and we have FCoE enabled on the adapter @@ -8257,11 +8252,9 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb, txq -= f->indices; return txq + f->offset; -#else - return fallback(dev, skb); -#endif } +#endif static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter, struct xdp_frame *xdpf) { @@ -10058,7 +10051,6 @@ static const struct net_device_ops ixgbe_netdev_ops = { .ndo_open = ixgbe_open, .ndo_stop = ixgbe_close, .ndo_start_xmit = ixgbe_xmit_frame, - .ndo_select_queue = ixgbe_select_queue, .ndo_set_rx_mode = ixgbe_set_rx_mode, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = ixgbe_set_mac, @@ -10081,6 +10073,7 @@ static const struct net_device_ops ixgbe_netdev_ops = { .ndo_poll_controller = ixgbe_netpoll, #endif #ifdef IXGBE_FCOE + .ndo_select_queue = ixgbe_select_queue, .ndo_fcoe_ddp_setup = ixgbe_fcoe_ddp_get, .ndo_fcoe_ddp_target = ixgbe_fcoe_ddp_target, .ndo_fcoe_ddp_done = ixgbe_fcoe_ddp_put, diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index adde8fc45588..401e1d1ce1ec 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -514,7 +514,6 @@ static int macvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev) const struct macvlan_dev *vlan = netdev_priv(dev); const struct macvlan_port *port = vlan->port; const struct macvlan_dev *dest; - void *accel_priv = NULL; if (vlan->mode == MACVLAN_MODE_BRIDGE) { const struct ethhdr *eth = (void *)skb->data; @@ -533,15 +532,10 @@ static int macvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev) return NET_XMIT_SUCCESS; } } - - /* For packets that are non-multicast and not bridged we will pass - * the necessary information so that the lowerdev can distinguish - * the source of the packets via the accel_priv value. - */ - accel_priv = vlan->accel_priv; xmit_world: skb->dev = vlan->lowerdev; - return dev_queue_xmit_accel(skb, accel_priv); + return dev_queue_xmit_accel(skb, + netdev_get_sb_channel(dev) ? dev : NULL); } static inline netdev_tx_t macvlan_netpoll_send_skb(struct macvlan_dev *vlan, struct sk_buff *skb) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b1ff77276bc4..fda0bcda7a42 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2103,7 +2103,7 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev, struct netdev_queue *netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, - void *accel_priv); + struct net_device *sb_dev); /* returns the headroom that the master device needs to take in account * when forwarding to this dev @@ -2568,7 +2568,7 @@ void dev_close_many(struct list_head *head, bool unlink); void dev_disable_lro(struct net_device *dev); int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb); int dev_queue_xmit(struct sk_buff *skb); -int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv); +int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev); int dev_direct_xmit(struct sk_buff *skb, u16 queue_id); int register_netdevice(struct net_device *dev); void unregister_netdevice_queue(struct net_device *dev, struct list_head *head); diff --git a/net/core/dev.c b/net/core/dev.c index cc1d6bba017a..09a7cc2f3c55 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2786,24 +2786,26 @@ EXPORT_SYMBOL(netif_device_attach); * Returns a Tx hash based on the given packet descriptor a Tx queues' number * to be used as a distribution range. */ -static u16 skb_tx_hash(const struct net_device *dev, struct sk_buff *skb) +static u16 skb_tx_hash(const struct net_device *dev, + const struct net_device *sb_dev, + struct sk_buff *skb) { u32 hash; u16 qoffset = 0; u16 qcount = dev->real_num_tx_queues; + if (dev->num_tc) { + u8 tc = netdev_get_prio_tc_map(dev, skb->priority); + + qoffset = sb_dev->tc_to_txq[tc].offset; + qcount = sb_dev->tc_to_txq[tc].count; + } + if (skb_rx_queue_recorded(skb)) { hash = skb_get_rx_queue(skb); while (unlikely(hash >= qcount)) hash -= qcount; - return hash; - } - - if (dev->num_tc) { - u8 tc = netdev_get_prio_tc_map(dev, skb->priority); - - qoffset = dev->tc_to_txq[tc].offset; - qcount = dev->tc_to_txq[tc].count; + return hash + qoffset; } return (u16) reciprocal_scale(skb_get_hash(skb), qcount) + qoffset; @@ -3573,7 +3575,8 @@ static int __get_xps_queue_idx(struct net_device *dev, struct sk_buff *skb, } #endif -static int get_xps_queue(struct net_device *dev, struct sk_buff *skb) +static int get_xps_queue(struct net_device *dev, struct net_device *sb_dev, + struct sk_buff *skb) { #ifdef CONFIG_XPS struct xps_dev_maps *dev_maps; @@ -3587,7 +3590,7 @@ static int get_xps_queue(struct net_device *dev, struct sk_buff *skb) if (!static_key_false(&xps_rxqs_needed)) goto get_cpus_map; - dev_maps = rcu_dereference(dev->xps_rxqs_map); + dev_maps = rcu_dereference(sb_dev->xps_rxqs_map); if (dev_maps) { int tci = sk_rx_queue_get(sk); @@ -3598,7 +3601,7 @@ static int get_xps_queue(struct net_device *dev, struct sk_buff *skb) get_cpus_map: if (queue_index < 0) { - dev_maps = rcu_dereference(dev->xps_cpus_map); + dev_maps = rcu_dereference(sb_dev->xps_cpus_map); if (dev_maps) { unsigned int tci = skb->sender_cpu - 1; @@ -3614,17 +3617,20 @@ get_cpus_map: #endif } -static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) +static u16 ___netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, + struct net_device *sb_dev) { struct sock *sk = skb->sk; int queue_index = sk_tx_queue_get(sk); + sb_dev = sb_dev ? : dev; + if (queue_index < 0 || skb->ooo_okay || queue_index >= dev->real_num_tx_queues) { - int new_index = get_xps_queue(dev, skb); + int new_index = get_xps_queue(dev, sb_dev, skb); if (new_index < 0) - new_index = skb_tx_hash(dev, skb); + new_index = skb_tx_hash(dev, sb_dev, skb); if (queue_index != new_index && sk && sk_fullsock(sk) && @@ -3637,9 +3643,15 @@ static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) return queue_index; } +static u16 __netdev_pick_tx(struct net_device *dev, + struct sk_buff *skb) +{ + return ___netdev_pick_tx(dev, skb, NULL); +} + struct netdev_queue *netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + struct net_device *sb_dev) { int queue_index = 0; @@ -3654,10 +3666,10 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev, const struct net_device_ops *ops = dev->netdev_ops; if (ops->ndo_select_queue) - queue_index = ops->ndo_select_queue(dev, skb, accel_priv, + queue_index = ops->ndo_select_queue(dev, skb, sb_dev, __netdev_pick_tx); else - queue_index = __netdev_pick_tx(dev, skb); + queue_index = ___netdev_pick_tx(dev, skb, sb_dev); queue_index = netdev_cap_txqueue(dev, queue_index); } @@ -3669,7 +3681,7 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev, /** * __dev_queue_xmit - transmit a buffer * @skb: buffer to transmit - * @accel_priv: private data used for L2 forwarding offload + * @sb_dev: suboordinate device used for L2 forwarding offload * * Queue a buffer for transmission to a network device. The caller must * have set the device and priority and built the buffer before calling @@ -3692,7 +3704,7 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev, * the BH enable code must have IRQs enabled so that it will not deadlock. * --BLG */ -static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv) +static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) { struct net_device *dev = skb->dev; struct netdev_queue *txq; @@ -3731,7 +3743,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv) else skb_dst_force(skb); - txq = netdev_pick_tx(dev, skb, accel_priv); + txq = netdev_pick_tx(dev, skb, sb_dev); q = rcu_dereference_bh(txq->qdisc); trace_net_dev_queue(skb); @@ -3805,9 +3817,9 @@ int dev_queue_xmit(struct sk_buff *skb) } EXPORT_SYMBOL(dev_queue_xmit); -int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv) +int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev) { - return __dev_queue_xmit(skb, accel_priv); + return __dev_queue_xmit(skb, sb_dev); } EXPORT_SYMBOL(dev_queue_xmit_accel); -- cgit v1.2.3 From a4ea8a3dacc312c3402c78f6e4843afdda9b43a0 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 9 Jul 2018 12:19:54 -0400 Subject: net: Add generic ndo_select_queue functions This patch adds a generic version of the ndo_select_queue functions for either returning 0 or selecting a queue based on the processor ID. This is generally meant to just reduce the number of functions we have to change in the future when we have to deal with ndo_select_queue changes. Signed-off-by: Alexander Duyck Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/lantiq_etop.c | 10 +--------- drivers/net/ethernet/ti/netcp_core.c | 9 +-------- drivers/staging/netlogic/xlr_net.c | 9 +-------- include/linux/netdevice.h | 4 ++++ net/core/dev.c | 14 ++++++++++++++ net/packet/af_packet.c | 2 +- 6 files changed, 22 insertions(+), 26 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c index afc810069440..7a637b51c7d2 100644 --- a/drivers/net/ethernet/lantiq_etop.c +++ b/drivers/net/ethernet/lantiq_etop.c @@ -563,14 +563,6 @@ ltq_etop_set_multicast_list(struct net_device *dev) spin_unlock_irqrestore(&priv->lock, flags); } -static u16 -ltq_etop_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv, select_queue_fallback_t fallback) -{ - /* we are currently only using the first queue */ - return 0; -} - static int ltq_etop_init(struct net_device *dev) { @@ -641,7 +633,7 @@ static const struct net_device_ops ltq_eth_netdev_ops = { .ndo_set_mac_address = ltq_etop_set_mac_address, .ndo_validate_addr = eth_validate_addr, .ndo_set_rx_mode = ltq_etop_set_multicast_list, - .ndo_select_queue = ltq_etop_select_queue, + .ndo_select_queue = dev_pick_tx_zero, .ndo_init = ltq_etop_init, .ndo_tx_timeout = ltq_etop_tx_timeout, }; diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index 6ebf110cd594..a1d335a3c5e4 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -1889,13 +1889,6 @@ static int netcp_rx_kill_vid(struct net_device *ndev, __be16 proto, u16 vid) return err; } -static u16 netcp_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv, - select_queue_fallback_t fallback) -{ - return 0; -} - static int netcp_setup_tc(struct net_device *dev, enum tc_setup_type type, void *type_data) { @@ -1972,7 +1965,7 @@ static const struct net_device_ops netcp_netdev_ops = { .ndo_vlan_rx_add_vid = netcp_rx_add_vid, .ndo_vlan_rx_kill_vid = netcp_rx_kill_vid, .ndo_tx_timeout = netcp_ndo_tx_timeout, - .ndo_select_queue = netcp_select_queue, + .ndo_select_queue = dev_pick_tx_zero, .ndo_setup_tc = netcp_setup_tc, }; diff --git a/drivers/staging/netlogic/xlr_net.c b/drivers/staging/netlogic/xlr_net.c index e461168313bf..4e6611e4c59b 100644 --- a/drivers/staging/netlogic/xlr_net.c +++ b/drivers/staging/netlogic/xlr_net.c @@ -290,13 +290,6 @@ static netdev_tx_t xlr_net_start_xmit(struct sk_buff *skb, return NETDEV_TX_OK; } -static u16 xlr_net_select_queue(struct net_device *ndev, struct sk_buff *skb, - void *accel_priv, - select_queue_fallback_t fallback) -{ - return (u16)smp_processor_id(); -} - static void xlr_hw_set_mac_addr(struct net_device *ndev) { struct xlr_net_priv *priv = netdev_priv(ndev); @@ -403,7 +396,7 @@ static const struct net_device_ops xlr_netdev_ops = { .ndo_open = xlr_net_open, .ndo_stop = xlr_net_stop, .ndo_start_xmit = xlr_net_start_xmit, - .ndo_select_queue = xlr_net_select_queue, + .ndo_select_queue = dev_pick_tx_cpu_id, .ndo_set_mac_address = xlr_net_set_mac_addr, .ndo_set_rx_mode = xlr_set_rx_mode, .ndo_get_stats64 = xlr_stats, diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index fda0bcda7a42..46f4c44ce3e4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2567,6 +2567,10 @@ void dev_close(struct net_device *dev); void dev_close_many(struct list_head *head, bool unlink); void dev_disable_lro(struct net_device *dev); int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb); +u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb, + void *accel_priv, select_queue_fallback_t fallback); +u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb, + void *accel_priv, select_queue_fallback_t fallback); int dev_queue_xmit(struct sk_buff *skb); int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev); int dev_direct_xmit(struct sk_buff *skb, u16 queue_id); diff --git a/net/core/dev.c b/net/core/dev.c index 09a7cc2f3c55..b5e538032d5e 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3617,6 +3617,20 @@ get_cpus_map: #endif } +u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb, + void *accel_priv, select_queue_fallback_t fallback) +{ + return 0; +} +EXPORT_SYMBOL(dev_pick_tx_zero); + +u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb, + void *accel_priv, select_queue_fallback_t fallback) +{ + return (u16)raw_smp_processor_id() % dev->real_num_tx_queues; +} +EXPORT_SYMBOL(dev_pick_tx_cpu_id); + static u16 ___netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) { diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 47931ebfaef3..f37d087ae652 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -277,7 +277,7 @@ static bool packet_use_direct_xmit(const struct packet_sock *po) static u16 __packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb) { - return (u16) raw_smp_processor_id() % dev->real_num_tx_queues; + return dev_pick_tx_cpu_id(dev, skb, NULL, NULL); } static u16 packet_pick_tx_queue(struct sk_buff *skb) -- cgit v1.2.3 From 4f49dec9075aa0277b8c9c657ec31e6361f88724 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 9 Jul 2018 12:19:59 -0400 Subject: net: allow ndo_select_queue to pass netdev This patch makes it so that instead of passing a void pointer as the accel_priv we instead pass a net_device pointer as sb_dev. Making this change allows us to pass the subordinate device through to the fallback function eventually so that we can keep the actual code in the ndo_select_queue call as focused on possible on the exception cases. Signed-off-by: Alexander Duyck Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/infiniband/hw/hfi1/vnic_main.c | 2 +- drivers/infiniband/ulp/opa_vnic/opa_vnic_netdev.c | 4 ++-- drivers/net/bonding/bond_main.c | 3 ++- drivers/net/ethernet/amazon/ena/ena_netdev.c | 3 ++- drivers/net/ethernet/broadcom/bcmsysport.c | 2 +- drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 3 ++- drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h | 3 ++- drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 3 ++- drivers/net/ethernet/hisilicon/hns/hns_enet.c | 3 ++- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 7 ++++--- drivers/net/ethernet/mellanox/mlx4/en_tx.c | 3 ++- drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 3 ++- drivers/net/ethernet/mellanox/mlx5/core/en.h | 3 ++- drivers/net/ethernet/mellanox/mlx5/core/en_tx.c | 3 ++- drivers/net/ethernet/renesas/ravb_main.c | 3 ++- drivers/net/ethernet/sun/ldmvsw.c | 3 ++- drivers/net/ethernet/sun/sunvnet.c | 3 ++- drivers/net/hyperv/netvsc_drv.c | 4 ++-- drivers/net/net_failover.c | 5 +++-- drivers/net/team/team.c | 3 ++- drivers/net/tun.c | 3 ++- drivers/net/wireless/marvell/mwifiex/main.c | 3 ++- drivers/net/xen-netback/interface.c | 2 +- drivers/net/xen-netfront.c | 3 ++- drivers/staging/rtl8188eu/os_dep/os_intfs.c | 3 ++- drivers/staging/rtl8723bs/os_dep/os_intfs.c | 7 +++---- include/linux/netdevice.h | 11 +++++++---- net/core/dev.c | 6 ++++-- net/mac80211/iface.c | 4 ++-- 29 files changed, 66 insertions(+), 42 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/hw/hfi1/vnic_main.c b/drivers/infiniband/hw/hfi1/vnic_main.c index 5d65582fe4d9..616fc9b6fad8 100644 --- a/drivers/infiniband/hw/hfi1/vnic_main.c +++ b/drivers/infiniband/hw/hfi1/vnic_main.c @@ -423,7 +423,7 @@ tx_finish: static u16 hfi1_vnic_select_queue(struct net_device *netdev, struct sk_buff *skb, - void *accel_priv, + struct net_device *sb_dev, select_queue_fallback_t fallback) { struct hfi1_vnic_vport_info *vinfo = opa_vnic_dev_priv(netdev); diff --git a/drivers/infiniband/ulp/opa_vnic/opa_vnic_netdev.c b/drivers/infiniband/ulp/opa_vnic/opa_vnic_netdev.c index 0c8aec62a425..61558788b3fa 100644 --- a/drivers/infiniband/ulp/opa_vnic/opa_vnic_netdev.c +++ b/drivers/infiniband/ulp/opa_vnic/opa_vnic_netdev.c @@ -95,7 +95,7 @@ static netdev_tx_t opa_netdev_start_xmit(struct sk_buff *skb, } static u16 opa_vnic_select_queue(struct net_device *netdev, struct sk_buff *skb, - void *accel_priv, + struct net_device *sb_dev, select_queue_fallback_t fallback) { struct opa_vnic_adapter *adapter = opa_vnic_priv(netdev); @@ -107,7 +107,7 @@ static u16 opa_vnic_select_queue(struct net_device *netdev, struct sk_buff *skb, mdata->entropy = opa_vnic_calc_entropy(skb); mdata->vl = opa_vnic_get_vl(adapter, skb); rc = adapter->rn_ops->ndo_select_queue(netdev, skb, - accel_priv, fallback); + sb_dev, fallback); skb_pull(skb, sizeof(*mdata)); return rc; } diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 63e3844c5bec..9a2ea3c1f949 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4094,7 +4094,8 @@ static inline int bond_slave_override(struct bonding *bond, static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv, select_queue_fallback_t fallback) + struct net_device *sb_dev, + select_queue_fallback_t fallback) { /* This helper function exists to help dev_pick_tx get the correct * destination queue. Using a helper function skips a call to diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index f2af87d70594..e3befb1f9204 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -2213,7 +2213,8 @@ static void ena_netpoll(struct net_device *netdev) #endif /* CONFIG_NET_POLL_CONTROLLER */ static u16 ena_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv, select_queue_fallback_t fallback) + struct net_device *sb_dev, + select_queue_fallback_t fallback) { u16 qid; /* we suspect that this is good for in--kernel network services that diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index d5fca2e5a9bc..32f548e6431d 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -2107,7 +2107,7 @@ static const struct ethtool_ops bcm_sysport_ethtool_ops = { }; static u16 bcm_sysport_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv, + struct net_device *sb_dev, select_queue_fallback_t fallback) { struct bcm_sysport_priv *priv = netdev_priv(dev); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index af7b5a4d8ba0..e4e1cf907ac6 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -1910,7 +1910,8 @@ void bnx2x_netif_stop(struct bnx2x *bp, int disable_hw) } u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv, select_queue_fallback_t fallback) + struct net_device *sb_dev, + select_queue_fallback_t fallback) { struct bnx2x *bp = netdev_priv(dev); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h index a8ce5c55bbb0..0e508e5defce 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h @@ -497,7 +497,8 @@ int bnx2x_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos, /* select_queue callback */ u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv, select_queue_fallback_t fallback); + struct net_device *sb_dev, + select_queue_fallback_t fallback); static inline void bnx2x_update_rx_prod(struct bnx2x *bp, struct bnx2x_fastpath *fp, diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 0d91716a2566..5dc5e5604f05 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -930,7 +930,8 @@ freeout: } static u16 cxgb_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv, select_queue_fallback_t fallback) + struct net_device *sb_dev, + select_queue_fallback_t fallback) { int txq; diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index ef9ef703d13a..ff7a74ec8f11 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -2022,7 +2022,8 @@ static void hns_nic_get_stats64(struct net_device *ndev, static u16 hns_nic_select_queue(struct net_device *ndev, struct sk_buff *skb, - void *accel_priv, select_queue_fallback_t fallback) + struct net_device *sb_dev, + select_queue_fallback_t fallback) { struct ethhdr *eth_hdr = (struct ethhdr *)skb->data; struct hns_nic_priv *priv = netdev_priv(ndev); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index abb176df2e7f..8c7a68c57afa 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -8210,15 +8210,16 @@ static void ixgbe_atr(struct ixgbe_ring *ring, #ifdef IXGBE_FCOE static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv, select_queue_fallback_t fallback) + struct net_device *sb_dev, + select_queue_fallback_t fallback) { struct ixgbe_adapter *adapter; struct ixgbe_ring_feature *f; int txq; - if (accel_priv) { + if (sb_dev) { u8 tc = netdev_get_prio_tc_map(dev, skb->priority); - struct net_device *vdev = accel_priv; + struct net_device *vdev = sb_dev; txq = vdev->tc_to_txq[tc].offset; txq += reciprocal_scale(skb_get_hash(skb), diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 0227786308af..df2996618cd1 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -688,7 +688,8 @@ static void build_inline_wqe(struct mlx4_en_tx_desc *tx_desc, } u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv, select_queue_fallback_t fallback) + struct net_device *sb_dev, + select_queue_fallback_t fallback) { struct mlx4_en_priv *priv = netdev_priv(dev); u16 rings_p_up = priv->num_tx_rings_p_up; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index ace6545f82e6..c3228b89df46 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -699,7 +699,8 @@ void mlx4_en_arm_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq); void mlx4_en_tx_irq(struct mlx4_cq *mcq); u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv, select_queue_fallback_t fallback); + struct net_device *sb_dev, + select_queue_fallback_t fallback); netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev); netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring, struct mlx4_en_rx_alloc *frame, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index e2b7586ed7a0..e1b237ccdf56 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -865,7 +865,8 @@ struct mlx5e_profile { void mlx5e_build_ptys2ethtool_map(void); u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv, select_queue_fallback_t fallback); + struct net_device *sb_dev, + select_queue_fallback_t fallback); netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev); netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, struct mlx5e_tx_wqe *wqe, u16 pi); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index f0739dae7b56..dfcc3710b65f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -111,7 +111,8 @@ static inline int mlx5e_get_dscp_up(struct mlx5e_priv *priv, struct sk_buff *skb #endif u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv, select_queue_fallback_t fallback) + struct net_device *sb_dev, + select_queue_fallback_t fallback) { struct mlx5e_priv *priv = netdev_priv(dev); int channel_ix = fallback(dev, skb); diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 68f122140966..4a7f54c8e7aa 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1656,7 +1656,8 @@ drop: } static u16 ravb_select_queue(struct net_device *ndev, struct sk_buff *skb, - void *accel_priv, select_queue_fallback_t fallback) + struct net_device *sb_dev, + select_queue_fallback_t fallback) { /* If skb needs TX timestamp, it is handled in network control queue */ return (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) ? RAVB_NC : diff --git a/drivers/net/ethernet/sun/ldmvsw.c b/drivers/net/ethernet/sun/ldmvsw.c index a5dd627fe2f9..d42f47f6c632 100644 --- a/drivers/net/ethernet/sun/ldmvsw.c +++ b/drivers/net/ethernet/sun/ldmvsw.c @@ -101,7 +101,8 @@ static struct vnet_port *vsw_tx_port_find(struct sk_buff *skb, } static u16 vsw_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv, select_queue_fallback_t fallback) + struct net_device *sb_dev, + select_queue_fallback_t fallback) { struct vnet_port *port = netdev_priv(dev); diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c index a94f50442613..12539b357a78 100644 --- a/drivers/net/ethernet/sun/sunvnet.c +++ b/drivers/net/ethernet/sun/sunvnet.c @@ -234,7 +234,8 @@ static struct vnet_port *vnet_tx_port_find(struct sk_buff *skb, } static u16 vnet_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv, select_queue_fallback_t fallback) + struct net_device *sb_dev, + select_queue_fallback_t fallback) { struct vnet *vp = netdev_priv(dev); struct vnet_port *port = __tx_port_find(vp, skb); diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index dd1d6e115145..98c0107d6ca1 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -329,7 +329,7 @@ static u16 netvsc_pick_tx(struct net_device *ndev, struct sk_buff *skb) } static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb, - void *accel_priv, + struct net_device *sb_dev, select_queue_fallback_t fallback) { struct net_device_context *ndc = netdev_priv(ndev); @@ -343,7 +343,7 @@ static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb, if (vf_ops->ndo_select_queue) txq = vf_ops->ndo_select_queue(vf_netdev, skb, - accel_priv, fallback); + sb_dev, fallback); else txq = fallback(vf_netdev, skb); diff --git a/drivers/net/net_failover.c b/drivers/net/net_failover.c index 4f390fa557e4..78b549698b7b 100644 --- a/drivers/net/net_failover.c +++ b/drivers/net/net_failover.c @@ -115,7 +115,8 @@ static netdev_tx_t net_failover_start_xmit(struct sk_buff *skb, } static u16 net_failover_select_queue(struct net_device *dev, - struct sk_buff *skb, void *accel_priv, + struct sk_buff *skb, + struct net_device *sb_dev, select_queue_fallback_t fallback) { struct net_failover_info *nfo_info = netdev_priv(dev); @@ -128,7 +129,7 @@ static u16 net_failover_select_queue(struct net_device *dev, if (ops->ndo_select_queue) txq = ops->ndo_select_queue(primary_dev, skb, - accel_priv, fallback); + sb_dev, fallback); else txq = fallback(primary_dev, skb); diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index b070959737ff..3a95eaae0c98 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1707,7 +1707,8 @@ static netdev_tx_t team_xmit(struct sk_buff *skb, struct net_device *dev) } static u16 team_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv, select_queue_fallback_t fallback) + struct net_device *sb_dev, + select_queue_fallback_t fallback) { /* * This helper function exists to help dev_pick_tx get the correct diff --git a/drivers/net/tun.c b/drivers/net/tun.c index a192a017cc68..76f0f4131197 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -607,7 +607,8 @@ static u16 tun_ebpf_select_queue(struct tun_struct *tun, struct sk_buff *skb) } static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv, select_queue_fallback_t fallback) + struct net_device *sb_dev, + select_queue_fallback_t fallback) { struct tun_struct *tun = netdev_priv(dev); u16 ret; diff --git a/drivers/net/wireless/marvell/mwifiex/main.c b/drivers/net/wireless/marvell/mwifiex/main.c index 510f6b8e717d..fa3e8ddfe9a9 100644 --- a/drivers/net/wireless/marvell/mwifiex/main.c +++ b/drivers/net/wireless/marvell/mwifiex/main.c @@ -1279,7 +1279,8 @@ static struct net_device_stats *mwifiex_get_stats(struct net_device *dev) static u16 mwifiex_netdev_select_wmm_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv, select_queue_fallback_t fallback) + struct net_device *sb_dev, + select_queue_fallback_t fallback) { skb->priority = cfg80211_classify8021d(skb, NULL); return mwifiex_1d_to_wmm_queue[skb->priority]; diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index 78ebe494fef0..19c4c585f472 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -148,7 +148,7 @@ void xenvif_wake_queue(struct xenvif_queue *queue) } static u16 xenvif_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv, + struct net_device *sb_dev, select_queue_fallback_t fallback) { struct xenvif *vif = netdev_priv(dev); diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index a57daecf1d57..d67cd379d156 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -545,7 +545,8 @@ static int xennet_count_skb_slots(struct sk_buff *skb) } static u16 xennet_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv, select_queue_fallback_t fallback) + struct net_device *sb_dev, + select_queue_fallback_t fallback) { unsigned int num_queues = dev->real_num_tx_queues; u32 hash; diff --git a/drivers/staging/rtl8188eu/os_dep/os_intfs.c b/drivers/staging/rtl8188eu/os_dep/os_intfs.c index add1ba00f3e9..38e85c8a85c8 100644 --- a/drivers/staging/rtl8188eu/os_dep/os_intfs.c +++ b/drivers/staging/rtl8188eu/os_dep/os_intfs.c @@ -253,7 +253,8 @@ static unsigned int rtw_classify8021d(struct sk_buff *skb) } static u16 rtw_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv, select_queue_fallback_t fallback) + struct net_device *sb_dev, + select_queue_fallback_t fallback) { struct adapter *padapter = rtw_netdev_priv(dev); struct mlme_priv *pmlmepriv = &padapter->mlmepriv; diff --git a/drivers/staging/rtl8723bs/os_dep/os_intfs.c b/drivers/staging/rtl8723bs/os_dep/os_intfs.c index ace68f023b49..181642358e3f 100644 --- a/drivers/staging/rtl8723bs/os_dep/os_intfs.c +++ b/drivers/staging/rtl8723bs/os_dep/os_intfs.c @@ -403,10 +403,9 @@ static unsigned int rtw_classify8021d(struct sk_buff *skb) } -static u16 rtw_select_queue(struct net_device *dev, struct sk_buff *skb - , void *accel_priv - , select_queue_fallback_t fallback -) +static u16 rtw_select_queue(struct net_device *dev, struct sk_buff *skb, + struct net_device *sb_dev, + select_queue_fallback_t fallback) { struct adapter *padapter = rtw_netdev_priv(dev); struct mlme_priv *pmlmepriv = &padapter->mlmepriv; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 46f4c44ce3e4..bbf062c1ca8a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -957,7 +957,8 @@ struct dev_ifalias { * those the driver believes to be appropriate. * * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb, - * void *accel_priv, select_queue_fallback_t fallback); + * struct net_device *sb_dev, + * select_queue_fallback_t fallback); * Called to decide which queue to use when device supports multiple * transmit queues. * @@ -1229,7 +1230,7 @@ struct net_device_ops { netdev_features_t features); u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb, - void *accel_priv, + struct net_device *sb_dev, select_queue_fallback_t fallback); void (*ndo_change_rx_flags)(struct net_device *dev, int flags); @@ -2568,9 +2569,11 @@ void dev_close_many(struct list_head *head, bool unlink); void dev_disable_lro(struct net_device *dev); int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb); u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb, - void *accel_priv, select_queue_fallback_t fallback); + struct net_device *sb_dev, + select_queue_fallback_t fallback); u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb, - void *accel_priv, select_queue_fallback_t fallback); + struct net_device *sb_dev, + select_queue_fallback_t fallback); int dev_queue_xmit(struct sk_buff *skb); int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev); int dev_direct_xmit(struct sk_buff *skb, u16 queue_id); diff --git a/net/core/dev.c b/net/core/dev.c index b5e538032d5e..a051ce27198b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3618,14 +3618,16 @@ get_cpus_map: } u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb, - void *accel_priv, select_queue_fallback_t fallback) + struct net_device *sb_dev, + select_queue_fallback_t fallback) { return 0; } EXPORT_SYMBOL(dev_pick_tx_zero); u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb, - void *accel_priv, select_queue_fallback_t fallback) + struct net_device *sb_dev, + select_queue_fallback_t fallback) { return (u16)raw_smp_processor_id() % dev->real_num_tx_queues; } diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 555e389b7dfa..5e6cf2cee965 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1130,7 +1130,7 @@ static void ieee80211_uninit(struct net_device *dev) static u16 ieee80211_netdev_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv, + struct net_device *sb_dev, select_queue_fallback_t fallback) { return ieee80211_select_queue(IEEE80211_DEV_TO_SUB_IF(dev), skb); @@ -1176,7 +1176,7 @@ static const struct net_device_ops ieee80211_dataif_ops = { static u16 ieee80211_monitor_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv, + struct net_device *sb_dev, select_queue_fallback_t fallback) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); -- cgit v1.2.3 From 8ec56fc3c5ee6f9700adac190e9ce5b8859a58b6 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 9 Jul 2018 12:20:04 -0400 Subject: net: allow fallback function to pass netdev For most of these calls we can just pass NULL through to the fallback function as the sb_dev. The only cases where we cannot are the cases where we might be dealing with either an upper device or a driver that would have configured things to support an sb_dev itself. The only driver that has any significant change in this patch set should be ixgbe as we can drop the redundant functionality that existed in both the ndo_select_queue function and the fallback function that was passed through to us. Signed-off-by: Alexander Duyck Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/amazon/ena/ena_netdev.c | 2 +- drivers/net/ethernet/broadcom/bcmsysport.c | 4 ++-- drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 3 ++- drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 2 +- drivers/net/ethernet/hisilicon/hns/hns_enet.c | 2 +- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 4 ++-- drivers/net/ethernet/mellanox/mlx4/en_tx.c | 4 ++-- drivers/net/ethernet/mellanox/mlx5/core/en_tx.c | 2 +- drivers/net/hyperv/netvsc_drv.c | 2 +- drivers/net/net_failover.c | 2 +- drivers/net/xen-netback/interface.c | 2 +- include/linux/netdevice.h | 3 ++- net/core/dev.c | 12 +++--------- net/packet/af_packet.c | 7 ++++--- 14 files changed, 24 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index e3befb1f9204..c673ac2df65b 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -2224,7 +2224,7 @@ static u16 ena_select_queue(struct net_device *dev, struct sk_buff *skb, if (skb_rx_queue_recorded(skb)) qid = skb_get_rx_queue(skb); else - qid = fallback(dev, skb); + qid = fallback(dev, skb, NULL); return qid; } diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index 32f548e6431d..eb890c4b3b2d 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -2116,7 +2116,7 @@ static u16 bcm_sysport_select_queue(struct net_device *dev, struct sk_buff *skb, unsigned int q, port; if (!netdev_uses_dsa(dev)) - return fallback(dev, skb); + return fallback(dev, skb, NULL); /* DSA tagging layer will have configured the correct queue */ q = BRCM_TAG_GET_QUEUE(queue); @@ -2124,7 +2124,7 @@ static u16 bcm_sysport_select_queue(struct net_device *dev, struct sk_buff *skb, tx_ring = priv->ring_map[q + port * priv->per_port_num_tx_queues]; if (unlikely(!tx_ring)) - return fallback(dev, skb); + return fallback(dev, skb, NULL); return tx_ring->index; } diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index e4e1cf907ac6..5a727d4729da 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -1933,7 +1933,8 @@ u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb, } /* select a non-FCoE queue */ - return fallback(dev, skb) % (BNX2X_NUM_ETH_QUEUES(bp) * bp->max_cos); + return fallback(dev, skb, NULL) % + (BNX2X_NUM_ETH_QUEUES(bp) * bp->max_cos); } void bnx2x_set_num_queues(struct bnx2x *bp) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 5dc5e5604f05..40cf8dc9f163 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -973,7 +973,7 @@ static u16 cxgb_select_queue(struct net_device *dev, struct sk_buff *skb, return txq; } - return fallback(dev, skb) % dev->real_num_tx_queues; + return fallback(dev, skb, NULL) % dev->real_num_tx_queues; } static int closest_timer(const struct sge *s, int time) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index ff7a74ec8f11..948b3e0d18f4 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -2033,7 +2033,7 @@ hns_nic_select_queue(struct net_device *ndev, struct sk_buff *skb, is_multicast_ether_addr(eth_hdr->h_dest)) return 0; else - return fallback(ndev, skb); + return fallback(ndev, skb, NULL); } static const struct net_device_ops hns_nic_netdev_ops = { diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 8c7a68c57afa..bd6d9ea27b4b 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -8237,11 +8237,11 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb, case htons(ETH_P_FIP): adapter = netdev_priv(dev); - if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) + if (!sb_dev && (adapter->flags & IXGBE_FLAG_FCOE_ENABLED)) break; /* fall through */ default: - return fallback(dev, skb); + return fallback(dev, skb, sb_dev); } f = &adapter->ring_feature[RING_F_FCOE]; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index df2996618cd1..1857ee0f0871 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -695,9 +695,9 @@ u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb, u16 rings_p_up = priv->num_tx_rings_p_up; if (netdev_get_num_tc(dev)) - return fallback(dev, skb); + return fallback(dev, skb, NULL); - return fallback(dev, skb) % rings_p_up; + return fallback(dev, skb, NULL) % rings_p_up; } static void mlx4_bf_copy(void __iomem *dst, const void *src, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index dfcc3710b65f..9106ea45e3cb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -115,7 +115,7 @@ u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb, select_queue_fallback_t fallback) { struct mlx5e_priv *priv = netdev_priv(dev); - int channel_ix = fallback(dev, skb); + int channel_ix = fallback(dev, skb, NULL); u16 num_channels; int up = 0; diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 98c0107d6ca1..cf4f40a04194 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -345,7 +345,7 @@ static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb, txq = vf_ops->ndo_select_queue(vf_netdev, skb, sb_dev, fallback); else - txq = fallback(vf_netdev, skb); + txq = fallback(vf_netdev, skb, NULL); /* Record the queue selected by VF so that it can be * used for common case where VF has more queues than diff --git a/drivers/net/net_failover.c b/drivers/net/net_failover.c index 78b549698b7b..d00d42c845b7 100644 --- a/drivers/net/net_failover.c +++ b/drivers/net/net_failover.c @@ -131,7 +131,7 @@ static u16 net_failover_select_queue(struct net_device *dev, txq = ops->ndo_select_queue(primary_dev, skb, sb_dev, fallback); else - txq = fallback(primary_dev, skb); + txq = fallback(primary_dev, skb, NULL); qdisc_skb_cb(skb)->slave_dev_queue_mapping = skb->queue_mapping; diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index 19c4c585f472..92274c237200 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -155,7 +155,7 @@ static u16 xenvif_select_queue(struct net_device *dev, struct sk_buff *skb, unsigned int size = vif->hash.size; if (vif->hash.alg == XEN_NETIF_CTRL_HASH_ALGORITHM_NONE) - return fallback(dev, skb) % dev->real_num_tx_queues; + return fallback(dev, skb, NULL) % dev->real_num_tx_queues; xenvif_set_skb_hash(vif, skb); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index bbf062c1ca8a..2daf2fa6554f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -793,7 +793,8 @@ static inline bool netdev_phys_item_id_same(struct netdev_phys_item_id *a, } typedef u16 (*select_queue_fallback_t)(struct net_device *dev, - struct sk_buff *skb); + struct sk_buff *skb, + struct net_device *sb_dev); enum tc_setup_type { TC_SETUP_QDISC_MQPRIO, diff --git a/net/core/dev.c b/net/core/dev.c index a051ce27198b..e18d81837a6c 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3633,8 +3633,8 @@ u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb, } EXPORT_SYMBOL(dev_pick_tx_cpu_id); -static u16 ___netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev) +static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, + struct net_device *sb_dev) { struct sock *sk = skb->sk; int queue_index = sk_tx_queue_get(sk); @@ -3659,12 +3659,6 @@ static u16 ___netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, return queue_index; } -static u16 __netdev_pick_tx(struct net_device *dev, - struct sk_buff *skb) -{ - return ___netdev_pick_tx(dev, skb, NULL); -} - struct netdev_queue *netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) @@ -3685,7 +3679,7 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev, queue_index = ops->ndo_select_queue(dev, skb, sb_dev, __netdev_pick_tx); else - queue_index = ___netdev_pick_tx(dev, skb, sb_dev); + queue_index = __netdev_pick_tx(dev, skb, sb_dev); queue_index = netdev_cap_txqueue(dev, queue_index); } diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index f37d087ae652..00189a3b07f2 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -275,9 +275,10 @@ static bool packet_use_direct_xmit(const struct packet_sock *po) return po->xmit == packet_direct_xmit; } -static u16 __packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb) +static u16 __packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb, + struct net_device *sb_dev) { - return dev_pick_tx_cpu_id(dev, skb, NULL, NULL); + return dev_pick_tx_cpu_id(dev, skb, sb_dev, NULL); } static u16 packet_pick_tx_queue(struct sk_buff *skb) @@ -291,7 +292,7 @@ static u16 packet_pick_tx_queue(struct sk_buff *skb) __packet_pick_tx_queue); queue_index = netdev_cap_txqueue(dev, queue_index); } else { - queue_index = __packet_pick_tx_queue(dev, skb); + queue_index = __packet_pick_tx_queue(dev, skb, NULL); } return queue_index; -- cgit v1.2.3 From 9f17dbf04ddf55ae48f5bbafea4c4920ea943215 Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Mon, 9 Jul 2018 18:10:02 +0100 Subject: netfilter: fix use-after-free in NF_HOOK_LIST nf_hook() can free the skb, so we need to remove it from the list before calling, and add passed skbs to a sublist afterwards. Fixes: 17266ee93984 ("net: ipv4: listified version of ip_rcv") Reported-by: Dan Carpenter Signed-off-by: Edward Cree Signed-off-by: David S. Miller --- include/linux/netfilter.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 5a5e0a2ab2a3..23b48de8c2e2 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -294,12 +294,16 @@ NF_HOOK_LIST(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { struct sk_buff *skb, *next; + struct list_head sublist; + INIT_LIST_HEAD(&sublist); list_for_each_entry_safe(skb, next, head, list) { - int ret = nf_hook(pf, hook, net, sk, skb, in, out, okfn); - if (ret != 1) - list_del(&skb->list); + list_del(&skb->list); + if (nf_hook(pf, hook, net, sk, skb, in, out, okfn) == 1) + list_add_tail(&skb->list, &sublist); } + /* Put passed packets back on main list */ + list_splice(&sublist, head); } /* Call setsockopt() */ -- cgit v1.2.3 From 52b509218f0ab5946f9cbaf5501d88f69333f0e3 Mon Sep 17 00:00:00 2001 From: Jesus Sanchez-Palencia Date: Mon, 9 Jul 2018 16:20:56 -0700 Subject: net: Use __u32 in uapi net_stamp.h We are not supposed to use u32 in uapi, so change the flags member of struct sock_txtime from u32 to __u32 instead. Fixes: 80b14dee2bea ("net: Add a new socket option for a future transmit time") Reported-by: Eric Dumazet Signed-off-by: Jesus Sanchez-Palencia Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- include/uapi/linux/net_tstamp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h index f8f4539f1135..97ff3c17ec4d 100644 --- a/include/uapi/linux/net_tstamp.h +++ b/include/uapi/linux/net_tstamp.h @@ -155,8 +155,8 @@ enum txtime_flags { }; struct sock_txtime { - clockid_t clockid; /* reference clockid */ - u32 flags; /* flags defined by enum txtime_flags */ + clockid_t clockid; /* reference clockid */ + __u32 flags; /* as defined by enum txtime_flags */ }; #endif /* _NET_TIMESTAMPING_H */ -- cgit v1.2.3 From c76f0f7cb546b661b5e0ac769850a5c854927f65 Mon Sep 17 00:00:00 2001 From: Noralf Trønnes Date: Tue, 3 Jul 2018 18:03:47 +0200 Subject: drm: Begin an API for in-kernel clients MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This the beginning of an API for in-kernel clients. First out is a way to get a framebuffer backed by a dumb buffer. Only GEM drivers are supported. The original idea of using an exported dma-buf was dropped because it also creates an anonomous file descriptor which doesn't work when the buffer is created from a kernel thread. The easy way out is to use drm_driver.gem_prime_vmap to get the virtual address, which requires a GEM object. This excludes the vmwgfx driver which is the only non-GEM driver apart from the legacy ones. A solution for vmwgfx will have to be worked out later if it wants to support the client API which it probably will when we have a bootsplash client. Suggested-by: Daniel Vetter Signed-off-by: Noralf Trønnes Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20180703160354.59955-2-noralf@tronnes.org --- Documentation/gpu/drm-client.rst | 12 ++ Documentation/gpu/index.rst | 1 + drivers/gpu/drm/Makefile | 2 +- drivers/gpu/drm/drm_client.c | 387 +++++++++++++++++++++++++++++++++++++ drivers/gpu/drm/drm_drv.c | 8 + drivers/gpu/drm/drm_file.c | 3 + drivers/gpu/drm/drm_probe_helper.c | 3 + include/drm/drm_client.h | 136 +++++++++++++ include/drm/drm_device.h | 21 ++ 9 files changed, 572 insertions(+), 1 deletion(-) create mode 100644 Documentation/gpu/drm-client.rst create mode 100644 drivers/gpu/drm/drm_client.c create mode 100644 include/drm/drm_client.h (limited to 'include') diff --git a/Documentation/gpu/drm-client.rst b/Documentation/gpu/drm-client.rst new file mode 100644 index 000000000000..7e672063e7eb --- /dev/null +++ b/Documentation/gpu/drm-client.rst @@ -0,0 +1,12 @@ +================= +Kernel clients +================= + +.. kernel-doc:: drivers/gpu/drm/drm_client.c + :doc: overview + +.. kernel-doc:: include/drm/drm_client.h + :internal: + +.. kernel-doc:: drivers/gpu/drm/drm_client.c + :export: diff --git a/Documentation/gpu/index.rst b/Documentation/gpu/index.rst index 00288f34c5a6..1fcf8e851e15 100644 --- a/Documentation/gpu/index.rst +++ b/Documentation/gpu/index.rst @@ -10,6 +10,7 @@ Linux GPU Driver Developer's Guide drm-kms drm-kms-helpers drm-uapi + drm-client drivers vga-switcheroo vgaarbiter diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile index 6ae535ca0914..0e0a3ef1abad 100644 --- a/drivers/gpu/drm/Makefile +++ b/drivers/gpu/drm/Makefile @@ -18,7 +18,7 @@ drm-y := drm_auth.o drm_bufs.o drm_cache.o \ drm_encoder.o drm_mode_object.o drm_property.o \ drm_plane.o drm_color_mgmt.o drm_print.o \ drm_dumb_buffers.o drm_mode_config.o drm_vblank.o \ - drm_syncobj.o drm_lease.o drm_writeback.o + drm_syncobj.o drm_lease.o drm_writeback.o drm_client.o drm-$(CONFIG_DRM_LIB_RANDOM) += lib/drm_random.o drm-$(CONFIG_DRM_VM) += drm_vm.o diff --git a/drivers/gpu/drm/drm_client.c b/drivers/gpu/drm/drm_client.c new file mode 100644 index 000000000000..743495f7f833 --- /dev/null +++ b/drivers/gpu/drm/drm_client.c @@ -0,0 +1,387 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright 2018 Noralf Trønnes + */ + +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "drm_crtc_internal.h" +#include "drm_internal.h" + +/** + * DOC: overview + * + * This library provides support for clients running in the kernel like fbdev and bootsplash. + * Currently it's only partially implemented, just enough to support fbdev. + * + * GEM drivers which provide a GEM based dumb buffer with a virtual address are supported. + */ + +static int drm_client_open(struct drm_client_dev *client) +{ + struct drm_device *dev = client->dev; + struct drm_file *file; + + file = drm_file_alloc(dev->primary); + if (IS_ERR(file)) + return PTR_ERR(file); + + mutex_lock(&dev->filelist_mutex); + list_add(&file->lhead, &dev->filelist_internal); + mutex_unlock(&dev->filelist_mutex); + + client->file = file; + + return 0; +} + +static void drm_client_close(struct drm_client_dev *client) +{ + struct drm_device *dev = client->dev; + + mutex_lock(&dev->filelist_mutex); + list_del(&client->file->lhead); + mutex_unlock(&dev->filelist_mutex); + + drm_file_free(client->file); +} +EXPORT_SYMBOL(drm_client_close); + +/** + * drm_client_new - Create a DRM client + * @dev: DRM device + * @client: DRM client + * @name: Client name + * @funcs: DRM client functions (optional) + * + * The caller needs to hold a reference on @dev before calling this function. + * The client is freed when the &drm_device is unregistered. See drm_client_release(). + * + * Returns: + * Zero on success or negative error code on failure. + */ +int drm_client_new(struct drm_device *dev, struct drm_client_dev *client, + const char *name, const struct drm_client_funcs *funcs) +{ + bool registered; + int ret; + + if (!drm_core_check_feature(dev, DRIVER_MODESET) || + !dev->driver->dumb_create || !dev->driver->gem_prime_vmap) + return -ENOTSUPP; + + if (funcs && !try_module_get(funcs->owner)) + return -ENODEV; + + client->dev = dev; + client->name = name; + client->funcs = funcs; + + ret = drm_client_open(client); + if (ret) + goto err_put_module; + + mutex_lock(&dev->clientlist_mutex); + registered = dev->registered; + if (registered) + list_add(&client->list, &dev->clientlist); + mutex_unlock(&dev->clientlist_mutex); + if (!registered) { + ret = -ENODEV; + goto err_close; + } + + drm_dev_get(dev); + + return 0; + +err_close: + drm_client_close(client); +err_put_module: + if (funcs) + module_put(funcs->owner); + + return ret; +} +EXPORT_SYMBOL(drm_client_new); + +/** + * drm_client_release - Release DRM client resources + * @client: DRM client + * + * Releases resources by closing the &drm_file that was opened by drm_client_new(). + * It is called automatically if the &drm_client_funcs.unregister callback is _not_ set. + * + * This function should only be called from the unregister callback. An exception + * is fbdev which cannot free the buffer if userspace has open file descriptors. + * + * Note: + * Clients cannot initiate a release by themselves. This is done to keep the code simple. + * The driver has to be unloaded before the client can be unloaded. + */ +void drm_client_release(struct drm_client_dev *client) +{ + struct drm_device *dev = client->dev; + + DRM_DEV_DEBUG_KMS(dev->dev, "%s\n", client->name); + + drm_client_close(client); + drm_dev_put(dev); + if (client->funcs) + module_put(client->funcs->owner); +} +EXPORT_SYMBOL(drm_client_release); + +void drm_client_dev_unregister(struct drm_device *dev) +{ + struct drm_client_dev *client, *tmp; + + if (!drm_core_check_feature(dev, DRIVER_MODESET)) + return; + + mutex_lock(&dev->clientlist_mutex); + list_for_each_entry_safe(client, tmp, &dev->clientlist, list) { + list_del(&client->list); + if (client->funcs && client->funcs->unregister) { + client->funcs->unregister(client); + } else { + drm_client_release(client); + kfree(client); + } + } + mutex_unlock(&dev->clientlist_mutex); +} + +/** + * drm_client_dev_hotplug - Send hotplug event to clients + * @dev: DRM device + * + * This function calls the &drm_client_funcs.hotplug callback on the attached clients. + * + * drm_kms_helper_hotplug_event() calls this function, so drivers that use it + * don't need to call this function themselves. + */ +void drm_client_dev_hotplug(struct drm_device *dev) +{ + struct drm_client_dev *client; + int ret; + + if (!drm_core_check_feature(dev, DRIVER_MODESET)) + return; + + mutex_lock(&dev->clientlist_mutex); + list_for_each_entry(client, &dev->clientlist, list) { + if (!client->funcs || !client->funcs->hotplug) + continue; + + ret = client->funcs->hotplug(client); + DRM_DEV_DEBUG_KMS(dev->dev, "%s: ret=%d\n", client->name, ret); + } + mutex_unlock(&dev->clientlist_mutex); +} +EXPORT_SYMBOL(drm_client_dev_hotplug); + +void drm_client_dev_restore(struct drm_device *dev) +{ + struct drm_client_dev *client; + int ret; + + if (!drm_core_check_feature(dev, DRIVER_MODESET)) + return; + + mutex_lock(&dev->clientlist_mutex); + list_for_each_entry(client, &dev->clientlist, list) { + if (!client->funcs || !client->funcs->restore) + continue; + + ret = client->funcs->restore(client); + DRM_DEV_DEBUG_KMS(dev->dev, "%s: ret=%d\n", client->name, ret); + if (!ret) /* The first one to return zero gets the privilege to restore */ + break; + } + mutex_unlock(&dev->clientlist_mutex); +} + +static void drm_client_buffer_delete(struct drm_client_buffer *buffer) +{ + struct drm_device *dev = buffer->client->dev; + + if (buffer->vaddr && dev->driver->gem_prime_vunmap) + dev->driver->gem_prime_vunmap(buffer->gem, buffer->vaddr); + + if (buffer->gem) + drm_gem_object_put_unlocked(buffer->gem); + + drm_mode_destroy_dumb(dev, buffer->handle, buffer->client->file); + kfree(buffer); +} + +static struct drm_client_buffer * +drm_client_buffer_create(struct drm_client_dev *client, u32 width, u32 height, u32 format) +{ + struct drm_mode_create_dumb dumb_args = { }; + struct drm_device *dev = client->dev; + struct drm_client_buffer *buffer; + struct drm_gem_object *obj; + void *vaddr; + int ret; + + buffer = kzalloc(sizeof(*buffer), GFP_KERNEL); + if (!buffer) + return ERR_PTR(-ENOMEM); + + buffer->client = client; + + dumb_args.width = width; + dumb_args.height = height; + dumb_args.bpp = drm_format_plane_cpp(format, 0) * 8; + ret = drm_mode_create_dumb(dev, &dumb_args, client->file); + if (ret) + goto err_free; + + buffer->handle = dumb_args.handle; + buffer->pitch = dumb_args.pitch; + + obj = drm_gem_object_lookup(client->file, dumb_args.handle); + if (!obj) { + ret = -ENOENT; + goto err_delete; + } + + buffer->gem = obj; + + /* + * FIXME: The dependency on GEM here isn't required, we could + * convert the driver handle to a dma-buf instead and use the + * backend-agnostic dma-buf vmap support instead. This would + * require that the handle2fd prime ioctl is reworked to pull the + * fd_install step out of the driver backend hooks, to make that + * final step optional for internal users. + */ + vaddr = dev->driver->gem_prime_vmap(obj); + if (!vaddr) { + ret = -ENOMEM; + goto err_delete; + } + + buffer->vaddr = vaddr; + + return buffer; + +err_delete: + drm_client_buffer_delete(buffer); +err_free: + kfree(buffer); + + return ERR_PTR(ret); +} + +static void drm_client_buffer_rmfb(struct drm_client_buffer *buffer) +{ + int ret; + + if (!buffer->fb) + return; + + ret = drm_mode_rmfb(buffer->client->dev, buffer->fb->base.id, buffer->client->file); + if (ret) + DRM_DEV_ERROR(buffer->client->dev->dev, + "Error removing FB:%u (%d)\n", buffer->fb->base.id, ret); + + buffer->fb = NULL; +} + +static int drm_client_buffer_addfb(struct drm_client_buffer *buffer, + u32 width, u32 height, u32 format) +{ + struct drm_client_dev *client = buffer->client; + struct drm_mode_fb_cmd fb_req = { }; + const struct drm_format_info *info; + int ret; + + info = drm_format_info(format); + fb_req.bpp = info->cpp[0] * 8; + fb_req.depth = info->depth; + fb_req.width = width; + fb_req.height = height; + fb_req.handle = buffer->handle; + fb_req.pitch = buffer->pitch; + + ret = drm_mode_addfb(client->dev, &fb_req, client->file); + if (ret) + return ret; + + buffer->fb = drm_framebuffer_lookup(client->dev, buffer->client->file, fb_req.fb_id); + if (WARN_ON(!buffer->fb)) + return -ENOENT; + + /* drop the reference we picked up in framebuffer lookup */ + drm_framebuffer_put(buffer->fb); + + strscpy(buffer->fb->comm, client->name, TASK_COMM_LEN); + + return 0; +} + +/** + * drm_client_framebuffer_create - Create a client framebuffer + * @client: DRM client + * @width: Framebuffer width + * @height: Framebuffer height + * @format: Buffer format + * + * This function creates a &drm_client_buffer which consists of a + * &drm_framebuffer backed by a dumb buffer. + * Call drm_client_framebuffer_delete() to free the buffer. + * + * Returns: + * Pointer to a client buffer or an error pointer on failure. + */ +struct drm_client_buffer * +drm_client_framebuffer_create(struct drm_client_dev *client, u32 width, u32 height, u32 format) +{ + struct drm_client_buffer *buffer; + int ret; + + buffer = drm_client_buffer_create(client, width, height, format); + if (IS_ERR(buffer)) + return buffer; + + ret = drm_client_buffer_addfb(buffer, width, height, format); + if (ret) { + drm_client_buffer_delete(buffer); + return ERR_PTR(ret); + } + + return buffer; +} +EXPORT_SYMBOL(drm_client_framebuffer_create); + +/** + * drm_client_framebuffer_delete - Delete a client framebuffer + * @buffer: DRM client buffer (can be NULL) + */ +void drm_client_framebuffer_delete(struct drm_client_buffer *buffer) +{ + if (!buffer) + return; + + drm_client_buffer_rmfb(buffer); + drm_client_buffer_delete(buffer); +} +EXPORT_SYMBOL(drm_client_framebuffer_delete); diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c index 7af748ed1c58..6eb935bb2f92 100644 --- a/drivers/gpu/drm/drm_drv.c +++ b/drivers/gpu/drm/drm_drv.c @@ -34,6 +34,7 @@ #include #include +#include #include #include @@ -505,6 +506,8 @@ int drm_dev_init(struct drm_device *dev, dev->driver = driver; INIT_LIST_HEAD(&dev->filelist); + INIT_LIST_HEAD(&dev->filelist_internal); + INIT_LIST_HEAD(&dev->clientlist); INIT_LIST_HEAD(&dev->ctxlist); INIT_LIST_HEAD(&dev->vmalist); INIT_LIST_HEAD(&dev->maplist); @@ -514,6 +517,7 @@ int drm_dev_init(struct drm_device *dev, spin_lock_init(&dev->event_lock); mutex_init(&dev->struct_mutex); mutex_init(&dev->filelist_mutex); + mutex_init(&dev->clientlist_mutex); mutex_init(&dev->ctxlist_mutex); mutex_init(&dev->master_mutex); @@ -569,6 +573,7 @@ err_minors: err_free: mutex_destroy(&dev->master_mutex); mutex_destroy(&dev->ctxlist_mutex); + mutex_destroy(&dev->clientlist_mutex); mutex_destroy(&dev->filelist_mutex); mutex_destroy(&dev->struct_mutex); return ret; @@ -603,6 +608,7 @@ void drm_dev_fini(struct drm_device *dev) mutex_destroy(&dev->master_mutex); mutex_destroy(&dev->ctxlist_mutex); + mutex_destroy(&dev->clientlist_mutex); mutex_destroy(&dev->filelist_mutex); mutex_destroy(&dev->struct_mutex); kfree(dev->unique); @@ -858,6 +864,8 @@ void drm_dev_unregister(struct drm_device *dev) dev->registered = false; + drm_client_dev_unregister(dev); + if (drm_core_check_feature(dev, DRIVER_MODESET)) drm_modeset_unregister_all(dev); diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c index 66bb403dc8ab..ffa8dc35515f 100644 --- a/drivers/gpu/drm/drm_file.c +++ b/drivers/gpu/drm/drm_file.c @@ -35,6 +35,7 @@ #include #include +#include #include #include @@ -444,6 +445,8 @@ void drm_lastclose(struct drm_device * dev) if (drm_core_check_feature(dev, DRIVER_LEGACY)) drm_legacy_dev_reinit(dev); + + drm_client_dev_restore(dev); } /** diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c index 1a901fe9e23e..34fe2704a31c 100644 --- a/drivers/gpu/drm/drm_probe_helper.c +++ b/drivers/gpu/drm/drm_probe_helper.c @@ -33,6 +33,7 @@ #include #include +#include #include #include #include @@ -559,6 +560,8 @@ void drm_kms_helper_hotplug_event(struct drm_device *dev) drm_sysfs_hotplug_event(dev); if (dev->mode_config.funcs->output_poll_changed) dev->mode_config.funcs->output_poll_changed(dev); + + drm_client_dev_hotplug(dev); } EXPORT_SYMBOL(drm_kms_helper_hotplug_event); diff --git a/include/drm/drm_client.h b/include/drm/drm_client.h new file mode 100644 index 000000000000..671052d80e38 --- /dev/null +++ b/include/drm/drm_client.h @@ -0,0 +1,136 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _DRM_CLIENT_H_ +#define _DRM_CLIENT_H_ + +#include + +struct drm_client_dev; +struct drm_device; +struct drm_file; +struct drm_framebuffer; +struct drm_gem_object; +struct module; + +/** + * struct drm_client_funcs - DRM client callbacks + */ +struct drm_client_funcs { + /** + * @owner: The module owner + */ + struct module *owner; + + /** + * @unregister: + * + * Called when &drm_device is unregistered. The client should respond by + * releasing it's resources using drm_client_release(). + * + * This callback is optional. + */ + void (*unregister)(struct drm_client_dev *client); + + /** + * @restore: + * + * Called on drm_lastclose(). The first client instance in the list that + * returns zero gets the privilege to restore and no more clients are + * called. This callback is not called after @unregister has been called. + * + * This callback is optional. + */ + int (*restore)(struct drm_client_dev *client); + + /** + * @hotplug: + * + * Called on drm_kms_helper_hotplug_event(). + * This callback is not called after @unregister has been called. + * + * This callback is optional. + */ + int (*hotplug)(struct drm_client_dev *client); +}; + +/** + * struct drm_client_dev - DRM client instance + */ +struct drm_client_dev { + /** + * @dev: DRM device + */ + struct drm_device *dev; + + /** + * @name: Name of the client. + */ + const char *name; + + /** + * @list: + * + * List of all clients of a DRM device, linked into + * &drm_device.clientlist. Protected by &drm_device.clientlist_mutex. + */ + struct list_head list; + + /** + * @funcs: DRM client functions (optional) + */ + const struct drm_client_funcs *funcs; + + /** + * @file: DRM file + */ + struct drm_file *file; +}; + +int drm_client_new(struct drm_device *dev, struct drm_client_dev *client, + const char *name, const struct drm_client_funcs *funcs); +void drm_client_release(struct drm_client_dev *client); + +void drm_client_dev_unregister(struct drm_device *dev); +void drm_client_dev_hotplug(struct drm_device *dev); +void drm_client_dev_restore(struct drm_device *dev); + +/** + * struct drm_client_buffer - DRM client buffer + */ +struct drm_client_buffer { + /** + * @client: DRM client + */ + struct drm_client_dev *client; + + /** + * @handle: Buffer handle + */ + u32 handle; + + /** + * @pitch: Buffer pitch + */ + u32 pitch; + + /** + * @gem: GEM object backing this buffer + */ + struct drm_gem_object *gem; + + /** + * @vaddr: Virtual address for the buffer + */ + void *vaddr; + + /** + * @fb: DRM framebuffer + */ + struct drm_framebuffer *fb; +}; + +struct drm_client_buffer * +drm_client_framebuffer_create(struct drm_client_dev *client, u32 width, u32 height, u32 format); +void drm_client_framebuffer_delete(struct drm_client_buffer *buffer); + +#endif diff --git a/include/drm/drm_device.h b/include/drm/drm_device.h index 858ba19a3e29..f9c6e0e3aec7 100644 --- a/include/drm/drm_device.h +++ b/include/drm/drm_device.h @@ -74,6 +74,27 @@ struct drm_device { struct mutex filelist_mutex; struct list_head filelist; + /** + * @filelist_internal: + * + * List of open DRM files for in-kernel clients. Protected by @filelist_mutex. + */ + struct list_head filelist_internal; + + /** + * @clientlist_mutex: + * + * Protects @clientlist access. + */ + struct mutex clientlist_mutex; + + /** + * @clientlist: + * + * List of in-kernel clients. Protected by @clientlist_mutex. + */ + struct list_head clientlist; + /** \name Memory management */ /*@{ */ struct list_head maplist; /**< Linked list of regions */ -- cgit v1.2.3 From d536540f304ce0ee35db9f67f7d880bc09f3743f Mon Sep 17 00:00:00 2001 From: Noralf Trønnes Date: Tue, 3 Jul 2018 18:03:48 +0200 Subject: drm/fb-helper: Add generic fbdev emulation .fb_probe function MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This is the first step in getting generic fbdev emulation. A drm_fb_helper_funcs.fb_probe function is added which uses the DRM client API to get a framebuffer backed by a dumb buffer. Signed-off-by: Noralf Trønnes Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20180703160354.59955-3-noralf@tronnes.org --- drivers/gpu/drm/drm_fb_helper.c | 199 +++++++++++++++++++++++++++++++++++++++- include/drm/drm_fb_helper.h | 31 +++++++ 2 files changed, 229 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index d697c1c4a067..7e29d5340a17 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -30,6 +30,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include +#include #include #include #include @@ -738,6 +739,24 @@ static void drm_fb_helper_resume_worker(struct work_struct *work) console_unlock(); } +static void drm_fb_helper_dirty_blit_real(struct drm_fb_helper *fb_helper, + struct drm_clip_rect *clip) +{ + struct drm_framebuffer *fb = fb_helper->fb; + unsigned int cpp = drm_format_plane_cpp(fb->format->format, 0); + size_t offset = clip->y1 * fb->pitches[0] + clip->x1 * cpp; + void *src = fb_helper->fbdev->screen_buffer + offset; + void *dst = fb_helper->buffer->vaddr + offset; + size_t len = (clip->x2 - clip->x1) * cpp; + unsigned int y; + + for (y = clip->y1; y < clip->y2; y++) { + memcpy(dst, src, len); + src += fb->pitches[0]; + dst += fb->pitches[0]; + } +} + static void drm_fb_helper_dirty_work(struct work_struct *work) { struct drm_fb_helper *helper = container_of(work, struct drm_fb_helper, @@ -753,8 +772,12 @@ static void drm_fb_helper_dirty_work(struct work_struct *work) spin_unlock_irqrestore(&helper->dirty_lock, flags); /* call dirty callback only when it has been really touched */ - if (clip_copy.x1 < clip_copy.x2 && clip_copy.y1 < clip_copy.y2) + if (clip_copy.x1 < clip_copy.x2 && clip_copy.y1 < clip_copy.y2) { + /* Generic fbdev uses a shadow buffer */ + if (helper->buffer) + drm_fb_helper_dirty_blit_real(helper, &clip_copy); helper->fb->funcs->dirty(helper->fb, NULL, 0, 0, &clip_copy, 1); + } } /** @@ -2921,6 +2944,180 @@ void drm_fb_helper_output_poll_changed(struct drm_device *dev) } EXPORT_SYMBOL(drm_fb_helper_output_poll_changed); +/* @user: 1=userspace, 0=fbcon */ +static int drm_fbdev_fb_open(struct fb_info *info, int user) +{ + struct drm_fb_helper *fb_helper = info->par; + + if (!try_module_get(fb_helper->dev->driver->fops->owner)) + return -ENODEV; + + return 0; +} + +static int drm_fbdev_fb_release(struct fb_info *info, int user) +{ + struct drm_fb_helper *fb_helper = info->par; + + module_put(fb_helper->dev->driver->fops->owner); + + return 0; +} + +/* + * fb_ops.fb_destroy is called by the last put_fb_info() call at the end of + * unregister_framebuffer() or fb_release(). + */ +static void drm_fbdev_fb_destroy(struct fb_info *info) +{ + struct drm_fb_helper *fb_helper = info->par; + struct fb_info *fbi = fb_helper->fbdev; + struct fb_ops *fbops = NULL; + void *shadow = NULL; + + if (fbi->fbdefio) { + fb_deferred_io_cleanup(fbi); + shadow = fbi->screen_buffer; + fbops = fbi->fbops; + } + + drm_fb_helper_fini(fb_helper); + + if (shadow) { + vfree(shadow); + kfree(fbops); + } + + drm_client_framebuffer_delete(fb_helper->buffer); + /* + * FIXME: + * Remove conditional when all CMA drivers have been moved over to using + * drm_fbdev_generic_setup(). + */ + if (fb_helper->client.funcs) { + drm_client_release(&fb_helper->client); + kfree(fb_helper); + } +} + +static int drm_fbdev_fb_mmap(struct fb_info *info, struct vm_area_struct *vma) +{ + struct drm_fb_helper *fb_helper = info->par; + + if (fb_helper->dev->driver->gem_prime_mmap) + return fb_helper->dev->driver->gem_prime_mmap(fb_helper->buffer->gem, vma); + else + return -ENODEV; +} + +static struct fb_ops drm_fbdev_fb_ops = { + .owner = THIS_MODULE, + DRM_FB_HELPER_DEFAULT_OPS, + .fb_open = drm_fbdev_fb_open, + .fb_release = drm_fbdev_fb_release, + .fb_destroy = drm_fbdev_fb_destroy, + .fb_mmap = drm_fbdev_fb_mmap, + .fb_read = drm_fb_helper_sys_read, + .fb_write = drm_fb_helper_sys_write, + .fb_fillrect = drm_fb_helper_sys_fillrect, + .fb_copyarea = drm_fb_helper_sys_copyarea, + .fb_imageblit = drm_fb_helper_sys_imageblit, +}; + +static struct fb_deferred_io drm_fbdev_defio = { + .delay = HZ / 20, + .deferred_io = drm_fb_helper_deferred_io, +}; + +/** + * drm_fb_helper_generic_probe - Generic fbdev emulation probe helper + * @fb_helper: fbdev helper structure + * @sizes: describes fbdev size and scanout surface size + * + * This function uses the client API to crate a framebuffer backed by a dumb buffer. + * + * The _sys_ versions are used for &fb_ops.fb_read, fb_write, fb_fillrect, + * fb_copyarea, fb_imageblit. + * + * Returns: + * Zero on success or negative error code on failure. + */ +int drm_fb_helper_generic_probe(struct drm_fb_helper *fb_helper, + struct drm_fb_helper_surface_size *sizes) +{ + struct drm_client_dev *client = &fb_helper->client; + struct drm_client_buffer *buffer; + struct drm_framebuffer *fb; + struct fb_info *fbi; + u32 format; + int ret; + + DRM_DEBUG_KMS("surface width(%d), height(%d) and bpp(%d)\n", + sizes->surface_width, sizes->surface_height, + sizes->surface_bpp); + + format = drm_mode_legacy_fb_format(sizes->surface_bpp, sizes->surface_depth); + buffer = drm_client_framebuffer_create(client, sizes->surface_width, + sizes->surface_height, format); + if (IS_ERR(buffer)) + return PTR_ERR(buffer); + + fb_helper->buffer = buffer; + fb_helper->fb = buffer->fb; + fb = buffer->fb; + + fbi = drm_fb_helper_alloc_fbi(fb_helper); + if (IS_ERR(fbi)) { + ret = PTR_ERR(fbi); + goto err_free_buffer; + } + + fbi->par = fb_helper; + fbi->fbops = &drm_fbdev_fb_ops; + fbi->screen_size = fb->height * fb->pitches[0]; + fbi->fix.smem_len = fbi->screen_size; + fbi->screen_buffer = buffer->vaddr; + strcpy(fbi->fix.id, "DRM emulated"); + + drm_fb_helper_fill_fix(fbi, fb->pitches[0], fb->format->depth); + drm_fb_helper_fill_var(fbi, fb_helper, sizes->fb_width, sizes->fb_height); + + if (fb->funcs->dirty) { + struct fb_ops *fbops; + void *shadow; + + /* + * fb_deferred_io_cleanup() clears &fbops->fb_mmap so a per + * instance version is necessary. + */ + fbops = kzalloc(sizeof(*fbops), GFP_KERNEL); + shadow = vzalloc(fbi->screen_size); + if (!fbops || !shadow) { + kfree(fbops); + vfree(shadow); + ret = -ENOMEM; + goto err_fb_info_destroy; + } + + *fbops = *fbi->fbops; + fbi->fbops = fbops; + fbi->screen_buffer = shadow; + fbi->fbdefio = &drm_fbdev_defio; + + fb_deferred_io_init(fbi); + } + + return 0; + +err_fb_info_destroy: + drm_fb_helper_fini(fb_helper); +err_free_buffer: + drm_client_framebuffer_delete(buffer); + + return ret; +} +EXPORT_SYMBOL(drm_fb_helper_generic_probe); + /* The Kconfig DRM_KMS_HELPER selects FRAMEBUFFER_CONSOLE (if !EXPERT) * but the module doesn't depend on any fb console symbols. At least * attempt to load fbcon to avoid leaving the system without a usable console. diff --git a/include/drm/drm_fb_helper.h b/include/drm/drm_fb_helper.h index b069433e7fc1..c134bbcfd2e9 100644 --- a/include/drm/drm_fb_helper.h +++ b/include/drm/drm_fb_helper.h @@ -32,6 +32,7 @@ struct drm_fb_helper; +#include #include #include #include @@ -154,6 +155,20 @@ struct drm_fb_helper_connector { * operations. */ struct drm_fb_helper { + /** + * @client: + * + * DRM client used by the generic fbdev emulation. + */ + struct drm_client_dev client; + + /** + * @buffer: + * + * Framebuffer used by the generic fbdev emulation. + */ + struct drm_client_buffer *buffer; + struct drm_framebuffer *fb; struct drm_device *dev; int crtc_count; @@ -234,6 +249,12 @@ struct drm_fb_helper { int preferred_bpp; }; +static inline struct drm_fb_helper * +drm_fb_helper_from_client(struct drm_client_dev *client) +{ + return container_of(client, struct drm_fb_helper, client); +} + /** * define DRM_FB_HELPER_DEFAULT_OPS - helper define for drm drivers * @@ -330,6 +351,9 @@ void drm_fb_helper_fbdev_teardown(struct drm_device *dev); void drm_fb_helper_lastclose(struct drm_device *dev); void drm_fb_helper_output_poll_changed(struct drm_device *dev); + +int drm_fb_helper_generic_probe(struct drm_fb_helper *fb_helper, + struct drm_fb_helper_surface_size *sizes); #else static inline void drm_fb_helper_prepare(struct drm_device *dev, struct drm_fb_helper *helper, @@ -564,6 +588,13 @@ static inline void drm_fb_helper_output_poll_changed(struct drm_device *dev) { } +static inline int +drm_fb_helper_generic_probe(struct drm_fb_helper *fb_helper, + struct drm_fb_helper_surface_size *sizes) +{ + return 0; +} + #endif static inline int -- cgit v1.2.3 From 894a677f4b3e6d2ab8d01bb46c1fbd5f92e4591b Mon Sep 17 00:00:00 2001 From: Noralf Trønnes Date: Tue, 3 Jul 2018 18:03:50 +0200 Subject: drm/cma-helper: Use the generic fbdev emulation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This switches the CMA helper drivers that use its fbdev emulation over to the generic fbdev emulation. It's the first phase of using generic fbdev. A later phase will use DRM client callbacks for the lastclose/hotplug/remove callbacks. There are currently 2 fbdev init/fini functions: - drm_fb_cma_fbdev_init/drm_fb_cma_fbdev_fini - drm_fbdev_cma_init/drm_fbdev_cma_fini This is because the work on generic fbdev came up during a fbdev refactoring and thus wasn't completed. No point in completing that refactoring when drivers will soon move to drm_fb_helper_generic_probe(). tinydrm uses drm_fb_cma_fbdev_init_with_funcs(). Cc: Laurent Pinchart Signed-off-by: Noralf Trønnes Acked-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20180703160354.59955-5-noralf@tronnes.org --- drivers/gpu/drm/drm_fb_cma_helper.c | 338 ++++-------------------------------- include/drm/drm_fb_cma_helper.h | 3 - 2 files changed, 31 insertions(+), 310 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_fb_cma_helper.c b/drivers/gpu/drm/drm_fb_cma_helper.c index 186d00adfb5f..718c7f961d8a 100644 --- a/drivers/gpu/drm/drm_fb_cma_helper.c +++ b/drivers/gpu/drm/drm_fb_cma_helper.c @@ -18,6 +18,7 @@ */ #include +#include #include #include #include @@ -26,11 +27,8 @@ #include #include -#define DEFAULT_FBDEFIO_DELAY_MS 50 - struct drm_fbdev_cma { struct drm_fb_helper fb_helper; - const struct drm_framebuffer_funcs *fb_funcs; }; /** @@ -44,36 +42,6 @@ struct drm_fbdev_cma { * * An fbdev framebuffer backed by cma is also available by calling * drm_fb_cma_fbdev_init(). drm_fb_cma_fbdev_fini() tears it down. - * If the &drm_framebuffer_funcs.dirty callback is set, fb_deferred_io will be - * set up automatically. &drm_framebuffer_funcs.dirty is called by - * drm_fb_helper_deferred_io() in process context (&struct delayed_work). - * - * Example fbdev deferred io code:: - * - * static int driver_fb_dirty(struct drm_framebuffer *fb, - * struct drm_file *file_priv, - * unsigned flags, unsigned color, - * struct drm_clip_rect *clips, - * unsigned num_clips) - * { - * struct drm_gem_cma_object *cma = drm_fb_cma_get_gem_obj(fb, 0); - * ... push changes ... - * return 0; - * } - * - * static struct drm_framebuffer_funcs driver_fb_funcs = { - * .destroy = drm_gem_fb_destroy, - * .create_handle = drm_gem_fb_create_handle, - * .dirty = driver_fb_dirty, - * }; - * - * Initialize:: - * - * fbdev = drm_fb_cma_fbdev_init_with_funcs(dev, 16, - * dev->mode_config.num_crtc, - * dev->mode_config.num_connector, - * &driver_fb_funcs); - * */ static inline struct drm_fbdev_cma *to_fbdev_cma(struct drm_fb_helper *helper) @@ -131,153 +99,6 @@ dma_addr_t drm_fb_cma_get_gem_addr(struct drm_framebuffer *fb, } EXPORT_SYMBOL_GPL(drm_fb_cma_get_gem_addr); -static int drm_fb_cma_mmap(struct fb_info *info, struct vm_area_struct *vma) -{ - return dma_mmap_writecombine(info->device, vma, info->screen_base, - info->fix.smem_start, info->fix.smem_len); -} - -static struct fb_ops drm_fbdev_cma_ops = { - .owner = THIS_MODULE, - DRM_FB_HELPER_DEFAULT_OPS, - .fb_fillrect = drm_fb_helper_sys_fillrect, - .fb_copyarea = drm_fb_helper_sys_copyarea, - .fb_imageblit = drm_fb_helper_sys_imageblit, - .fb_mmap = drm_fb_cma_mmap, -}; - -static int drm_fbdev_cma_deferred_io_mmap(struct fb_info *info, - struct vm_area_struct *vma) -{ - fb_deferred_io_mmap(info, vma); - vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot); - - return 0; -} - -static int drm_fbdev_cma_defio_init(struct fb_info *fbi, - struct drm_gem_cma_object *cma_obj) -{ - struct fb_deferred_io *fbdefio; - struct fb_ops *fbops; - - /* - * Per device structures are needed because: - * fbops: fb_deferred_io_cleanup() clears fbops.fb_mmap - * fbdefio: individual delays - */ - fbdefio = kzalloc(sizeof(*fbdefio), GFP_KERNEL); - fbops = kzalloc(sizeof(*fbops), GFP_KERNEL); - if (!fbdefio || !fbops) { - kfree(fbdefio); - kfree(fbops); - return -ENOMEM; - } - - /* can't be offset from vaddr since dirty() uses cma_obj */ - fbi->screen_buffer = cma_obj->vaddr; - /* fb_deferred_io_fault() needs a physical address */ - fbi->fix.smem_start = page_to_phys(virt_to_page(fbi->screen_buffer)); - - *fbops = *fbi->fbops; - fbi->fbops = fbops; - - fbdefio->delay = msecs_to_jiffies(DEFAULT_FBDEFIO_DELAY_MS); - fbdefio->deferred_io = drm_fb_helper_deferred_io; - fbi->fbdefio = fbdefio; - fb_deferred_io_init(fbi); - fbi->fbops->fb_mmap = drm_fbdev_cma_deferred_io_mmap; - - return 0; -} - -static void drm_fbdev_cma_defio_fini(struct fb_info *fbi) -{ - if (!fbi->fbdefio) - return; - - fb_deferred_io_cleanup(fbi); - kfree(fbi->fbdefio); - kfree(fbi->fbops); -} - -static int -drm_fbdev_cma_create(struct drm_fb_helper *helper, - struct drm_fb_helper_surface_size *sizes) -{ - struct drm_fbdev_cma *fbdev_cma = to_fbdev_cma(helper); - struct drm_device *dev = helper->dev; - struct drm_gem_cma_object *obj; - struct drm_framebuffer *fb; - unsigned int bytes_per_pixel; - unsigned long offset; - struct fb_info *fbi; - size_t size; - int ret; - - DRM_DEBUG_KMS("surface width(%d), height(%d) and bpp(%d)\n", - sizes->surface_width, sizes->surface_height, - sizes->surface_bpp); - - bytes_per_pixel = DIV_ROUND_UP(sizes->surface_bpp, 8); - size = sizes->surface_width * sizes->surface_height * bytes_per_pixel; - obj = drm_gem_cma_create(dev, size); - if (IS_ERR(obj)) - return -ENOMEM; - - fbi = drm_fb_helper_alloc_fbi(helper); - if (IS_ERR(fbi)) { - ret = PTR_ERR(fbi); - goto err_gem_free_object; - } - - fb = drm_gem_fbdev_fb_create(dev, sizes, 0, &obj->base, - fbdev_cma->fb_funcs); - if (IS_ERR(fb)) { - dev_err(dev->dev, "Failed to allocate DRM framebuffer.\n"); - ret = PTR_ERR(fb); - goto err_fb_info_destroy; - } - - helper->fb = fb; - - fbi->par = helper; - fbi->flags = FBINFO_FLAG_DEFAULT; - fbi->fbops = &drm_fbdev_cma_ops; - - drm_fb_helper_fill_fix(fbi, fb->pitches[0], fb->format->depth); - drm_fb_helper_fill_var(fbi, helper, sizes->fb_width, sizes->fb_height); - - offset = fbi->var.xoffset * bytes_per_pixel; - offset += fbi->var.yoffset * fb->pitches[0]; - - dev->mode_config.fb_base = (resource_size_t)obj->paddr; - fbi->screen_base = obj->vaddr + offset; - fbi->fix.smem_start = (unsigned long)(obj->paddr + offset); - fbi->screen_size = size; - fbi->fix.smem_len = size; - - if (fb->funcs->dirty) { - ret = drm_fbdev_cma_defio_init(fbi, obj); - if (ret) - goto err_cma_destroy; - } - - return 0; - -err_cma_destroy: - drm_framebuffer_remove(fb); -err_fb_info_destroy: - drm_fb_helper_fini(helper); -err_gem_free_object: - drm_gem_object_put_unlocked(&obj->base); - return ret; -} - -static const struct drm_fb_helper_funcs drm_fb_cma_helper_funcs = { - .fb_probe = drm_fbdev_cma_create, -}; - /** * drm_fb_cma_fbdev_init_with_funcs() - Allocate and initialize fbdev emulation * @dev: DRM device @@ -295,53 +116,7 @@ int drm_fb_cma_fbdev_init_with_funcs(struct drm_device *dev, unsigned int preferred_bpp, unsigned int max_conn_count, const struct drm_framebuffer_funcs *funcs) { - struct drm_fbdev_cma *fbdev_cma; - struct drm_fb_helper *fb_helper; - int ret; - - if (!preferred_bpp) - preferred_bpp = dev->mode_config.preferred_depth; - if (!preferred_bpp) - preferred_bpp = 32; - - if (!max_conn_count) - max_conn_count = dev->mode_config.num_connector; - - fbdev_cma = kzalloc(sizeof(*fbdev_cma), GFP_KERNEL); - if (!fbdev_cma) - return -ENOMEM; - - fbdev_cma->fb_funcs = funcs; - fb_helper = &fbdev_cma->fb_helper; - - drm_fb_helper_prepare(dev, fb_helper, &drm_fb_cma_helper_funcs); - - ret = drm_fb_helper_init(dev, fb_helper, max_conn_count); - if (ret < 0) { - DRM_DEV_ERROR(dev->dev, "Failed to initialize fbdev helper.\n"); - goto err_free; - } - - ret = drm_fb_helper_single_add_all_connectors(fb_helper); - if (ret < 0) { - DRM_DEV_ERROR(dev->dev, "Failed to add connectors.\n"); - goto err_drm_fb_helper_fini; - } - - ret = drm_fb_helper_initial_config(fb_helper, preferred_bpp); - if (ret < 0) { - DRM_DEV_ERROR(dev->dev, "Failed to set fbdev configuration.\n"); - goto err_drm_fb_helper_fini; - } - - return 0; - -err_drm_fb_helper_fini: - drm_fb_helper_fini(fb_helper); -err_free: - kfree(fbdev_cma); - - return ret; + return drm_fb_cma_fbdev_init(dev, preferred_bpp, max_conn_count); } EXPORT_SYMBOL_GPL(drm_fb_cma_fbdev_init_with_funcs); @@ -359,8 +134,14 @@ EXPORT_SYMBOL_GPL(drm_fb_cma_fbdev_init_with_funcs); int drm_fb_cma_fbdev_init(struct drm_device *dev, unsigned int preferred_bpp, unsigned int max_conn_count) { - return drm_fb_cma_fbdev_init_with_funcs(dev, preferred_bpp, - max_conn_count, NULL); + struct drm_fbdev_cma *fbdev_cma; + + /* dev->fb_helper will indirectly point to fbdev_cma after this call */ + fbdev_cma = drm_fbdev_cma_init(dev, preferred_bpp, max_conn_count); + if (IS_ERR(fbdev_cma)) + return PTR_ERR(fbdev_cma); + + return 0; } EXPORT_SYMBOL_GPL(drm_fb_cma_fbdev_init); @@ -370,104 +151,54 @@ EXPORT_SYMBOL_GPL(drm_fb_cma_fbdev_init); */ void drm_fb_cma_fbdev_fini(struct drm_device *dev) { - struct drm_fb_helper *fb_helper = dev->fb_helper; - - if (!fb_helper) - return; - - /* Unregister if it hasn't been done already */ - if (fb_helper->fbdev && fb_helper->fbdev->dev) - drm_fb_helper_unregister_fbi(fb_helper); - - if (fb_helper->fbdev) - drm_fbdev_cma_defio_fini(fb_helper->fbdev); - - if (fb_helper->fb) - drm_framebuffer_remove(fb_helper->fb); - - drm_fb_helper_fini(fb_helper); - kfree(to_fbdev_cma(fb_helper)); + if (dev->fb_helper) + drm_fbdev_cma_fini(to_fbdev_cma(dev->fb_helper)); } EXPORT_SYMBOL_GPL(drm_fb_cma_fbdev_fini); +static const struct drm_fb_helper_funcs drm_fb_cma_helper_funcs = { + .fb_probe = drm_fb_helper_generic_probe, +}; + /** - * drm_fbdev_cma_init_with_funcs() - Allocate and initializes a drm_fbdev_cma struct + * drm_fbdev_cma_init() - Allocate and initializes a drm_fbdev_cma struct * @dev: DRM device * @preferred_bpp: Preferred bits per pixel for the device * @max_conn_count: Maximum number of connectors - * @funcs: fb helper functions, in particular a custom dirty() callback * * Returns a newly allocated drm_fbdev_cma struct or a ERR_PTR. */ -struct drm_fbdev_cma *drm_fbdev_cma_init_with_funcs(struct drm_device *dev, - unsigned int preferred_bpp, unsigned int max_conn_count, - const struct drm_framebuffer_funcs *funcs) +struct drm_fbdev_cma *drm_fbdev_cma_init(struct drm_device *dev, + unsigned int preferred_bpp, unsigned int max_conn_count) { struct drm_fbdev_cma *fbdev_cma; - struct drm_fb_helper *helper; + struct drm_fb_helper *fb_helper; int ret; fbdev_cma = kzalloc(sizeof(*fbdev_cma), GFP_KERNEL); - if (!fbdev_cma) { - dev_err(dev->dev, "Failed to allocate drm fbdev.\n"); + if (!fbdev_cma) return ERR_PTR(-ENOMEM); - } - fbdev_cma->fb_funcs = funcs; - - helper = &fbdev_cma->fb_helper; - drm_fb_helper_prepare(dev, helper, &drm_fb_cma_helper_funcs); + fb_helper = &fbdev_cma->fb_helper; - ret = drm_fb_helper_init(dev, helper, max_conn_count); - if (ret < 0) { - dev_err(dev->dev, "Failed to initialize drm fb helper.\n"); + ret = drm_client_new(dev, &fb_helper->client, "fbdev", NULL); + if (ret) goto err_free; - } - - ret = drm_fb_helper_single_add_all_connectors(helper); - if (ret < 0) { - dev_err(dev->dev, "Failed to add connectors.\n"); - goto err_drm_fb_helper_fini; - } - - ret = drm_fb_helper_initial_config(helper, preferred_bpp); - if (ret < 0) { - dev_err(dev->dev, "Failed to set initial hw configuration.\n"); - goto err_drm_fb_helper_fini; - } + ret = drm_fb_helper_fbdev_setup(dev, fb_helper, &drm_fb_cma_helper_funcs, + preferred_bpp, max_conn_count); + if (ret) + goto err_client_put; return fbdev_cma; -err_drm_fb_helper_fini: - drm_fb_helper_fini(helper); +err_client_put: + drm_client_release(&fb_helper->client); err_free: kfree(fbdev_cma); return ERR_PTR(ret); } -EXPORT_SYMBOL_GPL(drm_fbdev_cma_init_with_funcs); - -static const struct drm_framebuffer_funcs drm_fb_cma_funcs = { - .destroy = drm_gem_fb_destroy, - .create_handle = drm_gem_fb_create_handle, -}; - -/** - * drm_fbdev_cma_init() - Allocate and initializes a drm_fbdev_cma struct - * @dev: DRM device - * @preferred_bpp: Preferred bits per pixel for the device - * @max_conn_count: Maximum number of connectors - * - * Returns a newly allocated drm_fbdev_cma struct or a ERR_PTR. - */ -struct drm_fbdev_cma *drm_fbdev_cma_init(struct drm_device *dev, - unsigned int preferred_bpp, unsigned int max_conn_count) -{ - return drm_fbdev_cma_init_with_funcs(dev, preferred_bpp, - max_conn_count, - &drm_fb_cma_funcs); -} EXPORT_SYMBOL_GPL(drm_fbdev_cma_init); /** @@ -477,14 +208,7 @@ EXPORT_SYMBOL_GPL(drm_fbdev_cma_init); void drm_fbdev_cma_fini(struct drm_fbdev_cma *fbdev_cma) { drm_fb_helper_unregister_fbi(&fbdev_cma->fb_helper); - if (fbdev_cma->fb_helper.fbdev) - drm_fbdev_cma_defio_fini(fbdev_cma->fb_helper.fbdev); - - if (fbdev_cma->fb_helper.fb) - drm_framebuffer_remove(fbdev_cma->fb_helper.fb); - - drm_fb_helper_fini(&fbdev_cma->fb_helper); - kfree(fbdev_cma); + /* All resources have now been freed by drm_fbdev_fb_destroy() */ } EXPORT_SYMBOL_GPL(drm_fbdev_cma_fini); diff --git a/include/drm/drm_fb_cma_helper.h b/include/drm/drm_fb_cma_helper.h index d532f88a8d55..a0546c3451f9 100644 --- a/include/drm/drm_fb_cma_helper.h +++ b/include/drm/drm_fb_cma_helper.h @@ -23,9 +23,6 @@ int drm_fb_cma_fbdev_init(struct drm_device *dev, unsigned int preferred_bpp, unsigned int max_conn_count); void drm_fb_cma_fbdev_fini(struct drm_device *dev); -struct drm_fbdev_cma *drm_fbdev_cma_init_with_funcs(struct drm_device *dev, - unsigned int preferred_bpp, unsigned int max_conn_count, - const struct drm_framebuffer_funcs *funcs); struct drm_fbdev_cma *drm_fbdev_cma_init(struct drm_device *dev, unsigned int preferred_bpp, unsigned int max_conn_count); void drm_fbdev_cma_fini(struct drm_fbdev_cma *fbdev_cma); -- cgit v1.2.3 From e896c132eb2cb4975d99477ea7e95aedb6dffa95 Mon Sep 17 00:00:00 2001 From: Noralf Trønnes Date: Tue, 3 Jul 2018 18:03:51 +0200 Subject: drm/debugfs: Add internal client debugfs file MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Print the names of the internal clients currently attached. Reviewed-by: Daniel Vetter Signed-off-by: Noralf Trønnes Link: https://patchwork.freedesktop.org/patch/msgid/20180703160354.59955-6-noralf@tronnes.org --- drivers/gpu/drm/drm_client.c | 28 ++++++++++++++++++++++++++++ drivers/gpu/drm/drm_debugfs.c | 7 +++++++ include/drm/drm_client.h | 3 +++ 3 files changed, 38 insertions(+) (limited to 'include') diff --git a/drivers/gpu/drm/drm_client.c b/drivers/gpu/drm/drm_client.c index 743495f7f833..4039a4d103a8 100644 --- a/drivers/gpu/drm/drm_client.c +++ b/drivers/gpu/drm/drm_client.c @@ -385,3 +385,31 @@ void drm_client_framebuffer_delete(struct drm_client_buffer *buffer) drm_client_buffer_delete(buffer); } EXPORT_SYMBOL(drm_client_framebuffer_delete); + +#ifdef CONFIG_DEBUG_FS +static int drm_client_debugfs_internal_clients(struct seq_file *m, void *data) +{ + struct drm_info_node *node = m->private; + struct drm_device *dev = node->minor->dev; + struct drm_printer p = drm_seq_file_printer(m); + struct drm_client_dev *client; + + mutex_lock(&dev->clientlist_mutex); + list_for_each_entry(client, &dev->clientlist, list) + drm_printf(&p, "%s\n", client->name); + mutex_unlock(&dev->clientlist_mutex); + + return 0; +} + +static const struct drm_info_list drm_client_debugfs_list[] = { + { "internal_clients", drm_client_debugfs_internal_clients, 0 }, +}; + +int drm_client_debugfs_init(struct drm_minor *minor) +{ + return drm_debugfs_create_files(drm_client_debugfs_list, + ARRAY_SIZE(drm_client_debugfs_list), + minor->debugfs_root, minor); +} +#endif diff --git a/drivers/gpu/drm/drm_debugfs.c b/drivers/gpu/drm/drm_debugfs.c index b2482818fee8..50a20bfc07ea 100644 --- a/drivers/gpu/drm/drm_debugfs.c +++ b/drivers/gpu/drm/drm_debugfs.c @@ -28,6 +28,7 @@ #include #include +#include #include #include #include @@ -164,6 +165,12 @@ int drm_debugfs_init(struct drm_minor *minor, int minor_id, DRM_ERROR("Failed to create framebuffer debugfs file\n"); return ret; } + + ret = drm_client_debugfs_init(minor); + if (ret) { + DRM_ERROR("Failed to create client debugfs file\n"); + return ret; + } } if (dev->driver->debugfs_init) { diff --git a/include/drm/drm_client.h b/include/drm/drm_client.h index 671052d80e38..989f8e52864d 100644 --- a/include/drm/drm_client.h +++ b/include/drm/drm_client.h @@ -10,6 +10,7 @@ struct drm_device; struct drm_file; struct drm_framebuffer; struct drm_gem_object; +struct drm_minor; struct module; /** @@ -133,4 +134,6 @@ struct drm_client_buffer * drm_client_framebuffer_create(struct drm_client_dev *client, u32 width, u32 height, u32 format); void drm_client_framebuffer_delete(struct drm_client_buffer *buffer); +int drm_client_debugfs_init(struct drm_minor *minor); + #endif -- cgit v1.2.3 From 9060d7f49376159dcc500a97cb247ca8e4b98f48 Mon Sep 17 00:00:00 2001 From: Noralf Trønnes Date: Tue, 3 Jul 2018 18:03:52 +0200 Subject: drm/fb-helper: Finish the generic fbdev emulation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This adds a drm_fbdev_generic_setup() function that sets up generic fbdev emulation with client callbacks for restore, hotplug and unregister. Signed-off-by: Noralf Trønnes Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20180703160354.59955-7-noralf@tronnes.org --- drivers/gpu/drm/drm_fb_helper.c | 117 ++++++++++++++++++++++++++++++++++++++++ include/drm/drm_fb_helper.h | 7 +++ 2 files changed, 124 insertions(+) (limited to 'include') diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index 7e29d5340a17..4b0dd20bccb8 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -67,6 +67,9 @@ static DEFINE_MUTEX(kernel_fb_helper_lock); * helper functions used by many drivers to implement the kernel mode setting * interfaces. * + * Drivers that support a dumb buffer with a virtual address and mmap support, + * should try out the generic fbdev emulation using drm_fbdev_generic_setup(). + * * Setup fbdev emulation by calling drm_fb_helper_fbdev_setup() and tear it * down by calling drm_fb_helper_fbdev_teardown(). * @@ -3118,6 +3121,120 @@ err_free_buffer: } EXPORT_SYMBOL(drm_fb_helper_generic_probe); +static const struct drm_fb_helper_funcs drm_fb_helper_generic_funcs = { + .fb_probe = drm_fb_helper_generic_probe, +}; + +static void drm_fbdev_client_unregister(struct drm_client_dev *client) +{ + struct drm_fb_helper *fb_helper = drm_fb_helper_from_client(client); + + if (fb_helper->fbdev) { + drm_fb_helper_unregister_fbi(fb_helper); + /* drm_fbdev_fb_destroy() takes care of cleanup */ + return; + } + + /* Did drm_fb_helper_fbdev_setup() run? */ + if (fb_helper->dev) + drm_fb_helper_fini(fb_helper); + + drm_client_release(client); + kfree(fb_helper); +} + +static int drm_fbdev_client_restore(struct drm_client_dev *client) +{ + struct drm_fb_helper *fb_helper = drm_fb_helper_from_client(client); + + drm_fb_helper_restore_fbdev_mode_unlocked(fb_helper); + + return 0; +} + +static int drm_fbdev_client_hotplug(struct drm_client_dev *client) +{ + struct drm_fb_helper *fb_helper = drm_fb_helper_from_client(client); + struct drm_device *dev = client->dev; + int ret; + + /* If drm_fb_helper_fbdev_setup() failed, we only try once */ + if (!fb_helper->dev && fb_helper->funcs) + return 0; + + if (dev->fb_helper) + return drm_fb_helper_hotplug_event(dev->fb_helper); + + if (!dev->mode_config.num_connector) + return 0; + + ret = drm_fb_helper_fbdev_setup(dev, fb_helper, &drm_fb_helper_generic_funcs, + fb_helper->preferred_bpp, 0); + if (ret) { + fb_helper->dev = NULL; + fb_helper->fbdev = NULL; + return ret; + } + + return 0; +} + +static const struct drm_client_funcs drm_fbdev_client_funcs = { + .owner = THIS_MODULE, + .unregister = drm_fbdev_client_unregister, + .restore = drm_fbdev_client_restore, + .hotplug = drm_fbdev_client_hotplug, +}; + +/** + * drm_fb_helper_generic_fbdev_setup() - Setup generic fbdev emulation + * @dev: DRM device + * @preferred_bpp: Preferred bits per pixel for the device. + * @dev->mode_config.preferred_depth is used if this is zero. + * + * This function sets up generic fbdev emulation for drivers that supports + * dumb buffers with a virtual address and that can be mmap'ed. + * + * Restore, hotplug events and teardown are all taken care of. Drivers that do + * suspend/resume need to call drm_fb_helper_set_suspend_unlocked() themselves. + * Simple drivers might use drm_mode_config_helper_suspend(). + * + * Drivers that set the dirty callback on their framebuffer will get a shadow + * fbdev buffer that is blitted onto the real buffer. This is done in order to + * make deferred I/O work with all kinds of buffers. + * + * This function is safe to call even when there are no connectors present. + * Setup will be retried on the next hotplug event. + * + * Returns: + * Zero on success or negative error code on failure. + */ +int drm_fbdev_generic_setup(struct drm_device *dev, unsigned int preferred_bpp) +{ + struct drm_fb_helper *fb_helper; + int ret; + + if (!drm_fbdev_emulation) + return 0; + + fb_helper = kzalloc(sizeof(*fb_helper), GFP_KERNEL); + if (!fb_helper) + return -ENOMEM; + + ret = drm_client_new(dev, &fb_helper->client, "fbdev", &drm_fbdev_client_funcs); + if (ret) { + kfree(fb_helper); + return ret; + } + + fb_helper->preferred_bpp = preferred_bpp; + + drm_fbdev_client_hotplug(&fb_helper->client); + + return 0; +} +EXPORT_SYMBOL(drm_fbdev_generic_setup); + /* The Kconfig DRM_KMS_HELPER selects FRAMEBUFFER_CONSOLE (if !EXPERT) * but the module doesn't depend on any fb console symbols. At least * attempt to load fbcon to avoid leaving the system without a usable console. diff --git a/include/drm/drm_fb_helper.h b/include/drm/drm_fb_helper.h index c134bbcfd2e9..5db08c8f1d25 100644 --- a/include/drm/drm_fb_helper.h +++ b/include/drm/drm_fb_helper.h @@ -354,6 +354,7 @@ void drm_fb_helper_output_poll_changed(struct drm_device *dev); int drm_fb_helper_generic_probe(struct drm_fb_helper *fb_helper, struct drm_fb_helper_surface_size *sizes); +int drm_fbdev_generic_setup(struct drm_device *dev, unsigned int preferred_bpp); #else static inline void drm_fb_helper_prepare(struct drm_device *dev, struct drm_fb_helper *helper, @@ -595,6 +596,12 @@ drm_fb_helper_generic_probe(struct drm_fb_helper *fb_helper, return 0; } +static inline int +drm_fbdev_generic_setup(struct drm_device *dev, unsigned int preferred_bpp) +{ + return 0; +} + #endif static inline int -- cgit v1.2.3 From 85b5bafb86e64f5d0ef143ab1a8363f5511eaabb Mon Sep 17 00:00:00 2001 From: Noralf Trønnes Date: Tue, 3 Jul 2018 18:03:54 +0200 Subject: drm/cma-helper: Remove drm_fb_cma_fbdev_init_with_funcs() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Remove drm_fb_cma_fbdev_init_with_funcs(), its only user tinydrm has moved to drm_fbdev_generic_setup(). Cc: Laurent Pinchart Signed-off-by: Noralf Trønnes Reviewed-by: David Lechner Link: https://patchwork.freedesktop.org/patch/msgid/20180703160354.59955-9-noralf@tronnes.org --- drivers/gpu/drm/drm_fb_cma_helper.c | 21 --------------------- include/drm/drm_fb_cma_helper.h | 3 --- 2 files changed, 24 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_fb_cma_helper.c b/drivers/gpu/drm/drm_fb_cma_helper.c index 718c7f961d8a..9da36a6271d3 100644 --- a/drivers/gpu/drm/drm_fb_cma_helper.c +++ b/drivers/gpu/drm/drm_fb_cma_helper.c @@ -99,27 +99,6 @@ dma_addr_t drm_fb_cma_get_gem_addr(struct drm_framebuffer *fb, } EXPORT_SYMBOL_GPL(drm_fb_cma_get_gem_addr); -/** - * drm_fb_cma_fbdev_init_with_funcs() - Allocate and initialize fbdev emulation - * @dev: DRM device - * @preferred_bpp: Preferred bits per pixel for the device. - * @dev->mode_config.preferred_depth is used if this is zero. - * @max_conn_count: Maximum number of connectors. - * @dev->mode_config.num_connector is used if this is zero. - * @funcs: Framebuffer functions, in particular a custom dirty() callback. - * Can be NULL. - * - * Returns: - * Zero on success or negative error code on failure. - */ -int drm_fb_cma_fbdev_init_with_funcs(struct drm_device *dev, - unsigned int preferred_bpp, unsigned int max_conn_count, - const struct drm_framebuffer_funcs *funcs) -{ - return drm_fb_cma_fbdev_init(dev, preferred_bpp, max_conn_count); -} -EXPORT_SYMBOL_GPL(drm_fb_cma_fbdev_init_with_funcs); - /** * drm_fb_cma_fbdev_init() - Allocate and initialize fbdev emulation * @dev: DRM device diff --git a/include/drm/drm_fb_cma_helper.h b/include/drm/drm_fb_cma_helper.h index a0546c3451f9..96e26e3b9a0c 100644 --- a/include/drm/drm_fb_cma_helper.h +++ b/include/drm/drm_fb_cma_helper.h @@ -16,9 +16,6 @@ struct drm_mode_fb_cmd2; struct drm_plane; struct drm_plane_state; -int drm_fb_cma_fbdev_init_with_funcs(struct drm_device *dev, - unsigned int preferred_bpp, unsigned int max_conn_count, - const struct drm_framebuffer_funcs *funcs); int drm_fb_cma_fbdev_init(struct drm_device *dev, unsigned int preferred_bpp, unsigned int max_conn_count); void drm_fb_cma_fbdev_fini(struct drm_device *dev); -- cgit v1.2.3 From aef92a8bed25d03b8f03ce499a56e8e8e5e2c05e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 10 Jul 2018 13:42:10 +0200 Subject: watchdog/softlockup: Fix the SOFTLOCKUP_DETECTOR=n build I got confused by all the various CONFIG options here about and conflated CONFIG_LOCKUP_DETECTOR and CONFIG_SOFTLOCKUP_DETECTOR. This results in a build failure for: CONFIG_LOCKUP_DETECTOR=y && CONFIG_SOFTLOCKUP_DETECTOR=n As reported by Abdul. Reported-and-tested-by: Abdul Haleem Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-next Cc: linuxppc-dev Cc: mpe Cc: sachinp Cc: stephen Rothwell Fixes: 9cf57731b63e ("watchdog/softlockup: Replace "watchdog/%u" threads with cpu_stop_work") Link: http://lkml.kernel.org/r/20180710114210.GI2476@hirez.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- include/linux/nmi.h | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 80664bbeca43..08f9247e9827 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -33,15 +33,10 @@ extern int sysctl_hardlockup_all_cpu_backtrace; #define sysctl_hardlockup_all_cpu_backtrace 0 #endif /* !CONFIG_SMP */ -extern int lockup_detector_online_cpu(unsigned int cpu); -extern int lockup_detector_offline_cpu(unsigned int cpu); - #else /* CONFIG_LOCKUP_DETECTOR */ static inline void lockup_detector_init(void) { } static inline void lockup_detector_soft_poweroff(void) { } static inline void lockup_detector_cleanup(void) { } -#define lockup_detector_online_cpu NULL -#define lockup_detector_offline_cpu NULL #endif /* !CONFIG_LOCKUP_DETECTOR */ #ifdef CONFIG_SOFTLOCKUP_DETECTOR @@ -50,12 +45,18 @@ extern void touch_softlockup_watchdog(void); extern void touch_softlockup_watchdog_sync(void); extern void touch_all_softlockup_watchdogs(void); extern unsigned int softlockup_panic; -#else + +extern int lockup_detector_online_cpu(unsigned int cpu); +extern int lockup_detector_offline_cpu(unsigned int cpu); +#else /* CONFIG_SOFTLOCKUP_DETECTOR */ static inline void touch_softlockup_watchdog_sched(void) { } static inline void touch_softlockup_watchdog(void) { } static inline void touch_softlockup_watchdog_sync(void) { } static inline void touch_all_softlockup_watchdogs(void) { } -#endif + +#define lockup_detector_online_cpu NULL +#define lockup_detector_offline_cpu NULL +#endif /* CONFIG_SOFTLOCKUP_DETECTOR */ #ifdef CONFIG_DETECT_HUNG_TASK void reset_hung_task_detector(void); -- cgit v1.2.3 From 5fa8e4a22182df8ea39adeba4bd518506e26a96d Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Wed, 9 May 2018 15:00:39 +0200 Subject: drm/panel: Make of_drm_find_panel() return an ERR_PTR() instead of NULL Right now, the DRM panel logic returns NULL when a panel pointing to the passed OF node is not present in the list of registered panels. Most drivers interpret this NULL value as -EPROBE_DEFER, but we are about to modify the semantic of of_drm_find_panel() and let the framework return -ENODEV when the device node we're pointing to has a status property that is not equal to "okay" or "ok". Let's first patch the of_drm_find_panel() implementation to return ERR_PTR(-EPROBE_DEFER) instead of NULL and patch all callers to replace the '!panel' check by an 'IS_ERR(panel)' one. Signed-off-by: Boris Brezillon Signed-off-by: Thierry Reding Link: https://patchwork.freedesktop.org/patch/msgid/20180509130042.9435-2-boris.brezillon@bootlin.com --- drivers/gpu/drm/bridge/cdns-dsi.c | 2 +- drivers/gpu/drm/bridge/lvds-encoder.c | 4 ++-- drivers/gpu/drm/drm_of.c | 4 +++- drivers/gpu/drm/drm_panel.c | 6 ++++-- drivers/gpu/drm/exynos/exynos_dp.c | 6 ++++-- drivers/gpu/drm/exynos/exynos_drm_dpi.c | 4 ++-- drivers/gpu/drm/exynos/exynos_drm_dsi.c | 3 +++ drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c | 5 +++-- drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c | 4 ++-- drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c | 5 ++++- drivers/gpu/drm/msm/dsi/dsi_host.c | 2 +- drivers/gpu/drm/rcar-du/rcar_lvds.c | 4 ++-- drivers/gpu/drm/rockchip/dw-mipi-dsi.c | 2 +- drivers/gpu/drm/sti/sti_dvo.c | 4 +++- drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c | 4 ++-- drivers/gpu/drm/tegra/dsi.c | 3 +++ drivers/gpu/drm/tegra/output.c | 4 ++-- include/drm/drm_panel.h | 2 +- 18 files changed, 43 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/bridge/cdns-dsi.c b/drivers/gpu/drm/bridge/cdns-dsi.c index f2d43f24acfb..ce9496d13986 100644 --- a/drivers/gpu/drm/bridge/cdns-dsi.c +++ b/drivers/gpu/drm/bridge/cdns-dsi.c @@ -1152,7 +1152,7 @@ static int cdns_dsi_attach(struct mipi_dsi_host *host, np = of_node_get(dev->dev.of_node); panel = of_drm_find_panel(np); - if (panel) { + if (!IS_ERR(panel)) { bridge = drm_panel_bridge_add(panel, DRM_MODE_CONNECTOR_DSI); } else { bridge = of_drm_find_bridge(dev->dev.of_node); diff --git a/drivers/gpu/drm/bridge/lvds-encoder.c b/drivers/gpu/drm/bridge/lvds-encoder.c index 75b0d3f6e4de..f56c92f7af7c 100644 --- a/drivers/gpu/drm/bridge/lvds-encoder.c +++ b/drivers/gpu/drm/bridge/lvds-encoder.c @@ -68,9 +68,9 @@ static int lvds_encoder_probe(struct platform_device *pdev) panel = of_drm_find_panel(panel_node); of_node_put(panel_node); - if (!panel) { + if (IS_ERR(panel)) { dev_dbg(&pdev->dev, "panel not found, deferring probe\n"); - return -EPROBE_DEFER; + return PTR_ERR(panel); } lvds_encoder->panel_bridge = diff --git a/drivers/gpu/drm/drm_of.c b/drivers/gpu/drm/drm_of.c index 3b8c7a6a5720..1f4a16772583 100644 --- a/drivers/gpu/drm/drm_of.c +++ b/drivers/gpu/drm/drm_of.c @@ -241,8 +241,10 @@ int drm_of_find_panel_or_bridge(const struct device_node *np, if (panel) { *panel = of_drm_find_panel(remote); - if (*panel) + if (!IS_ERR(*panel)) ret = 0; + else + *panel = NULL; } /* No panel found yet, check for a bridge next. */ diff --git a/drivers/gpu/drm/drm_panel.c b/drivers/gpu/drm/drm_panel.c index 965530a6f4cd..7e5530a04846 100644 --- a/drivers/gpu/drm/drm_panel.c +++ b/drivers/gpu/drm/drm_panel.c @@ -151,7 +151,9 @@ EXPORT_SYMBOL(drm_panel_detach); * tree node. If a matching panel is found, return a pointer to it. * * Return: A pointer to the panel registered for the specified device tree - * node or NULL if no panel matching the device tree node can be found. + * node or an ERR_PTR() if no panel matching the device tree node can be found. + * The only error that can be reported is -EPROBE_DEFER, meaning that the panel + * device has not been probed yet, and the caller should retry later. */ struct drm_panel *of_drm_find_panel(const struct device_node *np) { @@ -167,7 +169,7 @@ struct drm_panel *of_drm_find_panel(const struct device_node *np) } mutex_unlock(&panel_lock); - return NULL; + return ERR_PTR(-EPROBE_DEFER); } EXPORT_SYMBOL(of_drm_find_panel); #endif diff --git a/drivers/gpu/drm/exynos/exynos_dp.c b/drivers/gpu/drm/exynos/exynos_dp.c index 86330f396784..af7ab1ceb50f 100644 --- a/drivers/gpu/drm/exynos/exynos_dp.c +++ b/drivers/gpu/drm/exynos/exynos_dp.c @@ -232,9 +232,11 @@ static int exynos_dp_probe(struct platform_device *pdev) np = of_parse_phandle(dev->of_node, "panel", 0); if (np) { dp->plat_data.panel = of_drm_find_panel(np); + of_node_put(np); - if (!dp->plat_data.panel) - return -EPROBE_DEFER; + if (IS_ERR(dp->plat_data.panel)) + return PTR_ERR(dp->plat_data.panel); + goto out; } diff --git a/drivers/gpu/drm/exynos/exynos_drm_dpi.c b/drivers/gpu/drm/exynos/exynos_drm_dpi.c index 66945e0dc57f..5887e8522b70 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_dpi.c +++ b/drivers/gpu/drm/exynos/exynos_drm_dpi.c @@ -240,8 +240,8 @@ struct drm_encoder *exynos_dpi_probe(struct device *dev) if (ctx->panel_node) { ctx->panel = of_drm_find_panel(ctx->panel_node); - if (!ctx->panel) - return ERR_PTR(-EPROBE_DEFER); + if (IS_ERR(ctx->panel)) + return ERR_CAST(ctx->panel); } return &ctx->encoder; diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c index 6d29777884f9..809e1e0447df 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c +++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c @@ -1519,6 +1519,9 @@ static int exynos_dsi_host_attach(struct mipi_dsi_host *host, dsi->format = device->format; dsi->mode_flags = device->mode_flags; dsi->panel = of_drm_find_panel(device->dev.of_node); + if (IS_ERR(dsi->panel)) + dsi->panel = NULL; + if (dsi->panel) { drm_panel_attach(dsi->panel, &dsi->connector); dsi->connector.status = connector_status_connected; diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c index c54806d08dd7..681e2a07d03b 100644 --- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c +++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c @@ -148,8 +148,9 @@ int fsl_dcu_create_outputs(struct fsl_dcu_drm_device *fsl_dev) if (panel_node) { fsl_dev->connector.panel = of_drm_find_panel(panel_node); of_node_put(panel_node); - if (!fsl_dev->connector.panel) - return -EPROBE_DEFER; + if (IS_ERR(fsl_dev->connector.panel)) + return PTR_ERR(fsl_dev->connector.panel); + return fsl_dcu_attach_panel(fsl_dev, fsl_dev->connector.panel); } diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c index 4a645926edb7..2bfb39082f54 100644 --- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c +++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c @@ -341,7 +341,7 @@ static void mdp4_lcdc_encoder_disable(struct drm_encoder *encoder) mdp4_write(mdp4_kms, REG_MDP4_LCDC_ENABLE, 0); panel = of_drm_find_panel(mdp4_lcdc_encoder->panel_node); - if (panel) { + if (!IS_ERR(panel)) { drm_panel_disable(panel); drm_panel_unprepare(panel); } @@ -410,7 +410,7 @@ static void mdp4_lcdc_encoder_enable(struct drm_encoder *encoder) dev_err(dev->dev, "failed to enable lcdc_clk: %d\n", ret); panel = of_drm_find_panel(mdp4_lcdc_encoder->panel_node); - if (panel) { + if (!IS_ERR(panel)) { drm_panel_prepare(panel); drm_panel_enable(panel); } diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c index e3b1c86b7aae..32fba5664b0e 100644 --- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c +++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c @@ -34,9 +34,12 @@ static enum drm_connector_status mdp4_lvds_connector_detect( struct mdp4_lvds_connector *mdp4_lvds_connector = to_mdp4_lvds_connector(connector); - if (!mdp4_lvds_connector->panel) + if (!mdp4_lvds_connector->panel) { mdp4_lvds_connector->panel = of_drm_find_panel(mdp4_lvds_connector->panel_node); + if (IS_ERR(mdp4_lvds_connector->panel)) + mdp4_lvds_connector->panel = NULL; + } return mdp4_lvds_connector->panel ? connector_status_connected : diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c index 2f1a2780658a..29841f440111 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_host.c +++ b/drivers/gpu/drm/msm/dsi/dsi_host.c @@ -1898,7 +1898,7 @@ int msm_dsi_host_register(struct mipi_dsi_host *host, bool check_defer) * output */ if (check_defer && msm_host->device_node) { - if (!of_drm_find_panel(msm_host->device_node)) + if (IS_ERR(of_drm_find_panel(msm_host->device_node))) if (!of_drm_find_bridge(msm_host->device_node)) return -EPROBE_DEFER; } diff --git a/drivers/gpu/drm/rcar-du/rcar_lvds.c b/drivers/gpu/drm/rcar-du/rcar_lvds.c index 155ad840f3c5..5d8e391e75f4 100644 --- a/drivers/gpu/drm/rcar-du/rcar_lvds.c +++ b/drivers/gpu/drm/rcar-du/rcar_lvds.c @@ -434,8 +434,8 @@ static int rcar_lvds_parse_dt(struct rcar_lvds *lvds) ret = -EPROBE_DEFER; } else { lvds->panel = of_drm_find_panel(remote); - if (!lvds->panel) - ret = -EPROBE_DEFER; + if (IS_ERR(lvds->panel)) + ret = PTR_ERR(lvds->panel); } done: diff --git a/drivers/gpu/drm/rockchip/dw-mipi-dsi.c b/drivers/gpu/drm/rockchip/dw-mipi-dsi.c index d53d5a09547f..01642aaf6127 100644 --- a/drivers/gpu/drm/rockchip/dw-mipi-dsi.c +++ b/drivers/gpu/drm/rockchip/dw-mipi-dsi.c @@ -595,7 +595,7 @@ static int dw_mipi_dsi_host_attach(struct mipi_dsi_host *host, dsi->format = device->format; dsi->mode_flags = device->mode_flags; dsi->panel = of_drm_find_panel(device->dev.of_node); - if (dsi->panel) + if (!IS_ERR(dsi->panel)) return drm_panel_attach(dsi->panel, &dsi->connector); return -EINVAL; diff --git a/drivers/gpu/drm/sti/sti_dvo.c b/drivers/gpu/drm/sti/sti_dvo.c index a5979cd25cc7..030da55a8d30 100644 --- a/drivers/gpu/drm/sti/sti_dvo.c +++ b/drivers/gpu/drm/sti/sti_dvo.c @@ -387,7 +387,9 @@ sti_dvo_connector_detect(struct drm_connector *connector, bool force) if (!dvo->panel) { dvo->panel = of_drm_find_panel(dvo->panel_node); - if (dvo->panel) + if (IS_ERR(dvo->panel)) + dvo->panel = NULL; + else drm_panel_attach(dvo->panel, connector); } diff --git a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c index da9814f94d00..2b40d1f6aee8 100644 --- a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c +++ b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c @@ -833,8 +833,8 @@ static int sun6i_dsi_attach(struct mipi_dsi_host *host, dsi->device = device; dsi->panel = of_drm_find_panel(device->dev.of_node); - if (!dsi->panel) - return -EINVAL; + if (IS_ERR(dsi->panel)) + return PTR_ERR(dsi->panel); dev_info(host->dev, "Attached device %s\n", device->name); diff --git a/drivers/gpu/drm/tegra/dsi.c b/drivers/gpu/drm/tegra/dsi.c index 87c5d89bc9ba..ad88ec230329 100644 --- a/drivers/gpu/drm/tegra/dsi.c +++ b/drivers/gpu/drm/tegra/dsi.c @@ -1411,6 +1411,9 @@ static int tegra_dsi_host_attach(struct mipi_dsi_host *host, struct tegra_output *output = &dsi->output; output->panel = of_drm_find_panel(device->dev.of_node); + if (IS_ERR(output->panel)) + output->panel = NULL; + if (output->panel && output->connector.dev) { drm_panel_attach(output->panel, &output->connector); drm_helper_hpd_irq_event(output->connector.dev); diff --git a/drivers/gpu/drm/tegra/output.c b/drivers/gpu/drm/tegra/output.c index ffe34bd0bb9d..0c0936511bb4 100644 --- a/drivers/gpu/drm/tegra/output.c +++ b/drivers/gpu/drm/tegra/output.c @@ -110,8 +110,8 @@ int tegra_output_probe(struct tegra_output *output) panel = of_parse_phandle(output->of_node, "nvidia,panel", 0); if (panel) { output->panel = of_drm_find_panel(panel); - if (!output->panel) - return -EPROBE_DEFER; + if (IS_ERR(output->panel)) + return PTR_ERR(output->panel); of_node_put(panel); } diff --git a/include/drm/drm_panel.h b/include/drm/drm_panel.h index 26a1b5fd8796..582a0ec0aa70 100644 --- a/include/drm/drm_panel.h +++ b/include/drm/drm_panel.h @@ -200,7 +200,7 @@ struct drm_panel *of_drm_find_panel(const struct device_node *np); #else static inline struct drm_panel *of_drm_find_panel(const struct device_node *np) { - return NULL; + return ERR_PTR(-ENODEV); } #endif -- cgit v1.2.3 From 955f60db0f2b87094f64df3d7f608fdac4a6ebb1 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Mon, 18 Jun 2018 16:22:34 +0300 Subject: drm: Add support for extracting sync signal drive edge from videomode The sync in some panels needs to be driven by different edge of the pixel clock compared to data. This is reflected by the DISPLAY_FLAGS_SYNC_(POS|NEG)EDGE in videmode flags. Add similar similar definitions for bus_flags and convert the sync drive edge via drm_bus_flags_from_videomode(). Signed-off-by: Peter Ujfalusi Signed-off-by: Tomi Valkeinen Signed-off-by: Jyri Sarha Signed-off-by: Thierry Reding Link: https://patchwork.freedesktop.org/patch/msgid/20180618132242.8673-2-tomi.valkeinen@ti.com --- drivers/gpu/drm/drm_modes.c | 15 +++++++++++---- include/drm/drm_connector.h | 4 ++++ 2 files changed, 15 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c index 7f552d5fa88e..f8f7eae738ab 100644 --- a/drivers/gpu/drm/drm_modes.c +++ b/drivers/gpu/drm/drm_modes.c @@ -659,10 +659,12 @@ EXPORT_SYMBOL_GPL(drm_display_mode_to_videomode); * drm_bus_flags_from_videomode - extract information about pixelclk and * DE polarity from videomode and store it in a separate variable * @vm: videomode structure to use - * @bus_flags: information about pixelclk and DE polarity will be stored here + * @bus_flags: information about pixelclk, sync and DE polarity will be stored + * here * - * Sets DRM_BUS_FLAG_DE_(LOW|HIGH) and DRM_BUS_FLAG_PIXDATA_(POS|NEG)EDGE - * in @bus_flags according to DISPLAY_FLAGS found in @vm + * Sets DRM_BUS_FLAG_DE_(LOW|HIGH), DRM_BUS_FLAG_PIXDATA_(POS|NEG)EDGE and + * DISPLAY_FLAGS_SYNC_(POS|NEG)EDGE in @bus_flags according to DISPLAY_FLAGS + * found in @vm */ void drm_bus_flags_from_videomode(const struct videomode *vm, u32 *bus_flags) { @@ -672,6 +674,11 @@ void drm_bus_flags_from_videomode(const struct videomode *vm, u32 *bus_flags) if (vm->flags & DISPLAY_FLAGS_PIXDATA_NEGEDGE) *bus_flags |= DRM_BUS_FLAG_PIXDATA_NEGEDGE; + if (vm->flags & DISPLAY_FLAGS_SYNC_POSEDGE) + *bus_flags |= DRM_BUS_FLAG_SYNC_POSEDGE; + if (vm->flags & DISPLAY_FLAGS_SYNC_NEGEDGE) + *bus_flags |= DRM_BUS_FLAG_SYNC_NEGEDGE; + if (vm->flags & DISPLAY_FLAGS_DE_LOW) *bus_flags |= DRM_BUS_FLAG_DE_LOW; if (vm->flags & DISPLAY_FLAGS_DE_HIGH) @@ -684,7 +691,7 @@ EXPORT_SYMBOL_GPL(drm_bus_flags_from_videomode); * of_get_drm_display_mode - get a drm_display_mode from devicetree * @np: device_node with the timing specification * @dmode: will be set to the return value - * @bus_flags: information about pixelclk and DE polarity + * @bus_flags: information about pixelclk, sync and DE polarity * @index: index into the list of display timings in devicetree * * This function is expensive and should only be used, if only one mode is to be diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h index ad397dfc042b..a5179eb9e56f 100644 --- a/include/drm/drm_connector.h +++ b/include/drm/drm_connector.h @@ -290,6 +290,10 @@ struct drm_display_info { #define DRM_BUS_FLAG_DATA_MSB_TO_LSB (1<<4) /* data is transmitted LSB to MSB on the bus */ #define DRM_BUS_FLAG_DATA_LSB_TO_MSB (1<<5) +/* drive sync on pos. edge */ +#define DRM_BUS_FLAG_SYNC_POSEDGE (1<<6) +/* drive sync on neg. edge */ +#define DRM_BUS_FLAG_SYNC_NEGEDGE (1<<7) /** * @bus_flags: Additional information (like pixel signal polarity) for -- cgit v1.2.3 From 8d3e994241e6bcc7ead2b918c4f15b7683afa90a Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Tue, 10 Jul 2018 09:57:58 +0100 Subject: arm_pmu: Clean up maximum period handling Each PMU defines their max_period of the counter as the maximum value that can be counted. Since all the PMU backends support 32bit counters by default, let us remove the redundant field. No functional changes. Cc: Will Deacon Acked-by: Mark Rutland Reviewed-by: Julien Thierry Signed-off-by: Suzuki K Poulose Signed-off-by: Will Deacon --- arch/arm/kernel/perf_event_v6.c | 2 -- arch/arm/kernel/perf_event_v7.c | 1 - arch/arm/kernel/perf_event_xscale.c | 2 -- arch/arm64/kernel/perf_event.c | 1 - drivers/perf/arm_pmu.c | 16 ++++++++++++---- include/linux/perf/arm_pmu.h | 1 - 6 files changed, 12 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/arch/arm/kernel/perf_event_v6.c b/arch/arm/kernel/perf_event_v6.c index be42c4f66a40..f64a6bfebcec 100644 --- a/arch/arm/kernel/perf_event_v6.c +++ b/arch/arm/kernel/perf_event_v6.c @@ -495,7 +495,6 @@ static void armv6pmu_init(struct arm_pmu *cpu_pmu) cpu_pmu->stop = armv6pmu_stop; cpu_pmu->map_event = armv6_map_event; cpu_pmu->num_events = 3; - cpu_pmu->max_period = (1LLU << 32) - 1; } static int armv6_1136_pmu_init(struct arm_pmu *cpu_pmu) @@ -546,7 +545,6 @@ static int armv6mpcore_pmu_init(struct arm_pmu *cpu_pmu) cpu_pmu->stop = armv6pmu_stop; cpu_pmu->map_event = armv6mpcore_map_event; cpu_pmu->num_events = 3; - cpu_pmu->max_period = (1LLU << 32) - 1; return 0; } diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c index 5a5116794440..2cf1ca2925c8 100644 --- a/arch/arm/kernel/perf_event_v7.c +++ b/arch/arm/kernel/perf_event_v7.c @@ -1170,7 +1170,6 @@ static void armv7pmu_init(struct arm_pmu *cpu_pmu) cpu_pmu->start = armv7pmu_start; cpu_pmu->stop = armv7pmu_stop; cpu_pmu->reset = armv7pmu_reset; - cpu_pmu->max_period = (1LLU << 32) - 1; }; static void armv7_read_num_pmnc_events(void *info) diff --git a/arch/arm/kernel/perf_event_xscale.c b/arch/arm/kernel/perf_event_xscale.c index 88d1a76f5367..c4f029458b52 100644 --- a/arch/arm/kernel/perf_event_xscale.c +++ b/arch/arm/kernel/perf_event_xscale.c @@ -374,7 +374,6 @@ static int xscale1pmu_init(struct arm_pmu *cpu_pmu) cpu_pmu->stop = xscale1pmu_stop; cpu_pmu->map_event = xscale_map_event; cpu_pmu->num_events = 3; - cpu_pmu->max_period = (1LLU << 32) - 1; return 0; } @@ -743,7 +742,6 @@ static int xscale2pmu_init(struct arm_pmu *cpu_pmu) cpu_pmu->stop = xscale2pmu_stop; cpu_pmu->map_event = xscale_map_event; cpu_pmu->num_events = 5; - cpu_pmu->max_period = (1LLU << 32) - 1; return 0; } diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index 33147aacdafd..678ecffd3724 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -960,7 +960,6 @@ static int armv8_pmu_init(struct arm_pmu *cpu_pmu) cpu_pmu->start = armv8pmu_start, cpu_pmu->stop = armv8pmu_stop, cpu_pmu->reset = armv8pmu_reset, - cpu_pmu->max_period = (1LLU << 32) - 1, cpu_pmu->set_event_filter = armv8pmu_set_event_filter; return 0; diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c index a6347d487635..6ddc00da5373 100644 --- a/drivers/perf/arm_pmu.c +++ b/drivers/perf/arm_pmu.c @@ -28,6 +28,11 @@ static DEFINE_PER_CPU(struct arm_pmu *, cpu_armpmu); static DEFINE_PER_CPU(int, cpu_irq); +static inline u64 arm_pmu_max_period(void) +{ + return (1ULL << 32) - 1; +} + static int armpmu_map_cache_event(const unsigned (*cache_map) [PERF_COUNT_HW_CACHE_MAX] @@ -114,8 +119,10 @@ int armpmu_event_set_period(struct perf_event *event) struct hw_perf_event *hwc = &event->hw; s64 left = local64_read(&hwc->period_left); s64 period = hwc->sample_period; + u64 max_period; int ret = 0; + max_period = arm_pmu_max_period(); if (unlikely(left <= -period)) { left = period; local64_set(&hwc->period_left, left); @@ -136,8 +143,8 @@ int armpmu_event_set_period(struct perf_event *event) * effect we are reducing max_period to account for * interrupt latency (and we are being very conservative). */ - if (left > (armpmu->max_period >> 1)) - left = armpmu->max_period >> 1; + if (left > (max_period >> 1)) + left = (max_period >> 1); local64_set(&hwc->prev_count, (u64)-left); @@ -153,6 +160,7 @@ u64 armpmu_event_update(struct perf_event *event) struct arm_pmu *armpmu = to_arm_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; u64 delta, prev_raw_count, new_raw_count; + u64 max_period = arm_pmu_max_period(); again: prev_raw_count = local64_read(&hwc->prev_count); @@ -162,7 +170,7 @@ again: new_raw_count) != prev_raw_count) goto again; - delta = (new_raw_count - prev_raw_count) & armpmu->max_period; + delta = (new_raw_count - prev_raw_count) & max_period; local64_add(delta, &event->count); local64_sub(delta, &hwc->period_left); @@ -402,7 +410,7 @@ __hw_perf_event_init(struct perf_event *event) * is far less likely to overtake the previous one unless * you have some serious IRQ latency issues. */ - hwc->sample_period = armpmu->max_period >> 1; + hwc->sample_period = arm_pmu_max_period() >> 1; hwc->last_period = hwc->sample_period; local64_set(&hwc->period_left, hwc->sample_period); } diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index ad5444491975..12c30a22fc8d 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -94,7 +94,6 @@ struct arm_pmu { void (*reset)(void *); int (*map_event)(struct perf_event *event); int num_events; - u64 max_period; bool secure_access; /* 32-bit ARM only */ #define ARMV8_PMUV3_MAX_COMMON_EVENTS 0x40 DECLARE_BITMAP(pmceid_bitmap, ARMV8_PMUV3_MAX_COMMON_EVENTS); -- cgit v1.2.3 From 3a95200d3f89afd8b67f39d88d36cc7ec96ce385 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Tue, 10 Jul 2018 09:57:59 +0100 Subject: arm_pmu: Change API to support 64bit counter values Convert the {read/write}_counter APIs to handle 64bit values to enable supporting chained event counters. The backends still use 32bit values and we pass them 32bit values only. So in effect there are no functional changes. Cc: Will Deacon Acked-by: Mark Rutland Reviewed-by: Julien Thierry Signed-off-by: Suzuki K Poulose Signed-off-by: Will Deacon --- arch/arm/kernel/perf_event_v6.c | 4 ++-- arch/arm/kernel/perf_event_v7.c | 4 ++-- arch/arm/kernel/perf_event_xscale.c | 8 ++++---- arch/arm64/kernel/perf_event.c | 9 ++++----- include/linux/perf/arm_pmu.h | 4 ++-- 5 files changed, 14 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/arch/arm/kernel/perf_event_v6.c b/arch/arm/kernel/perf_event_v6.c index f64a6bfebcec..0729f9841ef4 100644 --- a/arch/arm/kernel/perf_event_v6.c +++ b/arch/arm/kernel/perf_event_v6.c @@ -233,7 +233,7 @@ armv6_pmcr_counter_has_overflowed(unsigned long pmcr, return ret; } -static inline u32 armv6pmu_read_counter(struct perf_event *event) +static inline u64 armv6pmu_read_counter(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; int counter = hwc->idx; @@ -251,7 +251,7 @@ static inline u32 armv6pmu_read_counter(struct perf_event *event) return value; } -static inline void armv6pmu_write_counter(struct perf_event *event, u32 value) +static inline void armv6pmu_write_counter(struct perf_event *event, u64 value) { struct hw_perf_event *hwc = &event->hw; int counter = hwc->idx; diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c index 2cf1ca2925c8..973043dd6187 100644 --- a/arch/arm/kernel/perf_event_v7.c +++ b/arch/arm/kernel/perf_event_v7.c @@ -743,7 +743,7 @@ static inline void armv7_pmnc_select_counter(int idx) isb(); } -static inline u32 armv7pmu_read_counter(struct perf_event *event) +static inline u64 armv7pmu_read_counter(struct perf_event *event) { struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; @@ -763,7 +763,7 @@ static inline u32 armv7pmu_read_counter(struct perf_event *event) return value; } -static inline void armv7pmu_write_counter(struct perf_event *event, u32 value) +static inline void armv7pmu_write_counter(struct perf_event *event, u64 value) { struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; diff --git a/arch/arm/kernel/perf_event_xscale.c b/arch/arm/kernel/perf_event_xscale.c index c4f029458b52..942230fe0426 100644 --- a/arch/arm/kernel/perf_event_xscale.c +++ b/arch/arm/kernel/perf_event_xscale.c @@ -316,7 +316,7 @@ static void xscale1pmu_stop(struct arm_pmu *cpu_pmu) raw_spin_unlock_irqrestore(&events->pmu_lock, flags); } -static inline u32 xscale1pmu_read_counter(struct perf_event *event) +static inline u64 xscale1pmu_read_counter(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; int counter = hwc->idx; @@ -337,7 +337,7 @@ static inline u32 xscale1pmu_read_counter(struct perf_event *event) return val; } -static inline void xscale1pmu_write_counter(struct perf_event *event, u32 val) +static inline void xscale1pmu_write_counter(struct perf_event *event, u64 val) { struct hw_perf_event *hwc = &event->hw; int counter = hwc->idx; @@ -678,7 +678,7 @@ static void xscale2pmu_stop(struct arm_pmu *cpu_pmu) raw_spin_unlock_irqrestore(&events->pmu_lock, flags); } -static inline u32 xscale2pmu_read_counter(struct perf_event *event) +static inline u64 xscale2pmu_read_counter(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; int counter = hwc->idx; @@ -705,7 +705,7 @@ static inline u32 xscale2pmu_read_counter(struct perf_event *event) return val; } -static inline void xscale2pmu_write_counter(struct perf_event *event, u32 val) +static inline void xscale2pmu_write_counter(struct perf_event *event, u64 val) { struct hw_perf_event *hwc = &event->hw; int counter = hwc->idx; diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index 678ecffd3724..66a2ffdca6dd 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -512,7 +512,7 @@ static inline int armv8pmu_select_counter(int idx) return idx; } -static inline u32 armv8pmu_read_counter(struct perf_event *event) +static inline u64 armv8pmu_read_counter(struct perf_event *event) { struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; @@ -530,7 +530,7 @@ static inline u32 armv8pmu_read_counter(struct perf_event *event) return value; } -static inline void armv8pmu_write_counter(struct perf_event *event, u32 value) +static inline void armv8pmu_write_counter(struct perf_event *event, u64 value) { struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; @@ -545,9 +545,8 @@ static inline void armv8pmu_write_counter(struct perf_event *event, u32 value) * count using the lower 32bits and we want an interrupt when * it overflows. */ - u64 value64 = 0xffffffff00000000ULL | value; - - write_sysreg(value64, pmccntr_el0); + value |= 0xffffffff00000000ULL; + write_sysreg(value, pmccntr_el0); } else if (armv8pmu_select_counter(idx) == idx) write_sysreg(value, pmxevcntr_el0); } diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index 12c30a22fc8d..f7126a21df30 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -87,8 +87,8 @@ struct arm_pmu { struct perf_event *event); int (*set_event_filter)(struct hw_perf_event *evt, struct perf_event_attr *attr); - u32 (*read_counter)(struct perf_event *event); - void (*write_counter)(struct perf_event *event, u32 val); + u64 (*read_counter)(struct perf_event *event); + void (*write_counter)(struct perf_event *event, u64 val); void (*start)(struct arm_pmu *); void (*stop)(struct arm_pmu *); void (*reset)(void *); -- cgit v1.2.3 From e2da97d328d4951d25f6634eda7213f7257417b6 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Tue, 10 Jul 2018 09:58:00 +0100 Subject: arm_pmu: Add support for 64bit event counters Each PMU has a set of 32bit event counters. But in some special cases, the events could be counted using counters which are effectively 64bit wide. e.g, Arm V8 PMUv3 has a 64 bit cycle counter which can count only the CPU cycles. Also, the PMU can chain the event counters to effectively count as a 64bit counter. Add support for tracking the events that uses 64bit counters. This only affects the periods set for each counter in the core driver. Cc: Will Deacon Reviewed-by: Julien Thierry Acked-by: Mark Rutland Signed-off-by: Suzuki K Poulose Signed-off-by: Will Deacon --- drivers/perf/arm_pmu.c | 16 ++++++++++------ include/linux/perf/arm_pmu.h | 6 ++++++ 2 files changed, 16 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c index 6ddc00da5373..8cad6b535a2c 100644 --- a/drivers/perf/arm_pmu.c +++ b/drivers/perf/arm_pmu.c @@ -28,9 +28,12 @@ static DEFINE_PER_CPU(struct arm_pmu *, cpu_armpmu); static DEFINE_PER_CPU(int, cpu_irq); -static inline u64 arm_pmu_max_period(void) +static inline u64 arm_pmu_event_max_period(struct perf_event *event) { - return (1ULL << 32) - 1; + if (event->hw.flags & ARMPMU_EVT_64BIT) + return GENMASK_ULL(63, 0); + else + return GENMASK_ULL(31, 0); } static int @@ -122,7 +125,7 @@ int armpmu_event_set_period(struct perf_event *event) u64 max_period; int ret = 0; - max_period = arm_pmu_max_period(); + max_period = arm_pmu_event_max_period(event); if (unlikely(left <= -period)) { left = period; local64_set(&hwc->period_left, left); @@ -148,7 +151,7 @@ int armpmu_event_set_period(struct perf_event *event) local64_set(&hwc->prev_count, (u64)-left); - armpmu->write_counter(event, (u64)(-left) & 0xffffffff); + armpmu->write_counter(event, (u64)(-left) & max_period); perf_event_update_userpage(event); @@ -160,7 +163,7 @@ u64 armpmu_event_update(struct perf_event *event) struct arm_pmu *armpmu = to_arm_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; u64 delta, prev_raw_count, new_raw_count; - u64 max_period = arm_pmu_max_period(); + u64 max_period = arm_pmu_event_max_period(event); again: prev_raw_count = local64_read(&hwc->prev_count); @@ -368,6 +371,7 @@ __hw_perf_event_init(struct perf_event *event) struct hw_perf_event *hwc = &event->hw; int mapping; + hwc->flags = 0; mapping = armpmu->map_event(event); if (mapping < 0) { @@ -410,7 +414,7 @@ __hw_perf_event_init(struct perf_event *event) * is far less likely to overtake the previous one unless * you have some serious IRQ latency issues. */ - hwc->sample_period = arm_pmu_max_period() >> 1; + hwc->sample_period = arm_pmu_event_max_period(event) >> 1; hwc->last_period = hwc->sample_period; local64_set(&hwc->period_left, hwc->sample_period); } diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index f7126a21df30..10f92e1d8e7b 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -25,6 +25,12 @@ */ #define ARMPMU_MAX_HWEVENTS 32 +/* + * ARM PMU hw_event flags + */ +/* Event uses a 64bit counter */ +#define ARMPMU_EVT_64BIT 1 + #define HW_OP_UNSUPPORTED 0xFFFF #define C(_x) PERF_COUNT_HW_CACHE_##_x #define CACHE_OP_UNSUPPORTED 0xFFFF -- cgit v1.2.3 From 89c815ef07a1db0ac2cc09d06cb2d5c3d86d6322 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Thu, 21 Jun 2018 15:21:35 +0200 Subject: drm/ttm: Introduce ttm_bo_get() and ttm_bo_put() for ref counting MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The TTM buffer-object interface provides ttm_bo_reference() and ttm_bo_unref() for managing reference counts. Replacing them with ttm_bo_get() and ttm_bo_put() aligns the API with conventions used throughout the Linux kernel. The implementation of ttm_bo_unref() clears the supplied pointer to NULL. This leads to workarounds where the caller saves the pointer's value before de-referencing the BO. ttm_bo_put() does not clear the supplied pointer. Signed-off-by: Thomas Zimmermann Reviewed-by: Christian König Signed-off-by: Alex Deucher --- drivers/gpu/drm/ttm/ttm_bo.c | 8 +++++++- include/drm/ttm/ttm_bo_api.h | 25 ++++++++++++++++++++++++- 2 files changed, 31 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 5142dcb8ce39..183e67c4197a 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -587,12 +587,18 @@ static void ttm_bo_release(struct kref *kref) kref_put(&bo->list_kref, ttm_bo_release_list); } +void ttm_bo_put(struct ttm_buffer_object *bo) +{ + kref_put(&bo->kref, ttm_bo_release); +} +EXPORT_SYMBOL(ttm_bo_put); + void ttm_bo_unref(struct ttm_buffer_object **p_bo) { struct ttm_buffer_object *bo = *p_bo; *p_bo = NULL; - kref_put(&bo->kref, ttm_bo_release); + ttm_bo_put(bo); } EXPORT_SYMBOL(ttm_bo_unref); diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h index c67977aa1a0e..a01ba2032f0e 100644 --- a/include/drm/ttm/ttm_bo_api.h +++ b/include/drm/ttm/ttm_bo_api.h @@ -283,18 +283,30 @@ struct ttm_operation_ctx { /* when serving page fault or suspend, allow alloc anyway */ #define TTM_OPT_FLAG_FORCE_ALLOC 0x2 +/** + * ttm_bo_get - reference a struct ttm_buffer_object + * + * @bo: The buffer object. + */ +static inline void ttm_bo_get(struct ttm_buffer_object *bo) +{ + kref_get(&bo->kref); +} + /** * ttm_bo_reference - reference a struct ttm_buffer_object * * @bo: The buffer object. * * Returns a refcounted pointer to a buffer object. + * + * This function is deprecated. Use @ttm_bo_get instead. */ static inline struct ttm_buffer_object * ttm_bo_reference(struct ttm_buffer_object *bo) { - kref_get(&bo->kref); + ttm_bo_get(bo); return bo; } @@ -345,12 +357,23 @@ int ttm_bo_validate(struct ttm_buffer_object *bo, struct ttm_placement *placement, struct ttm_operation_ctx *ctx); +/** + * ttm_bo_put + * + * @bo: The buffer object. + * + * Unreference a buffer object. + */ +void ttm_bo_put(struct ttm_buffer_object *bo); + /** * ttm_bo_unref * * @bo: The buffer object. * * Unreference and clear a pointer to a buffer object. + * + * This function is deprecated. Use @ttm_bo_put instead. */ void ttm_bo_unref(struct ttm_buffer_object **bo); -- cgit v1.2.3 From db0c8d8b031d2b5960f6407f7f2ca20e97e00605 Mon Sep 17 00:00:00 2001 From: Paulo Zanoni Date: Fri, 4 May 2018 13:32:51 -0700 Subject: x86/gpu: reserve ICL's graphics stolen memory ICL changes the registers and addresses to 64 bits. I also briefly looked at implementing an u64 version of the PCI config read functions, but I concluded this wouldn't be trivial, so it's not worth doing it for a single user that can't have any racing problems while reading the register in two separate operations. v2: - Scrub the development (non-public) changelog (Joonas). - Remove the i915.ko bits so this can be easily backported in order to properly avoid stolen memory even on machines without i915.ko (Joonas). - CC stable for the reasons above. Issue: VIZ-9250 CC: stable@vger.kernel.org Cc: Ingo Molnar Cc: H. Peter Anvin Cc: x86@kernel.org Cc: Daniele Ceraolo Spurio Cc: Joonas Lahtinen Signed-off-by: Paulo Zanoni Fixes: 412310019a20 ("drm/i915/icl: Add initial Icelake definitions.") Reviewed-by: Joonas Lahtinen Acked-by: Ingo Molnar Signed-off-by: Rodrigo Vivi Link: https://patchwork.freedesktop.org/patch/msgid/20180504203252.28048-1-paulo.r.zanoni@intel.com --- arch/x86/kernel/early-quirks.c | 18 ++++++++++++++++++ include/drm/i915_drm.h | 4 +++- 2 files changed, 21 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index bae0d32e327b..72c2cf961d44 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -340,6 +340,18 @@ static resource_size_t __init gen3_stolen_base(int num, int slot, int func, return bsm & INTEL_BSM_MASK; } +static resource_size_t __init gen11_stolen_base(int num, int slot, int func, + resource_size_t stolen_size) +{ + u64 bsm; + + bsm = read_pci_config(num, slot, func, INTEL_GEN11_BSM_DW0); + bsm &= INTEL_BSM_MASK; + bsm |= (u64)read_pci_config(num, slot, func, INTEL_GEN11_BSM_DW1) << 32; + + return bsm; +} + static resource_size_t __init i830_stolen_size(int num, int slot, int func) { u16 gmch_ctrl; @@ -500,6 +512,11 @@ static const struct intel_early_ops chv_early_ops __initconst = { .stolen_size = chv_stolen_size, }; +static const struct intel_early_ops gen11_early_ops __initconst = { + .stolen_base = gen11_stolen_base, + .stolen_size = gen9_stolen_size, +}; + static const struct pci_device_id intel_early_ids[] __initconst = { INTEL_I830_IDS(&i830_early_ops), INTEL_I845G_IDS(&i845_early_ops), @@ -531,6 +548,7 @@ static const struct pci_device_id intel_early_ids[] __initconst = { INTEL_CFL_IDS(&gen9_early_ops), INTEL_GLK_IDS(&gen9_early_ops), INTEL_CNL_IDS(&gen9_early_ops), + INTEL_ICL_11_IDS(&gen11_early_ops), }; struct resource intel_graphics_stolen_res __ro_after_init = DEFINE_RES_MEM(0, 0); diff --git a/include/drm/i915_drm.h b/include/drm/i915_drm.h index c9e5a6621b95..c44703f471b3 100644 --- a/include/drm/i915_drm.h +++ b/include/drm/i915_drm.h @@ -95,7 +95,9 @@ extern struct resource intel_graphics_stolen_res; #define I845_TSEG_SIZE_512K (2 << 1) #define I845_TSEG_SIZE_1M (3 << 1) -#define INTEL_BSM 0x5c +#define INTEL_BSM 0x5c +#define INTEL_GEN11_BSM_DW0 0xc0 +#define INTEL_GEN11_BSM_DW1 0xc4 #define INTEL_BSM_MASK (-(1u << 20)) #endif /* _I915_DRM_H_ */ -- cgit v1.2.3 From 14b470b56840dbb093abd71f214e9d63770c87b8 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 6 Jul 2018 22:19:07 +0200 Subject: scsi: target: sbitmap: add seq_file forward declaration The target core runs into a warning in the linux/sbitmap.h file in some configurations: In file included from include/target/target_core_base.h:7, from drivers/target/target_core_fabric_lib.c:41: include/linux/sbitmap.h:331:46: error: 'struct seq_file' declared inside parameter list will not be visible outside of this definition or declaration [-Werror] void sbitmap_show(struct sbitmap *sb, struct seq_file *m); ^~~~~~~~ In general, headers should not depend on others being included first, so this fixes it with a forward declaration for that struct name, but we probably want to merge the patch through the scsi tree to help bisection. Fixes: 10e9cbb6b531 ("scsi: target: Convert target drivers to use sbitmap") Signed-off-by: Arnd Bergmann Reviewed-by: Bart Van Assche Reviewed-by: Omar Sandoval Reviewed-by: Jens Axboe Signed-off-by: Martin K. Petersen --- include/linux/sbitmap.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h index e6539536dea9..804a50983ec5 100644 --- a/include/linux/sbitmap.h +++ b/include/linux/sbitmap.h @@ -23,6 +23,8 @@ #include #include +struct seq_file; + /** * struct sbitmap_word - Word in a &struct sbitmap. */ -- cgit v1.2.3 From 046f6fd5daefac7f5abdafb436b30f63bc7c602b Mon Sep 17 00:00:00 2001 From: Toke Høiland-Jørgensen Date: Fri, 6 Jul 2018 17:37:19 +0200 Subject: sched: Add Common Applications Kept Enhanced (cake) qdisc MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit sch_cake targets the home router use case and is intended to squeeze the most bandwidth and latency out of even the slowest ISP links and routers, while presenting an API simple enough that even an ISP can configure it. Example of use on a cable ISP uplink: tc qdisc add dev eth0 cake bandwidth 20Mbit nat docsis ack-filter To shape a cable download link (ifb and tc-mirred setup elided) tc qdisc add dev ifb0 cake bandwidth 200mbit nat docsis ingress wash CAKE is filled with: * A hybrid Codel/Blue AQM algorithm, "Cobalt", tied to an FQ_Codel derived Flow Queuing system, which autoconfigures based on the bandwidth. * A novel "triple-isolate" mode (the default) which balances per-host and per-flow FQ even through NAT. * An deficit based shaper, that can also be used in an unlimited mode. * 8 way set associative hashing to reduce flow collisions to a minimum. * A reasonable interpretation of various diffserv latency/loss tradeoffs. * Support for zeroing diffserv markings for entering and exiting traffic. * Support for interacting well with Docsis 3.0 shaper framing. * Extensive support for DSL framing types. * Support for ack filtering. * Extensive statistics for measuring, loss, ecn markings, latency variation. A paper describing the design of CAKE is available at https://arxiv.org/abs/1804.07617, and will be published at the 2018 IEEE International Symposium on Local and Metropolitan Area Networks (LANMAN). This patch adds the base shaper and packet scheduler, while subsequent commits add the optional (configurable) features. The full userspace API and most data structures are included in this commit, but options not understood in the base version will be ignored. Various versions baking have been available as an out of tree build for kernel versions going back to 3.10, as the embedded router world has been running a few years behind mainline Linux. A stable version has been generally available on lede-17.01 and later. sch_cake replaces a combination of iptables, tc filter, htb and fq_codel in the sqm-scripts, with sane defaults and vastly simpler configuration. CAKE's principal author is Jonathan Morton, with contributions from Kevin Darbyshire-Bryant, Toke Høiland-Jørgensen, Sebastian Moeller, Ryan Mounce, Tony Ambardar, Dean Scarff, Nils Andreas Svee, Dave Täht, and Loganaden Velvindron. Testing from Pete Heist, Georgios Amanakis, and the many other members of the cake@lists.bufferbloat.net mailing list. tc -s qdisc show dev eth2 qdisc cake 8017: root refcnt 2 bandwidth 1Gbit diffserv3 triple-isolate split-gso rtt 100.0ms noatm overhead 38 mpu 84 Sent 51504294511 bytes 37724591 pkt (dropped 6, overlimits 64958695 requeues 12) backlog 0b 0p requeues 12 memory used: 1053008b of 15140Kb capacity estimate: 970Mbit min/max network layer size: 28 / 1500 min/max overhead-adjusted size: 84 / 1538 average network hdr offset: 14 Bulk Best Effort Voice thresh 62500Kbit 1Gbit 250Mbit target 5.0ms 5.0ms 5.0ms interval 100.0ms 100.0ms 100.0ms pk_delay 5us 5us 6us av_delay 3us 2us 2us sp_delay 2us 1us 1us backlog 0b 0b 0b pkts 3164050 25030267 9530280 bytes 3227519915 35396974782 12879808898 way_inds 0 8 0 way_miss 21 366 25 way_cols 0 0 0 drops 5 0 1 marks 0 0 0 ack_drop 0 0 0 sp_flows 1 3 0 bk_flows 0 1 1 un_flows 0 0 0 max_len 68130 68130 68130 Tested-by: Pete Heist Tested-by: Georgios Amanakis Signed-off-by: Dave Taht Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: David S. Miller --- include/uapi/linux/pkt_sched.h | 114 +++ net/sched/Kconfig | 11 + net/sched/Makefile | 1 + net/sched/sch_cake.c | 1867 ++++++++++++++++++++++++++++++++++++++++ 4 files changed, 1993 insertions(+) create mode 100644 net/sched/sch_cake.c (limited to 'include') diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index 949118461009..d9cc9dc4f547 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -955,4 +955,118 @@ enum { #define TCA_ETF_MAX (__TCA_ETF_MAX - 1) + +/* CAKE */ +enum { + TCA_CAKE_UNSPEC, + TCA_CAKE_PAD, + TCA_CAKE_BASE_RATE64, + TCA_CAKE_DIFFSERV_MODE, + TCA_CAKE_ATM, + TCA_CAKE_FLOW_MODE, + TCA_CAKE_OVERHEAD, + TCA_CAKE_RTT, + TCA_CAKE_TARGET, + TCA_CAKE_AUTORATE, + TCA_CAKE_MEMORY, + TCA_CAKE_NAT, + TCA_CAKE_RAW, + TCA_CAKE_WASH, + TCA_CAKE_MPU, + TCA_CAKE_INGRESS, + TCA_CAKE_ACK_FILTER, + TCA_CAKE_SPLIT_GSO, + __TCA_CAKE_MAX +}; +#define TCA_CAKE_MAX (__TCA_CAKE_MAX - 1) + +enum { + __TCA_CAKE_STATS_INVALID, + TCA_CAKE_STATS_PAD, + TCA_CAKE_STATS_CAPACITY_ESTIMATE64, + TCA_CAKE_STATS_MEMORY_LIMIT, + TCA_CAKE_STATS_MEMORY_USED, + TCA_CAKE_STATS_AVG_NETOFF, + TCA_CAKE_STATS_MIN_NETLEN, + TCA_CAKE_STATS_MAX_NETLEN, + TCA_CAKE_STATS_MIN_ADJLEN, + TCA_CAKE_STATS_MAX_ADJLEN, + TCA_CAKE_STATS_TIN_STATS, + TCA_CAKE_STATS_DEFICIT, + TCA_CAKE_STATS_COBALT_COUNT, + TCA_CAKE_STATS_DROPPING, + TCA_CAKE_STATS_DROP_NEXT_US, + TCA_CAKE_STATS_P_DROP, + TCA_CAKE_STATS_BLUE_TIMER_US, + __TCA_CAKE_STATS_MAX +}; +#define TCA_CAKE_STATS_MAX (__TCA_CAKE_STATS_MAX - 1) + +enum { + __TCA_CAKE_TIN_STATS_INVALID, + TCA_CAKE_TIN_STATS_PAD, + TCA_CAKE_TIN_STATS_SENT_PACKETS, + TCA_CAKE_TIN_STATS_SENT_BYTES64, + TCA_CAKE_TIN_STATS_DROPPED_PACKETS, + TCA_CAKE_TIN_STATS_DROPPED_BYTES64, + TCA_CAKE_TIN_STATS_ACKS_DROPPED_PACKETS, + TCA_CAKE_TIN_STATS_ACKS_DROPPED_BYTES64, + TCA_CAKE_TIN_STATS_ECN_MARKED_PACKETS, + TCA_CAKE_TIN_STATS_ECN_MARKED_BYTES64, + TCA_CAKE_TIN_STATS_BACKLOG_PACKETS, + TCA_CAKE_TIN_STATS_BACKLOG_BYTES, + TCA_CAKE_TIN_STATS_THRESHOLD_RATE64, + TCA_CAKE_TIN_STATS_TARGET_US, + TCA_CAKE_TIN_STATS_INTERVAL_US, + TCA_CAKE_TIN_STATS_WAY_INDIRECT_HITS, + TCA_CAKE_TIN_STATS_WAY_MISSES, + TCA_CAKE_TIN_STATS_WAY_COLLISIONS, + TCA_CAKE_TIN_STATS_PEAK_DELAY_US, + TCA_CAKE_TIN_STATS_AVG_DELAY_US, + TCA_CAKE_TIN_STATS_BASE_DELAY_US, + TCA_CAKE_TIN_STATS_SPARSE_FLOWS, + TCA_CAKE_TIN_STATS_BULK_FLOWS, + TCA_CAKE_TIN_STATS_UNRESPONSIVE_FLOWS, + TCA_CAKE_TIN_STATS_MAX_SKBLEN, + TCA_CAKE_TIN_STATS_FLOW_QUANTUM, + __TCA_CAKE_TIN_STATS_MAX +}; +#define TCA_CAKE_TIN_STATS_MAX (__TCA_CAKE_TIN_STATS_MAX - 1) +#define TC_CAKE_MAX_TINS (8) + +enum { + CAKE_FLOW_NONE = 0, + CAKE_FLOW_SRC_IP, + CAKE_FLOW_DST_IP, + CAKE_FLOW_HOSTS, /* = CAKE_FLOW_SRC_IP | CAKE_FLOW_DST_IP */ + CAKE_FLOW_FLOWS, + CAKE_FLOW_DUAL_SRC, /* = CAKE_FLOW_SRC_IP | CAKE_FLOW_FLOWS */ + CAKE_FLOW_DUAL_DST, /* = CAKE_FLOW_DST_IP | CAKE_FLOW_FLOWS */ + CAKE_FLOW_TRIPLE, /* = CAKE_FLOW_HOSTS | CAKE_FLOW_FLOWS */ + CAKE_FLOW_MAX, +}; + +enum { + CAKE_DIFFSERV_DIFFSERV3 = 0, + CAKE_DIFFSERV_DIFFSERV4, + CAKE_DIFFSERV_DIFFSERV8, + CAKE_DIFFSERV_BESTEFFORT, + CAKE_DIFFSERV_PRECEDENCE, + CAKE_DIFFSERV_MAX +}; + +enum { + CAKE_ACK_NONE = 0, + CAKE_ACK_FILTER, + CAKE_ACK_AGGRESSIVE, + CAKE_ACK_MAX +}; + +enum { + CAKE_ATM_NONE = 0, + CAKE_ATM_ATM, + CAKE_ATM_PTM, + CAKE_ATM_MAX +}; + #endif diff --git a/net/sched/Kconfig b/net/sched/Kconfig index fcc89706745b..7af246764a35 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -295,6 +295,17 @@ config NET_SCH_FQ_CODEL If unsure, say N. +config NET_SCH_CAKE + tristate "Common Applications Kept Enhanced (CAKE)" + help + Say Y here if you want to use the Common Applications Kept Enhanced + (CAKE) queue management algorithm. + + To compile this driver as a module, choose M here: the module + will be called sch_cake. + + If unsure, say N. + config NET_SCH_FQ tristate "Fair Queue" help diff --git a/net/sched/Makefile b/net/sched/Makefile index 9a5a7077d217..673ee7d26ff2 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -50,6 +50,7 @@ obj-$(CONFIG_NET_SCH_CHOKE) += sch_choke.o obj-$(CONFIG_NET_SCH_QFQ) += sch_qfq.o obj-$(CONFIG_NET_SCH_CODEL) += sch_codel.o obj-$(CONFIG_NET_SCH_FQ_CODEL) += sch_fq_codel.o +obj-$(CONFIG_NET_SCH_CAKE) += sch_cake.o obj-$(CONFIG_NET_SCH_FQ) += sch_fq.o obj-$(CONFIG_NET_SCH_HHF) += sch_hhf.o obj-$(CONFIG_NET_SCH_PIE) += sch_pie.o diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c new file mode 100644 index 000000000000..ea0272615d63 --- /dev/null +++ b/net/sched/sch_cake.c @@ -0,0 +1,1867 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause + +/* COMMON Applications Kept Enhanced (CAKE) discipline + * + * Copyright (C) 2014-2018 Jonathan Morton + * Copyright (C) 2015-2018 Toke Høiland-Jørgensen + * Copyright (C) 2014-2018 Dave Täht + * Copyright (C) 2015-2018 Sebastian Moeller + * (C) 2015-2018 Kevin Darbyshire-Bryant + * Copyright (C) 2017-2018 Ryan Mounce + * + * The CAKE Principles: + * (or, how to have your cake and eat it too) + * + * This is a combination of several shaping, AQM and FQ techniques into one + * easy-to-use package: + * + * - An overall bandwidth shaper, to move the bottleneck away from dumb CPE + * equipment and bloated MACs. This operates in deficit mode (as in sch_fq), + * eliminating the need for any sort of burst parameter (eg. token bucket + * depth). Burst support is limited to that necessary to overcome scheduling + * latency. + * + * - A Diffserv-aware priority queue, giving more priority to certain classes, + * up to a specified fraction of bandwidth. Above that bandwidth threshold, + * the priority is reduced to avoid starving other tins. + * + * - Each priority tin has a separate Flow Queue system, to isolate traffic + * flows from each other. This prevents a burst on one flow from increasing + * the delay to another. Flows are distributed to queues using a + * set-associative hash function. + * + * - Each queue is actively managed by Cobalt, which is a combination of the + * Codel and Blue AQM algorithms. This serves flows fairly, and signals + * congestion early via ECN (if available) and/or packet drops, to keep + * latency low. The codel parameters are auto-tuned based on the bandwidth + * setting, as is necessary at low bandwidths. + * + * The configuration parameters are kept deliberately simple for ease of use. + * Everything has sane defaults. Complete generality of configuration is *not* + * a goal. + * + * The priority queue operates according to a weighted DRR scheme, combined with + * a bandwidth tracker which reuses the shaper logic to detect which side of the + * bandwidth sharing threshold the tin is operating. This determines whether a + * priority-based weight (high) or a bandwidth-based weight (low) is used for + * that tin in the current pass. + * + * This qdisc was inspired by Eric Dumazet's fq_codel code, which he kindly + * granted us permission to leverage. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define CAKE_SET_WAYS (8) +#define CAKE_MAX_TINS (8) +#define CAKE_QUEUES (1024) +#define CAKE_FLOW_MASK 63 +#define CAKE_FLOW_NAT_FLAG 64 + +/* struct cobalt_params - contains codel and blue parameters + * @interval: codel initial drop rate + * @target: maximum persistent sojourn time & blue update rate + * @mtu_time: serialisation delay of maximum-size packet + * @p_inc: increment of blue drop probability (0.32 fxp) + * @p_dec: decrement of blue drop probability (0.32 fxp) + */ +struct cobalt_params { + u64 interval; + u64 target; + u64 mtu_time; + u32 p_inc; + u32 p_dec; +}; + +/* struct cobalt_vars - contains codel and blue variables + * @count: codel dropping frequency + * @rec_inv_sqrt: reciprocal value of sqrt(count) >> 1 + * @drop_next: time to drop next packet, or when we dropped last + * @blue_timer: Blue time to next drop + * @p_drop: BLUE drop probability (0.32 fxp) + * @dropping: set if in dropping state + * @ecn_marked: set if marked + */ +struct cobalt_vars { + u32 count; + u32 rec_inv_sqrt; + ktime_t drop_next; + ktime_t blue_timer; + u32 p_drop; + bool dropping; + bool ecn_marked; +}; + +enum { + CAKE_SET_NONE = 0, + CAKE_SET_SPARSE, + CAKE_SET_SPARSE_WAIT, /* counted in SPARSE, actually in BULK */ + CAKE_SET_BULK, + CAKE_SET_DECAYING +}; + +struct cake_flow { + /* this stuff is all needed per-flow at dequeue time */ + struct sk_buff *head; + struct sk_buff *tail; + struct list_head flowchain; + s32 deficit; + u32 dropped; + struct cobalt_vars cvars; + u16 srchost; /* index into cake_host table */ + u16 dsthost; + u8 set; +}; /* please try to keep this structure <= 64 bytes */ + +struct cake_host { + u32 srchost_tag; + u32 dsthost_tag; + u16 srchost_refcnt; + u16 dsthost_refcnt; +}; + +struct cake_heap_entry { + u16 t:3, b:10; +}; + +struct cake_tin_data { + struct cake_flow flows[CAKE_QUEUES]; + u32 backlogs[CAKE_QUEUES]; + u32 tags[CAKE_QUEUES]; /* for set association */ + u16 overflow_idx[CAKE_QUEUES]; + struct cake_host hosts[CAKE_QUEUES]; /* for triple isolation */ + u16 flow_quantum; + + struct cobalt_params cparams; + u32 drop_overlimit; + u16 bulk_flow_count; + u16 sparse_flow_count; + u16 decaying_flow_count; + u16 unresponsive_flow_count; + + u32 max_skblen; + + struct list_head new_flows; + struct list_head old_flows; + struct list_head decaying_flows; + + /* time_next = time_this + ((len * rate_ns) >> rate_shft) */ + ktime_t time_next_packet; + u64 tin_rate_ns; + u64 tin_rate_bps; + u16 tin_rate_shft; + + u16 tin_quantum_prio; + u16 tin_quantum_band; + s32 tin_deficit; + u32 tin_backlog; + u32 tin_dropped; + u32 tin_ecn_mark; + + u32 packets; + u64 bytes; + + u32 ack_drops; + + /* moving averages */ + u64 avge_delay; + u64 peak_delay; + u64 base_delay; + + /* hash function stats */ + u32 way_directs; + u32 way_hits; + u32 way_misses; + u32 way_collisions; +}; /* number of tins is small, so size of this struct doesn't matter much */ + +struct cake_sched_data { + struct tcf_proto __rcu *filter_list; /* optional external classifier */ + struct tcf_block *block; + struct cake_tin_data *tins; + + struct cake_heap_entry overflow_heap[CAKE_QUEUES * CAKE_MAX_TINS]; + u16 overflow_timeout; + + u16 tin_cnt; + u8 tin_mode; + u8 flow_mode; + u8 ack_filter; + u8 atm_mode; + + /* time_next = time_this + ((len * rate_ns) >> rate_shft) */ + u16 rate_shft; + ktime_t time_next_packet; + ktime_t failsafe_next_packet; + u64 rate_ns; + u64 rate_bps; + u16 rate_flags; + s16 rate_overhead; + u16 rate_mpu; + u64 interval; + u64 target; + + /* resource tracking */ + u32 buffer_used; + u32 buffer_max_used; + u32 buffer_limit; + u32 buffer_config_limit; + + /* indices for dequeue */ + u16 cur_tin; + u16 cur_flow; + + struct qdisc_watchdog watchdog; + const u8 *tin_index; + const u8 *tin_order; + + /* bandwidth capacity estimate */ + ktime_t last_packet_time; + ktime_t avg_window_begin; + u64 avg_packet_interval; + u64 avg_window_bytes; + u64 avg_peak_bandwidth; + ktime_t last_reconfig_time; + + /* packet length stats */ + u32 avg_netoff; + u16 max_netlen; + u16 max_adjlen; + u16 min_netlen; + u16 min_adjlen; +}; + +enum { + CAKE_FLAG_OVERHEAD = BIT(0), + CAKE_FLAG_AUTORATE_INGRESS = BIT(1), + CAKE_FLAG_INGRESS = BIT(2), + CAKE_FLAG_WASH = BIT(3), + CAKE_FLAG_SPLIT_GSO = BIT(4) +}; + +/* COBALT operates the Codel and BLUE algorithms in parallel, in order to + * obtain the best features of each. Codel is excellent on flows which + * respond to congestion signals in a TCP-like way. BLUE is more effective on + * unresponsive flows. + */ + +struct cobalt_skb_cb { + ktime_t enqueue_time; +}; + +static u64 us_to_ns(u64 us) +{ + return us * NSEC_PER_USEC; +} + +static struct cobalt_skb_cb *get_cobalt_cb(const struct sk_buff *skb) +{ + qdisc_cb_private_validate(skb, sizeof(struct cobalt_skb_cb)); + return (struct cobalt_skb_cb *)qdisc_skb_cb(skb)->data; +} + +static ktime_t cobalt_get_enqueue_time(const struct sk_buff *skb) +{ + return get_cobalt_cb(skb)->enqueue_time; +} + +static void cobalt_set_enqueue_time(struct sk_buff *skb, + ktime_t now) +{ + get_cobalt_cb(skb)->enqueue_time = now; +} + +static u16 quantum_div[CAKE_QUEUES + 1] = {0}; + +#define REC_INV_SQRT_CACHE (16) +static u32 cobalt_rec_inv_sqrt_cache[REC_INV_SQRT_CACHE] = {0}; + +/* http://en.wikipedia.org/wiki/Methods_of_computing_square_roots + * new_invsqrt = (invsqrt / 2) * (3 - count * invsqrt^2) + * + * Here, invsqrt is a fixed point number (< 1.0), 32bit mantissa, aka Q0.32 + */ + +static void cobalt_newton_step(struct cobalt_vars *vars) +{ + u32 invsqrt, invsqrt2; + u64 val; + + invsqrt = vars->rec_inv_sqrt; + invsqrt2 = ((u64)invsqrt * invsqrt) >> 32; + val = (3LL << 32) - ((u64)vars->count * invsqrt2); + + val >>= 2; /* avoid overflow in following multiply */ + val = (val * invsqrt) >> (32 - 2 + 1); + + vars->rec_inv_sqrt = val; +} + +static void cobalt_invsqrt(struct cobalt_vars *vars) +{ + if (vars->count < REC_INV_SQRT_CACHE) + vars->rec_inv_sqrt = cobalt_rec_inv_sqrt_cache[vars->count]; + else + cobalt_newton_step(vars); +} + +/* There is a big difference in timing between the accurate values placed in + * the cache and the approximations given by a single Newton step for small + * count values, particularly when stepping from count 1 to 2 or vice versa. + * Above 16, a single Newton step gives sufficient accuracy in either + * direction, given the precision stored. + * + * The magnitude of the error when stepping up to count 2 is such as to give + * the value that *should* have been produced at count 4. + */ + +static void cobalt_cache_init(void) +{ + struct cobalt_vars v; + + memset(&v, 0, sizeof(v)); + v.rec_inv_sqrt = ~0U; + cobalt_rec_inv_sqrt_cache[0] = v.rec_inv_sqrt; + + for (v.count = 1; v.count < REC_INV_SQRT_CACHE; v.count++) { + cobalt_newton_step(&v); + cobalt_newton_step(&v); + cobalt_newton_step(&v); + cobalt_newton_step(&v); + + cobalt_rec_inv_sqrt_cache[v.count] = v.rec_inv_sqrt; + } +} + +static void cobalt_vars_init(struct cobalt_vars *vars) +{ + memset(vars, 0, sizeof(*vars)); + + if (!cobalt_rec_inv_sqrt_cache[0]) { + cobalt_cache_init(); + cobalt_rec_inv_sqrt_cache[0] = ~0; + } +} + +/* CoDel control_law is t + interval/sqrt(count) + * We maintain in rec_inv_sqrt the reciprocal value of sqrt(count) to avoid + * both sqrt() and divide operation. + */ +static ktime_t cobalt_control(ktime_t t, + u64 interval, + u32 rec_inv_sqrt) +{ + return ktime_add_ns(t, reciprocal_scale(interval, + rec_inv_sqrt)); +} + +/* Call this when a packet had to be dropped due to queue overflow. Returns + * true if the BLUE state was quiescent before but active after this call. + */ +static bool cobalt_queue_full(struct cobalt_vars *vars, + struct cobalt_params *p, + ktime_t now) +{ + bool up = false; + + if (ktime_to_ns(ktime_sub(now, vars->blue_timer)) > p->target) { + up = !vars->p_drop; + vars->p_drop += p->p_inc; + if (vars->p_drop < p->p_inc) + vars->p_drop = ~0; + vars->blue_timer = now; + } + vars->dropping = true; + vars->drop_next = now; + if (!vars->count) + vars->count = 1; + + return up; +} + +/* Call this when the queue was serviced but turned out to be empty. Returns + * true if the BLUE state was active before but quiescent after this call. + */ +static bool cobalt_queue_empty(struct cobalt_vars *vars, + struct cobalt_params *p, + ktime_t now) +{ + bool down = false; + + if (vars->p_drop && + ktime_to_ns(ktime_sub(now, vars->blue_timer)) > p->target) { + if (vars->p_drop < p->p_dec) + vars->p_drop = 0; + else + vars->p_drop -= p->p_dec; + vars->blue_timer = now; + down = !vars->p_drop; + } + vars->dropping = false; + + if (vars->count && ktime_to_ns(ktime_sub(now, vars->drop_next)) >= 0) { + vars->count--; + cobalt_invsqrt(vars); + vars->drop_next = cobalt_control(vars->drop_next, + p->interval, + vars->rec_inv_sqrt); + } + + return down; +} + +/* Call this with a freshly dequeued packet for possible congestion marking. + * Returns true as an instruction to drop the packet, false for delivery. + */ +static bool cobalt_should_drop(struct cobalt_vars *vars, + struct cobalt_params *p, + ktime_t now, + struct sk_buff *skb) +{ + bool next_due, over_target, drop = false; + ktime_t schedule; + u64 sojourn; + +/* The 'schedule' variable records, in its sign, whether 'now' is before or + * after 'drop_next'. This allows 'drop_next' to be updated before the next + * scheduling decision is actually branched, without destroying that + * information. Similarly, the first 'schedule' value calculated is preserved + * in the boolean 'next_due'. + * + * As for 'drop_next', we take advantage of the fact that 'interval' is both + * the delay between first exceeding 'target' and the first signalling event, + * *and* the scaling factor for the signalling frequency. It's therefore very + * natural to use a single mechanism for both purposes, and eliminates a + * significant amount of reference Codel's spaghetti code. To help with this, + * both the '0' and '1' entries in the invsqrt cache are 0xFFFFFFFF, as close + * as possible to 1.0 in fixed-point. + */ + + sojourn = ktime_to_ns(ktime_sub(now, cobalt_get_enqueue_time(skb))); + schedule = ktime_sub(now, vars->drop_next); + over_target = sojourn > p->target && + sojourn > p->mtu_time * 4; + next_due = vars->count && ktime_to_ns(schedule) >= 0; + + vars->ecn_marked = false; + + if (over_target) { + if (!vars->dropping) { + vars->dropping = true; + vars->drop_next = cobalt_control(now, + p->interval, + vars->rec_inv_sqrt); + } + if (!vars->count) + vars->count = 1; + } else if (vars->dropping) { + vars->dropping = false; + } + + if (next_due && vars->dropping) { + /* Use ECN mark if possible, otherwise drop */ + drop = !(vars->ecn_marked = INET_ECN_set_ce(skb)); + + vars->count++; + if (!vars->count) + vars->count--; + cobalt_invsqrt(vars); + vars->drop_next = cobalt_control(vars->drop_next, + p->interval, + vars->rec_inv_sqrt); + schedule = ktime_sub(now, vars->drop_next); + } else { + while (next_due) { + vars->count--; + cobalt_invsqrt(vars); + vars->drop_next = cobalt_control(vars->drop_next, + p->interval, + vars->rec_inv_sqrt); + schedule = ktime_sub(now, vars->drop_next); + next_due = vars->count && ktime_to_ns(schedule) >= 0; + } + } + + /* Simple BLUE implementation. Lack of ECN is deliberate. */ + if (vars->p_drop) + drop |= (prandom_u32() < vars->p_drop); + + /* Overload the drop_next field as an activity timeout */ + if (!vars->count) + vars->drop_next = ktime_add_ns(now, p->interval); + else if (ktime_to_ns(schedule) > 0 && !drop) + vars->drop_next = now; + + return drop; +} + +/* Cake has several subtle multiple bit settings. In these cases you + * would be matching triple isolate mode as well. + */ + +static bool cake_dsrc(int flow_mode) +{ + return (flow_mode & CAKE_FLOW_DUAL_SRC) == CAKE_FLOW_DUAL_SRC; +} + +static bool cake_ddst(int flow_mode) +{ + return (flow_mode & CAKE_FLOW_DUAL_DST) == CAKE_FLOW_DUAL_DST; +} + +static u32 cake_hash(struct cake_tin_data *q, const struct sk_buff *skb, + int flow_mode) +{ + u32 flow_hash = 0, srchost_hash, dsthost_hash; + u16 reduced_hash, srchost_idx, dsthost_idx; + struct flow_keys keys, host_keys; + + if (unlikely(flow_mode == CAKE_FLOW_NONE)) + return 0; + + skb_flow_dissect_flow_keys(skb, &keys, + FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); + + /* flow_hash_from_keys() sorts the addresses by value, so we have + * to preserve their order in a separate data structure to treat + * src and dst host addresses as independently selectable. + */ + host_keys = keys; + host_keys.ports.ports = 0; + host_keys.basic.ip_proto = 0; + host_keys.keyid.keyid = 0; + host_keys.tags.flow_label = 0; + + switch (host_keys.control.addr_type) { + case FLOW_DISSECTOR_KEY_IPV4_ADDRS: + host_keys.addrs.v4addrs.src = 0; + dsthost_hash = flow_hash_from_keys(&host_keys); + host_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src; + host_keys.addrs.v4addrs.dst = 0; + srchost_hash = flow_hash_from_keys(&host_keys); + break; + + case FLOW_DISSECTOR_KEY_IPV6_ADDRS: + memset(&host_keys.addrs.v6addrs.src, 0, + sizeof(host_keys.addrs.v6addrs.src)); + dsthost_hash = flow_hash_from_keys(&host_keys); + host_keys.addrs.v6addrs.src = keys.addrs.v6addrs.src; + memset(&host_keys.addrs.v6addrs.dst, 0, + sizeof(host_keys.addrs.v6addrs.dst)); + srchost_hash = flow_hash_from_keys(&host_keys); + break; + + default: + dsthost_hash = 0; + srchost_hash = 0; + } + + /* This *must* be after the above switch, since as a + * side-effect it sorts the src and dst addresses. + */ + if (flow_mode & CAKE_FLOW_FLOWS) + flow_hash = flow_hash_from_keys(&keys); + + if (!(flow_mode & CAKE_FLOW_FLOWS)) { + if (flow_mode & CAKE_FLOW_SRC_IP) + flow_hash ^= srchost_hash; + + if (flow_mode & CAKE_FLOW_DST_IP) + flow_hash ^= dsthost_hash; + } + + reduced_hash = flow_hash % CAKE_QUEUES; + + /* set-associative hashing */ + /* fast path if no hash collision (direct lookup succeeds) */ + if (likely(q->tags[reduced_hash] == flow_hash && + q->flows[reduced_hash].set)) { + q->way_directs++; + } else { + u32 inner_hash = reduced_hash % CAKE_SET_WAYS; + u32 outer_hash = reduced_hash - inner_hash; + bool allocate_src = false; + bool allocate_dst = false; + u32 i, k; + + /* check if any active queue in the set is reserved for + * this flow. + */ + for (i = 0, k = inner_hash; i < CAKE_SET_WAYS; + i++, k = (k + 1) % CAKE_SET_WAYS) { + if (q->tags[outer_hash + k] == flow_hash) { + if (i) + q->way_hits++; + + if (!q->flows[outer_hash + k].set) { + /* need to increment host refcnts */ + allocate_src = cake_dsrc(flow_mode); + allocate_dst = cake_ddst(flow_mode); + } + + goto found; + } + } + + /* no queue is reserved for this flow, look for an + * empty one. + */ + for (i = 0; i < CAKE_SET_WAYS; + i++, k = (k + 1) % CAKE_SET_WAYS) { + if (!q->flows[outer_hash + k].set) { + q->way_misses++; + allocate_src = cake_dsrc(flow_mode); + allocate_dst = cake_ddst(flow_mode); + goto found; + } + } + + /* With no empty queues, default to the original + * queue, accept the collision, update the host tags. + */ + q->way_collisions++; + q->hosts[q->flows[reduced_hash].srchost].srchost_refcnt--; + q->hosts[q->flows[reduced_hash].dsthost].dsthost_refcnt--; + allocate_src = cake_dsrc(flow_mode); + allocate_dst = cake_ddst(flow_mode); +found: + /* reserve queue for future packets in same flow */ + reduced_hash = outer_hash + k; + q->tags[reduced_hash] = flow_hash; + + if (allocate_src) { + srchost_idx = srchost_hash % CAKE_QUEUES; + inner_hash = srchost_idx % CAKE_SET_WAYS; + outer_hash = srchost_idx - inner_hash; + for (i = 0, k = inner_hash; i < CAKE_SET_WAYS; + i++, k = (k + 1) % CAKE_SET_WAYS) { + if (q->hosts[outer_hash + k].srchost_tag == + srchost_hash) + goto found_src; + } + for (i = 0; i < CAKE_SET_WAYS; + i++, k = (k + 1) % CAKE_SET_WAYS) { + if (!q->hosts[outer_hash + k].srchost_refcnt) + break; + } + q->hosts[outer_hash + k].srchost_tag = srchost_hash; +found_src: + srchost_idx = outer_hash + k; + q->hosts[srchost_idx].srchost_refcnt++; + q->flows[reduced_hash].srchost = srchost_idx; + } + + if (allocate_dst) { + dsthost_idx = dsthost_hash % CAKE_QUEUES; + inner_hash = dsthost_idx % CAKE_SET_WAYS; + outer_hash = dsthost_idx - inner_hash; + for (i = 0, k = inner_hash; i < CAKE_SET_WAYS; + i++, k = (k + 1) % CAKE_SET_WAYS) { + if (q->hosts[outer_hash + k].dsthost_tag == + dsthost_hash) + goto found_dst; + } + for (i = 0; i < CAKE_SET_WAYS; + i++, k = (k + 1) % CAKE_SET_WAYS) { + if (!q->hosts[outer_hash + k].dsthost_refcnt) + break; + } + q->hosts[outer_hash + k].dsthost_tag = dsthost_hash; +found_dst: + dsthost_idx = outer_hash + k; + q->hosts[dsthost_idx].dsthost_refcnt++; + q->flows[reduced_hash].dsthost = dsthost_idx; + } + } + + return reduced_hash; +} + +/* helper functions : might be changed when/if skb use a standard list_head */ +/* remove one skb from head of slot queue */ + +static struct sk_buff *dequeue_head(struct cake_flow *flow) +{ + struct sk_buff *skb = flow->head; + + if (skb) { + flow->head = skb->next; + skb->next = NULL; + } + + return skb; +} + +/* add skb to flow queue (tail add) */ + +static void flow_queue_add(struct cake_flow *flow, struct sk_buff *skb) +{ + if (!flow->head) + flow->head = skb; + else + flow->tail->next = skb; + flow->tail = skb; + skb->next = NULL; +} + +static u64 cake_ewma(u64 avg, u64 sample, u32 shift) +{ + avg -= avg >> shift; + avg += sample >> shift; + return avg; +} + +static void cake_heap_swap(struct cake_sched_data *q, u16 i, u16 j) +{ + struct cake_heap_entry ii = q->overflow_heap[i]; + struct cake_heap_entry jj = q->overflow_heap[j]; + + q->overflow_heap[i] = jj; + q->overflow_heap[j] = ii; + + q->tins[ii.t].overflow_idx[ii.b] = j; + q->tins[jj.t].overflow_idx[jj.b] = i; +} + +static u32 cake_heap_get_backlog(const struct cake_sched_data *q, u16 i) +{ + struct cake_heap_entry ii = q->overflow_heap[i]; + + return q->tins[ii.t].backlogs[ii.b]; +} + +static void cake_heapify(struct cake_sched_data *q, u16 i) +{ + static const u32 a = CAKE_MAX_TINS * CAKE_QUEUES; + u32 mb = cake_heap_get_backlog(q, i); + u32 m = i; + + while (m < a) { + u32 l = m + m + 1; + u32 r = l + 1; + + if (l < a) { + u32 lb = cake_heap_get_backlog(q, l); + + if (lb > mb) { + m = l; + mb = lb; + } + } + + if (r < a) { + u32 rb = cake_heap_get_backlog(q, r); + + if (rb > mb) { + m = r; + mb = rb; + } + } + + if (m != i) { + cake_heap_swap(q, i, m); + i = m; + } else { + break; + } + } +} + +static void cake_heapify_up(struct cake_sched_data *q, u16 i) +{ + while (i > 0 && i < CAKE_MAX_TINS * CAKE_QUEUES) { + u16 p = (i - 1) >> 1; + u32 ib = cake_heap_get_backlog(q, i); + u32 pb = cake_heap_get_backlog(q, p); + + if (ib > pb) { + cake_heap_swap(q, i, p); + i = p; + } else { + break; + } + } +} + +static int cake_advance_shaper(struct cake_sched_data *q, + struct cake_tin_data *b, + struct sk_buff *skb, + ktime_t now, bool drop) +{ + u32 len = qdisc_pkt_len(skb); + + /* charge packet bandwidth to this tin + * and to the global shaper. + */ + if (q->rate_ns) { + u64 tin_dur = (len * b->tin_rate_ns) >> b->tin_rate_shft; + u64 global_dur = (len * q->rate_ns) >> q->rate_shft; + u64 failsafe_dur = global_dur + (global_dur >> 1); + + if (ktime_before(b->time_next_packet, now)) + b->time_next_packet = ktime_add_ns(b->time_next_packet, + tin_dur); + + else if (ktime_before(b->time_next_packet, + ktime_add_ns(now, tin_dur))) + b->time_next_packet = ktime_add_ns(now, tin_dur); + + q->time_next_packet = ktime_add_ns(q->time_next_packet, + global_dur); + if (!drop) + q->failsafe_next_packet = \ + ktime_add_ns(q->failsafe_next_packet, + failsafe_dur); + } + return len; +} + +static unsigned int cake_drop(struct Qdisc *sch, struct sk_buff **to_free) +{ + struct cake_sched_data *q = qdisc_priv(sch); + ktime_t now = ktime_get(); + u32 idx = 0, tin = 0, len; + struct cake_heap_entry qq; + struct cake_tin_data *b; + struct cake_flow *flow; + struct sk_buff *skb; + + if (!q->overflow_timeout) { + int i; + /* Build fresh max-heap */ + for (i = CAKE_MAX_TINS * CAKE_QUEUES / 2; i >= 0; i--) + cake_heapify(q, i); + } + q->overflow_timeout = 65535; + + /* select longest queue for pruning */ + qq = q->overflow_heap[0]; + tin = qq.t; + idx = qq.b; + + b = &q->tins[tin]; + flow = &b->flows[idx]; + skb = dequeue_head(flow); + if (unlikely(!skb)) { + /* heap has gone wrong, rebuild it next time */ + q->overflow_timeout = 0; + return idx + (tin << 16); + } + + if (cobalt_queue_full(&flow->cvars, &b->cparams, now)) + b->unresponsive_flow_count++; + + len = qdisc_pkt_len(skb); + q->buffer_used -= skb->truesize; + b->backlogs[idx] -= len; + b->tin_backlog -= len; + sch->qstats.backlog -= len; + qdisc_tree_reduce_backlog(sch, 1, len); + + flow->dropped++; + b->tin_dropped++; + sch->qstats.drops++; + + __qdisc_drop(skb, to_free); + sch->q.qlen--; + + cake_heapify(q, 0); + + return idx + (tin << 16); +} + +static u32 cake_classify(struct Qdisc *sch, struct cake_tin_data *t, + struct sk_buff *skb, int flow_mode, int *qerr) +{ + struct cake_sched_data *q = qdisc_priv(sch); + struct tcf_proto *filter; + struct tcf_result res; + int result; + + filter = rcu_dereference_bh(q->filter_list); + if (!filter) + return cake_hash(t, skb, flow_mode) + 1; + + *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; + result = tcf_classify(skb, filter, &res, false); + if (result >= 0) { +#ifdef CONFIG_NET_CLS_ACT + switch (result) { + case TC_ACT_STOLEN: + case TC_ACT_QUEUED: + case TC_ACT_TRAP: + *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + /* fall through */ + case TC_ACT_SHOT: + return 0; + } +#endif + if (TC_H_MIN(res.classid) <= CAKE_QUEUES) + return TC_H_MIN(res.classid); + } + return 0; +} + +static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff **to_free) +{ + struct cake_sched_data *q = qdisc_priv(sch); + int len = qdisc_pkt_len(skb); + int uninitialized_var(ret); + ktime_t now = ktime_get(); + struct cake_tin_data *b; + struct cake_flow *flow; + u32 idx, tin; + + tin = 0; + b = &q->tins[tin]; + + /* choose flow to insert into */ + idx = cake_classify(sch, b, skb, q->flow_mode, &ret); + if (idx == 0) { + if (ret & __NET_XMIT_BYPASS) + qdisc_qstats_drop(sch); + __qdisc_drop(skb, to_free); + return ret; + } + idx--; + flow = &b->flows[idx]; + + /* ensure shaper state isn't stale */ + if (!b->tin_backlog) { + if (ktime_before(b->time_next_packet, now)) + b->time_next_packet = now; + + if (!sch->q.qlen) { + if (ktime_before(q->time_next_packet, now)) { + q->failsafe_next_packet = now; + q->time_next_packet = now; + } else if (ktime_after(q->time_next_packet, now) && + ktime_after(q->failsafe_next_packet, now)) { + u64 next = \ + min(ktime_to_ns(q->time_next_packet), + ktime_to_ns( + q->failsafe_next_packet)); + sch->qstats.overlimits++; + qdisc_watchdog_schedule_ns(&q->watchdog, next); + } + } + } + + if (unlikely(len > b->max_skblen)) + b->max_skblen = len; + + cobalt_set_enqueue_time(skb, now); + flow_queue_add(flow, skb); + + sch->q.qlen++; + q->buffer_used += skb->truesize; + + /* stats */ + b->packets++; + b->bytes += len; + b->backlogs[idx] += len; + b->tin_backlog += len; + sch->qstats.backlog += len; + q->avg_window_bytes += len; + + if (q->overflow_timeout) + cake_heapify_up(q, b->overflow_idx[idx]); + + /* incoming bandwidth capacity estimate */ + q->avg_window_bytes = 0; + q->last_packet_time = now; + + /* flowchain */ + if (!flow->set || flow->set == CAKE_SET_DECAYING) { + struct cake_host *srchost = &b->hosts[flow->srchost]; + struct cake_host *dsthost = &b->hosts[flow->dsthost]; + u16 host_load = 1; + + if (!flow->set) { + list_add_tail(&flow->flowchain, &b->new_flows); + } else { + b->decaying_flow_count--; + list_move_tail(&flow->flowchain, &b->new_flows); + } + flow->set = CAKE_SET_SPARSE; + b->sparse_flow_count++; + + if (cake_dsrc(q->flow_mode)) + host_load = max(host_load, srchost->srchost_refcnt); + + if (cake_ddst(q->flow_mode)) + host_load = max(host_load, dsthost->dsthost_refcnt); + + flow->deficit = (b->flow_quantum * + quantum_div[host_load]) >> 16; + } else if (flow->set == CAKE_SET_SPARSE_WAIT) { + /* this flow was empty, accounted as a sparse flow, but actually + * in the bulk rotation. + */ + flow->set = CAKE_SET_BULK; + b->sparse_flow_count--; + b->bulk_flow_count++; + } + + if (q->buffer_used > q->buffer_max_used) + q->buffer_max_used = q->buffer_used; + + if (q->buffer_used > q->buffer_limit) { + u32 dropped = 0; + + while (q->buffer_used > q->buffer_limit) { + dropped++; + cake_drop(sch, to_free); + } + b->drop_overlimit += dropped; + } + return NET_XMIT_SUCCESS; +} + +static struct sk_buff *cake_dequeue_one(struct Qdisc *sch) +{ + struct cake_sched_data *q = qdisc_priv(sch); + struct cake_tin_data *b = &q->tins[q->cur_tin]; + struct cake_flow *flow = &b->flows[q->cur_flow]; + struct sk_buff *skb = NULL; + u32 len; + + if (flow->head) { + skb = dequeue_head(flow); + len = qdisc_pkt_len(skb); + b->backlogs[q->cur_flow] -= len; + b->tin_backlog -= len; + sch->qstats.backlog -= len; + q->buffer_used -= skb->truesize; + sch->q.qlen--; + + if (q->overflow_timeout) + cake_heapify(q, b->overflow_idx[q->cur_flow]); + } + return skb; +} + +/* Discard leftover packets from a tin no longer in use. */ +static void cake_clear_tin(struct Qdisc *sch, u16 tin) +{ + struct cake_sched_data *q = qdisc_priv(sch); + struct sk_buff *skb; + + q->cur_tin = tin; + for (q->cur_flow = 0; q->cur_flow < CAKE_QUEUES; q->cur_flow++) + while (!!(skb = cake_dequeue_one(sch))) + kfree_skb(skb); +} + +static struct sk_buff *cake_dequeue(struct Qdisc *sch) +{ + struct cake_sched_data *q = qdisc_priv(sch); + struct cake_tin_data *b = &q->tins[q->cur_tin]; + struct cake_host *srchost, *dsthost; + ktime_t now = ktime_get(); + struct cake_flow *flow; + struct list_head *head; + bool first_flow = true; + struct sk_buff *skb; + u16 host_load; + u64 delay; + u32 len; + +begin: + if (!sch->q.qlen) + return NULL; + + /* global hard shaper */ + if (ktime_after(q->time_next_packet, now) && + ktime_after(q->failsafe_next_packet, now)) { + u64 next = min(ktime_to_ns(q->time_next_packet), + ktime_to_ns(q->failsafe_next_packet)); + + sch->qstats.overlimits++; + qdisc_watchdog_schedule_ns(&q->watchdog, next); + return NULL; + } + + /* Choose a class to work on. */ + if (!q->rate_ns) { + /* In unlimited mode, can't rely on shaper timings, just balance + * with DRR + */ + bool wrapped = false, empty = true; + + while (b->tin_deficit < 0 || + !(b->sparse_flow_count + b->bulk_flow_count)) { + if (b->tin_deficit <= 0) + b->tin_deficit += b->tin_quantum_band; + if (b->sparse_flow_count + b->bulk_flow_count) + empty = false; + + q->cur_tin++; + b++; + if (q->cur_tin >= q->tin_cnt) { + q->cur_tin = 0; + b = q->tins; + + if (wrapped) { + /* It's possible for q->qlen to be + * nonzero when we actually have no + * packets anywhere. + */ + if (empty) + return NULL; + } else { + wrapped = true; + } + } + } + } else { + /* In shaped mode, choose: + * - Highest-priority tin with queue and meeting schedule, or + * - The earliest-scheduled tin with queue. + */ + ktime_t best_time = KTIME_MAX; + int tin, best_tin = 0; + + for (tin = 0; tin < q->tin_cnt; tin++) { + b = q->tins + tin; + if ((b->sparse_flow_count + b->bulk_flow_count) > 0) { + ktime_t time_to_pkt = \ + ktime_sub(b->time_next_packet, now); + + if (ktime_to_ns(time_to_pkt) <= 0 || + ktime_compare(time_to_pkt, + best_time) <= 0) { + best_time = time_to_pkt; + best_tin = tin; + } + } + } + + q->cur_tin = best_tin; + b = q->tins + best_tin; + + /* No point in going further if no packets to deliver. */ + if (unlikely(!(b->sparse_flow_count + b->bulk_flow_count))) + return NULL; + } + +retry: + /* service this class */ + head = &b->decaying_flows; + if (!first_flow || list_empty(head)) { + head = &b->new_flows; + if (list_empty(head)) { + head = &b->old_flows; + if (unlikely(list_empty(head))) { + head = &b->decaying_flows; + if (unlikely(list_empty(head))) + goto begin; + } + } + } + flow = list_first_entry(head, struct cake_flow, flowchain); + q->cur_flow = flow - b->flows; + first_flow = false; + + /* triple isolation (modified DRR++) */ + srchost = &b->hosts[flow->srchost]; + dsthost = &b->hosts[flow->dsthost]; + host_load = 1; + + if (cake_dsrc(q->flow_mode)) + host_load = max(host_load, srchost->srchost_refcnt); + + if (cake_ddst(q->flow_mode)) + host_load = max(host_load, dsthost->dsthost_refcnt); + + WARN_ON(host_load > CAKE_QUEUES); + + /* flow isolation (DRR++) */ + if (flow->deficit <= 0) { + /* The shifted prandom_u32() is a way to apply dithering to + * avoid accumulating roundoff errors + */ + flow->deficit += (b->flow_quantum * quantum_div[host_load] + + (prandom_u32() >> 16)) >> 16; + list_move_tail(&flow->flowchain, &b->old_flows); + + /* Keep all flows with deficits out of the sparse and decaying + * rotations. No non-empty flow can go into the decaying + * rotation, so they can't get deficits + */ + if (flow->set == CAKE_SET_SPARSE) { + if (flow->head) { + b->sparse_flow_count--; + b->bulk_flow_count++; + flow->set = CAKE_SET_BULK; + } else { + /* we've moved it to the bulk rotation for + * correct deficit accounting but we still want + * to count it as a sparse flow, not a bulk one. + */ + flow->set = CAKE_SET_SPARSE_WAIT; + } + } + goto retry; + } + + /* Retrieve a packet via the AQM */ + while (1) { + skb = cake_dequeue_one(sch); + if (!skb) { + /* this queue was actually empty */ + if (cobalt_queue_empty(&flow->cvars, &b->cparams, now)) + b->unresponsive_flow_count--; + + if (flow->cvars.p_drop || flow->cvars.count || + ktime_before(now, flow->cvars.drop_next)) { + /* keep in the flowchain until the state has + * decayed to rest + */ + list_move_tail(&flow->flowchain, + &b->decaying_flows); + if (flow->set == CAKE_SET_BULK) { + b->bulk_flow_count--; + b->decaying_flow_count++; + } else if (flow->set == CAKE_SET_SPARSE || + flow->set == CAKE_SET_SPARSE_WAIT) { + b->sparse_flow_count--; + b->decaying_flow_count++; + } + flow->set = CAKE_SET_DECAYING; + } else { + /* remove empty queue from the flowchain */ + list_del_init(&flow->flowchain); + if (flow->set == CAKE_SET_SPARSE || + flow->set == CAKE_SET_SPARSE_WAIT) + b->sparse_flow_count--; + else if (flow->set == CAKE_SET_BULK) + b->bulk_flow_count--; + else + b->decaying_flow_count--; + + flow->set = CAKE_SET_NONE; + srchost->srchost_refcnt--; + dsthost->dsthost_refcnt--; + } + goto begin; + } + + /* Last packet in queue may be marked, shouldn't be dropped */ + if (!cobalt_should_drop(&flow->cvars, &b->cparams, now, skb) || + !flow->head) + break; + + flow->dropped++; + b->tin_dropped++; + qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(skb)); + qdisc_qstats_drop(sch); + kfree_skb(skb); + } + + b->tin_ecn_mark += !!flow->cvars.ecn_marked; + qdisc_bstats_update(sch, skb); + + /* collect delay stats */ + delay = ktime_to_ns(ktime_sub(now, cobalt_get_enqueue_time(skb))); + b->avge_delay = cake_ewma(b->avge_delay, delay, 8); + b->peak_delay = cake_ewma(b->peak_delay, delay, + delay > b->peak_delay ? 2 : 8); + b->base_delay = cake_ewma(b->base_delay, delay, + delay < b->base_delay ? 2 : 8); + + len = cake_advance_shaper(q, b, skb, now, false); + flow->deficit -= len; + b->tin_deficit -= len; + + if (ktime_after(q->time_next_packet, now) && sch->q.qlen) { + u64 next = min(ktime_to_ns(q->time_next_packet), + ktime_to_ns(q->failsafe_next_packet)); + + qdisc_watchdog_schedule_ns(&q->watchdog, next); + } else if (!sch->q.qlen) { + int i; + + for (i = 0; i < q->tin_cnt; i++) { + if (q->tins[i].decaying_flow_count) { + ktime_t next = \ + ktime_add_ns(now, + q->tins[i].cparams.target); + + qdisc_watchdog_schedule_ns(&q->watchdog, + ktime_to_ns(next)); + break; + } + } + } + + if (q->overflow_timeout) + q->overflow_timeout--; + + return skb; +} + +static void cake_reset(struct Qdisc *sch) +{ + u32 c; + + for (c = 0; c < CAKE_MAX_TINS; c++) + cake_clear_tin(sch, c); +} + +static const struct nla_policy cake_policy[TCA_CAKE_MAX + 1] = { + [TCA_CAKE_BASE_RATE64] = { .type = NLA_U64 }, + [TCA_CAKE_DIFFSERV_MODE] = { .type = NLA_U32 }, + [TCA_CAKE_ATM] = { .type = NLA_U32 }, + [TCA_CAKE_FLOW_MODE] = { .type = NLA_U32 }, + [TCA_CAKE_OVERHEAD] = { .type = NLA_S32 }, + [TCA_CAKE_RTT] = { .type = NLA_U32 }, + [TCA_CAKE_TARGET] = { .type = NLA_U32 }, + [TCA_CAKE_AUTORATE] = { .type = NLA_U32 }, + [TCA_CAKE_MEMORY] = { .type = NLA_U32 }, + [TCA_CAKE_NAT] = { .type = NLA_U32 }, + [TCA_CAKE_RAW] = { .type = NLA_U32 }, + [TCA_CAKE_WASH] = { .type = NLA_U32 }, + [TCA_CAKE_MPU] = { .type = NLA_U32 }, + [TCA_CAKE_INGRESS] = { .type = NLA_U32 }, + [TCA_CAKE_ACK_FILTER] = { .type = NLA_U32 }, +}; + +static void cake_set_rate(struct cake_tin_data *b, u64 rate, u32 mtu, + u64 target_ns, u64 rtt_est_ns) +{ + /* convert byte-rate into time-per-byte + * so it will always unwedge in reasonable time. + */ + static const u64 MIN_RATE = 64; + u32 byte_target = mtu; + u64 byte_target_ns; + u8 rate_shft = 0; + u64 rate_ns = 0; + + b->flow_quantum = 1514; + if (rate) { + b->flow_quantum = max(min(rate >> 12, 1514ULL), 300ULL); + rate_shft = 34; + rate_ns = ((u64)NSEC_PER_SEC) << rate_shft; + rate_ns = div64_u64(rate_ns, max(MIN_RATE, rate)); + while (!!(rate_ns >> 34)) { + rate_ns >>= 1; + rate_shft--; + } + } /* else unlimited, ie. zero delay */ + + b->tin_rate_bps = rate; + b->tin_rate_ns = rate_ns; + b->tin_rate_shft = rate_shft; + + byte_target_ns = (byte_target * rate_ns) >> rate_shft; + + b->cparams.target = max((byte_target_ns * 3) / 2, target_ns); + b->cparams.interval = max(rtt_est_ns + + b->cparams.target - target_ns, + b->cparams.target * 2); + b->cparams.mtu_time = byte_target_ns; + b->cparams.p_inc = 1 << 24; /* 1/256 */ + b->cparams.p_dec = 1 << 20; /* 1/4096 */ +} + +static void cake_reconfigure(struct Qdisc *sch) +{ + struct cake_sched_data *q = qdisc_priv(sch); + struct cake_tin_data *b = &q->tins[0]; + int c, ft = 0; + + q->tin_cnt = 1; + cake_set_rate(b, q->rate_bps, psched_mtu(qdisc_dev(sch)), + us_to_ns(q->target), us_to_ns(q->interval)); + b->tin_quantum_band = 65535; + b->tin_quantum_prio = 65535; + + for (c = q->tin_cnt; c < CAKE_MAX_TINS; c++) { + cake_clear_tin(sch, c); + q->tins[c].cparams.mtu_time = q->tins[ft].cparams.mtu_time; + } + + q->rate_ns = q->tins[ft].tin_rate_ns; + q->rate_shft = q->tins[ft].tin_rate_shft; + + if (q->buffer_config_limit) { + q->buffer_limit = q->buffer_config_limit; + } else if (q->rate_bps) { + u64 t = q->rate_bps * q->interval; + + do_div(t, USEC_PER_SEC / 4); + q->buffer_limit = max_t(u32, t, 4U << 20); + } else { + q->buffer_limit = ~0; + } + + sch->flags &= ~TCQ_F_CAN_BYPASS; + + q->buffer_limit = min(q->buffer_limit, + max(sch->limit * psched_mtu(qdisc_dev(sch)), + q->buffer_config_limit)); +} + +static int cake_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + struct cake_sched_data *q = qdisc_priv(sch); + struct nlattr *tb[TCA_CAKE_MAX + 1]; + int err; + + if (!opt) + return -EINVAL; + + err = nla_parse_nested(tb, TCA_CAKE_MAX, opt, cake_policy, extack); + if (err < 0) + return err; + + if (tb[TCA_CAKE_BASE_RATE64]) + q->rate_bps = nla_get_u64(tb[TCA_CAKE_BASE_RATE64]); + + if (tb[TCA_CAKE_FLOW_MODE]) + q->flow_mode = (nla_get_u32(tb[TCA_CAKE_FLOW_MODE]) & + CAKE_FLOW_MASK); + + if (tb[TCA_CAKE_RTT]) { + q->interval = nla_get_u32(tb[TCA_CAKE_RTT]); + + if (!q->interval) + q->interval = 1; + } + + if (tb[TCA_CAKE_TARGET]) { + q->target = nla_get_u32(tb[TCA_CAKE_TARGET]); + + if (!q->target) + q->target = 1; + } + + if (tb[TCA_CAKE_MEMORY]) + q->buffer_config_limit = nla_get_u32(tb[TCA_CAKE_MEMORY]); + + if (q->tins) { + sch_tree_lock(sch); + cake_reconfigure(sch); + sch_tree_unlock(sch); + } + + return 0; +} + +static void cake_destroy(struct Qdisc *sch) +{ + struct cake_sched_data *q = qdisc_priv(sch); + + qdisc_watchdog_cancel(&q->watchdog); + tcf_block_put(q->block); + kvfree(q->tins); +} + +static int cake_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + struct cake_sched_data *q = qdisc_priv(sch); + int i, j, err; + + sch->limit = 10240; + q->tin_mode = CAKE_DIFFSERV_BESTEFFORT; + q->flow_mode = CAKE_FLOW_TRIPLE; + + q->rate_bps = 0; /* unlimited by default */ + + q->interval = 100000; /* 100ms default */ + q->target = 5000; /* 5ms: codel RFC argues + * for 5 to 10% of interval + */ + + q->cur_tin = 0; + q->cur_flow = 0; + + qdisc_watchdog_init(&q->watchdog, sch); + + if (opt) { + int err = cake_change(sch, opt, extack); + + if (err) + return err; + } + + err = tcf_block_get(&q->block, &q->filter_list, sch, extack); + if (err) + return err; + + quantum_div[0] = ~0; + for (i = 1; i <= CAKE_QUEUES; i++) + quantum_div[i] = 65535 / i; + + q->tins = kvzalloc(CAKE_MAX_TINS * sizeof(struct cake_tin_data), + GFP_KERNEL); + if (!q->tins) + goto nomem; + + for (i = 0; i < CAKE_MAX_TINS; i++) { + struct cake_tin_data *b = q->tins + i; + + INIT_LIST_HEAD(&b->new_flows); + INIT_LIST_HEAD(&b->old_flows); + INIT_LIST_HEAD(&b->decaying_flows); + b->sparse_flow_count = 0; + b->bulk_flow_count = 0; + b->decaying_flow_count = 0; + + for (j = 0; j < CAKE_QUEUES; j++) { + struct cake_flow *flow = b->flows + j; + u32 k = j * CAKE_MAX_TINS + i; + + INIT_LIST_HEAD(&flow->flowchain); + cobalt_vars_init(&flow->cvars); + + q->overflow_heap[k].t = i; + q->overflow_heap[k].b = j; + b->overflow_idx[j] = k; + } + } + + cake_reconfigure(sch); + q->avg_peak_bandwidth = q->rate_bps; + q->min_netlen = ~0; + q->min_adjlen = ~0; + return 0; + +nomem: + cake_destroy(sch); + return -ENOMEM; +} + +static int cake_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + struct cake_sched_data *q = qdisc_priv(sch); + struct nlattr *opts; + + opts = nla_nest_start(skb, TCA_OPTIONS); + if (!opts) + goto nla_put_failure; + + if (nla_put_u64_64bit(skb, TCA_CAKE_BASE_RATE64, q->rate_bps, + TCA_CAKE_PAD)) + goto nla_put_failure; + + if (nla_put_u32(skb, TCA_CAKE_FLOW_MODE, + q->flow_mode & CAKE_FLOW_MASK)) + goto nla_put_failure; + + if (nla_put_u32(skb, TCA_CAKE_RTT, q->interval)) + goto nla_put_failure; + + if (nla_put_u32(skb, TCA_CAKE_TARGET, q->target)) + goto nla_put_failure; + + if (nla_put_u32(skb, TCA_CAKE_MEMORY, q->buffer_config_limit)) + goto nla_put_failure; + + return nla_nest_end(skb, opts); + +nla_put_failure: + return -1; +} + +static int cake_dump_stats(struct Qdisc *sch, struct gnet_dump *d) +{ + struct nlattr *stats = nla_nest_start(d->skb, TCA_STATS_APP); + struct cake_sched_data *q = qdisc_priv(sch); + struct nlattr *tstats, *ts; + int i; + + if (!stats) + return -1; + +#define PUT_STAT_U32(attr, data) do { \ + if (nla_put_u32(d->skb, TCA_CAKE_STATS_ ## attr, data)) \ + goto nla_put_failure; \ + } while (0) +#define PUT_STAT_U64(attr, data) do { \ + if (nla_put_u64_64bit(d->skb, TCA_CAKE_STATS_ ## attr, \ + data, TCA_CAKE_STATS_PAD)) \ + goto nla_put_failure; \ + } while (0) + + PUT_STAT_U64(CAPACITY_ESTIMATE64, q->avg_peak_bandwidth); + PUT_STAT_U32(MEMORY_LIMIT, q->buffer_limit); + PUT_STAT_U32(MEMORY_USED, q->buffer_max_used); + PUT_STAT_U32(AVG_NETOFF, ((q->avg_netoff + 0x8000) >> 16)); + PUT_STAT_U32(MAX_NETLEN, q->max_netlen); + PUT_STAT_U32(MAX_ADJLEN, q->max_adjlen); + PUT_STAT_U32(MIN_NETLEN, q->min_netlen); + PUT_STAT_U32(MIN_ADJLEN, q->min_adjlen); + +#undef PUT_STAT_U32 +#undef PUT_STAT_U64 + + tstats = nla_nest_start(d->skb, TCA_CAKE_STATS_TIN_STATS); + if (!tstats) + goto nla_put_failure; + +#define PUT_TSTAT_U32(attr, data) do { \ + if (nla_put_u32(d->skb, TCA_CAKE_TIN_STATS_ ## attr, data)) \ + goto nla_put_failure; \ + } while (0) +#define PUT_TSTAT_U64(attr, data) do { \ + if (nla_put_u64_64bit(d->skb, TCA_CAKE_TIN_STATS_ ## attr, \ + data, TCA_CAKE_TIN_STATS_PAD)) \ + goto nla_put_failure; \ + } while (0) + + for (i = 0; i < q->tin_cnt; i++) { + struct cake_tin_data *b = &q->tins[i]; + + ts = nla_nest_start(d->skb, i + 1); + if (!ts) + goto nla_put_failure; + + PUT_TSTAT_U64(THRESHOLD_RATE64, b->tin_rate_bps); + PUT_TSTAT_U64(SENT_BYTES64, b->bytes); + PUT_TSTAT_U32(BACKLOG_BYTES, b->tin_backlog); + + PUT_TSTAT_U32(TARGET_US, + ktime_to_us(ns_to_ktime(b->cparams.target))); + PUT_TSTAT_U32(INTERVAL_US, + ktime_to_us(ns_to_ktime(b->cparams.interval))); + + PUT_TSTAT_U32(SENT_PACKETS, b->packets); + PUT_TSTAT_U32(DROPPED_PACKETS, b->tin_dropped); + PUT_TSTAT_U32(ECN_MARKED_PACKETS, b->tin_ecn_mark); + PUT_TSTAT_U32(ACKS_DROPPED_PACKETS, b->ack_drops); + + PUT_TSTAT_U32(PEAK_DELAY_US, + ktime_to_us(ns_to_ktime(b->peak_delay))); + PUT_TSTAT_U32(AVG_DELAY_US, + ktime_to_us(ns_to_ktime(b->avge_delay))); + PUT_TSTAT_U32(BASE_DELAY_US, + ktime_to_us(ns_to_ktime(b->base_delay))); + + PUT_TSTAT_U32(WAY_INDIRECT_HITS, b->way_hits); + PUT_TSTAT_U32(WAY_MISSES, b->way_misses); + PUT_TSTAT_U32(WAY_COLLISIONS, b->way_collisions); + + PUT_TSTAT_U32(SPARSE_FLOWS, b->sparse_flow_count + + b->decaying_flow_count); + PUT_TSTAT_U32(BULK_FLOWS, b->bulk_flow_count); + PUT_TSTAT_U32(UNRESPONSIVE_FLOWS, b->unresponsive_flow_count); + PUT_TSTAT_U32(MAX_SKBLEN, b->max_skblen); + + PUT_TSTAT_U32(FLOW_QUANTUM, b->flow_quantum); + nla_nest_end(d->skb, ts); + } + +#undef PUT_TSTAT_U32 +#undef PUT_TSTAT_U64 + + nla_nest_end(d->skb, tstats); + return nla_nest_end(d->skb, stats); + +nla_put_failure: + nla_nest_cancel(d->skb, stats); + return -1; +} + +static struct Qdisc *cake_leaf(struct Qdisc *sch, unsigned long arg) +{ + return NULL; +} + +static unsigned long cake_find(struct Qdisc *sch, u32 classid) +{ + return 0; +} + +static unsigned long cake_bind(struct Qdisc *sch, unsigned long parent, + u32 classid) +{ + return 0; +} + +static void cake_unbind(struct Qdisc *q, unsigned long cl) +{ +} + +static struct tcf_block *cake_tcf_block(struct Qdisc *sch, unsigned long cl, + struct netlink_ext_ack *extack) +{ + struct cake_sched_data *q = qdisc_priv(sch); + + if (cl) + return NULL; + return q->block; +} + +static int cake_dump_class(struct Qdisc *sch, unsigned long cl, + struct sk_buff *skb, struct tcmsg *tcm) +{ + tcm->tcm_handle |= TC_H_MIN(cl); + return 0; +} + +static int cake_dump_class_stats(struct Qdisc *sch, unsigned long cl, + struct gnet_dump *d) +{ + struct cake_sched_data *q = qdisc_priv(sch); + const struct cake_flow *flow = NULL; + struct gnet_stats_queue qs = { 0 }; + struct nlattr *stats; + u32 idx = cl - 1; + + if (idx < CAKE_QUEUES * q->tin_cnt) { + const struct cake_tin_data *b = &q->tins[idx / CAKE_QUEUES]; + const struct sk_buff *skb; + + flow = &b->flows[idx % CAKE_QUEUES]; + + if (flow->head) { + sch_tree_lock(sch); + skb = flow->head; + while (skb) { + qs.qlen++; + skb = skb->next; + } + sch_tree_unlock(sch); + } + qs.backlog = b->backlogs[idx % CAKE_QUEUES]; + qs.drops = flow->dropped; + } + if (gnet_stats_copy_queue(d, NULL, &qs, qs.qlen) < 0) + return -1; + if (flow) { + ktime_t now = ktime_get(); + + stats = nla_nest_start(d->skb, TCA_STATS_APP); + if (!stats) + return -1; + +#define PUT_STAT_U32(attr, data) do { \ + if (nla_put_u32(d->skb, TCA_CAKE_STATS_ ## attr, data)) \ + goto nla_put_failure; \ + } while (0) +#define PUT_STAT_S32(attr, data) do { \ + if (nla_put_s32(d->skb, TCA_CAKE_STATS_ ## attr, data)) \ + goto nla_put_failure; \ + } while (0) + + PUT_STAT_S32(DEFICIT, flow->deficit); + PUT_STAT_U32(DROPPING, flow->cvars.dropping); + PUT_STAT_U32(COBALT_COUNT, flow->cvars.count); + PUT_STAT_U32(P_DROP, flow->cvars.p_drop); + if (flow->cvars.p_drop) { + PUT_STAT_S32(BLUE_TIMER_US, + ktime_to_us( + ktime_sub(now, + flow->cvars.blue_timer))); + } + if (flow->cvars.dropping) { + PUT_STAT_S32(DROP_NEXT_US, + ktime_to_us( + ktime_sub(now, + flow->cvars.drop_next))); + } + + if (nla_nest_end(d->skb, stats) < 0) + return -1; + } + + return 0; + +nla_put_failure: + nla_nest_cancel(d->skb, stats); + return -1; +} + +static void cake_walk(struct Qdisc *sch, struct qdisc_walker *arg) +{ + struct cake_sched_data *q = qdisc_priv(sch); + unsigned int i, j; + + if (arg->stop) + return; + + for (i = 0; i < q->tin_cnt; i++) { + struct cake_tin_data *b = &q->tins[i]; + + for (j = 0; j < CAKE_QUEUES; j++) { + if (list_empty(&b->flows[j].flowchain) || + arg->count < arg->skip) { + arg->count++; + continue; + } + if (arg->fn(sch, i * CAKE_QUEUES + j + 1, arg) < 0) { + arg->stop = 1; + break; + } + arg->count++; + } + } +} + +static const struct Qdisc_class_ops cake_class_ops = { + .leaf = cake_leaf, + .find = cake_find, + .tcf_block = cake_tcf_block, + .bind_tcf = cake_bind, + .unbind_tcf = cake_unbind, + .dump = cake_dump_class, + .dump_stats = cake_dump_class_stats, + .walk = cake_walk, +}; + +static struct Qdisc_ops cake_qdisc_ops __read_mostly = { + .cl_ops = &cake_class_ops, + .id = "cake", + .priv_size = sizeof(struct cake_sched_data), + .enqueue = cake_enqueue, + .dequeue = cake_dequeue, + .peek = qdisc_peek_dequeued, + .init = cake_init, + .reset = cake_reset, + .destroy = cake_destroy, + .change = cake_change, + .dump = cake_dump, + .dump_stats = cake_dump_stats, + .owner = THIS_MODULE, +}; + +static int __init cake_module_init(void) +{ + return register_qdisc(&cake_qdisc_ops); +} + +static void __exit cake_module_exit(void) +{ + unregister_qdisc(&cake_qdisc_ops); +} + +module_init(cake_module_init) +module_exit(cake_module_exit) +MODULE_AUTHOR("Jonathan Morton"); +MODULE_LICENSE("Dual BSD/GPL"); +MODULE_DESCRIPTION("The CAKE shaper."); -- cgit v1.2.3 From b60a60405fb95a688eb2ef4ef20f5fcaa7b64f68 Mon Sep 17 00:00:00 2001 From: Toke Høiland-Jørgensen Date: Fri, 6 Jul 2018 17:37:19 +0200 Subject: netfilter: Add nf_ct_get_tuple_skb global lookup function MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This adds a global netfilter function to extract a conntrack tuple from an skb. The function uses a new function added to nf_ct_hook, which will try to get the tuple from skb->_nfct, and do a full lookup if that fails. This makes it possible to use the lookup function before the skb has passed through the conntrack init hooks (e.g., in an ingress qdisc). The tuple is copied to the caller to avoid issues with reference counting. The function returns false if conntrack is not loaded, allowing it to be used without incurring a module dependency on conntrack. This is used by the NAT mode in sch_cake. Cc: netfilter-devel@vger.kernel.org Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: David S. Miller --- include/linux/netfilter.h | 11 +++++++++++ net/netfilter/core.c | 15 +++++++++++++++ net/netfilter/nf_conntrack_core.c | 36 ++++++++++++++++++++++++++++++++++++ 3 files changed, 62 insertions(+) (limited to 'include') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 23b48de8c2e2..07efffd0c759 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -414,8 +414,17 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) extern void (*ip_ct_attach)(struct sk_buff *, const struct sk_buff *) __rcu; void nf_ct_attach(struct sk_buff *, const struct sk_buff *); +struct nf_conntrack_tuple; +bool nf_ct_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple, + const struct sk_buff *skb); #else static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {} +struct nf_conntrack_tuple; +static inline bool nf_ct_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple, + const struct sk_buff *skb) +{ + return false; +} #endif struct nf_conn; @@ -424,6 +433,8 @@ enum ip_conntrack_info; struct nf_ct_hook { int (*update)(struct net *net, struct sk_buff *skb); void (*destroy)(struct nf_conntrack *); + bool (*get_tuple_skb)(struct nf_conntrack_tuple *, + const struct sk_buff *); }; extern struct nf_ct_hook __rcu *nf_ct_hook; diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 168af54db975..dc240cb47ddf 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -603,6 +603,21 @@ void nf_conntrack_destroy(struct nf_conntrack *nfct) } EXPORT_SYMBOL(nf_conntrack_destroy); +bool nf_ct_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple, + const struct sk_buff *skb) +{ + struct nf_ct_hook *ct_hook; + bool ret = false; + + rcu_read_lock(); + ct_hook = rcu_dereference(nf_ct_hook); + if (ct_hook) + ret = ct_hook->get_tuple_skb(dst_tuple, skb); + rcu_read_unlock(); + return ret; +} +EXPORT_SYMBOL(nf_ct_get_tuple_skb); + /* Built-in default zone used e.g. by modules. */ const struct nf_conntrack_zone nf_ct_zone_dflt = { .id = NF_CT_DEFAULT_ZONE_ID, diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 3465da2a98bd..85ab2fd6a665 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1683,6 +1683,41 @@ static int nf_conntrack_update(struct net *net, struct sk_buff *skb) return 0; } +static bool nf_conntrack_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple, + const struct sk_buff *skb) +{ + const struct nf_conntrack_tuple *src_tuple; + const struct nf_conntrack_tuple_hash *hash; + struct nf_conntrack_tuple srctuple; + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + + ct = nf_ct_get(skb, &ctinfo); + if (ct) { + src_tuple = nf_ct_tuple(ct, CTINFO2DIR(ctinfo)); + memcpy(dst_tuple, src_tuple, sizeof(*dst_tuple)); + return true; + } + + if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), + NFPROTO_IPV4, dev_net(skb->dev), + &srctuple)) + return false; + + hash = nf_conntrack_find_get(dev_net(skb->dev), + &nf_ct_zone_dflt, + &srctuple); + if (!hash) + return false; + + ct = nf_ct_tuplehash_to_ctrack(hash); + src_tuple = nf_ct_tuple(ct, !hash->tuple.dst.dir); + memcpy(dst_tuple, src_tuple, sizeof(*dst_tuple)); + nf_ct_put(ct); + + return true; +} + /* Bring out ya dead! */ static struct nf_conn * get_next_corpse(int (*iter)(struct nf_conn *i, void *data), @@ -2204,6 +2239,7 @@ err_cachep: static struct nf_ct_hook nf_conntrack_hook = { .update = nf_conntrack_update, .destroy = destroy_conntrack, + .get_tuple_skb = nf_conntrack_get_tuple_skb, }; void nf_conntrack_init_end(void) -- cgit v1.2.3 From 19f391eb05b8b005f2907ddc8f284487b446abf3 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 8 Jun 2018 11:19:32 -0400 Subject: turn filp_clone_open() into inline wrapper for dentry_open() it's exactly the same thing as dentry_open(&file->f_path, file->f_flags, file->f_cred) ... and rename it to file_clone_open(), while we are at it. 'filp' naming convention is bogus; sure, it's "file pointer", but we generally don't do that kind of Hungarian notation. Some of the instances have too many callers to touch, but this one has only two, so let's sanitize it while we can... Acked-by: Linus Torvalds Signed-off-by: Al Viro --- drivers/gpu/drm/drm_lease.c | 2 +- fs/binfmt_misc.c | 2 +- fs/open.c | 20 -------------------- include/linux/fs.h | 5 ++++- 4 files changed, 6 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_lease.c b/drivers/gpu/drm/drm_lease.c index d638c0fb3418..b54fb78a283c 100644 --- a/drivers/gpu/drm/drm_lease.c +++ b/drivers/gpu/drm/drm_lease.c @@ -553,7 +553,7 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev, /* Clone the lessor file to create a new file for us */ DRM_DEBUG_LEASE("Allocating lease file\n"); - lessee_file = filp_clone_open(lessor_file); + lessee_file = file_clone_open(lessor_file); if (IS_ERR(lessee_file)) { ret = PTR_ERR(lessee_file); goto out_lessee; diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index 4b5fff31ef27..aa4a7a23ff99 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -205,7 +205,7 @@ static int load_misc_binary(struct linux_binprm *bprm) goto error; if (fmt->flags & MISC_FMT_OPEN_FILE) { - interp_file = filp_clone_open(fmt->interp_file); + interp_file = file_clone_open(fmt->interp_file); if (!IS_ERR(interp_file)) deny_write_access(interp_file); } else { diff --git a/fs/open.c b/fs/open.c index d0e955b558ad..76c56966e297 100644 --- a/fs/open.c +++ b/fs/open.c @@ -1063,26 +1063,6 @@ struct file *file_open_root(struct dentry *dentry, struct vfsmount *mnt, } EXPORT_SYMBOL(file_open_root); -struct file *filp_clone_open(struct file *oldfile) -{ - struct file *file; - int retval; - - file = get_empty_filp(); - if (IS_ERR(file)) - return file; - - file->f_flags = oldfile->f_flags; - retval = vfs_open(&oldfile->f_path, file, oldfile->f_cred); - if (retval) { - put_filp(file); - return ERR_PTR(retval); - } - - return file; -} -EXPORT_SYMBOL(filp_clone_open); - long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode) { struct open_flags op; diff --git a/include/linux/fs.h b/include/linux/fs.h index aa9b4c169ed2..c4ca4c9c1130 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2422,7 +2422,10 @@ extern struct file *filp_open(const char *, int, umode_t); extern struct file *file_open_root(struct dentry *, struct vfsmount *, const char *, int, umode_t); extern struct file * dentry_open(const struct path *, int, const struct cred *); -extern struct file *filp_clone_open(struct file *); +static inline struct file *file_clone_open(struct file *file) +{ + return dentry_open(&file->f_path, file->f_flags, file->f_cred); +} extern int filp_close(struct file *, fl_owner_t id); extern struct filename *getname_flags(const char __user *, int, int *); -- cgit v1.2.3 From baacd8d100d571aa713c3c60b1471b9962e6ec8a Mon Sep 17 00:00:00 2001 From: Jerome Brunet Date: Thu, 5 Jul 2018 12:13:49 +0200 Subject: ASoC: dpcm: add rate merge to the BE stream merge As done for format and channels, add the possibility to merge the backend rates on the frontend rates. This useful if the backend does not support all rates supported by the frontend, or if several backends (cpu and codecs) with different capabilities are connected to the same frontend. Signed-off-by: Jerome Brunet Signed-off-by: Mark Brown --- include/sound/soc.h | 2 ++ sound/soc/soc-pcm.c | 60 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 62 insertions(+) (limited to 'include') diff --git a/include/sound/soc.h b/include/sound/soc.h index 870ba6b64817..a4915148f739 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -964,6 +964,8 @@ struct snd_soc_dai_link { unsigned int dpcm_merged_format:1; /* DPCM used FE & BE merged channel */ unsigned int dpcm_merged_chan:1; + /* DPCM used FE & BE merged rate */ + unsigned int dpcm_merged_rate:1; /* pmdown_time is ignored at stop */ unsigned int ignore_pmdown_time:1; diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index 114e6c060cae..4019bc10897c 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -1769,6 +1769,64 @@ static void dpcm_runtime_merge_chan(struct snd_pcm_substream *substream, } } +static void dpcm_runtime_merge_rate(struct snd_pcm_substream *substream, + unsigned int *rates, + unsigned int *rate_min, + unsigned int *rate_max) +{ + struct snd_soc_pcm_runtime *fe = substream->private_data; + struct snd_soc_dpcm *dpcm; + int stream = substream->stream; + + if (!fe->dai_link->dpcm_merged_rate) + return; + + /* + * It returns merged BE codec channel; + * if FE want to use it (= dpcm_merged_chan) + */ + + list_for_each_entry(dpcm, &fe->dpcm[stream].be_clients, list_be) { + struct snd_soc_pcm_runtime *be = dpcm->be; + struct snd_soc_dai_driver *cpu_dai_drv = be->cpu_dai->driver; + struct snd_soc_dai_driver *codec_dai_drv; + struct snd_soc_pcm_stream *codec_stream; + struct snd_soc_pcm_stream *cpu_stream; + int i; + + if (stream == SNDRV_PCM_STREAM_PLAYBACK) + cpu_stream = &cpu_dai_drv->playback; + else + cpu_stream = &cpu_dai_drv->capture; + + *rate_min = max(*rate_min, cpu_stream->rate_min); + *rate_max = min_not_zero(*rate_max, cpu_stream->rate_max); + *rates = snd_pcm_rate_mask_intersect(*rates, cpu_stream->rates); + + for (i = 0; i < be->num_codecs; i++) { + /* + * Skip CODECs which don't support the current stream + * type. See soc_pcm_init_runtime_hw() for more details + */ + if (!snd_soc_dai_stream_valid(be->codec_dais[i], + stream)) + continue; + + codec_dai_drv = be->codec_dais[i]->driver; + if (stream == SNDRV_PCM_STREAM_PLAYBACK) + codec_stream = &codec_dai_drv->playback; + else + codec_stream = &codec_dai_drv->capture; + + *rate_min = max(*rate_min, codec_stream->rate_min); + *rate_max = min_not_zero(*rate_max, + codec_stream->rate_max); + *rates = snd_pcm_rate_mask_intersect(*rates, + codec_stream->rates); + } + } +} + static void dpcm_set_fe_runtime(struct snd_pcm_substream *substream) { struct snd_pcm_runtime *runtime = substream->runtime; @@ -1784,6 +1842,8 @@ static void dpcm_set_fe_runtime(struct snd_pcm_substream *substream) dpcm_runtime_merge_format(substream, &runtime->hw.formats); dpcm_runtime_merge_chan(substream, &runtime->hw.channels_min, &runtime->hw.channels_max); + dpcm_runtime_merge_rate(substream, &runtime->hw.rates, + &runtime->hw.rate_min, &runtime->hw.rate_max); } static int dpcm_fe_dai_do_trigger(struct snd_pcm_substream *substream, int cmd); -- cgit v1.2.3 From db7a2d1809a5b6b08d138ff68837f805fc073351 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Wed, 20 Jun 2018 14:58:10 +0100 Subject: asm-generic: unistd.h: Wire up sys_rseq The new rseq call arrived in 4.18-rc1, so provide it in the asm-generic unistd.h for architectures such as arm64. Acked-by: Arnd Bergmann Acked-by: Mathieu Desnoyers Signed-off-by: Will Deacon --- include/uapi/asm-generic/unistd.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 42990676a55e..df4bedb9b01c 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -734,9 +734,11 @@ __SYSCALL(__NR_pkey_free, sys_pkey_free) __SYSCALL(__NR_statx, sys_statx) #define __NR_io_pgetevents 292 __SC_COMP(__NR_io_pgetevents, sys_io_pgetevents, compat_sys_io_pgetevents) +#define __NR_rseq 293 +__SYSCALL(__NR_rseq, sys_rseq) #undef __NR_syscalls -#define __NR_syscalls 293 +#define __NR_syscalls 294 /* * 32 bit systems traditionally used different -- cgit v1.2.3 From 03dc7a35fcc83a199121a5156c4a7a976b836682 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 11 Jul 2018 12:19:14 +0200 Subject: ipv6: xfrm: use 64-bit timestamps get_seconds() is deprecated because it can overflow on 32-bit architectures. For the xfrm_state->lastused member, we treat the data as a 64-bit number already, so we just need to use the right accessor that works on both 32-bit and 64-bit machines. Signed-off-by: Arnd Bergmann Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 2 +- net/ipv6/xfrm6_mode_ro.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index a5378613a49c..1350e2cf0749 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -227,7 +227,7 @@ struct xfrm_state { long saved_tmo; /* Last used time */ - unsigned long lastused; + time64_t lastused; struct page_frag xfrag; diff --git a/net/ipv6/xfrm6_mode_ro.c b/net/ipv6/xfrm6_mode_ro.c index 07d36573f50b..da28e4407b8f 100644 --- a/net/ipv6/xfrm6_mode_ro.c +++ b/net/ipv6/xfrm6_mode_ro.c @@ -55,7 +55,7 @@ static int xfrm6_ro_output(struct xfrm_state *x, struct sk_buff *skb) __skb_pull(skb, hdr_len); memmove(ipv6_hdr(skb), iph, hdr_len); - x->lastused = get_seconds(); + x->lastused = ktime_get_real_seconds(); return 0; } -- cgit v1.2.3 From 5685ca0ca292b656086085dc3847f10e7ff85225 Mon Sep 17 00:00:00 2001 From: Noralf Trønnes Date: Tue, 10 Jul 2018 17:05:18 +0200 Subject: drm/tinydrm: Fix doc build warnings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit include/drm/tinydrm/tinydrm.h:34: warning: Function parameter or member 'fb_dirty' not described in 'tinydrm_device' drivers/gpu/drm/tinydrm/mipi-dbi.c:272: warning: Function parameter or member 'crtc_state' not described in 'mipi_dbi_enable_flush' drivers/gpu/drm/tinydrm/mipi-dbi.c:272: warning: Function parameter or member 'plane_state' not described in 'mipi_dbi_enable_flush' Move struct member docs inline so it's not missed next time. Cc: David Lechner Signed-off-by: Noralf Trønnes Reviewed-by: David Lechner Link: https://patchwork.freedesktop.org/patch/msgid/20180710150518.10528-1-noralf@tronnes.org --- drivers/gpu/drm/tinydrm/mipi-dbi.c | 2 ++ include/drm/tinydrm/tinydrm.h | 23 +++++++++++++++++++---- 2 files changed, 21 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/tinydrm/mipi-dbi.c b/drivers/gpu/drm/tinydrm/mipi-dbi.c index 4d1fb31a781f..cb3441e51d5f 100644 --- a/drivers/gpu/drm/tinydrm/mipi-dbi.c +++ b/drivers/gpu/drm/tinydrm/mipi-dbi.c @@ -260,6 +260,8 @@ static const struct drm_framebuffer_funcs mipi_dbi_fb_funcs = { /** * mipi_dbi_enable_flush - MIPI DBI enable helper * @mipi: MIPI DBI structure + * @crtc_state: CRTC state + * @plane_state: Plane state * * This function sets &mipi_dbi->enabled, flushes the whole framebuffer and * enables the backlight. Drivers can use this in their diff --git a/include/drm/tinydrm/tinydrm.h b/include/drm/tinydrm/tinydrm.h index 56e4a916b5e8..fe9827d0ca8a 100644 --- a/include/drm/tinydrm/tinydrm.h +++ b/include/drm/tinydrm/tinydrm.h @@ -16,16 +16,31 @@ /** * struct tinydrm_device - tinydrm device - * @drm: DRM device - * @pipe: Display pipe structure - * @dirty_lock: Serializes framebuffer flushing - * @fb_funcs: Framebuffer functions used when creating framebuffers */ struct tinydrm_device { + /** + * @drm: DRM device + */ struct drm_device *drm; + + /** + * @pipe: Display pipe structure + */ struct drm_simple_display_pipe pipe; + + /** + * @dirty_lock: Serializes framebuffer flushing + */ struct mutex dirty_lock; + + /** + * @fb_funcs: Framebuffer functions used when creating framebuffers + */ const struct drm_framebuffer_funcs *fb_funcs; + + /** + * @fb_dirty: Framebuffer dirty callback + */ int (*fb_dirty)(struct drm_framebuffer *framebuffer, struct drm_file *file_priv, unsigned flags, unsigned color, struct drm_clip_rect *clips, -- cgit v1.2.3 From 2640c3facbd6e21e63c95f19588cc24913a263cd Mon Sep 17 00:00:00 2001 From: shaoyunl Date: Wed, 11 Jul 2018 22:32:50 -0400 Subject: drm/amdkfd: Handle VM faults in KFD MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit 1. Pre-GFX9 the amdgpu ISR saves the vm-fault status and address per per-vmid. amdkfd needs to get the information from amdgpu through the new get_vm_fault_info interface. On GFX9 and later, all the required information is in the IH ring 2. amdkfd unmaps all queues from the faulting process and create new run-list without the guilty process 3. amdkfd notifies the runtime of the vm fault trap via EVENT_TYPE_MEMORY Signed-off-by: shaoyun liu Signed-off-by: Felix Kuehling Acked-by: Christian König Signed-off-by: Oded Gabbay --- drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c | 25 ++++++++++++--- drivers/gpu/drm/amd/amdkfd/cik_int.h | 2 ++ .../gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 17 ++++++++++ drivers/gpu/drm/amd/amdkfd/kfd_events.c | 37 ++++++++++++++++++++++ drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c | 18 +++++++++-- drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 4 +++ include/uapi/linux/kfd_ioctl.h | 2 +- 7 files changed, 98 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c b/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c index 49df6c791cfc..cc33870e7edb 100644 --- a/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c +++ b/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c @@ -48,18 +48,19 @@ static bool cik_event_interrupt_isr(struct kfd_dev *dev, return ihre->source_id == CIK_INTSRC_CP_END_OF_PIPE || ihre->source_id == CIK_INTSRC_SDMA_TRAP || ihre->source_id == CIK_INTSRC_SQ_INTERRUPT_MSG || - ihre->source_id == CIK_INTSRC_CP_BAD_OPCODE; + ihre->source_id == CIK_INTSRC_CP_BAD_OPCODE || + ihre->source_id == CIK_INTSRC_GFX_PAGE_INV_FAULT || + ihre->source_id == CIK_INTSRC_GFX_MEM_PROT_FAULT; } static void cik_event_interrupt_wq(struct kfd_dev *dev, const uint32_t *ih_ring_entry) { - unsigned int pasid; const struct cik_ih_ring_entry *ihre = (const struct cik_ih_ring_entry *)ih_ring_entry; uint32_t context_id = ihre->data & 0xfffffff; - - pasid = (ihre->ring_id & 0xffff0000) >> 16; + unsigned int vmid = (ihre->ring_id & 0x0000ff00) >> 8; + unsigned int pasid = (ihre->ring_id & 0xffff0000) >> 16; if (pasid == 0) return; @@ -72,6 +73,22 @@ static void cik_event_interrupt_wq(struct kfd_dev *dev, kfd_signal_event_interrupt(pasid, context_id & 0xff, 8); else if (ihre->source_id == CIK_INTSRC_CP_BAD_OPCODE) kfd_signal_hw_exception_event(pasid); + else if (ihre->source_id == CIK_INTSRC_GFX_PAGE_INV_FAULT || + ihre->source_id == CIK_INTSRC_GFX_MEM_PROT_FAULT) { + struct kfd_vm_fault_info info; + + kfd_process_vm_fault(dev->dqm, pasid); + + memset(&info, 0, sizeof(info)); + dev->kfd2kgd->get_vm_fault_info(dev->kgd, &info); + if (!info.page_addr && !info.status) + return; + + if (info.vmid == vmid) + kfd_signal_vm_fault_event(dev, pasid, &info); + else + kfd_signal_vm_fault_event(dev, pasid, NULL); + } } const struct kfd_event_interrupt_class event_interrupt_class_cik = { diff --git a/drivers/gpu/drm/amd/amdkfd/cik_int.h b/drivers/gpu/drm/amd/amdkfd/cik_int.h index 109298b9d507..a2079a04a673 100644 --- a/drivers/gpu/drm/amd/amdkfd/cik_int.h +++ b/drivers/gpu/drm/amd/amdkfd/cik_int.h @@ -37,6 +37,8 @@ struct cik_ih_ring_entry { #define CIK_INTSRC_DEQUEUE_COMPLETE 0xC6 #define CIK_INTSRC_SDMA_TRAP 0xE0 #define CIK_INTSRC_SQ_INTERRUPT_MSG 0xEF +#define CIK_INTSRC_GFX_PAGE_INV_FAULT 0x92 +#define CIK_INTSRC_GFX_MEM_PROT_FAULT 0x93 #endif diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index f2f81d26db0c..44fc2038770e 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -1684,6 +1684,23 @@ void device_queue_manager_uninit(struct device_queue_manager *dqm) kfree(dqm); } +int kfd_process_vm_fault(struct device_queue_manager *dqm, + unsigned int pasid) +{ + struct kfd_process_device *pdd; + struct kfd_process *p = kfd_lookup_process_by_pasid(pasid); + int ret = 0; + + if (!p) + return -EINVAL; + pdd = kfd_get_process_device_data(dqm->dev, p); + if (pdd) + ret = dqm->ops.evict_process_queues(dqm, &pdd->qpd); + kfd_unref_process(p); + + return ret; +} + #if defined(CONFIG_DEBUG_FS) static void seq_reg_dump(struct seq_file *m, diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c index 3d5a8332e8c0..b58a0e665ebc 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c @@ -963,3 +963,40 @@ void kfd_signal_hw_exception_event(unsigned int pasid) mutex_unlock(&p->event_mutex); kfd_unref_process(p); } + +void kfd_signal_vm_fault_event(struct kfd_dev *dev, unsigned int pasid, + struct kfd_vm_fault_info *info) +{ + struct kfd_event *ev; + uint32_t id; + struct kfd_process *p = kfd_lookup_process_by_pasid(pasid); + struct kfd_hsa_memory_exception_data memory_exception_data; + + if (!p) + return; /* Presumably process exited. */ + memset(&memory_exception_data, 0, sizeof(memory_exception_data)); + memory_exception_data.gpu_id = dev->id; + memory_exception_data.failure.imprecise = 1; + /* Set failure reason */ + if (info) { + memory_exception_data.va = (info->page_addr) << PAGE_SHIFT; + memory_exception_data.failure.NotPresent = + info->prot_valid ? 1 : 0; + memory_exception_data.failure.NoExecute = + info->prot_exec ? 1 : 0; + memory_exception_data.failure.ReadOnly = + info->prot_write ? 1 : 0; + memory_exception_data.failure.imprecise = 0; + } + mutex_lock(&p->event_mutex); + + id = KFD_FIRST_NONSIGNAL_EVENT_ID; + idr_for_each_entry_continue(&p->event_idr, ev, id) + if (ev->type == KFD_EVENT_TYPE_MEMORY) { + ev->memory_exception_data = memory_exception_data; + set_event(ev); + } + + mutex_unlock(&p->event_mutex); + kfd_unref_process(p); +} diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c index 37029baa3346..d6b64e692760 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c @@ -57,7 +57,9 @@ static bool event_interrupt_isr_v9(struct kfd_dev *dev, return source_id == SOC15_INTSRC_CP_END_OF_PIPE || source_id == SOC15_INTSRC_SDMA_TRAP || source_id == SOC15_INTSRC_SQ_INTERRUPT_MSG || - source_id == SOC15_INTSRC_CP_BAD_OPCODE; + source_id == SOC15_INTSRC_CP_BAD_OPCODE || + client_id == SOC15_IH_CLIENTID_VMC || + client_id == SOC15_IH_CLIENTID_UTCL2; } static void event_interrupt_wq_v9(struct kfd_dev *dev, @@ -82,7 +84,19 @@ static void event_interrupt_wq_v9(struct kfd_dev *dev, kfd_signal_hw_exception_event(pasid); else if (client_id == SOC15_IH_CLIENTID_VMC || client_id == SOC15_IH_CLIENTID_UTCL2) { - /* TODO */ + struct kfd_vm_fault_info info = {0}; + uint16_t ring_id = SOC15_RING_ID_FROM_IH_ENTRY(ih_ring_entry); + + info.vmid = vmid; + info.mc_id = client_id; + info.page_addr = ih_ring_entry[4] | + (uint64_t)(ih_ring_entry[5] & 0xf) << 32; + info.prot_valid = ring_id & 0x08; + info.prot_read = ring_id & 0x10; + info.prot_write = ring_id & 0x20; + + kfd_process_vm_fault(dev->dqm, pasid); + kfd_signal_vm_fault_event(dev, pasid, &info); } } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index 5e3990bb4c4b..91a3368421b1 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -838,6 +838,7 @@ void device_queue_manager_uninit(struct device_queue_manager *dqm); struct kernel_queue *kernel_queue_init(struct kfd_dev *dev, enum kfd_queue_type type); void kernel_queue_uninit(struct kernel_queue *kq); +int kfd_process_vm_fault(struct device_queue_manager *dqm, unsigned int pasid); /* Process Queue Manager */ struct process_queue_node { @@ -964,6 +965,9 @@ int kfd_event_create(struct file *devkfd, struct kfd_process *p, uint64_t *event_page_offset, uint32_t *event_slot_index); int kfd_event_destroy(struct kfd_process *p, uint32_t event_id); +void kfd_signal_vm_fault_event(struct kfd_dev *dev, unsigned int pasid, + struct kfd_vm_fault_info *info); + void kfd_flush_tlb(struct kfd_process_device *pdd); int dbgdev_wave_reset_wavefronts(struct kfd_dev *dev, struct kfd_process *p); diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index b4f5073dbac2..46a54ab1e728 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -219,7 +219,7 @@ struct kfd_memory_exception_failure { __u32 NotPresent; /* Page not present or supervisor privilege */ __u32 ReadOnly; /* Write access to a read-only page */ __u32 NoExecute; /* Execute access to a page marked NX */ - __u32 pad; + __u32 imprecise; /* Can't determine the exact fault address */ }; /* memory exception data*/ -- cgit v1.2.3 From 0c119abad7f0d7987c3ce4ea76b30bde76d0436e Mon Sep 17 00:00:00 2001 From: Shaoyun Liu Date: Wed, 11 Jul 2018 22:32:53 -0400 Subject: drm/amd: Add kfd ioctl defines for hw_exception event MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Shaoyun Liu Reviewed-by: Felix Kuehling Signed-off-by: Felix Kuehling Acked-by: Christian König Signed-off-by: Oded Gabbay --- include/uapi/linux/kfd_ioctl.h | 20 +++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index 46a54ab1e728..88d17c39dbf9 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -189,6 +189,15 @@ struct kfd_ioctl_dbg_wave_control_args { #define KFD_SIGNAL_EVENT_LIMIT 4096 +/* For kfd_event_data.hw_exception_data.reset_type. */ +#define KFD_HW_EXCEPTION_WHOLE_GPU_RESET 0 +#define KFD_HW_EXCEPTION_PER_ENGINE_RESET 1 + +/* For kfd_event_data.hw_exception_data.reset_cause. */ +#define KFD_HW_EXCEPTION_GPU_HANG 0 +#define KFD_HW_EXCEPTION_ECC 1 + + struct kfd_ioctl_create_event_args { __u64 event_page_offset; /* from KFD */ __u32 event_trigger_data; /* from KFD - signal events only */ @@ -230,10 +239,19 @@ struct kfd_hsa_memory_exception_data { __u32 pad; }; -/* Event data*/ +/* hw exception data */ +struct kfd_hsa_hw_exception_data { + uint32_t reset_type; + uint32_t reset_cause; + uint32_t memory_lost; + uint32_t gpu_id; +}; + +/* Event data */ struct kfd_event_data { union { struct kfd_hsa_memory_exception_data memory_exception_data; + struct kfd_hsa_hw_exception_data hw_exception_data; }; /* From KFD */ __u64 kfd_event_data_ext; /* pointer to an extension structure for future exception types */ -- cgit v1.2.3 From 9dc55f1389f9569acf9659e58dd836a9c70df217 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 11 Jul 2018 22:26:05 -0700 Subject: iomap: add support for sub-pagesize buffered I/O without buffer heads After already supporting a simple implementation of buffered writes for the blocksize == PAGE_SIZE case in the last commit this adds full support even for smaller block sizes. There are three bits of per-block information in the buffer_head structure that really matter for the iomap read and write path: - uptodate status (BH_uptodate) - marked as currently under read I/O (BH_Async_Read) - marked as currently under write I/O (BH_Async_Write) Instead of having new per-block structures this now adds a per-page structure called struct iomap_page to track this information in a slightly different form: - a bitmap for the per-block uptodate status. For worst case of a 64k page size system this bitmap needs to contain 128 bits. For the typical 4k page size case it only needs 8 bits, although we still need a full unsigned long due to the way the atomic bitmap API works. - two atomic_t counters are used to track the outstanding read and write counts There is quite a bit of boilerplate code as the buffered I/O path uses various helper methods, but the actual code is very straight forward. Signed-off-by: Christoph Hellwig Reviewed-by: Brian Foster Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/iomap.c | 280 ++++++++++++++++++++++++++++++++++++++++++++++---- include/linux/iomap.h | 31 ++++++ 2 files changed, 290 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/fs/iomap.c b/fs/iomap.c index 13cdcf33e6c0..07501a647d13 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include @@ -104,6 +105,138 @@ iomap_sector(struct iomap *iomap, loff_t pos) return (iomap->addr + pos - iomap->offset) >> SECTOR_SHIFT; } +static struct iomap_page * +iomap_page_create(struct inode *inode, struct page *page) +{ + struct iomap_page *iop = to_iomap_page(page); + + if (iop || i_blocksize(inode) == PAGE_SIZE) + return iop; + + iop = kmalloc(sizeof(*iop), GFP_NOFS | __GFP_NOFAIL); + atomic_set(&iop->read_count, 0); + atomic_set(&iop->write_count, 0); + bitmap_zero(iop->uptodate, PAGE_SIZE / SECTOR_SIZE); + set_page_private(page, (unsigned long)iop); + SetPagePrivate(page); + return iop; +} + +static void +iomap_page_release(struct page *page) +{ + struct iomap_page *iop = to_iomap_page(page); + + if (!iop) + return; + WARN_ON_ONCE(atomic_read(&iop->read_count)); + WARN_ON_ONCE(atomic_read(&iop->write_count)); + ClearPagePrivate(page); + set_page_private(page, 0); + kfree(iop); +} + +/* + * Calculate the range inside the page that we actually need to read. + */ +static void +iomap_adjust_read_range(struct inode *inode, struct iomap_page *iop, + loff_t *pos, loff_t length, unsigned *offp, unsigned *lenp) +{ + unsigned block_bits = inode->i_blkbits; + unsigned block_size = (1 << block_bits); + unsigned poff = *pos & (PAGE_SIZE - 1); + unsigned plen = min_t(loff_t, PAGE_SIZE - poff, length); + unsigned first = poff >> block_bits; + unsigned last = (poff + plen - 1) >> block_bits; + unsigned end = (i_size_read(inode) & (PAGE_SIZE - 1)) >> block_bits; + + /* + * If the block size is smaller than the page size we need to check the + * per-block uptodate status and adjust the offset and length if needed + * to avoid reading in already uptodate ranges. + */ + if (iop) { + unsigned int i; + + /* move forward for each leading block marked uptodate */ + for (i = first; i <= last; i++) { + if (!test_bit(i, iop->uptodate)) + break; + *pos += block_size; + poff += block_size; + plen -= block_size; + first++; + } + + /* truncate len if we find any trailing uptodate block(s) */ + for ( ; i <= last; i++) { + if (test_bit(i, iop->uptodate)) { + plen -= (last - i + 1) * block_size; + last = i - 1; + break; + } + } + } + + /* + * If the extent spans the block that contains the i_size we need to + * handle both halves separately so that we properly zero data in the + * page cache for blocks that are entirely outside of i_size. + */ + if (first <= end && last > end) + plen -= (last - end) * block_size; + + *offp = poff; + *lenp = plen; +} + +static void +iomap_set_range_uptodate(struct page *page, unsigned off, unsigned len) +{ + struct iomap_page *iop = to_iomap_page(page); + struct inode *inode = page->mapping->host; + unsigned first = off >> inode->i_blkbits; + unsigned last = (off + len - 1) >> inode->i_blkbits; + unsigned int i; + bool uptodate = true; + + if (iop) { + for (i = 0; i < PAGE_SIZE / i_blocksize(inode); i++) { + if (i >= first && i <= last) + set_bit(i, iop->uptodate); + else if (!test_bit(i, iop->uptodate)) + uptodate = false; + } + } + + if (uptodate && !PageError(page)) + SetPageUptodate(page); +} + +static void +iomap_read_finish(struct iomap_page *iop, struct page *page) +{ + if (!iop || atomic_dec_and_test(&iop->read_count)) + unlock_page(page); +} + +static void +iomap_read_page_end_io(struct bio_vec *bvec, int error) +{ + struct page *page = bvec->bv_page; + struct iomap_page *iop = to_iomap_page(page); + + if (unlikely(error)) { + ClearPageUptodate(page); + SetPageError(page); + } else { + iomap_set_range_uptodate(page, bvec->bv_offset, bvec->bv_len); + } + + iomap_read_finish(iop, page); +} + static void iomap_read_inline_data(struct inode *inode, struct page *page, struct iomap *iomap) @@ -132,7 +265,7 @@ iomap_read_end_io(struct bio *bio) int i; bio_for_each_segment_all(bvec, bio, i) - page_endio(bvec->bv_page, false, error); + iomap_read_page_end_io(bvec, error); bio_put(bio); } @@ -150,9 +283,10 @@ iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data, { struct iomap_readpage_ctx *ctx = data; struct page *page = ctx->cur_page; - unsigned poff = pos & (PAGE_SIZE - 1); - unsigned plen = min_t(loff_t, PAGE_SIZE - poff, length); + struct iomap_page *iop = iomap_page_create(inode, page); bool is_contig = false; + loff_t orig_pos = pos; + unsigned poff, plen; sector_t sector; if (iomap->type == IOMAP_INLINE) { @@ -161,13 +295,14 @@ iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data, return PAGE_SIZE; } - /* we don't support blocksize < PAGE_SIZE quite yet. */ - WARN_ON_ONCE(pos != page_offset(page)); - WARN_ON_ONCE(plen != PAGE_SIZE); + /* zero post-eof blocks as the page may be mapped */ + iomap_adjust_read_range(inode, iop, &pos, length, &poff, &plen); + if (plen == 0) + goto done; if (iomap->type != IOMAP_MAPPED || pos >= i_size_read(inode)) { zero_user(page, poff, plen); - SetPageUptodate(page); + iomap_set_range_uptodate(page, poff, plen); goto done; } @@ -183,6 +318,14 @@ iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data, is_contig = true; } + /* + * If we start a new segment we need to increase the read count, and we + * need to do so before submitting any previous full bio to make sure + * that we don't prematurely unlock the page. + */ + if (iop) + atomic_inc(&iop->read_count); + if (!ctx->bio || !is_contig || bio_full(ctx->bio)) { gfp_t gfp = mapping_gfp_constraint(page->mapping, GFP_KERNEL); int nr_vecs = (length + PAGE_SIZE - 1) >> PAGE_SHIFT; @@ -203,7 +346,13 @@ iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data, __bio_add_page(ctx->bio, page, plen, poff); done: - return plen; + /* + * Move the caller beyond our range so that it keeps making progress. + * For that we have to include any leading non-uptodate ranges, but + * we can skip trailing ones as they will be handled in the next + * iteration. + */ + return pos - orig_pos + plen; } int @@ -214,8 +363,6 @@ iomap_readpage(struct page *page, const struct iomap_ops *ops) unsigned poff; loff_t ret; - WARN_ON_ONCE(page_has_buffers(page)); - for (poff = 0; poff < PAGE_SIZE; poff += ret) { ret = iomap_apply(inode, page_offset(page) + poff, PAGE_SIZE - poff, 0, ops, &ctx, @@ -341,6 +488,84 @@ done: } EXPORT_SYMBOL_GPL(iomap_readpages); +int +iomap_is_partially_uptodate(struct page *page, unsigned long from, + unsigned long count) +{ + struct iomap_page *iop = to_iomap_page(page); + struct inode *inode = page->mapping->host; + unsigned first = from >> inode->i_blkbits; + unsigned last = (from + count - 1) >> inode->i_blkbits; + unsigned i; + + if (iop) { + for (i = first; i <= last; i++) + if (!test_bit(i, iop->uptodate)) + return 0; + return 1; + } + + return 0; +} +EXPORT_SYMBOL_GPL(iomap_is_partially_uptodate); + +int +iomap_releasepage(struct page *page, gfp_t gfp_mask) +{ + /* + * mm accommodates an old ext3 case where clean pages might not have had + * the dirty bit cleared. Thus, it can send actual dirty pages to + * ->releasepage() via shrink_active_list(), skip those here. + */ + if (PageDirty(page) || PageWriteback(page)) + return 0; + iomap_page_release(page); + return 1; +} +EXPORT_SYMBOL_GPL(iomap_releasepage); + +void +iomap_invalidatepage(struct page *page, unsigned int offset, unsigned int len) +{ + /* + * If we are invalidating the entire page, clear the dirty state from it + * and release it to avoid unnecessary buildup of the LRU. + */ + if (offset == 0 && len == PAGE_SIZE) { + WARN_ON_ONCE(PageWriteback(page)); + cancel_dirty_page(page); + iomap_page_release(page); + } +} +EXPORT_SYMBOL_GPL(iomap_invalidatepage); + +#ifdef CONFIG_MIGRATION +int +iomap_migrate_page(struct address_space *mapping, struct page *newpage, + struct page *page, enum migrate_mode mode) +{ + int ret; + + ret = migrate_page_move_mapping(mapping, newpage, page, NULL, mode, 0); + if (ret != MIGRATEPAGE_SUCCESS) + return ret; + + if (page_has_private(page)) { + ClearPagePrivate(page); + set_page_private(newpage, page_private(page)); + set_page_private(page, 0); + SetPagePrivate(newpage); + } + + if (mode != MIGRATE_SYNC_NO_COPY) + migrate_page_copy(newpage, page); + else + migrate_page_states(newpage, page); + return MIGRATEPAGE_SUCCESS; +} +EXPORT_SYMBOL_GPL(iomap_migrate_page); +#endif /* CONFIG_MIGRATION */ + static void iomap_write_failed(struct inode *inode, loff_t pos, unsigned len) { @@ -364,6 +589,7 @@ iomap_read_page_sync(struct inode *inode, loff_t block_start, struct page *page, if (iomap->type != IOMAP_MAPPED || block_start >= i_size_read(inode)) { zero_user_segments(page, poff, from, to, poff + plen); + iomap_set_range_uptodate(page, poff, plen); return 0; } @@ -379,21 +605,33 @@ static int __iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, struct page *page, struct iomap *iomap) { + struct iomap_page *iop = iomap_page_create(inode, page); loff_t block_size = i_blocksize(inode); loff_t block_start = pos & ~(block_size - 1); loff_t block_end = (pos + len + block_size - 1) & ~(block_size - 1); - unsigned poff = block_start & (PAGE_SIZE - 1); - unsigned plen = min_t(loff_t, PAGE_SIZE - poff, block_end - block_start); - unsigned from = pos & (PAGE_SIZE - 1), to = from + len; - - WARN_ON_ONCE(i_blocksize(inode) < PAGE_SIZE); + unsigned from = pos & (PAGE_SIZE - 1), to = from + len, poff, plen; + int status = 0; if (PageUptodate(page)) return 0; - if (from <= poff && to >= poff + plen) - return 0; - return iomap_read_page_sync(inode, block_start, page, - poff, plen, from, to, iomap); + + do { + iomap_adjust_read_range(inode, iop, &block_start, + block_end - block_start, &poff, &plen); + if (plen == 0) + break; + + if ((from > poff && from < poff + plen) || + (to > poff && to < poff + plen)) { + status = iomap_read_page_sync(inode, block_start, page, + poff, plen, from, to, iomap); + if (status) + break; + } + + } while ((block_start += plen) < block_end); + + return status; } static int @@ -476,7 +714,7 @@ __iomap_write_end(struct inode *inode, loff_t pos, unsigned len, if (unlikely(copied < len && !PageUptodate(page))) { copied = 0; } else { - SetPageUptodate(page); + iomap_set_range_uptodate(page, pos & (PAGE_SIZE - 1), len); iomap_set_page_dirty(page); } return __generic_write_end(inode, pos, copied, page); @@ -812,7 +1050,7 @@ iomap_page_mkwrite_actor(struct inode *inode, loff_t pos, loff_t length, block_commit_write(page, 0, length); } else { WARN_ON_ONCE(!PageUptodate(page)); - WARN_ON_ONCE(i_blocksize(inode) < PAGE_SIZE); + iomap_page_create(inode, page); } return length; diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 5eb9ca8d7ce5..3555d54bf79a 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -2,6 +2,9 @@ #ifndef LINUX_IOMAP_H #define LINUX_IOMAP_H 1 +#include +#include +#include #include struct address_space; @@ -98,12 +101,40 @@ struct iomap_ops { ssize_t written, unsigned flags, struct iomap *iomap); }; +/* + * Structure allocate for each page when block size < PAGE_SIZE to track + * sub-page uptodate status and I/O completions. + */ +struct iomap_page { + atomic_t read_count; + atomic_t write_count; + DECLARE_BITMAP(uptodate, PAGE_SIZE / 512); +}; + +static inline struct iomap_page *to_iomap_page(struct page *page) +{ + if (page_has_private(page)) + return (struct iomap_page *)page_private(page); + return NULL; +} + ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from, const struct iomap_ops *ops); int iomap_readpage(struct page *page, const struct iomap_ops *ops); int iomap_readpages(struct address_space *mapping, struct list_head *pages, unsigned nr_pages, const struct iomap_ops *ops); int iomap_set_page_dirty(struct page *page); +int iomap_is_partially_uptodate(struct page *page, unsigned long from, + unsigned long count); +int iomap_releasepage(struct page *page, gfp_t gfp_mask); +void iomap_invalidatepage(struct page *page, unsigned int offset, + unsigned int len); +#ifdef CONFIG_MIGRATION +int iomap_migrate_page(struct address_space *mapping, struct page *newpage, + struct page *page, enum migrate_mode mode); +#else +#define iomap_migrate_page NULL +#endif int iomap_file_dirty(struct inode *inode, loff_t pos, loff_t len, const struct iomap_ops *ops); int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, -- cgit v1.2.3 From 4929c9428a171145f82f81aae0c3c25ef7d82837 Mon Sep 17 00:00:00 2001 From: Deepti Raghavan Date: Mon, 9 Jul 2018 17:53:39 +0000 Subject: tcp: expose both send and receive intervals for rate sample Congestion control algorithms, which access the rate sample through the tcp_cong_control function, only have access to the maximum of the send and receive interval, for cases where the acknowledgment rate may be inaccurate due to ACK compression or decimation. Algorithms may want to use send rates and receive rates as separate signals. Signed-off-by: Deepti Raghavan Acked-by: Neal Cardwell Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 2 ++ net/ipv4/tcp_rate.c | 4 ++++ 2 files changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index cce37694776e..f6cb20e6e524 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -954,6 +954,8 @@ struct rate_sample { u32 prior_delivered; /* tp->delivered at "prior_mstamp" */ s32 delivered; /* number of packets delivered over interval */ long interval_us; /* time for tp->delivered to incr "delivered" */ + u32 snd_interval_us; /* snd interval for delivered packets */ + u32 rcv_interval_us; /* rcv interval for delivered packets */ long rtt_us; /* RTT of last (S)ACKed packet (or -1) */ int losses; /* number of packets marked lost upon ACK */ u32 acked_sacked; /* number of packets newly (S)ACKed upon ACK */ diff --git a/net/ipv4/tcp_rate.c b/net/ipv4/tcp_rate.c index c61240e43923..4dff40dad4dc 100644 --- a/net/ipv4/tcp_rate.c +++ b/net/ipv4/tcp_rate.c @@ -146,6 +146,10 @@ void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost, rs->prior_mstamp); /* ack phase */ rs->interval_us = max(snd_us, ack_us); + /* Record both segment send and ack receive intervals */ + rs->snd_interval_us = snd_us; + rs->rcv_interval_us = ack_us; + /* Normally we expect interval_us >= min-rtt. * Note that rate may still be over-estimated when a spuriously * retransmistted skb was first (s)acked because "interval_us" -- cgit v1.2.3 From 3443b00e07eed5798605ba6524de37e1d3f1a4bf Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Tue, 10 Jul 2018 10:02:57 +0300 Subject: team: Publish team_port_get_rcu() A follow-up patch adds a new entry point, team_port_dev_txable(). Making it an ordinary exported function would mean that any module that may need the service in one of the supported configurations also unconditionally needs to pull in the team module, whether or not the user actually intends to create team interfaces. To prevent that, team_port_dev_txable() is defined in if_team.h, and therefore all dependencies of that function also need to be publicly-visible. Therefore move team_port_get_rcu() from team.c to if_team.h. Signed-off-by: Petr Machata Reviewed-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/team/team.c | 5 ----- include/linux/if_team.h | 5 +++++ 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 3a95eaae0c98..6a047d30e8c6 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -41,11 +41,6 @@ #define team_port_exists(dev) (dev->priv_flags & IFF_TEAM_PORT) -static struct team_port *team_port_get_rcu(const struct net_device *dev) -{ - return rcu_dereference(dev->rx_handler_data); -} - static struct team_port *team_port_get_rtnl(const struct net_device *dev) { struct team_port *port = rtnl_dereference(dev->rx_handler_data); diff --git a/include/linux/if_team.h b/include/linux/if_team.h index d95cae09dea0..0d07c6655cce 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -74,6 +74,11 @@ struct team_port { long mode_priv[0]; }; +static inline struct team_port *team_port_get_rcu(const struct net_device *dev) +{ + return rcu_dereference(dev->rx_handler_data); +} + static inline bool team_port_enabled(struct team_port *port) { return port->index != -1; -- cgit v1.2.3 From eeed992b776c54af6108187c87ac60d028e69d37 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Tue, 10 Jul 2018 10:02:58 +0300 Subject: net: Add lag.h, net_lag_port_dev_txable() LAG devices (team or bond) recognize for each one of their slave devices whether LAG traffic is going to be sent through that device. Bond calls such devices "active", team calls them "txable". When this state changes, a NETDEV_CHANGELOWERSTATE notification is distributed, together with a netdev_notifier_changelowerstate_info structure that for LAG devices includes a tx_enabled flag that refers to the new state. The notification thus makes it possible to react to the changes in txability in drivers. However there's no way to query txability from the outside on demand. That is problematic namely for mlxsw, which when resolving ERSPAN packet path, may encounter a LAG device, and needs to determine which of the slaves it should choose. To that end, introduce a new function, net_lag_port_dev_txable(), which determines whether a given slave device is "active" or "txable" (depending on the flavor of the LAG device). That function then dispatches to per-LAG-flavor helpers, bond_is_active_slave_dev() resp. team_port_dev_txable(). Because there currently is no good place where net_lag_port_dev_txable() should be added, introduce a new header file, lag.h, which should from now on hold any logic common to both team and bond. (But keep netif_is_lag_master() together with the rest of netif_is_*_master() functions). Signed-off-by: Petr Machata Reviewed-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/linux/if_team.h | 13 +++++++++++++ include/net/bonding.h | 13 +++++++++++++ include/net/lag.h | 17 +++++++++++++++++ 3 files changed, 43 insertions(+) create mode 100644 include/net/lag.h (limited to 'include') diff --git a/include/linux/if_team.h b/include/linux/if_team.h index 0d07c6655cce..ac42da56f7a2 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -89,6 +89,19 @@ static inline bool team_port_txable(struct team_port *port) return port->linkup && team_port_enabled(port); } +static inline bool team_port_dev_txable(const struct net_device *port_dev) +{ + struct team_port *port; + bool txable; + + rcu_read_lock(); + port = team_port_get_rcu(port_dev); + txable = port ? team_port_txable(port) : false; + rcu_read_unlock(); + + return txable; +} + #ifdef CONFIG_NET_POLL_CONTROLLER static inline void team_netpoll_send_skb(struct team_port *port, struct sk_buff *skb) diff --git a/include/net/bonding.h b/include/net/bonding.h index 808f1d167349..a2d058170ea3 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -411,6 +411,19 @@ static inline bool bond_slave_can_tx(struct slave *slave) bond_is_active_slave(slave); } +static inline bool bond_is_active_slave_dev(const struct net_device *slave_dev) +{ + struct slave *slave; + bool active; + + rcu_read_lock(); + slave = bond_slave_get_rcu(slave_dev); + active = bond_is_active_slave(slave); + rcu_read_unlock(); + + return active; +} + static inline void bond_hw_addr_copy(u8 *dst, const u8 *src, unsigned int len) { if (len == ETH_ALEN) { diff --git a/include/net/lag.h b/include/net/lag.h new file mode 100644 index 000000000000..95b880e6fdde --- /dev/null +++ b/include/net/lag.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_IF_LAG_H +#define _LINUX_IF_LAG_H + +#include +#include +#include + +static inline bool net_lag_port_dev_txable(const struct net_device *port_dev) +{ + if (netif_is_team_port(port_dev)) + return team_port_dev_txable(port_dev); + else + return bond_is_active_slave_dev(port_dev); +} + +#endif /* _LINUX_IF_LAG_H */ -- cgit v1.2.3 From bf1c77b4644f46d2986b7ca5e43e012f0fc8984b Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 11 Jul 2018 14:56:50 +0100 Subject: kernel: add ksys_personality() Using this helper allows us to avoid the in-kernel call to the sys_personality() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_personality(). Since ksys_personality is trivial, it is implemented directly in , as we do for ksys_close() and friends. This helper is necessary to enable conversion of arm64's syscall handling to use pt_regs wrappers. Signed-off-by: Mark Rutland Reviewed-by: Dominik Brodowski Cc: Al Viro Cc: Christoph Hellwig Cc: Dave Martin Signed-off-by: Will Deacon --- include/linux/syscalls.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index a368a68cb667..abfe12d8a9c5 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -80,6 +80,7 @@ union bpf_attr; #include #include #include +#include #include #ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER @@ -1281,4 +1282,14 @@ static inline long ksys_truncate(const char __user *pathname, loff_t length) return do_sys_truncate(pathname, length); } +static inline unsigned int ksys_personality(unsigned int personality) +{ + unsigned int old = current->personality; + + if (personality != 0xffffffff) + set_personality(personality); + + return old; +} + #endif -- cgit v1.2.3 From 9b54bf9d6a5b30e2cc22b18793e9a4158c5b4882 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 11 Jul 2018 14:56:51 +0100 Subject: kernel: add kcompat_sys_{f,}statfs64() Using this helper allows us to avoid the in-kernel calls to the compat_sys_{f,}statfs64() sycalls, as are necessary for parameter mangling in arm64's compat handling. Following the example of ksys_* functions, kcompat_sys_* functions are intended to be a drop-in replacement for their compat_sys_* counterparts, with the same calling convention. This is necessary to enable conversion of arm64's syscall handling to use pt_regs wrappers. Signed-off-by: Mark Rutland Reviewed-by: Dominik Brodowski Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Signed-off-by: Will Deacon --- fs/statfs.c | 14 ++++++++++++-- include/linux/compat.h | 11 +++++++++++ 2 files changed, 23 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/fs/statfs.c b/fs/statfs.c index 5b2a24f0f263..f0216629621d 100644 --- a/fs/statfs.c +++ b/fs/statfs.c @@ -335,7 +335,7 @@ static int put_compat_statfs64(struct compat_statfs64 __user *ubuf, struct kstat return 0; } -COMPAT_SYSCALL_DEFINE3(statfs64, const char __user *, pathname, compat_size_t, sz, struct compat_statfs64 __user *, buf) +int kcompat_sys_statfs64(const char __user * pathname, compat_size_t sz, struct compat_statfs64 __user * buf) { struct kstatfs tmp; int error; @@ -349,7 +349,12 @@ COMPAT_SYSCALL_DEFINE3(statfs64, const char __user *, pathname, compat_size_t, s return error; } -COMPAT_SYSCALL_DEFINE3(fstatfs64, unsigned int, fd, compat_size_t, sz, struct compat_statfs64 __user *, buf) +COMPAT_SYSCALL_DEFINE3(statfs64, const char __user *, pathname, compat_size_t, sz, struct compat_statfs64 __user *, buf) +{ + return kcompat_sys_statfs64(pathname, sz, buf); +} + +int kcompat_sys_fstatfs64(unsigned int fd, compat_size_t sz, struct compat_statfs64 __user * buf) { struct kstatfs tmp; int error; @@ -363,6 +368,11 @@ COMPAT_SYSCALL_DEFINE3(fstatfs64, unsigned int, fd, compat_size_t, sz, struct co return error; } +COMPAT_SYSCALL_DEFINE3(fstatfs64, unsigned int, fd, compat_size_t, sz, struct compat_statfs64 __user *, buf) +{ + return kcompat_sys_fstatfs64(fd, sz, buf); +} + /* * This is a copy of sys_ustat, just dealing with a structure layout. * Given how simple this syscall is that apporach is more maintainable diff --git a/include/linux/compat.h b/include/linux/compat.h index c68acc47da57..43f4ed44c5d5 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -1028,6 +1028,17 @@ static inline struct compat_timeval ns_to_compat_timeval(s64 nsec) return ctv; } +/* + * Kernel code should not call compat syscalls (i.e., compat_sys_xyzyyz()) + * directly. Instead, use one of the functions which work equivalently, such + * as the kcompat_sys_xyzyyz() functions prototyped below. + */ + +int kcompat_sys_statfs64(const char __user * pathname, compat_size_t sz, + struct compat_statfs64 __user * buf); +int kcompat_sys_fstatfs64(unsigned int fd, compat_size_t sz, + struct compat_statfs64 __user * buf); + #else /* !CONFIG_COMPAT */ #define is_compat_task() (0) -- cgit v1.2.3 From c9c554f21490bbc96cc554f80024d27d09670480 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 11 Jul 2018 14:19:04 -0400 Subject: alloc_file(): switch to passing O_... flags instead of FMODE_... mode ... so that it could set both ->f_flags and ->f_mode, without callers having to set ->f_flags manually. Signed-off-by: Al Viro --- drivers/misc/cxl/api.c | 3 +-- drivers/scsi/cxlflash/ocxl_hw.c | 3 +-- fs/aio.c | 8 ++------ fs/anon_inodes.c | 3 +-- fs/file_table.c | 17 +++++++++-------- fs/hugetlbfs/inode.c | 3 +-- fs/pipe.c | 8 ++++---- include/linux/file.h | 2 +- ipc/shm.c | 8 ++++---- mm/memfd.c | 2 +- mm/shmem.c | 3 +-- net/socket.c | 3 +-- 12 files changed, 27 insertions(+), 36 deletions(-) (limited to 'include') diff --git a/drivers/misc/cxl/api.c b/drivers/misc/cxl/api.c index 6b16946f9b05..0b5cb6cf91a0 100644 --- a/drivers/misc/cxl/api.c +++ b/drivers/misc/cxl/api.c @@ -102,12 +102,11 @@ static struct file *cxl_getfile(const char *name, path.mnt = mntget(cxl_vfs_mount); d_instantiate(path.dentry, inode); - file = alloc_file(&path, OPEN_FMODE(flags), fops); + file = alloc_file(&path, flags & (O_ACCMODE | O_NONBLOCK), fops); if (IS_ERR(file)) { path_put(&path); goto err_fs; } - file->f_flags = flags & (O_ACCMODE | O_NONBLOCK); file->private_data = priv; return file; diff --git a/drivers/scsi/cxlflash/ocxl_hw.c b/drivers/scsi/cxlflash/ocxl_hw.c index 497a68389461..99bb393a8a34 100644 --- a/drivers/scsi/cxlflash/ocxl_hw.c +++ b/drivers/scsi/cxlflash/ocxl_hw.c @@ -129,7 +129,7 @@ static struct file *ocxlflash_getfile(struct device *dev, const char *name, path.mnt = mntget(ocxlflash_vfs_mount); d_instantiate(path.dentry, inode); - file = alloc_file(&path, OPEN_FMODE(flags), fops); + file = alloc_file(&path, flags & (O_ACCMODE | O_NONBLOCK), fops); if (IS_ERR(file)) { rc = PTR_ERR(file); dev_err(dev, "%s: alloc_file failed rc=%d\n", @@ -138,7 +138,6 @@ static struct file *ocxlflash_getfile(struct device *dev, const char *name, goto err3; } - file->f_flags = flags & (O_ACCMODE | O_NONBLOCK); file->private_data = priv; out: return file; diff --git a/fs/aio.c b/fs/aio.c index e1d20124ec0e..9eea53887d6c 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -234,13 +234,9 @@ static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages) path.mnt = mntget(aio_mnt); d_instantiate(path.dentry, inode); - file = alloc_file(&path, FMODE_READ | FMODE_WRITE, &aio_ring_fops); - if (IS_ERR(file)) { + file = alloc_file(&path, O_RDWR, &aio_ring_fops); + if (IS_ERR(file)) path_put(&path); - return file; - } - - file->f_flags = O_RDWR; return file; } diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c index 3168ee4e77f4..6b235ab1df6c 100644 --- a/fs/anon_inodes.c +++ b/fs/anon_inodes.c @@ -102,12 +102,11 @@ struct file *anon_inode_getfile(const char *name, d_instantiate(path.dentry, anon_inode_inode); - file = alloc_file(&path, OPEN_FMODE(flags), fops); + file = alloc_file(&path, flags & (O_ACCMODE | O_NONBLOCK), fops); if (IS_ERR(file)) goto err_dput; file->f_mapping = anon_inode_inode->i_mapping; - file->f_flags = flags & (O_ACCMODE | O_NONBLOCK); file->private_data = priv; return file; diff --git a/fs/file_table.c b/fs/file_table.c index eee7cf629e52..086c3f5ec31a 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -153,10 +153,10 @@ over: * alloc_file - allocate and initialize a 'struct file' * * @path: the (dentry, vfsmount) pair for the new file - * @mode: the mode with which the new file will be opened + * @flags: O_... flags with which the new file will be opened * @fop: the 'struct file_operations' for the new file */ -struct file *alloc_file(const struct path *path, fmode_t mode, +struct file *alloc_file(const struct path *path, int flags, const struct file_operations *fop) { struct file *file; @@ -165,19 +165,20 @@ struct file *alloc_file(const struct path *path, fmode_t mode, if (IS_ERR(file)) return file; + file->f_mode = OPEN_FMODE(flags); + file->f_flags = flags; file->f_path = *path; file->f_inode = path->dentry->d_inode; file->f_mapping = path->dentry->d_inode->i_mapping; file->f_wb_err = filemap_sample_wb_err(file->f_mapping); - if ((mode & FMODE_READ) && + if ((file->f_mode & FMODE_READ) && likely(fop->read || fop->read_iter)) - mode |= FMODE_CAN_READ; - if ((mode & FMODE_WRITE) && + file->f_mode |= FMODE_CAN_READ; + if ((file->f_mode & FMODE_WRITE) && likely(fop->write || fop->write_iter)) - mode |= FMODE_CAN_WRITE; - file->f_mode = mode; + file->f_mode |= FMODE_CAN_WRITE; file->f_op = fop; - if ((mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) + if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) i_readcount_inc(path->dentry->d_inode); return file; } diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index d508c7844681..71aed47422e2 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -1375,8 +1375,7 @@ struct file *hugetlb_file_setup(const char *name, size_t size, inode->i_size = size; clear_nlink(inode); - file = alloc_file(&path, FMODE_WRITE | FMODE_READ, - &hugetlbfs_file_operations); + file = alloc_file(&path, O_RDWR, &hugetlbfs_file_operations); if (IS_ERR(file)) goto out_dentry; /* inode is already attached */ diff --git a/fs/pipe.c b/fs/pipe.c index 9405e455f5b1..1909422e5a78 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -760,16 +760,17 @@ int create_pipe_files(struct file **res, int flags) d_instantiate(path.dentry, inode); - f = alloc_file(&path, FMODE_WRITE, &pipefifo_fops); + f = alloc_file(&path, O_WRONLY | (flags & (O_NONBLOCK | O_DIRECT)), + &pipefifo_fops); if (IS_ERR(f)) { err = PTR_ERR(f); goto err_dentry; } - f->f_flags = O_WRONLY | (flags & (O_NONBLOCK | O_DIRECT)); f->private_data = inode->i_pipe; - res[0] = alloc_file(&path, FMODE_READ, &pipefifo_fops); + res[0] = alloc_file(&path, O_RDONLY | (flags & O_NONBLOCK), + &pipefifo_fops); if (IS_ERR(res[0])) { put_pipe_info(inode, inode->i_pipe); fput(f); @@ -778,7 +779,6 @@ int create_pipe_files(struct file **res, int flags) path_get(&path); res[0]->private_data = inode->i_pipe; - res[0]->f_flags = O_RDONLY | (flags & O_NONBLOCK); res[1] = f; return 0; diff --git a/include/linux/file.h b/include/linux/file.h index 279720db984a..6d34a1262b31 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -18,7 +18,7 @@ struct file_operations; struct vfsmount; struct dentry; struct path; -extern struct file *alloc_file(const struct path *, fmode_t mode, +extern struct file *alloc_file(const struct path *, int flags, const struct file_operations *fop); static inline void fput_light(struct file *file, int fput_needed) diff --git a/ipc/shm.c b/ipc/shm.c index 051a3e1fb8df..c702abd578a7 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -1362,7 +1362,7 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg, struct ipc_namespace *ns; struct shm_file_data *sfd; struct path path; - fmode_t f_mode; + int f_flags; unsigned long populate = 0; err = -EINVAL; @@ -1395,11 +1395,11 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg, if (shmflg & SHM_RDONLY) { prot = PROT_READ; acc_mode = S_IRUGO; - f_mode = FMODE_READ; + f_flags = O_RDONLY; } else { prot = PROT_READ | PROT_WRITE; acc_mode = S_IRUGO | S_IWUGO; - f_mode = FMODE_READ | FMODE_WRITE; + f_flags = O_RDWR; } if (shmflg & SHM_EXEC) { prot |= PROT_EXEC; @@ -1449,7 +1449,7 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg, goto out_nattch; } - file = alloc_file(&path, f_mode, + file = alloc_file(&path, f_flags, is_file_hugepages(shp->shm_file) ? &shm_file_operations_huge : &shm_file_operations); diff --git a/mm/memfd.c b/mm/memfd.c index 27069518e3c5..2bb5e257080e 100644 --- a/mm/memfd.c +++ b/mm/memfd.c @@ -326,7 +326,7 @@ SYSCALL_DEFINE2(memfd_create, goto err_fd; } file->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE; - file->f_flags |= O_RDWR | O_LARGEFILE; + file->f_flags |= O_LARGEFILE; if (flags & MFD_ALLOW_SEALING) { file_seals = memfd_file_seals_ptr(file); diff --git a/mm/shmem.c b/mm/shmem.c index 2cab84403055..84844e52bf24 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -3942,8 +3942,7 @@ static struct file *__shmem_file_setup(struct vfsmount *mnt, const char *name, l if (IS_ERR(res)) goto put_path; - res = alloc_file(&path, FMODE_WRITE | FMODE_READ, - &shmem_file_operations); + res = alloc_file(&path, O_RDWR, &shmem_file_operations); if (IS_ERR(res)) goto put_path; diff --git a/net/socket.c b/net/socket.c index 8a109012608a..2cdbe8f71b7f 100644 --- a/net/socket.c +++ b/net/socket.c @@ -411,7 +411,7 @@ struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname) d_instantiate(path.dentry, SOCK_INODE(sock)); - file = alloc_file(&path, FMODE_READ | FMODE_WRITE, + file = alloc_file(&path, O_RDWR | (flags & O_NONBLOCK), &socket_file_ops); if (IS_ERR(file)) { /* drop dentry, keep inode for a bit */ @@ -423,7 +423,6 @@ struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname) } sock->file = file; - file->f_flags = O_RDWR | (flags & O_NONBLOCK); file->private_data = sock; return file; } -- cgit v1.2.3 From e3f20ae21079ecac282df65d83865c5771f4bca0 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 10 Jul 2018 13:25:29 -0400 Subject: security_file_open(): lose cred argument Acked-by: Linus Torvalds Signed-off-by: Al Viro --- fs/open.c | 2 +- include/linux/security.h | 5 ++--- security/security.c | 4 ++-- 3 files changed, 5 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/fs/open.c b/fs/open.c index 0a9f00b7f3d5..4c65edefa487 100644 --- a/fs/open.c +++ b/fs/open.c @@ -776,7 +776,7 @@ static int do_dentry_open(struct file *f, goto cleanup_all; } - error = security_file_open(f, f->f_cred); + error = security_file_open(f); if (error) goto cleanup_all; diff --git a/include/linux/security.h b/include/linux/security.h index 63030c85ee19..88d30fc975e7 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -309,7 +309,7 @@ void security_file_set_fowner(struct file *file); int security_file_send_sigiotask(struct task_struct *tsk, struct fown_struct *fown, int sig); int security_file_receive(struct file *file); -int security_file_open(struct file *file, const struct cred *cred); +int security_file_open(struct file *file); int security_task_alloc(struct task_struct *task, unsigned long clone_flags); void security_task_free(struct task_struct *task); int security_cred_alloc_blank(struct cred *cred, gfp_t gfp); @@ -858,8 +858,7 @@ static inline int security_file_receive(struct file *file) return 0; } -static inline int security_file_open(struct file *file, - const struct cred *cred) +static inline int security_file_open(struct file *file) { return 0; } diff --git a/security/security.c b/security/security.c index 68f46d849abe..235b35f58a65 100644 --- a/security/security.c +++ b/security/security.c @@ -970,11 +970,11 @@ int security_file_receive(struct file *file) return call_int_hook(file_receive, 0, file); } -int security_file_open(struct file *file, const struct cred *cred) +int security_file_open(struct file *file) { int ret; - ret = call_int_hook(file_open, 0, file, cred); + ret = call_int_hook(file_open, 0, file, file->f_cred); if (ret) return ret; -- cgit v1.2.3 From 9481769208b5e39b871ae4e89f5328c776ec38dc Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 10 Jul 2018 14:13:18 -0400 Subject: ->file_open(): lose cred argument Acked-by: Linus Torvalds Signed-off-by: Al Viro --- include/linux/lsm_hooks.h | 2 +- security/apparmor/lsm.c | 4 ++-- security/security.c | 2 +- security/selinux/hooks.c | 4 ++-- security/smack/smack_lsm.c | 6 +++--- security/tomoyo/tomoyo.c | 2 +- 6 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 8f1131c8dd54..a8ee106b865d 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -1569,7 +1569,7 @@ union security_list_options { int (*file_send_sigiotask)(struct task_struct *tsk, struct fown_struct *fown, int sig); int (*file_receive)(struct file *file); - int (*file_open)(struct file *file, const struct cred *cred); + int (*file_open)(struct file *file); int (*task_alloc)(struct task_struct *task, unsigned long clone_flags); void (*task_free)(struct task_struct *task); diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index 74f17376202b..8b8b70620bbe 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -395,7 +395,7 @@ static int apparmor_inode_getattr(const struct path *path) return common_perm_cond(OP_GETATTR, path, AA_MAY_GETATTR); } -static int apparmor_file_open(struct file *file, const struct cred *cred) +static int apparmor_file_open(struct file *file) { struct aa_file_ctx *fctx = file_ctx(file); struct aa_label *label; @@ -414,7 +414,7 @@ static int apparmor_file_open(struct file *file, const struct cred *cred) return 0; } - label = aa_get_newest_cred_label(cred); + label = aa_get_newest_cred_label(file->f_cred); if (!unconfined(label)) { struct inode *inode = file_inode(file); struct path_cond cond = { inode->i_uid, inode->i_mode }; diff --git a/security/security.c b/security/security.c index 235b35f58a65..5dce67070cdf 100644 --- a/security/security.c +++ b/security/security.c @@ -974,7 +974,7 @@ int security_file_open(struct file *file) { int ret; - ret = call_int_hook(file_open, 0, file, file->f_cred); + ret = call_int_hook(file_open, 0, file); if (ret) return ret; diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 2b5ee5fbd652..18006be15713 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -3862,7 +3862,7 @@ static int selinux_file_receive(struct file *file) return file_has_perm(cred, file, file_to_av(file)); } -static int selinux_file_open(struct file *file, const struct cred *cred) +static int selinux_file_open(struct file *file) { struct file_security_struct *fsec; struct inode_security_struct *isec; @@ -3886,7 +3886,7 @@ static int selinux_file_open(struct file *file, const struct cred *cred) * new inode label or new policy. * This check is not redundant - do not remove. */ - return file_path_has_perm(cred, file, open_file_to_av(file)); + return file_path_has_perm(file->f_cred, file, open_file_to_av(file)); } /* task security operations */ diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index 7ad226018f51..e7b6c012431d 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -1927,9 +1927,9 @@ static int smack_file_receive(struct file *file) * * Returns 0 */ -static int smack_file_open(struct file *file, const struct cred *cred) +static int smack_file_open(struct file *file) { - struct task_smack *tsp = cred->security; + struct task_smack *tsp = file->f_cred->security; struct inode *inode = file_inode(file); struct smk_audit_info ad; int rc; @@ -1937,7 +1937,7 @@ static int smack_file_open(struct file *file, const struct cred *cred) smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_PATH); smk_ad_setfield_u_fs_path(&ad, file->f_path); rc = smk_tskacc(tsp, smk_of_inode(inode), MAY_READ, &ad); - rc = smk_bu_credfile(cred, file, MAY_READ, rc); + rc = smk_bu_credfile(file->f_cred, file, MAY_READ, rc); return rc; } diff --git a/security/tomoyo/tomoyo.c b/security/tomoyo/tomoyo.c index 213b8c593668..9f932e2d6852 100644 --- a/security/tomoyo/tomoyo.c +++ b/security/tomoyo/tomoyo.c @@ -320,7 +320,7 @@ static int tomoyo_file_fcntl(struct file *file, unsigned int cmd, * * Returns 0 on success, negative value otherwise. */ -static int tomoyo_file_open(struct file *f, const struct cred *cred) +static int tomoyo_file_open(struct file *f) { int flags = f->f_flags; /* Don't check read permission here if called from do_execve(). */ -- cgit v1.2.3 From f5d11409e61dadf1f9af91b22bbedc28a60a2e2c Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 9 Jul 2018 02:35:08 -0400 Subject: introduce FMODE_OPENED basically, "is that instance set up enough for regular fput(), or do we want put_filp() for that one". NOTE: the only alloc_file() caller that could be followed by put_filp() is in arch/ia64/kernel/perfmon.c, which is (Kconfig-level) broken. Acked-by: Linus Torvalds Signed-off-by: Al Viro --- fs/file_table.c | 1 + fs/open.c | 3 ++- include/linux/fs.h | 2 ++ 3 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/fs/file_table.c b/fs/file_table.c index 705f486f7007..d664d10acfeb 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -176,6 +176,7 @@ struct file *alloc_file(const struct path *path, int flags, if ((file->f_mode & FMODE_WRITE) && likely(fop->write || fop->write_iter)) file->f_mode |= FMODE_CAN_WRITE; + file->f_mode |= FMODE_OPENED; file->f_op = fop; if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) i_readcount_inc(path->dentry->d_inode); diff --git a/fs/open.c b/fs/open.c index 4c65edefa487..f3c6cb6a57b9 100644 --- a/fs/open.c +++ b/fs/open.c @@ -749,7 +749,7 @@ static int do_dentry_open(struct file *f, f->f_wb_err = filemap_sample_wb_err(f->f_mapping); if (unlikely(f->f_flags & O_PATH)) { - f->f_mode = FMODE_PATH; + f->f_mode = FMODE_PATH | FMODE_OPENED; f->f_op = &empty_fops; return 0; } @@ -793,6 +793,7 @@ static int do_dentry_open(struct file *f, if (error) goto cleanup_all; } + f->f_mode |= FMODE_OPENED; if ((f->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) i_readcount_inc(inode); if ((f->f_mode & FMODE_READ) && diff --git a/include/linux/fs.h b/include/linux/fs.h index c4ca4c9c1130..05f34726e29c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -148,6 +148,8 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* Has write method(s) */ #define FMODE_CAN_WRITE ((__force fmode_t)0x40000) +#define FMODE_OPENED ((__force fmode_t)0x80000) + /* File was opened by fanotify and shouldn't generate fanotify events */ #define FMODE_NONOTIFY ((__force fmode_t)0x4000000) -- cgit v1.2.3 From 4d27f3266f14e4d1d13125ce32cb49a40f3122c3 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 9 Jul 2018 11:14:39 -0400 Subject: fold put_filp() into fput() Just check FMODE_OPENED in __fput() and be done with that... Acked-by: Linus Torvalds Signed-off-by: Al Viro --- fs/file_table.c | 15 +++++---------- fs/namei.c | 4 ++-- fs/open.c | 11 +++-------- include/linux/file.h | 1 - 4 files changed, 10 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/fs/file_table.c b/fs/file_table.c index d664d10acfeb..9b70ed2bbc4e 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -192,6 +192,9 @@ static void __fput(struct file *file) struct vfsmount *mnt = file->f_path.mnt; struct inode *inode = file->f_inode; + if (unlikely(!(file->f_mode & FMODE_OPENED))) + goto out; + might_sleep(); fsnotify_close(file); @@ -221,12 +224,10 @@ static void __fput(struct file *file) put_write_access(inode); __mnt_drop_write(mnt); } - file->f_path.dentry = NULL; - file->f_path.mnt = NULL; - file->f_inode = NULL; - file_free(file); dput(dentry); mntput(mnt); +out: + file_free(file); } static LLIST_HEAD(delayed_fput_list); @@ -301,12 +302,6 @@ void __fput_sync(struct file *file) EXPORT_SYMBOL(fput); -void put_filp(struct file *file) -{ - if (atomic_long_dec_and_test(&file->f_count)) - file_free(file); -} - void __init files_init(void) { filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0, diff --git a/fs/namei.c b/fs/namei.c index 3cf02804d5ff..503c4b968415 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3531,7 +3531,7 @@ static struct file *path_openat(struct nameidata *nd, s = path_init(nd, flags); if (IS_ERR(s)) { - put_filp(file); + fput(file); return ERR_CAST(s); } while (!(error = link_path_walk(s, nd)) && @@ -3547,7 +3547,7 @@ static struct file *path_openat(struct nameidata *nd, out2: if (!(opened & FILE_OPENED)) { BUG_ON(!error); - put_filp(file); + fput(file); } if (unlikely(error)) { if (error == -EOPENSTALE) { diff --git a/fs/open.c b/fs/open.c index f3c6cb6a57b9..3d09b823f12b 100644 --- a/fs/open.c +++ b/fs/open.c @@ -921,15 +921,10 @@ struct file *dentry_open(const struct path *path, int flags, f = alloc_empty_file(flags, cred); if (!IS_ERR(f)) { error = vfs_open(path, f); - if (!error) { - /* from now on we need fput() to dispose of f */ + if (!error) error = open_check_o_direct(f); - if (error) { - fput(f); - f = ERR_PTR(error); - } - } else { - put_filp(f); + if (error) { + fput(f); f = ERR_PTR(error); } } diff --git a/include/linux/file.h b/include/linux/file.h index 6d34a1262b31..aed45d69811e 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -78,7 +78,6 @@ extern int f_dupfd(unsigned int from, struct file *file, unsigned flags); extern int replace_fd(unsigned fd, struct file *file, unsigned flags); extern void set_close_on_exec(unsigned int fd, int flag); extern bool get_close_on_exec(unsigned int fd); -extern void put_filp(struct file *); extern int get_unused_fd_flags(unsigned flags); extern void put_unused_fd(unsigned int fd); -- cgit v1.2.3 From 73a09dd94377e4b186b300bd5461920710c7c3d5 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 8 Jun 2018 13:22:02 -0400 Subject: introduce FMODE_CREATED and switch to it Parallel to FILE_CREATED, goes into ->f_mode instead of *opened. NFS is a bit of a wart here - it doesn't have file at the point where FILE_CREATED used to be set, so we need to propagate it there (for now). IMA is another one (here and everywhere)... Note that this needs do_dentry_open() to leave old bits in ->f_mode alone - we want it to preserve FMODE_CREATED if it had been already set (no other bit can be there). Acked-by: Linus Torvalds Signed-off-by: Al Viro --- fs/9p/vfs_inode.c | 2 +- fs/9p/vfs_inode_dotl.c | 2 +- fs/ceph/file.c | 2 +- fs/cifs/dir.c | 2 +- fs/fuse/dir.c | 2 +- fs/gfs2/inode.c | 2 +- fs/namei.c | 15 ++++++++------- fs/nfs/dir.c | 5 ++++- fs/nfs/nfs4proc.c | 2 +- include/linux/fs.h | 1 + 10 files changed, 20 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 42e102e2e74a..566929792480 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -925,7 +925,7 @@ v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry, if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) v9fs_cache_inode_set_cookie(d_inode(dentry), file); - *opened |= FILE_CREATED; + file->f_mode |= FMODE_CREATED; out: dput(res); return err; diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index 7f6ae21a27b3..ee65db5c7eb0 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -358,7 +358,7 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry, file->private_data = ofid; if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) v9fs_cache_inode_set_cookie(inode, file); - *opened |= FILE_CREATED; + file->f_mode |= FMODE_CREATED; out: v9fs_put_acl(dacl, pacl); dput(res); diff --git a/fs/ceph/file.c b/fs/ceph/file.c index ad0bed99b1d5..38a63fff7903 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -507,7 +507,7 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry, dout("atomic_open finish_open on dn %p\n", dn); if (req->r_op == CEPH_MDS_OP_CREATE && req->r_reply_info.has_create_ino) { ceph_init_inode_acls(d_inode(dentry), &acls); - *opened |= FILE_CREATED; + file->f_mode |= FMODE_CREATED; } err = finish_open(file, dentry, ceph_open, opened); } diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index ddae52bd1993..21d7e393900e 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -539,7 +539,7 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry, } if ((oflags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL)) - *opened |= FILE_CREATED; + file->f_mode |= FMODE_CREATED; rc = finish_open(file, direntry, generic_file_open, opened); if (rc) { diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 56231b31f806..d4bdcf51e6cb 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -508,7 +508,7 @@ static int fuse_atomic_open(struct inode *dir, struct dentry *entry, goto no_open; /* Only creates */ - *opened |= FILE_CREATED; + file->f_mode |= FMODE_CREATED; if (fc->no_create) goto mknod; diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 67c588edf8d8..4aba00a6004b 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -767,7 +767,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, mark_inode_dirty(inode); d_instantiate(dentry, inode); if (file) { - *opened |= FILE_CREATED; + file->f_mode |= FMODE_CREATED; error = finish_open(file, dentry, gfs2_open_common, opened); } gfs2_glock_dq_uninit(ghs); diff --git a/fs/namei.c b/fs/namei.c index 8a1ae074c1c1..4bd7cc0d7522 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3061,7 +3061,7 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry, * permission here. */ int acc_mode = op->acc_mode; - if (*opened & FILE_CREATED) { + if (file->f_mode & FMODE_CREATED) { WARN_ON(!(open_flag & O_CREAT)); fsnotify_create(dir, dentry); acc_mode = 0; @@ -3077,7 +3077,7 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry, dput(dentry); dentry = file->f_path.dentry; } - if (*opened & FILE_CREATED) + if (file->f_mode & FMODE_CREATED) fsnotify_create(dir, dentry); if (unlikely(d_is_negative(dentry))) { error = -ENOENT; @@ -3126,7 +3126,7 @@ static int lookup_open(struct nameidata *nd, struct path *path, if (unlikely(IS_DEADDIR(dir_inode))) return -ENOENT; - *opened &= ~FILE_CREATED; + file->f_mode &= ~FMODE_CREATED; dentry = d_lookup(dir, &nd->last); for (;;) { if (!dentry) { @@ -3211,7 +3211,7 @@ no_open: /* Negative dentry, just create the file */ if (!dentry->d_inode && (open_flag & O_CREAT)) { - *opened |= FILE_CREATED; + file->f_mode |= FMODE_CREATED; audit_inode_child(dir_inode, dentry, AUDIT_TYPE_CHILD_CREATE); if (!dir_inode->i_op->create) { error = -EACCES; @@ -3318,7 +3318,7 @@ static int do_last(struct nameidata *nd, if (error) goto out; - if ((*opened & FILE_CREATED) || + if ((file->f_mode & FMODE_CREATED) || !S_ISREG(file_inode(file)->i_mode)) will_truncate = false; @@ -3326,7 +3326,7 @@ static int do_last(struct nameidata *nd, goto opened; } - if (*opened & FILE_CREATED) { + if (file->f_mode & FMODE_CREATED) { /* Don't check for write permission, don't truncate */ open_flag &= ~O_TRUNC; will_truncate = false; @@ -3400,7 +3400,8 @@ finish_open_created: if (error) goto out; opened: - error = ima_file_check(file, op->acc_mode, *opened); + error = ima_file_check(file, op->acc_mode, + file->f_mode & FMODE_CREATED ? FILE_CREATED : 0); if (!error && will_truncate) error = handle_truncate(file); out: diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 7a9c14426855..0ac50983fc4e 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1461,6 +1461,7 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry, struct inode *inode; unsigned int lookup_flags = 0; bool switched = false; + int created = 0; int err; /* Expect a negative dentry */ @@ -1521,7 +1522,9 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry, goto out; trace_nfs_atomic_open_enter(dir, ctx, open_flags); - inode = NFS_PROTO(dir)->open_context(dir, ctx, open_flags, &attr, opened); + inode = NFS_PROTO(dir)->open_context(dir, ctx, open_flags, &attr, &created); + if (created) + file->f_mode |= FMODE_CREATED; if (IS_ERR(inode)) { err = PTR_ERR(inode); trace_nfs_atomic_open_exit(dir, ctx, open_flags, err); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index ed45090e4df6..2c4df0ffbca1 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2951,7 +2951,7 @@ static int _nfs4_do_open(struct inode *dir, } } if (opened && opendata->file_created) - *opened |= FILE_CREATED; + *opened = 1; if (pnfs_use_threshold(ctx_th, opendata->f_attr.mdsthreshold, server)) { *ctx_th = opendata->f_attr.mdsthreshold; diff --git a/include/linux/fs.h b/include/linux/fs.h index 05f34726e29c..ca668c7e48a7 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -149,6 +149,7 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define FMODE_CAN_WRITE ((__force fmode_t)0x40000) #define FMODE_OPENED ((__force fmode_t)0x80000) +#define FMODE_CREATED ((__force fmode_t)0x100000) /* File was opened by fanotify and shouldn't generate fanotify events */ #define FMODE_NONOTIFY ((__force fmode_t)0x4000000) -- cgit v1.2.3 From 6035a27b25ab9dadc8c3d5c5df5eae3fca62fc95 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 8 Jun 2018 13:40:10 -0400 Subject: IMA: don't propagate opened through the entire thing just check ->f_mode in ima_appraise_measurement() Acked-by: Linus Torvalds Signed-off-by: Al Viro --- fs/namei.c | 3 +-- fs/nfsd/vfs.c | 2 +- include/linux/ima.h | 4 ++-- security/integrity/ima/ima.h | 4 ++-- security/integrity/ima/ima_appraise.c | 4 ++-- security/integrity/ima/ima_main.c | 16 ++++++++-------- 6 files changed, 16 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/fs/namei.c b/fs/namei.c index 4bd7cc0d7522..d2aeb282ed05 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3400,8 +3400,7 @@ finish_open_created: if (error) goto out; opened: - error = ima_file_check(file, op->acc_mode, - file->f_mode & FMODE_CREATED ? FILE_CREATED : 0); + error = ima_file_check(file, op->acc_mode); if (!error && will_truncate) error = handle_truncate(file); out: diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index b0555d7d8200..55a099e47ba2 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -763,7 +763,7 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, goto out_nfserr; } - host_err = ima_file_check(file, may_flags, 0); + host_err = ima_file_check(file, may_flags); if (host_err) { fput(file); goto out_nfserr; diff --git a/include/linux/ima.h b/include/linux/ima.h index 0e4647e0eb60..d9ba3fc363b7 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -16,7 +16,7 @@ struct linux_binprm; #ifdef CONFIG_IMA extern int ima_bprm_check(struct linux_binprm *bprm); -extern int ima_file_check(struct file *file, int mask, int opened); +extern int ima_file_check(struct file *file, int mask); extern void ima_file_free(struct file *file); extern int ima_file_mmap(struct file *file, unsigned long prot); extern int ima_read_file(struct file *file, enum kernel_read_file_id id); @@ -34,7 +34,7 @@ static inline int ima_bprm_check(struct linux_binprm *bprm) return 0; } -static inline int ima_file_check(struct file *file, int mask, int opened) +static inline int ima_file_check(struct file *file, int mask) { return 0; } diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h index 354bb5716ce3..e4c1a236976c 100644 --- a/security/integrity/ima/ima.h +++ b/security/integrity/ima/ima.h @@ -238,7 +238,7 @@ int ima_appraise_measurement(enum ima_hooks func, struct integrity_iint_cache *iint, struct file *file, const unsigned char *filename, struct evm_ima_xattr_data *xattr_value, - int xattr_len, int opened); + int xattr_len); int ima_must_appraise(struct inode *inode, int mask, enum ima_hooks func); void ima_update_xattr(struct integrity_iint_cache *iint, struct file *file); enum integrity_status ima_get_cache_status(struct integrity_iint_cache *iint, @@ -254,7 +254,7 @@ static inline int ima_appraise_measurement(enum ima_hooks func, struct file *file, const unsigned char *filename, struct evm_ima_xattr_data *xattr_value, - int xattr_len, int opened) + int xattr_len) { return INTEGRITY_UNKNOWN; } diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c index 8bd7a0733e51..deec1804a00a 100644 --- a/security/integrity/ima/ima_appraise.c +++ b/security/integrity/ima/ima_appraise.c @@ -212,7 +212,7 @@ int ima_appraise_measurement(enum ima_hooks func, struct integrity_iint_cache *iint, struct file *file, const unsigned char *filename, struct evm_ima_xattr_data *xattr_value, - int xattr_len, int opened) + int xattr_len) { static const char op[] = "appraise_data"; const char *cause = "unknown"; @@ -231,7 +231,7 @@ int ima_appraise_measurement(enum ima_hooks func, cause = iint->flags & IMA_DIGSIG_REQUIRED ? "IMA-signature-required" : "missing-hash"; status = INTEGRITY_NOLABEL; - if (opened & FILE_CREATED) + if (file->f_mode & FMODE_CREATED) iint->flags |= IMA_NEW_FILE; if ((iint->flags & IMA_NEW_FILE) && (!(iint->flags & IMA_DIGSIG_REQUIRED) || diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c index dca44cf7838e..b286f37712d5 100644 --- a/security/integrity/ima/ima_main.c +++ b/security/integrity/ima/ima_main.c @@ -168,7 +168,7 @@ void ima_file_free(struct file *file) static int process_measurement(struct file *file, const struct cred *cred, u32 secid, char *buf, loff_t size, int mask, - enum ima_hooks func, int opened) + enum ima_hooks func) { struct inode *inode = file_inode(file); struct integrity_iint_cache *iint = NULL; @@ -294,7 +294,7 @@ static int process_measurement(struct file *file, const struct cred *cred, if (rc == 0 && (action & IMA_APPRAISE_SUBMASK)) { inode_lock(inode); rc = ima_appraise_measurement(func, iint, file, pathname, - xattr_value, xattr_len, opened); + xattr_value, xattr_len); inode_unlock(inode); } if (action & IMA_AUDIT) @@ -338,7 +338,7 @@ int ima_file_mmap(struct file *file, unsigned long prot) if (file && (prot & PROT_EXEC)) { security_task_getsecid(current, &secid); return process_measurement(file, current_cred(), secid, NULL, - 0, MAY_EXEC, MMAP_CHECK, 0); + 0, MAY_EXEC, MMAP_CHECK); } return 0; @@ -364,13 +364,13 @@ int ima_bprm_check(struct linux_binprm *bprm) security_task_getsecid(current, &secid); ret = process_measurement(bprm->file, current_cred(), secid, NULL, 0, - MAY_EXEC, BPRM_CHECK, 0); + MAY_EXEC, BPRM_CHECK); if (ret) return ret; security_cred_getsecid(bprm->cred, &secid); return process_measurement(bprm->file, bprm->cred, secid, NULL, 0, - MAY_EXEC, CREDS_CHECK, 0); + MAY_EXEC, CREDS_CHECK); } /** @@ -383,14 +383,14 @@ int ima_bprm_check(struct linux_binprm *bprm) * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ -int ima_file_check(struct file *file, int mask, int opened) +int ima_file_check(struct file *file, int mask) { u32 secid; security_task_getsecid(current, &secid); return process_measurement(file, current_cred(), secid, NULL, 0, mask & (MAY_READ | MAY_WRITE | MAY_EXEC | - MAY_APPEND), FILE_CHECK, opened); + MAY_APPEND), FILE_CHECK); } EXPORT_SYMBOL_GPL(ima_file_check); @@ -493,7 +493,7 @@ int ima_post_read_file(struct file *file, void *buf, loff_t size, func = read_idmap[read_id] ?: FILE_CHECK; security_task_getsecid(current, &secid); return process_measurement(file, current_cred(), secid, buf, size, - MAY_READ, func, 0); + MAY_READ, func); } static int __init init_ima(void) -- cgit v1.2.3 From be12af3ef5e61ebc44d065e121424ac605d7bb8e Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 8 Jun 2018 11:44:56 -0400 Subject: getting rid of 'opened' argument of ->atomic_open() - part 1 'opened' argument of finish_open() is unused. Kill it. Signed-off-by Al Viro --- fs/9p/vfs_inode.c | 2 +- fs/9p/vfs_inode_dotl.c | 2 +- fs/ceph/file.c | 2 +- fs/cifs/dir.c | 2 +- fs/fuse/dir.c | 2 +- fs/gfs2/inode.c | 6 +++--- fs/namei.c | 2 +- fs/nfs/dir.c | 2 +- fs/open.c | 3 +-- include/linux/fs.h | 3 +-- 10 files changed, 12 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 566929792480..7b6ff3275d9c 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -917,7 +917,7 @@ v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry, v9inode->writeback_fid = (void *) inode_fid; } mutex_unlock(&v9inode->v_mutex); - err = finish_open(file, dentry, generic_file_open, opened); + err = finish_open(file, dentry, generic_file_open); if (err) goto error; diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index ee65db5c7eb0..c6939b7cb18c 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -352,7 +352,7 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry, } mutex_unlock(&v9inode->v_mutex); /* Since we are opening a file, assign the open fid to the file */ - err = finish_open(file, dentry, generic_file_open, opened); + err = finish_open(file, dentry, generic_file_open); if (err) goto err_clunk_old_fid; file->private_data = ofid; diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 38a63fff7903..38b28cb2fac1 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -509,7 +509,7 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry, ceph_init_inode_acls(d_inode(dentry), &acls); file->f_mode |= FMODE_CREATED; } - err = finish_open(file, dentry, ceph_open, opened); + err = finish_open(file, dentry, ceph_open); } out_req: if (!req->r_err && req->r_target_inode) diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index 21d7e393900e..891bfd62e67a 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -541,7 +541,7 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry, if ((oflags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL)) file->f_mode |= FMODE_CREATED; - rc = finish_open(file, direntry, generic_file_open, opened); + rc = finish_open(file, direntry, generic_file_open); if (rc) { if (server->ops->close) server->ops->close(xid, tcon, &fid); diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index d4bdcf51e6cb..a5b1f5ff8cb7 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -469,7 +469,7 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, d_instantiate(entry, inode); fuse_change_entry_timeout(entry, &outentry); fuse_invalidate_attr(dir); - err = finish_open(file, entry, generic_file_open, opened); + err = finish_open(file, entry, generic_file_open); if (err) { fuse_sync_release(ff, flags); } else { diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 4aba00a6004b..59f695e96d63 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -626,7 +626,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, error = 0; if (file) { if (S_ISREG(inode->i_mode)) - error = finish_open(file, dentry, gfs2_open_common, opened); + error = finish_open(file, dentry, gfs2_open_common); else error = finish_no_open(file, NULL); } @@ -768,7 +768,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, d_instantiate(dentry, inode); if (file) { file->f_mode |= FMODE_CREATED; - error = finish_open(file, dentry, gfs2_open_common, opened); + error = finish_open(file, dentry, gfs2_open_common); } gfs2_glock_dq_uninit(ghs); gfs2_glock_dq_uninit(ghs + 1); @@ -866,7 +866,7 @@ static struct dentry *__gfs2_lookup(struct inode *dir, struct dentry *dentry, return d; } if (file && S_ISREG(inode->i_mode)) - error = finish_open(file, dentry, gfs2_open_common, opened); + error = finish_open(file, dentry, gfs2_open_common); gfs2_glock_dq_uninit(&gh); if (error) { diff --git a/fs/namei.c b/fs/namei.c index d2aeb282ed05..117b118853f2 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3475,7 +3475,7 @@ static int do_tmpfile(struct nameidata *nd, unsigned flags, if (error) goto out2; file->f_path.mnt = path.mnt; - error = finish_open(file, child, NULL, opened); + error = finish_open(file, child, NULL); out2: mnt_drop_write(path.mnt); out: diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 0ac50983fc4e..22176a3818d5 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1439,7 +1439,7 @@ static int nfs_finish_open(struct nfs_open_context *ctx, { int err; - err = finish_open(file, dentry, do_open, opened); + err = finish_open(file, dentry, do_open); if (err) goto out; if (S_ISREG(file->f_path.dentry->d_inode->i_mode)) diff --git a/fs/open.c b/fs/open.c index d2030a3c5c52..dbaac9efc7fc 100644 --- a/fs/open.c +++ b/fs/open.c @@ -843,8 +843,7 @@ cleanup_file: * Returns zero on success or -errno if the open failed. */ int finish_open(struct file *file, struct dentry *dentry, - int (*open)(struct inode *, struct file *), - int *opened) + int (*open)(struct inode *, struct file *)) { BUG_ON(file->f_mode & FMODE_OPENED); /* once it's opened, it's opened */ diff --git a/include/linux/fs.h b/include/linux/fs.h index ca668c7e48a7..70be3e4c26ac 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2441,8 +2441,7 @@ enum { FILE_OPENED = 2 }; extern int finish_open(struct file *file, struct dentry *dentry, - int (*open)(struct inode *, struct file *), - int *opened); + int (*open)(struct inode *, struct file *)); extern int finish_no_open(struct file *file, struct dentry *dentry); /* fs/ioctl.c */ -- cgit v1.2.3 From 44907d79002466049fdbb8ef15730d185e0808b4 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 8 Jun 2018 13:32:02 -0400 Subject: get rid of 'opened' argument of ->atomic_open() - part 3 now it can be done... Acked-by: Linus Torvalds Signed-off-by: Al Viro --- fs/9p/vfs_inode.c | 3 +-- fs/9p/vfs_inode_dotl.c | 3 +-- fs/bad_inode.c | 2 +- fs/ceph/file.c | 3 +-- fs/ceph/super.h | 3 +-- fs/cifs/cifsfs.h | 3 +-- fs/cifs/dir.c | 3 +-- fs/fuse/dir.c | 2 +- fs/gfs2/inode.c | 3 +-- fs/namei.c | 3 +-- fs/nfs/dir.c | 2 +- fs/nfs/nfs4_fs.h | 2 +- include/linux/fs.h | 2 +- 13 files changed, 13 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 7b6ff3275d9c..85ff859d3af5 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -859,8 +859,7 @@ struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry, static int v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry, - struct file *file, unsigned flags, umode_t mode, - int *opened) + struct file *file, unsigned flags, umode_t mode) { int err; u32 perm; diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index c6939b7cb18c..4823e1c46999 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -241,8 +241,7 @@ v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, umode_t omode, static int v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry, - struct file *file, unsigned flags, umode_t omode, - int *opened) + struct file *file, unsigned flags, umode_t omode) { int err = 0; kgid_t gid; diff --git a/fs/bad_inode.c b/fs/bad_inode.c index 125e8bbd22a2..8035d2a44561 100644 --- a/fs/bad_inode.c +++ b/fs/bad_inode.c @@ -134,7 +134,7 @@ static int bad_inode_update_time(struct inode *inode, struct timespec64 *time, static int bad_inode_atomic_open(struct inode *inode, struct dentry *dentry, struct file *file, unsigned int open_flag, - umode_t create_mode, int *opened) + umode_t create_mode) { return -EIO; } diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 38b28cb2fac1..e2679e8a2535 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -429,8 +429,7 @@ out: * file or symlink, return 1 so the VFS can retry. */ int ceph_atomic_open(struct inode *dir, struct dentry *dentry, - struct file *file, unsigned flags, umode_t mode, - int *opened) + struct file *file, unsigned flags, umode_t mode) { struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb); struct ceph_mds_client *mdsc = fsc->mdsc; diff --git a/fs/ceph/super.h b/fs/ceph/super.h index a7077a0c989f..971328b99ede 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -1025,8 +1025,7 @@ extern const struct file_operations ceph_file_fops; extern int ceph_renew_caps(struct inode *inode); extern int ceph_open(struct inode *inode, struct file *file); extern int ceph_atomic_open(struct inode *dir, struct dentry *dentry, - struct file *file, unsigned flags, umode_t mode, - int *opened); + struct file *file, unsigned flags, umode_t mode); extern int ceph_release(struct inode *inode, struct file *filp); extern void ceph_fill_inline_data(struct inode *inode, struct page *locked_page, char *data, size_t len); diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 5f0231803431..f3a78efc3109 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -65,8 +65,7 @@ extern struct inode *cifs_root_iget(struct super_block *); extern int cifs_create(struct inode *, struct dentry *, umode_t, bool excl); extern int cifs_atomic_open(struct inode *, struct dentry *, - struct file *, unsigned, umode_t, - int *); + struct file *, unsigned, umode_t); extern struct dentry *cifs_lookup(struct inode *, struct dentry *, unsigned int); extern int cifs_unlink(struct inode *dir, struct dentry *dentry); diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index 891bfd62e67a..3713d22b95a7 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -465,8 +465,7 @@ out_err: int cifs_atomic_open(struct inode *inode, struct dentry *direntry, - struct file *file, unsigned oflags, umode_t mode, - int *opened) + struct file *file, unsigned oflags, umode_t mode) { int rc; unsigned int xid; diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index b8d7e9d423c8..c979329311c8 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -489,7 +489,7 @@ out_err: static int fuse_mknod(struct inode *, struct dentry *, umode_t, dev_t); static int fuse_atomic_open(struct inode *dir, struct dentry *entry, struct file *file, unsigned flags, - umode_t mode, int *opened) + umode_t mode) { int err; struct fuse_conn *fc = get_fuse_conn(dir); diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 15e2a8a3b917..648f0ca1ad57 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -1228,14 +1228,13 @@ static int gfs2_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, * @file: The proposed new struct file * @flags: open flags * @mode: File mode - * @opened: Flag to say whether the file has been opened or not * * Returns: error code or 0 for success */ static int gfs2_atomic_open(struct inode *dir, struct dentry *dentry, struct file *file, unsigned flags, - umode_t mode, int *opened) + umode_t mode) { struct dentry *d; bool excl = !!(flags & O_EXCL); diff --git a/fs/namei.c b/fs/namei.c index 117b118853f2..1da272bf8ed3 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3052,8 +3052,7 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry, file->f_path.dentry = DENTRY_NOT_SET; file->f_path.mnt = nd->path.mnt; error = dir->i_op->atomic_open(dir, dentry, file, - open_to_namei_flags(open_flag), - mode, opened); + open_to_namei_flags(open_flag), mode); d_lookup_done(dentry); if (!error) { /* diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 71ae3cc3e53a..f447b1a24350 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1451,7 +1451,7 @@ out: int nfs_atomic_open(struct inode *dir, struct dentry *dentry, struct file *file, unsigned open_flags, - umode_t mode, int *opened) + umode_t mode) { DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); struct nfs_open_context *ctx; diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 137e18abb7e7..51beb6e38c90 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -258,7 +258,7 @@ extern const struct dentry_operations nfs4_dentry_operations; /* dir.c */ int nfs_atomic_open(struct inode *, struct dentry *, struct file *, - unsigned, umode_t, int *); + unsigned, umode_t); /* super.c */ extern struct file_system_type nfs4_fs_type; diff --git a/include/linux/fs.h b/include/linux/fs.h index 70be3e4c26ac..c25896b30e9f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1781,7 +1781,7 @@ struct inode_operations { int (*update_time)(struct inode *, struct timespec64 *, int); int (*atomic_open)(struct inode *, struct dentry *, struct file *, unsigned open_flag, - umode_t create_mode, int *opened); + umode_t create_mode); int (*tmpfile) (struct inode *, struct dentry *, umode_t); int (*set_acl)(struct inode *, struct posix_acl *, int); } ____cacheline_aligned; -- cgit v1.2.3 From dbae8f2ca2f0586f4b80201c78ff0aed2a012ab5 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 8 Jun 2018 17:51:47 -0400 Subject: kill FILE_{CREATED,OPENED} no users left Acked-by: Linus Torvalds Signed-off-by: Al Viro --- include/linux/fs.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index c25896b30e9f..bd904c496878 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2436,10 +2436,6 @@ extern struct filename *getname(const char __user *); extern struct filename *getname_kernel(const char *); extern void putname(struct filename *name); -enum { - FILE_CREATED = 1, - FILE_OPENED = 2 -}; extern int finish_open(struct file *file, struct dentry *dentry, int (*open)(struct inode *, struct file *)); extern int finish_no_open(struct file *file, struct dentry *dentry); -- cgit v1.2.3 From d93aa9d82aea80b80f225dbf9c7986df444d8106 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 9 Jun 2018 09:40:05 -0400 Subject: new wrapper: alloc_file_pseudo() takes inode, vfsmount, name, O_... flags and file_operations and either returns a new struct file (in which case inode reference we held is consumed) or returns ERR_PTR(), in which case no refcounts are altered. converted aio_private_file() and sock_alloc_file() to it Acked-by: Linus Torvalds Signed-off-by: Al Viro --- fs/aio.c | 20 ++++---------------- fs/file_table.c | 27 +++++++++++++++++++++++++++ include/linux/file.h | 3 +++ net/socket.c | 28 +++++----------------------- 4 files changed, 39 insertions(+), 39 deletions(-) (limited to 'include') diff --git a/fs/aio.c b/fs/aio.c index 9eea53887d6c..c3a8bac16374 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -215,9 +215,7 @@ static const struct address_space_operations aio_ctx_aops; static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages) { - struct qstr this = QSTR_INIT("[aio]", 5); struct file *file; - struct path path; struct inode *inode = alloc_anon_inode(aio_mnt->mnt_sb); if (IS_ERR(inode)) return ERR_CAST(inode); @@ -226,27 +224,17 @@ static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages) inode->i_mapping->private_data = ctx; inode->i_size = PAGE_SIZE * nr_pages; - path.dentry = d_alloc_pseudo(aio_mnt->mnt_sb, &this); - if (!path.dentry) { - iput(inode); - return ERR_PTR(-ENOMEM); - } - path.mnt = mntget(aio_mnt); - - d_instantiate(path.dentry, inode); - file = alloc_file(&path, O_RDWR, &aio_ring_fops); + file = alloc_file_pseudo(inode, aio_mnt, "[aio]", + O_RDWR, &aio_ring_fops); if (IS_ERR(file)) - path_put(&path); + iput(inode); return file; } static struct dentry *aio_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data) { - static const struct dentry_operations ops = { - .d_dname = simple_dname, - }; - struct dentry *root = mount_pseudo(fs_type, "aio:", NULL, &ops, + struct dentry *root = mount_pseudo(fs_type, "aio:", NULL, NULL, AIO_RING_MAGIC); if (!IS_ERR(root)) diff --git a/fs/file_table.c b/fs/file_table.c index 9b70ed2bbc4e..6b3723909342 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -184,6 +184,33 @@ struct file *alloc_file(const struct path *path, int flags, } EXPORT_SYMBOL(alloc_file); +struct file *alloc_file_pseudo(struct inode *inode, struct vfsmount *mnt, + const char *name, int flags, + const struct file_operations *fops) +{ + static const struct dentry_operations anon_ops = { + .d_dname = simple_dname + }; + struct qstr this = QSTR_INIT(name, strlen(name)); + struct path path; + struct file *file; + + path.dentry = d_alloc_pseudo(mnt->mnt_sb, &this); + if (!path.dentry) + return ERR_PTR(-ENOMEM); + if (!mnt->mnt_sb->s_d_op) + d_set_d_op(path.dentry, &anon_ops); + path.mnt = mntget(mnt); + d_instantiate(path.dentry, inode); + file = alloc_file(&path, flags, fops); + if (IS_ERR(file)) { + ihold(inode); + path_put(&path); + } + return file; +} +EXPORT_SYMBOL(alloc_file_pseudo); + /* the real guts of fput() - releasing the last reference to file */ static void __fput(struct file *file) diff --git a/include/linux/file.h b/include/linux/file.h index aed45d69811e..5b25388f2f79 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -17,9 +17,12 @@ extern void fput(struct file *); struct file_operations; struct vfsmount; struct dentry; +struct inode; struct path; extern struct file *alloc_file(const struct path *, int flags, const struct file_operations *fop); +extern struct file *alloc_file_pseudo(struct inode *, struct vfsmount *, + const char *, int flags, const struct file_operations *); static inline void fput_light(struct file *file, int fput_needed) { diff --git a/net/socket.c b/net/socket.c index 2cdbe8f71b7f..4cf3568caf9f 100644 --- a/net/socket.c +++ b/net/socket.c @@ -391,33 +391,15 @@ static struct file_system_type sock_fs_type = { struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname) { - struct qstr name = { .name = "" }; - struct path path; struct file *file; - if (dname) { - name.name = dname; - name.len = strlen(name.name); - } else if (sock->sk) { - name.name = sock->sk->sk_prot_creator->name; - name.len = strlen(name.name); - } - path.dentry = d_alloc_pseudo(sock_mnt->mnt_sb, &name); - if (unlikely(!path.dentry)) { - sock_release(sock); - return ERR_PTR(-ENOMEM); - } - path.mnt = mntget(sock_mnt); - - d_instantiate(path.dentry, SOCK_INODE(sock)); + if (!dname) + dname = sock->sk ? sock->sk->sk_prot_creator->name : ""; - file = alloc_file(&path, O_RDWR | (flags & O_NONBLOCK), - &socket_file_ops); + file = alloc_file_pseudo(SOCK_INODE(sock), sock_mnt, dname, + O_RDWR | (flags & O_NONBLOCK), + &socket_file_ops); if (IS_ERR(file)) { - /* drop dentry, keep inode for a bit */ - ihold(d_inode(path.dentry)); - path_put(&path); - /* ... and now kill it properly */ sock_release(sock); return file; } -- cgit v1.2.3 From 183266f26f45a47958afb5c9aa1b3d4651e2eb8c Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 17 Jun 2018 14:15:10 -0400 Subject: new helper: alloc_file_clone() alloc_file_clone(old_file, mode, ops): create a new struct file with ->f_path equal to that of old_file. pipe converted. Acked-by: Linus Torvalds Signed-off-by: Al Viro --- fs/file_table.c | 11 +++++++++++ fs/pipe.c | 6 ++---- include/linux/file.h | 2 ++ 3 files changed, 15 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/fs/file_table.c b/fs/file_table.c index 6b3723909342..78b067ddb386 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -211,6 +211,17 @@ struct file *alloc_file_pseudo(struct inode *inode, struct vfsmount *mnt, } EXPORT_SYMBOL(alloc_file_pseudo); +struct file *alloc_file_clone(struct file *base, int flags, + const struct file_operations *fops) +{ + struct file *f = alloc_file(&base->f_path, flags, fops); + if (!IS_ERR(f)) { + path_get(&f->f_path); + f->f_mapping = base->f_mapping; + } + return f; +} + /* the real guts of fput() - releasing the last reference to file */ static void __fput(struct file *file) diff --git a/fs/pipe.c b/fs/pipe.c index 9701bd3458d1..5f50070774bc 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -761,15 +761,13 @@ int create_pipe_files(struct file **res, int flags) f->private_data = inode->i_pipe; - res[0] = alloc_file(&f->f_path, O_RDONLY | (flags & O_NONBLOCK), - &pipefifo_fops); + res[0] = alloc_file_clone(f, O_RDONLY | (flags & O_NONBLOCK), + &pipefifo_fops); if (IS_ERR(res[0])) { put_pipe_info(inode, inode->i_pipe); fput(f); return PTR_ERR(res[0]); } - - path_get(&f->f_path); res[0]->private_data = inode->i_pipe; res[1] = f; return 0; diff --git a/include/linux/file.h b/include/linux/file.h index 5b25388f2f79..60914843c737 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -23,6 +23,8 @@ extern struct file *alloc_file(const struct path *, int flags, const struct file_operations *fop); extern struct file *alloc_file_pseudo(struct inode *, struct vfsmount *, const char *, int flags, const struct file_operations *); +extern struct file *alloc_file_clone(struct file *, int flags, + const struct file_operations *); static inline void fput_light(struct file *file, int fput_needed) { -- cgit v1.2.3 From ee1904ba44bd4a242b453e8fe179b374906da173 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 17 Jun 2018 14:21:27 -0400 Subject: make alloc_file() static Acked-by: Linus Torvalds Signed-off-by: Al Viro --- fs/file_table.c | 3 +-- include/linux/file.h | 2 -- 2 files changed, 1 insertion(+), 4 deletions(-) (limited to 'include') diff --git a/fs/file_table.c b/fs/file_table.c index 78b067ddb386..d6eccd04d703 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -157,7 +157,7 @@ over: * @flags: O_... flags with which the new file will be opened * @fop: the 'struct file_operations' for the new file */ -struct file *alloc_file(const struct path *path, int flags, +static struct file *alloc_file(const struct path *path, int flags, const struct file_operations *fop) { struct file *file; @@ -182,7 +182,6 @@ struct file *alloc_file(const struct path *path, int flags, i_readcount_inc(path->dentry->d_inode); return file; } -EXPORT_SYMBOL(alloc_file); struct file *alloc_file_pseudo(struct inode *inode, struct vfsmount *mnt, const char *name, int flags, diff --git a/include/linux/file.h b/include/linux/file.h index 60914843c737..6b2fb032416c 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -19,8 +19,6 @@ struct vfsmount; struct dentry; struct inode; struct path; -extern struct file *alloc_file(const struct path *, int flags, - const struct file_operations *fop); extern struct file *alloc_file_pseudo(struct inode *, struct vfsmount *, const char *, int flags, const struct file_operations *); extern struct file *alloc_file_clone(struct file *, int flags, -- cgit v1.2.3 From 2bae79d2d38f3dc50bfef81d3b4f7328b2883a17 Mon Sep 17 00:00:00 2001 From: Quentin Monnet Date: Thu, 12 Jul 2018 12:52:22 +0100 Subject: bpf: fix documentation for eBPF helpers Minor formatting edits for eBPF helpers documentation, including blank lines removal, fix of item list for return values in bpf_fib_lookup(), and missing prefix on bpf_skb_load_bytes_relative(). Signed-off-by: Quentin Monnet Reviewed-by: Jakub Kicinski Signed-off-by: Daniel Borkmann --- include/uapi/linux/bpf.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index b7db3261c62d..6bcb287a888d 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1826,7 +1826,7 @@ union bpf_attr { * A non-negative value equal to or less than *size* on success, * or a negative error in case of failure. * - * int skb_load_bytes_relative(const struct sk_buff *skb, u32 offset, void *to, u32 len, u32 start_header) + * int bpf_skb_load_bytes_relative(const struct sk_buff *skb, u32 offset, void *to, u32 len, u32 start_header) * Description * This helper is similar to **bpf_skb_load_bytes**\ () in that * it provides an easy way to load *len* bytes from *offset* @@ -1877,7 +1877,7 @@ union bpf_attr { * * < 0 if any input argument is invalid * * 0 on success (packet is forwarded, nexthop neighbor exists) * * > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the - * * packet is not forwarded or needs assist from full stack + * packet is not forwarded or needs assist from full stack * * int bpf_sock_hash_update(struct bpf_sock_ops_kern *skops, struct bpf_map *map, void *key, u64 flags) * Description @@ -2033,7 +2033,6 @@ union bpf_attr { * This helper is only available is the kernel was compiled with * the **CONFIG_BPF_LIRC_MODE2** configuration option set to * "**y**". - * * Return * 0 * @@ -2053,7 +2052,6 @@ union bpf_attr { * This helper is only available is the kernel was compiled with * the **CONFIG_BPF_LIRC_MODE2** configuration option set to * "**y**". - * * Return * 0 * -- cgit v1.2.3 From a8802d97e73346bc81609df9dfba7d3306f40d87 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 11 Jul 2018 11:16:41 -0700 Subject: ktime: Provide typesafe ktime_to_ns() Using ktime_to_ns() is nice to help backports to stable kernels. Having a typesafe function instead of a macro avoid stupid typos and waste of time tracking these typos. Reported-by: Willem de Bruijn Signed-off-by: Eric Dumazet Signed-off-by: Thomas Gleixner Cc: Eric Dumazet Cc: John Stultz Cc: Peter Zijlstra Cc: Linus Torvalds Link: https://lkml.kernel.org/r/20180711181641.10369-1-edumazet@google.com --- include/linux/ktime.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/ktime.h b/include/linux/ktime.h index 5b9fddbaac41..b2bb44f87f5a 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -93,8 +93,11 @@ static inline ktime_t timeval_to_ktime(struct timeval tv) /* Map the ktime_t to timeval conversion to ns_to_timeval function */ #define ktime_to_timeval(kt) ns_to_timeval((kt)) -/* Convert ktime_t to nanoseconds - NOP in the scalar storage format: */ -#define ktime_to_ns(kt) (kt) +/* Convert ktime_t to nanoseconds */ +static inline s64 ktime_to_ns(const ktime_t kt) +{ + return kt; +} /** * ktime_compare - Compares two ktime_t variables for less, greater or equal -- cgit v1.2.3 From cca9bab1b72cd2296097c75f59ef11ef80461279 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 11 Jul 2018 12:16:12 +0200 Subject: tcp: use monotonic timestamps for PAWS Using get_seconds() for timestamps is deprecated since it can lead to overflows on 32-bit systems. While the interface generally doesn't overflow until year 2106, the specific implementation of the TCP PAWS algorithm breaks in 2038 when the intermediate signed 32-bit timestamps overflow. A related problem is that the local timestamps in CLOCK_REALTIME form lead to unexpected behavior when settimeofday is called to set the system clock backwards or forwards by more than 24 days. While the first problem could be solved by using an overflow-safe method of comparing the timestamps, a nicer solution is to use a monotonic clocksource with ktime_get_seconds() that simply doesn't overflow (at least not until 136 years after boot) and that doesn't change during settimeofday(). To make 32-bit and 64-bit architectures behave the same way here, and also save a few bytes in the tcp_options_received structure, I'm changing the type to a 32-bit integer, which is now safe on all architectures. Finally, the ts_recent_stamp field also (confusingly) gets used to store a jiffies value in tcp_synq_overflow()/tcp_synq_no_recent_overflow(). This is currently safe, but changing the type to 32-bit requires some small changes there to keep it working. Signed-off-by: Arnd Bergmann Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- drivers/crypto/chelsio/chtls/chtls_cm.c | 2 +- include/linux/tcp.h | 4 ++-- include/net/tcp.h | 17 ++++++++++------- net/ipv4/tcp_input.c | 2 +- net/ipv4/tcp_ipv4.c | 3 ++- net/ipv4/tcp_minisocks.c | 8 ++++---- 6 files changed, 20 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/drivers/crypto/chelsio/chtls/chtls_cm.c b/drivers/crypto/chelsio/chtls/chtls_cm.c index 2bb6f0380758..0997e166ea57 100644 --- a/drivers/crypto/chelsio/chtls/chtls_cm.c +++ b/drivers/crypto/chelsio/chtls/chtls_cm.c @@ -1673,7 +1673,7 @@ static void chtls_timewait(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); tp->rcv_nxt++; - tp->rx_opt.ts_recent_stamp = get_seconds(); + tp->rx_opt.ts_recent_stamp = ktime_get_seconds(); tp->srtt_us = 0; tcp_time_wait(sk, TCP_TIME_WAIT, 0); } diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 3dbea6610304..58a8d7d71354 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -89,7 +89,7 @@ struct tcp_sack_block { struct tcp_options_received { /* PAWS/RTTM data */ - long ts_recent_stamp;/* Time we stored ts_recent (for aging) */ + int ts_recent_stamp;/* Time we stored ts_recent (for aging) */ u32 ts_recent; /* Time stamp to echo next */ u32 rcv_tsval; /* Time stamp value */ u32 rcv_tsecr; /* Time stamp echo reply */ @@ -426,7 +426,7 @@ struct tcp_timewait_sock { /* The time we sent the last out-of-window ACK: */ u32 tw_last_oow_ack_time; - long tw_ts_recent_stamp; + int tw_ts_recent_stamp; #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *tw_md5_key; #endif diff --git a/include/net/tcp.h b/include/net/tcp.h index f6cb20e6e524..582304955087 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -472,19 +472,20 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb); */ static inline void tcp_synq_overflow(const struct sock *sk) { - unsigned long last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp; - unsigned long now = jiffies; + unsigned int last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp; + unsigned int now = jiffies; - if (time_after(now, last_overflow + HZ)) + if (time_after32(now, last_overflow + HZ)) tcp_sk(sk)->rx_opt.ts_recent_stamp = now; } /* syncookies: no recent synqueue overflow on this listening socket? */ static inline bool tcp_synq_no_recent_overflow(const struct sock *sk) { - unsigned long last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp; + unsigned int last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp; + unsigned int now = jiffies; - return time_after(jiffies, last_overflow + TCP_SYNCOOKIE_VALID); + return time_after32(now, last_overflow + TCP_SYNCOOKIE_VALID); } static inline u32 tcp_cookie_time(void) @@ -1375,7 +1376,8 @@ static inline bool tcp_paws_check(const struct tcp_options_received *rx_opt, { if ((s32)(rx_opt->ts_recent - rx_opt->rcv_tsval) <= paws_win) return true; - if (unlikely(get_seconds() >= rx_opt->ts_recent_stamp + TCP_PAWS_24DAYS)) + if (unlikely(!time_before32(ktime_get_seconds(), + rx_opt->ts_recent_stamp + TCP_PAWS_24DAYS))) return true; /* * Some OSes send SYN and SYNACK messages with tsval=0 tsecr=0, @@ -1405,7 +1407,8 @@ static inline bool tcp_paws_reject(const struct tcp_options_received *rx_opt, However, we can relax time bounds for RST segments to MSL. */ - if (rst && get_seconds() >= rx_opt->ts_recent_stamp + TCP_PAWS_MSL) + if (rst && !time_before32(ktime_get_seconds(), + rx_opt->ts_recent_stamp + TCP_PAWS_MSL)) return false; return true; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 814ea43dd12f..d3b6390ecf23 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3462,7 +3462,7 @@ static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb) static void tcp_store_ts_recent(struct tcp_sock *tp) { tp->rx_opt.ts_recent = tp->rx_opt.rcv_tsval; - tp->rx_opt.ts_recent_stamp = get_seconds(); + tp->rx_opt.ts_recent_stamp = ktime_get_seconds(); } static void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index bea17f1e8302..dc415c66a33a 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -155,7 +155,8 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) and use initial timestamp retrieved from peer table. */ if (tcptw->tw_ts_recent_stamp && - (!twp || (reuse && get_seconds() - tcptw->tw_ts_recent_stamp > 1))) { + (!twp || (reuse && time_after32(ktime_get_seconds(), + tcptw->tw_ts_recent_stamp)))) { tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2; if (tp->write_seq == 0) tp->write_seq = 1; diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index dac5893a52b4..75ef332a7caf 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -144,7 +144,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, tw->tw_substate = TCP_TIME_WAIT; tcptw->tw_rcv_nxt = TCP_SKB_CB(skb)->end_seq; if (tmp_opt.saw_tstamp) { - tcptw->tw_ts_recent_stamp = get_seconds(); + tcptw->tw_ts_recent_stamp = ktime_get_seconds(); tcptw->tw_ts_recent = tmp_opt.rcv_tsval; } @@ -189,7 +189,7 @@ kill: if (tmp_opt.saw_tstamp) { tcptw->tw_ts_recent = tmp_opt.rcv_tsval; - tcptw->tw_ts_recent_stamp = get_seconds(); + tcptw->tw_ts_recent_stamp = ktime_get_seconds(); } inet_twsk_put(tw); @@ -537,7 +537,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, if (newtp->rx_opt.tstamp_ok) { newtp->rx_opt.ts_recent = req->ts_recent; - newtp->rx_opt.ts_recent_stamp = get_seconds(); + newtp->rx_opt.ts_recent_stamp = ktime_get_seconds(); newtp->tcp_header_len = sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED; } else { newtp->rx_opt.ts_recent_stamp = 0; @@ -603,7 +603,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, * it can be estimated (approximately) * from another data. */ - tmp_opt.ts_recent_stamp = get_seconds() - ((TCP_TIMEOUT_INIT/HZ)<num_timeout); + tmp_opt.ts_recent_stamp = ktime_get_seconds() - ((TCP_TIMEOUT_INIT/HZ)<num_timeout); paws_reject = tcp_paws_reject(&tmp_opt, th->rst); } } -- cgit v1.2.3 From c749cdda9089eb1fdb6a9ab98f945124d12f2595 Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Wed, 11 Jul 2018 16:04:50 +0200 Subject: net/sched: act_skbedit: don't use spinlock in the data path use RCU instead of spin_{,un}lock_bh, to protect concurrent read/write on act_skbedit configuration. This reduces the effects of contention in the data path, in case multiple readers are present. Signed-off-by: Davide Caratti Signed-off-by: David S. Miller --- include/net/tc_act/tc_skbedit.h | 37 ++++++++++---- net/sched/act_skbedit.c | 107 +++++++++++++++++++++++++--------------- 2 files changed, 95 insertions(+), 49 deletions(-) (limited to 'include') diff --git a/include/net/tc_act/tc_skbedit.h b/include/net/tc_act/tc_skbedit.h index 19cd3d345804..911bbac838a2 100644 --- a/include/net/tc_act/tc_skbedit.h +++ b/include/net/tc_act/tc_skbedit.h @@ -22,14 +22,19 @@ #include #include +struct tcf_skbedit_params { + u32 flags; + u32 priority; + u32 mark; + u32 mask; + u16 queue_mapping; + u16 ptype; + struct rcu_head rcu; +}; + struct tcf_skbedit { - struct tc_action common; - u32 flags; - u32 priority; - u32 mark; - u32 mask; - u16 queue_mapping; - u16 ptype; + struct tc_action common; + struct tcf_skbedit_params __rcu *params; }; #define to_skbedit(a) ((struct tcf_skbedit *)a) @@ -37,15 +42,27 @@ struct tcf_skbedit { static inline bool is_tcf_skbedit_mark(const struct tc_action *a) { #ifdef CONFIG_NET_CLS_ACT - if (a->ops && a->ops->type == TCA_ACT_SKBEDIT) - return to_skbedit(a)->flags == SKBEDIT_F_MARK; + u32 flags; + + if (a->ops && a->ops->type == TCA_ACT_SKBEDIT) { + rcu_read_lock(); + flags = rcu_dereference(to_skbedit(a)->params)->flags; + rcu_read_unlock(); + return flags == SKBEDIT_F_MARK; + } #endif return false; } static inline u32 tcf_skbedit_mark(const struct tc_action *a) { - return to_skbedit(a)->mark; + u32 mark; + + rcu_read_lock(); + mark = rcu_dereference(to_skbedit(a)->params)->mark; + rcu_read_unlock(); + + return mark; } #endif /* __NET_TC_SKBEDIT_H */ diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 8651b5bd6b59..da56e6938c9e 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -37,14 +37,19 @@ static int tcf_skbedit(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_skbedit *d = to_skbedit(a); + struct tcf_skbedit_params *params; + int action; tcf_lastuse_update(&d->tcf_tm); bstats_cpu_update(this_cpu_ptr(d->common.cpu_bstats), skb); - spin_lock(&d->tcf_lock); - if (d->flags & SKBEDIT_F_PRIORITY) - skb->priority = d->priority; - if (d->flags & SKBEDIT_F_INHERITDSFIELD) { + rcu_read_lock(); + params = rcu_dereference(d->params); + action = READ_ONCE(d->tcf_action); + + if (params->flags & SKBEDIT_F_PRIORITY) + skb->priority = params->priority; + if (params->flags & SKBEDIT_F_INHERITDSFIELD) { int wlen = skb_network_offset(skb); switch (tc_skb_protocol(skb)) { @@ -63,23 +68,23 @@ static int tcf_skbedit(struct sk_buff *skb, const struct tc_action *a, break; } } - if (d->flags & SKBEDIT_F_QUEUE_MAPPING && - skb->dev->real_num_tx_queues > d->queue_mapping) - skb_set_queue_mapping(skb, d->queue_mapping); - if (d->flags & SKBEDIT_F_MARK) { - skb->mark &= ~d->mask; - skb->mark |= d->mark & d->mask; + if (params->flags & SKBEDIT_F_QUEUE_MAPPING && + skb->dev->real_num_tx_queues > params->queue_mapping) + skb_set_queue_mapping(skb, params->queue_mapping); + if (params->flags & SKBEDIT_F_MARK) { + skb->mark &= ~params->mask; + skb->mark |= params->mark & params->mask; } - if (d->flags & SKBEDIT_F_PTYPE) - skb->pkt_type = d->ptype; - - spin_unlock(&d->tcf_lock); - return d->tcf_action; + if (params->flags & SKBEDIT_F_PTYPE) + skb->pkt_type = params->ptype; +unlock: + rcu_read_unlock(); + return action; err: - spin_unlock(&d->tcf_lock); qstats_drop_inc(this_cpu_ptr(d->common.cpu_qstats)); - return TC_ACT_SHOT; + action = TC_ACT_SHOT; + goto unlock; } static const struct nla_policy skbedit_policy[TCA_SKBEDIT_MAX + 1] = { @@ -98,6 +103,7 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, skbedit_net_id); + struct tcf_skbedit_params *params_old, *params_new; struct nlattr *tb[TCA_SKBEDIT_MAX + 1]; struct tc_skbedit *parm; struct tcf_skbedit *d; @@ -185,25 +191,34 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, } } - spin_lock_bh(&d->tcf_lock); + ASSERT_RTNL(); - d->flags = flags; + params_new = kzalloc(sizeof(*params_new), GFP_KERNEL); + if (unlikely(!params_new)) { + if (ret == ACT_P_CREATED) + tcf_idr_release(*a, bind); + return -ENOMEM; + } + + params_new->flags = flags; if (flags & SKBEDIT_F_PRIORITY) - d->priority = *priority; + params_new->priority = *priority; if (flags & SKBEDIT_F_QUEUE_MAPPING) - d->queue_mapping = *queue_mapping; + params_new->queue_mapping = *queue_mapping; if (flags & SKBEDIT_F_MARK) - d->mark = *mark; + params_new->mark = *mark; if (flags & SKBEDIT_F_PTYPE) - d->ptype = *ptype; + params_new->ptype = *ptype; /* default behaviour is to use all the bits */ - d->mask = 0xffffffff; + params_new->mask = 0xffffffff; if (flags & SKBEDIT_F_MASK) - d->mask = *mask; + params_new->mask = *mask; d->tcf_action = parm->action; - - spin_unlock_bh(&d->tcf_lock); + params_old = rtnl_dereference(d->params); + rcu_assign_pointer(d->params, params_new); + if (params_old) + kfree_rcu(params_old, rcu); if (ret == ACT_P_CREATED) tcf_idr_insert(tn, *a); @@ -215,33 +230,36 @@ static int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a, { unsigned char *b = skb_tail_pointer(skb); struct tcf_skbedit *d = to_skbedit(a); + struct tcf_skbedit_params *params; struct tc_skbedit opt = { .index = d->tcf_index, .refcnt = refcount_read(&d->tcf_refcnt) - ref, .bindcnt = atomic_read(&d->tcf_bindcnt) - bind, .action = d->tcf_action, }; - struct tcf_t t; u64 pure_flags = 0; + struct tcf_t t; + + params = rtnl_dereference(d->params); if (nla_put(skb, TCA_SKBEDIT_PARMS, sizeof(opt), &opt)) goto nla_put_failure; - if ((d->flags & SKBEDIT_F_PRIORITY) && - nla_put_u32(skb, TCA_SKBEDIT_PRIORITY, d->priority)) + if ((params->flags & SKBEDIT_F_PRIORITY) && + nla_put_u32(skb, TCA_SKBEDIT_PRIORITY, params->priority)) goto nla_put_failure; - if ((d->flags & SKBEDIT_F_QUEUE_MAPPING) && - nla_put_u16(skb, TCA_SKBEDIT_QUEUE_MAPPING, d->queue_mapping)) + if ((params->flags & SKBEDIT_F_QUEUE_MAPPING) && + nla_put_u16(skb, TCA_SKBEDIT_QUEUE_MAPPING, params->queue_mapping)) goto nla_put_failure; - if ((d->flags & SKBEDIT_F_MARK) && - nla_put_u32(skb, TCA_SKBEDIT_MARK, d->mark)) + if ((params->flags & SKBEDIT_F_MARK) && + nla_put_u32(skb, TCA_SKBEDIT_MARK, params->mark)) goto nla_put_failure; - if ((d->flags & SKBEDIT_F_PTYPE) && - nla_put_u16(skb, TCA_SKBEDIT_PTYPE, d->ptype)) + if ((params->flags & SKBEDIT_F_PTYPE) && + nla_put_u16(skb, TCA_SKBEDIT_PTYPE, params->ptype)) goto nla_put_failure; - if ((d->flags & SKBEDIT_F_MASK) && - nla_put_u32(skb, TCA_SKBEDIT_MASK, d->mask)) + if ((params->flags & SKBEDIT_F_MASK) && + nla_put_u32(skb, TCA_SKBEDIT_MASK, params->mask)) goto nla_put_failure; - if (d->flags & SKBEDIT_F_INHERITDSFIELD) + if (params->flags & SKBEDIT_F_INHERITDSFIELD) pure_flags |= SKBEDIT_F_INHERITDSFIELD; if (pure_flags != 0 && nla_put(skb, TCA_SKBEDIT_FLAGS, sizeof(pure_flags), &pure_flags)) @@ -257,6 +275,16 @@ nla_put_failure: return -1; } +static void tcf_skbedit_cleanup(struct tc_action *a) +{ + struct tcf_skbedit *d = to_skbedit(a); + struct tcf_skbedit_params *params; + + params = rcu_dereference_protected(d->params, 1); + if (params) + kfree_rcu(params, rcu); +} + static int tcf_skbedit_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, const struct tc_action_ops *ops, @@ -289,6 +317,7 @@ static struct tc_action_ops act_skbedit_ops = { .act = tcf_skbedit, .dump = tcf_skbedit_dump, .init = tcf_skbedit_init, + .cleanup = tcf_skbedit_cleanup, .walk = tcf_skbedit_walker, .lookup = tcf_skbedit_search, .delete = tcf_skbedit_delete, -- cgit v1.2.3 From 477351f7829d2268769c5d545511081555066529 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 1 May 2018 12:54:11 -0700 Subject: rcu: Convert rcu_grace_period tracepoint to gp_seq This commit makes the rcu_grace_period tracepoint use gp_seq instead of ->gpnum or ->completed. It also introduces a "cpuofl-bgp" string to less obscurely indicate when a CPU has gone offline while a grace period is waiting on it. Signed-off-by: Paul E. McKenney --- include/trace/events/rcu.h | 13 +++++++------ kernel/rcu/tree.c | 43 +++++++++++++++++++++---------------------- kernel/rcu/tree_plugin.h | 2 +- 3 files changed, 29 insertions(+), 29 deletions(-) (limited to 'include') diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h index 5936aac357ab..cd229e82ec8b 100644 --- a/include/trace/events/rcu.h +++ b/include/trace/events/rcu.h @@ -52,6 +52,7 @@ TRACE_EVENT(rcu_utilization, * "cpuqs": CPU passes through a quiescent state. * "cpuonl": CPU comes online. * "cpuofl": CPU goes offline. + * "cpuofl-bgp": CPU goes offline while blocking a grace period. * "reqwait": GP kthread sleeps waiting for grace-period request. * "reqwaitsig": GP kthread awakened by signal from reqwait state. * "fqswait": GP kthread waiting until time to force quiescent states. @@ -63,24 +64,24 @@ TRACE_EVENT(rcu_utilization, */ TRACE_EVENT(rcu_grace_period, - TP_PROTO(const char *rcuname, unsigned long gpnum, const char *gpevent), + TP_PROTO(const char *rcuname, unsigned long gp_seq, const char *gpevent), - TP_ARGS(rcuname, gpnum, gpevent), + TP_ARGS(rcuname, gp_seq, gpevent), TP_STRUCT__entry( __field(const char *, rcuname) - __field(unsigned long, gpnum) + __field(unsigned long, gp_seq) __field(const char *, gpevent) ), TP_fast_assign( __entry->rcuname = rcuname; - __entry->gpnum = gpnum; + __entry->gp_seq = gp_seq; __entry->gpevent = gpevent; ), TP_printk("%s %lu %s", - __entry->rcuname, __entry->gpnum, __entry->gpevent) + __entry->rcuname, __entry->gp_seq, __entry->gpevent) ); /* @@ -753,7 +754,7 @@ TRACE_EVENT(rcu_barrier, #else /* #ifdef CONFIG_RCU_TRACE */ -#define trace_rcu_grace_period(rcuname, gpnum, gpevent) do { } while (0) +#define trace_rcu_grace_period(rcuname, gp_seq, gpevent) do { } while (0) #define trace_rcu_future_grace_period(rcuname, gpnum, completed, c, \ level, grplo, grphi, event) \ do { } while (0) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 4826598867c3..7ce85ad39af6 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -234,7 +234,7 @@ void rcu_sched_qs(void) if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.s)) return; trace_rcu_grace_period(TPS("rcu_sched"), - __this_cpu_read(rcu_sched_data.gpnum), + __this_cpu_read(rcu_sched_data.gp_seq), TPS("cpuqs")); __this_cpu_write(rcu_sched_data.cpu_no_qs.b.norm, false); if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp)) @@ -249,7 +249,7 @@ void rcu_bh_qs(void) RCU_LOCKDEP_WARN(preemptible(), "rcu_bh_qs() invoked with preemption enabled!!!"); if (__this_cpu_read(rcu_bh_data.cpu_no_qs.s)) { trace_rcu_grace_period(TPS("rcu_bh"), - __this_cpu_read(rcu_bh_data.gpnum), + __this_cpu_read(rcu_bh_data.gp_seq), TPS("cpuqs")); __this_cpu_write(rcu_bh_data.cpu_no_qs.b.norm, false); } @@ -1615,7 +1615,7 @@ static bool rcu_start_this_gp(struct rcu_node *rnp, struct rcu_data *rdp, trace_rcu_this_gp(rnp_root, rdp, c, TPS("NoGPkthread")); goto unlock_out; } - trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum), TPS("newreq")); + trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gp_seq), TPS("newreq")); ret = true; /* Caller must wake GP kthread. */ unlock_out: /* Push furthest requested GP to leaf node and rcu_data structure. */ @@ -1702,9 +1702,9 @@ static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp, /* Trace depending on how much we were able to accelerate. */ if (rcu_segcblist_restempty(&rdp->cblist, RCU_WAIT_TAIL)) - trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("AccWaitCB")); + trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("AccWaitCB")); else - trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("AccReadyCB")); + trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("AccReadyCB")); return ret; } @@ -1774,7 +1774,7 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp, * go looking for one. */ rdp->gpnum = rnp->gpnum; - trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpustart")); + trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("cpustart")); need_gp = !!(rnp->qsmask & rdp->grpmask); rdp->cpu_no_qs.b.norm = need_gp; rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_dynticks.rcu_qs_ctr); @@ -1851,7 +1851,7 @@ static bool rcu_gp_init(struct rcu_state *rsp) rcu_seq_start(&rsp->gp_seq); if (WARN_ON_ONCE(((rnp->completed << RCU_SEQ_CTR_SHIFT) >> RCU_SEQ_CTR_SHIFT) != rcu_seq_ctr(rnp->gp_seq))) /* Catch any ->completed/->gp_seq mismatches. */ pr_info("%s ->completed: %#lx (%#lx) ->gp_seq %#lx (%#lx)\n", __func__, rnp->completed, (rnp->completed << RCU_SEQ_CTR_SHIFT) >> RCU_SEQ_CTR_SHIFT, rnp->gp_seq, rcu_seq_ctr(rnp->gp_seq)); - trace_rcu_grace_period(rsp->name, rsp->gpnum, TPS("start")); + trace_rcu_grace_period(rsp->name, rsp->gp_seq, TPS("start")); raw_spin_unlock_irq_rcu_node(rnp); /* @@ -1928,7 +1928,7 @@ static bool rcu_gp_init(struct rcu_state *rsp) if (rnp == rdp->mynode) (void)__note_gp_changes(rsp, rnp, rdp); rcu_preempt_boost_start_gp(rnp); - trace_rcu_grace_period_init(rsp->name, rnp->gpnum, + trace_rcu_grace_period_init(rsp->name, rnp->gp_seq, rnp->level, rnp->grplo, rnp->grphi, rnp->qsmask); raw_spin_unlock_irq_rcu_node(rnp); @@ -2048,7 +2048,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) /* Declare grace period done. */ WRITE_ONCE(rsp->completed, rsp->gpnum); rcu_seq_end(&rsp->gp_seq); - trace_rcu_grace_period(rsp->name, rsp->completed, TPS("end")); + trace_rcu_grace_period(rsp->name, rsp->gp_seq, TPS("end")); rsp->gp_state = RCU_GP_IDLE; /* Check for GP requests since above loop. */ rdp = this_cpu_ptr(rsp->rda); @@ -2061,7 +2061,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) if (!rcu_accelerate_cbs(rsp, rnp, rdp) && needgp) { WRITE_ONCE(rsp->gp_flags, RCU_GP_FLAG_INIT); rsp->gp_req_activity = jiffies; - trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum), + trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gp_seq), TPS("newreq")); } else { WRITE_ONCE(rsp->gp_flags, rsp->gp_flags & RCU_GP_FLAG_INIT); @@ -2087,7 +2087,7 @@ static int __noreturn rcu_gp_kthread(void *arg) /* Handle grace-period start. */ for (;;) { trace_rcu_grace_period(rsp->name, - READ_ONCE(rsp->gpnum), + READ_ONCE(rsp->gp_seq), TPS("reqwait")); rsp->gp_state = RCU_GP_WAIT_GPS; swait_event_idle(rsp->gp_wq, READ_ONCE(rsp->gp_flags) & @@ -2100,7 +2100,7 @@ static int __noreturn rcu_gp_kthread(void *arg) WRITE_ONCE(rsp->gp_activity, jiffies); WARN_ON(signal_pending(current)); trace_rcu_grace_period(rsp->name, - READ_ONCE(rsp->gpnum), + READ_ONCE(rsp->gp_seq), TPS("reqwaitsig")); } @@ -2119,7 +2119,7 @@ static int __noreturn rcu_gp_kthread(void *arg) jiffies + 3 * j); } trace_rcu_grace_period(rsp->name, - READ_ONCE(rsp->gpnum), + READ_ONCE(rsp->gp_seq), TPS("fqswait")); rsp->gp_state = RCU_GP_WAIT_FQS; ret = swait_event_idle_timeout(rsp->gp_wq, @@ -2134,12 +2134,12 @@ static int __noreturn rcu_gp_kthread(void *arg) if (ULONG_CMP_GE(jiffies, rsp->jiffies_force_qs) || (gf & RCU_GP_FLAG_FQS)) { trace_rcu_grace_period(rsp->name, - READ_ONCE(rsp->gpnum), + READ_ONCE(rsp->gp_seq), TPS("fqsstart")); rcu_gp_fqs(rsp, first_gp_fqs); first_gp_fqs = false; trace_rcu_grace_period(rsp->name, - READ_ONCE(rsp->gpnum), + READ_ONCE(rsp->gp_seq), TPS("fqsend")); cond_resched_tasks_rcu_qs(); WRITE_ONCE(rsp->gp_activity, jiffies); @@ -2158,7 +2158,7 @@ static int __noreturn rcu_gp_kthread(void *arg) WRITE_ONCE(rsp->gp_activity, jiffies); WARN_ON(signal_pending(current)); trace_rcu_grace_period(rsp->name, - READ_ONCE(rsp->gpnum), + READ_ONCE(rsp->gp_seq), TPS("fqswaitsig")); ret = 1; /* Keep old FQS timing. */ j = jiffies; @@ -2388,17 +2388,16 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp) */ static void rcu_cleanup_dying_cpu(struct rcu_state *rsp) { - RCU_TRACE(unsigned long mask;) + RCU_TRACE(bool blkd;) RCU_TRACE(struct rcu_data *rdp = this_cpu_ptr(rsp->rda);) RCU_TRACE(struct rcu_node *rnp = rdp->mynode;) if (!IS_ENABLED(CONFIG_HOTPLUG_CPU)) return; - RCU_TRACE(mask = rdp->grpmask;) - trace_rcu_grace_period(rsp->name, - rnp->gpnum + 1 - !!(rnp->qsmask & mask), - TPS("cpuofl")); + RCU_TRACE(blkd = !!(rnp->qsmask & rdp->grpmask);) + trace_rcu_grace_period(rsp->name, rnp->gp_seq, + blkd ? TPS("cpuofl") : TPS("cpuofl-bgp")); } /* @@ -3538,7 +3537,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp) rdp->core_needs_qs = false; rdp->rcu_iw_pending = false; rdp->rcu_iw_gp_seq = rnp->gp_seq - 1; - trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl")); + trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("cpuonl")); raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index ca73931f7b30..aca9d187c509 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -301,7 +301,7 @@ static void rcu_preempt_qs(void) RCU_LOCKDEP_WARN(preemptible(), "rcu_preempt_qs() invoked with preemption enabled!!!\n"); if (__this_cpu_read(rcu_data_p->cpu_no_qs.s)) { trace_rcu_grace_period(TPS("rcu_preempt"), - __this_cpu_read(rcu_data_p->gpnum), + __this_cpu_read(rcu_data_p->gp_seq), TPS("cpuqs")); __this_cpu_write(rcu_data_p->cpu_no_qs.b.norm, false); barrier(); /* Coordinate with rcu_preempt_check_callbacks(). */ -- cgit v1.2.3 From abd13fdd9516e5baae2257721b921684ecb090d3 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 1 May 2018 13:08:46 -0700 Subject: rcu: Convert rcu_future_grace_period tracepoint to gp_seq This commit makes the rcu_future_grace_period tracepoint use gp_seq instead of ->gpnum and ->completed. Signed-off-by: Paul E. McKenney --- include/trace/events/rcu.h | 22 +++++++++------------- kernel/rcu/tree.c | 7 +++---- 2 files changed, 12 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h index cd229e82ec8b..286047d22314 100644 --- a/include/trace/events/rcu.h +++ b/include/trace/events/rcu.h @@ -103,16 +103,14 @@ TRACE_EVENT(rcu_grace_period, */ TRACE_EVENT(rcu_future_grace_period, - TP_PROTO(const char *rcuname, unsigned long gpnum, unsigned long completed, - unsigned long c, u8 level, int grplo, int grphi, - const char *gpevent), + TP_PROTO(const char *rcuname, unsigned long gp_seq, unsigned long c, + u8 level, int grplo, int grphi, const char *gpevent), - TP_ARGS(rcuname, gpnum, completed, c, level, grplo, grphi, gpevent), + TP_ARGS(rcuname, gp_seq, c, level, grplo, grphi, gpevent), TP_STRUCT__entry( __field(const char *, rcuname) - __field(unsigned long, gpnum) - __field(unsigned long, completed) + __field(unsigned long, gp_seq) __field(unsigned long, c) __field(u8, level) __field(int, grplo) @@ -122,8 +120,7 @@ TRACE_EVENT(rcu_future_grace_period, TP_fast_assign( __entry->rcuname = rcuname; - __entry->gpnum = gpnum; - __entry->completed = completed; + __entry->gp_seq = gp_seq; __entry->c = c; __entry->level = level; __entry->grplo = grplo; @@ -131,10 +128,9 @@ TRACE_EVENT(rcu_future_grace_period, __entry->gpevent = gpevent; ), - TP_printk("%s %lu %lu %lu %u %d %d %s", - __entry->rcuname, __entry->gpnum, __entry->completed, - __entry->c, __entry->level, __entry->grplo, __entry->grphi, - __entry->gpevent) + TP_printk("%s %lu %lu %u %d %d %s", + __entry->rcuname, __entry->gp_seq, __entry->c, __entry->level, + __entry->grplo, __entry->grphi, __entry->gpevent) ); /* @@ -755,7 +751,7 @@ TRACE_EVENT(rcu_barrier, #else /* #ifdef CONFIG_RCU_TRACE */ #define trace_rcu_grace_period(rcuname, gp_seq, gpevent) do { } while (0) -#define trace_rcu_future_grace_period(rcuname, gpnum, completed, c, \ +#define trace_rcu_future_grace_period(rcuname, gp_seq, c, \ level, grplo, grphi, event) \ do { } while (0) #define trace_rcu_grace_period_init(rcuname, gpnum, level, grplo, grphi, \ diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 7ce85ad39af6..066dbaacec30 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -1552,9 +1552,8 @@ void rcu_cpu_stall_reset(void) static void trace_rcu_this_gp(struct rcu_node *rnp, struct rcu_data *rdp, unsigned long c, const char *s) { - trace_rcu_future_grace_period(rdp->rsp->name, rnp->gpnum, - rnp->completed, c, rnp->level, - rnp->grplo, rnp->grphi, s); + trace_rcu_future_grace_period(rdp->rsp->name, rnp->gp_seq, c, + rnp->level, rnp->grplo, rnp->grphi, s); } /* @@ -2053,7 +2052,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) /* Check for GP requests since above loop. */ rdp = this_cpu_ptr(rsp->rda); if (ULONG_CMP_LT(rnp->gp_seq, rnp->gp_seq_needed)) { - trace_rcu_this_gp(rnp, rdp, rsp->completed - 1, + trace_rcu_this_gp(rnp, rdp, rnp->gp_seq_needed, TPS("CleanupMore")); needgp = true; } -- cgit v1.2.3 From 63d86a7e85f84b8ac3b2f394570965aedbb03787 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 1 May 2018 13:08:46 -0700 Subject: rcu: Convert rcu_grace_period_init tracepoint to gp_seq This commit makes the rcu_grace_period_init tracepoint use gp_seq instead of ->gpnum. Signed-off-by: Paul E. McKenney --- include/trace/events/rcu.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h index 286047d22314..892016ad0647 100644 --- a/include/trace/events/rcu.h +++ b/include/trace/events/rcu.h @@ -142,14 +142,14 @@ TRACE_EVENT(rcu_future_grace_period, */ TRACE_EVENT(rcu_grace_period_init, - TP_PROTO(const char *rcuname, unsigned long gpnum, u8 level, + TP_PROTO(const char *rcuname, unsigned long gp_seq, u8 level, int grplo, int grphi, unsigned long qsmask), - TP_ARGS(rcuname, gpnum, level, grplo, grphi, qsmask), + TP_ARGS(rcuname, gp_seq, level, grplo, grphi, qsmask), TP_STRUCT__entry( __field(const char *, rcuname) - __field(unsigned long, gpnum) + __field(unsigned long, gp_seq) __field(u8, level) __field(int, grplo) __field(int, grphi) @@ -158,7 +158,7 @@ TRACE_EVENT(rcu_grace_period_init, TP_fast_assign( __entry->rcuname = rcuname; - __entry->gpnum = gpnum; + __entry->gp_seq = gp_seq; __entry->level = level; __entry->grplo = grplo; __entry->grphi = grphi; @@ -166,7 +166,7 @@ TRACE_EVENT(rcu_grace_period_init, ), TP_printk("%s %lu %u %d %d %lx", - __entry->rcuname, __entry->gpnum, __entry->level, + __entry->rcuname, __entry->gp_seq, __entry->level, __entry->grplo, __entry->grphi, __entry->qsmask) ); @@ -754,7 +754,7 @@ TRACE_EVENT(rcu_barrier, #define trace_rcu_future_grace_period(rcuname, gp_seq, c, \ level, grplo, grphi, event) \ do { } while (0) -#define trace_rcu_grace_period_init(rcuname, gpnum, level, grplo, grphi, \ +#define trace_rcu_grace_period_init(rcuname, gp_seq, level, grplo, grphi, \ qsmask) do { } while (0) #define trace_rcu_exp_grace_period(rcuname, gqseq, gpevent) \ do { } while (0) -- cgit v1.2.3 From 598ce09480efb6b48799df60c66bac70bea5ef54 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 1 May 2018 13:35:20 -0700 Subject: rcu: Convert rcu_preempt_task tracepoint to ->gp_seq This commit makes the rcu_preempt_task tracepoint use ->gp_seq instead of ->gpnum. Signed-off-by: Paul E. McKenney --- include/trace/events/rcu.h | 12 ++++++------ kernel/rcu/tree_plugin.h | 4 ++-- 2 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h index 892016ad0647..38dbd97d65a3 100644 --- a/include/trace/events/rcu.h +++ b/include/trace/events/rcu.h @@ -298,24 +298,24 @@ TRACE_EVENT(rcu_nocb_wake, */ TRACE_EVENT(rcu_preempt_task, - TP_PROTO(const char *rcuname, int pid, unsigned long gpnum), + TP_PROTO(const char *rcuname, int pid, unsigned long gp_seq), - TP_ARGS(rcuname, pid, gpnum), + TP_ARGS(rcuname, pid, gp_seq), TP_STRUCT__entry( __field(const char *, rcuname) - __field(unsigned long, gpnum) + __field(unsigned long, gp_seq) __field(int, pid) ), TP_fast_assign( __entry->rcuname = rcuname; - __entry->gpnum = gpnum; + __entry->gp_seq = gp_seq; __entry->pid = pid; ), TP_printk("%s %lu %d", - __entry->rcuname, __entry->gpnum, __entry->pid) + __entry->rcuname, __entry->gp_seq, __entry->pid) ); /* @@ -761,7 +761,7 @@ TRACE_EVENT(rcu_barrier, #define trace_rcu_exp_funnel_lock(rcuname, level, grplo, grphi, gpevent) \ do { } while (0) #define trace_rcu_nocb_wake(rcuname, cpu, reason) do { } while (0) -#define trace_rcu_preempt_task(rcuname, pid, gpnum) do { } while (0) +#define trace_rcu_preempt_task(rcuname, pid, gp_seq) do { } while (0) #define trace_rcu_unlock_preempted_task(rcuname, gpnum, pid) do { } while (0) #define trace_rcu_quiescent_state_report(rcuname, gpnum, mask, qsmask, level, \ grplo, grphi, gp_tasks) do { } \ diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index aca9d187c509..02ca3b4e6a8f 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -350,8 +350,8 @@ static void rcu_preempt_note_context_switch(bool preempt) trace_rcu_preempt_task(rdp->rsp->name, t->pid, (rnp->qsmask & rdp->grpmask) - ? rnp->gpnum - : rnp->gpnum + 1); + ? rnp->gp_seq + : rcu_seq_snap(&rnp->gp_seq)); rcu_preempt_ctxt_queue(rnp, rdp); } else if (t->rcu_read_lock_nesting < 0 && t->rcu_read_unlock_special.s) { -- cgit v1.2.3 From 865aa1e08d8aefdfd1f5d30ecfce1b8ef8cd520a Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 1 May 2018 13:35:20 -0700 Subject: rcu: Convert rcu_unlock_preempted_task tracepoint to ->gp_seq This commit makes the rcu_unlock_preempted_task tracepoint use ->gp_seq instead of ->gpnum. Signed-off-by: Paul E. McKenney --- include/trace/events/rcu.h | 12 ++++++------ kernel/rcu/tree_plugin.h | 4 ++-- 2 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h index 38dbd97d65a3..95b7491196aa 100644 --- a/include/trace/events/rcu.h +++ b/include/trace/events/rcu.h @@ -325,23 +325,23 @@ TRACE_EVENT(rcu_preempt_task, */ TRACE_EVENT(rcu_unlock_preempted_task, - TP_PROTO(const char *rcuname, unsigned long gpnum, int pid), + TP_PROTO(const char *rcuname, unsigned long gp_seq, int pid), - TP_ARGS(rcuname, gpnum, pid), + TP_ARGS(rcuname, gp_seq, pid), TP_STRUCT__entry( __field(const char *, rcuname) - __field(unsigned long, gpnum) + __field(unsigned long, gp_seq) __field(int, pid) ), TP_fast_assign( __entry->rcuname = rcuname; - __entry->gpnum = gpnum; + __entry->gp_seq = gp_seq; __entry->pid = pid; ), - TP_printk("%s %lu %d", __entry->rcuname, __entry->gpnum, __entry->pid) + TP_printk("%s %lu %d", __entry->rcuname, __entry->gp_seq, __entry->pid) ); /* @@ -762,7 +762,7 @@ TRACE_EVENT(rcu_barrier, do { } while (0) #define trace_rcu_nocb_wake(rcuname, cpu, reason) do { } while (0) #define trace_rcu_preempt_task(rcuname, pid, gp_seq) do { } while (0) -#define trace_rcu_unlock_preempted_task(rcuname, gpnum, pid) do { } while (0) +#define trace_rcu_unlock_preempted_task(rcuname, gp_seq, pid) do { } while (0) #define trace_rcu_quiescent_state_report(rcuname, gpnum, mask, qsmask, level, \ grplo, grphi, gp_tasks) do { } \ while (0) diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 02ca3b4e6a8f..a10b0e26ce19 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -545,7 +545,7 @@ void rcu_read_unlock_special(struct task_struct *t) list_del_init(&t->rcu_node_entry); t->rcu_blocked_node = NULL; trace_rcu_unlock_preempted_task(TPS("rcu_preempt"), - rnp->gpnum, t->pid); + rnp->gp_seq, t->pid); if (&t->rcu_node_entry == rnp->gp_tasks) rnp->gp_tasks = np; if (&t->rcu_node_entry == rnp->exp_tasks) @@ -708,7 +708,7 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp) t = container_of(rnp->gp_tasks, struct task_struct, rcu_node_entry); trace_rcu_unlock_preempted_task(TPS("rcu_preempt-GPS"), - rnp->gpnum, t->pid); + rnp->gp_seq, t->pid); } WARN_ON_ONCE(rnp->qsmask); } -- cgit v1.2.3 From db023296f0115d2fe01fdabad54678f2b806da23 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 1 May 2018 13:35:20 -0700 Subject: rcu: Convert rcu_quiescent_state_report tracepoint to ->gp_seq This commit makes the rcu_quiescent_state_report tracepoint use ->gp_seq instead of ->gpnum. Signed-off-by: Paul E. McKenney --- include/trace/events/rcu.h | 12 ++++++------ kernel/rcu/tree.c | 2 +- kernel/rcu/tree_plugin.h | 2 +- 3 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h index 95b7491196aa..ac4d9d4a1ebf 100644 --- a/include/trace/events/rcu.h +++ b/include/trace/events/rcu.h @@ -354,15 +354,15 @@ TRACE_EVENT(rcu_unlock_preempted_task, */ TRACE_EVENT(rcu_quiescent_state_report, - TP_PROTO(const char *rcuname, unsigned long gpnum, + TP_PROTO(const char *rcuname, unsigned long gp_seq, unsigned long mask, unsigned long qsmask, u8 level, int grplo, int grphi, int gp_tasks), - TP_ARGS(rcuname, gpnum, mask, qsmask, level, grplo, grphi, gp_tasks), + TP_ARGS(rcuname, gp_seq, mask, qsmask, level, grplo, grphi, gp_tasks), TP_STRUCT__entry( __field(const char *, rcuname) - __field(unsigned long, gpnum) + __field(unsigned long, gp_seq) __field(unsigned long, mask) __field(unsigned long, qsmask) __field(u8, level) @@ -373,7 +373,7 @@ TRACE_EVENT(rcu_quiescent_state_report, TP_fast_assign( __entry->rcuname = rcuname; - __entry->gpnum = gpnum; + __entry->gp_seq = gp_seq; __entry->mask = mask; __entry->qsmask = qsmask; __entry->level = level; @@ -383,7 +383,7 @@ TRACE_EVENT(rcu_quiescent_state_report, ), TP_printk("%s %lu %lx>%lx %u %d %d %u", - __entry->rcuname, __entry->gpnum, + __entry->rcuname, __entry->gp_seq, __entry->mask, __entry->qsmask, __entry->level, __entry->grplo, __entry->grphi, __entry->gp_tasks) ); @@ -763,7 +763,7 @@ TRACE_EVENT(rcu_barrier, #define trace_rcu_nocb_wake(rcuname, cpu, reason) do { } while (0) #define trace_rcu_preempt_task(rcuname, pid, gp_seq) do { } while (0) #define trace_rcu_unlock_preempted_task(rcuname, gp_seq, pid) do { } while (0) -#define trace_rcu_quiescent_state_report(rcuname, gpnum, mask, qsmask, level, \ +#define trace_rcu_quiescent_state_report(rcuname, gp_seq, mask, qsmask, level, \ grplo, grphi, gp_tasks) do { } \ while (0) #define trace_rcu_fqs(rcuname, gpnum, cpu, qsevent) do { } while (0) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 066dbaacec30..7c6c11d5479c 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -2229,7 +2229,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, WARN_ON_ONCE(!rcu_is_leaf_node(rnp) && rcu_preempt_blocked_readers_cgp(rnp)); rnp->qsmask &= ~mask; - trace_rcu_quiescent_state_report(rsp->name, rnp->gpnum, + trace_rcu_quiescent_state_report(rsp->name, rnp->gp_seq, mask, rnp->qsmask, rnp->level, rnp->grplo, rnp->grphi, !!rnp->gp_tasks); diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index a10b0e26ce19..c8a2c7760121 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -566,7 +566,7 @@ void rcu_read_unlock_special(struct task_struct *t) empty_exp_now = sync_rcu_preempt_exp_done(rnp); if (!empty_norm && !rcu_preempt_blocked_readers_cgp(rnp)) { trace_rcu_quiescent_state_report(TPS("preempt_rcu"), - rnp->gpnum, + rnp->gp_seq, 0, rnp->qsmask, rnp->level, rnp->grplo, -- cgit v1.2.3 From fee5997c17562e95fb1fecc142efb2da0934baa4 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 1 May 2018 13:35:20 -0700 Subject: rcu: Convert rcu_fqs tracepoint to ->gp_seq This commit makes the rcu_fqs tracepoint use ->gp_seq instead of ->gpnum. Signed-off-by: Paul E. McKenney --- include/trace/events/rcu.h | 12 ++++++------ kernel/rcu/tree.c | 8 ++++---- 2 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h index ac4d9d4a1ebf..7d3650cc9d30 100644 --- a/include/trace/events/rcu.h +++ b/include/trace/events/rcu.h @@ -398,26 +398,26 @@ TRACE_EVENT(rcu_quiescent_state_report, */ TRACE_EVENT(rcu_fqs, - TP_PROTO(const char *rcuname, unsigned long gpnum, int cpu, const char *qsevent), + TP_PROTO(const char *rcuname, unsigned long gp_seq, int cpu, const char *qsevent), - TP_ARGS(rcuname, gpnum, cpu, qsevent), + TP_ARGS(rcuname, gp_seq, cpu, qsevent), TP_STRUCT__entry( __field(const char *, rcuname) - __field(unsigned long, gpnum) + __field(unsigned long, gp_seq) __field(int, cpu) __field(const char *, qsevent) ), TP_fast_assign( __entry->rcuname = rcuname; - __entry->gpnum = gpnum; + __entry->gp_seq = gp_seq; __entry->cpu = cpu; __entry->qsevent = qsevent; ), TP_printk("%s %lu %d %s", - __entry->rcuname, __entry->gpnum, + __entry->rcuname, __entry->gp_seq, __entry->cpu, __entry->qsevent) ); @@ -766,7 +766,7 @@ TRACE_EVENT(rcu_barrier, #define trace_rcu_quiescent_state_report(rcuname, gp_seq, mask, qsmask, level, \ grplo, grphi, gp_tasks) do { } \ while (0) -#define trace_rcu_fqs(rcuname, gpnum, cpu, qsevent) do { } while (0) +#define trace_rcu_fqs(rcuname, gp_seq, cpu, qsevent) do { } while (0) #define trace_rcu_dyntick(polarity, oldnesting, newnesting, dyntick) do { } while (0) #define trace_rcu_callback(rcuname, rhp, qlen_lazy, qlen) do { } while (0) #define trace_rcu_kfree_callback(rcuname, rhp, offset, qlen_lazy, qlen) \ diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 7c6c11d5479c..42e89d4f1e33 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -1111,7 +1111,7 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp) { rdp->dynticks_snap = rcu_dynticks_snap(rdp->dynticks); if (rcu_dynticks_in_eqs(rdp->dynticks_snap)) { - trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti")); + trace_rcu_fqs(rdp->rsp->name, rdp->gp_seq, rdp->cpu, TPS("dti")); rcu_gpnum_ovf(rdp->mynode, rdp); return 1; } @@ -1161,7 +1161,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) * of the current RCU grace period. */ if (rcu_dynticks_in_eqs_since(rdp->dynticks, rdp->dynticks_snap)) { - trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti")); + trace_rcu_fqs(rdp->rsp->name, rdp->gp_seq, rdp->cpu, TPS("dti")); rdp->dynticks_fqs++; rcu_gpnum_ovf(rnp, rdp); return 1; @@ -1178,7 +1178,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) if (time_after(jiffies, rdp->rsp->gp_start + jtsq) && READ_ONCE(rdp->rcu_qs_ctr_snap) != per_cpu(rcu_dynticks.rcu_qs_ctr, rdp->cpu) && rcu_seq_current(&rdp->gp_seq) == rnp->gp_seq && !rdp->gpwrap) { - trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("rqc")); + trace_rcu_fqs(rdp->rsp->name, rdp->gp_seq, rdp->cpu, TPS("rqc")); rcu_gpnum_ovf(rnp, rdp); return 1; } else if (time_after(jiffies, rdp->rsp->gp_start + jtsq)) { @@ -1188,7 +1188,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) /* Check for the CPU being offline. */ if (!(rdp->grpmask & rcu_rnp_online_cpus(rnp))) { - trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("ofl")); + trace_rcu_fqs(rdp->rsp->name, rdp->gp_seq, rdp->cpu, TPS("ofl")); rdp->offline_fqs++; rcu_gpnum_ovf(rnp, rdp); return 1; -- cgit v1.2.3 From a2165e416878b325747f871df4b236b49bf61486 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sat, 12 May 2018 07:42:20 -0700 Subject: rcu: Don't funnel-lock above leaf node if GP in progress The old grace-period start code would acquire only the leaf's rcu_node structure's ->lock if that structure believed that a grace period was in progress. The new code advances to the leaf's parent in this case, needlessly acquiring then leaf's parent's ->lock. This commit therefore checks the grace-period state after marking the leaf with the need for the specified grace period, and if the leaf believes that a grace period is in progress, takes an early exit. Reported-by: Joel Fernandes Signed-off-by: Paul E. McKenney [ paulmck: Add "Startedleaf" tracing as suggested by Joel Fernandes. ] --- include/trace/events/rcu.h | 4 ++-- kernel/rcu/tree.c | 9 +++++++++ 2 files changed, 11 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h index 7d3650cc9d30..5ab1df0a2801 100644 --- a/include/trace/events/rcu.h +++ b/include/trace/events/rcu.h @@ -91,8 +91,8 @@ TRACE_EVENT(rcu_grace_period, * * "Startleaf": Request a grace period based on leaf-node data. * "Prestarted": Someone beat us to the request - * "Startedleaf": Leaf-node start proved sufficient. - * "Startedleafroot": Leaf-node start proved sufficient after checking root. + * "Startedleaf": Leaf node marked for future GP. + * "Startedleafroot": All nodes from leaf to root marked for future GP. * "Startedroot": Requested a nocb grace period based on root-node data. * "NoGPkthread": The RCU grace-period kthread has not yet started. * "StartWait": Start waiting for the requested grace period. diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 5643c135fb06..24a79e85b81f 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -1590,6 +1590,15 @@ static bool rcu_start_this_gp(struct rcu_node *rnp, struct rcu_data *rdp, goto unlock_out; } rnp_root->gp_seq_needed = c; + if (rcu_seq_state(rcu_seq_current(&rnp->gp_seq))) { + /* + * We just marked the leaf, and a grace period + * is in progress, which means that rcu_gp_cleanup() + * will see the marking. Bail to reduce contention. + */ + trace_rcu_this_gp(rnp, rdp, c, TPS("Startedleaf")); + goto unlock_out; + } if (rnp_root != rnp && rnp_root->parent != NULL) raw_spin_unlock_rcu_node(rnp_root); if (!rnp_root->parent) -- cgit v1.2.3 From b73de91d6a4c97ed586b2a5a6ce7c6fe395d9a3b Mon Sep 17 00:00:00 2001 From: Joel Fernandes Date: Sun, 20 May 2018 21:42:18 -0700 Subject: rcu: Rename the grace-period-request variables and parameters The name 'c' is used for variables and parameters holding the requested grace-period sequence number. However it is no longer very meaningful given the conversions from ->gpnum and (especially) ->completed to ->gp_seq. This commit therefore renames 'c' to 'gp_seq_req'. Previous patch discussion is at: https://patchwork.kernel.org/patch/10396579/ Signed-off-by: Joel Fernandes Signed-off-by: Paul E. McKenney --- include/trace/events/rcu.h | 15 ++++++++------- kernel/rcu/tree.c | 46 +++++++++++++++++++++++++++------------------- 2 files changed, 35 insertions(+), 26 deletions(-) (limited to 'include') diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h index 5ab1df0a2801..759e7e83733d 100644 --- a/include/trace/events/rcu.h +++ b/include/trace/events/rcu.h @@ -103,15 +103,16 @@ TRACE_EVENT(rcu_grace_period, */ TRACE_EVENT(rcu_future_grace_period, - TP_PROTO(const char *rcuname, unsigned long gp_seq, unsigned long c, - u8 level, int grplo, int grphi, const char *gpevent), + TP_PROTO(const char *rcuname, unsigned long gp_seq, + unsigned long gp_seq_req, u8 level, int grplo, int grphi, + const char *gpevent), - TP_ARGS(rcuname, gp_seq, c, level, grplo, grphi, gpevent), + TP_ARGS(rcuname, gp_seq, gp_seq_req, level, grplo, grphi, gpevent), TP_STRUCT__entry( __field(const char *, rcuname) __field(unsigned long, gp_seq) - __field(unsigned long, c) + __field(unsigned long, gp_seq_req) __field(u8, level) __field(int, grplo) __field(int, grphi) @@ -121,7 +122,7 @@ TRACE_EVENT(rcu_future_grace_period, TP_fast_assign( __entry->rcuname = rcuname; __entry->gp_seq = gp_seq; - __entry->c = c; + __entry->gp_seq_req = gp_seq_req; __entry->level = level; __entry->grplo = grplo; __entry->grphi = grphi; @@ -129,7 +130,7 @@ TRACE_EVENT(rcu_future_grace_period, ), TP_printk("%s %lu %lu %u %d %d %s", - __entry->rcuname, __entry->gp_seq, __entry->c, __entry->level, + __entry->rcuname, __entry->gp_seq, __entry->gp_seq_req, __entry->level, __entry->grplo, __entry->grphi, __entry->gpevent) ); @@ -751,7 +752,7 @@ TRACE_EVENT(rcu_barrier, #else /* #ifdef CONFIG_RCU_TRACE */ #define trace_rcu_grace_period(rcuname, gp_seq, gpevent) do { } while (0) -#define trace_rcu_future_grace_period(rcuname, gp_seq, c, \ +#define trace_rcu_future_grace_period(rcuname, gp_seq, gp_seq_req, \ level, grplo, grphi, event) \ do { } while (0) #define trace_rcu_grace_period_init(rcuname, gp_seq, level, grplo, grphi, \ diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 161e8fb8b83f..8c31b1740afc 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -1546,13 +1546,18 @@ void rcu_cpu_stall_reset(void) /* Trace-event wrapper function for trace_rcu_future_grace_period. */ static void trace_rcu_this_gp(struct rcu_node *rnp, struct rcu_data *rdp, - unsigned long c, const char *s) + unsigned long gp_seq_req, const char *s) { - trace_rcu_future_grace_period(rdp->rsp->name, rnp->gp_seq, c, + trace_rcu_future_grace_period(rdp->rsp->name, rnp->gp_seq, gp_seq_req, rnp->level, rnp->grplo, rnp->grphi, s); } /* + * rcu_start_this_gp - Request the start of a particular grace period + * @rnp: The leaf node of the CPU from which to start. + * @rdp: The rcu_data corresponding to the CPU from which to start. + * @gp_seq_req: The gp_seq of the grace period to start. + * * Start the specified grace period, as needed to handle newly arrived * callbacks. The required future grace periods are recorded in each * rcu_node structure's ->gp_seq_needed field. Returns true if there @@ -1560,9 +1565,11 @@ static void trace_rcu_this_gp(struct rcu_node *rnp, struct rcu_data *rdp, * * The caller must hold the specified rcu_node structure's ->lock, which * is why the caller is responsible for waking the grace-period kthread. + * + * Returns true if the GP thread needs to be awakened else false. */ static bool rcu_start_this_gp(struct rcu_node *rnp, struct rcu_data *rdp, - unsigned long c) + unsigned long gp_seq_req) { bool ret = false; struct rcu_state *rsp = rdp->rsp; @@ -1578,25 +1585,27 @@ static bool rcu_start_this_gp(struct rcu_node *rnp, struct rcu_data *rdp, * not be released. */ raw_lockdep_assert_held_rcu_node(rnp); - trace_rcu_this_gp(rnp, rdp, c, TPS("Startleaf")); + trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("Startleaf")); for (rnp_root = rnp; 1; rnp_root = rnp_root->parent) { if (rnp_root != rnp) raw_spin_lock_rcu_node(rnp_root); - if (ULONG_CMP_GE(rnp_root->gp_seq_needed, c) || - rcu_seq_started(&rnp_root->gp_seq, c) || + if (ULONG_CMP_GE(rnp_root->gp_seq_needed, gp_seq_req) || + rcu_seq_started(&rnp_root->gp_seq, gp_seq_req) || (rnp != rnp_root && rcu_seq_state(rcu_seq_current(&rnp_root->gp_seq)))) { - trace_rcu_this_gp(rnp_root, rdp, c, TPS("Prestarted")); + trace_rcu_this_gp(rnp_root, rdp, gp_seq_req, + TPS("Prestarted")); goto unlock_out; } - rnp_root->gp_seq_needed = c; + rnp_root->gp_seq_needed = gp_seq_req; if (rcu_seq_state(rcu_seq_current(&rnp->gp_seq))) { /* * We just marked the leaf, and a grace period * is in progress, which means that rcu_gp_cleanup() * will see the marking. Bail to reduce contention. */ - trace_rcu_this_gp(rnp, rdp, c, TPS("Startedleaf")); + trace_rcu_this_gp(rnp, rdp, gp_seq_req, + TPS("Startedleaf")); goto unlock_out; } if (rnp_root != rnp && rnp_root->parent != NULL) @@ -1607,21 +1616,21 @@ static bool rcu_start_this_gp(struct rcu_node *rnp, struct rcu_data *rdp, /* If GP already in progress, just leave, otherwise start one. */ if (rcu_gp_in_progress(rsp)) { - trace_rcu_this_gp(rnp_root, rdp, c, TPS("Startedleafroot")); + trace_rcu_this_gp(rnp_root, rdp, gp_seq_req, TPS("Startedleafroot")); goto unlock_out; } - trace_rcu_this_gp(rnp_root, rdp, c, TPS("Startedroot")); + trace_rcu_this_gp(rnp_root, rdp, gp_seq_req, TPS("Startedroot")); WRITE_ONCE(rsp->gp_flags, rsp->gp_flags | RCU_GP_FLAG_INIT); rsp->gp_req_activity = jiffies; if (!rsp->gp_kthread) { - trace_rcu_this_gp(rnp_root, rdp, c, TPS("NoGPkthread")); + trace_rcu_this_gp(rnp_root, rdp, gp_seq_req, TPS("NoGPkthread")); goto unlock_out; } trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gp_seq), TPS("newreq")); ret = true; /* Caller must wake GP kthread. */ unlock_out: /* Push furthest requested GP to leaf node and rcu_data structure. */ - if (ULONG_CMP_LT(c, rnp_root->gp_seq_needed)) { + if (ULONG_CMP_LT(gp_seq_req, rnp_root->gp_seq_needed)) { rnp->gp_seq_needed = rnp_root->gp_seq_needed; rdp->gp_seq_needed = rnp_root->gp_seq_needed; } @@ -1636,14 +1645,13 @@ unlock_out: */ static bool rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) { - unsigned long c = rnp->gp_seq; bool needmore; struct rcu_data *rdp = this_cpu_ptr(rsp->rda); needmore = ULONG_CMP_LT(rnp->gp_seq, rnp->gp_seq_needed); if (!needmore) rnp->gp_seq_needed = rnp->gp_seq; /* Avoid counter wrap. */ - trace_rcu_this_gp(rnp, rdp, c, + trace_rcu_this_gp(rnp, rdp, rnp->gp_seq, needmore ? TPS("CleanupMore") : TPS("Cleanup")); return needmore; } @@ -1679,7 +1687,7 @@ static void rcu_gp_kthread_wake(struct rcu_state *rsp) static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp) { - unsigned long c; + unsigned long gp_seq_req; bool ret = false; raw_lockdep_assert_held_rcu_node(rnp); @@ -1698,9 +1706,9 @@ static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp, * accelerating callback invocation to an earlier grace-period * number. */ - c = rcu_seq_snap(&rsp->gp_seq); - if (rcu_segcblist_accelerate(&rdp->cblist, c)) - ret = rcu_start_this_gp(rnp, rdp, c); + gp_seq_req = rcu_seq_snap(&rsp->gp_seq); + if (rcu_segcblist_accelerate(&rdp->cblist, gp_seq_req)) + ret = rcu_start_this_gp(rnp, rdp, gp_seq_req); /* Trace depending on how much we were able to accelerate. */ if (rcu_segcblist_restempty(&rdp->cblist, RCU_WAIT_TAIL)) -- cgit v1.2.3 From e05121ba5b81e2f85349f038642410578457f6db Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 7 May 2018 12:07:48 -0700 Subject: rcu: Remove CPU-hotplug failsafe from force-quiescent-state code path Now that quiescent states for newly offlined CPUs are reported either when that CPU goes offline or at the end of grace-period initialization, the CPU-hotplug failsafe in the force-quiescent-state code path is no longer needed. This commit therefore removes this failsafe. Signed-off-by: Paul E. McKenney --- include/trace/events/rcu.h | 10 +++++----- kernel/rcu/tree.c | 9 +-------- kernel/rcu/tree.h | 1 - 3 files changed, 6 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h index 759e7e83733d..a8d07feff6a0 100644 --- a/include/trace/events/rcu.h +++ b/include/trace/events/rcu.h @@ -391,11 +391,11 @@ TRACE_EVENT(rcu_quiescent_state_report, /* * Tracepoint for quiescent states detected by force_quiescent_state(). - * These trace events include the type of RCU, the grace-period number that - * was blocked by the CPU, the CPU itself, and the type of quiescent state, - * which can be "dti" for dyntick-idle mode, "ofl" for CPU offline, "kick" - * when kicking a CPU that has been in dyntick-idle mode for too long, or - * "rqc" if the CPU got a quiescent state via its rcu_qs_ctr. + * These trace events include the type of RCU, the grace-period number + * that was blocked by the CPU, the CPU itself, and the type of quiescent + * state, which can be "dti" for dyntick-idle mode, "kick" when kicking + * a CPU that has been in dyntick-idle mode for too long, or "rqc" if the + * CPU got a quiescent state via its rcu_qs_ctr. */ TRACE_EVENT(rcu_fqs, diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 770f0df54015..5f1a11f1f7bc 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -1188,14 +1188,6 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) smp_store_release(ruqp, true); } - /* Check for the CPU being offline. */ - if (!(rdp->grpmask & rcu_rnp_online_cpus(rnp))) { - trace_rcu_fqs(rdp->rsp->name, rdp->gp_seq, rdp->cpu, TPS("ofl")); - rdp->offline_fqs++; - rcu_gpnum_ovf(rnp, rdp); - return 1; - } - /* * A CPU running for an extended time within the kernel can * delay RCU grace periods. When the CPU is in NO_HZ_FULL mode, @@ -3718,6 +3710,7 @@ void rcu_cpu_starting(unsigned int cpu) nbits = bitmap_weight(&oldmask, BITS_PER_LONG); /* Allow lockless access for expedited grace periods. */ smp_store_release(&rsp->ncpus, rsp->ncpus + nbits); /* ^^^ */ + rcu_gpnum_ovf(rnp, rdp); /* Offline-induced counter wrap? */ if (rnp->qsmask & mask) { /* RCU waiting on incoming CPU? */ /* Report QS -after- changing ->qsmaskinitnext! */ rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags); diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 6683da6e4ecc..795d469c6f67 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -217,7 +217,6 @@ struct rcu_data { /* 4) reasons this CPU needed to be kicked by force_quiescent_state */ unsigned long dynticks_fqs; /* Kicked due to dynticks idle. */ - unsigned long offline_fqs; /* Kicked due to being offline. */ unsigned long cond_resched_completed; /* Grace period that needs help */ /* from cond_resched(). */ -- cgit v1.2.3 From 3949fa9bac090ad217534c30bc3b6572289abf21 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 8 May 2018 15:29:10 -0700 Subject: rcu: Make rcu_read_unlock_special() static Because rcu_read_unlock_special() is no longer used outside of kernel/rcu/tree_plugin.h, this commit makes it static. Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 1 - kernel/rcu/tree_plugin.h | 3 ++- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 65163aa0bb04..67ec077c7ee5 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -64,7 +64,6 @@ void rcu_barrier_tasks(void); void __rcu_read_lock(void); void __rcu_read_unlock(void); -void rcu_read_unlock_special(struct task_struct *t); void synchronize_rcu(void); /* diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 613372246a07..54a251640f53 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -127,6 +127,7 @@ static struct rcu_data __percpu *const rcu_data_p = &rcu_preempt_data; static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, bool wake); +static void rcu_read_unlock_special(struct task_struct *t); /* * Tell them what RCU they are running. @@ -461,7 +462,7 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp) * notify RCU core processing or task having blocked during the RCU * read-side critical section. */ -void rcu_read_unlock_special(struct task_struct *t) +static void rcu_read_unlock_special(struct task_struct *t) { bool empty_exp; bool empty_norm; -- cgit v1.2.3 From 07f27570dcd148a5f4de7dc3513c1d1cd069b362 Mon Sep 17 00:00:00 2001 From: Byungchul Park Date: Fri, 11 May 2018 17:30:34 +0900 Subject: rcu: Improve rcu_note_voluntary_context_switch() reporting We expect a quiescent state of TASKS_RCU when cond_resched_tasks_rcu_qs() is called, no matter whether it actually be scheduled or not. However, it currently doesn't report the quiescent state when the task enters into __schedule() as it's called with preempt = true. So make it report the quiescent state unconditionally when cond_resched_tasks_rcu_qs() is called. And in TINY_RCU, even though the quiescent state of rcu_bh also should be reported when the tick interrupt comes from user, it doesn't. So make it reported. Lastly in TREE_RCU, rcu_note_voluntary_context_switch() should be reported when the tick interrupt comes from not only user but also idle, as an extended quiescent state. Signed-off-by: Byungchul Park Signed-off-by: Paul E. McKenney [ paulmck: Simplify rcutiny portion given no RCU-tasks for !PREEMPT. ] --- include/linux/rcupdate.h | 4 ++-- kernel/rcu/tiny.c | 4 +--- kernel/rcu/tree.c | 4 ++-- 3 files changed, 5 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 67ec077c7ee5..5cab15e7ec83 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -194,8 +194,8 @@ static inline void exit_tasks_rcu_finish(void) { } */ #define cond_resched_tasks_rcu_qs() \ do { \ - if (!cond_resched()) \ - rcu_note_voluntary_context_switch_lite(current); \ + rcu_note_voluntary_context_switch_lite(current); \ + cond_resched(); \ } while (0) /* diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c index a64eee0db39e..befc9321a89c 100644 --- a/kernel/rcu/tiny.c +++ b/kernel/rcu/tiny.c @@ -122,10 +122,8 @@ void rcu_check_callbacks(int user) { if (user) rcu_sched_qs(); - else if (!in_softirq()) + if (user || !in_softirq()) rcu_bh_qs(); - if (user) - rcu_note_voluntary_context_switch(current); } /* diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index d3333ee2c6f5..19beabe73629 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -2645,6 +2645,7 @@ void rcu_check_callbacks(int user) rcu_sched_qs(); rcu_bh_qs(); + rcu_note_voluntary_context_switch(current); } else if (!in_softirq()) { @@ -2660,8 +2661,7 @@ void rcu_check_callbacks(int user) rcu_preempt_check_callbacks(); if (rcu_pending()) invoke_rcu_core(); - if (user) - rcu_note_voluntary_context_switch(current); + trace_rcu_utilization(TPS("End scheduler-tick")); } -- cgit v1.2.3 From 1445e9175bead409bb9930f3c745246a09f22cf6 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 7 May 2018 06:35:46 -0300 Subject: rcu: rcupdate.h: Get rid of Sphinx warnings at rcu_pointer_handoff() The code example at rcupdate.h currently produce lots of warnings: ./include/linux/rcupdate.h:572: WARNING: Unexpected indentation. ./include/linux/rcupdate.h:576: WARNING: Unexpected indentation. ./include/linux/rcupdate.h:580: WARNING: Block quote ends without a blank line; unexpected unindent. ./include/linux/rcupdate.h:582: WARNING: Block quote ends without a blank line; unexpected unindent. ./include/linux/rcupdate.h:582: WARNING: Inline literal start-string without end-string. This commit therefore changes it to a code-block. Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 5cab15e7ec83..dacc90358b33 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -566,8 +566,8 @@ static inline void rcu_preempt_sleep_check(void) { } * This is simply an identity function, but it documents where a pointer * is handed off from RCU to some other synchronization mechanism, for * example, reference counting or locking. In C11, it would map to - * kill_dependency(). It could be used as follows: - * `` + * kill_dependency(). It could be used as follows:: + * * rcu_read_lock(); * p = rcu_dereference(gp); * long_lived = is_long_lived(p); @@ -578,7 +578,6 @@ static inline void rcu_preempt_sleep_check(void) { } * p = rcu_pointer_handoff(p); * } * rcu_read_unlock(); - *`` */ #define rcu_pointer_handoff(p) (p) -- cgit v1.2.3 From 6f56f714db067056c80f5d71510118f82872e34c Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 14 May 2018 13:52:27 -0700 Subject: rcu: Improve RCU-tasks naming and comments The naming and comments associated with some RCU-tasks code make the faulty assumption that context switches due to cond_resched() are voluntary. As several people pointed out, this is not the case. This commit therefore updates function names and comments to better reflect current reality. Reported-by: Byungchul Park Reported-by: Joel Fernandes Reported-by: Steven Rostedt Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 12 ++++++------ include/linux/rcutiny.h | 2 +- kernel/rcu/tree.c | 2 +- kernel/rcu/update.c | 27 ++++++++++++++------------- 4 files changed, 22 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index dacc90358b33..75e5b393cf44 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -158,11 +158,11 @@ static inline void rcu_init_nohz(void) { } } while (0) /* - * Note a voluntary context switch for RCU-tasks benefit. This is a - * macro rather than an inline function to avoid #include hell. + * Note a quasi-voluntary context switch for RCU-tasks's benefit. + * This is a macro rather than an inline function to avoid #include hell. */ #ifdef CONFIG_TASKS_RCU -#define rcu_note_voluntary_context_switch_lite(t) \ +#define rcu_tasks_qs(t) \ do { \ if (READ_ONCE((t)->rcu_tasks_holdout)) \ WRITE_ONCE((t)->rcu_tasks_holdout, false); \ @@ -170,14 +170,14 @@ static inline void rcu_init_nohz(void) { } #define rcu_note_voluntary_context_switch(t) \ do { \ rcu_all_qs(); \ - rcu_note_voluntary_context_switch_lite(t); \ + rcu_tasks_qs(t); \ } while (0) void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func); void synchronize_rcu_tasks(void); void exit_tasks_rcu_start(void); void exit_tasks_rcu_finish(void); #else /* #ifdef CONFIG_TASKS_RCU */ -#define rcu_note_voluntary_context_switch_lite(t) do { } while (0) +#define rcu_tasks_qs(t) do { } while (0) #define rcu_note_voluntary_context_switch(t) rcu_all_qs() #define call_rcu_tasks call_rcu_sched #define synchronize_rcu_tasks synchronize_sched @@ -194,7 +194,7 @@ static inline void exit_tasks_rcu_finish(void) { } */ #define cond_resched_tasks_rcu_qs() \ do { \ - rcu_note_voluntary_context_switch_lite(current); \ + rcu_tasks_qs(current); \ cond_resched(); \ } while (0) diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 7b3c82e8a625..8d9a0ea8f0b5 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -93,7 +93,7 @@ static inline void kfree_call_rcu(struct rcu_head *head, #define rcu_note_context_switch(preempt) \ do { \ rcu_sched_qs(); \ - rcu_note_voluntary_context_switch_lite(current); \ + rcu_tasks_qs(current); \ } while (0) static inline int rcu_needs_cpu(u64 basemono, u64 *nextevt) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 6f2922168216..ccc061acf887 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -457,7 +457,7 @@ void rcu_note_context_switch(bool preempt) rcu_momentary_dyntick_idle(); this_cpu_inc(rcu_dynticks.rcu_qs_ctr); if (!preempt) - rcu_note_voluntary_context_switch_lite(current); + rcu_tasks_qs(current); out: trace_rcu_utilization(TPS("End context switch")); barrier(); /* Avoid RCU read-side critical sections leaking up. */ diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 4c230a60ece4..5783bdf86e5a 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -507,14 +507,15 @@ early_initcall(check_cpu_stall_init); #ifdef CONFIG_TASKS_RCU /* - * Simple variant of RCU whose quiescent states are voluntary context switch, - * user-space execution, and idle. As such, grace periods can take one good - * long time. There are no read-side primitives similar to rcu_read_lock() - * and rcu_read_unlock() because this implementation is intended to get - * the system into a safe state for some of the manipulations involved in - * tracing and the like. Finally, this implementation does not support - * high call_rcu_tasks() rates from multiple CPUs. If this is required, - * per-CPU callback lists will be needed. + * Simple variant of RCU whose quiescent states are voluntary context + * switch, cond_resched_rcu_qs(), user-space execution, and idle. + * As such, grace periods can take one good long time. There are no + * read-side primitives similar to rcu_read_lock() and rcu_read_unlock() + * because this implementation is intended to get the system into a safe + * state for some of the manipulations involved in tracing and the like. + * Finally, this implementation does not support high call_rcu_tasks() + * rates from multiple CPUs. If this is required, per-CPU callback lists + * will be needed. */ /* Global list of callbacks and associated lock. */ @@ -542,11 +543,11 @@ static struct task_struct *rcu_tasks_kthread_ptr; * period elapses, in other words after all currently executing RCU * read-side critical sections have completed. call_rcu_tasks() assumes * that the read-side critical sections end at a voluntary context - * switch (not a preemption!), entry into idle, or transition to usermode - * execution. As such, there are no read-side primitives analogous to - * rcu_read_lock() and rcu_read_unlock() because this primitive is intended - * to determine that all tasks have passed through a safe state, not so - * much for data-strcuture synchronization. + * switch (not a preemption!), cond_resched_rcu_qs(), entry into idle, + * or transition to usermode execution. As such, there are no read-side + * primitives analogous to rcu_read_lock() and rcu_read_unlock() because + * this primitive is intended to determine that all tasks have passed + * through a safe state, not so much for data-strcuture synchronization. * * See the description of call_rcu() for more detailed information on * memory ordering guarantees. -- cgit v1.2.3 From b7b6f94cf6e6d961f78064315b6f5de5d9c6414b Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 18 Jun 2018 14:22:40 +1000 Subject: rculist: Improve documentation for list_for_each_entry_from_rcu() Unfortunately the patch for adding list_for_each_entry_from_rcu() wasn't the final patch after all review. It is functionally correct but the documentation was incomplete. This patch adds this missing documentation which includes an update to the documentation for list_for_each_entry_continue_rcu() to match the documentation for the new list_for_each_entry_from_rcu(), and adds list_for_each_entry_from_rcu() and the already existing hlist_for_each_entry_from_rcu() to section 7 of whatisRCU.txt. Reviewed-by: Paul E. McKenney Signed-off-by: NeilBrown Signed-off-by: Paul E. McKenney --- Documentation/RCU/whatisRCU.txt | 2 ++ include/linux/rculist.h | 19 ++++++++++++++++++- 2 files changed, 20 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt index 94288f1b8759..c2a7facf7ff9 100644 --- a/Documentation/RCU/whatisRCU.txt +++ b/Documentation/RCU/whatisRCU.txt @@ -820,11 +820,13 @@ RCU list traversal: list_next_rcu list_for_each_entry_rcu list_for_each_entry_continue_rcu + list_for_each_entry_from_rcu hlist_first_rcu hlist_next_rcu hlist_pprev_rcu hlist_for_each_entry_rcu hlist_for_each_entry_rcu_bh + hlist_for_each_entry_from_rcu hlist_for_each_entry_continue_rcu hlist_for_each_entry_continue_rcu_bh hlist_nulls_first_rcu diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 36df6ccbc874..4786c2235b98 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -396,7 +396,16 @@ static inline void list_splice_tail_init_rcu(struct list_head *list, * @member: the name of the list_head within the struct. * * Continue to iterate over list of given type, continuing after - * the current position. + * the current position which must have been in the list when the RCU read + * lock was taken. + * This would typically require either that you obtained the node from a + * previous walk of the list in the same RCU read-side critical section, or + * that you held some sort of non-RCU reference (such as a reference count) + * to keep the node alive *and* in the list. + * + * This iterator is similar to list_for_each_entry_from_rcu() except + * this starts after the given position and that one starts at the given + * position. */ #define list_for_each_entry_continue_rcu(pos, head, member) \ for (pos = list_entry_rcu(pos->member.next, typeof(*pos), member); \ @@ -411,6 +420,14 @@ static inline void list_splice_tail_init_rcu(struct list_head *list, * * Iterate over the tail of a list starting from a given position, * which must have been in the list when the RCU read lock was taken. + * This would typically require either that you obtained the node from a + * previous walk of the list in the same RCU read-side critical section, or + * that you held some sort of non-RCU reference (such as a reference count) + * to keep the node alive *and* in the list. + * + * This iterator is similar to list_for_each_entry_continue_rcu() except + * this starts from the given position and that one starts from the position + * after the given position. */ #define list_for_each_entry_from_rcu(pos, head, member) \ for (; &(pos)->member != (head); \ -- cgit v1.2.3 From 3025520ec424df8b0fd5cdc319ad6b83406d9954 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 22 May 2018 11:38:47 -0700 Subject: rcutorture: Use per-CPU random state for rcu_torture_timer() Currently, the rcu_torture_timer() function uses a single global torture_random_state structure protected by a single global lock. This conflicts to some extent with performance and scalability, but even more with the goal of consolidating read-side testing with rcu_torture_reader(). This commit therefore creates a per-CPU torture_random_state structure for use by rcu_torture_timer() and eliminates the lock. Signed-off-by: Paul E. McKenney [ paulmck: Make rcu_torture_timer_rand static, per 0day Test Robot report. ] --- include/linux/torture.h | 2 ++ kernel/rcu/rcutorture.c | 10 +++++----- 2 files changed, 7 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/torture.h b/include/linux/torture.h index a55e80817dae..61dfd93b6ee4 100644 --- a/include/linux/torture.h +++ b/include/linux/torture.h @@ -64,6 +64,8 @@ struct torture_random_state { long trs_count; }; #define DEFINE_TORTURE_RANDOM(name) struct torture_random_state name = { 0, 0 } +#define DEFINE_TORTURE_RANDOM_PERCPU(name) \ + DEFINE_PER_CPU(struct torture_random_state, name) unsigned long torture_random(struct torture_random_state *trsp); /* Task shuffler, which causes CPUs to occasionally go idle. */ diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index 2452e4a29923..d5a5465d2507 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -1143,6 +1143,8 @@ static bool rcu_torture_one_read(struct torture_random_state *trsp) return true; } +static DEFINE_TORTURE_RANDOM_PERCPU(rcu_torture_timer_rand); + /* * RCU torture reader from timer handler. Dereferences rcu_torture_current, * incrementing the corresponding element of the pipeline array. The @@ -1154,12 +1156,12 @@ static void rcu_torture_timer(struct timer_list *unused) int idx; unsigned long started; unsigned long completed; - static DEFINE_TORTURE_RANDOM(rand); - static DEFINE_SPINLOCK(rand_lock); struct rcu_torture *p; int pipe_count; + struct torture_random_state *trsp; unsigned long long ts; + trsp = this_cpu_ptr(&rcu_torture_timer_rand); atomic_long_inc(&n_rcu_torture_timers); idx = cur_ops->readlock(); started = cur_ops->get_gp_seq(); @@ -1176,9 +1178,7 @@ static void rcu_torture_timer(struct timer_list *unused) } if (p->rtort_mbtest == 0) atomic_inc(&n_rcu_torture_mberror); - spin_lock(&rand_lock); - cur_ops->read_delay(&rand); - spin_unlock(&rand_lock); + cur_ops->read_delay(trsp); preempt_disable(); pipe_count = p->rtort_pipe_count; if (pipe_count > RCU_TORTURE_PIPE_LEN) { -- cgit v1.2.3 From b16ebe925a4400a2ec3dc663c81dce2fd9bf0998 Mon Sep 17 00:00:00 2001 From: Alex Vesker Date: Thu, 12 Jul 2018 15:13:08 +0300 Subject: devlink: Add support for creating and destroying regions This allows a device to register its supported address regions. Each address region can be accessed directly for example reading the snapshots taken of this address space. Drivers are not limited in the name selection for different regions. An example of a region-name can be: pci cr-space, register-space. Signed-off-by: Alex Vesker Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/devlink.h | 22 ++++++++++++++ net/core/devlink.c | 84 +++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 106 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index f67c29cede15..e5397652f2fb 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -28,6 +28,7 @@ struct devlink { struct list_head dpipe_table_list; struct list_head resource_list; struct list_head param_list; + struct list_head region_list; struct devlink_dpipe_headers *dpipe_headers; const struct devlink_ops *ops; struct device *dev; @@ -397,6 +398,8 @@ enum devlink_param_generic_id { .validate = _validate, \ } +struct devlink_region; + struct devlink_ops { int (*reload)(struct devlink *devlink, struct netlink_ext_ack *extack); int (*port_type_set)(struct devlink_port *devlink_port, @@ -543,6 +546,11 @@ int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id, int devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id, union devlink_param_value init_val); void devlink_param_value_changed(struct devlink *devlink, u32 param_id); +struct devlink_region *devlink_region_create(struct devlink *devlink, + const char *region_name, + u32 region_max_snapshots, + u64 region_size); +void devlink_region_destroy(struct devlink_region *region); #else @@ -770,6 +778,20 @@ devlink_param_value_changed(struct devlink *devlink, u32 param_id) { } +static inline struct devlink_region * +devlink_region_create(struct devlink *devlink, + const char *region_name, + u32 region_max_snapshots, + u64 region_size) +{ + return NULL; +} + +static inline void +devlink_region_destroy(struct devlink_region *region) +{ +} + #endif #endif /* _NET_DEVLINK_H_ */ diff --git a/net/core/devlink.c b/net/core/devlink.c index 470f3dbfecfe..cac856136ac6 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -326,6 +326,28 @@ devlink_sb_tc_index_get_from_info(struct devlink_sb *devlink_sb, pool_type, p_tc_index); } +struct devlink_region { + struct devlink *devlink; + struct list_head list; + const char *name; + struct list_head snapshot_list; + u32 max_snapshots; + u32 cur_snapshots; + u64 size; +}; + +static struct devlink_region * +devlink_region_get_by_name(struct devlink *devlink, const char *region_name) +{ + struct devlink_region *region; + + list_for_each_entry(region, &devlink->region_list, list) + if (!strcmp(region->name, region_name)) + return region; + + return NULL; +} + #define DEVLINK_NL_FLAG_NEED_DEVLINK BIT(0) #define DEVLINK_NL_FLAG_NEED_PORT BIT(1) #define DEVLINK_NL_FLAG_NEED_SB BIT(2) @@ -3358,6 +3380,7 @@ struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size) INIT_LIST_HEAD_RCU(&devlink->dpipe_table_list); INIT_LIST_HEAD(&devlink->resource_list); INIT_LIST_HEAD(&devlink->param_list); + INIT_LIST_HEAD(&devlink->region_list); mutex_init(&devlink->lock); return devlink; } @@ -4109,6 +4132,67 @@ void devlink_param_value_changed(struct devlink *devlink, u32 param_id) } EXPORT_SYMBOL_GPL(devlink_param_value_changed); +/** + * devlink_region_create - create a new address region + * + * @devlink: devlink + * @region_name: region name + * @region_max_snapshots: Maximum supported number of snapshots for region + * @region_size: size of region + */ +struct devlink_region *devlink_region_create(struct devlink *devlink, + const char *region_name, + u32 region_max_snapshots, + u64 region_size) +{ + struct devlink_region *region; + int err = 0; + + mutex_lock(&devlink->lock); + + if (devlink_region_get_by_name(devlink, region_name)) { + err = -EEXIST; + goto unlock; + } + + region = kzalloc(sizeof(*region), GFP_KERNEL); + if (!region) { + err = -ENOMEM; + goto unlock; + } + + region->devlink = devlink; + region->max_snapshots = region_max_snapshots; + region->name = region_name; + region->size = region_size; + INIT_LIST_HEAD(®ion->snapshot_list); + list_add_tail(®ion->list, &devlink->region_list); + + mutex_unlock(&devlink->lock); + return region; + +unlock: + mutex_unlock(&devlink->lock); + return ERR_PTR(err); +} +EXPORT_SYMBOL_GPL(devlink_region_create); + +/** + * devlink_region_destroy - destroy address region + * + * @region: devlink region to destroy + */ +void devlink_region_destroy(struct devlink_region *region) +{ + struct devlink *devlink = region->devlink; + + mutex_lock(&devlink->lock); + list_del(®ion->list); + mutex_unlock(&devlink->lock); + kfree(region); +} +EXPORT_SYMBOL_GPL(devlink_region_destroy); + static int __init devlink_module_init(void) { return genl_register_family(&devlink_nl_family); -- cgit v1.2.3 From ccadfa444b34c6ec7bb458eee17fdd8c9a456c63 Mon Sep 17 00:00:00 2001 From: Alex Vesker Date: Thu, 12 Jul 2018 15:13:09 +0300 Subject: devlink: Add callback to query for snapshot id before snapshot create To restrict the driver with the snapshot ID selection a new callback is introduced for the driver to get the snapshot ID before creating a new snapshot. This will also allow giving the same ID for multiple snapshots taken of different regions on the same time. Signed-off-by: Alex Vesker Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/devlink.h | 8 ++++++++ net/core/devlink.c | 21 +++++++++++++++++++++ 2 files changed, 29 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index e5397652f2fb..f27d8593687a 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -29,6 +29,7 @@ struct devlink { struct list_head resource_list; struct list_head param_list; struct list_head region_list; + u32 snapshot_id; struct devlink_dpipe_headers *dpipe_headers; const struct devlink_ops *ops; struct device *dev; @@ -551,6 +552,7 @@ struct devlink_region *devlink_region_create(struct devlink *devlink, u32 region_max_snapshots, u64 region_size); void devlink_region_destroy(struct devlink_region *region); +u32 devlink_region_shapshot_id_get(struct devlink *devlink); #else @@ -792,6 +794,12 @@ devlink_region_destroy(struct devlink_region *region) { } +static inline u32 +devlink_region_shapshot_id_get(struct devlink *devlink) +{ + return 0; +} + #endif #endif /* _NET_DEVLINK_H_ */ diff --git a/net/core/devlink.c b/net/core/devlink.c index cac856136ac6..6c92ddd2465d 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -4193,6 +4193,27 @@ void devlink_region_destroy(struct devlink_region *region) } EXPORT_SYMBOL_GPL(devlink_region_destroy); +/** + * devlink_region_shapshot_id_get - get snapshot ID + * + * This callback should be called when adding a new snapshot, + * Driver should use the same id for multiple snapshots taken + * on multiple regions at the same time/by the same trigger. + * + * @devlink: devlink + */ +u32 devlink_region_shapshot_id_get(struct devlink *devlink) +{ + u32 id; + + mutex_lock(&devlink->lock); + id = ++devlink->snapshot_id; + mutex_unlock(&devlink->lock); + + return id; +} +EXPORT_SYMBOL_GPL(devlink_region_shapshot_id_get); + static int __init devlink_module_init(void) { return genl_register_family(&devlink_nl_family); -- cgit v1.2.3 From d7e5272282d93bedbbeb6174b8af8425d7dcfd6f Mon Sep 17 00:00:00 2001 From: Alex Vesker Date: Thu, 12 Jul 2018 15:13:10 +0300 Subject: devlink: Add support for creating region snapshots Each device address region can store multiple snapshots, each snapshot is identified using a different numerical ID. This ID is used when deleting a snapshot or showing an address region specific snapshot. This patch exposes a callback to add a new snapshot to an address region. The snapshot will be deleted using the destructor function when destroying a region or when a snapshot delete command from devlink user tool. Signed-off-by: Alex Vesker Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/devlink.h | 13 +++++++ net/core/devlink.c | 95 +++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 108 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index f27d8593687a..905f0bb7b4ba 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -401,6 +401,8 @@ enum devlink_param_generic_id { struct devlink_region; +typedef void devlink_snapshot_data_dest_t(const void *data); + struct devlink_ops { int (*reload)(struct devlink *devlink, struct netlink_ext_ack *extack); int (*port_type_set)(struct devlink_port *devlink_port, @@ -553,6 +555,9 @@ struct devlink_region *devlink_region_create(struct devlink *devlink, u64 region_size); void devlink_region_destroy(struct devlink_region *region); u32 devlink_region_shapshot_id_get(struct devlink *devlink); +int devlink_region_snapshot_create(struct devlink_region *region, u64 data_len, + u8 *data, u32 snapshot_id, + devlink_snapshot_data_dest_t *data_destructor); #else @@ -800,6 +805,14 @@ devlink_region_shapshot_id_get(struct devlink *devlink) return 0; } +static inline int +devlink_region_snapshot_create(struct devlink_region *region, u64 data_len, + u8 *data, u32 snapshot_id, + devlink_snapshot_data_dest_t *data_destructor) +{ + return 0; +} + #endif #endif /* _NET_DEVLINK_H_ */ diff --git a/net/core/devlink.c b/net/core/devlink.c index 6c92ddd2465d..7d09fe60fa4b 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -336,6 +336,15 @@ struct devlink_region { u64 size; }; +struct devlink_snapshot { + struct list_head list; + struct devlink_region *region; + devlink_snapshot_data_dest_t *data_destructor; + u64 data_len; + u8 *data; + u32 id; +}; + static struct devlink_region * devlink_region_get_by_name(struct devlink *devlink, const char *region_name) { @@ -348,6 +357,26 @@ devlink_region_get_by_name(struct devlink *devlink, const char *region_name) return NULL; } +static struct devlink_snapshot * +devlink_region_snapshot_get_by_id(struct devlink_region *region, u32 id) +{ + struct devlink_snapshot *snapshot; + + list_for_each_entry(snapshot, ®ion->snapshot_list, list) + if (snapshot->id == id) + return snapshot; + + return NULL; +} + +static void devlink_region_snapshot_del(struct devlink_snapshot *snapshot) +{ + snapshot->region->cur_snapshots--; + list_del(&snapshot->list); + (*snapshot->data_destructor)(snapshot->data); + kfree(snapshot); +} + #define DEVLINK_NL_FLAG_NEED_DEVLINK BIT(0) #define DEVLINK_NL_FLAG_NEED_PORT BIT(1) #define DEVLINK_NL_FLAG_NEED_SB BIT(2) @@ -4185,8 +4214,14 @@ EXPORT_SYMBOL_GPL(devlink_region_create); void devlink_region_destroy(struct devlink_region *region) { struct devlink *devlink = region->devlink; + struct devlink_snapshot *snapshot, *ts; mutex_lock(&devlink->lock); + + /* Free all snapshots of region */ + list_for_each_entry_safe(snapshot, ts, ®ion->snapshot_list, list) + devlink_region_snapshot_del(snapshot); + list_del(®ion->list); mutex_unlock(&devlink->lock); kfree(region); @@ -4214,6 +4249,66 @@ u32 devlink_region_shapshot_id_get(struct devlink *devlink) } EXPORT_SYMBOL_GPL(devlink_region_shapshot_id_get); +/** + * devlink_region_snapshot_create - create a new snapshot + * This will add a new snapshot of a region. The snapshot + * will be stored on the region struct and can be accessed + * from devlink. This is useful for future analyses of snapshots. + * Multiple snapshots can be created on a region. + * The @snapshot_id should be obtained using the getter function. + * + * @devlink_region: devlink region of the snapshot + * @data_len: size of snapshot data + * @data: snapshot data + * @snapshot_id: snapshot id to be created + * @data_destructor: pointer to destructor function to free data + */ +int devlink_region_snapshot_create(struct devlink_region *region, u64 data_len, + u8 *data, u32 snapshot_id, + devlink_snapshot_data_dest_t *data_destructor) +{ + struct devlink *devlink = region->devlink; + struct devlink_snapshot *snapshot; + int err; + + mutex_lock(&devlink->lock); + + /* check if region can hold one more snapshot */ + if (region->cur_snapshots == region->max_snapshots) { + err = -ENOMEM; + goto unlock; + } + + if (devlink_region_snapshot_get_by_id(region, snapshot_id)) { + err = -EEXIST; + goto unlock; + } + + snapshot = kzalloc(sizeof(*snapshot), GFP_KERNEL); + if (!snapshot) { + err = -ENOMEM; + goto unlock; + } + + snapshot->id = snapshot_id; + snapshot->region = region; + snapshot->data = data; + snapshot->data_len = data_len; + snapshot->data_destructor = data_destructor; + + list_add_tail(&snapshot->list, ®ion->snapshot_list); + + region->cur_snapshots++; + + mutex_unlock(&devlink->lock); + return 0; + +unlock: + mutex_unlock(&devlink->lock); + return err; +} +EXPORT_SYMBOL_GPL(devlink_region_snapshot_create); + static int __init devlink_module_init(void) { return genl_register_family(&devlink_nl_family); -- cgit v1.2.3 From d8db7ea55f2ff5890ad31137233a3808d80c7f62 Mon Sep 17 00:00:00 2001 From: Alex Vesker Date: Thu, 12 Jul 2018 15:13:11 +0300 Subject: devlink: Add support for region get command Add support for DEVLINK_CMD_REGION_GET command which is used for querying for the supported DEV/REGION values of devlink devices. The support is both for doit and dumpit. Reply includes: BUS_NAME, DEVICE_NAME, REGION_NAME, REGION_SIZE Signed-off-by: Alex Vesker Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/uapi/linux/devlink.h | 6 +++ net/core/devlink.c | 114 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 120 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 68641fb56654..28bfa8aa3d91 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -83,6 +83,9 @@ enum devlink_command { DEVLINK_CMD_PARAM_NEW, DEVLINK_CMD_PARAM_DEL, + DEVLINK_CMD_REGION_GET, + DEVLINK_CMD_REGION_SET, + /* add new commands above here */ __DEVLINK_CMD_MAX, DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1 @@ -262,6 +265,9 @@ enum devlink_attr { DEVLINK_ATTR_PARAM_VALUE_DATA, /* dynamic */ DEVLINK_ATTR_PARAM_VALUE_CMODE, /* u8 */ + DEVLINK_ATTR_REGION_NAME, /* string */ + DEVLINK_ATTR_REGION_SIZE, /* u64 */ + /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, diff --git a/net/core/devlink.c b/net/core/devlink.c index 7d09fe60fa4b..221ddb6bae48 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -3149,6 +3149,111 @@ static void devlink_param_unregister_one(struct devlink *devlink, kfree(param_item); } +static int devlink_nl_region_fill(struct sk_buff *msg, struct devlink *devlink, + enum devlink_command cmd, u32 portid, + u32 seq, int flags, + struct devlink_region *region) +{ + void *hdr; + int err; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + err = devlink_nl_put_handle(msg, devlink); + if (err) + goto nla_put_failure; + + err = nla_put_string(msg, DEVLINK_ATTR_REGION_NAME, region->name); + if (err) + goto nla_put_failure; + + err = nla_put_u64_64bit(msg, DEVLINK_ATTR_REGION_SIZE, + region->size, + DEVLINK_ATTR_PAD); + if (err) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return err; +} + +static int devlink_nl_cmd_region_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_region *region; + const char *region_name; + struct sk_buff *msg; + int err; + + if (!info->attrs[DEVLINK_ATTR_REGION_NAME]) + return -EINVAL; + + region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]); + region = devlink_region_get_by_name(devlink, region_name); + if (!region) + return -EINVAL; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_region_fill(msg, devlink, DEVLINK_CMD_REGION_GET, + info->snd_portid, info->snd_seq, 0, + region); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +static int devlink_nl_cmd_region_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + struct devlink_region *region; + struct devlink *devlink; + int start = cb->args[0]; + int idx = 0; + int err; + + mutex_lock(&devlink_mutex); + list_for_each_entry(devlink, &devlink_list, list) { + if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + continue; + + mutex_lock(&devlink->lock); + list_for_each_entry(region, &devlink->region_list, list) { + if (idx < start) { + idx++; + continue; + } + err = devlink_nl_region_fill(msg, devlink, + DEVLINK_CMD_REGION_GET, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI, region); + if (err) { + mutex_unlock(&devlink->lock); + goto out; + } + idx++; + } + mutex_unlock(&devlink->lock); + } +out: + mutex_unlock(&devlink_mutex); + cb->args[0] = idx; + return msg->len; +} + static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING }, @@ -3172,6 +3277,7 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_PARAM_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_PARAM_TYPE] = { .type = NLA_U8 }, [DEVLINK_ATTR_PARAM_VALUE_CMODE] = { .type = NLA_U8 }, + [DEVLINK_ATTR_REGION_NAME] = { .type = NLA_NUL_STRING }, }; static const struct genl_ops devlink_nl_ops[] = { @@ -3370,6 +3476,14 @@ static const struct genl_ops devlink_nl_ops[] = { .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, }, + { + .cmd = DEVLINK_CMD_REGION_GET, + .doit = devlink_nl_cmd_region_get_doit, + .dumpit = devlink_nl_cmd_region_get_dumpit, + .policy = devlink_nl_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + }, }; static struct genl_family devlink_nl_family __ro_after_init = { -- cgit v1.2.3 From a006d467fbf1d405e73cd167829d7a9e3df600e3 Mon Sep 17 00:00:00 2001 From: Alex Vesker Date: Thu, 12 Jul 2018 15:13:12 +0300 Subject: devlink: Extend the support querying for region snapshot IDs Extend the support for DEVLINK_CMD_REGION_GET command to also return the IDs of the snapshot currently present on the region. Each reply will include a nested snapshots attribute that can contain multiple snapshot attributes each with an ID. Signed-off-by: Alex Vesker Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/uapi/linux/devlink.h | 3 +++ net/core/devlink.c | 53 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 56 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 28bfa8aa3d91..abde4e306375 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -267,6 +267,9 @@ enum devlink_attr { DEVLINK_ATTR_REGION_NAME, /* string */ DEVLINK_ATTR_REGION_SIZE, /* u64 */ + DEVLINK_ATTR_REGION_SNAPSHOTS, /* nested */ + DEVLINK_ATTR_REGION_SNAPSHOT, /* nested */ + DEVLINK_ATTR_REGION_SNAPSHOT_ID, /* u32 */ /* add new attributes above here, update the policy in devlink.c */ diff --git a/net/core/devlink.c b/net/core/devlink.c index 221ddb6bae48..cb75e26d70ff 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -3149,6 +3149,55 @@ static void devlink_param_unregister_one(struct devlink *devlink, kfree(param_item); } +static int devlink_nl_region_snapshot_id_put(struct sk_buff *msg, + struct devlink *devlink, + struct devlink_snapshot *snapshot) +{ + struct nlattr *snap_attr; + int err; + + snap_attr = nla_nest_start(msg, DEVLINK_ATTR_REGION_SNAPSHOT); + if (!snap_attr) + return -EINVAL; + + err = nla_put_u32(msg, DEVLINK_ATTR_REGION_SNAPSHOT_ID, snapshot->id); + if (err) + goto nla_put_failure; + + nla_nest_end(msg, snap_attr); + return 0; + +nla_put_failure: + nla_nest_cancel(msg, snap_attr); + return err; +} + +static int devlink_nl_region_snapshots_id_put(struct sk_buff *msg, + struct devlink *devlink, + struct devlink_region *region) +{ + struct devlink_snapshot *snapshot; + struct nlattr *snapshots_attr; + int err; + + snapshots_attr = nla_nest_start(msg, DEVLINK_ATTR_REGION_SNAPSHOTS); + if (!snapshots_attr) + return -EINVAL; + + list_for_each_entry(snapshot, ®ion->snapshot_list, list) { + err = devlink_nl_region_snapshot_id_put(msg, devlink, snapshot); + if (err) + goto nla_put_failure; + } + + nla_nest_end(msg, snapshots_attr); + return 0; + +nla_put_failure: + nla_nest_cancel(msg, snapshots_attr); + return err; +} + static int devlink_nl_region_fill(struct sk_buff *msg, struct devlink *devlink, enum devlink_command cmd, u32 portid, u32 seq, int flags, @@ -3175,6 +3224,10 @@ static int devlink_nl_region_fill(struct sk_buff *msg, struct devlink *devlink, if (err) goto nla_put_failure; + err = devlink_nl_region_snapshots_id_put(msg, devlink, region); + if (err) + goto nla_put_failure; + genlmsg_end(msg, hdr); return 0; -- cgit v1.2.3 From 866319bb9437614407ca36f8b16f89ab77a6a831 Mon Sep 17 00:00:00 2001 From: Alex Vesker Date: Thu, 12 Jul 2018 15:13:13 +0300 Subject: devlink: Add support for region snapshot delete command Add support for DEVLINK_CMD_REGION_DEL used for deleting a snapshot from a region. The snapshot ID is required. Also added notification support for NEW and DEL of snapshots. Signed-off-by: Alex Vesker Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/uapi/linux/devlink.h | 2 + net/core/devlink.c | 93 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 95 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index abde4e306375..d212e02f843f 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -85,6 +85,8 @@ enum devlink_command { DEVLINK_CMD_REGION_GET, DEVLINK_CMD_REGION_SET, + DEVLINK_CMD_REGION_NEW, + DEVLINK_CMD_REGION_DEL, /* add new commands above here */ __DEVLINK_CMD_MAX, diff --git a/net/core/devlink.c b/net/core/devlink.c index cb75e26d70ff..fc0836371a71 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -3236,6 +3236,58 @@ nla_put_failure: return err; } +static void devlink_nl_region_notify(struct devlink_region *region, + struct devlink_snapshot *snapshot, + enum devlink_command cmd) +{ + struct devlink *devlink = region->devlink; + struct sk_buff *msg; + void *hdr; + int err; + + WARN_ON(cmd != DEVLINK_CMD_REGION_NEW && cmd != DEVLINK_CMD_REGION_DEL); + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + hdr = genlmsg_put(msg, 0, 0, &devlink_nl_family, 0, cmd); + if (!hdr) + goto out_free_msg; + + err = devlink_nl_put_handle(msg, devlink); + if (err) + goto out_cancel_msg; + + err = nla_put_string(msg, DEVLINK_ATTR_REGION_NAME, + region->name); + if (err) + goto out_cancel_msg; + + if (snapshot) { + err = nla_put_u32(msg, DEVLINK_ATTR_REGION_SNAPSHOT_ID, + snapshot->id); + if (err) + goto out_cancel_msg; + } else { + err = nla_put_u64_64bit(msg, DEVLINK_ATTR_REGION_SIZE, + region->size, DEVLINK_ATTR_PAD); + if (err) + goto out_cancel_msg; + } + genlmsg_end(msg, hdr); + + genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), + msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); + + return; + +out_cancel_msg: + genlmsg_cancel(msg, hdr); +out_free_msg: + nlmsg_free(msg); +} + static int devlink_nl_cmd_region_get_doit(struct sk_buff *skb, struct genl_info *info) { @@ -3307,6 +3359,35 @@ out: return msg->len; } +static int devlink_nl_cmd_region_del(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_snapshot *snapshot; + struct devlink_region *region; + const char *region_name; + u32 snapshot_id; + + if (!info->attrs[DEVLINK_ATTR_REGION_NAME] || + !info->attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]) + return -EINVAL; + + region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]); + snapshot_id = nla_get_u32(info->attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]); + + region = devlink_region_get_by_name(devlink, region_name); + if (!region) + return -EINVAL; + + snapshot = devlink_region_snapshot_get_by_id(region, snapshot_id); + if (!snapshot) + return -EINVAL; + + devlink_nl_region_notify(region, snapshot, DEVLINK_CMD_REGION_DEL); + devlink_region_snapshot_del(snapshot); + return 0; +} + static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING }, @@ -3331,6 +3412,7 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_PARAM_TYPE] = { .type = NLA_U8 }, [DEVLINK_ATTR_PARAM_VALUE_CMODE] = { .type = NLA_U8 }, [DEVLINK_ATTR_REGION_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_REGION_SNAPSHOT_ID] = { .type = NLA_U32 }, }; static const struct genl_ops devlink_nl_ops[] = { @@ -3537,6 +3619,13 @@ static const struct genl_ops devlink_nl_ops[] = { .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, }, + { + .cmd = DEVLINK_CMD_REGION_DEL, + .doit = devlink_nl_cmd_region_del, + .policy = devlink_nl_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + }, }; static struct genl_family devlink_nl_family __ro_after_init = { @@ -4363,6 +4452,7 @@ struct devlink_region *devlink_region_create(struct devlink *devlink, region->size = region_size; INIT_LIST_HEAD(®ion->snapshot_list); list_add_tail(®ion->list, &devlink->region_list); + devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_NEW); mutex_unlock(&devlink->lock); return region; @@ -4390,6 +4480,8 @@ void devlink_region_destroy(struct devlink_region *region) devlink_region_snapshot_del(snapshot); list_del(®ion->list); + + devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_DEL); mutex_unlock(&devlink->lock); kfree(region); } @@ -4467,6 +4559,7 @@ int devlink_region_snapshot_create(struct devlink_region *region, u64 data_len, region->cur_snapshots++; + devlink_nl_region_notify(region, snapshot, DEVLINK_CMD_REGION_NEW); mutex_unlock(&devlink->lock); return 0; -- cgit v1.2.3 From 4e54795a27f56102649f121a34b8445e42f79ccd Mon Sep 17 00:00:00 2001 From: Alex Vesker Date: Thu, 12 Jul 2018 15:13:14 +0300 Subject: devlink: Add support for region snapshot read command Add support for DEVLINK_CMD_REGION_READ_GET used for both reading and dumping region data. Read allows reading from a region specific address for given length. Dump allows reading the full region. If only snapshot ID is provided a snapshot dump will be done. If snapshot ID, Address and Length are provided a snapshot read will done. This is used for both snapshot access and will be used in the same way to access current data on the region. Signed-off-by: Alex Vesker Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/uapi/linux/devlink.h | 7 ++ net/core/devlink.c | 182 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 189 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index d212e02f843f..79407bbd296d 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -87,6 +87,7 @@ enum devlink_command { DEVLINK_CMD_REGION_SET, DEVLINK_CMD_REGION_NEW, DEVLINK_CMD_REGION_DEL, + DEVLINK_CMD_REGION_READ, /* add new commands above here */ __DEVLINK_CMD_MAX, @@ -273,6 +274,12 @@ enum devlink_attr { DEVLINK_ATTR_REGION_SNAPSHOT, /* nested */ DEVLINK_ATTR_REGION_SNAPSHOT_ID, /* u32 */ + DEVLINK_ATTR_REGION_CHUNKS, /* nested */ + DEVLINK_ATTR_REGION_CHUNK, /* nested */ + DEVLINK_ATTR_REGION_CHUNK_DATA, /* binary */ + DEVLINK_ATTR_REGION_CHUNK_ADDR, /* u64 */ + DEVLINK_ATTR_REGION_CHUNK_LEN, /* u64 */ + /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, diff --git a/net/core/devlink.c b/net/core/devlink.c index fc0836371a71..e5118dba6bb4 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -3388,6 +3388,181 @@ static int devlink_nl_cmd_region_del(struct sk_buff *skb, return 0; } +static int devlink_nl_cmd_region_read_chunk_fill(struct sk_buff *msg, + struct devlink *devlink, + u8 *chunk, u32 chunk_size, + u64 addr) +{ + struct nlattr *chunk_attr; + int err; + + chunk_attr = nla_nest_start(msg, DEVLINK_ATTR_REGION_CHUNK); + if (!chunk_attr) + return -EINVAL; + + err = nla_put(msg, DEVLINK_ATTR_REGION_CHUNK_DATA, chunk_size, chunk); + if (err) + goto nla_put_failure; + + err = nla_put_u64_64bit(msg, DEVLINK_ATTR_REGION_CHUNK_ADDR, addr, + DEVLINK_ATTR_PAD); + if (err) + goto nla_put_failure; + + nla_nest_end(msg, chunk_attr); + return 0; + +nla_put_failure: + nla_nest_cancel(msg, chunk_attr); + return err; +} + +#define DEVLINK_REGION_READ_CHUNK_SIZE 256 + +static int devlink_nl_region_read_snapshot_fill(struct sk_buff *skb, + struct devlink *devlink, + struct devlink_region *region, + struct nlattr **attrs, + u64 start_offset, + u64 end_offset, + bool dump, + u64 *new_offset) +{ + struct devlink_snapshot *snapshot; + u64 curr_offset = start_offset; + u32 snapshot_id; + int err = 0; + + *new_offset = start_offset; + + snapshot_id = nla_get_u32(attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]); + snapshot = devlink_region_snapshot_get_by_id(region, snapshot_id); + if (!snapshot) + return -EINVAL; + + if (end_offset > snapshot->data_len || dump) + end_offset = snapshot->data_len; + + while (curr_offset < end_offset) { + u32 data_size; + u8 *data; + + if (end_offset - curr_offset < DEVLINK_REGION_READ_CHUNK_SIZE) + data_size = end_offset - curr_offset; + else + data_size = DEVLINK_REGION_READ_CHUNK_SIZE; + + data = &snapshot->data[curr_offset]; + err = devlink_nl_cmd_region_read_chunk_fill(skb, devlink, + data, data_size, + curr_offset); + if (err) + break; + + curr_offset += data_size; + } + *new_offset = curr_offset; + + return err; +} + +static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, + struct netlink_callback *cb) +{ + u64 ret_offset, start_offset, end_offset = 0; + struct nlattr *attrs[DEVLINK_ATTR_MAX + 1]; + const struct genl_ops *ops = cb->data; + struct devlink_region *region; + struct nlattr *chunks_attr; + const char *region_name; + struct devlink *devlink; + bool dump = true; + void *hdr; + int err; + + start_offset = *((u64 *)&cb->args[0]); + + err = nlmsg_parse(cb->nlh, GENL_HDRLEN + devlink_nl_family.hdrsize, + attrs, DEVLINK_ATTR_MAX, ops->policy, NULL); + if (err) + goto out; + + devlink = devlink_get_from_attrs(sock_net(cb->skb->sk), attrs); + if (IS_ERR(devlink)) + goto out; + + mutex_lock(&devlink_mutex); + mutex_lock(&devlink->lock); + + if (!attrs[DEVLINK_ATTR_REGION_NAME] || + !attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]) + goto out_unlock; + + region_name = nla_data(attrs[DEVLINK_ATTR_REGION_NAME]); + region = devlink_region_get_by_name(devlink, region_name); + if (!region) + goto out_unlock; + + hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + &devlink_nl_family, NLM_F_ACK | NLM_F_MULTI, + DEVLINK_CMD_REGION_READ); + if (!hdr) + goto out_unlock; + + err = devlink_nl_put_handle(skb, devlink); + if (err) + goto nla_put_failure; + + err = nla_put_string(skb, DEVLINK_ATTR_REGION_NAME, region_name); + if (err) + goto nla_put_failure; + + chunks_attr = nla_nest_start(skb, DEVLINK_ATTR_REGION_CHUNKS); + if (!chunks_attr) + goto nla_put_failure; + + if (attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR] && + attrs[DEVLINK_ATTR_REGION_CHUNK_LEN]) { + if (!start_offset) + start_offset = + nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR]); + + end_offset = nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR]); + end_offset += nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_LEN]); + dump = false; + } + + err = devlink_nl_region_read_snapshot_fill(skb, devlink, + region, attrs, + start_offset, + end_offset, dump, + &ret_offset); + + if (err && err != -EMSGSIZE) + goto nla_put_failure; + + /* Check if there was any progress done to prevent infinite loop */ + if (ret_offset == start_offset) + goto nla_put_failure; + + *((u64 *)&cb->args[0]) = ret_offset; + + nla_nest_end(skb, chunks_attr); + genlmsg_end(skb, hdr); + mutex_unlock(&devlink->lock); + mutex_unlock(&devlink_mutex); + + return skb->len; + +nla_put_failure: + genlmsg_cancel(skb, hdr); +out_unlock: + mutex_unlock(&devlink->lock); + mutex_unlock(&devlink_mutex); +out: + return 0; +} + static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING }, @@ -3626,6 +3801,13 @@ static const struct genl_ops devlink_nl_ops[] = { .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, }, + { + .cmd = DEVLINK_CMD_REGION_READ, + .dumpit = devlink_nl_cmd_region_read_dumpit, + .policy = devlink_nl_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + }, }; static struct genl_family devlink_nl_family __ro_after_init = { -- cgit v1.2.3 From 523f9eb1ef25aab4aaf9aeb5356160e8039411ef Mon Sep 17 00:00:00 2001 From: Alex Vesker Date: Thu, 12 Jul 2018 15:13:15 +0300 Subject: net/mlx4_core: Add health buffer address capability Health buffer address is a 32 bit PCI address offset provided by the FW. This offset is used for reading FW health debug data located on the shared CR space. Cr space is accessible in both driver and FW and allows for different queries and configurations. Health buffer size is always 64B of readable data followed by a lock which is used to block volatile CR space access. Signed-off-by: Alex Vesker Signed-off-by: Tariq Toukan Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/fw.c | 5 ++++- drivers/net/ethernet/mellanox/mlx4/fw.h | 1 + drivers/net/ethernet/mellanox/mlx4/main.c | 1 + include/linux/mlx4/device.h | 1 + 4 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index 46dcbfbe4c5e..babcfd9c0571 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -825,7 +825,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) #define QUERY_DEV_CAP_QP_RATE_LIMIT_NUM_OFFSET 0xcc #define QUERY_DEV_CAP_QP_RATE_LIMIT_MAX_OFFSET 0xd0 #define QUERY_DEV_CAP_QP_RATE_LIMIT_MIN_OFFSET 0xd2 - +#define QUERY_DEV_CAP_HEALTH_BUFFER_ADDRESS_OFFSET 0xe4 dev_cap->flags2 = 0; mailbox = mlx4_alloc_cmd_mailbox(dev); @@ -1082,6 +1082,9 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) dev_cap->rl_caps.min_unit = size >> 14; } + MLX4_GET(dev_cap->health_buffer_addrs, outbox, + QUERY_DEV_CAP_HEALTH_BUFFER_ADDRESS_OFFSET); + MLX4_GET(field32, outbox, QUERY_DEV_CAP_EXT_2_FLAGS_OFFSET); if (field32 & (1 << 16)) dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_UPDATE_QP; diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h index cd6399c76bfd..650ae08c71de 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.h +++ b/drivers/net/ethernet/mellanox/mlx4/fw.h @@ -128,6 +128,7 @@ struct mlx4_dev_cap { u32 dmfs_high_rate_qpn_base; u32 dmfs_high_rate_qpn_range; struct mlx4_rate_limit_caps rl_caps; + u32 health_buffer_addrs; struct mlx4_port_cap port_cap[MLX4_MAX_PORTS + 1]; bool wol_port[MLX4_MAX_PORTS + 1]; }; diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index c42eddfcd2b5..806d441b3701 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -523,6 +523,7 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) dev->caps.max_rss_tbl_sz = dev_cap->max_rss_tbl_sz; dev->caps.wol_port[1] = dev_cap->wol_port[1]; dev->caps.wol_port[2] = dev_cap->wol_port[2]; + dev->caps.health_buffer_addrs = dev_cap->health_buffer_addrs; /* Save uar page shift */ if (!mlx4_is_slave(dev)) { diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 122e7e9d3091..e3bfe76aea98 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -630,6 +630,7 @@ struct mlx4_caps { u32 vf_caps; bool wol_port[MLX4_MAX_PORTS + 1]; struct mlx4_rate_limit_caps rl_caps; + u32 health_buffer_addrs; }; struct mlx4_buf_list { -- cgit v1.2.3 From bedc989b0c98285b277ff8a08ff9514e580913f4 Mon Sep 17 00:00:00 2001 From: Alex Vesker Date: Thu, 12 Jul 2018 15:13:16 +0300 Subject: net/mlx4_core: Add Crdump FW snapshot support Crdump allows the driver to create a snapshot of the FW PCI crspace and health buffer during a critical FW issue. In case of a FW command timeout, FW getting stuck or a non zero value on the catastrophic buffer, a snapshot will be taken. The snapshot is exposed using devlink, cr-space, fw-health address regions are registered on init and snapshots are attached once a new snapshot is collected by the driver. Signed-off-by: Alex Vesker Signed-off-by: Tariq Toukan Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/Makefile | 2 +- drivers/net/ethernet/mellanox/mlx4/catas.c | 6 +- drivers/net/ethernet/mellanox/mlx4/crdump.c | 231 ++++++++++++++++++++++++++++ drivers/net/ethernet/mellanox/mlx4/main.c | 10 +- drivers/net/ethernet/mellanox/mlx4/mlx4.h | 4 + include/linux/mlx4/device.h | 6 + 6 files changed, 255 insertions(+), 4 deletions(-) create mode 100644 drivers/net/ethernet/mellanox/mlx4/crdump.c (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx4/Makefile b/drivers/net/ethernet/mellanox/mlx4/Makefile index 16b10d01fcf4..3f400770fcd8 100644 --- a/drivers/net/ethernet/mellanox/mlx4/Makefile +++ b/drivers/net/ethernet/mellanox/mlx4/Makefile @@ -3,7 +3,7 @@ obj-$(CONFIG_MLX4_CORE) += mlx4_core.o mlx4_core-y := alloc.o catas.o cmd.o cq.o eq.o fw.o fw_qos.o icm.o intf.o \ main.o mcg.o mr.o pd.o port.o profile.o qp.o reset.o sense.o \ - srq.o resource_tracker.o + srq.o resource_tracker.o crdump.o obj-$(CONFIG_MLX4_EN) += mlx4_en.o diff --git a/drivers/net/ethernet/mellanox/mlx4/catas.c b/drivers/net/ethernet/mellanox/mlx4/catas.c index 8afe4b5fb09b..c81d15bf259c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/catas.c +++ b/drivers/net/ethernet/mellanox/mlx4/catas.c @@ -178,10 +178,12 @@ void mlx4_enter_error_state(struct mlx4_dev_persistent *persist) dev = persist->dev; mlx4_err(dev, "device is going to be reset\n"); - if (mlx4_is_slave(dev)) + if (mlx4_is_slave(dev)) { err = mlx4_reset_slave(dev); - else + } else { + mlx4_crdump_collect(dev); err = mlx4_reset_master(dev); + } if (!err) { mlx4_err(dev, "device was reset successfully\n"); diff --git a/drivers/net/ethernet/mellanox/mlx4/crdump.c b/drivers/net/ethernet/mellanox/mlx4/crdump.c new file mode 100644 index 000000000000..4d5524dffec4 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx4/crdump.c @@ -0,0 +1,231 @@ +/* + * Copyright (c) 2018, Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include "mlx4.h" + +#define BAD_ACCESS 0xBADACCE5 +#define HEALTH_BUFFER_SIZE 0x40 +#define CR_ENABLE_BIT swab32(BIT(6)) +#define CR_ENABLE_BIT_OFFSET 0xF3F04 +#define MAX_NUM_OF_DUMPS_TO_STORE (8) + +static const char *region_cr_space_str = "cr-space"; +static const char *region_fw_health_str = "fw-health"; + +/* Set to true in case cr enable bit was set to true before crdump */ +static bool crdump_enbale_bit_set; + +static void crdump_enable_crspace_access(struct mlx4_dev *dev, + u8 __iomem *cr_space) +{ + /* Get current enable bit value */ + crdump_enbale_bit_set = + readl(cr_space + CR_ENABLE_BIT_OFFSET) & CR_ENABLE_BIT; + + /* Enable FW CR filter (set bit6 to 0) */ + if (crdump_enbale_bit_set) + writel(readl(cr_space + CR_ENABLE_BIT_OFFSET) & ~CR_ENABLE_BIT, + cr_space + CR_ENABLE_BIT_OFFSET); + + /* Enable block volatile crspace accesses */ + writel(swab32(1), cr_space + dev->caps.health_buffer_addrs + + HEALTH_BUFFER_SIZE); +} + +static void crdump_disable_crspace_access(struct mlx4_dev *dev, + u8 __iomem *cr_space) +{ + /* Disable block volatile crspace accesses */ + writel(0, cr_space + dev->caps.health_buffer_addrs + + HEALTH_BUFFER_SIZE); + + /* Restore FW CR filter value (set bit6 to original value) */ + if (crdump_enbale_bit_set) + writel(readl(cr_space + CR_ENABLE_BIT_OFFSET) | CR_ENABLE_BIT, + cr_space + CR_ENABLE_BIT_OFFSET); +} + +static void mlx4_crdump_collect_crspace(struct mlx4_dev *dev, + u8 __iomem *cr_space, + u32 id) +{ + struct mlx4_fw_crdump *crdump = &dev->persist->crdump; + struct pci_dev *pdev = dev->persist->pdev; + unsigned long cr_res_size; + u8 *crspace_data; + int offset; + int err; + + if (!crdump->region_crspace) { + mlx4_err(dev, "crdump: cr-space region is NULL\n"); + return; + } + + /* Try to collect CR space */ + cr_res_size = pci_resource_len(pdev, 0); + crspace_data = kvmalloc(cr_res_size, GFP_KERNEL); + if (crspace_data) { + for (offset = 0; offset < cr_res_size; offset += 4) + *(u32 *)(crspace_data + offset) = + readl(cr_space + offset); + + err = devlink_region_snapshot_create(crdump->region_crspace, + cr_res_size, crspace_data, + id, &kvfree); + if (err) { + kvfree(crspace_data); + mlx4_warn(dev, "crdump: devlink create %s snapshot id %d err %d\n", + region_cr_space_str, id, err); + } else { + mlx4_info(dev, "crdump: added snapshot %d to devlink region %s\n", + id, region_cr_space_str); + } + } else { + mlx4_err(dev, "crdump: Failed to allocate crspace buffer\n"); + } +} + +static void mlx4_crdump_collect_fw_health(struct mlx4_dev *dev, + u8 __iomem *cr_space, + u32 id) +{ + struct mlx4_fw_crdump *crdump = &dev->persist->crdump; + u8 *health_data; + int offset; + int err; + + if (!crdump->region_fw_health) { + mlx4_err(dev, "crdump: fw-health region is NULL\n"); + return; + } + + /* Try to collect health buffer */ + health_data = kvmalloc(HEALTH_BUFFER_SIZE, GFP_KERNEL); + if (health_data) { + u8 __iomem *health_buf_start = + cr_space + dev->caps.health_buffer_addrs; + + for (offset = 0; offset < HEALTH_BUFFER_SIZE; offset += 4) + *(u32 *)(health_data + offset) = + readl(health_buf_start + offset); + + err = devlink_region_snapshot_create(crdump->region_fw_health, + HEALTH_BUFFER_SIZE, + health_data, + id, &kvfree); + if (err) { + kvfree(health_data); + mlx4_warn(dev, "crdump: devlink create %s snapshot id %d err %d\n", + region_fw_health_str, id, err); + } else { + mlx4_info(dev, "crdump: added snapshot %d to devlink region %s\n", + id, region_fw_health_str); + } + } else { + mlx4_err(dev, "crdump: Failed to allocate health buffer\n"); + } +} + +int mlx4_crdump_collect(struct mlx4_dev *dev) +{ + struct devlink *devlink = priv_to_devlink(mlx4_priv(dev)); + struct pci_dev *pdev = dev->persist->pdev; + unsigned long cr_res_size; + u8 __iomem *cr_space; + u32 id; + + if (!dev->caps.health_buffer_addrs) { + mlx4_info(dev, "crdump: FW doesn't support health buffer access, skipping\n"); + return 0; + } + + cr_res_size = pci_resource_len(pdev, 0); + + cr_space = ioremap(pci_resource_start(pdev, 0), cr_res_size); + if (!cr_space) { + mlx4_err(dev, "crdump: Failed to map pci cr region\n"); + return -ENODEV; + } + + crdump_enable_crspace_access(dev, cr_space); + + /* Get the available snapshot ID for the dumps */ + id = devlink_region_shapshot_id_get(devlink); + + /* Try to capture dumps */ + mlx4_crdump_collect_crspace(dev, cr_space, id); + mlx4_crdump_collect_fw_health(dev, cr_space, id); + + crdump_disable_crspace_access(dev, cr_space); + + iounmap(cr_space); + return 0; +} + +int mlx4_crdump_init(struct mlx4_dev *dev) +{ + struct devlink *devlink = priv_to_devlink(mlx4_priv(dev)); + struct mlx4_fw_crdump *crdump = &dev->persist->crdump; + struct pci_dev *pdev = dev->persist->pdev; + + /* Create cr-space region */ + crdump->region_crspace = + devlink_region_create(devlink, + region_cr_space_str, + MAX_NUM_OF_DUMPS_TO_STORE, + pci_resource_len(pdev, 0)); + if (IS_ERR(crdump->region_crspace)) + mlx4_warn(dev, "crdump: create devlink region %s err %ld\n", + region_cr_space_str, + PTR_ERR(crdump->region_crspace)); + + /* Create fw-health region */ + crdump->region_fw_health = + devlink_region_create(devlink, + region_fw_health_str, + MAX_NUM_OF_DUMPS_TO_STORE, + HEALTH_BUFFER_SIZE); + if (IS_ERR(crdump->region_fw_health)) + mlx4_warn(dev, "crdump: create devlink region %s err %ld\n", + region_fw_health_str, + PTR_ERR(crdump->region_fw_health)); + + return 0; +} + +void mlx4_crdump_end(struct mlx4_dev *dev) +{ + struct mlx4_fw_crdump *crdump = &dev->persist->crdump; + + devlink_region_destroy(crdump->region_fw_health); + devlink_region_destroy(crdump->region_crspace); +} diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 806d441b3701..46b021409b8b 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -3807,10 +3807,14 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data, } } - err = mlx4_catas_init(&priv->dev); + err = mlx4_crdump_init(&priv->dev); if (err) goto err_release_regions; + err = mlx4_catas_init(&priv->dev); + if (err) + goto err_crdump; + err = mlx4_load_one(pdev, pci_dev_data, total_vfs, nvfs, priv, 0); if (err) goto err_catas; @@ -3820,6 +3824,9 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data, err_catas: mlx4_catas_end(&priv->dev); +err_crdump: + mlx4_crdump_end(&priv->dev); + err_release_regions: pci_release_regions(pdev); @@ -4081,6 +4088,7 @@ static void mlx4_remove_one(struct pci_dev *pdev) else mlx4_info(dev, "%s: interface is down\n", __func__); mlx4_catas_end(dev); + mlx4_crdump_end(dev); if (dev->flags & MLX4_FLAG_SRIOV && !active_vfs) { mlx4_warn(dev, "Disabling SR-IOV\n"); pci_disable_sriov(pdev); diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index 2ebaa3bee42f..6e016092a6f1 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -1042,6 +1042,8 @@ void mlx4_start_catas_poll(struct mlx4_dev *dev); void mlx4_stop_catas_poll(struct mlx4_dev *dev); int mlx4_catas_init(struct mlx4_dev *dev); void mlx4_catas_end(struct mlx4_dev *dev); +int mlx4_crdump_init(struct mlx4_dev *dev); +void mlx4_crdump_end(struct mlx4_dev *dev); int mlx4_restart_one(struct pci_dev *pdev, bool reload, struct devlink *devlink); int mlx4_register_device(struct mlx4_dev *dev); @@ -1228,6 +1230,8 @@ void mlx4_srq_event(struct mlx4_dev *dev, u32 srqn, int event_type); void mlx4_enter_error_state(struct mlx4_dev_persistent *persist); int mlx4_comm_internal_err(u32 slave_read); +int mlx4_crdump_collect(struct mlx4_dev *dev); + int mlx4_SENSE_PORT(struct mlx4_dev *dev, int port, enum mlx4_port_type *type); void mlx4_do_sense_ports(struct mlx4_dev *dev, diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index e3bfe76aea98..300b944e6e1e 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -852,6 +852,11 @@ struct mlx4_vf_dev { u8 n_ports; }; +struct mlx4_fw_crdump { + struct devlink_region *region_crspace; + struct devlink_region *region_fw_health; +}; + enum mlx4_pci_status { MLX4_PCI_STATUS_DISABLED, MLX4_PCI_STATUS_ENABLED, @@ -872,6 +877,7 @@ struct mlx4_dev_persistent { u8 interface_state; struct mutex pci_status_mutex; /* sync pci state */ enum mlx4_pci_status pci_status; + struct mlx4_fw_crdump crdump; }; struct mlx4_dev { -- cgit v1.2.3 From f6a69885f2e38be0229ab9f6a2d9d4a1b4ba2be5 Mon Sep 17 00:00:00 2001 From: Alex Vesker Date: Thu, 12 Jul 2018 15:13:17 +0300 Subject: devlink: Add generic parameters region_snapshot region_snapshot - When set enables capturing region snapshots Signed-off-by: Alex Vesker Signed-off-by: Jiri Pirko Reviewed-by: Moshe Shemesh Signed-off-by: David S. Miller --- include/net/devlink.h | 4 ++++ net/core/devlink.c | 5 +++++ 2 files changed, 9 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 905f0bb7b4ba..b9b89d6604d4 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -361,6 +361,7 @@ enum devlink_param_generic_id { DEVLINK_PARAM_GENERIC_ID_INT_ERR_RESET, DEVLINK_PARAM_GENERIC_ID_MAX_MACS, DEVLINK_PARAM_GENERIC_ID_ENABLE_SRIOV, + DEVLINK_PARAM_GENERIC_ID_REGION_SNAPSHOT, /* add new param generic ids above here*/ __DEVLINK_PARAM_GENERIC_ID_MAX, @@ -376,6 +377,9 @@ enum devlink_param_generic_id { #define DEVLINK_PARAM_GENERIC_ENABLE_SRIOV_NAME "enable_sriov" #define DEVLINK_PARAM_GENERIC_ENABLE_SRIOV_TYPE DEVLINK_PARAM_TYPE_BOOL +#define DEVLINK_PARAM_GENERIC_REGION_SNAPSHOT_NAME "region_snapshot_enable" +#define DEVLINK_PARAM_GENERIC_REGION_SNAPSHOT_TYPE DEVLINK_PARAM_TYPE_BOOL + #define DEVLINK_PARAM_GENERIC(_id, _cmodes, _get, _set, _validate) \ { \ .id = DEVLINK_PARAM_GENERIC_ID_##_id, \ diff --git a/net/core/devlink.c b/net/core/devlink.c index e5118dba6bb4..65fc366a78a4 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -2671,6 +2671,11 @@ static const struct devlink_param devlink_param_generic[] = { .name = DEVLINK_PARAM_GENERIC_ENABLE_SRIOV_NAME, .type = DEVLINK_PARAM_GENERIC_ENABLE_SRIOV_TYPE, }, + { + .id = DEVLINK_PARAM_GENERIC_ID_REGION_SNAPSHOT, + .name = DEVLINK_PARAM_GENERIC_REGION_SNAPSHOT_NAME, + .type = DEVLINK_PARAM_GENERIC_REGION_SNAPSHOT_TYPE, + }, }; static int devlink_param_generic_verify(const struct devlink_param *param) -- cgit v1.2.3 From 3c641ba4a852cf4e90e3d7f29c5df08e24213c5d Mon Sep 17 00:00:00 2001 From: Alex Vesker Date: Thu, 12 Jul 2018 15:13:18 +0300 Subject: net/mlx4_core: Use devlink region_snapshot parameter This parameter enables capturing region snapshot of the crspace during critical errors. The default value of this parameter is disabled, it can be enabled using devlink param commands. It is possible to configure during runtime and also driver init. Signed-off-by: Alex Vesker Signed-off-by: Jiri Pirko Reviewed-by: Moshe Shemesh Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/crdump.c | 8 ++++++ drivers/net/ethernet/mellanox/mlx4/main.c | 41 +++++++++++++++++++++++++++++ include/linux/mlx4/device.h | 1 + 3 files changed, 50 insertions(+) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx4/crdump.c b/drivers/net/ethernet/mellanox/mlx4/crdump.c index 4d5524dffec4..88316c743820 100644 --- a/drivers/net/ethernet/mellanox/mlx4/crdump.c +++ b/drivers/net/ethernet/mellanox/mlx4/crdump.c @@ -158,6 +158,7 @@ static void mlx4_crdump_collect_fw_health(struct mlx4_dev *dev, int mlx4_crdump_collect(struct mlx4_dev *dev) { struct devlink *devlink = priv_to_devlink(mlx4_priv(dev)); + struct mlx4_fw_crdump *crdump = &dev->persist->crdump; struct pci_dev *pdev = dev->persist->pdev; unsigned long cr_res_size; u8 __iomem *cr_space; @@ -168,6 +169,11 @@ int mlx4_crdump_collect(struct mlx4_dev *dev) return 0; } + if (!crdump->snapshot_enable) { + mlx4_info(dev, "crdump: devlink snapshot disabled, skipping\n"); + return 0; + } + cr_res_size = pci_resource_len(pdev, 0); cr_space = ioremap(pci_resource_start(pdev, 0), cr_res_size); @@ -197,6 +203,8 @@ int mlx4_crdump_init(struct mlx4_dev *dev) struct mlx4_fw_crdump *crdump = &dev->persist->crdump; struct pci_dev *pdev = dev->persist->pdev; + crdump->snapshot_enable = false; + /* Create cr-space region */ crdump->region_crspace = devlink_region_create(devlink, diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 46b021409b8b..2d979a652b7b 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -191,6 +191,26 @@ static int mlx4_devlink_ierr_reset_set(struct devlink *devlink, u32 id, return 0; } +static int mlx4_devlink_crdump_snapshot_get(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx) +{ + struct mlx4_priv *priv = devlink_priv(devlink); + struct mlx4_dev *dev = &priv->dev; + + ctx->val.vbool = dev->persist->crdump.snapshot_enable; + return 0; +} + +static int mlx4_devlink_crdump_snapshot_set(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx) +{ + struct mlx4_priv *priv = devlink_priv(devlink); + struct mlx4_dev *dev = &priv->dev; + + dev->persist->crdump.snapshot_enable = ctx->val.vbool; + return 0; +} + static int mlx4_devlink_max_macs_validate(struct devlink *devlink, u32 id, union devlink_param_value val, @@ -224,6 +244,11 @@ static const struct devlink_param mlx4_devlink_params[] = { DEVLINK_PARAM_GENERIC(MAX_MACS, BIT(DEVLINK_PARAM_CMODE_DRIVERINIT), NULL, NULL, mlx4_devlink_max_macs_validate), + DEVLINK_PARAM_GENERIC(REGION_SNAPSHOT, + BIT(DEVLINK_PARAM_CMODE_RUNTIME) | + BIT(DEVLINK_PARAM_CMODE_DRIVERINIT), + mlx4_devlink_crdump_snapshot_get, + mlx4_devlink_crdump_snapshot_set, NULL), DEVLINK_PARAM_DRIVER(MLX4_DEVLINK_PARAM_ID_ENABLE_64B_CQE_EQE, "enable_64b_cqe_eqe", DEVLINK_PARAM_TYPE_BOOL, BIT(DEVLINK_PARAM_CMODE_DRIVERINIT), @@ -270,6 +295,11 @@ static void mlx4_devlink_set_params_init_values(struct devlink *devlink) mlx4_devlink_set_init_value(devlink, MLX4_DEVLINK_PARAM_ID_ENABLE_4K_UAR, value); + + value.vbool = false; + mlx4_devlink_set_init_value(devlink, + DEVLINK_PARAM_GENERIC_ID_REGION_SNAPSHOT, + value); } static inline void mlx4_set_num_reserved_uars(struct mlx4_dev *dev, @@ -3862,6 +3892,9 @@ static int mlx4_devlink_port_type_set(struct devlink_port *devlink_port, static void mlx4_devlink_param_load_driverinit_values(struct devlink *devlink) { + struct mlx4_priv *priv = devlink_priv(devlink); + struct mlx4_dev *dev = &priv->dev; + struct mlx4_fw_crdump *crdump = &dev->persist->crdump; union devlink_param_value saved_value; int err; @@ -3889,6 +3922,14 @@ static void mlx4_devlink_param_load_driverinit_values(struct devlink *devlink) &saved_value); if (!err) enable_4k_uar = saved_value.vbool; + err = devlink_param_driverinit_value_get(devlink, + DEVLINK_PARAM_GENERIC_ID_REGION_SNAPSHOT, + &saved_value); + if (!err && crdump->snapshot_enable != saved_value.vbool) { + crdump->snapshot_enable = saved_value.vbool; + devlink_param_value_changed(devlink, + DEVLINK_PARAM_GENERIC_ID_REGION_SNAPSHOT); + } } static int mlx4_devlink_reload(struct devlink *devlink, diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 300b944e6e1e..dca6ab4eaa99 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -853,6 +853,7 @@ struct mlx4_vf_dev { }; struct mlx4_fw_crdump { + bool snapshot_enable; struct devlink_region *region_crspace; struct devlink_region *region_fw_health; }; -- cgit v1.2.3 From afed7bcf9487bb28e2e2b016a195085c07416c0b Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 11 Jul 2018 10:36:07 +0100 Subject: locking/refcount: Always allow checked forms In many cases, it would be useful to be able to use the full sanity-checked refcount helpers regardless of CONFIG_REFCOUNT_FULL, as this would help to avoid duplicate warnings where callers try to sanity-check refcount manipulation. This patch refactors things such that the full refcount helpers were always built, as refcount_${op}_checked(), such that they can be used regardless of CONFIG_REFCOUNT_FULL. This will allow code which *always* wants a checked refcount to opt-in, avoiding the need to duplicate the logic for warnings. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Reviewed-by: David Sterba Acked-by: Kees Cook Acked-by: Will Deacon Cc: Boqun Feng Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20180711093607.1644-1-mark.rutland@arm.com Signed-off-by: Ingo Molnar --- include/linux/refcount.h | 27 +++++++++++++++++------- lib/refcount.c | 53 +++++++++++++++++++++++------------------------- 2 files changed, 45 insertions(+), 35 deletions(-) (limited to 'include') diff --git a/include/linux/refcount.h b/include/linux/refcount.h index c36addd27dd5..53c5eca24d83 100644 --- a/include/linux/refcount.h +++ b/include/linux/refcount.h @@ -43,17 +43,30 @@ static inline unsigned int refcount_read(const refcount_t *r) return atomic_read(&r->refs); } +extern __must_check bool refcount_add_not_zero_checked(unsigned int i, refcount_t *r); +extern void refcount_add_checked(unsigned int i, refcount_t *r); + +extern __must_check bool refcount_inc_not_zero_checked(refcount_t *r); +extern void refcount_inc_checked(refcount_t *r); + +extern __must_check bool refcount_sub_and_test_checked(unsigned int i, refcount_t *r); + +extern __must_check bool refcount_dec_and_test_checked(refcount_t *r); +extern void refcount_dec_checked(refcount_t *r); + #ifdef CONFIG_REFCOUNT_FULL -extern __must_check bool refcount_add_not_zero(unsigned int i, refcount_t *r); -extern void refcount_add(unsigned int i, refcount_t *r); -extern __must_check bool refcount_inc_not_zero(refcount_t *r); -extern void refcount_inc(refcount_t *r); +#define refcount_add_not_zero refcount_add_not_zero_checked +#define refcount_add refcount_add_checked + +#define refcount_inc_not_zero refcount_inc_not_zero_checked +#define refcount_inc refcount_inc_checked + +#define refcount_sub_and_test refcount_sub_and_test_checked -extern __must_check bool refcount_sub_and_test(unsigned int i, refcount_t *r); +#define refcount_dec_and_test refcount_dec_and_test_checked +#define refcount_dec refcount_dec_checked -extern __must_check bool refcount_dec_and_test(refcount_t *r); -extern void refcount_dec(refcount_t *r); #else # ifdef CONFIG_ARCH_HAS_REFCOUNT # include diff --git a/lib/refcount.c b/lib/refcount.c index 4bd842f20749..5c4aaefc0682 100644 --- a/lib/refcount.c +++ b/lib/refcount.c @@ -40,10 +40,8 @@ #include #include -#ifdef CONFIG_REFCOUNT_FULL - /** - * refcount_add_not_zero - add a value to a refcount unless it is 0 + * refcount_add_not_zero_checked - add a value to a refcount unless it is 0 * @i: the value to add to the refcount * @r: the refcount * @@ -60,7 +58,7 @@ * * Return: false if the passed refcount is 0, true otherwise */ -bool refcount_add_not_zero(unsigned int i, refcount_t *r) +bool refcount_add_not_zero_checked(unsigned int i, refcount_t *r) { unsigned int new, val = atomic_read(&r->refs); @@ -81,10 +79,10 @@ bool refcount_add_not_zero(unsigned int i, refcount_t *r) return true; } -EXPORT_SYMBOL(refcount_add_not_zero); +EXPORT_SYMBOL(refcount_add_not_zero_checked); /** - * refcount_add - add a value to a refcount + * refcount_add_checked - add a value to a refcount * @i: the value to add to the refcount * @r: the refcount * @@ -99,14 +97,14 @@ EXPORT_SYMBOL(refcount_add_not_zero); * cases, refcount_inc(), or one of its variants, should instead be used to * increment a reference count. */ -void refcount_add(unsigned int i, refcount_t *r) +void refcount_add_checked(unsigned int i, refcount_t *r) { - WARN_ONCE(!refcount_add_not_zero(i, r), "refcount_t: addition on 0; use-after-free.\n"); + WARN_ONCE(!refcount_add_not_zero_checked(i, r), "refcount_t: addition on 0; use-after-free.\n"); } -EXPORT_SYMBOL(refcount_add); +EXPORT_SYMBOL(refcount_add_checked); /** - * refcount_inc_not_zero - increment a refcount unless it is 0 + * refcount_inc_not_zero_checked - increment a refcount unless it is 0 * @r: the refcount to increment * * Similar to atomic_inc_not_zero(), but will saturate at UINT_MAX and WARN. @@ -117,7 +115,7 @@ EXPORT_SYMBOL(refcount_add); * * Return: true if the increment was successful, false otherwise */ -bool refcount_inc_not_zero(refcount_t *r) +bool refcount_inc_not_zero_checked(refcount_t *r) { unsigned int new, val = atomic_read(&r->refs); @@ -136,10 +134,10 @@ bool refcount_inc_not_zero(refcount_t *r) return true; } -EXPORT_SYMBOL(refcount_inc_not_zero); +EXPORT_SYMBOL(refcount_inc_not_zero_checked); /** - * refcount_inc - increment a refcount + * refcount_inc_checked - increment a refcount * @r: the refcount to increment * * Similar to atomic_inc(), but will saturate at UINT_MAX and WARN. @@ -150,14 +148,14 @@ EXPORT_SYMBOL(refcount_inc_not_zero); * Will WARN if the refcount is 0, as this represents a possible use-after-free * condition. */ -void refcount_inc(refcount_t *r) +void refcount_inc_checked(refcount_t *r) { - WARN_ONCE(!refcount_inc_not_zero(r), "refcount_t: increment on 0; use-after-free.\n"); + WARN_ONCE(!refcount_inc_not_zero_checked(r), "refcount_t: increment on 0; use-after-free.\n"); } -EXPORT_SYMBOL(refcount_inc); +EXPORT_SYMBOL(refcount_inc_checked); /** - * refcount_sub_and_test - subtract from a refcount and test if it is 0 + * refcount_sub_and_test_checked - subtract from a refcount and test if it is 0 * @i: amount to subtract from the refcount * @r: the refcount * @@ -176,7 +174,7 @@ EXPORT_SYMBOL(refcount_inc); * * Return: true if the resulting refcount is 0, false otherwise */ -bool refcount_sub_and_test(unsigned int i, refcount_t *r) +bool refcount_sub_and_test_checked(unsigned int i, refcount_t *r) { unsigned int new, val = atomic_read(&r->refs); @@ -194,10 +192,10 @@ bool refcount_sub_and_test(unsigned int i, refcount_t *r) return !new; } -EXPORT_SYMBOL(refcount_sub_and_test); +EXPORT_SYMBOL(refcount_sub_and_test_checked); /** - * refcount_dec_and_test - decrement a refcount and test if it is 0 + * refcount_dec_and_test_checked - decrement a refcount and test if it is 0 * @r: the refcount * * Similar to atomic_dec_and_test(), it will WARN on underflow and fail to @@ -209,14 +207,14 @@ EXPORT_SYMBOL(refcount_sub_and_test); * * Return: true if the resulting refcount is 0, false otherwise */ -bool refcount_dec_and_test(refcount_t *r) +bool refcount_dec_and_test_checked(refcount_t *r) { - return refcount_sub_and_test(1, r); + return refcount_sub_and_test_checked(1, r); } -EXPORT_SYMBOL(refcount_dec_and_test); +EXPORT_SYMBOL(refcount_dec_and_test_checked); /** - * refcount_dec - decrement a refcount + * refcount_dec_checked - decrement a refcount * @r: the refcount * * Similar to atomic_dec(), it will WARN on underflow and fail to decrement @@ -225,12 +223,11 @@ EXPORT_SYMBOL(refcount_dec_and_test); * Provides release memory ordering, such that prior loads and stores are done * before. */ -void refcount_dec(refcount_t *r) +void refcount_dec_checked(refcount_t *r) { - WARN_ONCE(refcount_dec_and_test(r), "refcount_t: decrement hit 0; leaking memory.\n"); + WARN_ONCE(refcount_dec_and_test_checked(r), "refcount_t: decrement hit 0; leaking memory.\n"); } -EXPORT_SYMBOL(refcount_dec); -#endif /* CONFIG_REFCOUNT_FULL */ +EXPORT_SYMBOL(refcount_dec_checked); /** * refcount_dec_if_one - decrement a refcount if it is 1 -- cgit v1.2.3 From 05814a10370b3252fe2b0898b6adac3cdd531096 Mon Sep 17 00:00:00 2001 From: Vladimir Zapolskiy Date: Fri, 13 Jul 2018 17:07:26 +0300 Subject: block: remove blkdev_entry_to_request() macro Remove blkdev_entry_to_request() macro, which remained unused through the observable history, also note that it repeats list_entry_rq() macro verbatim. Signed-off-by: Vladimir Zapolskiy Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 137759862f07..1939ed95f936 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1436,8 +1436,6 @@ enum blk_default_limits { BLK_SEG_BOUNDARY_MASK = 0xFFFFFFFFUL, }; -#define blkdev_entry_to_request(entry) list_entry((entry), struct request, queuelist) - static inline unsigned long queue_segment_boundary(struct request_queue *q) { return q->limits.seg_boundary_mask; -- cgit v1.2.3 From 8e1b706b6e819bed215c0db16345568864660393 Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Fri, 13 Jul 2018 16:23:23 +0200 Subject: cpu/hotplug: Expose SMT control init function The L1TF mitigation will gain a commend line parameter which allows to set a combination of hypervisor mitigation and SMT control. Expose cpu_smt_disable() so the command line parser can tweak SMT settings. [ tglx: Split out of larger patch and made it preserve an already existing force off state ] Signed-off-by: Jiri Kosina Signed-off-by: Thomas Gleixner Tested-by: Jiri Kosina Reviewed-by: Greg Kroah-Hartman Reviewed-by: Josh Poimboeuf Link: https://lkml.kernel.org/r/20180713142323.039715135@linutronix.de --- include/linux/cpu.h | 2 ++ kernel/cpu.c | 16 +++++++++++++--- 2 files changed, 15 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 7532cbf27b1d..c9b23ad27b38 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -177,8 +177,10 @@ enum cpuhp_smt_control { #if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_SMT) extern enum cpuhp_smt_control cpu_smt_control; +extern void cpu_smt_disable(bool force); #else # define cpu_smt_control (CPU_SMT_ENABLED) +static inline void cpu_smt_disable(bool force) { } #endif #endif /* _LINUX_CPU_H_ */ diff --git a/kernel/cpu.c b/kernel/cpu.c index d79e24df2420..8453e31f2d1a 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -347,13 +347,23 @@ EXPORT_SYMBOL_GPL(cpu_hotplug_enable); enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED; EXPORT_SYMBOL_GPL(cpu_smt_control); -static int __init smt_cmdline_disable(char *str) +void __init cpu_smt_disable(bool force) { - cpu_smt_control = CPU_SMT_DISABLED; - if (str && !strcmp(str, "force")) { + if (cpu_smt_control == CPU_SMT_FORCE_DISABLED || + cpu_smt_control == CPU_SMT_NOT_SUPPORTED) + return; + + if (force) { pr_info("SMT: Force disabled\n"); cpu_smt_control = CPU_SMT_FORCE_DISABLED; + } else { + cpu_smt_control = CPU_SMT_DISABLED; } +} + +static int __init smt_cmdline_disable(char *str) +{ + cpu_smt_disable(str && !strcmp(str, "force")); return 0; } early_param("nosmt", smt_cmdline_disable); -- cgit v1.2.3 From fee0aede6f4739c87179eca76136f83210953b86 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 13 Jul 2018 16:23:24 +0200 Subject: cpu/hotplug: Set CPU_SMT_NOT_SUPPORTED early The CPU_SMT_NOT_SUPPORTED state is set (if the processor does not support SMT) when the sysfs SMT control file is initialized. That was fine so far as this was only required to make the output of the control file correct and to prevent writes in that case. With the upcoming l1tf command line parameter, this needs to be set up before the L1TF mitigation selection and command line parsing happens. Signed-off-by: Thomas Gleixner Tested-by: Jiri Kosina Reviewed-by: Greg Kroah-Hartman Reviewed-by: Josh Poimboeuf Link: https://lkml.kernel.org/r/20180713142323.121795971@linutronix.de --- arch/x86/kernel/cpu/bugs.c | 6 ++++++ include/linux/cpu.h | 2 ++ kernel/cpu.c | 13 ++++++++++--- 3 files changed, 18 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 7df7df9a2753..4be69a7bef0b 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -58,6 +58,12 @@ void __init check_bugs(void) { identify_boot_cpu(); + /* + * identify_boot_cpu() initialized SMT support information, let the + * core code know. + */ + cpu_smt_check_topology(); + if (!IS_ENABLED(CONFIG_SMP)) { pr_info("CPU: "); print_cpu_info(&boot_cpu_data); diff --git a/include/linux/cpu.h b/include/linux/cpu.h index c9b23ad27b38..ccdf3a67ce56 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -178,9 +178,11 @@ enum cpuhp_smt_control { #if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_SMT) extern enum cpuhp_smt_control cpu_smt_control; extern void cpu_smt_disable(bool force); +extern void cpu_smt_check_topology(void); #else # define cpu_smt_control (CPU_SMT_ENABLED) static inline void cpu_smt_disable(bool force) { } +static inline void cpu_smt_check_topology(void) { } #endif #endif /* _LINUX_CPU_H_ */ diff --git a/kernel/cpu.c b/kernel/cpu.c index 8453e31f2d1a..37eec872042b 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -361,6 +361,16 @@ void __init cpu_smt_disable(bool force) } } +/* + * The decision whether SMT is supported can only be done after the full + * CPU identification. Called from architecture code. + */ +void __init cpu_smt_check_topology(void) +{ + if (!topology_smt_supported()) + cpu_smt_control = CPU_SMT_NOT_SUPPORTED; +} + static int __init smt_cmdline_disable(char *str) { cpu_smt_disable(str && !strcmp(str, "force")); @@ -2115,9 +2125,6 @@ static const struct attribute_group cpuhp_smt_attr_group = { static int __init cpu_smt_state_init(void) { - if (!topology_smt_supported()) - cpu_smt_control = CPU_SMT_NOT_SUPPORTED; - return sysfs_create_group(&cpu_subsys.dev_root->kobj, &cpuhp_smt_attr_group); } -- cgit v1.2.3 From 2c6d1fffa1d9b0a5b5ac1a23be9ad64abe60910d Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Wed, 11 Jul 2018 15:29:07 +0200 Subject: drm: add support for DisplayPort CEC-Tunneling-over-AUX MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This adds support for the DisplayPort CEC-Tunneling-over-AUX feature that is part of the DisplayPort 1.3 standard. Unfortunately, not all DisplayPort/USB-C to HDMI adapters with a chip that has this capability actually hook up the CEC pin, so even though a CEC device is created, it may not actually work. Signed-off-by: Hans Verkuil Reviewed-by: Ville Syrjälä Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20180711132909.25409-2-hverkuil@xs4all.nl --- drivers/gpu/drm/Kconfig | 10 + drivers/gpu/drm/Makefile | 1 + drivers/gpu/drm/drm_dp_cec.c | 428 ++++++++++++++++++++++++++++++++++++++++ drivers/gpu/drm/drm_dp_helper.c | 1 + include/drm/drm_dp_helper.h | 56 ++++++ 5 files changed, 496 insertions(+) create mode 100644 drivers/gpu/drm/drm_dp_cec.c (limited to 'include') diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index a8054dde49b5..cb88528e7b10 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -122,6 +122,16 @@ config DRM_LOAD_EDID_FIRMWARE default case is N. Details and instructions how to build your own EDID data are given in Documentation/EDID/HOWTO.txt. +config DRM_DP_CEC + bool "Enable DisplayPort CEC-Tunneling-over-AUX HDMI support" + select CEC_CORE + help + Choose this option if you want to enable HDMI CEC support for + DisplayPort/USB-C to HDMI adapters. + + Note: not all adapters support this feature, and even for those + that do support this they often do not hook up the CEC pin. + config DRM_TTM tristate depends on DRM && MMU diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile index 0e0a3ef1abad..a6771cef85e2 100644 --- a/drivers/gpu/drm/Makefile +++ b/drivers/gpu/drm/Makefile @@ -41,6 +41,7 @@ drm_kms_helper-$(CONFIG_DRM_PANEL_BRIDGE) += bridge/panel.o drm_kms_helper-$(CONFIG_DRM_FBDEV_EMULATION) += drm_fb_helper.o drm_kms_helper-$(CONFIG_DRM_KMS_CMA_HELPER) += drm_fb_cma_helper.o drm_kms_helper-$(CONFIG_DRM_DP_AUX_CHARDEV) += drm_dp_aux_dev.o +drm_kms_helper-$(CONFIG_DRM_DP_CEC) += drm_dp_cec.o obj-$(CONFIG_DRM_KMS_HELPER) += drm_kms_helper.o obj-$(CONFIG_DRM_DEBUG_SELFTEST) += selftests/ diff --git a/drivers/gpu/drm/drm_dp_cec.c b/drivers/gpu/drm/drm_dp_cec.c new file mode 100644 index 000000000000..ddb1c5adebb9 --- /dev/null +++ b/drivers/gpu/drm/drm_dp_cec.c @@ -0,0 +1,428 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * DisplayPort CEC-Tunneling-over-AUX support + * + * Copyright 2018 Cisco Systems, Inc. and/or its affiliates. All rights reserved. + */ + +#include +#include +#include +#include +#include + +/* + * Unfortunately it turns out that we have a chicken-and-egg situation + * here. Quite a few active (mini-)DP-to-HDMI or USB-C-to-HDMI adapters + * have a converter chip that supports CEC-Tunneling-over-AUX (usually the + * Parade PS176), but they do not wire up the CEC pin, thus making CEC + * useless. + * + * Sadly there is no way for this driver to know this. What happens is + * that a /dev/cecX device is created that is isolated and unable to see + * any of the other CEC devices. Quite literally the CEC wire is cut + * (or in this case, never connected in the first place). + * + * The reason so few adapters support this is that this tunneling protocol + * was never supported by any OS. So there was no easy way of testing it, + * and no incentive to correctly wire up the CEC pin. + * + * Hopefully by creating this driver it will be easier for vendors to + * finally fix their adapters and test the CEC functionality. + * + * I keep a list of known working adapters here: + * + * https://hverkuil.home.xs4all.nl/cec-status.txt + * + * Please mail me (hverkuil@xs4all.nl) if you find an adapter that works + * and is not yet listed there. + * + * Note that the current implementation does not support CEC over an MST hub. + * As far as I can see there is no mechanism defined in the DisplayPort + * standard to transport CEC interrupts over an MST device. It might be + * possible to do this through polling, but I have not been able to get that + * to work. + */ + +/** + * DOC: dp cec helpers + * + * These functions take care of supporting the CEC-Tunneling-over-AUX + * feature of DisplayPort-to-HDMI adapters. + */ + +/* + * When the EDID is unset because the HPD went low, then the CEC DPCD registers + * typically can no longer be read (true for a DP-to-HDMI adapter since it is + * powered by the HPD). However, some displays toggle the HPD off and on for a + * short period for one reason or another, and that would cause the CEC adapter + * to be removed and added again, even though nothing else changed. + * + * This module parameter sets a delay in seconds before the CEC adapter is + * actually unregistered. Only if the HPD does not return within that time will + * the CEC adapter be unregistered. + * + * If it is set to a value >= NEVER_UNREG_DELAY, then the CEC adapter will never + * be unregistered for as long as the connector remains registered. + * + * If it is set to 0, then the CEC adapter will be unregistered immediately as + * soon as the HPD disappears. + * + * The default is one second to prevent short HPD glitches from unregistering + * the CEC adapter. + * + * Note that for integrated HDMI branch devices that support CEC the DPCD + * registers remain available even if the HPD goes low since it is not powered + * by the HPD. In that case the CEC adapter will never be unregistered during + * the life time of the connector. At least, this is the theory since I do not + * have hardware with an integrated HDMI branch device that supports CEC. + */ +#define NEVER_UNREG_DELAY 1000 +static unsigned int drm_dp_cec_unregister_delay = 1; +module_param(drm_dp_cec_unregister_delay, uint, 0600); +MODULE_PARM_DESC(drm_dp_cec_unregister_delay, + "CEC unregister delay in seconds, 0: no delay, >= 1000: never unregister"); + +static int drm_dp_cec_adap_enable(struct cec_adapter *adap, bool enable) +{ + struct drm_dp_aux *aux = cec_get_drvdata(adap); + u32 val = enable ? DP_CEC_TUNNELING_ENABLE : 0; + ssize_t err = 0; + + err = drm_dp_dpcd_writeb(aux, DP_CEC_TUNNELING_CONTROL, val); + return (enable && err < 0) ? err : 0; +} + +static int drm_dp_cec_adap_log_addr(struct cec_adapter *adap, u8 addr) +{ + struct drm_dp_aux *aux = cec_get_drvdata(adap); + /* Bit 15 (logical address 15) should always be set */ + u16 la_mask = 1 << CEC_LOG_ADDR_BROADCAST; + u8 mask[2]; + ssize_t err; + + if (addr != CEC_LOG_ADDR_INVALID) + la_mask |= adap->log_addrs.log_addr_mask | (1 << addr); + mask[0] = la_mask & 0xff; + mask[1] = la_mask >> 8; + err = drm_dp_dpcd_write(aux, DP_CEC_LOGICAL_ADDRESS_MASK, mask, 2); + return (addr != CEC_LOG_ADDR_INVALID && err < 0) ? err : 0; +} + +static int drm_dp_cec_adap_transmit(struct cec_adapter *adap, u8 attempts, + u32 signal_free_time, struct cec_msg *msg) +{ + struct drm_dp_aux *aux = cec_get_drvdata(adap); + unsigned int retries = min(5, attempts - 1); + ssize_t err; + + err = drm_dp_dpcd_write(aux, DP_CEC_TX_MESSAGE_BUFFER, + msg->msg, msg->len); + if (err < 0) + return err; + + err = drm_dp_dpcd_writeb(aux, DP_CEC_TX_MESSAGE_INFO, + (msg->len - 1) | (retries << 4) | + DP_CEC_TX_MESSAGE_SEND); + return err < 0 ? err : 0; +} + +static int drm_dp_cec_adap_monitor_all_enable(struct cec_adapter *adap, + bool enable) +{ + struct drm_dp_aux *aux = cec_get_drvdata(adap); + ssize_t err; + u8 val; + + if (!(adap->capabilities & CEC_CAP_MONITOR_ALL)) + return 0; + + err = drm_dp_dpcd_readb(aux, DP_CEC_TUNNELING_CONTROL, &val); + if (err >= 0) { + if (enable) + val |= DP_CEC_SNOOPING_ENABLE; + else + val &= ~DP_CEC_SNOOPING_ENABLE; + err = drm_dp_dpcd_writeb(aux, DP_CEC_TUNNELING_CONTROL, val); + } + return (enable && err < 0) ? err : 0; +} + +static void drm_dp_cec_adap_status(struct cec_adapter *adap, + struct seq_file *file) +{ + struct drm_dp_aux *aux = cec_get_drvdata(adap); + struct drm_dp_desc desc; + struct drm_dp_dpcd_ident *id = &desc.ident; + + if (drm_dp_read_desc(aux, &desc, true)) + return; + seq_printf(file, "OUI: %*pdH\n", + (int)sizeof(id->oui), id->oui); + seq_printf(file, "ID: %*pE\n", + (int)strnlen(id->device_id, sizeof(id->device_id)), + id->device_id); + seq_printf(file, "HW Rev: %d.%d\n", id->hw_rev >> 4, id->hw_rev & 0xf); + /* + * Show this both in decimal and hex: at least one vendor + * always reports this in hex. + */ + seq_printf(file, "FW/SW Rev: %d.%d (0x%02x.0x%02x)\n", + id->sw_major_rev, id->sw_minor_rev, + id->sw_major_rev, id->sw_minor_rev); +} + +static const struct cec_adap_ops drm_dp_cec_adap_ops = { + .adap_enable = drm_dp_cec_adap_enable, + .adap_log_addr = drm_dp_cec_adap_log_addr, + .adap_transmit = drm_dp_cec_adap_transmit, + .adap_monitor_all_enable = drm_dp_cec_adap_monitor_all_enable, + .adap_status = drm_dp_cec_adap_status, +}; + +static int drm_dp_cec_received(struct drm_dp_aux *aux) +{ + struct cec_adapter *adap = aux->cec.adap; + struct cec_msg msg; + u8 rx_msg_info; + ssize_t err; + + err = drm_dp_dpcd_readb(aux, DP_CEC_RX_MESSAGE_INFO, &rx_msg_info); + if (err < 0) + return err; + + if (!(rx_msg_info & DP_CEC_RX_MESSAGE_ENDED)) + return 0; + + msg.len = (rx_msg_info & DP_CEC_RX_MESSAGE_LEN_MASK) + 1; + err = drm_dp_dpcd_read(aux, DP_CEC_RX_MESSAGE_BUFFER, msg.msg, msg.len); + if (err < 0) + return err; + + cec_received_msg(adap, &msg); + return 0; +} + +static void drm_dp_cec_handle_irq(struct drm_dp_aux *aux) +{ + struct cec_adapter *adap = aux->cec.adap; + u8 flags; + + if (drm_dp_dpcd_readb(aux, DP_CEC_TUNNELING_IRQ_FLAGS, &flags) < 0) + return; + + if (flags & DP_CEC_RX_MESSAGE_INFO_VALID) + drm_dp_cec_received(aux); + + if (flags & DP_CEC_TX_MESSAGE_SENT) + cec_transmit_attempt_done(adap, CEC_TX_STATUS_OK); + else if (flags & DP_CEC_TX_LINE_ERROR) + cec_transmit_attempt_done(adap, CEC_TX_STATUS_ERROR | + CEC_TX_STATUS_MAX_RETRIES); + else if (flags & + (DP_CEC_TX_ADDRESS_NACK_ERROR | DP_CEC_TX_DATA_NACK_ERROR)) + cec_transmit_attempt_done(adap, CEC_TX_STATUS_NACK | + CEC_TX_STATUS_MAX_RETRIES); + drm_dp_dpcd_writeb(aux, DP_CEC_TUNNELING_IRQ_FLAGS, flags); +} + +/** + * drm_dp_cec_irq() - handle CEC interrupt, if any + * @aux: DisplayPort AUX channel + * + * Should be called when handling an IRQ_HPD request. If CEC-tunneling-over-AUX + * is present, then it will check for a CEC_IRQ and handle it accordingly. + */ +void drm_dp_cec_irq(struct drm_dp_aux *aux) +{ + u8 cec_irq; + int ret; + + mutex_lock(&aux->cec.lock); + if (!aux->cec.adap) + goto unlock; + + ret = drm_dp_dpcd_readb(aux, DP_DEVICE_SERVICE_IRQ_VECTOR_ESI1, + &cec_irq); + if (ret < 0 || !(cec_irq & DP_CEC_IRQ)) + goto unlock; + + drm_dp_cec_handle_irq(aux); + drm_dp_dpcd_writeb(aux, DP_DEVICE_SERVICE_IRQ_VECTOR_ESI1, DP_CEC_IRQ); +unlock: + mutex_unlock(&aux->cec.lock); +} +EXPORT_SYMBOL(drm_dp_cec_irq); + +static bool drm_dp_cec_cap(struct drm_dp_aux *aux, u8 *cec_cap) +{ + u8 cap = 0; + + if (drm_dp_dpcd_readb(aux, DP_CEC_TUNNELING_CAPABILITY, &cap) != 1 || + !(cap & DP_CEC_TUNNELING_CAPABLE)) + return false; + if (cec_cap) + *cec_cap = cap; + return true; +} + +/* + * Called if the HPD was low for more than drm_dp_cec_unregister_delay + * seconds. This unregisters the CEC adapter. + */ +static void drm_dp_cec_unregister_work(struct work_struct *work) +{ + struct drm_dp_aux *aux = container_of(work, struct drm_dp_aux, + cec.unregister_work.work); + + mutex_lock(&aux->cec.lock); + cec_unregister_adapter(aux->cec.adap); + aux->cec.adap = NULL; + mutex_unlock(&aux->cec.lock); +} + +/* + * A new EDID is set. If there is no CEC adapter, then create one. If + * there was a CEC adapter, then check if the CEC adapter properties + * were unchanged and just update the CEC physical address. Otherwise + * unregister the old CEC adapter and create a new one. + */ +void drm_dp_cec_set_edid(struct drm_dp_aux *aux, const struct edid *edid) +{ + u32 cec_caps = CEC_CAP_DEFAULTS | CEC_CAP_NEEDS_HPD; + unsigned int num_las = 1; + u8 cap; + +#ifndef CONFIG_MEDIA_CEC_RC + /* + * CEC_CAP_RC is part of CEC_CAP_DEFAULTS, but it is stripped by + * cec_allocate_adapter() if CONFIG_MEDIA_CEC_RC is undefined. + * + * Do this here as well to ensure the tests against cec_caps are + * correct. + */ + cec_caps &= ~CEC_CAP_RC; +#endif + cancel_delayed_work_sync(&aux->cec.unregister_work); + + mutex_lock(&aux->cec.lock); + if (!drm_dp_cec_cap(aux, &cap)) { + /* CEC is not supported, unregister any existing adapter */ + cec_unregister_adapter(aux->cec.adap); + aux->cec.adap = NULL; + goto unlock; + } + + if (cap & DP_CEC_SNOOPING_CAPABLE) + cec_caps |= CEC_CAP_MONITOR_ALL; + if (cap & DP_CEC_MULTIPLE_LA_CAPABLE) + num_las = CEC_MAX_LOG_ADDRS; + + if (aux->cec.adap) { + if (aux->cec.adap->capabilities == cec_caps && + aux->cec.adap->available_log_addrs == num_las) { + /* Unchanged, so just set the phys addr */ + cec_s_phys_addr_from_edid(aux->cec.adap, edid); + goto unlock; + } + /* + * The capabilities changed, so unregister the old + * adapter first. + */ + cec_unregister_adapter(aux->cec.adap); + } + + /* Create a new adapter */ + aux->cec.adap = cec_allocate_adapter(&drm_dp_cec_adap_ops, + aux, aux->cec.name, cec_caps, + num_las); + if (IS_ERR(aux->cec.adap)) { + aux->cec.adap = NULL; + goto unlock; + } + if (cec_register_adapter(aux->cec.adap, aux->cec.parent)) { + cec_delete_adapter(aux->cec.adap); + aux->cec.adap = NULL; + } else { + /* + * Update the phys addr for the new CEC adapter. When called + * from drm_dp_cec_register_connector() edid == NULL, so in + * that case the phys addr is just invalidated. + */ + cec_s_phys_addr_from_edid(aux->cec.adap, edid); + } +unlock: + mutex_unlock(&aux->cec.lock); +} +EXPORT_SYMBOL(drm_dp_cec_set_edid); + +/* + * The EDID disappeared (likely because of the HPD going down). + */ +void drm_dp_cec_unset_edid(struct drm_dp_aux *aux) +{ + cancel_delayed_work_sync(&aux->cec.unregister_work); + + mutex_lock(&aux->cec.lock); + if (!aux->cec.adap) + goto unlock; + + cec_phys_addr_invalidate(aux->cec.adap); + /* + * We're done if we want to keep the CEC device + * (drm_dp_cec_unregister_delay is >= NEVER_UNREG_DELAY) or if the + * DPCD still indicates the CEC capability (expected for an integrated + * HDMI branch device). + */ + if (drm_dp_cec_unregister_delay < NEVER_UNREG_DELAY && + !drm_dp_cec_cap(aux, NULL)) { + /* + * Unregister the CEC adapter after drm_dp_cec_unregister_delay + * seconds. This to debounce short HPD off-and-on cycles from + * displays. + */ + schedule_delayed_work(&aux->cec.unregister_work, + drm_dp_cec_unregister_delay * HZ); + } +unlock: + mutex_unlock(&aux->cec.lock); +} +EXPORT_SYMBOL(drm_dp_cec_unset_edid); + +/** + * drm_dp_cec_register_connector() - register a new connector + * @aux: DisplayPort AUX channel + * @name: name of the CEC device + * @parent: parent device + * + * A new connector was registered with associated CEC adapter name and + * CEC adapter parent device. After registering the name and parent + * drm_dp_cec_set_edid() is called to check if the connector supports + * CEC and to register a CEC adapter if that is the case. + */ +void drm_dp_cec_register_connector(struct drm_dp_aux *aux, const char *name, + struct device *parent) +{ + WARN_ON(aux->cec.adap); + aux->cec.name = name; + aux->cec.parent = parent; + INIT_DELAYED_WORK(&aux->cec.unregister_work, + drm_dp_cec_unregister_work); + + drm_dp_cec_set_edid(aux, NULL); +} +EXPORT_SYMBOL(drm_dp_cec_register_connector); + +/** + * drm_dp_cec_unregister_connector() - unregister the CEC adapter, if any + * @aux: DisplayPort AUX channel + */ +void drm_dp_cec_unregister_connector(struct drm_dp_aux *aux) +{ + if (!aux->cec.adap) + return; + cancel_delayed_work_sync(&aux->cec.unregister_work); + cec_unregister_adapter(aux->cec.adap); + aux->cec.adap = NULL; +} +EXPORT_SYMBOL(drm_dp_cec_unregister_connector); diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c index a7ba602a43a8..f4a06b54aa7d 100644 --- a/drivers/gpu/drm/drm_dp_helper.c +++ b/drivers/gpu/drm/drm_dp_helper.c @@ -1087,6 +1087,7 @@ static void drm_dp_aux_crc_work(struct work_struct *work) void drm_dp_aux_init(struct drm_dp_aux *aux) { mutex_init(&aux->hw_mutex); + mutex_init(&aux->cec.lock); INIT_WORK(&aux->crc_work, drm_dp_aux_crc_work); aux->ddc.algo = &drm_dp_i2c_algo; diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h index c01564991a9f..05cc31b5db16 100644 --- a/include/drm/drm_dp_helper.h +++ b/include/drm/drm_dp_helper.h @@ -1078,6 +1078,25 @@ struct drm_dp_aux_msg { size_t size; }; +struct cec_adapter; +struct edid; + +/** + * struct drm_dp_aux_cec - DisplayPort CEC-Tunneling-over-AUX + * @lock: mutex protecting this struct + * @adap: the CEC adapter for CEC-Tunneling-over-AUX support. + * @name: name of the CEC adapter + * @parent: parent device of the CEC adapter + * @unregister_work: unregister the CEC adapter + */ +struct drm_dp_aux_cec { + struct mutex lock; + struct cec_adapter *adap; + const char *name; + struct device *parent; + struct delayed_work unregister_work; +}; + /** * struct drm_dp_aux - DisplayPort AUX channel * @name: user-visible name of this AUX channel and the I2C-over-AUX adapter @@ -1136,6 +1155,10 @@ struct drm_dp_aux { * @i2c_defer_count: Counts I2C DEFERs, used for DP validation. */ unsigned i2c_defer_count; + /** + * @cec: struct containing fields used for CEC-Tunneling-over-AUX. + */ + struct drm_dp_aux_cec cec; }; ssize_t drm_dp_dpcd_read(struct drm_dp_aux *aux, unsigned int offset, @@ -1258,4 +1281,37 @@ drm_dp_has_quirk(const struct drm_dp_desc *desc, enum drm_dp_quirk quirk) return desc->quirks & BIT(quirk); } +#ifdef CONFIG_DRM_DP_CEC +void drm_dp_cec_irq(struct drm_dp_aux *aux); +void drm_dp_cec_register_connector(struct drm_dp_aux *aux, const char *name, + struct device *parent); +void drm_dp_cec_unregister_connector(struct drm_dp_aux *aux); +void drm_dp_cec_set_edid(struct drm_dp_aux *aux, const struct edid *edid); +void drm_dp_cec_unset_edid(struct drm_dp_aux *aux); +#else +static inline void drm_dp_cec_irq(struct drm_dp_aux *aux) +{ +} + +static inline void drm_dp_cec_register_connector(struct drm_dp_aux *aux, + const char *name, + struct device *parent) +{ +} + +static inline void drm_dp_cec_unregister_connector(struct drm_dp_aux *aux) +{ +} + +static inline void drm_dp_cec_set_edid(struct drm_dp_aux *aux, + const struct edid *edid) +{ +} + +static inline void drm_dp_cec_unset_edid(struct drm_dp_aux *aux) +{ +} + +#endif + #endif /* _DRM_DP_HELPER_H_ */ -- cgit v1.2.3 From 3e977ac6179b39faa3c0eda5fce4f00663ae298d Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Thu, 12 Jul 2018 19:53:13 +0100 Subject: drm/i915: Prevent writing into a read-only object via a GGTT mmap If the user has created a read-only object, they should not be allowed to circumvent the write protection by using a GGTT mmapping. Deny it. Also most machines do not support read-only GGTT PTEs, so again we have to reject attempted writes. Fortunately, this is known a priori, so we can at least reject in the call to create the mmap (with a sanity check in the fault handler). v2: Check the vma->vm_flags during mmap() to allow readonly access. v3: Remove VM_MAYWRITE to curtail mprotect() Testcase: igt/gem_userptr_blits/readonly_mmap* Signed-off-by: Chris Wilson Cc: Jon Bloomfield Cc: Joonas Lahtinen Cc: Matthew Auld Cc: David Herrmann Reviewed-by: Matthew Auld #v1 Reviewed-by: Jon Bloomfield Reviewed-by: Joonas Lahtinen Link: https://patchwork.freedesktop.org/patch/msgid/20180712185315.3288-4-chris@chris-wilson.co.uk --- drivers/gpu/drm/drm_gem.c | 9 +++++++++ drivers/gpu/drm/i915/i915_gem.c | 4 ++++ drivers/gpu/drm/i915/i915_gem_gtt.c | 12 +++++++----- drivers/gpu/drm/i915/i915_gem_object.h | 13 ++++++++++++- drivers/gpu/drm/i915/intel_ringbuffer.c | 2 +- drivers/gpu/drm/i915/selftests/i915_gem_context.c | 5 +++-- include/drm/drm_vma_manager.h | 1 + 7 files changed, 37 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index 4a16d7b26c89..bf90625df3c5 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -1036,6 +1036,15 @@ int drm_gem_mmap(struct file *filp, struct vm_area_struct *vma) return -EACCES; } + if (node->readonly) { + if (vma->vm_flags & VM_WRITE) { + drm_gem_object_put_unlocked(obj); + return -EINVAL; + } + + vma->vm_flags &= ~VM_MAYWRITE; + } + ret = drm_gem_mmap_obj(obj, drm_vma_node_size(node) << PAGE_SHIFT, vma); diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index ed2be33ec58a..1910c66f48e2 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -2012,6 +2012,10 @@ vm_fault_t i915_gem_fault(struct vm_fault *vmf) pgoff_t page_offset; int ret; + /* Sanity check that we allow writing into this object */ + if (i915_gem_object_is_readonly(obj) && write) + return VM_FAULT_SIGBUS; + /* We don't use vmf->pgoff since that has the fake offset */ page_offset = (vmf->address - area->vm_start) >> PAGE_SHIFT; diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 86a9618bab24..3d75f2bb5623 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -206,7 +206,7 @@ static int ppgtt_bind_vma(struct i915_vma *vma, /* Applicable to VLV, and gen8+ */ pte_flags = 0; - if (vma->obj->gt_ro) + if (i915_gem_object_is_readonly(vma->obj)) pte_flags |= PTE_READ_ONLY; vma->vm->insert_entries(vma->vm, vma, cache_level, pte_flags); @@ -2491,8 +2491,10 @@ static void gen8_ggtt_insert_entries(struct i915_address_space *vm, const gen8_pte_t pte_encode = gen8_pte_encode(0, level, 0); dma_addr_t addr; - /* The GTT does not support read-only mappings */ - GEM_BUG_ON(flags & PTE_READ_ONLY); + /* + * Note that we ignore PTE_READ_ONLY here. The caller must be careful + * not to allow the user to override access to a read only page. + */ gtt_entries = (gen8_pte_t __iomem *)ggtt->gsm; gtt_entries += vma->node.start >> PAGE_SHIFT; @@ -2731,7 +2733,7 @@ static int ggtt_bind_vma(struct i915_vma *vma, /* Applicable to VLV (gen8+ do not support RO in the GGTT) */ pte_flags = 0; - if (obj->gt_ro) + if (i915_gem_object_is_readonly(obj)) pte_flags |= PTE_READ_ONLY; intel_runtime_pm_get(i915); @@ -2769,7 +2771,7 @@ static int aliasing_gtt_bind_vma(struct i915_vma *vma, /* Currently applicable only to VLV */ pte_flags = 0; - if (vma->obj->gt_ro) + if (i915_gem_object_is_readonly(vma->obj)) pte_flags |= PTE_READ_ONLY; if (flags & I915_VMA_LOCAL_BIND) { diff --git a/drivers/gpu/drm/i915/i915_gem_object.h b/drivers/gpu/drm/i915/i915_gem_object.h index c3c6f2e588fb..56e9f00d2c4c 100644 --- a/drivers/gpu/drm/i915/i915_gem_object.h +++ b/drivers/gpu/drm/i915/i915_gem_object.h @@ -141,7 +141,6 @@ struct drm_i915_gem_object { * Is the object to be mapped as read-only to the GPU * Only honoured if hardware has relevant pte bit */ - unsigned long gt_ro:1; unsigned int cache_level:3; unsigned int cache_coherent:2; #define I915_BO_CACHE_COHERENT_FOR_READ BIT(0) @@ -358,6 +357,18 @@ static inline void i915_gem_object_unlock(struct drm_i915_gem_object *obj) reservation_object_unlock(obj->resv); } +static inline void +i915_gem_object_set_readonly(struct drm_i915_gem_object *obj) +{ + obj->base.vma_node.readonly = true; +} + +static inline bool +i915_gem_object_is_readonly(const struct drm_i915_gem_object *obj) +{ + return obj->base.vma_node.readonly; +} + static inline bool i915_gem_object_has_struct_page(const struct drm_i915_gem_object *obj) { diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 6de88add508a..69bd7f697f6d 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -1100,7 +1100,7 @@ intel_ring_create_vma(struct drm_i915_private *dev_priv, int size) * if supported by the platform's GGTT. */ if (vm->has_read_only) - obj->gt_ro = 1; + i915_gem_object_set_readonly(obj); vma = i915_vma_instance(obj, vm, NULL); if (IS_ERR(vma)) diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/selftests/i915_gem_context.c index 2e2a3c44b8e9..1c92560d35da 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_context.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_context.c @@ -487,7 +487,8 @@ static int igt_ctx_readonly(void *arg) goto out_unlock; } - obj->gt_ro = prandom_u32_state(&prng); + if (prandom_u32_state(&prng) & 1) + i915_gem_object_set_readonly(obj); } intel_runtime_pm_get(i915); @@ -518,7 +519,7 @@ static int igt_ctx_readonly(void *arg) unsigned int num_writes; num_writes = rem; - if (obj->gt_ro) + if (i915_gem_object_is_readonly(obj)) num_writes = 0; err = cpu_check(obj, num_writes); diff --git a/include/drm/drm_vma_manager.h b/include/drm/drm_vma_manager.h index 8758df94e9a0..c7987daeaed0 100644 --- a/include/drm/drm_vma_manager.h +++ b/include/drm/drm_vma_manager.h @@ -41,6 +41,7 @@ struct drm_vma_offset_node { rwlock_t vm_lock; struct drm_mm_node vm_node; struct rb_root vm_files; + bool readonly:1; }; struct drm_vma_offset_manager { -- cgit v1.2.3 From 90a460d5dd205b1b39dae3dad041a37cf7c4241d Mon Sep 17 00:00:00 2001 From: Sean Paul Date: Fri, 13 Jul 2018 11:34:44 -0400 Subject: drm: Fix kerneldoc for DRM_MODE_PROP_IMMUTABLE MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Noticed this while browsing the docs. Reviewed-by: Ville Syrjälä Signed-off-by: Sean Paul Link: https://patchwork.freedesktop.org/patch/msgid/20180713153444.95466-1-seanpaul@chromium.org --- include/drm/drm_property.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/drm/drm_property.h b/include/drm/drm_property.h index 1d5c0b2a8956..c030f6ccab99 100644 --- a/include/drm/drm_property.h +++ b/include/drm/drm_property.h @@ -147,10 +147,10 @@ struct drm_property { * properties are not exposed to legacy userspace. * * DRM_MODE_PROP_IMMUTABLE - * Set for properties where userspace cannot be changed by + * Set for properties whose values cannot be changed by * userspace. The kernel is allowed to update the value of these * properties. This is generally used to expose probe state to - * usersapce, e.g. the EDID, or the connector path property on DP + * userspace, e.g. the EDID, or the connector path property on DP * MST sinks. */ uint32_t flags; -- cgit v1.2.3 From 811e299f4645588cc7a1b78d97b6847c155324b9 Mon Sep 17 00:00:00 2001 From: Romuald CARI Date: Thu, 7 Jun 2018 16:08:02 +0200 Subject: ieee802154: add rx LQI from userspace MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The Link Quality Indication data exposed by drivers could not be accessed from userspace. Since this data is per-datagram received, it makes sense to make it available to userspace application through the ancillary data mechanism in recvmsg rather than through ioctls. This can be activated using the socket option WPAN_WANTLQI under SOL_IEEE802154 protocol. This LQI data is available in the ancillary data buffer under the SOL_IEEE802154 level as the type WPAN_LQI. The value is an unsigned byte indicating the link quality with values ranging 0-255. Signed-off-by: Romuald Cari Signed-off-by: Clément Peron Signed-off-by: Stefan Schmidt --- include/net/af_ieee802154.h | 1 + net/ieee802154/socket.c | 17 +++++++++++++++++ 2 files changed, 18 insertions(+) (limited to 'include') diff --git a/include/net/af_ieee802154.h b/include/net/af_ieee802154.h index a5563d27a3eb..8003a9f6eb43 100644 --- a/include/net/af_ieee802154.h +++ b/include/net/af_ieee802154.h @@ -56,6 +56,7 @@ struct sockaddr_ieee802154 { #define WPAN_WANTACK 0 #define WPAN_SECURITY 1 #define WPAN_SECURITY_LEVEL 2 +#define WPAN_WANTLQI 3 #define WPAN_SECURITY_DEFAULT 0 #define WPAN_SECURITY_OFF 1 diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c index a60658c85a9a..bc6b912603f1 100644 --- a/net/ieee802154/socket.c +++ b/net/ieee802154/socket.c @@ -25,6 +25,7 @@ #include /* For TIOCOUTQ/INQ */ #include #include +#include #include #include #include @@ -452,6 +453,7 @@ struct dgram_sock { unsigned int bound:1; unsigned int connected:1; unsigned int want_ack:1; + unsigned int want_lqi:1; unsigned int secen:1; unsigned int secen_override:1; unsigned int seclevel:3; @@ -486,6 +488,7 @@ static int dgram_init(struct sock *sk) struct dgram_sock *ro = dgram_sk(sk); ro->want_ack = 1; + ro->want_lqi = 0; return 0; } @@ -713,6 +716,7 @@ static int dgram_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, size_t copied = 0; int err = -EOPNOTSUPP; struct sk_buff *skb; + struct dgram_sock *ro = dgram_sk(sk); DECLARE_SOCKADDR(struct sockaddr_ieee802154 *, saddr, msg->msg_name); skb = skb_recv_datagram(sk, flags, noblock, &err); @@ -744,6 +748,13 @@ static int dgram_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, *addr_len = sizeof(*saddr); } + if (ro->want_lqi) { + err = put_cmsg(msg, SOL_IEEE802154, WPAN_WANTLQI, + sizeof(uint8_t), &(mac_cb(skb)->lqi)); + if (err) + goto done; + } + if (flags & MSG_TRUNC) copied = skb->len; done: @@ -847,6 +858,9 @@ static int dgram_getsockopt(struct sock *sk, int level, int optname, case WPAN_WANTACK: val = ro->want_ack; break; + case WPAN_WANTLQI: + val = ro->want_lqi; + break; case WPAN_SECURITY: if (!ro->secen_override) val = WPAN_SECURITY_DEFAULT; @@ -892,6 +906,9 @@ static int dgram_setsockopt(struct sock *sk, int level, int optname, case WPAN_WANTACK: ro->want_ack = !!val; break; + case WPAN_WANTLQI: + ro->want_lqi = !!val; + break; case WPAN_SECURITY: if (!ns_capable(net->user_ns, CAP_NET_ADMIN) && !ns_capable(net->user_ns, CAP_NET_RAW)) { -- cgit v1.2.3 From ce6058039bca7f1f11f1723549eec1bc069dcb28 Mon Sep 17 00:00:00 2001 From: Ayan Kumar Halder Date: Tue, 10 Jul 2018 14:18:54 +0100 Subject: drm/arm/malidp: Add modifier definitions for describing Arm Framebuffer Compression (AFBC). AFBC is a proprietary lossless image compression protocol and format. It provides fine-grained random access and minimizes the amount of data transferred between IP blocks. AFBC has several features which may be supported and/or used, which are represented using bits in the modifier. Not all combinations are valid, and different devices or use-cases may support different combinations. Changes from v2:- - Added ack by Maarten Lankhorst Signed-off-by: Rosen Zhelev Signed-off-by: Ayan Kumar halder Reviewed-by: Brian Starkey Reviewed-by: Liviu Dudau Reviewed-by: James (Qian) Wang Acked-by: Maarten Lankhorst Link: https://lkml.org/lkml/2018/7/10/360 --- include/uapi/drm/drm_fourcc.h | 83 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 83 insertions(+) (limited to 'include') diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h index d5e52350a3aa..d43949b5bb3e 100644 --- a/include/uapi/drm/drm_fourcc.h +++ b/include/uapi/drm/drm_fourcc.h @@ -183,6 +183,7 @@ extern "C" { #define DRM_FORMAT_MOD_VENDOR_QCOM 0x05 #define DRM_FORMAT_MOD_VENDOR_VIVANTE 0x06 #define DRM_FORMAT_MOD_VENDOR_BROADCOM 0x07 +#define DRM_FORMAT_MOD_VENDOR_ARM 0x08 /* add more to the end as needed */ #define DRM_FORMAT_RESERVED ((1ULL << 56) - 1) @@ -485,6 +486,88 @@ extern "C" { */ #define DRM_FORMAT_MOD_BROADCOM_UIF fourcc_mod_code(BROADCOM, 6) +/* + * Arm Framebuffer Compression (AFBC) modifiers + * + * AFBC is a proprietary lossless image compression protocol and format. + * It provides fine-grained random access and minimizes the amount of data + * transferred between IP blocks. + * + * AFBC has several features which may be supported and/or used, which are + * represented using bits in the modifier. Not all combinations are valid, + * and different devices or use-cases may support different combinations. + */ +#define DRM_FORMAT_MOD_ARM_AFBC(__afbc_mode) fourcc_mod_code(ARM, __afbc_mode) + +/* + * AFBC superblock size + * + * Indicates the superblock size(s) used for the AFBC buffer. The buffer + * size (in pixels) must be aligned to a multiple of the superblock size. + * Four lowest significant bits(LSBs) are reserved for block size. + */ +#define AFBC_FORMAT_MOD_BLOCK_SIZE_MASK 0xf +#define AFBC_FORMAT_MOD_BLOCK_SIZE_16x16 (1ULL) +#define AFBC_FORMAT_MOD_BLOCK_SIZE_32x8 (2ULL) + +/* + * AFBC lossless colorspace transform + * + * Indicates that the buffer makes use of the AFBC lossless colorspace + * transform. + */ +#define AFBC_FORMAT_MOD_YTR (1ULL << 4) + +/* + * AFBC block-split + * + * Indicates that the payload of each superblock is split. The second + * half of the payload is positioned at a predefined offset from the start + * of the superblock payload. + */ +#define AFBC_FORMAT_MOD_SPLIT (1ULL << 5) + +/* + * AFBC sparse layout + * + * This flag indicates that the payload of each superblock must be stored at a + * predefined position relative to the other superblocks in the same AFBC + * buffer. This order is the same order used by the header buffer. In this mode + * each superblock is given the same amount of space as an uncompressed + * superblock of the particular format would require, rounding up to the next + * multiple of 128 bytes in size. + */ +#define AFBC_FORMAT_MOD_SPARSE (1ULL << 6) + +/* + * AFBC copy-block restrict + * + * Buffers with this flag must obey the copy-block restriction. The restriction + * is such that there are no copy-blocks referring across the border of 8x8 + * blocks. For the subsampled data the 8x8 limitation is also subsampled. + */ +#define AFBC_FORMAT_MOD_CBR (1ULL << 7) + +/* + * AFBC tiled layout + * + * The tiled layout groups superblocks in 8x8 or 4x4 tiles, where all + * superblocks inside a tile are stored together in memory. 8x8 tiles are used + * for pixel formats up to and including 32 bpp while 4x4 tiles are used for + * larger bpp formats. The order between the tiles is scan line. + * When the tiled layout is used, the buffer size (in pixels) must be aligned + * to the tile size. + */ +#define AFBC_FORMAT_MOD_TILED (1ULL << 8) + +/* + * AFBC solid color blocks + * + * Indicates that the buffer makes use of solid-color blocks, whereby bandwidth + * can be reduced if a whole superblock is a single color. + */ +#define AFBC_FORMAT_MOD_SC (1ULL << 9) + #if defined(__cplusplus) } #endif -- cgit v1.2.3 From 3479fc248bf383549ff629c607df0486813e14fd Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Mon, 9 Jul 2018 10:40:02 +0200 Subject: drm: move drv test macros out of drmP.h Last bit the prevented us from starting to delete the drmP.h monster includes from source files! Also add kernel-doc while moving them. A nice consistent drm_dev_ prefix would be cute for these, but since they're used everywhere I've figured I'll leave this bikeshed aside for now. Reviewed-by: Sean Paul Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20180709084016.23750-2-daniel.vetter@ffwll.ch --- include/drm/drmP.h | 19 ------------------- include/drm/drm_drv.h | 29 +++++++++++++++++++++++++++++ 2 files changed, 29 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/drm/drmP.h b/include/drm/drmP.h index c5dfbdb7271d..f7a19c2a7a80 100644 --- a/include/drm/drmP.h +++ b/include/drm/drmP.h @@ -102,25 +102,6 @@ struct pci_controller; #define DRM_SWITCH_POWER_CHANGING 2 #define DRM_SWITCH_POWER_DYNAMIC_OFF 3 -static inline bool drm_core_check_feature(struct drm_device *dev, int feature) -{ - return dev->driver->driver_features & feature; -} - -/** - * drm_drv_uses_atomic_modeset - check if the driver implements - * atomic_commit() - * @dev: DRM device - * - * This check is useful if drivers do not have DRIVER_ATOMIC set but - * have atomic modesetting internally implemented. - */ -static inline bool drm_drv_uses_atomic_modeset(struct drm_device *dev) -{ - return drm_core_check_feature(dev, DRIVER_ATOMIC) || - dev->mode_config.funcs->atomic_commit != NULL; -} - /* returns true if currently okay to sleep */ static inline bool drm_can_sleep(void) { diff --git a/include/drm/drm_drv.h b/include/drm/drm_drv.h index 7e545f5f94d3..46a8009784df 100644 --- a/include/drm/drm_drv.h +++ b/include/drm/drm_drv.h @@ -649,6 +649,35 @@ static inline bool drm_dev_is_unplugged(struct drm_device *dev) return true; } +/** + * drm_core_check_feature - check driver feature flags + * @dev: DRM device to check + * @feature: feature flag + * + * This checks @dev for driver features, see &drm_driver.driver_features and the + * various DRIVER_\* flags. + * + * Returns true if the @feature is supported, false otherwise. + */ +static inline bool drm_core_check_feature(struct drm_device *dev, int feature) +{ + return dev->driver->driver_features & feature; +} + +/** + * drm_drv_uses_atomic_modeset - check if the driver implements + * atomic_commit() + * @dev: DRM device + * + * This check is useful if drivers do not have DRIVER_ATOMIC set but + * have atomic modesetting internally implemented. + */ +static inline bool drm_drv_uses_atomic_modeset(struct drm_device *dev) +{ + return drm_core_check_feature(dev, DRIVER_ATOMIC) || + dev->mode_config.funcs->atomic_commit != NULL; +} + int drm_dev_set_unique(struct drm_device *dev, const char *name); -- cgit v1.2.3 From aab999a66e4bc448a439733d60c83c86bee4c2be Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Mon, 9 Jul 2018 10:40:04 +0200 Subject: drm/doc: switch drm_connector_state to inline comments For consistency. Also spelled out the docs for ->best_encoder a bit more while at it. Reviewed-by: Sean Paul Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20180709084016.23750-4-daniel.vetter@ffwll.ch --- include/drm/drm_connector.h | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h index a5179eb9e56f..99fd75d7a3a9 100644 --- a/include/drm/drm_connector.h +++ b/include/drm/drm_connector.h @@ -378,12 +378,9 @@ struct drm_tv_connector_state { /** * struct drm_connector_state - mutable connector state - * @connector: backpointer to the connector - * @best_encoder: can be used by helpers and drivers to select the encoder - * @state: backpointer to global drm_atomic_state - * @tv: TV connector state */ struct drm_connector_state { + /** @connector: backpointer to the connector */ struct drm_connector *connector; /** @@ -394,6 +391,13 @@ struct drm_connector_state { */ struct drm_crtc *crtc; + /** + * @best_encoder: + * + * Used by the atomic helpers to select the encoder, through the + * &drm_connector_helper_funcs.atomic_best_encoder or + * &drm_connector_helper_funcs.best_encoder callbacks. + */ struct drm_encoder *best_encoder; /** @@ -402,6 +406,7 @@ struct drm_connector_state { */ enum drm_link_status link_status; + /** @state: backpointer to global drm_atomic_state */ struct drm_atomic_state *state; /** @@ -411,6 +416,7 @@ struct drm_connector_state { */ struct drm_crtc_commit *commit; + /** @tv: TV connector state */ struct drm_tv_connector_state tv; /** -- cgit v1.2.3 From 92e1d26324e095252f3baf2c953615715c7c2a89 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Mon, 9 Jul 2018 10:40:05 +0200 Subject: drm/doc: polish for sturct drm_connector - switch everything over to inline comments - add notes about locking, links to functions and other related stuff - also include a note about Ville's soon-to-be-merged drm_connector_for_each_possible_encoder(). Also check that all the hyperlinks in drm_connector.h work and fix them as needed. Reviewed-by: Sean Paul Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20180709084016.23750-5-daniel.vetter@ffwll.ch --- include/drm/drm_connector.h | 191 ++++++++++++++++++++++++++++---------------- 1 file changed, 120 insertions(+), 71 deletions(-) (limited to 'include') diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h index 99fd75d7a3a9..e09e16b3e054 100644 --- a/include/drm/drm_connector.h +++ b/include/drm/drm_connector.h @@ -561,8 +561,7 @@ struct drm_connector_funcs { * received for this output connector->edid must be NULL. * * Drivers using the probe helpers should use - * drm_helper_probe_single_connector_modes() or - * drm_helper_probe_single_connector_modes_nomerge() to implement this + * drm_helper_probe_single_connector_modes() to implement this * function. * * RETURNS: @@ -773,45 +772,6 @@ struct drm_cmdline_mode { /** * struct drm_connector - central DRM connector control structure - * @dev: parent DRM device - * @kdev: kernel device for sysfs attributes - * @attr: sysfs attributes - * @head: list management - * @base: base KMS object - * @name: human readable name, can be overwritten by the driver - * @connector_type: one of the DRM_MODE_CONNECTOR_ types from drm_mode.h - * @connector_type_id: index into connector type enum - * @interlace_allowed: can this connector handle interlaced modes? - * @doublescan_allowed: can this connector handle doublescan? - * @stereo_allowed: can this connector handle stereo modes? - * @funcs: connector control functions - * @edid_blob_ptr: DRM property containing EDID if present - * @properties: property tracking for this connector - * @dpms: current dpms state - * @helper_private: mid-layer private data - * @cmdline_mode: mode line parsed from the kernel cmdline for this connector - * @force: a DRM_FORCE_ state for forced mode sets - * @override_edid: has the EDID been overwritten through debugfs for testing? - * @encoder_ids: valid encoders for this connector - * @eld: EDID-like data, if present - * @latency_present: AV delay info from ELD, if found - * @video_latency: video latency info from ELD, if found - * @audio_latency: audio latency info from ELD, if found - * @null_edid_counter: track sinks that give us all zeros for the EDID - * @bad_edid_counter: track sinks that give us an EDID with invalid checksum - * @edid_corrupt: indicates whether the last read EDID was corrupt - * @debugfs_entry: debugfs directory for this connector - * @has_tile: is this connector connected to a tiled monitor - * @tile_group: tile group for the connected monitor - * @tile_is_single_monitor: whether the tile is one monitor housing - * @num_h_tile: number of horizontal tiles in the tile group - * @num_v_tile: number of vertical tiles in the tile group - * @tile_h_loc: horizontal location of this tile - * @tile_v_loc: vertical location of this tile - * @tile_h_size: horizontal size of this tile. - * @tile_v_size: vertical size of this tile. - * @scaling_mode_property: Optional atomic property to control the upscaling. - * @content_protection_property: Optional property to control content protection * * Each connector may be connected to one or more CRTCs, or may be clonable by * another connector if they can share a CRTC. Each connector also has a specific @@ -819,13 +779,27 @@ struct drm_cmdline_mode { * span multiple monitors). */ struct drm_connector { + /** @dev: parent DRM device */ struct drm_device *dev; + /** @kdev: kernel device for sysfs attributes */ struct device *kdev; + /** @attr: sysfs attributes */ struct device_attribute *attr; + + /** + * @head: + * + * List of all connectors on a @dev, linked from + * &drm_mode_config.connector_list. Protected by + * &drm_mode_config.connector_list_lock, but please only use + * &drm_connector_list_iter to walk this list. + */ struct list_head head; + /** @base: base KMS object */ struct drm_mode_object base; + /** @name: human readable name, can be overwritten by the driver */ char *name; /** @@ -843,10 +817,30 @@ struct drm_connector { */ unsigned index; + /** + * @connector_type: + * one of the DRM_MODE_CONNECTOR_ types from drm_mode.h + */ int connector_type; + /** @connector_type_id: index into connector type enum */ int connector_type_id; + /** + * @interlace_allowed: + * Can this connector handle interlaced modes? Only used by + * drm_helper_probe_single_connector_modes() for mode filtering. + */ bool interlace_allowed; + /** + * @doublescan_allowed: + * Can this connector handle doublescan? Only used by + * drm_helper_probe_single_connector_modes() for mode filtering. + */ bool doublescan_allowed; + /** + * @stereo_allowed: + * Can this connector handle stereo modes? Only used by + * drm_helper_probe_single_connector_modes() for mode filtering. + */ bool stereo_allowed; /** @@ -895,45 +889,42 @@ struct drm_connector { * Protected by &drm_mode_config.mutex. */ struct drm_display_info display_info; + + /** @funcs: connector control functions */ const struct drm_connector_funcs *funcs; + /** + * @edid_blob_ptr: DRM property containing EDID if present. Protected by + * &drm_mode_config.mutex. This should be updated only by calling + * drm_mode_connector_update_edid_property(). + */ struct drm_property_blob *edid_blob_ptr; + + /** @properties: property tracking for this connector */ struct drm_object_properties properties; + /** + * @scaling_mode_property: Optional atomic property to control the + * upscaling. See drm_connector_attach_content_protection_property(). + */ struct drm_property *scaling_mode_property; /** * @content_protection_property: DRM ENUM property for content - * protection + * protection. See drm_connector_attach_content_protection_property(). */ struct drm_property *content_protection_property; /** * @path_blob_ptr: * - * DRM blob property data for the DP MST path property. + * DRM blob property data for the DP MST path property. This should only + * be updated by calling drm_mode_connector_set_path_property(). */ struct drm_property_blob *path_blob_ptr; - /** - * @tile_blob_ptr: - * - * DRM blob property data for the tile property (used mostly by DP MST). - * This is meant for screens which are driven through separate display - * pipelines represented by &drm_crtc, which might not be running with - * genlocked clocks. For tiled panels which are genlocked, like - * dual-link LVDS or dual-link DSI, the driver should try to not expose - * the tiling and virtualize both &drm_crtc and &drm_plane if needed. - */ - struct drm_property_blob *tile_blob_ptr; - -/* should we poll this connector for connects and disconnects */ -/* hot plug detectable */ #define DRM_CONNECTOR_POLL_HPD (1 << 0) -/* poll for connections */ #define DRM_CONNECTOR_POLL_CONNECT (1 << 1) -/* can cleanly poll for disconnections without flickering the screen */ -/* DACs should rarely do this without a lot of testing */ #define DRM_CONNECTOR_POLL_DISCONNECT (1 << 2) /** @@ -950,25 +941,40 @@ struct drm_connector { * Periodically poll the connector for connection. * * DRM_CONNECTOR_POLL_DISCONNECT - * Periodically poll the connector for disconnection. + * Periodically poll the connector for disconnection, without + * causing flickering even when the connector is in use. DACs should + * rarely do this without a lot of testing. * * Set to 0 for connectors that don't support connection status * discovery. */ uint8_t polled; - /* requested DPMS state */ + /** + * @dpms: Current dpms state. For legacy drivers the + * &drm_connector_funcs.dpms callback must update this. For atomic + * drivers, this is handled by the core atomic code, and drivers must + * only take &drm_crtc_state.active into account. + */ int dpms; + /** @helper_private: mid-layer private data */ const struct drm_connector_helper_funcs *helper_private; - /* forced on connector */ + /** @cmdline_mode: mode line parsed from the kernel cmdline for this connector */ struct drm_cmdline_mode cmdline_mode; + /** @force: a DRM_FORCE_ state for forced mode sets */ enum drm_connector_force force; + /** @override_edid: has the EDID been overwritten through debugfs for testing? */ bool override_edid; #define DRM_CONNECTOR_MAX_ENCODER 3 + /** + * @encoder_ids: Valid encoders for this connector. Please only use + * drm_connector_for_each_possible_encoder() to enumerate these. + */ uint32_t encoder_ids[DRM_CONNECTOR_MAX_ENCODER]; + /** * @encoder: Currently bound encoder driving this connector, if any. * Only really meaningful for non-atomic drivers. Atomic drivers should @@ -978,19 +984,37 @@ struct drm_connector { struct drm_encoder *encoder; #define MAX_ELD_BYTES 128 - /* EDID bits */ + /** @eld: EDID-like data, if present */ uint8_t eld[MAX_ELD_BYTES]; + /** @latency_present: AV delay info from ELD, if found */ bool latency_present[2]; - int video_latency[2]; /* [0]: progressive, [1]: interlaced */ + /** + * @video_latency: Video latency info from ELD, if found. + * [0]: progressive, [1]: interlaced + */ + int video_latency[2]; + /** + * @audio_latency: audio latency info from ELD, if found + * [0]: progressive, [1]: interlaced + */ int audio_latency[2]; - int null_edid_counter; /* needed to workaround some HW bugs where we get all 0s */ + /** + * @null_edid_counter: track sinks that give us all zeros for the EDID. + * Needed to workaround some HW bugs where we get all 0s + */ + int null_edid_counter; + + /** @bad_edid_counter: track sinks that give us an EDID with invalid checksum */ unsigned bad_edid_counter; - /* Flag for raw EDID header corruption - used in Displayport - * compliance testing - * Displayport Link CTS Core 1.2 rev1.1 4.2.2.6 + /** + * @edid_corrupt: Indicates whether the last read EDID was corrupt. Used + * in Displayport compliance testing - Displayport Link CTS Core 1.2 + * rev1.1 4.2.2.6 */ bool edid_corrupt; + /** @debugfs_entry: debugfs directory for this connector */ struct dentry *debugfs_entry; /** @@ -998,7 +1022,7 @@ struct drm_connector { * * Current atomic state for this connector. * - * This is protected by @drm_mode_config.connection_mutex. Note that + * This is protected by &drm_mode_config.connection_mutex. Note that * nonblocking atomic commits access the current connector state without * taking locks. Either by going through the &struct drm_atomic_state * pointers, see for_each_oldnew_connector_in_state(), @@ -1009,19 +1033,44 @@ struct drm_connector { */ struct drm_connector_state *state; - /* DisplayID bits */ + /* DisplayID bits. FIXME: Extract into a substruct? */ + + /** + * @tile_blob_ptr: + * + * DRM blob property data for the tile property (used mostly by DP MST). + * This is meant for screens which are driven through separate display + * pipelines represented by &drm_crtc, which might not be running with + * genlocked clocks. For tiled panels which are genlocked, like + * dual-link LVDS or dual-link DSI, the driver should try to not expose + * the tiling and virtualize both &drm_crtc and &drm_plane if needed. + * + * This should only be updated by calling + * drm_mode_connector_set_tile_property(). + */ + struct drm_property_blob *tile_blob_ptr; + + /** @has_tile: is this connector connected to a tiled monitor */ bool has_tile; + /** @tile_group: tile group for the connected monitor */ struct drm_tile_group *tile_group; + /** @tile_is_single_monitor: whether the tile is one monitor housing */ bool tile_is_single_monitor; + /** @num_h_tile: number of horizontal tiles in the tile group */ + /** @num_v_tile: number of vertical tiles in the tile group */ uint8_t num_h_tile, num_v_tile; + /** @tile_h_loc: horizontal location of this tile */ + /** @tile_v_loc: vertical location of this tile */ uint8_t tile_h_loc, tile_v_loc; + /** @tile_h_size: horizontal size of this tile. */ + /** @tile_v_size: vertical size of this tile. */ uint16_t tile_h_size, tile_v_size; /** * @free_node: * - * List used only by &drm_connector_iter to be able to clean up a + * List used only by &drm_connector_list_iter to be able to clean up a * connector from any context, in conjunction with * &drm_mode_config.connector_free_work. */ -- cgit v1.2.3 From c555f02371c338b06752577aebf738dbdb6907bd Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Mon, 9 Jul 2018 10:40:06 +0200 Subject: drm: drop _mode_ from update_edit_property() Just makes it longer, and for most things in drm_connector.[hc] we just use the drm_connector_ prefix. Done with sed + a bit of manual fixup for the indenting. Reviewed-by: Sean Paul Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20180709084016.23750-6-daniel.vetter@ffwll.ch --- drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c | 4 ++-- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 4 ++-- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c | 4 ++-- drivers/gpu/drm/ast/ast_mode.c | 4 ++-- drivers/gpu/drm/bridge/adv7511/adv7511_drv.c | 2 +- drivers/gpu/drm/bridge/analogix-anx78xx.c | 4 ++-- drivers/gpu/drm/bridge/analogix/analogix_dp_core.c | 4 ++-- drivers/gpu/drm/bridge/dumb-vga-dac.c | 2 +- drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c | 2 +- drivers/gpu/drm/bridge/nxp-ptn3460.c | 2 +- drivers/gpu/drm/bridge/sii902x.c | 2 +- drivers/gpu/drm/bridge/synopsys/dw-hdmi.c | 2 +- drivers/gpu/drm/bridge/tc358767.c | 2 +- drivers/gpu/drm/bridge/ti-tfp410.c | 2 +- drivers/gpu/drm/drm_connector.c | 8 ++++---- drivers/gpu/drm/drm_debugfs.c | 4 ++-- drivers/gpu/drm/drm_probe_helper.c | 2 +- drivers/gpu/drm/exynos/exynos_drm_vidi.c | 2 +- drivers/gpu/drm/exynos/exynos_hdmi.c | 2 +- drivers/gpu/drm/gma500/cdv_intel_dp.c | 2 +- drivers/gpu/drm/gma500/cdv_intel_hdmi.c | 2 +- drivers/gpu/drm/gma500/oaktrail_hdmi.c | 2 +- drivers/gpu/drm/gma500/oaktrail_lvds.c | 2 +- drivers/gpu/drm/gma500/psb_intel_modes.c | 2 +- drivers/gpu/drm/gma500/psb_intel_sdvo.c | 2 +- drivers/gpu/drm/i2c/tda998x_drv.c | 2 +- drivers/gpu/drm/i915/intel_dp.c | 2 +- drivers/gpu/drm/i915/intel_lvds.c | 2 +- drivers/gpu/drm/i915/intel_modes.c | 2 +- drivers/gpu/drm/i915/intel_sdvo.c | 2 +- drivers/gpu/drm/imx/imx-ldb.c | 2 +- drivers/gpu/drm/imx/imx-tve.c | 2 +- drivers/gpu/drm/imx/parallel-display.c | 2 +- drivers/gpu/drm/mediatek/mtk_hdmi.c | 2 +- drivers/gpu/drm/mgag200/mgag200_mode.c | 2 +- drivers/gpu/drm/msm/edp/edp_connector.c | 2 +- drivers/gpu/drm/msm/hdmi/hdmi_connector.c | 2 +- drivers/gpu/drm/nouveau/dispnv50/disp.c | 2 +- drivers/gpu/drm/nouveau/nouveau_connector.c | 8 ++++---- drivers/gpu/drm/omapdrm/omap_connector.c | 4 ++-- drivers/gpu/drm/panel/panel-simple.c | 2 +- drivers/gpu/drm/radeon/radeon_connectors.c | 4 ++-- drivers/gpu/drm/radeon/radeon_dp_mst.c | 4 ++-- drivers/gpu/drm/rockchip/cdn-dp-core.c | 2 +- drivers/gpu/drm/rockchip/inno_hdmi.c | 2 +- drivers/gpu/drm/sti/sti_hdmi.c | 2 +- drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c | 2 +- drivers/gpu/drm/tegra/output.c | 2 +- drivers/gpu/drm/tilcdc/tilcdc_tfp410.c | 2 +- drivers/gpu/drm/udl/udl_connector.c | 2 +- drivers/gpu/drm/vc4/vc4_hdmi.c | 2 +- drivers/gpu/drm/zte/zx_hdmi.c | 2 +- drivers/gpu/drm/zte/zx_vga.c | 2 +- drivers/staging/vboxvideo/vbox_mode.c | 2 +- include/drm/drm_connector.h | 6 +++--- include/drm/drm_modeset_helper_vtables.h | 2 +- 56 files changed, 74 insertions(+), 74 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c index 881f7cb7ae6e..c770d73352a7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c @@ -334,11 +334,11 @@ static int amdgpu_connector_ddc_get_modes(struct drm_connector *connector) int ret; if (amdgpu_connector->edid) { - drm_mode_connector_update_edid_property(connector, amdgpu_connector->edid); + drm_connector_update_edid_property(connector, amdgpu_connector->edid); ret = drm_add_edid_modes(connector, amdgpu_connector->edid); return ret; } - drm_mode_connector_update_edid_property(connector, NULL); + drm_connector_update_edid_property(connector, NULL); return 0; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 66bd3cc3e387..c4ab19831344 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -900,14 +900,14 @@ amdgpu_dm_update_connector_after_detect(struct amdgpu_dm_connector *aconnector) (struct edid *) sink->dc_edid.raw_edid; - drm_mode_connector_update_edid_property(connector, + drm_connector_update_edid_property(connector, aconnector->edid); } amdgpu_dm_add_sink_to_freesync_module(connector, aconnector->edid); } else { amdgpu_dm_remove_sink_from_freesync_module(connector); - drm_mode_connector_update_edid_property(connector, NULL); + drm_connector_update_edid_property(connector, NULL); aconnector->num_modes = 0; aconnector->dc_sink = NULL; aconnector->edid = NULL; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 4304d9e408b8..581bb75d08eb 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -233,7 +233,7 @@ static int dm_dp_mst_get_modes(struct drm_connector *connector) edid = drm_dp_mst_get_edid(connector, &aconnector->mst_port->mst_mgr, aconnector->port); if (!edid) { - drm_mode_connector_update_edid_property( + drm_connector_update_edid_property( &aconnector->base, NULL); return ret; @@ -261,7 +261,7 @@ static int dm_dp_mst_get_modes(struct drm_connector *connector) connector, aconnector->edid); } - drm_mode_connector_update_edid_property( + drm_connector_update_edid_property( &aconnector->base, aconnector->edid); ret = drm_add_edid_modes(connector, aconnector->edid); diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c index 036dff8a1f33..1bb8174ad155 100644 --- a/drivers/gpu/drm/ast/ast_mode.c +++ b/drivers/gpu/drm/ast/ast_mode.c @@ -790,12 +790,12 @@ static int ast_get_modes(struct drm_connector *connector) if (!flags) edid = drm_get_edid(connector, &ast_connector->i2c->adapter); if (edid) { - drm_mode_connector_update_edid_property(&ast_connector->base, edid); + drm_connector_update_edid_property(&ast_connector->base, edid); ret = drm_add_edid_modes(connector, edid); kfree(edid); return ret; } else - drm_mode_connector_update_edid_property(&ast_connector->base, NULL); + drm_connector_update_edid_property(&ast_connector->base, NULL); return 0; } diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c index 73021b388e12..1f4745953aca 100644 --- a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c +++ b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c @@ -601,7 +601,7 @@ static int adv7511_get_modes(struct adv7511 *adv7511, __adv7511_power_off(adv7511); - drm_mode_connector_update_edid_property(connector, edid); + drm_connector_update_edid_property(connector, edid); count = drm_add_edid_modes(connector, edid); adv7511_set_config_csc(adv7511, connector, adv7511->rgb, diff --git a/drivers/gpu/drm/bridge/analogix-anx78xx.c b/drivers/gpu/drm/bridge/analogix-anx78xx.c index b49043866be6..37f947dcadec 100644 --- a/drivers/gpu/drm/bridge/analogix-anx78xx.c +++ b/drivers/gpu/drm/bridge/analogix-anx78xx.c @@ -969,8 +969,8 @@ static int anx78xx_get_modes(struct drm_connector *connector) goto unlock; } - err = drm_mode_connector_update_edid_property(connector, - anx78xx->edid); + err = drm_connector_update_edid_property(connector, + anx78xx->edid); if (err) { DRM_ERROR("Failed to update EDID property: %d\n", err); goto unlock; diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c index 2bcbfadb6ac5..288c015f7460 100644 --- a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c +++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c @@ -1119,8 +1119,8 @@ static int analogix_dp_get_modes(struct drm_connector *connector) edid = drm_get_edid(connector, &dp->aux.ddc); pm_runtime_put(dp->dev); if (edid) { - drm_mode_connector_update_edid_property(&dp->connector, - edid); + drm_connector_update_edid_property(&dp->connector, + edid); num_modes += drm_add_edid_modes(&dp->connector, edid); kfree(edid); } diff --git a/drivers/gpu/drm/bridge/dumb-vga-dac.c b/drivers/gpu/drm/bridge/dumb-vga-dac.c index 9837c8d69e69..da99b8ba4ee1 100644 --- a/drivers/gpu/drm/bridge/dumb-vga-dac.c +++ b/drivers/gpu/drm/bridge/dumb-vga-dac.c @@ -55,7 +55,7 @@ static int dumb_vga_get_modes(struct drm_connector *connector) goto fallback; } - drm_mode_connector_update_edid_property(connector, edid); + drm_connector_update_edid_property(connector, edid); ret = drm_add_edid_modes(connector, edid); kfree(edid); return ret; diff --git a/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c b/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c index 7ccadba7c98c..b49b543bd1f6 100644 --- a/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c +++ b/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c @@ -152,7 +152,7 @@ static int ge_b850v3_lvds_get_modes(struct drm_connector *connector) ge_b850v3_lvds_ptr->edid = (struct edid *)stdp2690_get_edid(client); if (ge_b850v3_lvds_ptr->edid) { - drm_mode_connector_update_edid_property(connector, + drm_connector_update_edid_property(connector, ge_b850v3_lvds_ptr->edid); num_modes = drm_add_edid_modes(connector, ge_b850v3_lvds_ptr->edid); diff --git a/drivers/gpu/drm/bridge/nxp-ptn3460.c b/drivers/gpu/drm/bridge/nxp-ptn3460.c index d64a3283822a..bd5c191858cb 100644 --- a/drivers/gpu/drm/bridge/nxp-ptn3460.c +++ b/drivers/gpu/drm/bridge/nxp-ptn3460.c @@ -222,7 +222,7 @@ static int ptn3460_get_modes(struct drm_connector *connector) } ptn_bridge->edid = (struct edid *)edid; - drm_mode_connector_update_edid_property(connector, ptn_bridge->edid); + drm_connector_update_edid_property(connector, ptn_bridge->edid); num_modes = drm_add_edid_modes(connector, ptn_bridge->edid); diff --git a/drivers/gpu/drm/bridge/sii902x.c b/drivers/gpu/drm/bridge/sii902x.c index 60373d7eb220..cd331933c230 100644 --- a/drivers/gpu/drm/bridge/sii902x.c +++ b/drivers/gpu/drm/bridge/sii902x.c @@ -170,7 +170,7 @@ static int sii902x_get_modes(struct drm_connector *connector) return ret; edid = drm_get_edid(connector, sii902x->i2c->adapter); - drm_mode_connector_update_edid_property(connector, edid); + drm_connector_update_edid_property(connector, edid); if (edid) { num = drm_add_edid_modes(connector, edid); kfree(edid); diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c index 3c136f2b954f..ab32aceb6f24 100644 --- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c +++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c @@ -1922,7 +1922,7 @@ static int dw_hdmi_connector_get_modes(struct drm_connector *connector) hdmi->sink_is_hdmi = drm_detect_hdmi_monitor(edid); hdmi->sink_has_audio = drm_detect_monitor_audio(edid); - drm_mode_connector_update_edid_property(connector, edid); + drm_connector_update_edid_property(connector, edid); cec_notifier_set_phys_addr_from_edid(hdmi->cec_notifier, edid); ret = drm_add_edid_modes(connector, edid); kfree(edid); diff --git a/drivers/gpu/drm/bridge/tc358767.c b/drivers/gpu/drm/bridge/tc358767.c index 0fd9cf27542c..ee2fd0a349b3 100644 --- a/drivers/gpu/drm/bridge/tc358767.c +++ b/drivers/gpu/drm/bridge/tc358767.c @@ -1140,7 +1140,7 @@ static int tc_connector_get_modes(struct drm_connector *connector) if (!edid) return 0; - drm_mode_connector_update_edid_property(connector, edid); + drm_connector_update_edid_property(connector, edid); count = drm_add_edid_modes(connector, edid); return count; diff --git a/drivers/gpu/drm/bridge/ti-tfp410.c b/drivers/gpu/drm/bridge/ti-tfp410.c index acb857030951..c81bf7910bbe 100644 --- a/drivers/gpu/drm/bridge/ti-tfp410.c +++ b/drivers/gpu/drm/bridge/ti-tfp410.c @@ -62,7 +62,7 @@ static int tfp410_get_modes(struct drm_connector *connector) goto fallback; } - drm_mode_connector_update_edid_property(connector, edid); + drm_connector_update_edid_property(connector, edid); return drm_add_edid_modes(connector, edid); fallback: diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c index 5ada0640de5a..b2b182ffdbe9 100644 --- a/drivers/gpu/drm/drm_connector.c +++ b/drivers/gpu/drm/drm_connector.c @@ -814,7 +814,7 @@ DRM_ENUM_NAME_FN(drm_get_content_protection_name, drm_cp_enum_list) * Blob property which contains the current EDID read from the sink. This * is useful to parse sink identification information like vendor, model * and serial. Drivers should update this property by calling - * drm_mode_connector_update_edid_property(), usually after having parsed + * drm_connector_update_edid_property(), usually after having parsed * the EDID using drm_add_edid_modes(). Userspace cannot change this * property. * DPMS: @@ -1497,7 +1497,7 @@ int drm_mode_connector_set_tile_property(struct drm_connector *connector) EXPORT_SYMBOL(drm_mode_connector_set_tile_property); /** - * drm_mode_connector_update_edid_property - update the edid property of a connector + * drm_connector_update_edid_property - update the edid property of a connector * @connector: drm connector * @edid: new value of the edid property * @@ -1507,7 +1507,7 @@ EXPORT_SYMBOL(drm_mode_connector_set_tile_property); * Returns: * Zero on success, negative errno on failure. */ -int drm_mode_connector_update_edid_property(struct drm_connector *connector, +int drm_connector_update_edid_property(struct drm_connector *connector, const struct edid *edid) { struct drm_device *dev = connector->dev; @@ -1546,7 +1546,7 @@ int drm_mode_connector_update_edid_property(struct drm_connector *connector, dev->mode_config.edid_property); return ret; } -EXPORT_SYMBOL(drm_mode_connector_update_edid_property); +EXPORT_SYMBOL(drm_connector_update_edid_property); /** * drm_mode_connector_set_link_status_property - Set link status property of a connector diff --git a/drivers/gpu/drm/drm_debugfs.c b/drivers/gpu/drm/drm_debugfs.c index 50a20bfc07ea..6f28fe58f169 100644 --- a/drivers/gpu/drm/drm_debugfs.c +++ b/drivers/gpu/drm/drm_debugfs.c @@ -314,13 +314,13 @@ static ssize_t edid_write(struct file *file, const char __user *ubuf, if (len == 5 && !strncmp(buf, "reset", 5)) { connector->override_edid = false; - ret = drm_mode_connector_update_edid_property(connector, NULL); + ret = drm_connector_update_edid_property(connector, NULL); } else if (len < EDID_LENGTH || EDID_LENGTH * (1 + edid->extensions) > len) ret = -EINVAL; else { connector->override_edid = false; - ret = drm_mode_connector_update_edid_property(connector, edid); + ret = drm_connector_update_edid_property(connector, edid); if (!ret) connector->override_edid = true; } diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c index 34fe2704a31c..3d58e0eb26a4 100644 --- a/drivers/gpu/drm/drm_probe_helper.c +++ b/drivers/gpu/drm/drm_probe_helper.c @@ -472,7 +472,7 @@ retry: if (connector->status == connector_status_disconnected) { DRM_DEBUG_KMS("[CONNECTOR:%d:%s] disconnected\n", connector->base.id, connector->name); - drm_mode_connector_update_edid_property(connector, NULL); + drm_connector_update_edid_property(connector, NULL); verbose_prune = false; goto prune; } diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c index e6b0940b1ac2..dfea61edba4a 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c +++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c @@ -319,7 +319,7 @@ static int vidi_get_modes(struct drm_connector *connector) return -ENOMEM; } - drm_mode_connector_update_edid_property(connector, edid); + drm_connector_update_edid_property(connector, edid); return drm_add_edid_modes(connector, edid); } diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c index db91932550cf..6672d0ff0423 100644 --- a/drivers/gpu/drm/exynos/exynos_hdmi.c +++ b/drivers/gpu/drm/exynos/exynos_hdmi.c @@ -888,7 +888,7 @@ static int hdmi_get_modes(struct drm_connector *connector) (hdata->dvi_mode ? "dvi monitor" : "hdmi monitor"), edid->width_cm, edid->height_cm); - drm_mode_connector_update_edid_property(connector, edid); + drm_connector_update_edid_property(connector, edid); cec_notifier_set_phys_addr_from_edid(hdata->notifier, edid); ret = drm_add_edid_modes(connector, edid); diff --git a/drivers/gpu/drm/gma500/cdv_intel_dp.c b/drivers/gpu/drm/gma500/cdv_intel_dp.c index 5ea785f07ba8..90ed20083009 100644 --- a/drivers/gpu/drm/gma500/cdv_intel_dp.c +++ b/drivers/gpu/drm/gma500/cdv_intel_dp.c @@ -1770,7 +1770,7 @@ static int cdv_intel_dp_get_modes(struct drm_connector *connector) edid = drm_get_edid(connector, &intel_dp->adapter); if (edid) { - drm_mode_connector_update_edid_property(connector, edid); + drm_connector_update_edid_property(connector, edid); ret = drm_add_edid_modes(connector, edid); kfree(edid); } diff --git a/drivers/gpu/drm/gma500/cdv_intel_hdmi.c b/drivers/gpu/drm/gma500/cdv_intel_hdmi.c index f0878998526a..4e4e4a66eaee 100644 --- a/drivers/gpu/drm/gma500/cdv_intel_hdmi.c +++ b/drivers/gpu/drm/gma500/cdv_intel_hdmi.c @@ -216,7 +216,7 @@ static int cdv_hdmi_get_modes(struct drm_connector *connector) edid = drm_get_edid(connector, &gma_encoder->i2c_bus->adapter); if (edid) { - drm_mode_connector_update_edid_property(connector, edid); + drm_connector_update_edid_property(connector, edid); ret = drm_add_edid_modes(connector, edid); kfree(edid); } diff --git a/drivers/gpu/drm/gma500/oaktrail_hdmi.c b/drivers/gpu/drm/gma500/oaktrail_hdmi.c index 78566a80ad25..c6d72de1c054 100644 --- a/drivers/gpu/drm/gma500/oaktrail_hdmi.c +++ b/drivers/gpu/drm/gma500/oaktrail_hdmi.c @@ -578,7 +578,7 @@ static int oaktrail_hdmi_get_modes(struct drm_connector *connector) } if (edid) { - drm_mode_connector_update_edid_property(connector, edid); + drm_connector_update_edid_property(connector, edid); ret = drm_add_edid_modes(connector, edid); } return ret; diff --git a/drivers/gpu/drm/gma500/oaktrail_lvds.c b/drivers/gpu/drm/gma500/oaktrail_lvds.c index e6943fef0611..83babb815a5d 100644 --- a/drivers/gpu/drm/gma500/oaktrail_lvds.c +++ b/drivers/gpu/drm/gma500/oaktrail_lvds.c @@ -376,7 +376,7 @@ void oaktrail_lvds_init(struct drm_device *dev, * preferred mode is the right one. */ if (edid) { - drm_mode_connector_update_edid_property(connector, edid); + drm_connector_update_edid_property(connector, edid); drm_add_edid_modes(connector, edid); kfree(edid); diff --git a/drivers/gpu/drm/gma500/psb_intel_modes.c b/drivers/gpu/drm/gma500/psb_intel_modes.c index e5360726d80b..fb4da3cd6681 100644 --- a/drivers/gpu/drm/gma500/psb_intel_modes.c +++ b/drivers/gpu/drm/gma500/psb_intel_modes.c @@ -66,7 +66,7 @@ int psb_intel_ddc_get_modes(struct drm_connector *connector, edid = drm_get_edid(connector, adapter); if (edid) { - drm_mode_connector_update_edid_property(connector, edid); + drm_connector_update_edid_property(connector, edid); ret = drm_add_edid_modes(connector, edid); kfree(edid); } diff --git a/drivers/gpu/drm/gma500/psb_intel_sdvo.c b/drivers/gpu/drm/gma500/psb_intel_sdvo.c index 1d40746ab625..dd3cec0e3190 100644 --- a/drivers/gpu/drm/gma500/psb_intel_sdvo.c +++ b/drivers/gpu/drm/gma500/psb_intel_sdvo.c @@ -1472,7 +1472,7 @@ static void psb_intel_sdvo_get_ddc_modes(struct drm_connector *connector) bool connector_is_digital = !!IS_TMDS(psb_intel_sdvo_connector); if (connector_is_digital == monitor_is_digital) { - drm_mode_connector_update_edid_property(connector, edid); + drm_connector_update_edid_property(connector, edid); drm_add_edid_modes(connector, edid); } diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c index 0038c976536a..d434f576e6b2 100644 --- a/drivers/gpu/drm/i2c/tda998x_drv.c +++ b/drivers/gpu/drm/i2c/tda998x_drv.c @@ -1243,7 +1243,7 @@ static int tda998x_connector_get_modes(struct drm_connector *connector) return 0; } - drm_mode_connector_update_edid_property(connector, edid); + drm_connector_update_edid_property(connector, edid); n = drm_add_edid_modes(connector, edid); kfree(edid); diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index b021801dbd48..c8268f377602 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -6231,7 +6231,7 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp, edid = drm_get_edid(connector, &intel_dp->aux.ddc); if (edid) { if (drm_add_edid_modes(connector, edid)) { - drm_mode_connector_update_edid_property(connector, + drm_connector_update_edid_property(connector, edid); } else { kfree(edid); diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c index bb06744d28a4..ca55b0a82ba6 100644 --- a/drivers/gpu/drm/i915/intel_lvds.c +++ b/drivers/gpu/drm/i915/intel_lvds.c @@ -1131,7 +1131,7 @@ void intel_lvds_init(struct drm_i915_private *dev_priv) intel_gmbus_get_adapter(dev_priv, pin)); if (edid) { if (drm_add_edid_modes(connector, edid)) { - drm_mode_connector_update_edid_property(connector, + drm_connector_update_edid_property(connector, edid); } else { kfree(edid); diff --git a/drivers/gpu/drm/i915/intel_modes.c b/drivers/gpu/drm/i915/intel_modes.c index b39846613e3c..ca44bf368e24 100644 --- a/drivers/gpu/drm/i915/intel_modes.c +++ b/drivers/gpu/drm/i915/intel_modes.c @@ -40,7 +40,7 @@ int intel_connector_update_modes(struct drm_connector *connector, { int ret; - drm_mode_connector_update_edid_property(connector, edid); + drm_connector_update_edid_property(connector, edid); ret = drm_add_edid_modes(connector, edid); return ret; diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c index e6a64b3ecd91..a88611a73b03 100644 --- a/drivers/gpu/drm/i915/intel_sdvo.c +++ b/drivers/gpu/drm/i915/intel_sdvo.c @@ -1913,7 +1913,7 @@ static void intel_sdvo_get_ddc_modes(struct drm_connector *connector) if (edid != NULL) { if (intel_sdvo_connector_matches_edid(to_intel_sdvo_connector(connector), edid)) { - drm_mode_connector_update_edid_property(connector, edid); + drm_connector_update_edid_property(connector, edid); drm_add_edid_modes(connector, edid); } diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c index 56dd7a9a8e25..ae81cbb75f51 100644 --- a/drivers/gpu/drm/imx/imx-ldb.c +++ b/drivers/gpu/drm/imx/imx-ldb.c @@ -143,7 +143,7 @@ static int imx_ldb_connector_get_modes(struct drm_connector *connector) imx_ldb_ch->edid = drm_get_edid(connector, imx_ldb_ch->ddc); if (imx_ldb_ch->edid) { - drm_mode_connector_update_edid_property(connector, + drm_connector_update_edid_property(connector, imx_ldb_ch->edid); num_modes = drm_add_edid_modes(connector, imx_ldb_ch->edid); } diff --git a/drivers/gpu/drm/imx/imx-tve.c b/drivers/gpu/drm/imx/imx-tve.c index bc27c2699464..1a4ced5c09b5 100644 --- a/drivers/gpu/drm/imx/imx-tve.c +++ b/drivers/gpu/drm/imx/imx-tve.c @@ -235,7 +235,7 @@ static int imx_tve_connector_get_modes(struct drm_connector *connector) edid = drm_get_edid(connector, tve->ddc); if (edid) { - drm_mode_connector_update_edid_property(connector, edid); + drm_connector_update_edid_property(connector, edid); ret = drm_add_edid_modes(connector, edid); kfree(edid); } diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c index aedecda9728a..4fc1cf583435 100644 --- a/drivers/gpu/drm/imx/parallel-display.c +++ b/drivers/gpu/drm/imx/parallel-display.c @@ -63,7 +63,7 @@ static int imx_pd_connector_get_modes(struct drm_connector *connector) } if (imxpd->edid) { - drm_mode_connector_update_edid_property(connector, imxpd->edid); + drm_connector_update_edid_property(connector, imxpd->edid); num_modes = drm_add_edid_modes(connector, imxpd->edid); } diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c index 59a11026dceb..835313940395 100644 --- a/drivers/gpu/drm/mediatek/mtk_hdmi.c +++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c @@ -1220,7 +1220,7 @@ static int mtk_hdmi_conn_get_modes(struct drm_connector *conn) hdmi->dvi_mode = !drm_detect_monitor_audio(edid); - drm_mode_connector_update_edid_property(conn, edid); + drm_connector_update_edid_property(conn, edid); ret = drm_add_edid_modes(conn, edid); kfree(edid); diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c index 8918539a19aa..5f104f139197 100644 --- a/drivers/gpu/drm/mgag200/mgag200_mode.c +++ b/drivers/gpu/drm/mgag200/mgag200_mode.c @@ -1553,7 +1553,7 @@ static int mga_vga_get_modes(struct drm_connector *connector) edid = drm_get_edid(connector, &mga_connector->i2c->adapter); if (edid) { - drm_mode_connector_update_edid_property(connector, edid); + drm_connector_update_edid_property(connector, edid); ret = drm_add_edid_modes(connector, edid); kfree(edid); } diff --git a/drivers/gpu/drm/msm/edp/edp_connector.c b/drivers/gpu/drm/msm/edp/edp_connector.c index 6f3fc6b0f0a3..0b5eac054195 100644 --- a/drivers/gpu/drm/msm/edp/edp_connector.c +++ b/drivers/gpu/drm/msm/edp/edp_connector.c @@ -56,7 +56,7 @@ static int edp_connector_get_modes(struct drm_connector *connector) if (ret) return ret; - drm_mode_connector_update_edid_property(connector, drm_edid); + drm_connector_update_edid_property(connector, drm_edid); if (drm_edid) ret = drm_add_edid_modes(connector, drm_edid); diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_connector.c b/drivers/gpu/drm/msm/hdmi/hdmi_connector.c index c0848dfedd50..07feacc5a441 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi_connector.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi_connector.c @@ -392,7 +392,7 @@ static int msm_hdmi_connector_get_modes(struct drm_connector *connector) hdmi_write(hdmi, REG_HDMI_CTRL, hdmi_ctrl); hdmi->hdmi_mode = drm_detect_hdmi_monitor(edid); - drm_mode_connector_update_edid_property(connector, edid); + drm_connector_update_edid_property(connector, edid); if (edid) { ret = drm_add_edid_modes(connector, edid); diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index b83465ae7c1b..2fabb69e452b 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -850,7 +850,7 @@ nv50_mstc_get_modes(struct drm_connector *connector) int ret = 0; mstc->edid = drm_dp_mst_get_edid(&mstc->connector, mstc->port->mgr, mstc->port); - drm_mode_connector_update_edid_property(&mstc->connector, mstc->edid); + drm_connector_update_edid_property(&mstc->connector, mstc->edid); if (mstc->edid) ret = drm_add_edid_modes(&mstc->connector, mstc->edid); diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c index bb46c1d489cf..22a15478d23d 100644 --- a/drivers/gpu/drm/nouveau/nouveau_connector.c +++ b/drivers/gpu/drm/nouveau/nouveau_connector.c @@ -550,7 +550,7 @@ nouveau_connector_detect(struct drm_connector *connector, bool force) /* Cleanup the previous EDID block. */ if (nv_connector->edid) { - drm_mode_connector_update_edid_property(connector, NULL); + drm_connector_update_edid_property(connector, NULL); kfree(nv_connector->edid); nv_connector->edid = NULL; } @@ -575,7 +575,7 @@ nouveau_connector_detect(struct drm_connector *connector, bool force) else nv_connector->edid = drm_get_edid(connector, i2c); - drm_mode_connector_update_edid_property(connector, + drm_connector_update_edid_property(connector, nv_connector->edid); if (!nv_connector->edid) { NV_ERROR(drm, "DDC responded, but no EDID for %s\n", @@ -657,7 +657,7 @@ nouveau_connector_detect_lvds(struct drm_connector *connector, bool force) /* Cleanup the previous EDID block. */ if (nv_connector->edid) { - drm_mode_connector_update_edid_property(connector, NULL); + drm_connector_update_edid_property(connector, NULL); kfree(nv_connector->edid); nv_connector->edid = NULL; } @@ -721,7 +721,7 @@ out: status = connector_status_unknown; #endif - drm_mode_connector_update_edid_property(connector, nv_connector->edid); + drm_connector_update_edid_property(connector, nv_connector->edid); nouveau_connector_set_encoder(connector, nv_encoder); return status; } diff --git a/drivers/gpu/drm/omapdrm/omap_connector.c b/drivers/gpu/drm/omapdrm/omap_connector.c index 5cde26ac937b..2ddb856666c4 100644 --- a/drivers/gpu/drm/omapdrm/omap_connector.c +++ b/drivers/gpu/drm/omapdrm/omap_connector.c @@ -126,14 +126,14 @@ static int omap_connector_get_modes(struct drm_connector *connector) if ((dssdrv->read_edid(dssdev, edid, MAX_EDID) > 0) && drm_edid_is_valid(edid)) { - drm_mode_connector_update_edid_property( + drm_connector_update_edid_property( connector, edid); n = drm_add_edid_modes(connector, edid); omap_connector->hdmi_mode = drm_detect_hdmi_monitor(edid); } else { - drm_mode_connector_update_edid_property( + drm_connector_update_edid_property( connector, NULL); } diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index 86fec03dd260..5b5d0a24e713 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -252,7 +252,7 @@ static int panel_simple_get_modes(struct drm_panel *panel) /* probe EDID if a DDC bus is available */ if (p->ddc) { struct edid *edid = drm_get_edid(panel->connector, p->ddc); - drm_mode_connector_update_edid_property(panel->connector, edid); + drm_connector_update_edid_property(panel->connector, edid); if (edid) { num += drm_add_edid_modes(panel->connector, edid); kfree(edid); diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c index 0655698f2956..414642e5b7a3 100644 --- a/drivers/gpu/drm/radeon/radeon_connectors.c +++ b/drivers/gpu/drm/radeon/radeon_connectors.c @@ -368,11 +368,11 @@ static int radeon_ddc_get_modes(struct drm_connector *connector) int ret; if (radeon_connector->edid) { - drm_mode_connector_update_edid_property(connector, radeon_connector->edid); + drm_connector_update_edid_property(connector, radeon_connector->edid); ret = drm_add_edid_modes(connector, radeon_connector->edid); return ret; } - drm_mode_connector_update_edid_property(connector, NULL); + drm_connector_update_edid_property(connector, NULL); return 0; } diff --git a/drivers/gpu/drm/radeon/radeon_dp_mst.c b/drivers/gpu/drm/radeon/radeon_dp_mst.c index cd8a3ee16649..37956cfc0b6d 100644 --- a/drivers/gpu/drm/radeon/radeon_dp_mst.c +++ b/drivers/gpu/drm/radeon/radeon_dp_mst.c @@ -195,11 +195,11 @@ static int radeon_dp_mst_get_ddc_modes(struct drm_connector *connector) radeon_connector->edid = edid; DRM_DEBUG_KMS("edid retrieved %p\n", edid); if (radeon_connector->edid) { - drm_mode_connector_update_edid_property(&radeon_connector->base, radeon_connector->edid); + drm_connector_update_edid_property(&radeon_connector->base, radeon_connector->edid); ret = drm_add_edid_modes(&radeon_connector->base, radeon_connector->edid); return ret; } - drm_mode_connector_update_edid_property(&radeon_connector->base, NULL); + drm_connector_update_edid_property(&radeon_connector->base, NULL); return ret; } diff --git a/drivers/gpu/drm/rockchip/cdn-dp-core.c b/drivers/gpu/drm/rockchip/cdn-dp-core.c index c6fbdcd87c16..a40cb2be50e1 100644 --- a/drivers/gpu/drm/rockchip/cdn-dp-core.c +++ b/drivers/gpu/drm/rockchip/cdn-dp-core.c @@ -275,7 +275,7 @@ static int cdn_dp_connector_get_modes(struct drm_connector *connector) dp->sink_has_audio = drm_detect_monitor_audio(edid); ret = drm_add_edid_modes(connector, edid); if (ret) - drm_mode_connector_update_edid_property(connector, + drm_connector_update_edid_property(connector, edid); } mutex_unlock(&dp->lock); diff --git a/drivers/gpu/drm/rockchip/inno_hdmi.c b/drivers/gpu/drm/rockchip/inno_hdmi.c index 88d0774c97bd..510fcb33e31d 100644 --- a/drivers/gpu/drm/rockchip/inno_hdmi.c +++ b/drivers/gpu/drm/rockchip/inno_hdmi.c @@ -565,7 +565,7 @@ static int inno_hdmi_connector_get_modes(struct drm_connector *connector) if (edid) { hdmi->hdmi_data.sink_is_hdmi = drm_detect_hdmi_monitor(edid); hdmi->hdmi_data.sink_has_audio = drm_detect_monitor_audio(edid); - drm_mode_connector_update_edid_property(connector, edid); + drm_connector_update_edid_property(connector, edid); ret = drm_add_edid_modes(connector, edid); kfree(edid); } diff --git a/drivers/gpu/drm/sti/sti_hdmi.c b/drivers/gpu/drm/sti/sti_hdmi.c index 58f431102512..0c3008356ab8 100644 --- a/drivers/gpu/drm/sti/sti_hdmi.c +++ b/drivers/gpu/drm/sti/sti_hdmi.c @@ -977,7 +977,7 @@ static int sti_hdmi_connector_get_modes(struct drm_connector *connector) cec_notifier_set_phys_addr_from_edid(hdmi->notifier, edid); count = drm_add_edid_modes(connector, edid); - drm_mode_connector_update_edid_property(connector, edid); + drm_connector_update_edid_property(connector, edid); kfree(edid); return count; diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c index fa4bcd092eaf..9b4b1d015423 100644 --- a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c +++ b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c @@ -220,7 +220,7 @@ static int sun4i_hdmi_get_modes(struct drm_connector *connector) DRM_DEBUG_DRIVER("Monitor is %s monitor\n", hdmi->hdmi_monitor ? "an HDMI" : "a DVI"); - drm_mode_connector_update_edid_property(connector, edid); + drm_connector_update_edid_property(connector, edid); cec_s_phys_addr_from_edid(hdmi->cec_adap, edid); ret = drm_add_edid_modes(connector, edid); kfree(edid); diff --git a/drivers/gpu/drm/tegra/output.c b/drivers/gpu/drm/tegra/output.c index 0c0936511bb4..c662efc7e413 100644 --- a/drivers/gpu/drm/tegra/output.c +++ b/drivers/gpu/drm/tegra/output.c @@ -37,7 +37,7 @@ int tegra_output_connector_get_modes(struct drm_connector *connector) edid = drm_get_edid(connector, output->ddc); cec_notifier_set_phys_addr_from_edid(output->notifier, edid); - drm_mode_connector_update_edid_property(connector, edid); + drm_connector_update_edid_property(connector, edid); if (edid) { err = drm_add_edid_modes(connector, edid); diff --git a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c index c45cabb38db0..46dacca3cce8 100644 --- a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c +++ b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c @@ -173,7 +173,7 @@ static int tfp410_connector_get_modes(struct drm_connector *connector) edid = drm_get_edid(connector, tfp410_connector->mod->i2c); - drm_mode_connector_update_edid_property(connector, edid); + drm_connector_update_edid_property(connector, edid); if (edid) { ret = drm_add_edid_modes(connector, edid); diff --git a/drivers/gpu/drm/udl/udl_connector.c b/drivers/gpu/drm/udl/udl_connector.c index 09dc585aa46f..8fac12e1a1a4 100644 --- a/drivers/gpu/drm/udl/udl_connector.c +++ b/drivers/gpu/drm/udl/udl_connector.c @@ -99,7 +99,7 @@ static int udl_get_modes(struct drm_connector *connector) struct udl_drm_connector, connector); - drm_mode_connector_update_edid_property(connector, udl_connector->edid); + drm_connector_update_edid_property(connector, udl_connector->edid); if (udl_connector->edid) return drm_add_edid_modes(connector, udl_connector->edid); return 0; diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index b8d50533e2bb..91f284e1b908 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -285,7 +285,7 @@ static int vc4_hdmi_connector_get_modes(struct drm_connector *connector) drm_rgb_quant_range_selectable(edid); } - drm_mode_connector_update_edid_property(connector, edid); + drm_connector_update_edid_property(connector, edid); ret = drm_add_edid_modes(connector, edid); kfree(edid); diff --git a/drivers/gpu/drm/zte/zx_hdmi.c b/drivers/gpu/drm/zte/zx_hdmi.c index 13ea90f7a185..d073c6737500 100644 --- a/drivers/gpu/drm/zte/zx_hdmi.c +++ b/drivers/gpu/drm/zte/zx_hdmi.c @@ -272,7 +272,7 @@ static int zx_hdmi_connector_get_modes(struct drm_connector *connector) hdmi->sink_is_hdmi = drm_detect_hdmi_monitor(edid); hdmi->sink_has_audio = drm_detect_monitor_audio(edid); - drm_mode_connector_update_edid_property(connector, edid); + drm_connector_update_edid_property(connector, edid); ret = drm_add_edid_modes(connector, edid); kfree(edid); diff --git a/drivers/gpu/drm/zte/zx_vga.c b/drivers/gpu/drm/zte/zx_vga.c index 3e7e33cd3dfa..3e78ee21b8d0 100644 --- a/drivers/gpu/drm/zte/zx_vga.c +++ b/drivers/gpu/drm/zte/zx_vga.c @@ -109,7 +109,7 @@ static int zx_vga_connector_get_modes(struct drm_connector *connector) */ zx_writel(vga->mmio + VGA_AUTO_DETECT_SEL, VGA_DETECT_SEL_HAS_DEVICE); - drm_mode_connector_update_edid_property(connector, edid); + drm_connector_update_edid_property(connector, edid); ret = drm_add_edid_modes(connector, edid); kfree(edid); diff --git a/drivers/staging/vboxvideo/vbox_mode.c b/drivers/staging/vboxvideo/vbox_mode.c index 5c7ea237893e..a943d2f683ed 100644 --- a/drivers/staging/vboxvideo/vbox_mode.c +++ b/drivers/staging/vboxvideo/vbox_mode.c @@ -504,7 +504,7 @@ static void vbox_set_edid(struct drm_connector *connector, int width, for (i = 0; i < EDID_SIZE - 1; ++i) sum += edid[i]; edid[EDID_SIZE - 1] = (0x100 - (sum & 0xFF)) & 0xFF; - drm_mode_connector_update_edid_property(connector, (struct edid *)edid); + drm_connector_update_edid_property(connector, (struct edid *)edid); } static int vbox_get_modes(struct drm_connector *connector) diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h index e09e16b3e054..4411c0542871 100644 --- a/include/drm/drm_connector.h +++ b/include/drm/drm_connector.h @@ -896,7 +896,7 @@ struct drm_connector { /** * @edid_blob_ptr: DRM property containing EDID if present. Protected by * &drm_mode_config.mutex. This should be updated only by calling - * drm_mode_connector_update_edid_property(). + * drm_connector_update_edid_property(). */ struct drm_property_blob *edid_blob_ptr; @@ -1194,8 +1194,8 @@ int drm_mode_create_suggested_offset_properties(struct drm_device *dev); int drm_mode_connector_set_path_property(struct drm_connector *connector, const char *path); int drm_mode_connector_set_tile_property(struct drm_connector *connector); -int drm_mode_connector_update_edid_property(struct drm_connector *connector, - const struct edid *edid); +int drm_connector_update_edid_property(struct drm_connector *connector, + const struct edid *edid); void drm_mode_connector_set_link_status_property(struct drm_connector *connector, uint64_t link_status); int drm_connector_init_panel_orientation_property( diff --git a/include/drm/drm_modeset_helper_vtables.h b/include/drm/drm_modeset_helper_vtables.h index d0eb76c4b309..61142aa0ab23 100644 --- a/include/drm/drm_modeset_helper_vtables.h +++ b/include/drm/drm_modeset_helper_vtables.h @@ -785,7 +785,7 @@ struct drm_connector_helper_funcs { * * This function should fill in all modes currently valid for the sink * into the &drm_connector.probed_modes list. It should also update the - * EDID property by calling drm_mode_connector_update_edid_property(). + * EDID property by calling drm_connector_update_edid_property(). * * The usual way to implement this is to cache the EDID retrieved in the * probe callback somewhere in the driver-private connector structure. -- cgit v1.2.3 From cde4c44d8769c1be16074c097592c46c7d64092b Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Mon, 9 Jul 2018 10:40:07 +0200 Subject: drm: drop _mode_ from drm_mode_connector_attach_encoder Again to align with the usual prefix of just drm_connector_. Again done with sed + manual fixup for indent issues. Reviewed-by: Sean Paul Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20180709084016.23750-7-daniel.vetter@ffwll.ch --- Documentation/gpu/drm-kms.rst | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_encoders.c | 2 +- drivers/gpu/drm/amd/amdgpu/dce_virtual.c | 2 +- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 2 +- drivers/gpu/drm/arc/arcpgu_sim.c | 2 +- drivers/gpu/drm/ast/ast_mode.c | 2 +- drivers/gpu/drm/bochs/bochs_kms.c | 2 +- drivers/gpu/drm/bridge/adv7511/adv7511_drv.c | 2 +- drivers/gpu/drm/bridge/analogix-anx78xx.c | 4 ++-- drivers/gpu/drm/bridge/analogix/analogix_dp_core.c | 2 +- drivers/gpu/drm/bridge/dumb-vga-dac.c | 2 +- drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c | 2 +- drivers/gpu/drm/bridge/nxp-ptn3460.c | 2 +- drivers/gpu/drm/bridge/panel.c | 2 +- drivers/gpu/drm/bridge/parade-ps8622.c | 2 +- drivers/gpu/drm/bridge/sii902x.c | 2 +- drivers/gpu/drm/bridge/synopsys/dw-hdmi.c | 2 +- drivers/gpu/drm/bridge/tc358767.c | 2 +- drivers/gpu/drm/bridge/ti-tfp410.c | 2 +- drivers/gpu/drm/cirrus/cirrus_mode.c | 2 +- drivers/gpu/drm/drm_connector.c | 10 +++++----- drivers/gpu/drm/drm_simple_kms_helper.c | 2 +- drivers/gpu/drm/drm_writeback.c | 2 +- drivers/gpu/drm/exynos/exynos_drm_dpi.c | 2 +- drivers/gpu/drm/exynos/exynos_drm_dsi.c | 2 +- drivers/gpu/drm/exynos/exynos_drm_vidi.c | 2 +- drivers/gpu/drm/exynos/exynos_hdmi.c | 2 +- drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c | 2 +- drivers/gpu/drm/gma500/gma_display.c | 2 +- drivers/gpu/drm/gma500/mdfld_dsi_dpi.c | 2 +- drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c | 2 +- drivers/gpu/drm/i2c/tda998x_drv.c | 2 +- drivers/gpu/drm/i915/intel_display.c | 3 +-- drivers/gpu/drm/i915/intel_dp_mst.c | 3 +-- drivers/gpu/drm/imx/imx-ldb.c | 3 +-- drivers/gpu/drm/imx/imx-tve.c | 2 +- drivers/gpu/drm/imx/parallel-display.c | 2 +- drivers/gpu/drm/mediatek/mtk_dsi.c | 2 +- drivers/gpu/drm/mediatek/mtk_hdmi.c | 2 +- drivers/gpu/drm/meson/meson_venc_cvbs.c | 2 +- drivers/gpu/drm/mgag200/mgag200_mode.c | 2 +- drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c | 2 +- drivers/gpu/drm/msm/dsi/dsi_manager.c | 2 +- drivers/gpu/drm/msm/edp/edp_connector.c | 2 +- drivers/gpu/drm/msm/hdmi/hdmi_connector.c | 2 +- drivers/gpu/drm/nouveau/dispnv04/dac.c | 2 +- drivers/gpu/drm/nouveau/dispnv04/dfp.c | 2 +- drivers/gpu/drm/nouveau/dispnv04/tvnv04.c | 2 +- drivers/gpu/drm/nouveau/dispnv04/tvnv17.c | 2 +- drivers/gpu/drm/nouveau/dispnv50/disp.c | 8 ++++---- drivers/gpu/drm/omapdrm/omap_drv.c | 2 +- drivers/gpu/drm/qxl/qxl_display.c | 2 +- drivers/gpu/drm/radeon/radeon_encoders.c | 2 +- drivers/gpu/drm/rcar-du/rcar_lvds.c | 2 +- drivers/gpu/drm/rockchip/cdn-dp-core.c | 2 +- drivers/gpu/drm/rockchip/dw-mipi-dsi.c | 2 +- drivers/gpu/drm/rockchip/inno_hdmi.c | 2 +- drivers/gpu/drm/rockchip/rockchip_lvds.c | 2 +- drivers/gpu/drm/shmobile/shmob_drm_crtc.c | 2 +- drivers/gpu/drm/sti/sti_dvo.c | 2 +- drivers/gpu/drm/sti/sti_hda.c | 2 +- drivers/gpu/drm/sti/sti_hdmi.c | 2 +- drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c | 2 +- drivers/gpu/drm/sun4i/sun4i_lvds.c | 2 +- drivers/gpu/drm/sun4i/sun4i_rgb.c | 2 +- drivers/gpu/drm/sun4i/sun4i_tv.c | 2 +- drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c | 2 +- drivers/gpu/drm/tegra/dsi.c | 2 +- drivers/gpu/drm/tegra/hdmi.c | 2 +- drivers/gpu/drm/tegra/rgb.c | 2 +- drivers/gpu/drm/tegra/sor.c | 2 +- drivers/gpu/drm/tilcdc/tilcdc_panel.c | 2 +- drivers/gpu/drm/tilcdc/tilcdc_tfp410.c | 2 +- drivers/gpu/drm/udl/udl_connector.c | 2 +- drivers/gpu/drm/vc4/vc4_hdmi.c | 2 +- drivers/gpu/drm/vc4/vc4_vec.c | 2 +- drivers/gpu/drm/virtio/virtgpu_display.c | 2 +- drivers/gpu/drm/vkms/vkms_output.c | 2 +- drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c | 2 +- drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c | 2 +- drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c | 2 +- drivers/gpu/drm/zte/zx_hdmi.c | 2 +- drivers/gpu/drm/zte/zx_tvenc.c | 2 +- drivers/gpu/drm/zte/zx_vga.c | 2 +- drivers/staging/vboxvideo/vbox_mode.c | 2 +- include/drm/drm_connector.h | 2 +- 86 files changed, 94 insertions(+), 97 deletions(-) (limited to 'include') diff --git a/Documentation/gpu/drm-kms.rst b/Documentation/gpu/drm-kms.rst index 514939433004..58eed08fbe31 100644 --- a/Documentation/gpu/drm-kms.rst +++ b/Documentation/gpu/drm-kms.rst @@ -466,7 +466,7 @@ Output discovery and initialization example drm_encoder_init(dev, &intel_output->enc, &intel_crt_enc_funcs, DRM_MODE_ENCODER_DAC); - drm_mode_connector_attach_encoder(&intel_output->base, + drm_connector_attach_encoder(&intel_output->base, &intel_output->enc); /* Set up the DDC bus. */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_encoders.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_encoders.c index 94138abe093b..ae8fac34f7a5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_encoders.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_encoders.c @@ -46,7 +46,7 @@ amdgpu_link_encoder_connector(struct drm_device *dev) list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) { amdgpu_encoder = to_amdgpu_encoder(encoder); if (amdgpu_encoder->devices & amdgpu_connector->devices) { - drm_mode_connector_attach_encoder(connector, encoder); + drm_connector_attach_encoder(connector, encoder); if (amdgpu_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT)) { amdgpu_atombios_encoder_init_backlight(amdgpu_encoder, connector); adev->mode_info.bl_encoder = amdgpu_encoder; diff --git a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c index 016f15093173..677e96a56330 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c @@ -627,7 +627,7 @@ static int dce_virtual_connector_encoder_init(struct amdgpu_device *adev, drm_connector_register(connector); /* link them */ - drm_mode_connector_attach_encoder(connector, encoder); + drm_connector_attach_encoder(connector, encoder); return 0; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index c4ab19831344..ae09331eed00 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -3615,7 +3615,7 @@ static int amdgpu_dm_connector_init(struct amdgpu_display_manager *dm, link, link_index); - drm_mode_connector_attach_encoder( + drm_connector_attach_encoder( &aconnector->base, &aencoder->base); drm_connector_register(&aconnector->base); diff --git a/drivers/gpu/drm/arc/arcpgu_sim.c b/drivers/gpu/drm/arc/arcpgu_sim.c index b8f6f9a5dfbe..68629e614990 100644 --- a/drivers/gpu/drm/arc/arcpgu_sim.c +++ b/drivers/gpu/drm/arc/arcpgu_sim.c @@ -99,7 +99,7 @@ int arcpgu_drm_sim_init(struct drm_device *drm, struct device_node *np) goto error_encoder_cleanup; } - ret = drm_mode_connector_attach_encoder(connector, encoder); + ret = drm_connector_attach_encoder(connector, encoder); if (ret < 0) { dev_err(drm->dev, "could not attach connector to encoder\n"); drm_connector_unregister(connector); diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c index 1bb8174ad155..5e77d456d9bb 100644 --- a/drivers/gpu/drm/ast/ast_mode.c +++ b/drivers/gpu/drm/ast/ast_mode.c @@ -900,7 +900,7 @@ static int ast_connector_init(struct drm_device *dev) connector->polled = DRM_CONNECTOR_POLL_CONNECT; encoder = list_first_entry(&dev->mode_config.encoder_list, struct drm_encoder, head); - drm_mode_connector_attach_encoder(connector, encoder); + drm_connector_attach_encoder(connector, encoder); ast_connector->i2c = ast_i2c_create(dev); if (!ast_connector->i2c) diff --git a/drivers/gpu/drm/bochs/bochs_kms.c b/drivers/gpu/drm/bochs/bochs_kms.c index 233980a78591..ca5a9afdd5cf 100644 --- a/drivers/gpu/drm/bochs/bochs_kms.c +++ b/drivers/gpu/drm/bochs/bochs_kms.c @@ -259,7 +259,7 @@ int bochs_kms_init(struct bochs_device *bochs) bochs_crtc_init(bochs->dev); bochs_encoder_init(bochs->dev); bochs_connector_init(bochs->dev); - drm_mode_connector_attach_encoder(&bochs->connector, + drm_connector_attach_encoder(&bochs->connector, &bochs->encoder); return 0; diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c index 1f4745953aca..6437b878724a 100644 --- a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c +++ b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c @@ -860,7 +860,7 @@ static int adv7511_bridge_attach(struct drm_bridge *bridge) } drm_connector_helper_add(&adv->connector, &adv7511_connector_helper_funcs); - drm_mode_connector_attach_encoder(&adv->connector, bridge->encoder); + drm_connector_attach_encoder(&adv->connector, bridge->encoder); if (adv->type == ADV7533) ret = adv7533_attach_dsi(adv); diff --git a/drivers/gpu/drm/bridge/analogix-anx78xx.c b/drivers/gpu/drm/bridge/analogix-anx78xx.c index 37f947dcadec..f8433c93f463 100644 --- a/drivers/gpu/drm/bridge/analogix-anx78xx.c +++ b/drivers/gpu/drm/bridge/analogix-anx78xx.c @@ -1048,8 +1048,8 @@ static int anx78xx_bridge_attach(struct drm_bridge *bridge) anx78xx->connector.polled = DRM_CONNECTOR_POLL_HPD; - err = drm_mode_connector_attach_encoder(&anx78xx->connector, - bridge->encoder); + err = drm_connector_attach_encoder(&anx78xx->connector, + bridge->encoder); if (err) { DRM_ERROR("Failed to link up connector to encoder: %d\n", err); return err; diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c index 288c015f7460..d68986cea132 100644 --- a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c +++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c @@ -1210,7 +1210,7 @@ static int analogix_dp_bridge_attach(struct drm_bridge *bridge) drm_connector_helper_add(connector, &analogix_dp_connector_helper_funcs); - drm_mode_connector_attach_encoder(connector, encoder); + drm_connector_attach_encoder(connector, encoder); } /* diff --git a/drivers/gpu/drm/bridge/dumb-vga-dac.c b/drivers/gpu/drm/bridge/dumb-vga-dac.c index da99b8ba4ee1..9b706789a341 100644 --- a/drivers/gpu/drm/bridge/dumb-vga-dac.c +++ b/drivers/gpu/drm/bridge/dumb-vga-dac.c @@ -122,7 +122,7 @@ static int dumb_vga_attach(struct drm_bridge *bridge) return ret; } - drm_mode_connector_attach_encoder(&vga->connector, + drm_connector_attach_encoder(&vga->connector, bridge->encoder); return 0; diff --git a/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c b/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c index b49b543bd1f6..2136c97aeb8e 100644 --- a/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c +++ b/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c @@ -241,7 +241,7 @@ static int ge_b850v3_lvds_attach(struct drm_bridge *bridge) return ret; } - ret = drm_mode_connector_attach_encoder(connector, bridge->encoder); + ret = drm_connector_attach_encoder(connector, bridge->encoder); if (ret) return ret; diff --git a/drivers/gpu/drm/bridge/nxp-ptn3460.c b/drivers/gpu/drm/bridge/nxp-ptn3460.c index bd5c191858cb..a3e817abace1 100644 --- a/drivers/gpu/drm/bridge/nxp-ptn3460.c +++ b/drivers/gpu/drm/bridge/nxp-ptn3460.c @@ -265,7 +265,7 @@ static int ptn3460_bridge_attach(struct drm_bridge *bridge) drm_connector_helper_add(&ptn_bridge->connector, &ptn3460_connector_helper_funcs); drm_connector_register(&ptn_bridge->connector); - drm_mode_connector_attach_encoder(&ptn_bridge->connector, + drm_connector_attach_encoder(&ptn_bridge->connector, bridge->encoder); if (ptn_bridge->panel) diff --git a/drivers/gpu/drm/bridge/panel.c b/drivers/gpu/drm/bridge/panel.c index 6d99d4a3beb3..7cbaba213ef6 100644 --- a/drivers/gpu/drm/bridge/panel.c +++ b/drivers/gpu/drm/bridge/panel.c @@ -79,7 +79,7 @@ static int panel_bridge_attach(struct drm_bridge *bridge) return ret; } - drm_mode_connector_attach_encoder(&panel_bridge->connector, + drm_connector_attach_encoder(&panel_bridge->connector, bridge->encoder); ret = drm_panel_attach(panel_bridge->panel, &panel_bridge->connector); diff --git a/drivers/gpu/drm/bridge/parade-ps8622.c b/drivers/gpu/drm/bridge/parade-ps8622.c index 81198f5e9afa..7334d1b62b71 100644 --- a/drivers/gpu/drm/bridge/parade-ps8622.c +++ b/drivers/gpu/drm/bridge/parade-ps8622.c @@ -503,7 +503,7 @@ static int ps8622_attach(struct drm_bridge *bridge) drm_connector_helper_add(&ps8622->connector, &ps8622_connector_helper_funcs); drm_connector_register(&ps8622->connector); - drm_mode_connector_attach_encoder(&ps8622->connector, + drm_connector_attach_encoder(&ps8622->connector, bridge->encoder); if (ps8622->panel) diff --git a/drivers/gpu/drm/bridge/sii902x.c b/drivers/gpu/drm/bridge/sii902x.c index cd331933c230..e59a13542333 100644 --- a/drivers/gpu/drm/bridge/sii902x.c +++ b/drivers/gpu/drm/bridge/sii902x.c @@ -324,7 +324,7 @@ static int sii902x_bridge_attach(struct drm_bridge *bridge) else sii902x->connector.polled = DRM_CONNECTOR_POLL_CONNECT; - drm_mode_connector_attach_encoder(&sii902x->connector, bridge->encoder); + drm_connector_attach_encoder(&sii902x->connector, bridge->encoder); return 0; } diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c index ab32aceb6f24..5971976284bf 100644 --- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c +++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c @@ -1974,7 +1974,7 @@ static int dw_hdmi_bridge_attach(struct drm_bridge *bridge) drm_connector_init(bridge->dev, connector, &dw_hdmi_connector_funcs, DRM_MODE_CONNECTOR_HDMIA); - drm_mode_connector_attach_encoder(connector, encoder); + drm_connector_attach_encoder(connector, encoder); return 0; } diff --git a/drivers/gpu/drm/bridge/tc358767.c b/drivers/gpu/drm/bridge/tc358767.c index ee2fd0a349b3..8e28e738cb52 100644 --- a/drivers/gpu/drm/bridge/tc358767.c +++ b/drivers/gpu/drm/bridge/tc358767.c @@ -1195,7 +1195,7 @@ static int tc_bridge_attach(struct drm_bridge *bridge) drm_display_info_set_bus_formats(&tc->connector.display_info, &bus_format, 1); - drm_mode_connector_attach_encoder(&tc->connector, tc->bridge.encoder); + drm_connector_attach_encoder(&tc->connector, tc->bridge.encoder); return 0; } diff --git a/drivers/gpu/drm/bridge/ti-tfp410.c b/drivers/gpu/drm/bridge/ti-tfp410.c index c81bf7910bbe..c3e32138c6bb 100644 --- a/drivers/gpu/drm/bridge/ti-tfp410.c +++ b/drivers/gpu/drm/bridge/ti-tfp410.c @@ -132,7 +132,7 @@ static int tfp410_attach(struct drm_bridge *bridge) return ret; } - drm_mode_connector_attach_encoder(&dvi->connector, + drm_connector_attach_encoder(&dvi->connector, bridge->encoder); return 0; diff --git a/drivers/gpu/drm/cirrus/cirrus_mode.c b/drivers/gpu/drm/cirrus/cirrus_mode.c index b529f8c8e2a6..336bfda40125 100644 --- a/drivers/gpu/drm/cirrus/cirrus_mode.c +++ b/drivers/gpu/drm/cirrus/cirrus_mode.c @@ -530,7 +530,7 @@ int cirrus_modeset_init(struct cirrus_device *cdev) return -1; } - drm_mode_connector_attach_encoder(connector, encoder); + drm_connector_attach_encoder(connector, encoder); ret = cirrus_fbdev_init(cdev); if (ret) { diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c index b2b182ffdbe9..8997792e2e23 100644 --- a/drivers/gpu/drm/drm_connector.c +++ b/drivers/gpu/drm/drm_connector.c @@ -48,7 +48,7 @@ * * Connectors must be attached to an encoder to be used. For devices that map * connectors to encoders 1:1, the connector should be attached at - * initialization time with a call to drm_mode_connector_attach_encoder(). The + * initialization time with a call to drm_connector_attach_encoder(). The * driver must also set the &drm_connector.encoder field to point to the * attached encoder. * @@ -291,7 +291,7 @@ out_put: EXPORT_SYMBOL(drm_connector_init); /** - * drm_mode_connector_attach_encoder - attach a connector to an encoder + * drm_connector_attach_encoder - attach a connector to an encoder * @connector: connector to attach * @encoder: encoder to attach @connector to * @@ -302,8 +302,8 @@ EXPORT_SYMBOL(drm_connector_init); * Returns: * Zero on success, negative errno on failure. */ -int drm_mode_connector_attach_encoder(struct drm_connector *connector, - struct drm_encoder *encoder) +int drm_connector_attach_encoder(struct drm_connector *connector, + struct drm_encoder *encoder) { int i; @@ -329,7 +329,7 @@ int drm_mode_connector_attach_encoder(struct drm_connector *connector, } return -ENOMEM; } -EXPORT_SYMBOL(drm_mode_connector_attach_encoder); +EXPORT_SYMBOL(drm_connector_attach_encoder); /** * drm_connector_has_possible_encoder - check if the connector and encoder are assosicated with each other diff --git a/drivers/gpu/drm/drm_simple_kms_helper.c b/drivers/gpu/drm/drm_simple_kms_helper.c index b72fcf1e9605..51fa978f0d23 100644 --- a/drivers/gpu/drm/drm_simple_kms_helper.c +++ b/drivers/gpu/drm/drm_simple_kms_helper.c @@ -287,7 +287,7 @@ int drm_simple_display_pipe_init(struct drm_device *dev, if (ret || !connector) return ret; - return drm_mode_connector_attach_encoder(connector, encoder); + return drm_connector_attach_encoder(connector, encoder); } EXPORT_SYMBOL(drm_simple_display_pipe_init); diff --git a/drivers/gpu/drm/drm_writeback.c b/drivers/gpu/drm/drm_writeback.c index 69e7a63cfcc3..169746f6b567 100644 --- a/drivers/gpu/drm/drm_writeback.c +++ b/drivers/gpu/drm/drm_writeback.c @@ -202,7 +202,7 @@ int drm_writeback_connector_init(struct drm_device *dev, if (ret) goto connector_fail; - ret = drm_mode_connector_attach_encoder(connector, + ret = drm_connector_attach_encoder(connector, &wb_connector->encoder); if (ret) goto attach_fail; diff --git a/drivers/gpu/drm/exynos/exynos_drm_dpi.c b/drivers/gpu/drm/exynos/exynos_drm_dpi.c index 5887e8522b70..2f0babb67c51 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_dpi.c +++ b/drivers/gpu/drm/exynos/exynos_drm_dpi.c @@ -113,7 +113,7 @@ static int exynos_dpi_create_connector(struct drm_encoder *encoder) } drm_connector_helper_add(connector, &exynos_dpi_connector_helper_funcs); - drm_mode_connector_attach_encoder(connector, encoder); + drm_connector_attach_encoder(connector, encoder); return 0; } diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c index 809e1e0447df..a1ed6146a3b5 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c +++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c @@ -1479,7 +1479,7 @@ static int exynos_dsi_create_connector(struct drm_encoder *encoder) connector->status = connector_status_disconnected; drm_connector_helper_add(connector, &exynos_dsi_connector_helper_funcs); - drm_mode_connector_attach_encoder(connector, encoder); + drm_connector_attach_encoder(connector, encoder); return 0; } diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c index dfea61edba4a..19697c1362d8 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c +++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c @@ -344,7 +344,7 @@ static int vidi_create_connector(struct drm_encoder *encoder) } drm_connector_helper_add(connector, &vidi_connector_helper_funcs); - drm_mode_connector_attach_encoder(connector, encoder); + drm_connector_attach_encoder(connector, encoder); return 0; } diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c index 6672d0ff0423..3a11c719a580 100644 --- a/drivers/gpu/drm/exynos/exynos_hdmi.c +++ b/drivers/gpu/drm/exynos/exynos_hdmi.c @@ -951,7 +951,7 @@ static int hdmi_create_connector(struct drm_encoder *encoder) } drm_connector_helper_add(connector, &hdmi_connector_helper_funcs); - drm_mode_connector_attach_encoder(connector, encoder); + drm_connector_attach_encoder(connector, encoder); if (hdata->bridge) { ret = drm_bridge_attach(encoder, hdata->bridge, NULL); diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c index 681e2a07d03b..2298ed2a9e1c 100644 --- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c +++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c @@ -117,7 +117,7 @@ static int fsl_dcu_attach_panel(struct fsl_dcu_drm_device *fsl_dev, if (ret < 0) goto err_cleanup; - ret = drm_mode_connector_attach_encoder(connector, encoder); + ret = drm_connector_attach_encoder(connector, encoder); if (ret < 0) goto err_sysfs; diff --git a/drivers/gpu/drm/gma500/gma_display.c b/drivers/gpu/drm/gma500/gma_display.c index 08f17f85b801..09c1161a7ac6 100644 --- a/drivers/gpu/drm/gma500/gma_display.c +++ b/drivers/gpu/drm/gma500/gma_display.c @@ -665,7 +665,7 @@ void gma_connector_attach_encoder(struct gma_connector *connector, struct gma_encoder *encoder) { connector->encoder = encoder; - drm_mode_connector_attach_encoder(&connector->base, + drm_connector_attach_encoder(&connector->base, &encoder->base); } diff --git a/drivers/gpu/drm/gma500/mdfld_dsi_dpi.c b/drivers/gpu/drm/gma500/mdfld_dsi_dpi.c index a05c020602bd..d0bf5a1e94e8 100644 --- a/drivers/gpu/drm/gma500/mdfld_dsi_dpi.c +++ b/drivers/gpu/drm/gma500/mdfld_dsi_dpi.c @@ -999,7 +999,7 @@ struct mdfld_dsi_encoder *mdfld_dsi_dpi_init(struct drm_device *dev, p_funcs->encoder_helper_funcs); /*attach to given connector*/ - drm_mode_connector_attach_encoder(connector, encoder); + drm_connector_attach_encoder(connector, encoder); /*set possible crtcs and clones*/ if (dsi_connector->pipe) { diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c index d2f4749ebf8d..744956cea749 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c @@ -133,7 +133,7 @@ int hibmc_vdac_init(struct hibmc_drm_private *priv) } drm_encoder_helper_add(encoder, &hibmc_encoder_helper_funcs); - drm_mode_connector_attach_encoder(connector, encoder); + drm_connector_attach_encoder(connector, encoder); return 0; } diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c index d434f576e6b2..eecdc327b9f8 100644 --- a/drivers/gpu/drm/i2c/tda998x_drv.c +++ b/drivers/gpu/drm/i2c/tda998x_drv.c @@ -1301,7 +1301,7 @@ static int tda998x_connector_init(struct tda998x_priv *priv, if (ret) return ret; - drm_mode_connector_attach_encoder(&priv->connector, &priv->encoder); + drm_connector_attach_encoder(&priv->connector, &priv->encoder); return 0; } diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 694a4703042f..fbe5a6572d7d 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -15899,8 +15899,7 @@ void intel_connector_attach_encoder(struct intel_connector *connector, struct intel_encoder *encoder) { connector->encoder = encoder; - drm_mode_connector_attach_encoder(&connector->base, - &encoder->base); + drm_connector_attach_encoder(&connector->base, &encoder->base); } /* diff --git a/drivers/gpu/drm/i915/intel_dp_mst.c b/drivers/gpu/drm/i915/intel_dp_mst.c index 0f012fbe34eb..364330fc5d6a 100644 --- a/drivers/gpu/drm/i915/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/intel_dp_mst.c @@ -466,8 +466,7 @@ static struct drm_connector *intel_dp_add_mst_connector(struct drm_dp_mst_topolo struct drm_encoder *enc = &intel_dp->mst_encoders[pipe]->base.base; - ret = drm_mode_connector_attach_encoder(&intel_connector->base, - enc); + ret = drm_connector_attach_encoder(&intel_connector->base, enc); if (ret) goto err; } diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c index ae81cbb75f51..7312beb6f1fc 100644 --- a/drivers/gpu/drm/imx/imx-ldb.c +++ b/drivers/gpu/drm/imx/imx-ldb.c @@ -471,8 +471,7 @@ static int imx_ldb_register(struct drm_device *drm, drm_connector_init(drm, &imx_ldb_ch->connector, &imx_ldb_connector_funcs, DRM_MODE_CONNECTOR_LVDS); - drm_mode_connector_attach_encoder(&imx_ldb_ch->connector, - encoder); + drm_connector_attach_encoder(&imx_ldb_ch->connector, encoder); } if (imx_ldb_ch->panel) { diff --git a/drivers/gpu/drm/imx/imx-tve.c b/drivers/gpu/drm/imx/imx-tve.c index 1a4ced5c09b5..cffd3310240e 100644 --- a/drivers/gpu/drm/imx/imx-tve.c +++ b/drivers/gpu/drm/imx/imx-tve.c @@ -493,7 +493,7 @@ static int imx_tve_register(struct drm_device *drm, struct imx_tve *tve) drm_connector_init(drm, &tve->connector, &imx_tve_connector_funcs, DRM_MODE_CONNECTOR_VGA); - drm_mode_connector_attach_encoder(&tve->connector, &tve->encoder); + drm_connector_attach_encoder(&tve->connector, &tve->encoder); return 0; } diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c index 4fc1cf583435..aefd04e18f93 100644 --- a/drivers/gpu/drm/imx/parallel-display.c +++ b/drivers/gpu/drm/imx/parallel-display.c @@ -197,7 +197,7 @@ static int imx_pd_register(struct drm_device *drm, return ret; } } else { - drm_mode_connector_attach_encoder(&imxpd->connector, encoder); + drm_connector_attach_encoder(&imxpd->connector, encoder); } return 0; diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c index aa0943ec32b0..66df1b177959 100644 --- a/drivers/gpu/drm/mediatek/mtk_dsi.c +++ b/drivers/gpu/drm/mediatek/mtk_dsi.c @@ -782,7 +782,7 @@ static int mtk_dsi_create_connector(struct drm_device *drm, struct mtk_dsi *dsi) drm_connector_helper_add(&dsi->conn, &mtk_dsi_connector_helper_funcs); dsi->conn.dpms = DRM_MODE_DPMS_OFF; - drm_mode_connector_attach_encoder(&dsi->conn, &dsi->encoder); + drm_connector_attach_encoder(&dsi->conn, &dsi->encoder); if (dsi->panel) { ret = drm_panel_attach(dsi->panel, &dsi->conn); diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c index 835313940395..2d45d1dd9554 100644 --- a/drivers/gpu/drm/mediatek/mtk_hdmi.c +++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c @@ -1306,7 +1306,7 @@ static int mtk_hdmi_bridge_attach(struct drm_bridge *bridge) hdmi->conn.interlace_allowed = true; hdmi->conn.doublescan_allowed = false; - ret = drm_mode_connector_attach_encoder(&hdmi->conn, + ret = drm_connector_attach_encoder(&hdmi->conn, bridge->encoder); if (ret) { dev_err(hdmi->dev, diff --git a/drivers/gpu/drm/meson/meson_venc_cvbs.c b/drivers/gpu/drm/meson/meson_venc_cvbs.c index 79d95ca8a0c0..f7945bae3b4a 100644 --- a/drivers/gpu/drm/meson/meson_venc_cvbs.c +++ b/drivers/gpu/drm/meson/meson_venc_cvbs.c @@ -282,7 +282,7 @@ int meson_venc_cvbs_create(struct meson_drm *priv) encoder->possible_crtcs = BIT(0); - drm_mode_connector_attach_encoder(connector, encoder); + drm_connector_attach_encoder(connector, encoder); return 0; } diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c index 5f104f139197..acf7bfe68454 100644 --- a/drivers/gpu/drm/mgag200/mgag200_mode.c +++ b/drivers/gpu/drm/mgag200/mgag200_mode.c @@ -1747,7 +1747,7 @@ int mgag200_modeset_init(struct mga_device *mdev) return -1; } - drm_mode_connector_attach_encoder(connector, encoder); + drm_connector_attach_encoder(connector, encoder); ret = mgag200_fbdev_init(mdev); if (ret) { diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c index 32fba5664b0e..5368e621999c 100644 --- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c +++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c @@ -132,7 +132,7 @@ struct drm_connector *mdp4_lvds_connector_init(struct drm_device *dev, connector->interlace_allowed = 0; connector->doublescan_allowed = 0; - drm_mode_connector_attach_encoder(connector, encoder); + drm_connector_attach_encoder(connector, encoder); return connector; } diff --git a/drivers/gpu/drm/msm/dsi/dsi_manager.c b/drivers/gpu/drm/msm/dsi/dsi_manager.c index 4beba3f7d067..21e0dc51531d 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_manager.c +++ b/drivers/gpu/drm/msm/dsi/dsi_manager.c @@ -684,7 +684,7 @@ struct drm_connector *msm_dsi_manager_connector_init(u8 id) connector->interlace_allowed = 0; connector->doublescan_allowed = 0; - drm_mode_connector_attach_encoder(connector, msm_dsi->encoder); + drm_connector_attach_encoder(connector, msm_dsi->encoder); return connector; } diff --git a/drivers/gpu/drm/msm/edp/edp_connector.c b/drivers/gpu/drm/msm/edp/edp_connector.c index 0b5eac054195..058ff92a0207 100644 --- a/drivers/gpu/drm/msm/edp/edp_connector.c +++ b/drivers/gpu/drm/msm/edp/edp_connector.c @@ -134,7 +134,7 @@ struct drm_connector *msm_edp_connector_init(struct msm_edp *edp) connector->interlace_allowed = false; connector->doublescan_allowed = false; - drm_mode_connector_attach_encoder(connector, edp->encoder); + drm_connector_attach_encoder(connector, edp->encoder); return connector; } diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_connector.c b/drivers/gpu/drm/msm/hdmi/hdmi_connector.c index 07feacc5a441..e9c9a0af508e 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi_connector.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi_connector.c @@ -477,7 +477,7 @@ struct drm_connector *msm_hdmi_connector_init(struct hdmi *hdmi) return ERR_PTR(ret); } - drm_mode_connector_attach_encoder(connector, hdmi->encoder); + drm_connector_attach_encoder(connector, hdmi->encoder); return connector; } diff --git a/drivers/gpu/drm/nouveau/dispnv04/dac.c b/drivers/gpu/drm/nouveau/dispnv04/dac.c index 4feab0a5419d..e7af95d37ddb 100644 --- a/drivers/gpu/drm/nouveau/dispnv04/dac.c +++ b/drivers/gpu/drm/nouveau/dispnv04/dac.c @@ -556,6 +556,6 @@ nv04_dac_create(struct drm_connector *connector, struct dcb_output *entry) encoder->possible_crtcs = entry->heads; encoder->possible_clones = 0; - drm_mode_connector_attach_encoder(connector, encoder); + drm_connector_attach_encoder(connector, encoder); return 0; } diff --git a/drivers/gpu/drm/nouveau/dispnv04/dfp.c b/drivers/gpu/drm/nouveau/dispnv04/dfp.c index 9805d2cdc1a1..73d41abbb510 100644 --- a/drivers/gpu/drm/nouveau/dispnv04/dfp.c +++ b/drivers/gpu/drm/nouveau/dispnv04/dfp.c @@ -716,6 +716,6 @@ nv04_dfp_create(struct drm_connector *connector, struct dcb_output *entry) entry->location != DCB_LOC_ON_CHIP) nv04_tmds_slave_init(encoder); - drm_mode_connector_attach_encoder(connector, encoder); + drm_connector_attach_encoder(connector, encoder); return 0; } diff --git a/drivers/gpu/drm/nouveau/dispnv04/tvnv04.c b/drivers/gpu/drm/nouveau/dispnv04/tvnv04.c index 01664357d3e1..de4490b4ed30 100644 --- a/drivers/gpu/drm/nouveau/dispnv04/tvnv04.c +++ b/drivers/gpu/drm/nouveau/dispnv04/tvnv04.c @@ -244,7 +244,7 @@ nv04_tv_create(struct drm_connector *connector, struct dcb_output *entry) /* Attach it to the specified connector. */ get_slave_funcs(encoder)->create_resources(encoder, connector); - drm_mode_connector_attach_encoder(connector, encoder); + drm_connector_attach_encoder(connector, encoder); return 0; diff --git a/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c b/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c index 6d99f11fee4e..6a4ca139cf5d 100644 --- a/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c +++ b/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c @@ -821,6 +821,6 @@ nv17_tv_create(struct drm_connector *connector, struct dcb_output *entry) encoder->possible_clones = 0; nv17_tv_create_resources(encoder, connector); - drm_mode_connector_attach_encoder(connector, encoder); + drm_connector_attach_encoder(connector, encoder); return 0; } diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index 2fabb69e452b..475456c19b76 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -424,7 +424,7 @@ nv50_dac_create(struct drm_connector *connector, struct dcb_output *dcbe) "dac-%04x-%04x", dcbe->hasht, dcbe->hashm); drm_encoder_helper_add(encoder, &nv50_dac_help); - drm_mode_connector_attach_encoder(connector, encoder); + drm_connector_attach_encoder(connector, encoder); return 0; } @@ -927,7 +927,7 @@ nv50_mstc_new(struct nv50_mstm *mstm, struct drm_dp_mst_port *port, nouveau_conn_attach_properties(&mstc->connector); for (i = 0; i < ARRAY_SIZE(mstm->msto) && mstm->msto[i]; i++) - drm_mode_connector_attach_encoder(&mstc->connector, &mstm->msto[i]->encoder); + drm_connector_attach_encoder(&mstc->connector, &mstm->msto[i]->encoder); drm_object_attach_property(&mstc->connector.base, dev->mode_config.path_property, 0); drm_object_attach_property(&mstc->connector.base, dev->mode_config.tile_property, 0); @@ -1418,7 +1418,7 @@ nv50_sor_create(struct drm_connector *connector, struct dcb_output *dcbe) "sor-%04x-%04x", dcbe->hasht, dcbe->hashm); drm_encoder_helper_add(encoder, &nv50_sor_help); - drm_mode_connector_attach_encoder(connector, encoder); + drm_connector_attach_encoder(connector, encoder); if (dcbe->type == DCB_OUTPUT_DP) { struct nv50_disp *disp = nv50_disp(encoder->dev); @@ -1576,7 +1576,7 @@ nv50_pior_create(struct drm_connector *connector, struct dcb_output *dcbe) "pior-%04x-%04x", dcbe->hasht, dcbe->hashm); drm_encoder_helper_add(encoder, &nv50_pior_help); - drm_mode_connector_attach_encoder(connector, encoder); + drm_connector_attach_encoder(connector, encoder); return 0; } diff --git a/drivers/gpu/drm/omapdrm/omap_drv.c b/drivers/gpu/drm/omapdrm/omap_drv.c index 5005ecc284d2..1b6601e9b107 100644 --- a/drivers/gpu/drm/omapdrm/omap_drv.c +++ b/drivers/gpu/drm/omapdrm/omap_drv.c @@ -274,7 +274,7 @@ static int omap_modeset_init(struct drm_device *dev) if (IS_ERR(crtc)) return PTR_ERR(crtc); - drm_mode_connector_attach_encoder(connector, encoder); + drm_connector_attach_encoder(connector, encoder); encoder->possible_crtcs = (1 << crtc_idx); priv->crtcs[priv->num_crtcs++] = crtc; diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c index 768207fbbae3..0570c6826bff 100644 --- a/drivers/gpu/drm/qxl/qxl_display.c +++ b/drivers/gpu/drm/qxl/qxl_display.c @@ -1086,7 +1086,7 @@ static int qdev_output_init(struct drm_device *dev, int num_output) /* we get HPD via client monitors config */ connector->polled = DRM_CONNECTOR_POLL_HPD; encoder->possible_crtcs = 1 << num_output; - drm_mode_connector_attach_encoder(&qxl_output->base, + drm_connector_attach_encoder(&qxl_output->base, &qxl_output->enc); drm_encoder_helper_add(encoder, &qxl_enc_helper_funcs); drm_connector_helper_add(connector, &qxl_connector_helper_funcs); diff --git a/drivers/gpu/drm/radeon/radeon_encoders.c b/drivers/gpu/drm/radeon/radeon_encoders.c index c6ee80216cf4..c341fb2a5b56 100644 --- a/drivers/gpu/drm/radeon/radeon_encoders.c +++ b/drivers/gpu/drm/radeon/radeon_encoders.c @@ -211,7 +211,7 @@ radeon_link_encoder_connector(struct drm_device *dev) list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) { radeon_encoder = to_radeon_encoder(encoder); if (radeon_encoder->devices & radeon_connector->devices) { - drm_mode_connector_attach_encoder(connector, encoder); + drm_connector_attach_encoder(connector, encoder); if (radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT)) radeon_encoder_add_backlight(radeon_encoder, connector); } diff --git a/drivers/gpu/drm/rcar-du/rcar_lvds.c b/drivers/gpu/drm/rcar-du/rcar_lvds.c index 5d8e391e75f4..4c39de3f4f0f 100644 --- a/drivers/gpu/drm/rcar-du/rcar_lvds.c +++ b/drivers/gpu/drm/rcar-du/rcar_lvds.c @@ -353,7 +353,7 @@ static int rcar_lvds_attach(struct drm_bridge *bridge) drm_connector_helper_add(connector, &rcar_lvds_conn_helper_funcs); - ret = drm_mode_connector_attach_encoder(connector, encoder); + ret = drm_connector_attach_encoder(connector, encoder); if (ret < 0) return ret; diff --git a/drivers/gpu/drm/rockchip/cdn-dp-core.c b/drivers/gpu/drm/rockchip/cdn-dp-core.c index a40cb2be50e1..8ad0d773dc33 100644 --- a/drivers/gpu/drm/rockchip/cdn-dp-core.c +++ b/drivers/gpu/drm/rockchip/cdn-dp-core.c @@ -1062,7 +1062,7 @@ static int cdn_dp_bind(struct device *dev, struct device *master, void *data) drm_connector_helper_add(connector, &cdn_dp_connector_helper_funcs); - ret = drm_mode_connector_attach_encoder(connector, encoder); + ret = drm_connector_attach_encoder(connector, encoder); if (ret) { DRM_ERROR("failed to attach connector and encoder\n"); goto err_free_connector; diff --git a/drivers/gpu/drm/rockchip/dw-mipi-dsi.c b/drivers/gpu/drm/rockchip/dw-mipi-dsi.c index 01642aaf6127..662b6cb5d3f0 100644 --- a/drivers/gpu/drm/rockchip/dw-mipi-dsi.c +++ b/drivers/gpu/drm/rockchip/dw-mipi-dsi.c @@ -1129,7 +1129,7 @@ static int dw_mipi_dsi_register(struct drm_device *drm, &dw_mipi_dsi_atomic_connector_funcs, DRM_MODE_CONNECTOR_DSI); - drm_mode_connector_attach_encoder(connector, encoder); + drm_connector_attach_encoder(connector, encoder); return 0; } diff --git a/drivers/gpu/drm/rockchip/inno_hdmi.c b/drivers/gpu/drm/rockchip/inno_hdmi.c index 510fcb33e31d..1c02b3e61299 100644 --- a/drivers/gpu/drm/rockchip/inno_hdmi.c +++ b/drivers/gpu/drm/rockchip/inno_hdmi.c @@ -634,7 +634,7 @@ static int inno_hdmi_register(struct drm_device *drm, struct inno_hdmi *hdmi) drm_connector_init(drm, &hdmi->connector, &inno_hdmi_connector_funcs, DRM_MODE_CONNECTOR_HDMIA); - drm_mode_connector_attach_encoder(&hdmi->connector, encoder); + drm_connector_attach_encoder(&hdmi->connector, encoder); return 0; } diff --git a/drivers/gpu/drm/rockchip/rockchip_lvds.c b/drivers/gpu/drm/rockchip/rockchip_lvds.c index b3f6f524b402..456bd9f13bae 100644 --- a/drivers/gpu/drm/rockchip/rockchip_lvds.c +++ b/drivers/gpu/drm/rockchip/rockchip_lvds.c @@ -434,7 +434,7 @@ static int rockchip_lvds_bind(struct device *dev, struct device *master, drm_connector_helper_add(connector, &rockchip_lvds_connector_helper_funcs); - ret = drm_mode_connector_attach_encoder(connector, encoder); + ret = drm_connector_attach_encoder(connector, encoder); if (ret < 0) { DRM_DEV_ERROR(drm_dev->dev, "failed to attach encoder: %d\n", ret); diff --git a/drivers/gpu/drm/shmobile/shmob_drm_crtc.c b/drivers/gpu/drm/shmobile/shmob_drm_crtc.c index 40df8887fc17..fc66167b0641 100644 --- a/drivers/gpu/drm/shmobile/shmob_drm_crtc.c +++ b/drivers/gpu/drm/shmobile/shmob_drm_crtc.c @@ -675,7 +675,7 @@ int shmob_drm_connector_create(struct shmob_drm_device *sdev, if (ret < 0) goto err_cleanup; - ret = drm_mode_connector_attach_encoder(connector, encoder); + ret = drm_connector_attach_encoder(connector, encoder); if (ret < 0) goto err_backlight; diff --git a/drivers/gpu/drm/sti/sti_dvo.c b/drivers/gpu/drm/sti/sti_dvo.c index 030da55a8d30..b08376b7611b 100644 --- a/drivers/gpu/drm/sti/sti_dvo.c +++ b/drivers/gpu/drm/sti/sti_dvo.c @@ -486,7 +486,7 @@ static int sti_dvo_bind(struct device *dev, struct device *master, void *data) drm_connector_helper_add(drm_connector, &sti_dvo_connector_helper_funcs); - err = drm_mode_connector_attach_encoder(drm_connector, encoder); + err = drm_connector_attach_encoder(drm_connector, encoder); if (err) { DRM_ERROR("Failed to attach a connector to a encoder\n"); goto err_sysfs; diff --git a/drivers/gpu/drm/sti/sti_hda.c b/drivers/gpu/drm/sti/sti_hda.c index 67bbdb49fffc..49438337f70d 100644 --- a/drivers/gpu/drm/sti/sti_hda.c +++ b/drivers/gpu/drm/sti/sti_hda.c @@ -709,7 +709,7 @@ static int sti_hda_bind(struct device *dev, struct device *master, void *data) drm_connector_helper_add(drm_connector, &sti_hda_connector_helper_funcs); - err = drm_mode_connector_attach_encoder(drm_connector, encoder); + err = drm_connector_attach_encoder(drm_connector, encoder); if (err) { DRM_ERROR("Failed to attach a connector to a encoder\n"); goto err_sysfs; diff --git a/drivers/gpu/drm/sti/sti_hdmi.c b/drivers/gpu/drm/sti/sti_hdmi.c index 0c3008356ab8..34cdc4644435 100644 --- a/drivers/gpu/drm/sti/sti_hdmi.c +++ b/drivers/gpu/drm/sti/sti_hdmi.c @@ -1290,7 +1290,7 @@ static int sti_hdmi_bind(struct device *dev, struct device *master, void *data) hdmi->drm_connector = drm_connector; - err = drm_mode_connector_attach_encoder(drm_connector, encoder); + err = drm_connector_attach_encoder(drm_connector, encoder); if (err) { DRM_ERROR("Failed to attach a connector to a encoder\n"); goto err_sysfs; diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c index 9b4b1d015423..061d2e0d9011 100644 --- a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c +++ b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c @@ -623,7 +623,7 @@ static int sun4i_hdmi_bind(struct device *dev, struct device *master, ret = cec_register_adapter(hdmi->cec_adap, dev); if (ret < 0) goto err_cleanup_connector; - drm_mode_connector_attach_encoder(&hdmi->connector, &hdmi->encoder); + drm_connector_attach_encoder(&hdmi->connector, &hdmi->encoder); return 0; diff --git a/drivers/gpu/drm/sun4i/sun4i_lvds.c b/drivers/gpu/drm/sun4i/sun4i_lvds.c index a69fe2e1f9d1..af7dcb6da351 100644 --- a/drivers/gpu/drm/sun4i/sun4i_lvds.c +++ b/drivers/gpu/drm/sun4i/sun4i_lvds.c @@ -149,7 +149,7 @@ int sun4i_lvds_init(struct drm_device *drm, struct sun4i_tcon *tcon) goto err_cleanup_connector; } - drm_mode_connector_attach_encoder(&lvds->connector, + drm_connector_attach_encoder(&lvds->connector, &lvds->encoder); ret = drm_panel_attach(tcon->panel, &lvds->connector); diff --git a/drivers/gpu/drm/sun4i/sun4i_rgb.c b/drivers/gpu/drm/sun4i/sun4i_rgb.c index 96d21b07f8fc..bf068da6b12e 100644 --- a/drivers/gpu/drm/sun4i/sun4i_rgb.c +++ b/drivers/gpu/drm/sun4i/sun4i_rgb.c @@ -215,7 +215,7 @@ int sun4i_rgb_init(struct drm_device *drm, struct sun4i_tcon *tcon) goto err_cleanup_connector; } - drm_mode_connector_attach_encoder(&rgb->connector, + drm_connector_attach_encoder(&rgb->connector, &rgb->encoder); ret = drm_panel_attach(tcon->panel, &rgb->connector); diff --git a/drivers/gpu/drm/sun4i/sun4i_tv.c b/drivers/gpu/drm/sun4i/sun4i_tv.c index b070d522ed8d..1a838d208211 100644 --- a/drivers/gpu/drm/sun4i/sun4i_tv.c +++ b/drivers/gpu/drm/sun4i/sun4i_tv.c @@ -623,7 +623,7 @@ static int sun4i_tv_bind(struct device *dev, struct device *master, } tv->connector.interlace_allowed = true; - drm_mode_connector_attach_encoder(&tv->connector, &tv->encoder); + drm_connector_attach_encoder(&tv->connector, &tv->encoder); return 0; diff --git a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c index 2b40d1f6aee8..e3b34a345546 100644 --- a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c +++ b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c @@ -941,7 +941,7 @@ static int sun6i_dsi_bind(struct device *dev, struct device *master, goto err_cleanup_connector; } - drm_mode_connector_attach_encoder(&dsi->connector, &dsi->encoder); + drm_connector_attach_encoder(&dsi->connector, &dsi->encoder); drm_panel_attach(dsi->panel, &dsi->connector); return 0; diff --git a/drivers/gpu/drm/tegra/dsi.c b/drivers/gpu/drm/tegra/dsi.c index ad88ec230329..ee6ca8fa1c65 100644 --- a/drivers/gpu/drm/tegra/dsi.c +++ b/drivers/gpu/drm/tegra/dsi.c @@ -1052,7 +1052,7 @@ static int tegra_dsi_init(struct host1x_client *client) drm_encoder_helper_add(&dsi->output.encoder, &tegra_dsi_encoder_helper_funcs); - drm_mode_connector_attach_encoder(&dsi->output.connector, + drm_connector_attach_encoder(&dsi->output.connector, &dsi->output.encoder); drm_connector_register(&dsi->output.connector); diff --git a/drivers/gpu/drm/tegra/hdmi.c b/drivers/gpu/drm/tegra/hdmi.c index 784739a9f497..0082468f703c 100644 --- a/drivers/gpu/drm/tegra/hdmi.c +++ b/drivers/gpu/drm/tegra/hdmi.c @@ -1488,7 +1488,7 @@ static int tegra_hdmi_init(struct host1x_client *client) drm_encoder_helper_add(&hdmi->output.encoder, &tegra_hdmi_encoder_helper_funcs); - drm_mode_connector_attach_encoder(&hdmi->output.connector, + drm_connector_attach_encoder(&hdmi->output.connector, &hdmi->output.encoder); drm_connector_register(&hdmi->output.connector); diff --git a/drivers/gpu/drm/tegra/rgb.c b/drivers/gpu/drm/tegra/rgb.c index 78ec5193741d..28a78d3120bc 100644 --- a/drivers/gpu/drm/tegra/rgb.c +++ b/drivers/gpu/drm/tegra/rgb.c @@ -289,7 +289,7 @@ int tegra_dc_rgb_init(struct drm_device *drm, struct tegra_dc *dc) drm_encoder_helper_add(&output->encoder, &tegra_rgb_encoder_helper_funcs); - drm_mode_connector_attach_encoder(&output->connector, + drm_connector_attach_encoder(&output->connector, &output->encoder); drm_connector_register(&output->connector); diff --git a/drivers/gpu/drm/tegra/sor.c b/drivers/gpu/drm/tegra/sor.c index 7d2a955fc515..d7fe9f15def1 100644 --- a/drivers/gpu/drm/tegra/sor.c +++ b/drivers/gpu/drm/tegra/sor.c @@ -2622,7 +2622,7 @@ static int tegra_sor_init(struct host1x_client *client) encoder, NULL); drm_encoder_helper_add(&sor->output.encoder, helpers); - drm_mode_connector_attach_encoder(&sor->output.connector, + drm_connector_attach_encoder(&sor->output.connector, &sor->output.encoder); drm_connector_register(&sor->output.connector); diff --git a/drivers/gpu/drm/tilcdc/tilcdc_panel.c b/drivers/gpu/drm/tilcdc/tilcdc_panel.c index d616d64a6725..a1acab39d87f 100644 --- a/drivers/gpu/drm/tilcdc/tilcdc_panel.c +++ b/drivers/gpu/drm/tilcdc/tilcdc_panel.c @@ -223,7 +223,7 @@ static struct drm_connector *panel_connector_create(struct drm_device *dev, connector->interlace_allowed = 0; connector->doublescan_allowed = 0; - ret = drm_mode_connector_attach_encoder(connector, encoder); + ret = drm_connector_attach_encoder(connector, encoder); if (ret) goto fail; diff --git a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c index 46dacca3cce8..daebf1aa6b0a 100644 --- a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c +++ b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c @@ -240,7 +240,7 @@ static struct drm_connector *tfp410_connector_create(struct drm_device *dev, connector->interlace_allowed = 0; connector->doublescan_allowed = 0; - ret = drm_mode_connector_attach_encoder(connector, encoder); + ret = drm_connector_attach_encoder(connector, encoder); if (ret) goto fail; diff --git a/drivers/gpu/drm/udl/udl_connector.c b/drivers/gpu/drm/udl/udl_connector.c index 8fac12e1a1a4..68e88bed77ca 100644 --- a/drivers/gpu/drm/udl/udl_connector.c +++ b/drivers/gpu/drm/udl/udl_connector.c @@ -200,7 +200,7 @@ int udl_connector_init(struct drm_device *dev, struct drm_encoder *encoder) drm_connector_helper_add(connector, &udl_connector_helper_funcs); drm_connector_register(connector); - drm_mode_connector_attach_encoder(connector, encoder); + drm_connector_attach_encoder(connector, encoder); connector->polled = DRM_CONNECTOR_POLL_HPD | DRM_CONNECTOR_POLL_CONNECT | DRM_CONNECTOR_POLL_DISCONNECT; diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index 91f284e1b908..fd5522fd179e 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -329,7 +329,7 @@ static struct drm_connector *vc4_hdmi_connector_init(struct drm_device *dev, connector->interlace_allowed = 1; connector->doublescan_allowed = 0; - drm_mode_connector_attach_encoder(connector, encoder); + drm_connector_attach_encoder(connector, encoder); return connector; } diff --git a/drivers/gpu/drm/vc4/vc4_vec.c b/drivers/gpu/drm/vc4/vc4_vec.c index 3a9a302247a2..8e7facb6514e 100644 --- a/drivers/gpu/drm/vc4/vc4_vec.c +++ b/drivers/gpu/drm/vc4/vc4_vec.c @@ -404,7 +404,7 @@ static struct drm_connector *vc4_vec_connector_init(struct drm_device *dev, VC4_VEC_TV_MODE_NTSC); vec->tv_mode = &vc4_vec_tv_modes[VC4_VEC_TV_MODE_NTSC]; - drm_mode_connector_attach_encoder(connector, vec->encoder); + drm_connector_attach_encoder(connector, vec->encoder); return connector; } diff --git a/drivers/gpu/drm/virtio/virtgpu_display.c b/drivers/gpu/drm/virtio/virtgpu_display.c index ff9933e79416..25503b933599 100644 --- a/drivers/gpu/drm/virtio/virtgpu_display.c +++ b/drivers/gpu/drm/virtio/virtgpu_display.c @@ -292,7 +292,7 @@ static int vgdev_output_init(struct virtio_gpu_device *vgdev, int index) drm_encoder_helper_add(encoder, &virtio_gpu_enc_helper_funcs); encoder->possible_crtcs = 1 << index; - drm_mode_connector_attach_encoder(connector, encoder); + drm_connector_attach_encoder(connector, encoder); drm_connector_register(connector); return 0; } diff --git a/drivers/gpu/drm/vkms/vkms_output.c b/drivers/gpu/drm/vkms/vkms_output.c index a7c0ec9b643f..901012cb1af1 100644 --- a/drivers/gpu/drm/vkms/vkms_output.c +++ b/drivers/gpu/drm/vkms/vkms_output.c @@ -83,7 +83,7 @@ int vkms_output_init(struct vkms_device *vkmsdev) } encoder->possible_crtcs = 1; - ret = drm_mode_connector_attach_encoder(connector, encoder); + ret = drm_connector_attach_encoder(connector, encoder); if (ret) { DRM_ERROR("Failed to attach connector to encoder\n"); goto err_attach; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c index dc0cfda26b1b..a234fe0e1061 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c @@ -438,7 +438,7 @@ static int vmw_ldu_init(struct vmw_private *dev_priv, unsigned unit) goto err_free_connector; } - (void) drm_mode_connector_attach_encoder(connector, encoder); + (void) drm_connector_attach_encoder(connector, encoder); encoder->possible_crtcs = (1 << unit); encoder->possible_clones = 0; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c index 73cf3c6e1591..dd417eb74524 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c @@ -695,7 +695,7 @@ static int vmw_sou_init(struct vmw_private *dev_priv, unsigned unit) goto err_free_connector; } - (void) drm_mode_connector_attach_encoder(connector, encoder); + (void) drm_connector_attach_encoder(connector, encoder); encoder->possible_crtcs = (1 << unit); encoder->possible_clones = 0; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c index a474d87b1af3..4cca78cab03f 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c @@ -1486,7 +1486,7 @@ static int vmw_stdu_init(struct vmw_private *dev_priv, unsigned unit) goto err_free_connector; } - (void) drm_mode_connector_attach_encoder(connector, encoder); + (void) drm_connector_attach_encoder(connector, encoder); encoder->possible_crtcs = (1 << unit); encoder->possible_clones = 0; diff --git a/drivers/gpu/drm/zte/zx_hdmi.c b/drivers/gpu/drm/zte/zx_hdmi.c index d073c6737500..78655269d843 100644 --- a/drivers/gpu/drm/zte/zx_hdmi.c +++ b/drivers/gpu/drm/zte/zx_hdmi.c @@ -326,7 +326,7 @@ static int zx_hdmi_register(struct drm_device *drm, struct zx_hdmi *hdmi) drm_connector_helper_add(&hdmi->connector, &zx_hdmi_connector_helper_funcs); - drm_mode_connector_attach_encoder(&hdmi->connector, encoder); + drm_connector_attach_encoder(&hdmi->connector, encoder); return 0; } diff --git a/drivers/gpu/drm/zte/zx_tvenc.c b/drivers/gpu/drm/zte/zx_tvenc.c index 0de1a71ca4e0..b73afb212fb2 100644 --- a/drivers/gpu/drm/zte/zx_tvenc.c +++ b/drivers/gpu/drm/zte/zx_tvenc.c @@ -297,7 +297,7 @@ static int zx_tvenc_register(struct drm_device *drm, struct zx_tvenc *tvenc) DRM_MODE_CONNECTOR_Composite); drm_connector_helper_add(connector, &zx_tvenc_connector_helper_funcs); - drm_mode_connector_attach_encoder(connector, encoder); + drm_connector_attach_encoder(connector, encoder); return 0; } diff --git a/drivers/gpu/drm/zte/zx_vga.c b/drivers/gpu/drm/zte/zx_vga.c index 3e78ee21b8d0..23d1ff4355a0 100644 --- a/drivers/gpu/drm/zte/zx_vga.c +++ b/drivers/gpu/drm/zte/zx_vga.c @@ -175,7 +175,7 @@ static int zx_vga_register(struct drm_device *drm, struct zx_vga *vga) drm_connector_helper_add(connector, &zx_vga_connector_helper_funcs); - ret = drm_mode_connector_attach_encoder(connector, encoder); + ret = drm_connector_attach_encoder(connector, encoder); if (ret) { DRM_DEV_ERROR(dev, "failed to attach encoder: %d\n", ret); goto clean_connector; diff --git a/drivers/staging/vboxvideo/vbox_mode.c b/drivers/staging/vboxvideo/vbox_mode.c index a943d2f683ed..da4a93df8d75 100644 --- a/drivers/staging/vboxvideo/vbox_mode.c +++ b/drivers/staging/vboxvideo/vbox_mode.c @@ -655,7 +655,7 @@ static int vbox_connector_init(struct drm_device *dev, dev->mode_config.suggested_y_property, 0); drm_connector_register(connector); - drm_mode_connector_attach_encoder(connector, encoder); + drm_connector_attach_encoder(connector, encoder); return 0; } diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h index 4411c0542871..f9a78a53bd9f 100644 --- a/include/drm/drm_connector.h +++ b/include/drm/drm_connector.h @@ -1085,7 +1085,7 @@ int drm_connector_init(struct drm_device *dev, int connector_type); int drm_connector_register(struct drm_connector *connector); void drm_connector_unregister(struct drm_connector *connector); -int drm_mode_connector_attach_encoder(struct drm_connector *connector, +int drm_connector_attach_encoder(struct drm_connector *connector, struct drm_encoder *encoder); void drm_connector_cleanup(struct drm_connector *connector); -- cgit v1.2.3 From 97e14fbeb53fe060c5f6a7a07e37fd24c087ed0c Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Mon, 9 Jul 2018 10:40:08 +0200 Subject: drm: drop _mode_ from remaining connector functions Since there's very few callers of these I've decided to do them all in one patch. With this the unecessarily long drm_mode_connector_ prefix is gone from the codebase! The only exception being struct drm_mode_connector_set_property, which is part of the uapi so can't be renamed. Again done with sed+some manual fixups for indent issues. Reviewed-by: Sean Paul Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20180709084016.23750-8-daniel.vetter@ffwll.ch --- .../amd/display/amdgpu_dm/amdgpu_dm_mst_types.c | 6 ++-- drivers/gpu/drm/drm_atomic_helper.c | 2 +- drivers/gpu/drm/drm_connector.c | 36 +++++++++++----------- drivers/gpu/drm/drm_crtc_internal.h | 6 ++-- drivers/gpu/drm/drm_dp_mst_topology.c | 4 +-- drivers/gpu/drm/drm_ioctl.c | 2 +- drivers/gpu/drm/drm_mode_object.c | 3 +- drivers/gpu/drm/drm_modes.c | 6 ++-- drivers/gpu/drm/drm_probe_helper.c | 4 +-- drivers/gpu/drm/i915/intel_dp.c | 4 +-- drivers/gpu/drm/i915/intel_dp_mst.c | 2 +- drivers/gpu/drm/msm/dsi/dsi_manager.c | 2 +- drivers/gpu/drm/nouveau/dispnv50/disp.c | 2 +- drivers/gpu/drm/radeon/radeon_dp_mst.c | 2 +- drivers/gpu/drm/vmwgfx/vmwgfx_kms.c | 2 +- include/drm/drm_connector.h | 14 ++++----- include/drm/drm_modes.h | 2 +- 17 files changed, 49 insertions(+), 50 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 581bb75d08eb..65f210d3497b 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -345,7 +345,7 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr, aconnector, connector->base.id, aconnector->mst_port); aconnector->port = port; - drm_mode_connector_set_path_property(connector, pathprop); + drm_connector_set_path_property(connector, pathprop); drm_connector_list_iter_end(&conn_iter); aconnector->mst_connected = true; @@ -393,7 +393,7 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr, dev->mode_config.tile_property, 0); - drm_mode_connector_set_path_property(connector, pathprop); + drm_connector_set_path_property(connector, pathprop); /* * Initialize connector state before adding the connectror to drm and @@ -441,7 +441,7 @@ static void dm_dp_mst_hotplug(struct drm_dp_mst_topology_mgr *mgr) static void dm_dp_mst_link_status_reset(struct drm_connector *connector) { mutex_lock(&connector->dev->mode_config.mutex); - drm_mode_connector_set_link_status_property(connector, DRM_MODE_LINK_STATUS_BAD); + drm_connector_set_link_status_property(connector, DRM_MODE_LINK_STATUS_BAD); mutex_unlock(&connector->dev->mode_config.mutex); } diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index 91fda6b8926e..866a2cc72ef6 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -2867,7 +2867,7 @@ static int update_output_state(struct drm_atomic_state *state, * resets the "link-status" property to GOOD, to force any link * re-training. The SETCRTC ioctl does not define whether an update does * need a full modeset or just a plane update, hence we're allowed to do - * that. See also drm_mode_connector_set_link_status_property(). + * that. See also drm_connector_set_link_status_property(). * * Returns: * Returns 0 on success, negative errno numbers on failure. diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c index 8997792e2e23..8f3f672a47b0 100644 --- a/drivers/gpu/drm/drm_connector.c +++ b/drivers/gpu/drm/drm_connector.c @@ -852,7 +852,7 @@ DRM_ENUM_NAME_FN(drm_get_content_protection_name, drm_cp_enum_list) * PATH: * Connector path property to identify how this sink is physically * connected. Used by DP MST. This should be set by calling - * drm_mode_connector_set_path_property(), in the case of DP MST with the + * drm_connector_set_path_property(), in the case of DP MST with the * path property the MST manager created. Userspace cannot change this * property. * TILE: @@ -863,14 +863,14 @@ DRM_ENUM_NAME_FN(drm_get_content_protection_name, drm_cp_enum_list) * are not gen-locked. Note that for tiled panels which are genlocked, like * dual-link LVDS or dual-link DSI, the driver should try to not expose the * tiling and virtualize both &drm_crtc and &drm_plane if needed. Drivers - * should update this value using drm_mode_connector_set_tile_property(). + * should update this value using drm_connector_set_tile_property(). * Userspace cannot change this property. * link-status: * Connector link-status property to indicate the status of link. The * default value of link-status is "GOOD". If something fails during or * after modeset, the kernel driver may set this to "BAD" and issue a * hotplug uevent. Drivers should update this value using - * drm_mode_connector_set_link_status_property(). + * drm_connector_set_link_status_property(). * non_desktop: * Indicates the output should be ignored for purposes of displaying a * standard desktop environment or console. This is most likely because @@ -1425,7 +1425,7 @@ int drm_mode_create_suggested_offset_properties(struct drm_device *dev) EXPORT_SYMBOL(drm_mode_create_suggested_offset_properties); /** - * drm_mode_connector_set_path_property - set tile property on connector + * drm_connector_set_path_property - set tile property on connector * @connector: connector to set property on. * @path: path to use for property; must not be NULL. * @@ -1437,8 +1437,8 @@ EXPORT_SYMBOL(drm_mode_create_suggested_offset_properties); * Returns: * Zero on success, negative errno on failure. */ -int drm_mode_connector_set_path_property(struct drm_connector *connector, - const char *path) +int drm_connector_set_path_property(struct drm_connector *connector, + const char *path) { struct drm_device *dev = connector->dev; int ret; @@ -1451,10 +1451,10 @@ int drm_mode_connector_set_path_property(struct drm_connector *connector, dev->mode_config.path_property); return ret; } -EXPORT_SYMBOL(drm_mode_connector_set_path_property); +EXPORT_SYMBOL(drm_connector_set_path_property); /** - * drm_mode_connector_set_tile_property - set tile property on connector + * drm_connector_set_tile_property - set tile property on connector * @connector: connector to set property on. * * This looks up the tile information for a connector, and creates a @@ -1464,7 +1464,7 @@ EXPORT_SYMBOL(drm_mode_connector_set_path_property); * Returns: * Zero on success, errno on failure. */ -int drm_mode_connector_set_tile_property(struct drm_connector *connector) +int drm_connector_set_tile_property(struct drm_connector *connector) { struct drm_device *dev = connector->dev; char tile[256]; @@ -1494,7 +1494,7 @@ int drm_mode_connector_set_tile_property(struct drm_connector *connector) dev->mode_config.tile_property); return ret; } -EXPORT_SYMBOL(drm_mode_connector_set_tile_property); +EXPORT_SYMBOL(drm_connector_set_tile_property); /** * drm_connector_update_edid_property - update the edid property of a connector @@ -1508,7 +1508,7 @@ EXPORT_SYMBOL(drm_mode_connector_set_tile_property); * Zero on success, negative errno on failure. */ int drm_connector_update_edid_property(struct drm_connector *connector, - const struct edid *edid) + const struct edid *edid) { struct drm_device *dev = connector->dev; size_t size = 0; @@ -1549,7 +1549,7 @@ int drm_connector_update_edid_property(struct drm_connector *connector, EXPORT_SYMBOL(drm_connector_update_edid_property); /** - * drm_mode_connector_set_link_status_property - Set link status property of a connector + * drm_connector_set_link_status_property - Set link status property of a connector * @connector: drm connector * @link_status: new value of link status property (0: Good, 1: Bad) * @@ -1567,8 +1567,8 @@ EXPORT_SYMBOL(drm_connector_update_edid_property); * it is not limited to DP or link training. For example, if we implement * asynchronous setcrtc, this property can be used to report any failures in that. */ -void drm_mode_connector_set_link_status_property(struct drm_connector *connector, - uint64_t link_status) +void drm_connector_set_link_status_property(struct drm_connector *connector, + uint64_t link_status) { struct drm_device *dev = connector->dev; @@ -1576,7 +1576,7 @@ void drm_mode_connector_set_link_status_property(struct drm_connector *connector connector->state->link_status = link_status; drm_modeset_unlock(&dev->mode_config.connection_mutex); } -EXPORT_SYMBOL(drm_mode_connector_set_link_status_property); +EXPORT_SYMBOL(drm_connector_set_link_status_property); /** * drm_connector_init_panel_orientation_property - @@ -1629,7 +1629,7 @@ int drm_connector_init_panel_orientation_property( } EXPORT_SYMBOL(drm_connector_init_panel_orientation_property); -int drm_mode_connector_set_obj_prop(struct drm_mode_object *obj, +int drm_connector_set_obj_prop(struct drm_mode_object *obj, struct drm_property *property, uint64_t value) { @@ -1647,8 +1647,8 @@ int drm_mode_connector_set_obj_prop(struct drm_mode_object *obj, return ret; } -int drm_mode_connector_property_set_ioctl(struct drm_device *dev, - void *data, struct drm_file *file_priv) +int drm_connector_property_set_ioctl(struct drm_device *dev, + void *data, struct drm_file *file_priv) { struct drm_mode_connector_set_property *conn_set_prop = data; struct drm_mode_obj_set_property obj_set_prop = { diff --git a/drivers/gpu/drm/drm_crtc_internal.h b/drivers/gpu/drm/drm_crtc_internal.h index 235d40fce8b5..b61322763394 100644 --- a/drivers/gpu/drm/drm_crtc_internal.h +++ b/drivers/gpu/drm/drm_crtc_internal.h @@ -148,7 +148,7 @@ void drm_connector_ida_init(void); void drm_connector_ida_destroy(void); void drm_connector_unregister_all(struct drm_device *dev); int drm_connector_register_all(struct drm_device *dev); -int drm_mode_connector_set_obj_prop(struct drm_mode_object *obj, +int drm_connector_set_obj_prop(struct drm_mode_object *obj, struct drm_property *property, uint64_t value); int drm_connector_create_standard_properties(struct drm_device *dev); @@ -156,8 +156,8 @@ const char *drm_get_connector_force_name(enum drm_connector_force force); void drm_connector_free_work_fn(struct work_struct *work); /* IOCTL */ -int drm_mode_connector_property_set_ioctl(struct drm_device *dev, - void *data, struct drm_file *file_priv); +int drm_connector_property_set_ioctl(struct drm_device *dev, + void *data, struct drm_file *file_priv); int drm_mode_getconnector(struct drm_device *dev, void *data, struct drm_file *file_priv); diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index 658830620ca3..7780567aa669 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -1215,7 +1215,7 @@ static void drm_dp_add_port(struct drm_dp_mst_branch *mstb, port->pdt == DP_PEER_DEVICE_SST_SINK) && port->port_num >= DP_MST_LOGICAL_PORT_0) { port->cached_edid = drm_get_edid(port->connector, &port->aux.ddc); - drm_mode_connector_set_tile_property(port->connector); + drm_connector_set_tile_property(port->connector); } (*mstb->mgr->cbs->register_connector)(port->connector); } @@ -2559,7 +2559,7 @@ struct edid *drm_dp_mst_get_edid(struct drm_connector *connector, struct drm_dp_ edid = drm_edid_duplicate(port->cached_edid); else { edid = drm_get_edid(connector, &port->aux.ddc); - drm_mode_connector_set_tile_property(connector); + drm_connector_set_tile_property(connector); } port->has_audio = drm_detect_monitor_audio(edid); drm_dp_put_port(port); diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c index 3c125041a597..ea10e9a26aad 100644 --- a/drivers/gpu/drm/drm_ioctl.c +++ b/drivers/gpu/drm/drm_ioctl.c @@ -641,7 +641,7 @@ static const struct drm_ioctl_desc drm_ioctls[] = { DRM_IOCTL_DEF(DRM_IOCTL_MODE_ATTACHMODE, drm_noop, DRM_MASTER|DRM_UNLOCKED), DRM_IOCTL_DEF(DRM_IOCTL_MODE_DETACHMODE, drm_noop, DRM_MASTER|DRM_UNLOCKED), DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPROPERTY, drm_mode_getproperty_ioctl, DRM_UNLOCKED), - DRM_IOCTL_DEF(DRM_IOCTL_MODE_SETPROPERTY, drm_mode_connector_property_set_ioctl, DRM_MASTER|DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_IOCTL_MODE_SETPROPERTY, drm_connector_property_set_ioctl, DRM_MASTER|DRM_UNLOCKED), DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPROPBLOB, drm_mode_getblob_ioctl, DRM_UNLOCKED), DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETFB, drm_mode_getfb, DRM_UNLOCKED), DRM_IOCTL_DEF(DRM_IOCTL_MODE_ADDFB, drm_mode_addfb_ioctl, DRM_UNLOCKED), diff --git a/drivers/gpu/drm/drm_mode_object.c b/drivers/gpu/drm/drm_mode_object.c index ce4d2fb32810..fcb0ab0abb75 100644 --- a/drivers/gpu/drm/drm_mode_object.c +++ b/drivers/gpu/drm/drm_mode_object.c @@ -433,8 +433,7 @@ static int set_property_legacy(struct drm_mode_object *obj, drm_modeset_lock_all(dev); switch (obj->type) { case DRM_MODE_OBJECT_CONNECTOR: - ret = drm_mode_connector_set_obj_prop(obj, prop, - prop_value); + ret = drm_connector_set_obj_prop(obj, prop, prop_value); break; case DRM_MODE_OBJECT_CRTC: ret = drm_mode_crtc_set_obj_prop(obj, prop, prop_value); diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c index f8f7eae738ab..02db9ac82d7a 100644 --- a/drivers/gpu/drm/drm_modes.c +++ b/drivers/gpu/drm/drm_modes.c @@ -1353,7 +1353,7 @@ void drm_mode_sort(struct list_head *mode_list) EXPORT_SYMBOL(drm_mode_sort); /** - * drm_mode_connector_list_update - update the mode list for the connector + * drm_connector_list_update - update the mode list for the connector * @connector: the connector to update * * This moves the modes from the @connector probed_modes list @@ -1363,7 +1363,7 @@ EXPORT_SYMBOL(drm_mode_sort); * This is just a helper functions doesn't validate any modes itself and also * doesn't prune any invalid modes. Callers need to do that themselves. */ -void drm_mode_connector_list_update(struct drm_connector *connector) +void drm_connector_list_update(struct drm_connector *connector) { struct drm_display_mode *pmode, *pt; @@ -1412,7 +1412,7 @@ void drm_mode_connector_list_update(struct drm_connector *connector) } } } -EXPORT_SYMBOL(drm_mode_connector_list_update); +EXPORT_SYMBOL(drm_connector_list_update); /** * drm_mode_parse_command_line_for_connector - parse command line modeline for connector diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c index 3d58e0eb26a4..a1bb157bfdfa 100644 --- a/drivers/gpu/drm/drm_probe_helper.c +++ b/drivers/gpu/drm/drm_probe_helper.c @@ -360,7 +360,7 @@ EXPORT_SYMBOL(drm_helper_probe_detect); * using the VESA GTF/CVT formulas. * * 3. Modes are moved from the probed_modes list to the modes list. Potential - * duplicates are merged together (see drm_mode_connector_list_update()). + * duplicates are merged together (see drm_connector_list_update()). * After this step the probed_modes list will be empty again. * * 4. Any non-stale mode on the modes list then undergoes validation @@ -485,7 +485,7 @@ retry: if (count == 0) goto prune; - drm_mode_connector_list_update(connector); + drm_connector_list_update(connector); if (connector->interlace_allowed) mode_flags |= DRM_MODE_FLAG_INTERLACE; diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index c8268f377602..8caf20fb6587 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -6320,8 +6320,8 @@ static void intel_dp_modeset_retry_work_fn(struct work_struct *work) /* Set connector link status to BAD and send a Uevent to notify * userspace to do a modeset. */ - drm_mode_connector_set_link_status_property(connector, - DRM_MODE_LINK_STATUS_BAD); + drm_connector_set_link_status_property(connector, + DRM_MODE_LINK_STATUS_BAD); mutex_unlock(&connector->dev->mode_config.mutex); /* Send Hotplug uevent so userspace can reprobe */ drm_kms_helper_hotplug_event(connector->dev); diff --git a/drivers/gpu/drm/i915/intel_dp_mst.c b/drivers/gpu/drm/i915/intel_dp_mst.c index 364330fc5d6a..0095c197f155 100644 --- a/drivers/gpu/drm/i915/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/intel_dp_mst.c @@ -474,7 +474,7 @@ static struct drm_connector *intel_dp_add_mst_connector(struct drm_dp_mst_topolo drm_object_attach_property(&connector->base, dev->mode_config.path_property, 0); drm_object_attach_property(&connector->base, dev->mode_config.tile_property, 0); - ret = drm_mode_connector_set_path_property(connector, pathprop); + ret = drm_connector_set_path_property(connector, pathprop); if (ret) goto err; diff --git a/drivers/gpu/drm/msm/dsi/dsi_manager.c b/drivers/gpu/drm/msm/dsi/dsi_manager.c index 21e0dc51531d..d5006d6923e0 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_manager.c +++ b/drivers/gpu/drm/msm/dsi/dsi_manager.c @@ -393,7 +393,7 @@ static int dsi_mgr_connector_get_modes(struct drm_connector *connector) ret = dsi_dual_connector_tile_init(connector, id); if (ret) return ret; - ret = drm_mode_connector_set_tile_property(connector); + ret = drm_connector_set_tile_property(connector); if (ret) { pr_err("%s: set tile property failed, %d\n", __func__, ret); diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index 475456c19b76..5a247eb71899 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -931,7 +931,7 @@ nv50_mstc_new(struct nv50_mstm *mstm, struct drm_dp_mst_port *port, drm_object_attach_property(&mstc->connector.base, dev->mode_config.path_property, 0); drm_object_attach_property(&mstc->connector.base, dev->mode_config.tile_property, 0); - drm_mode_connector_set_path_property(&mstc->connector, path); + drm_connector_set_path_property(&mstc->connector, path); return 0; } diff --git a/drivers/gpu/drm/radeon/radeon_dp_mst.c b/drivers/gpu/drm/radeon/radeon_dp_mst.c index 37956cfc0b6d..f920be236cc9 100644 --- a/drivers/gpu/drm/radeon/radeon_dp_mst.c +++ b/drivers/gpu/drm/radeon/radeon_dp_mst.c @@ -290,7 +290,7 @@ static struct drm_connector *radeon_dp_add_mst_connector(struct drm_dp_mst_topol drm_object_attach_property(&connector->base, dev->mode_config.path_property, 0); drm_object_attach_property(&connector->base, dev->mode_config.tile_property, 0); - drm_mode_connector_set_path_property(connector, pathprop); + drm_connector_set_path_property(connector, pathprop); return connector; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index bc5fbd39cf9a..4a0f0f41afa1 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -2114,7 +2114,7 @@ int vmw_du_connector_fill_modes(struct drm_connector *connector, drm_mode_probed_add(connector, mode); } - drm_mode_connector_list_update(connector); + drm_connector_list_update(connector); /* Move the prefered mode first, help apps pick the right mode. */ drm_mode_sort(&connector->modes); diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h index f9a78a53bd9f..97ea41dc678f 100644 --- a/include/drm/drm_connector.h +++ b/include/drm/drm_connector.h @@ -919,7 +919,7 @@ struct drm_connector { * @path_blob_ptr: * * DRM blob property data for the DP MST path property. This should only - * be updated by calling drm_mode_connector_set_path_property(). + * be updated by calling drm_connector_set_path_property(). */ struct drm_property_blob *path_blob_ptr; @@ -1046,7 +1046,7 @@ struct drm_connector { * the tiling and virtualize both &drm_crtc and &drm_plane if needed. * * This should only be updated by calling - * drm_mode_connector_set_tile_property(). + * drm_connector_set_tile_property(). */ struct drm_property_blob *tile_blob_ptr; @@ -1191,13 +1191,13 @@ void drm_hdmi_avi_infoframe_content_type(struct hdmi_avi_infoframe *frame, int drm_mode_create_suggested_offset_properties(struct drm_device *dev); -int drm_mode_connector_set_path_property(struct drm_connector *connector, - const char *path); -int drm_mode_connector_set_tile_property(struct drm_connector *connector); +int drm_connector_set_path_property(struct drm_connector *connector, + const char *path); +int drm_connector_set_tile_property(struct drm_connector *connector); int drm_connector_update_edid_property(struct drm_connector *connector, const struct edid *edid); -void drm_mode_connector_set_link_status_property(struct drm_connector *connector, - uint64_t link_status); +void drm_connector_set_link_status_property(struct drm_connector *connector, + uint64_t link_status); int drm_connector_init_panel_orientation_property( struct drm_connector *connector, int width, int height); diff --git a/include/drm/drm_modes.h b/include/drm/drm_modes.h index b159fe07fcf9..baded6514456 100644 --- a/include/drm/drm_modes.h +++ b/include/drm/drm_modes.h @@ -530,7 +530,7 @@ drm_mode_validate_ycbcr420(const struct drm_display_mode *mode, void drm_mode_prune_invalid(struct drm_device *dev, struct list_head *mode_list, bool verbose); void drm_mode_sort(struct list_head *mode_list); -void drm_mode_connector_list_update(struct drm_connector *connector); +void drm_connector_list_update(struct drm_connector *connector); /* parsing cmdline modes */ bool -- cgit v1.2.3 From 2e784a91424892cc8c75853dd40b63c0d5855af9 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Mon, 9 Jul 2018 10:40:09 +0200 Subject: drm: Switch drm_plane_state to inline kerneldoc style For consistency and to encourage more detailed documentation. While doing this also beefed up a few of the comments, linking at least to the setup function. Plus fixed all the hyperlinks. Reviewed-by: Sean Paul Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20180709084016.23750-9-daniel.vetter@ffwll.ch --- include/drm/drm_plane.h | 86 ++++++++++++++++++++++++++++++++----------------- 1 file changed, 56 insertions(+), 30 deletions(-) (limited to 'include') diff --git a/include/drm/drm_plane.h b/include/drm/drm_plane.h index cee9dfaaa740..1a647f8f5661 100644 --- a/include/drm/drm_plane.h +++ b/include/drm/drm_plane.h @@ -34,31 +34,15 @@ struct drm_modeset_acquire_ctx; /** * struct drm_plane_state - mutable plane state - * @plane: backpointer to the plane - * @crtc_w: width of visible portion of plane on crtc - * @crtc_h: height of visible portion of plane on crtc - * @src_x: left position of visible portion of plane within - * plane (in 16.16) - * @src_y: upper position of visible portion of plane within - * plane (in 16.16) - * @src_w: width of visible portion of plane (in 16.16) - * @src_h: height of visible portion of plane (in 16.16) - * @alpha: opacity of the plane - * @rotation: rotation of the plane - * @zpos: priority of the given plane on crtc (optional) - * Note that multiple active planes on the same crtc can have an identical - * zpos value. The rule to solving the conflict is to compare the plane - * object IDs; the plane with a higher ID must be stacked on top of a - * plane with a lower ID. - * @normalized_zpos: normalized value of zpos: unique, range from 0 to N-1 - * where N is the number of active planes for given crtc. Note that - * the driver must set drm_mode_config.normalize_zpos or call - * drm_atomic_normalize_zpos() to update this before it can be trusted. - * @src: clipped source coordinates of the plane (in 16.16) - * @dst: clipped destination coordinates of the plane - * @state: backpointer to global drm_atomic_state + * + * Please not that the destination coordinates @crtc_x, @crtc_y, @crtc_h and + * @crtc_w and the source coordinates @src_x, @src_y, @src_h and @src_w are the + * raw coordinates provided by userspace. Drivers should use + * drm_atomic_helper_check_plane_state() and only use the derived rectangles in + * @src and @dst to program the hardware. */ struct drm_plane_state { + /** @plane: backpointer to the plane */ struct drm_plane *plane; /** @@ -87,7 +71,7 @@ struct drm_plane_state { * preserved. * * Drivers should store any implicit fence in this from their - * &drm_plane_helper.prepare_fb callback. See drm_gem_fb_prepare_fb() + * &drm_plane_helper_funcs.prepare_fb callback. See drm_gem_fb_prepare_fb() * and drm_gem_fb_simple_display_pipe_prepare_fb() for suitable helpers. */ struct dma_fence *fence; @@ -108,20 +92,60 @@ struct drm_plane_state { */ int32_t crtc_y; + /** @crtc_w: width of visible portion of plane on crtc */ + /** @crtc_h: height of visible portion of plane on crtc */ uint32_t crtc_w, crtc_h; - /* Source values are 16.16 fixed point */ - uint32_t src_x, src_y; + /** + * @src_x: left position of visible portion of plane within plane (in + * 16.16 fixed point). + */ + uint32_t src_x; + /** + * @src_y: upper position of visible portion of plane within plane (in + * 16.16 fixed point). + */ + uint32_t src_y; + /** @src_w: width of visible portion of plane (in 16.16) */ + /** @src_h: height of visible portion of plane (in 16.16) */ uint32_t src_h, src_w; - /* Plane opacity */ + /** + * @alpha: + * Opacity of the plane with 0 as completely transparent and 0xffff as + * completely opaque. See drm_plane_create_alpha_property() for more + * details. + */ u16 alpha; - /* Plane rotation */ + /** + * @rotation: + * Rotation of the plane. See drm_plane_create_rotation_property() for + * more details. + */ unsigned int rotation; - /* Plane zpos */ + /** + * @zpos: + * Priority of the given plane on crtc (optional). + * + * Note that multiple active planes on the same crtc can have an + * identical zpos value. The rule to solving the conflict is to compare + * the plane object IDs; the plane with a higher ID must be stacked on + * top of a plane with a lower ID. + * + * See drm_plane_create_zpos_property() and + * drm_plane_create_zpos_immutable_property() for more details. + */ unsigned int zpos; + + /** + * @normalized_zpos: + * Normalized value of zpos: unique, range from 0 to N-1 where N is the + * number of active planes for given crtc. Note that the driver must set + * &drm_mode_config.normalize_zpos or call drm_atomic_normalize_zpos() to + * update this before it can be trusted. + */ unsigned int normalized_zpos; /** @@ -138,7 +162,8 @@ struct drm_plane_state { */ enum drm_color_range color_range; - /* Clipped coordinates */ + /** @src: clipped source coordinates of the plane (in 16.16) */ + /** @dst: clipped destination coordinates of the plane */ struct drm_rect src, dst; /** @@ -157,6 +182,7 @@ struct drm_plane_state { */ struct drm_crtc_commit *commit; + /** @state: backpointer to global drm_atomic_state */ struct drm_atomic_state *state; }; -- cgit v1.2.3 From 268bc24e861efd6892d2911bf25a3d1192aa51f5 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Mon, 9 Jul 2018 10:40:10 +0200 Subject: drm: switch drm_plane to inline comments And use that opportunity to polish the kernel doc all around: - Beef up some of the documentation. - Intro text for drm_plane and better links - Fix all the hyperlinks! v2: Fix linebreaks. Reviewed-by: Sean Paul Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20180709084016.23750-10-daniel.vetter@ffwll.ch --- Documentation/gpu/drm-kms.rst | 11 +++--- include/drm/drm_crtc.h | 4 +- include/drm/drm_plane.h | 88 +++++++++++++++++++++++++++++++------------ 3 files changed, 72 insertions(+), 31 deletions(-) (limited to 'include') diff --git a/Documentation/gpu/drm-kms.rst b/Documentation/gpu/drm-kms.rst index 58eed08fbe31..5dee6b8a4c12 100644 --- a/Documentation/gpu/drm-kms.rst +++ b/Documentation/gpu/drm-kms.rst @@ -56,11 +56,12 @@ Overview The basic object structure KMS presents to userspace is fairly simple. Framebuffers (represented by :c:type:`struct drm_framebuffer `, -see `Frame Buffer Abstraction`_) feed into planes. One or more (or even no) -planes feed their pixel data into a CRTC (represented by :c:type:`struct -drm_crtc `, see `CRTC Abstraction`_) for blending. The precise -blending step is explained in more detail in `Plane Composition Properties`_ and -related chapters. +see `Frame Buffer Abstraction`_) feed into planes. Planes are represented by +:c:type:`struct drm_plane `, see `Plane Abstraction`_ for more +details. One or more (or even no) planes feed their pixel data into a CRTC +(represented by :c:type:`struct drm_crtc `, see `CRTC Abstraction`_) +for blending. The precise blending step is explained in more detail in `Plane +Composition Properties`_ and related chapters. For the output routing the first step is encoders (represented by :c:type:`struct drm_encoder `, see `Encoder Abstraction`_). Those diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h index 17f4f93340b8..71b276a05e36 100644 --- a/include/drm/drm_crtc.h +++ b/include/drm/drm_crtc.h @@ -965,8 +965,8 @@ static inline unsigned int drm_crtc_index(const struct drm_crtc *crtc) * drm_crtc_mask - find the mask of a registered CRTC * @crtc: CRTC to find mask for * - * Given a registered CRTC, return the mask bit of that CRTC for an - * encoder's possible_crtcs field. + * Given a registered CRTC, return the mask bit of that CRTC for the + * &drm_encoder.possible_crtcs and &drm_plane.possible_crtcs fields. */ static inline uint32_t drm_crtc_mask(const struct drm_crtc *crtc) { diff --git a/include/drm/drm_plane.h b/include/drm/drm_plane.h index 1a647f8f5661..8a152dc16ea5 100644 --- a/include/drm/drm_plane.h +++ b/include/drm/drm_plane.h @@ -525,30 +525,27 @@ enum drm_plane_type { /** * struct drm_plane - central DRM plane control structure - * @dev: DRM device this plane belongs to - * @head: for list management - * @name: human readable name, can be overwritten by the driver - * @base: base mode object - * @possible_crtcs: pipes this plane can be bound to - * @format_types: array of formats supported by this plane - * @format_count: number of formats supported - * @format_default: driver hasn't supplied supported formats for the plane - * @modifiers: array of modifiers supported by this plane - * @modifier_count: number of modifiers supported - * @old_fb: Temporary tracking of the old fb while a modeset is ongoing. Used by - * drm_mode_set_config_internal() to implement correct refcounting. - * @funcs: helper functions - * @properties: property tracking for this plane - * @type: type of plane (overlay, primary, cursor) - * @alpha_property: alpha property for this plane - * @zpos_property: zpos property for this plane - * @rotation_property: rotation property for this plane - * @helper_private: mid-layer private data + * + * Planes represent the scanout hardware of a display block. They receive their + * input data from a &drm_framebuffer and feed it to a &drm_crtc. Planes control + * the color conversion, see `Plane Composition Properties`_ for more details, + * and are also involved in the color conversion of input pixels, see `Color + * Management Properties`_ for details on that. */ struct drm_plane { + /** @dev: DRM device this plane belongs to */ struct drm_device *dev; + + /** + * @head: + * + * List of all planes on @dev, linked from &drm_mode_config.plane_list. + * Invariant over the lifetime of @dev and therefore does not need + * locking. + */ struct list_head head; + /** @name: human readable name, can be overwritten by the driver */ char *name; /** @@ -562,35 +559,62 @@ struct drm_plane { */ struct drm_modeset_lock mutex; + /** @base: base mode object */ struct drm_mode_object base; + /** + * @possible_crtcs: pipes this plane can be bound to constructed from + * drm_crtc_mask() + */ uint32_t possible_crtcs; + /** @format_types: array of formats supported by this plane */ uint32_t *format_types; + /** @format_count: Size of the array pointed at by @format_types. */ unsigned int format_count; + /** + * @format_default: driver hasn't supplied supported formats for the + * plane. Used by the drm_plane_init compatibility wrapper only. + */ bool format_default; + /** @modifiers: array of modifiers supported by this plane */ uint64_t *modifiers; + /** @modifier_count: Size of the array pointed at by @modifier_count. */ unsigned int modifier_count; /** - * @crtc: Currently bound CRTC, only really meaningful for non-atomic - * drivers. Atomic drivers should instead check &drm_plane_state.crtc. + * @crtc: + * + * Currently bound CRTC, only meaningful for non-atomic drivers. For + * atomic drivers this is forced to be NULL, atomic drivers should + * instead check &drm_plane_state.crtc. */ struct drm_crtc *crtc; /** - * @fb: Currently bound framebuffer, only really meaningful for - * non-atomic drivers. Atomic drivers should instead check - * &drm_plane_state.fb. + * @fb: + * + * Currently bound framebuffer, only meaningful for non-atomic drivers. + * For atomic drivers this is forced to be NULL, atomic drivers should + * instead check &drm_plane_state.fb. */ struct drm_framebuffer *fb; + /** + * @old_fb: + * + * Temporary tracking of the old fb while a modeset is ongoing. Only + * used by non-atomic drivers, forced to be NULL for atomic drivers. + */ struct drm_framebuffer *old_fb; + /** @funcs: plane control functions */ const struct drm_plane_funcs *funcs; + /** @properties: property tracking for this plane */ struct drm_object_properties properties; + /** @type: Type of plane, see &enum drm_plane_type for details. */ enum drm_plane_type type; /** @@ -599,6 +623,7 @@ struct drm_plane { */ unsigned index; + /** @helper_private: mid-layer private data */ const struct drm_plane_helper_funcs *helper_private; /** @@ -616,8 +641,23 @@ struct drm_plane { */ struct drm_plane_state *state; + /** + * @alpha_property: + * Optional alpha property for this plane. See + * drm_plane_create_alpha_property(). + */ struct drm_property *alpha_property; + /** + * @zpos_property: + * Optional zpos property for this plane. See + * drm_plane_create_zpos_property(). + */ struct drm_property *zpos_property; + /** + * @rotation_property: + * Optional rotation property for this plane. See + * drm_plane_create_rotation_property(). + */ struct drm_property *rotation_property; /** -- cgit v1.2.3 From 15185aa20cbdf4404198b74f86a1ce9f6fe0fad7 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Mon, 9 Jul 2018 10:40:12 +0200 Subject: drm/doc: move struct drm_crtc to in-line comments And clean them up a bit, as usual. v2: Fix nits (Sean). Reviewed-by: Sean Paul Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20180709084016.23750-12-daniel.vetter@ffwll.ch --- include/drm/drm_crtc.h | 126 +++++++++++++++++++++++++++++++++++++------------ 1 file changed, 97 insertions(+), 29 deletions(-) (limited to 'include') diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h index 71b276a05e36..7fe06ad6e5f0 100644 --- a/include/drm/drm_crtc.h +++ b/include/drm/drm_crtc.h @@ -747,35 +747,25 @@ struct drm_crtc_funcs { /** * struct drm_crtc - central CRTC control structure - * @dev: parent DRM device - * @port: OF node used by drm_of_find_possible_crtcs() - * @head: list management - * @name: human readable name, can be overwritten by the driver - * @mutex: per-CRTC locking - * @base: base KMS object for ID tracking etc. - * @primary: primary plane for this CRTC - * @cursor: cursor plane for this CRTC - * @cursor_x: current x position of the cursor, used for universal cursor planes - * @cursor_y: current y position of the cursor, used for universal cursor planes - * @enabled: is this CRTC enabled? - * @mode: current mode timings - * @hwmode: mode timings as programmed to hw regs - * @x: x position on screen - * @y: y position on screen - * @funcs: CRTC control functions - * @gamma_size: size of gamma ramp - * @gamma_store: gamma ramp values - * @helper_private: mid-layer private data - * @properties: property tracking for this CRTC * * Each CRTC may have one or more connectors associated with it. This structure * allows the CRTC to be controlled. */ struct drm_crtc { + /** @dev: parent DRM device */ struct drm_device *dev; + /** @port: OF node used by drm_of_find_possible_crtcs(). */ struct device_node *port; + /** + * @head: + * + * List of all CRTCs on @dev, linked from &drm_mode_config.crtc_list. + * Invariant over the lifetime of @dev and therefore does not need + * locking. + */ struct list_head head; + /** @name: human readable name, can be overwritten by the driver */ char *name; /** @@ -790,10 +780,25 @@ struct drm_crtc { */ struct drm_modeset_lock mutex; + /** @base: base KMS object for ID tracking etc. */ struct drm_mode_object base; - /* primary and cursor planes for CRTC */ + /** + * @primary: + * Primary plane for this CRTC. Note that this is only + * relevant for legacy IOCTL, it specifies the plane implicitly used by + * the SETCRTC and PAGE_FLIP IOCTLs. It does not have any significance + * beyond that. + */ struct drm_plane *primary; + + /** + * @cursor: + * Cursor plane for this CRTC. Note that this is only relevant for + * legacy IOCTL, it specifies the plane implicitly used by the SETCURSOR + * and SETCURSOR2 IOCTLs. It does not have any significance + * beyond that. + */ struct drm_plane *cursor; /** @@ -802,30 +807,94 @@ struct drm_crtc { */ unsigned index; - /* position of cursor plane on crtc */ + /** + * @cursor_x: Current x position of the cursor, used for universal + * cursor planes because the SETCURSOR IOCTL only can update the + * framebuffer without supplying the coordinates. Drivers should not use + * this directly, atomic drivers should look at &drm_plane_state.crtc_x + * of the cursor plane instead. + */ int cursor_x; + /** + * @cursor_y: Current y position of the cursor, used for universal + * cursor planes because the SETCURSOR IOCTL only can update the + * framebuffer without supplying the coordinates. Drivers should not use + * this directly, atomic drivers should look at &drm_plane_state.crtc_y + * of the cursor plane instead. + */ int cursor_y; + /** + * @enabled: + * + * Is this CRTC enabled? Should only be used by legacy drivers, atomic + * drivers should instead consult &drm_crtc_state.enable and + * &drm_crtc_state.active. Atomic drivers can update this by calling + * drm_atomic_helper_update_legacy_modeset_state(). + */ bool enabled; - /* Requested mode from modesetting. */ + /** + * @mode: + * + * Current mode timings. Should only be used by legacy drivers, atomic + * drivers should instead consult &drm_crtc_state.mode. Atomic drivers + * can update this by calling + * drm_atomic_helper_update_legacy_modeset_state(). + */ struct drm_display_mode mode; - /* Programmed mode in hw, after adjustments for encoders, - * crtc, panel scaling etc. Needed for timestamping etc. + /** + * @hwmode: + * + * Programmed mode in hw, after adjustments for encoders, crtc, panel + * scaling etc. Should only be used by legacy drivers, for high + * precision vblank timestamps in + * drm_calc_vbltimestamp_from_scanoutpos(). + * + * Note that atomic drivers should not use this, but instead use + * &drm_crtc_state.adjusted_mode. And for high-precision timestamps + * drm_calc_vbltimestamp_from_scanoutpos() used &drm_vblank_crtc.hwmode, + * which is filled out by calling drm_calc_timestamping_constants(). */ struct drm_display_mode hwmode; - int x, y; + /** + * @x: + * x position on screen. Should only be used by legacy drivers, atomic + * drivers should look at &drm_plane_state.crtc_x of the primary plane + * instead. Updated by calling + * drm_atomic_helper_update_legacy_modeset_state(). + */ + int x; + /** + * @y: + * y position on screen. Should only be used by legacy drivers, atomic + * drivers should look at &drm_plane_state.crtc_y of the primary plane + * instead. Updated by calling + * drm_atomic_helper_update_legacy_modeset_state(). + */ + int y; + + /** @funcs: CRTC control functions */ const struct drm_crtc_funcs *funcs; - /* Legacy FB CRTC gamma size for reporting to userspace */ + /** + * @gamma_size: Size of legacy gamma ramp reported to userspace. Set up + * by calling drm_mode_crtc_set_gamma_size(). + */ uint32_t gamma_size; + + /** + * @gamma_store: Gamma ramp values used by the legacy SETGAMMA and + * GETGAMMA IOCTls. Set up by calling drm_mode_crtc_set_gamma_size(). + */ uint16_t *gamma_store; - /* if you are using the helper */ + /** @helper_private: mid-layer private data */ const struct drm_crtc_helper_funcs *helper_private; + /** @properties: property tracking for this CRTC */ struct drm_object_properties properties; /** @@ -895,7 +964,6 @@ struct drm_crtc { * * spinlock to protect the fences in the fence_context. */ - spinlock_t fence_lock; /** * @fence_seqno: -- cgit v1.2.3 From 620eec75f35ce470cb59410b2ed91ad750b867a2 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Mon, 9 Jul 2018 10:40:15 +0200 Subject: drm/doc: use inline kerneldoc style for drm_crtc_state Lots of added text here since I think the various control flow bits are worth explaining a bit better. v2: Fix conflict with Boris' no_vblank addition. Reviewed-by: Sean Paul Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20180709084016.23750-15-daniel.vetter@ffwll.ch --- include/drm/drm_crtc.h | 110 ++++++++++++++++++++++++++++++++++++++----------- 1 file changed, 86 insertions(+), 24 deletions(-) (limited to 'include') diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h index 7fe06ad6e5f0..92e7fc7f05a4 100644 --- a/include/drm/drm_crtc.h +++ b/include/drm/drm_crtc.h @@ -77,21 +77,6 @@ struct drm_plane_helper_funcs; /** * struct drm_crtc_state - mutable CRTC state - * @crtc: backpointer to the CRTC - * @enable: whether the CRTC should be enabled, gates all other state - * @active: whether the CRTC is actively displaying (used for DPMS) - * @planes_changed: planes on this crtc are updated - * @mode_changed: @mode or @enable has been changed - * @active_changed: @active has been toggled. - * @connectors_changed: connectors to this crtc have been updated - * @zpos_changed: zpos values of planes on this crtc have been updated - * @color_mgmt_changed: color management properties have changed (degamma or - * gamma LUT or CSC matrix) - * @plane_mask: bitmask of (1 << drm_plane_index(plane)) of attached planes - * @connector_mask: bitmask of (1 << drm_connector_index(connector)) of attached connectors - * @encoder_mask: bitmask of (1 << drm_encoder_index(encoder)) of attached encoders - * @mode_blob: &drm_property_blob for @mode - * @state: backpointer to global drm_atomic_state * * Note that the distinction between @enable and @active is rather subtile: * Flipping @active while @enable is set without changing anything else may @@ -102,21 +87,86 @@ struct drm_plane_helper_funcs; * * The three booleans active_changed, connectors_changed and mode_changed are * intended to indicate whether a full modeset is needed, rather than strictly - * describing what has changed in a commit. - * See also: drm_atomic_crtc_needs_modeset() + * describing what has changed in a commit. See also: + * drm_atomic_crtc_needs_modeset() + * + * WARNING: Transitional helpers (like drm_helper_crtc_mode_set() or + * drm_helper_crtc_mode_set_base()) do not maintain many of the derived control + * state like @plane_mask so drivers not converted over to atomic helpers should + * not rely on these being accurate! */ struct drm_crtc_state { + /** @crtc: backpointer to the CRTC */ struct drm_crtc *crtc; + /** + * @enable: Whether the CRTC should be enabled, gates all other state. + * This controls reservations of shared resources. Actual hardware state + * is controlled by @active. + */ bool enable; + + /** + * @active: Whether the CRTC is actively displaying (used for DPMS). + * Implies that @enable is set. The driver must not release any shared + * resources if @active is set to false but @enable still true, because + * userspace expects that a DPMS ON always succeeds. + * + * Hence drivers must not consult @active in their various + * &drm_mode_config_funcs.atomic_check callback to reject an atomic + * commit. They can consult it to aid in the computation of derived + * hardware state, since even in the DPMS OFF state the display hardware + * should be as much powered down as when the CRTC is completely + * disabled through setting @enable to false. + */ bool active; - /* computed state bits used by helpers and drivers */ + /** + * @planes_changed: Planes on this crtc are updated. Used by the atomic + * helpers and drivers to steer the atomic commit control flow. + */ bool planes_changed : 1; + + /** + * @mode_changed: @mode or @enable has been changed. Used by the atomic + * helpers and drivers to steer the atomic commit control flow. See also + * drm_atomic_crtc_needs_modeset(). + * + * Drivers are supposed to set this for any CRTC state changes that + * require a full modeset. They can also reset it to false if e.g. a + * @mode change can be done without a full modeset by only changing + * scaler settings. + */ bool mode_changed : 1; + + /** + * @active_changed: @active has been toggled. Used by the atomic + * helpers and drivers to steer the atomic commit control flow. See also + * drm_atomic_crtc_needs_modeset(). + */ bool active_changed : 1; + + /** + * @connectors_changed: Connectors to this crtc have been updated, + * either in their state or routing. Used by the atomic + * helpers and drivers to steer the atomic commit control flow. See also + * drm_atomic_crtc_needs_modeset(). + * + * Drivers are supposed to set this as-needed from their own atomic + * check code, e.g. from &drm_encoder_helper_funcs.atomic_check + */ bool connectors_changed : 1; + /** + * @zpos_changed: zpos values of planes on this crtc have been updated. + * Used by the atomic helpers and drivers to steer the atomic commit + * control flow. + */ bool zpos_changed : 1; + /** + * @color_mgmt_changed: Color management properties have changed + * (@gamma_lut, @degamma_lut or @ctm). Used by the atomic helpers and + * drivers to steer the atomic commit control flow. + */ bool color_mgmt_changed : 1; /** @@ -142,14 +192,22 @@ struct drm_crtc_state { */ bool no_vblank : 1; - /* attached planes bitmask: - * WARNING: transitional helpers do not maintain plane_mask so - * drivers not converted over to atomic helpers should not rely - * on plane_mask being accurate! + /** + * @plane_mask: Bitmask of drm_plane_mask(plane) of planes attached to + * this CRTC. */ u32 plane_mask; + /** + * @connector_mask: Bitmask of drm_connector_mask(connector) of + * connectors attached to this CRTC. + */ u32 connector_mask; + + /** + * @encoder_mask: Bitmask of drm_encoder_mask(encoder) of encoders + * attached to this CRTC. + */ u32 encoder_mask; /** @@ -159,7 +217,7 @@ struct drm_crtc_state { * differences between the mode requested by userspace in @mode and what * is actually programmed into the hardware. * - * For drivers using drm_bridge, this stores hardware display timings + * For drivers using &drm_bridge, this stores hardware display timings * used between the CRTC and the first bridge. For other drivers, the * meaning of the adjusted_mode field is purely driver implementation * defined information, and will usually be used to store the hardware @@ -184,7 +242,10 @@ struct drm_crtc_state { */ struct drm_display_mode mode; - /* blob property to expose current mode to atomic userspace */ + /** + * @mode_blob: &drm_property_blob for @mode, for exposing the mode to + * atomic userspace. + */ struct drm_property_blob *mode_blob; /** @@ -288,6 +349,7 @@ struct drm_crtc_state { */ struct drm_crtc_commit *commit; + /** @state: backpointer to global drm_atomic_state */ struct drm_atomic_state *state; }; -- cgit v1.2.3 From 4f91da26c81145f255cb153152ffed70014b1c41 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 11 Jul 2018 20:36:38 -0700 Subject: xdp: add per mode attributes for attached programs In preparation for support of simultaneous driver and hardware XDP support add per-mode attributes. The catch-all IFLA_XDP_PROG_ID will still be reported, but user space can now also access the program ID in a new IFLA_XDP__PROG_ID attribute. Signed-off-by: Jakub Kicinski Reviewed-by: Quentin Monnet Signed-off-by: Daniel Borkmann --- include/uapi/linux/if_link.h | 3 +++ net/core/rtnetlink.c | 30 ++++++++++++++++++++++++++---- 2 files changed, 29 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index cf01b6824244..bc86c2b105ec 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -928,6 +928,9 @@ enum { IFLA_XDP_ATTACHED, IFLA_XDP_FLAGS, IFLA_XDP_PROG_ID, + IFLA_XDP_DRV_PROG_ID, + IFLA_XDP_SKB_PROG_ID, + IFLA_XDP_HW_PROG_ID, __IFLA_XDP_MAX, }; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 5ef61222fdef..b40242459907 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -964,7 +964,8 @@ static size_t rtnl_xdp_size(void) { size_t xdp_size = nla_total_size(0) + /* nest IFLA_XDP */ nla_total_size(1) + /* XDP_ATTACHED */ - nla_total_size(4); /* XDP_PROG_ID */ + nla_total_size(4) + /* XDP_PROG_ID */ + nla_total_size(4); /* XDP__PROG_ID */ return xdp_size; } @@ -1378,16 +1379,17 @@ static u8 rtnl_xdp_attached_mode(struct net_device *dev, u32 *prog_id) static int rtnl_xdp_fill(struct sk_buff *skb, struct net_device *dev) { + u32 prog_attr, prog_id; struct nlattr *xdp; - u32 prog_id; int err; + u8 mode; xdp = nla_nest_start(skb, IFLA_XDP); if (!xdp) return -EMSGSIZE; - err = nla_put_u8(skb, IFLA_XDP_ATTACHED, - rtnl_xdp_attached_mode(dev, &prog_id)); + mode = rtnl_xdp_attached_mode(dev, &prog_id); + err = nla_put_u8(skb, IFLA_XDP_ATTACHED, mode); if (err) goto err_cancel; @@ -1395,6 +1397,26 @@ static int rtnl_xdp_fill(struct sk_buff *skb, struct net_device *dev) err = nla_put_u32(skb, IFLA_XDP_PROG_ID, prog_id); if (err) goto err_cancel; + + switch (mode) { + case XDP_ATTACHED_DRV: + prog_attr = IFLA_XDP_DRV_PROG_ID; + break; + case XDP_ATTACHED_SKB: + prog_attr = IFLA_XDP_SKB_PROG_ID; + break; + case XDP_ATTACHED_HW: + prog_attr = IFLA_XDP_HW_PROG_ID; + break; + case XDP_ATTACHED_NONE: + default: + err = -EINVAL; + goto err_cancel; + } + + err = nla_put_u32(skb, prog_attr, prog_id); + if (err) + goto err_cancel; } nla_nest_end(skb, xdp); -- cgit v1.2.3 From 6b8675897338f874c41612655a85d8e10cdb23d8 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 11 Jul 2018 20:36:39 -0700 Subject: xdp: don't make drivers report attachment mode prog_attached of struct netdev_bpf should have been superseded by simply setting prog_id long time ago, but we kept it around to allow offloading drivers to communicate attachment mode (drv vs hw). Subsequently drivers were also allowed to report back attachment flags (prog_flags), and since nowadays only programs attached will XDP_FLAGS_HW_MODE can get offloaded, we can tell the attachment mode from the flags driver reports. Remove prog_attached member. Signed-off-by: Jakub Kicinski Reviewed-by: Quentin Monnet Signed-off-by: Daniel Borkmann --- drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c | 1 - drivers/net/ethernet/cavium/thunder/nicvf_main.c | 1 - drivers/net/ethernet/intel/i40e/i40e_main.c | 1 - drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 1 - drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 1 - drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 1 - drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 1 - drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 3 --- drivers/net/ethernet/qlogic/qede/qede_filter.c | 1 - drivers/net/netdevsim/bpf.c | 1 - drivers/net/tun.c | 1 - drivers/net/virtio_net.c | 1 - include/linux/netdevice.h | 5 ----- net/core/dev.c | 7 +++---- net/core/rtnetlink.c | 8 ++++++-- 15 files changed, 9 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c index 1f0e872d0667..0584d07c8c33 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c @@ -219,7 +219,6 @@ int bnxt_xdp(struct net_device *dev, struct netdev_bpf *xdp) rc = bnxt_xdp_set(bp, xdp->prog); break; case XDP_QUERY_PROG: - xdp->prog_attached = !!bp->xdp_prog; xdp->prog_id = bp->xdp_prog ? bp->xdp_prog->aux->id : 0; rc = 0; break; diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index 135766c4296b..768f584f8392 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -1848,7 +1848,6 @@ static int nicvf_xdp(struct net_device *netdev, struct netdev_bpf *xdp) case XDP_SETUP_PROG: return nicvf_xdp_setup(nic, xdp->prog); case XDP_QUERY_PROG: - xdp->prog_attached = !!nic->xdp_prog; xdp->prog_id = nic->xdp_prog ? nic->xdp_prog->aux->id : 0; return 0; default: diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 426b0ccb1fc6..51762428b40e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -11841,7 +11841,6 @@ static int i40e_xdp(struct net_device *dev, case XDP_SETUP_PROG: return i40e_xdp_setup(vsi, xdp->prog); case XDP_QUERY_PROG: - xdp->prog_attached = i40e_enabled_xdp_vsi(vsi); xdp->prog_id = vsi->xdp_prog ? vsi->xdp_prog->aux->id : 0; return 0; default: diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index a8e21becb619..3862fea1c923 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -9966,7 +9966,6 @@ static int ixgbe_xdp(struct net_device *dev, struct netdev_bpf *xdp) case XDP_SETUP_PROG: return ixgbe_xdp_setup(dev, xdp->prog); case XDP_QUERY_PROG: - xdp->prog_attached = !!(adapter->xdp_prog); xdp->prog_id = adapter->xdp_prog ? adapter->xdp_prog->aux->id : 0; return 0; diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 59416eddd840..d86446d202d5 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -4462,7 +4462,6 @@ static int ixgbevf_xdp(struct net_device *dev, struct netdev_bpf *xdp) case XDP_SETUP_PROG: return ixgbevf_xdp_setup(dev, xdp->prog); case XDP_QUERY_PROG: - xdp->prog_attached = !!(adapter->xdp_prog); xdp->prog_id = adapter->xdp_prog ? adapter->xdp_prog->aux->id : 0; return 0; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 65eb06e017e4..6785661d1a72 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2926,7 +2926,6 @@ static int mlx4_xdp(struct net_device *dev, struct netdev_bpf *xdp) return mlx4_xdp_set(dev, xdp->prog); case XDP_QUERY_PROG: xdp->prog_id = mlx4_xdp_query(dev); - xdp->prog_attached = !!xdp->prog_id; return 0; default: return -EINVAL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index bbd2fd0b2e06..e4a9a0768a81 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -4192,7 +4192,6 @@ static int mlx5e_xdp(struct net_device *dev, struct netdev_bpf *xdp) return mlx5e_xdp_set(dev, xdp->prog); case XDP_QUERY_PROG: xdp->prog_id = mlx5e_xdp_query(dev); - xdp->prog_attached = !!xdp->prog_id; return 0; default: return -EINVAL; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 7df5ca37bfb8..d20714598613 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -3459,9 +3459,6 @@ static int nfp_net_xdp(struct net_device *netdev, struct netdev_bpf *xdp) return nfp_net_xdp_setup(nn, xdp->prog, xdp->flags, xdp->extack); case XDP_QUERY_PROG: - xdp->prog_attached = !!nn->xdp_prog; - if (nn->dp.bpf_offload_xdp) - xdp->prog_attached = XDP_ATTACHED_HW; xdp->prog_id = nn->xdp_prog ? nn->xdp_prog->aux->id : 0; xdp->prog_flags = nn->xdp_prog ? nn->xdp_flags : 0; return 0; diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c index b823bfe2ea4d..f9a327c821eb 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_filter.c +++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c @@ -1116,7 +1116,6 @@ int qede_xdp(struct net_device *dev, struct netdev_bpf *xdp) case XDP_SETUP_PROG: return qede_xdp_set(edev, xdp->prog); case XDP_QUERY_PROG: - xdp->prog_attached = !!edev->xdp_prog; xdp->prog_id = edev->xdp_prog ? edev->xdp_prog->aux->id : 0; return 0; default: diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c index 75c25306d234..712e6f918065 100644 --- a/drivers/net/netdevsim/bpf.c +++ b/drivers/net/netdevsim/bpf.c @@ -567,7 +567,6 @@ int nsim_bpf(struct net_device *dev, struct netdev_bpf *bpf) nsim_bpf_destroy_prog(bpf->offload.prog); return 0; case XDP_QUERY_PROG: - bpf->prog_attached = ns->xdp_prog_mode; bpf->prog_id = ns->xdp_prog ? ns->xdp_prog->aux->id : 0; bpf->prog_flags = ns->xdp_prog ? ns->xdp_flags : 0; return 0; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index a192a017cc68..49a50219d0da 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1268,7 +1268,6 @@ static int tun_xdp(struct net_device *dev, struct netdev_bpf *xdp) return tun_xdp_set(dev, xdp->prog, xdp->extack); case XDP_QUERY_PROG: xdp->prog_id = tun_xdp_query(dev); - xdp->prog_attached = !!xdp->prog_id; return 0; default: return -EINVAL; diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 53085c63277b..2ff08bc103a9 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -2343,7 +2343,6 @@ static int virtnet_xdp(struct net_device *dev, struct netdev_bpf *xdp) return virtnet_xdp_set(dev, xdp->prog, xdp->extack); case XDP_QUERY_PROG: xdp->prog_id = virtnet_xdp_query(dev); - xdp->prog_attached = !!xdp->prog_id; return 0; default: return -EINVAL; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b683971e500d..69a664789b33 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -819,10 +819,6 @@ enum bpf_netdev_command { */ XDP_SETUP_PROG, XDP_SETUP_PROG_HW, - /* Check if a bpf program is set on the device. The callee should - * set @prog_attached to one of XDP_ATTACHED_* values, note that "true" - * is equivalent to XDP_ATTACHED_DRV. - */ XDP_QUERY_PROG, /* BPF program for offload callbacks, invoked at program load time. */ BPF_OFFLOAD_VERIFIER_PREP, @@ -849,7 +845,6 @@ struct netdev_bpf { }; /* XDP_QUERY_PROG */ struct { - u8 prog_attached; u32 prog_id; /* flags with which program was installed */ u32 prog_flags; diff --git a/net/core/dev.c b/net/core/dev.c index 89825c1eccdc..9fa3b3705a8e 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4926,7 +4926,6 @@ static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp) break; case XDP_QUERY_PROG: - xdp->prog_attached = !!old; xdp->prog_id = old ? old->aux->id : 0; break; @@ -7593,13 +7592,13 @@ void __dev_xdp_query(struct net_device *dev, bpf_op_t bpf_op, WARN_ON(bpf_op(dev, xdp) < 0); } -static u8 __dev_xdp_attached(struct net_device *dev, bpf_op_t bpf_op) +static bool __dev_xdp_attached(struct net_device *dev, bpf_op_t bpf_op) { struct netdev_bpf xdp; __dev_xdp_query(dev, bpf_op, &xdp); - return xdp.prog_attached; + return xdp.prog_id; } static int dev_xdp_install(struct net_device *dev, bpf_op_t bpf_op, @@ -7634,7 +7633,7 @@ static void dev_xdp_uninstall(struct net_device *dev) return; __dev_xdp_query(dev, ndo_bpf, &xdp); - if (xdp.prog_attached == XDP_ATTACHED_NONE) + if (!xdp.prog_id) return; /* Program removal should always succeed */ diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index b40242459907..02ebc056a688 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1372,9 +1372,13 @@ static u8 rtnl_xdp_attached_mode(struct net_device *dev, u32 *prog_id) return XDP_ATTACHED_NONE; __dev_xdp_query(dev, ops->ndo_bpf, &xdp); - *prog_id = xdp.prog_id; + if (!xdp.prog_id) + return XDP_ATTACHED_NONE; - return xdp.prog_attached; + *prog_id = xdp.prog_id; + if (xdp.prog_flags & XDP_FLAGS_HW_MODE) + return XDP_ATTACHED_HW; + return XDP_ATTACHED_DRV; } static int rtnl_xdp_fill(struct sk_buff *skb, struct net_device *dev) -- cgit v1.2.3 From 05296620f6d14dce0030b87e1e57891a770fb65c Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 11 Jul 2018 20:36:40 -0700 Subject: xdp: factor out common program/flags handling from drivers Basic operations drivers perform during xdp setup and query can be moved to helpers in the core. Encapsulate program and flags into a structure and add helpers. Note that the structure is intended as the "main" program information source in the driver. Most drivers will additionally place the program pointer in their fast path or ring structures. The helpers don't have a huge impact now, but they will decrease the code duplication when programs can be installed in HW and driver at the same time. Encapsulating the basic operations in helpers will hopefully also reduce the number of changes to drivers which adopt them. Helpers could really be static inline, but they depend on definition of struct netdev_bpf which means they'd have to be placed in netdevice.h, an already 4500 line header. Signed-off-by: Jakub Kicinski Reviewed-by: Quentin Monnet Signed-off-by: Daniel Borkmann --- drivers/net/ethernet/netronome/nfp/nfp_net.h | 6 ++-- .../net/ethernet/netronome/nfp/nfp_net_common.c | 28 +++++++----------- drivers/net/netdevsim/bpf.c | 16 +++------- drivers/net/netdevsim/netdevsim.h | 4 +-- include/net/xdp.h | 13 +++++++++ net/core/xdp.c | 34 ++++++++++++++++++++++ tools/testing/selftests/bpf/test_offload.py | 4 +-- 7 files changed, 67 insertions(+), 38 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h index 2a71a9ffd095..2021dda595b7 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h @@ -553,8 +553,7 @@ struct nfp_net_dp { * @rss_cfg: RSS configuration * @rss_key: RSS secret key * @rss_itbl: RSS indirection table - * @xdp_flags: Flags with which XDP prog was loaded - * @xdp_prog: XDP prog (for ctrl path, both DRV and HW modes) + * @xdp: Information about the attached XDP program * @max_r_vecs: Number of allocated interrupt vectors for RX/TX * @max_tx_rings: Maximum number of TX rings supported by the Firmware * @max_rx_rings: Maximum number of RX rings supported by the Firmware @@ -610,8 +609,7 @@ struct nfp_net { u8 rss_key[NFP_NET_CFG_RSS_KEY_SZ]; u8 rss_itbl[NFP_NET_CFG_RSS_ITBL_SZ]; - u32 xdp_flags; - struct bpf_prog *xdp_prog; + struct xdp_attachment_info xdp; unsigned int max_tx_rings; unsigned int max_rx_rings; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index d20714598613..4bb589dbffbc 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -3417,34 +3417,29 @@ nfp_net_xdp_setup_drv(struct nfp_net *nn, struct bpf_prog *prog, return nfp_net_ring_reconfig(nn, dp, extack); } -static int -nfp_net_xdp_setup(struct nfp_net *nn, struct bpf_prog *prog, u32 flags, - struct netlink_ext_ack *extack) +static int nfp_net_xdp_setup(struct nfp_net *nn, struct netdev_bpf *bpf) { struct bpf_prog *drv_prog, *offload_prog; int err; - if (nn->xdp_prog && (flags ^ nn->xdp_flags) & XDP_FLAGS_MODES) + if (!xdp_attachment_flags_ok(&nn->xdp, bpf)) return -EBUSY; /* Load both when no flags set to allow easy activation of driver path * when program is replaced by one which can't be offloaded. */ - drv_prog = flags & XDP_FLAGS_HW_MODE ? NULL : prog; - offload_prog = flags & XDP_FLAGS_DRV_MODE ? NULL : prog; + drv_prog = bpf->flags & XDP_FLAGS_HW_MODE ? NULL : bpf->prog; + offload_prog = bpf->flags & XDP_FLAGS_DRV_MODE ? NULL : bpf->prog; - err = nfp_net_xdp_setup_drv(nn, drv_prog, extack); + err = nfp_net_xdp_setup_drv(nn, drv_prog, bpf->extack); if (err) return err; - err = nfp_app_xdp_offload(nn->app, nn, offload_prog, extack); - if (err && flags & XDP_FLAGS_HW_MODE) + err = nfp_app_xdp_offload(nn->app, nn, offload_prog, bpf->extack); + if (err && bpf->flags & XDP_FLAGS_HW_MODE) return err; - if (nn->xdp_prog) - bpf_prog_put(nn->xdp_prog); - nn->xdp_prog = prog; - nn->xdp_flags = flags; + xdp_attachment_setup(&nn->xdp, bpf); return 0; } @@ -3456,12 +3451,9 @@ static int nfp_net_xdp(struct net_device *netdev, struct netdev_bpf *xdp) switch (xdp->command) { case XDP_SETUP_PROG: case XDP_SETUP_PROG_HW: - return nfp_net_xdp_setup(nn, xdp->prog, xdp->flags, - xdp->extack); + return nfp_net_xdp_setup(nn, xdp); case XDP_QUERY_PROG: - xdp->prog_id = nn->xdp_prog ? nn->xdp_prog->aux->id : 0; - xdp->prog_flags = nn->xdp_prog ? nn->xdp_flags : 0; - return 0; + return xdp_attachment_query(&nn->xdp, xdp); default: return nfp_app_bpf(nn->app, nn, xdp); } diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c index 712e6f918065..c485d97b5df4 100644 --- a/drivers/net/netdevsim/bpf.c +++ b/drivers/net/netdevsim/bpf.c @@ -199,10 +199,8 @@ static int nsim_xdp_set_prog(struct netdevsim *ns, struct netdev_bpf *bpf) { int err; - if (ns->xdp_prog && (bpf->flags ^ ns->xdp_flags) & XDP_FLAGS_MODES) { - NSIM_EA(bpf->extack, "program loaded with different flags"); + if (!xdp_attachment_flags_ok(&ns->xdp, bpf)) return -EBUSY; - } if (bpf->command == XDP_SETUP_PROG && !ns->bpf_xdpdrv_accept) { NSIM_EA(bpf->extack, "driver XDP disabled in DebugFS"); @@ -219,11 +217,7 @@ static int nsim_xdp_set_prog(struct netdevsim *ns, struct netdev_bpf *bpf) return err; } - if (ns->xdp_prog) - bpf_prog_put(ns->xdp_prog); - - ns->xdp_prog = bpf->prog; - ns->xdp_flags = bpf->flags; + xdp_attachment_setup(&ns->xdp, bpf); if (!bpf->prog) ns->xdp_prog_mode = XDP_ATTACHED_NONE; @@ -567,9 +561,7 @@ int nsim_bpf(struct net_device *dev, struct netdev_bpf *bpf) nsim_bpf_destroy_prog(bpf->offload.prog); return 0; case XDP_QUERY_PROG: - bpf->prog_id = ns->xdp_prog ? ns->xdp_prog->aux->id : 0; - bpf->prog_flags = ns->xdp_prog ? ns->xdp_flags : 0; - return 0; + return xdp_attachment_query(&ns->xdp, bpf); case XDP_SETUP_PROG: err = nsim_setup_prog_checks(ns, bpf); if (err) @@ -636,6 +628,6 @@ void nsim_bpf_uninit(struct netdevsim *ns) { WARN_ON(!list_empty(&ns->bpf_bound_progs)); WARN_ON(!list_empty(&ns->bpf_bound_maps)); - WARN_ON(ns->xdp_prog); + WARN_ON(ns->xdp.prog); WARN_ON(ns->bpf_offloaded); } diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h index d8a7cc995e88..69ffb4a2d14b 100644 --- a/drivers/net/netdevsim/netdevsim.h +++ b/drivers/net/netdevsim/netdevsim.h @@ -18,6 +18,7 @@ #include #include #include +#include #define DRV_NAME "netdevsim" @@ -67,9 +68,8 @@ struct netdevsim { struct bpf_prog *bpf_offloaded; u32 bpf_offloaded_id; - u32 xdp_flags; + struct xdp_attachment_info xdp; int xdp_prog_mode; - struct bpf_prog *xdp_prog; u32 prog_id_gen; diff --git a/include/net/xdp.h b/include/net/xdp.h index 2deea7166a34..fcb033f51d8c 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -144,4 +144,17 @@ xdp_data_meta_unsupported(const struct xdp_buff *xdp) return unlikely(xdp->data_meta > xdp->data); } +struct xdp_attachment_info { + struct bpf_prog *prog; + u32 flags; +}; + +struct netdev_bpf; +int xdp_attachment_query(struct xdp_attachment_info *info, + struct netdev_bpf *bpf); +bool xdp_attachment_flags_ok(struct xdp_attachment_info *info, + struct netdev_bpf *bpf); +void xdp_attachment_setup(struct xdp_attachment_info *info, + struct netdev_bpf *bpf); + #endif /* __LINUX_NET_XDP_H__ */ diff --git a/net/core/xdp.c b/net/core/xdp.c index 31c58719b5a9..57285383ed00 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -3,8 +3,11 @@ * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc. * Released under terms in GPL version 2. See COPYING. */ +#include +#include #include #include +#include #include #include #include @@ -370,3 +373,34 @@ void xdp_return_buff(struct xdp_buff *xdp) __xdp_return(xdp->data, &xdp->rxq->mem, true, xdp->handle); } EXPORT_SYMBOL_GPL(xdp_return_buff); + +int xdp_attachment_query(struct xdp_attachment_info *info, + struct netdev_bpf *bpf) +{ + bpf->prog_id = info->prog ? info->prog->aux->id : 0; + bpf->prog_flags = info->prog ? info->flags : 0; + return 0; +} +EXPORT_SYMBOL_GPL(xdp_attachment_query); + +bool xdp_attachment_flags_ok(struct xdp_attachment_info *info, + struct netdev_bpf *bpf) +{ + if (info->prog && (bpf->flags ^ info->flags) & XDP_FLAGS_MODES) { + NL_SET_ERR_MSG(bpf->extack, + "program loaded with different flags"); + return false; + } + return true; +} +EXPORT_SYMBOL_GPL(xdp_attachment_flags_ok); + +void xdp_attachment_setup(struct xdp_attachment_info *info, + struct netdev_bpf *bpf) +{ + if (info->prog) + bpf_prog_put(info->prog); + info->prog = bpf->prog; + info->flags = bpf->flags; +} +EXPORT_SYMBOL_GPL(xdp_attachment_setup); diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py index f8d9bd81d9a4..40401e9e9351 100755 --- a/tools/testing/selftests/bpf/test_offload.py +++ b/tools/testing/selftests/bpf/test_offload.py @@ -821,7 +821,7 @@ try: ret, _, err = sim.set_xdp(obj, "", force=True, fail=False, include_stderr=True) fail(ret == 0, "Replaced XDP program with a program in different mode") - check_extack_nsim(err, "program loaded with different flags.", args) + check_extack(err, "program loaded with different flags.", args) start_test("Test XDP prog remove with bad flags...") ret, _, err = sim.unset_xdp("offload", force=True, @@ -831,7 +831,7 @@ try: ret, _, err = sim.unset_xdp("", force=True, fail=False, include_stderr=True) fail(ret == 0, "Removed program with a bad mode") - check_extack_nsim(err, "program loaded with different flags.", args) + check_extack(err, "program loaded with different flags.", args) start_test("Test MTU restrictions...") ret, _ = sim.set_mtu(9000, fail=False) -- cgit v1.2.3 From a25717d2b604347d9af8da81deea7b08e8c94220 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 11 Jul 2018 20:36:41 -0700 Subject: xdp: support simultaneous driver and hw XDP attachment Split the query of HW-attached program from the software one. Introduce new .ndo_bpf command to query HW-attached program. This will allow drivers to install different programs in HW and SW at the same time. Netlink can now also carry multiple programs on dump (in which case mode will be set to XDP_ATTACHED_MULTI and user has to check per-attachment point attributes, IFLA_XDP_PROG_ID will not be present). We reuse IFLA_XDP_PROG_ID skb space for second mode, so rtnl_xdp_size() doesn't need to be updated. Note that the installation side is still not there, since all drivers currently reject installing more than one program at the time. Signed-off-by: Jakub Kicinski Reviewed-by: Quentin Monnet Signed-off-by: Daniel Borkmann --- .../net/ethernet/netronome/nfp/nfp_net_common.c | 6 ++ drivers/net/netdevsim/bpf.c | 6 ++ include/linux/netdevice.h | 7 +- include/uapi/linux/if_link.h | 1 + net/core/dev.c | 45 ++++++----- net/core/rtnetlink.c | 93 ++++++++++++---------- 6 files changed, 96 insertions(+), 62 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 4bb589dbffbc..bb1e72e8dbc2 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -3453,6 +3453,12 @@ static int nfp_net_xdp(struct net_device *netdev, struct netdev_bpf *xdp) case XDP_SETUP_PROG_HW: return nfp_net_xdp_setup(nn, xdp); case XDP_QUERY_PROG: + if (nn->dp.bpf_offload_xdp) + return 0; + return xdp_attachment_query(&nn->xdp, xdp); + case XDP_QUERY_PROG_HW: + if (!nn->dp.bpf_offload_xdp) + return 0; return xdp_attachment_query(&nn->xdp, xdp); default: return nfp_app_bpf(nn->app, nn, xdp); diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c index c485d97b5df4..5544c9b51173 100644 --- a/drivers/net/netdevsim/bpf.c +++ b/drivers/net/netdevsim/bpf.c @@ -561,6 +561,12 @@ int nsim_bpf(struct net_device *dev, struct netdev_bpf *bpf) nsim_bpf_destroy_prog(bpf->offload.prog); return 0; case XDP_QUERY_PROG: + if (ns->xdp_prog_mode != XDP_ATTACHED_DRV) + return 0; + return xdp_attachment_query(&ns->xdp, bpf); + case XDP_QUERY_PROG_HW: + if (ns->xdp_prog_mode != XDP_ATTACHED_HW) + return 0; return xdp_attachment_query(&ns->xdp, bpf); case XDP_SETUP_PROG: err = nsim_setup_prog_checks(ns, bpf); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 69a664789b33..2422c0e88f5c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -820,6 +820,7 @@ enum bpf_netdev_command { XDP_SETUP_PROG, XDP_SETUP_PROG_HW, XDP_QUERY_PROG, + XDP_QUERY_PROG_HW, /* BPF program for offload callbacks, invoked at program load time. */ BPF_OFFLOAD_VERIFIER_PREP, BPF_OFFLOAD_TRANSLATE, @@ -843,7 +844,7 @@ struct netdev_bpf { struct bpf_prog *prog; struct netlink_ext_ack *extack; }; - /* XDP_QUERY_PROG */ + /* XDP_QUERY_PROG, XDP_QUERY_PROG_HW */ struct { u32 prog_id; /* flags with which program was installed */ @@ -3533,8 +3534,8 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, typedef int (*bpf_op_t)(struct net_device *dev, struct netdev_bpf *bpf); int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, int fd, u32 flags); -void __dev_xdp_query(struct net_device *dev, bpf_op_t xdp_op, - struct netdev_bpf *xdp); +u32 __dev_xdp_query(struct net_device *dev, bpf_op_t xdp_op, + enum bpf_netdev_command cmd); int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb); int dev_forward_skb(struct net_device *dev, struct sk_buff *skb); diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index bc86c2b105ec..8759cfb8aa2e 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -920,6 +920,7 @@ enum { XDP_ATTACHED_DRV, XDP_ATTACHED_SKB, XDP_ATTACHED_HW, + XDP_ATTACHED_MULTI, }; enum { diff --git a/net/core/dev.c b/net/core/dev.c index 9fa3b3705a8e..993cdc3cd086 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -7582,21 +7582,19 @@ int dev_change_proto_down(struct net_device *dev, bool proto_down) } EXPORT_SYMBOL(dev_change_proto_down); -void __dev_xdp_query(struct net_device *dev, bpf_op_t bpf_op, - struct netdev_bpf *xdp) +u32 __dev_xdp_query(struct net_device *dev, bpf_op_t bpf_op, + enum bpf_netdev_command cmd) { - memset(xdp, 0, sizeof(*xdp)); - xdp->command = XDP_QUERY_PROG; + struct netdev_bpf xdp; - /* Query must always succeed. */ - WARN_ON(bpf_op(dev, xdp) < 0); -} + if (!bpf_op) + return 0; -static bool __dev_xdp_attached(struct net_device *dev, bpf_op_t bpf_op) -{ - struct netdev_bpf xdp; + memset(&xdp, 0, sizeof(xdp)); + xdp.command = cmd; - __dev_xdp_query(dev, bpf_op, &xdp); + /* Query must always succeed. */ + WARN_ON(bpf_op(dev, &xdp) < 0 && cmd == XDP_QUERY_PROG); return xdp.prog_id; } @@ -7632,12 +7630,19 @@ static void dev_xdp_uninstall(struct net_device *dev) if (!ndo_bpf) return; - __dev_xdp_query(dev, ndo_bpf, &xdp); - if (!xdp.prog_id) - return; + memset(&xdp, 0, sizeof(xdp)); + xdp.command = XDP_QUERY_PROG; + WARN_ON(ndo_bpf(dev, &xdp)); + if (xdp.prog_id) + WARN_ON(dev_xdp_install(dev, ndo_bpf, NULL, xdp.prog_flags, + NULL)); - /* Program removal should always succeed */ - WARN_ON(dev_xdp_install(dev, ndo_bpf, NULL, xdp.prog_flags, NULL)); + /* Remove HW offload */ + memset(&xdp, 0, sizeof(xdp)); + xdp.command = XDP_QUERY_PROG_HW; + if (!ndo_bpf(dev, &xdp) && xdp.prog_id) + WARN_ON(dev_xdp_install(dev, ndo_bpf, NULL, xdp.prog_flags, + NULL)); } /** @@ -7653,12 +7658,15 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, int fd, u32 flags) { const struct net_device_ops *ops = dev->netdev_ops; + enum bpf_netdev_command query; struct bpf_prog *prog = NULL; bpf_op_t bpf_op, bpf_chk; int err; ASSERT_RTNL(); + query = flags & XDP_FLAGS_HW_MODE ? XDP_QUERY_PROG_HW : XDP_QUERY_PROG; + bpf_op = bpf_chk = ops->ndo_bpf; if (!bpf_op && (flags & (XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE))) return -EOPNOTSUPP; @@ -7668,10 +7676,11 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, bpf_chk = generic_xdp_install; if (fd >= 0) { - if (bpf_chk && __dev_xdp_attached(dev, bpf_chk)) + if (__dev_xdp_query(dev, bpf_chk, XDP_QUERY_PROG) || + __dev_xdp_query(dev, bpf_chk, XDP_QUERY_PROG_HW)) return -EEXIST; if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) && - __dev_xdp_attached(dev, bpf_op)) + __dev_xdp_query(dev, bpf_op, query)) return -EBUSY; prog = bpf_prog_get_type_dev(fd, BPF_PROG_TYPE_XDP, diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 02ebc056a688..c9929ef17539 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -964,7 +964,7 @@ static size_t rtnl_xdp_size(void) { size_t xdp_size = nla_total_size(0) + /* nest IFLA_XDP */ nla_total_size(1) + /* XDP_ATTACHED */ - nla_total_size(4) + /* XDP_PROG_ID */ + nla_total_size(4) + /* XDP_PROG_ID (or 1st mode) */ nla_total_size(4); /* XDP__PROG_ID */ return xdp_size; @@ -1354,37 +1354,57 @@ static int rtnl_fill_link_ifmap(struct sk_buff *skb, struct net_device *dev) return 0; } -static u8 rtnl_xdp_attached_mode(struct net_device *dev, u32 *prog_id) +static u32 rtnl_xdp_prog_skb(struct net_device *dev) { - const struct net_device_ops *ops = dev->netdev_ops; const struct bpf_prog *generic_xdp_prog; - struct netdev_bpf xdp; ASSERT_RTNL(); - *prog_id = 0; generic_xdp_prog = rtnl_dereference(dev->xdp_prog); - if (generic_xdp_prog) { - *prog_id = generic_xdp_prog->aux->id; - return XDP_ATTACHED_SKB; - } - if (!ops->ndo_bpf) - return XDP_ATTACHED_NONE; + if (!generic_xdp_prog) + return 0; + return generic_xdp_prog->aux->id; +} + +static u32 rtnl_xdp_prog_drv(struct net_device *dev) +{ + return __dev_xdp_query(dev, dev->netdev_ops->ndo_bpf, XDP_QUERY_PROG); +} + +static u32 rtnl_xdp_prog_hw(struct net_device *dev) +{ + return __dev_xdp_query(dev, dev->netdev_ops->ndo_bpf, + XDP_QUERY_PROG_HW); +} + +static int rtnl_xdp_report_one(struct sk_buff *skb, struct net_device *dev, + u32 *prog_id, u8 *mode, u8 tgt_mode, u32 attr, + u32 (*get_prog_id)(struct net_device *dev)) +{ + u32 curr_id; + int err; + + curr_id = get_prog_id(dev); + if (!curr_id) + return 0; + + *prog_id = curr_id; + err = nla_put_u32(skb, attr, curr_id); + if (err) + return err; - __dev_xdp_query(dev, ops->ndo_bpf, &xdp); - if (!xdp.prog_id) - return XDP_ATTACHED_NONE; + if (*mode != XDP_ATTACHED_NONE) + *mode = XDP_ATTACHED_MULTI; + else + *mode = tgt_mode; - *prog_id = xdp.prog_id; - if (xdp.prog_flags & XDP_FLAGS_HW_MODE) - return XDP_ATTACHED_HW; - return XDP_ATTACHED_DRV; + return 0; } static int rtnl_xdp_fill(struct sk_buff *skb, struct net_device *dev) { - u32 prog_attr, prog_id; struct nlattr *xdp; + u32 prog_id; int err; u8 mode; @@ -1392,35 +1412,26 @@ static int rtnl_xdp_fill(struct sk_buff *skb, struct net_device *dev) if (!xdp) return -EMSGSIZE; - mode = rtnl_xdp_attached_mode(dev, &prog_id); + prog_id = 0; + mode = XDP_ATTACHED_NONE; + if (rtnl_xdp_report_one(skb, dev, &prog_id, &mode, XDP_ATTACHED_SKB, + IFLA_XDP_SKB_PROG_ID, rtnl_xdp_prog_skb)) + goto err_cancel; + if (rtnl_xdp_report_one(skb, dev, &prog_id, &mode, XDP_ATTACHED_DRV, + IFLA_XDP_DRV_PROG_ID, rtnl_xdp_prog_drv)) + goto err_cancel; + if (rtnl_xdp_report_one(skb, dev, &prog_id, &mode, XDP_ATTACHED_HW, + IFLA_XDP_HW_PROG_ID, rtnl_xdp_prog_hw)) + goto err_cancel; + err = nla_put_u8(skb, IFLA_XDP_ATTACHED, mode); if (err) goto err_cancel; - if (prog_id) { + if (prog_id && mode != XDP_ATTACHED_MULTI) { err = nla_put_u32(skb, IFLA_XDP_PROG_ID, prog_id); if (err) goto err_cancel; - - switch (mode) { - case XDP_ATTACHED_DRV: - prog_attr = IFLA_XDP_DRV_PROG_ID; - break; - case XDP_ATTACHED_SKB: - prog_attr = IFLA_XDP_SKB_PROG_ID; - break; - case XDP_ATTACHED_HW: - prog_attr = IFLA_XDP_HW_PROG_ID; - break; - case XDP_ATTACHED_NONE: - default: - err = -EINVAL; - goto err_cancel; - } - - err = nla_put_u32(skb, prog_attr, prog_id); - if (err) - goto err_cancel; } nla_nest_end(skb, xdp); -- cgit v1.2.3 From 8dc9fbbf274b7b2a647e06141aee70ffabf6dbc0 Mon Sep 17 00:00:00 2001 From: Nayan Deshmukh Date: Fri, 13 Jul 2018 15:21:13 +0530 Subject: drm/scheduler: add a pointer to scheduler in the rq MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch is in preparation for a better load balancing in scheduler. It allows us to associate entities with the run queues instead of binding them to a scheduler. Signed-off-by: Nayan Deshmukh Reviewed-by: Christian König Acked-by: Eric Anholt Signed-off-by: Alex Deucher --- drivers/gpu/drm/scheduler/gpu_scheduler.c | 6 ++++-- include/drm/gpu_scheduler.h | 2 ++ 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/scheduler/gpu_scheduler.c b/drivers/gpu/drm/scheduler/gpu_scheduler.c index 7d2560699b84..429b1328653a 100644 --- a/drivers/gpu/drm/scheduler/gpu_scheduler.c +++ b/drivers/gpu/drm/scheduler/gpu_scheduler.c @@ -69,11 +69,13 @@ static void drm_sched_process_job(struct dma_fence *f, struct dma_fence_cb *cb); * * Initializes a scheduler runqueue. */ -static void drm_sched_rq_init(struct drm_sched_rq *rq) +static void drm_sched_rq_init(struct drm_gpu_scheduler *sched, + struct drm_sched_rq *rq) { spin_lock_init(&rq->lock); INIT_LIST_HEAD(&rq->entities); rq->current_entity = NULL; + rq->sched = sched; } /** @@ -926,7 +928,7 @@ int drm_sched_init(struct drm_gpu_scheduler *sched, sched->timeout = timeout; sched->hang_limit = hang_limit; for (i = DRM_SCHED_PRIORITY_MIN; i < DRM_SCHED_PRIORITY_MAX; i++) - drm_sched_rq_init(&sched->sched_rq[i]); + drm_sched_rq_init(sched, &sched->sched_rq[i]); init_waitqueue_head(&sched->wake_up_worker); init_waitqueue_head(&sched->job_scheduled); diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index 4214ceb71c05..43e93d6077cf 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -93,6 +93,7 @@ struct drm_sched_entity { * struct drm_sched_rq - queue of entities to be scheduled. * * @lock: to modify the entities list. + * @sched: the scheduler to which this rq belongs to. * @entities: list of the entities to be scheduled. * @current_entity: the entity which is to be scheduled. * @@ -102,6 +103,7 @@ struct drm_sched_entity { */ struct drm_sched_rq { spinlock_t lock; + struct drm_gpu_scheduler *sched; struct list_head entities; struct drm_sched_entity *current_entity; }; -- cgit v1.2.3 From aa16b6c6b4d979234f830a48add47d02c12bb569 Mon Sep 17 00:00:00 2001 From: Nayan Deshmukh Date: Fri, 13 Jul 2018 15:21:14 +0530 Subject: drm/scheduler: modify args of drm_sched_entity_init MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit replace run queue by a list of run queues and remove the sched arg as that is part of run queue itself Signed-off-by: Nayan Deshmukh Reviewed-by: Christian König Acked-by: Eric Anholt Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 3 +-- drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c | 3 +-- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 3 +-- drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c | 4 ++-- drivers/gpu/drm/etnaviv/etnaviv_drv.c | 8 ++++---- drivers/gpu/drm/scheduler/gpu_scheduler.c | 20 ++++++++++++-------- drivers/gpu/drm/v3d/v3d_drv.c | 7 +++---- include/drm/gpu_scheduler.h | 6 +++--- 11 files changed, 33 insertions(+), 33 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c index 0120b24fae1b..83e3b320a793 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c @@ -90,8 +90,8 @@ static int amdgpu_ctx_init(struct amdgpu_device *adev, if (ring == &adev->gfx.kiq.ring) continue; - r = drm_sched_entity_init(&ring->sched, &ctx->rings[i].entity, - rq, &ctx->guilty); + r = drm_sched_entity_init(&ctx->rings[i].entity, + &rq, 1, &ctx->guilty); if (r) goto failed; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 6a3fead5c1f0..11a12483c995 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -1918,8 +1918,7 @@ void amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, bool enable) ring = adev->mman.buffer_funcs_ring; rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_KERNEL]; - r = drm_sched_entity_init(&ring->sched, &adev->mman.entity, - rq, NULL); + r = drm_sched_entity_init(&adev->mman.entity, &rq, 1, NULL); if (r) { DRM_ERROR("Failed setting up TTM BO move entity (%d)\n", r); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c index 3e70eb61a960..a6c2cace4b9d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c @@ -266,8 +266,8 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev) ring = &adev->uvd.inst[j].ring; rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL]; - r = drm_sched_entity_init(&ring->sched, &adev->uvd.inst[j].entity, - rq, NULL); + r = drm_sched_entity_init(&adev->uvd.inst[j].entity, &rq, + 1, NULL); if (r != 0) { DRM_ERROR("Failed setting up UVD(%d) run queue.\n", j); return r; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c index 6ae1ad7e83b3..ffb0fcc9707e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c @@ -190,8 +190,7 @@ int amdgpu_vce_sw_init(struct amdgpu_device *adev, unsigned long size) ring = &adev->vce.ring[0]; rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL]; - r = drm_sched_entity_init(&ring->sched, &adev->vce.entity, - rq, NULL); + r = drm_sched_entity_init(&adev->vce.entity, &rq, 1, NULL); if (r != 0) { DRM_ERROR("Failed setting up VCE run queue.\n"); return r; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 0fd0a718763b..484e2c19c027 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -2564,8 +2564,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, ring_instance %= adev->vm_manager.vm_pte_num_rings; ring = adev->vm_manager.vm_pte_rings[ring_instance]; rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_KERNEL]; - r = drm_sched_entity_init(&ring->sched, &vm->entity, - rq, NULL); + r = drm_sched_entity_init(&vm->entity, &rq, 1, NULL); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c index 2623f249cb7a..1c118c02e8cb 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c @@ -430,8 +430,8 @@ static int uvd_v6_0_sw_init(void *handle) struct drm_sched_rq *rq; ring = &adev->uvd.inst->ring_enc[0]; rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL]; - r = drm_sched_entity_init(&ring->sched, &adev->uvd.inst->entity_enc, - rq, NULL); + r = drm_sched_entity_init(&adev->uvd.inst->entity_enc, + &rq, 1, NULL); if (r) { DRM_ERROR("Failed setting up UVD ENC run queue.\n"); return r; diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c index ce360ad16856..d48bc3393545 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c @@ -432,8 +432,8 @@ static int uvd_v7_0_sw_init(void *handle) for (j = 0; j < adev->uvd.num_uvd_inst; j++) { ring = &adev->uvd.inst[j].ring_enc[0]; rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL]; - r = drm_sched_entity_init(&ring->sched, &adev->uvd.inst[j].entity_enc, - rq, NULL); + r = drm_sched_entity_init(&adev->uvd.inst[j].entity_enc, + &rq, 1, NULL); if (r) { DRM_ERROR("(%d)Failed setting up UVD ENC run queue.\n", j); return r; diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.c b/drivers/gpu/drm/etnaviv/etnaviv_drv.c index 45bfdf4cc107..36414ba56b22 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_drv.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.c @@ -49,12 +49,12 @@ static int etnaviv_open(struct drm_device *dev, struct drm_file *file) for (i = 0; i < ETNA_MAX_PIPES; i++) { struct etnaviv_gpu *gpu = priv->gpu[i]; + struct drm_sched_rq *rq; if (gpu) { - drm_sched_entity_init(&gpu->sched, - &ctx->sched_entity[i], - &gpu->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL], - NULL); + rq = &gpu->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL]; + drm_sched_entity_init(&ctx->sched_entity[i], + &rq, 1, NULL); } } diff --git a/drivers/gpu/drm/scheduler/gpu_scheduler.c b/drivers/gpu/drm/scheduler/gpu_scheduler.c index 429b1328653a..16bf446aa6b3 100644 --- a/drivers/gpu/drm/scheduler/gpu_scheduler.c +++ b/drivers/gpu/drm/scheduler/gpu_scheduler.c @@ -162,26 +162,30 @@ drm_sched_rq_select_entity(struct drm_sched_rq *rq) * drm_sched_entity_init - Init a context entity used by scheduler when * submit to HW ring. * - * @sched: scheduler instance * @entity: scheduler entity to init - * @rq: the run queue this entity belongs + * @rq_list: the list of run queue on which jobs from this + * entity can be submitted + * @num_rq_list: number of run queue in rq_list * @guilty: atomic_t set to 1 when a job on this queue * is found to be guilty causing a timeout * + * Note: the rq_list should have atleast one element to schedule + * the entity + * * Returns 0 on success or a negative error code on failure. */ -int drm_sched_entity_init(struct drm_gpu_scheduler *sched, - struct drm_sched_entity *entity, - struct drm_sched_rq *rq, +int drm_sched_entity_init(struct drm_sched_entity *entity, + struct drm_sched_rq **rq_list, + unsigned int num_rq_list, atomic_t *guilty) { - if (!(sched && entity && rq)) + if (!(entity && rq_list && num_rq_list > 0 && rq_list[0])) return -EINVAL; memset(entity, 0, sizeof(struct drm_sched_entity)); INIT_LIST_HEAD(&entity->list); - entity->rq = rq; - entity->sched = sched; + entity->rq = rq_list[0]; + entity->sched = rq_list[0]->sched; entity->guilty = guilty; entity->last_scheduled = NULL; diff --git a/drivers/gpu/drm/v3d/v3d_drv.c b/drivers/gpu/drm/v3d/v3d_drv.c index 567f7d46d912..1dceba2b42fd 100644 --- a/drivers/gpu/drm/v3d/v3d_drv.c +++ b/drivers/gpu/drm/v3d/v3d_drv.c @@ -123,6 +123,7 @@ v3d_open(struct drm_device *dev, struct drm_file *file) { struct v3d_dev *v3d = to_v3d_dev(dev); struct v3d_file_priv *v3d_priv; + struct drm_sched_rq *rq; int i; v3d_priv = kzalloc(sizeof(*v3d_priv), GFP_KERNEL); @@ -132,10 +133,8 @@ v3d_open(struct drm_device *dev, struct drm_file *file) v3d_priv->v3d = v3d; for (i = 0; i < V3D_MAX_QUEUES; i++) { - drm_sched_entity_init(&v3d->queue[i].sched, - &v3d_priv->sched_entity[i], - &v3d->queue[i].sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL], - NULL); + rq = &v3d->queue[i].sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL]; + drm_sched_entity_init(&v3d_priv->sched_entity[i], &rq, 1, NULL); } file->driver_priv = v3d_priv; diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index 43e93d6077cf..2205e89722f6 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -282,9 +282,9 @@ int drm_sched_init(struct drm_gpu_scheduler *sched, const char *name); void drm_sched_fini(struct drm_gpu_scheduler *sched); -int drm_sched_entity_init(struct drm_gpu_scheduler *sched, - struct drm_sched_entity *entity, - struct drm_sched_rq *rq, +int drm_sched_entity_init(struct drm_sched_entity *entity, + struct drm_sched_rq **rq_list, + unsigned int num_rq_list, atomic_t *guilty); long drm_sched_entity_flush(struct drm_gpu_scheduler *sched, struct drm_sched_entity *entity, long timeout); -- cgit v1.2.3 From c921c2077b32081617789a645120148bc8b60c98 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Fri, 13 Jul 2018 12:16:43 +0300 Subject: net: ipmr: add support for passing full packet on wrong vif This patch adds support for IGMPMSG_WRVIFWHOLE which is used to pass full packet and real vif id when the incoming interface is wrong. While the RP and FHR are setting up state we need to be sending the registers encapsulated with all the data inside otherwise we lose it. The RP then decapsulates it and forwards it to the interested parties. Currently with WRONGVIF we can only be sending empty register packets and will lose that data. This behaviour can be enabled by using MRT_PIM with val == IGMPMSG_WRVIFWHOLE. This doesn't prevent IGMPMSG_WRONGVIF from happening, it happens in addition to it, also it is controlled by the same throttling parameters as WRONGVIF (i.e. 1 packet per 3 seconds currently). Both messages are generated to keep backwards compatibily and avoid breaking someone who was enabling MRT_PIM with val == 4, since any positive val is accepted and treated the same. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/linux/mroute_base.h | 1 + include/uapi/linux/mroute.h | 2 ++ net/ipv4/ipmr.c | 21 ++++++++++++++++----- 3 files changed, 19 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/mroute_base.h b/include/linux/mroute_base.h index fd436cdd4725..6675b9f81979 100644 --- a/include/linux/mroute_base.h +++ b/include/linux/mroute_base.h @@ -254,6 +254,7 @@ struct mr_table { atomic_t cache_resolve_queue_len; bool mroute_do_assert; bool mroute_do_pim; + bool mroute_do_wrvifwhole; int mroute_reg_vif_num; }; diff --git a/include/uapi/linux/mroute.h b/include/uapi/linux/mroute.h index 10f9ff9426a2..5d37a9ccce63 100644 --- a/include/uapi/linux/mroute.h +++ b/include/uapi/linux/mroute.h @@ -120,6 +120,7 @@ enum { IPMRA_TABLE_MROUTE_DO_ASSERT, IPMRA_TABLE_MROUTE_DO_PIM, IPMRA_TABLE_VIFS, + IPMRA_TABLE_MROUTE_DO_WRVIFWHOLE, __IPMRA_TABLE_MAX }; #define IPMRA_TABLE_MAX (__IPMRA_TABLE_MAX - 1) @@ -173,5 +174,6 @@ enum { #define IGMPMSG_NOCACHE 1 /* Kern cache fill request to mrouted */ #define IGMPMSG_WRONGVIF 2 /* For PIM assert processing (unused) */ #define IGMPMSG_WHOLEPKT 3 /* For PIM Register processing */ +#define IGMPMSG_WRVIFWHOLE 4 /* For PIM Register and assert processing */ #endif /* _UAPI__LINUX_MROUTE_H */ diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 82f914122f1b..5660adcf7a04 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1052,7 +1052,7 @@ static int ipmr_cache_report(struct mr_table *mrt, struct sk_buff *skb; int ret; - if (assert == IGMPMSG_WHOLEPKT) + if (assert == IGMPMSG_WHOLEPKT || assert == IGMPMSG_WRVIFWHOLE) skb = skb_realloc_headroom(pkt, sizeof(struct iphdr)); else skb = alloc_skb(128, GFP_ATOMIC); @@ -1060,7 +1060,7 @@ static int ipmr_cache_report(struct mr_table *mrt, if (!skb) return -ENOBUFS; - if (assert == IGMPMSG_WHOLEPKT) { + if (assert == IGMPMSG_WHOLEPKT || assert == IGMPMSG_WRVIFWHOLE) { /* Ugly, but we have no choice with this interface. * Duplicate old header, fix ihl, length etc. * And all this only to mangle msg->im_msgtype and @@ -1071,9 +1071,12 @@ static int ipmr_cache_report(struct mr_table *mrt, skb_reset_transport_header(skb); msg = (struct igmpmsg *)skb_network_header(skb); memcpy(msg, skb_network_header(pkt), sizeof(struct iphdr)); - msg->im_msgtype = IGMPMSG_WHOLEPKT; + msg->im_msgtype = assert; msg->im_mbz = 0; - msg->im_vif = mrt->mroute_reg_vif_num; + if (assert == IGMPMSG_WRVIFWHOLE) + msg->im_vif = vifi; + else + msg->im_vif = mrt->mroute_reg_vif_num; ip_hdr(skb)->ihl = sizeof(struct iphdr) >> 2; ip_hdr(skb)->tot_len = htons(ntohs(ip_hdr(pkt)->tot_len) + sizeof(struct iphdr)); @@ -1372,6 +1375,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, struct mr_table *mrt; struct vifctl vif; struct mfcctl mfc; + bool do_wrvifwhole; u32 uval; /* There's one exception to the lock - MRT_DONE which needs to unlock */ @@ -1502,10 +1506,12 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, break; } + do_wrvifwhole = (val == IGMPMSG_WRVIFWHOLE); val = !!val; if (val != mrt->mroute_do_pim) { mrt->mroute_do_pim = val; mrt->mroute_do_assert = val; + mrt->mroute_do_wrvifwhole = do_wrvifwhole; } break; case MRT_TABLE: @@ -1983,6 +1989,9 @@ static void ip_mr_forward(struct net *net, struct mr_table *mrt, MFC_ASSERT_THRESH)) { c->_c.mfc_un.res.last_assert = jiffies; ipmr_cache_report(mrt, skb, true_vifi, IGMPMSG_WRONGVIF); + if (mrt->mroute_do_wrvifwhole) + ipmr_cache_report(mrt, skb, true_vifi, + IGMPMSG_WRVIFWHOLE); } goto dont_forward; } @@ -2659,7 +2668,9 @@ static bool ipmr_fill_table(struct mr_table *mrt, struct sk_buff *skb) mrt->mroute_reg_vif_num) || nla_put_u8(skb, IPMRA_TABLE_MROUTE_DO_ASSERT, mrt->mroute_do_assert) || - nla_put_u8(skb, IPMRA_TABLE_MROUTE_DO_PIM, mrt->mroute_do_pim)) + nla_put_u8(skb, IPMRA_TABLE_MROUTE_DO_PIM, mrt->mroute_do_pim) || + nla_put_u8(skb, IPMRA_TABLE_MROUTE_DO_WRVIFWHOLE, + mrt->mroute_do_wrvifwhole)) return false; return true; -- cgit v1.2.3 From 01683a1469995cc7aaf833d6f8b3f1c1d2fc3b92 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Mon, 9 Jul 2018 13:29:11 +0300 Subject: net: sched: refactor flower walk to iterate over idr Extend struct tcf_walker with additional 'cookie' field. It is intended to be used by classifier walk implementations to continue iteration directly from particular filter, instead of iterating 'skip' number of times. Change flower walk implementation to save filter handle in 'cookie'. Each time flower walk is called, it looks up filter with saved handle directly with idr, instead of iterating over filter linked list 'skip' number of times. This change improves complexity of dumping flower classifier from quadratic to linearithmic. (assuming idr lookup has logarithmic complexity) Reviewed-by: Jiri Pirko Signed-off-by: Vlad Buslov Reported-by: Simon Horman Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/net/pkt_cls.h | 1 + net/sched/cls_api.c | 2 ++ net/sched/cls_flower.c | 20 +++++++++----------- 3 files changed, 12 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 2081e4219f81..e4252a176eec 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -13,6 +13,7 @@ struct tcf_walker { int stop; int skip; int count; + unsigned long cookie; int (*fn)(struct tcf_proto *, void *node, struct tcf_walker *); }; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 73d9967c3739..c51b1b12450d 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1508,7 +1508,9 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent, arg.w.stop = 0; arg.w.skip = cb->args[1] - 1; arg.w.count = 0; + arg.w.cookie = cb->args[2]; tp->ops->walk(tp, &arg.w); + cb->args[2] = arg.w.cookie; cb->args[1] = arg.w.count + 1; if (arg.w.stop) return false; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 8b2474293db1..c53fdd411f90 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -1099,19 +1099,17 @@ static void fl_walk(struct tcf_proto *tp, struct tcf_walker *arg) { struct cls_fl_head *head = rtnl_dereference(tp->root); struct cls_fl_filter *f; - struct fl_flow_mask *mask; - list_for_each_entry_rcu(mask, &head->masks, list) { - list_for_each_entry_rcu(f, &mask->filters, list) { - if (arg->count < arg->skip) - goto skip; - if (arg->fn(tp, f, arg) < 0) { - arg->stop = 1; - break; - } -skip: - arg->count++; + arg->count = arg->skip; + + while ((f = idr_get_next_ul(&head->handle_idr, + &arg->cookie)) != NULL) { + if (arg->fn(tp, f, arg) < 0) { + arg->stop = 1; + break; } + arg->cookie = f->handle + 1; + arg->count++; } } -- cgit v1.2.3 From f333ee0cdb27ba201e6cc0c99c76b1364aa29b86 Mon Sep 17 00:00:00 2001 From: Andrey Ignatov Date: Wed, 11 Jul 2018 17:33:32 -0700 Subject: bpf: Add BPF_SOCK_OPS_TCP_LISTEN_CB Add new TCP-BPF callback that is called on listen(2) right after socket transition to TCP_LISTEN state. It fills the gap for listening sockets in TCP-BPF. For example BPF program can set BPF_SOCK_OPS_STATE_CB_FLAG when socket becomes listening and track later transition from TCP_LISTEN to TCP_CLOSE with BPF_SOCK_OPS_STATE_CB callback. Before there was no way to do it with TCP-BPF and other options were much harder to work with. E.g. socket state tracking can be done with tracepoints (either raw or regular) but they can't be attached to cgroup and their lifetime has to be managed separately. Signed-off-by: Andrey Ignatov Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/uapi/linux/bpf.h | 3 +++ net/ipv4/af_inet.c | 1 + 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 6bcb287a888d..870113916cac 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2555,6 +2555,9 @@ enum { * Arg1: old_state * Arg2: new_state */ + BPF_SOCK_OPS_TCP_LISTEN_CB, /* Called on listen(2), right after + * socket transition to LISTEN state. + */ }; /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index c716be13d58c..f2a0a3bab6b5 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -229,6 +229,7 @@ int inet_listen(struct socket *sock, int backlog) err = inet_csk_listen_start(sk, backlog); if (err) goto out; + tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_LISTEN_CB, 0, NULL); } sk->sk_max_ack_backlog = backlog; err = 0; -- cgit v1.2.3 From a7fe68a1e8e4bce007505f729bc33e427c540386 Mon Sep 17 00:00:00 2001 From: Felix Kuehling Date: Sat, 14 Jul 2018 19:05:58 -0400 Subject: drm/amd: Add CU-masking ioctl definition to kfd_ioctl.h Signed-off-by: Felix Kuehling Acked-by: Oded Gabbay Signed-off-by: Oded Gabbay --- include/uapi/linux/kfd_ioctl.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index 88d17c39dbf9..01674b56e14f 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -76,6 +76,12 @@ struct kfd_ioctl_update_queue_args { __u32 queue_priority; /* to KFD */ }; +struct kfd_ioctl_set_cu_mask_args { + __u32 queue_id; /* to KFD */ + __u32 num_cu_mask; /* to KFD */ + __u64 cu_mask_ptr; /* to KFD */ +}; + /* For kfd_ioctl_set_memory_policy_args.default_policy and alternate_policy */ #define KFD_IOC_CACHE_POLICY_COHERENT 0 #define KFD_IOC_CACHE_POLICY_NONCOHERENT 1 @@ -466,7 +472,10 @@ struct kfd_ioctl_unmap_memory_from_gpu_args { #define AMDKFD_IOC_UNMAP_MEMORY_FROM_GPU \ AMDKFD_IOWR(0x19, struct kfd_ioctl_unmap_memory_from_gpu_args) +#define AMDKFD_IOC_SET_CU_MASK \ + AMDKFD_IOW(0x1A, struct kfd_ioctl_set_cu_mask_args) + #define AMDKFD_COMMAND_START 0x01 -#define AMDKFD_COMMAND_END 0x1A +#define AMDKFD_COMMAND_END 0x1B #endif -- cgit v1.2.3 From 6c26fcd2abfe0a56bbd95271fce02df2896cfd24 Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Sat, 14 Jul 2018 21:56:13 +0200 Subject: x86/speculation/l1tf: Unbreak !__HAVE_ARCH_PFN_MODIFY_ALLOWED architectures pfn_modify_allowed() and arch_has_pfn_modify_check() are outside of the !__ASSEMBLY__ section in include/asm-generic/pgtable.h, which confuses assembler on archs that don't have __HAVE_ARCH_PFN_MODIFY_ALLOWED (e.g. ia64) and breaks build: include/asm-generic/pgtable.h: Assembler messages: include/asm-generic/pgtable.h:538: Error: Unknown opcode `static inline bool pfn_modify_allowed(unsigned long pfn,pgprot_t prot)' include/asm-generic/pgtable.h:540: Error: Unknown opcode `return true' include/asm-generic/pgtable.h:543: Error: Unknown opcode `static inline bool arch_has_pfn_modify_check(void)' include/asm-generic/pgtable.h:545: Error: Unknown opcode `return false' arch/ia64/kernel/entry.S:69: Error: `mov' does not fit into bundle Move those two static inlines into the !__ASSEMBLY__ section so that they don't confuse the asm build pass. Fixes: 42e4089c7890 ("x86/speculation/l1tf: Disallow non privileged high MMIO PROT_NONE mappings") Signed-off-by: Jiri Kosina Signed-off-by: Thomas Gleixner --- include/asm-generic/pgtable.h | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index 0ecc1197084b..26ca0276b503 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -1083,6 +1083,18 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, static inline void init_espfix_bsp(void) { } #endif +#ifndef __HAVE_ARCH_PFN_MODIFY_ALLOWED +static inline bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot) +{ + return true; +} + +static inline bool arch_has_pfn_modify_check(void) +{ + return false; +} +#endif /* !_HAVE_ARCH_PFN_MODIFY_ALLOWED */ + #endif /* !__ASSEMBLY__ */ #ifndef io_remap_pfn_range @@ -1097,16 +1109,4 @@ static inline void init_espfix_bsp(void) { } #endif #endif -#ifndef __HAVE_ARCH_PFN_MODIFY_ALLOWED -static inline bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot) -{ - return true; -} - -static inline bool arch_has_pfn_modify_check(void) -{ - return false; -} -#endif - #endif /* _ASM_GENERIC_PGTABLE_H */ -- cgit v1.2.3 From 5fd778915ad29184a5ff8eb82d1118f6916b79e4 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Thu, 28 Jun 2018 17:45:14 +0200 Subject: sched/sysctl: Remove unused sched_time_avg_ms sysctl /proc/sys/kernel/sched_time_avg_ms entry is not used anywhere, remove it. Signed-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Luis R. Rodriguez Cc: Kees Cook Cc: Linus Torvalds Cc: Morten.Rasmussen@arm.com Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: claudio@evidence.eu.com Cc: daniel.lezcano@linaro.org Cc: dietmar.eggemann@arm.com Cc: joel@joelfernandes.org Cc: juri.lelli@redhat.com Cc: luca.abeni@santannapisa.it Cc: patrick.bellasi@arm.com Cc: quentin.perret@arm.com Cc: rjw@rjwysocki.net Cc: valentin.schneider@arm.com Cc: viresh.kumar@linaro.org Link: http://lkml.kernel.org/r/1530200714-4504-12-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar --- include/linux/sched/sysctl.h | 1 - kernel/sched/core.c | 8 -------- kernel/sched/sched.h | 1 - kernel/sysctl.c | 8 -------- 4 files changed, 18 deletions(-) (limited to 'include') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 1c1a1512ec55..913488d828cb 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -40,7 +40,6 @@ extern unsigned int sysctl_numa_balancing_scan_size; #ifdef CONFIG_SCHED_DEBUG extern __read_mostly unsigned int sysctl_sched_migration_cost; extern __read_mostly unsigned int sysctl_sched_nr_migrate; -extern __read_mostly unsigned int sysctl_sched_time_avg; int sched_proc_update_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, diff --git a/kernel/sched/core.c b/kernel/sched/core.c index a691b07390ab..ba6bb805693a 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -46,14 +46,6 @@ const_debug unsigned int sysctl_sched_features = */ const_debug unsigned int sysctl_sched_nr_migrate = 32; -/* - * period over which we average the RT time consumption, measured - * in ms. - * - * default: 1s - */ -const_debug unsigned int sysctl_sched_time_avg = MSEC_PER_SEC; - /* * period over which we measure -rt task CPU usage in us. * default: 1s diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 14aac2d2de80..ebb4b3c3ece7 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1713,7 +1713,6 @@ extern void deactivate_task(struct rq *rq, struct task_struct *p, int flags); extern void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags); -extern const_debug unsigned int sysctl_sched_time_avg; extern const_debug unsigned int sysctl_sched_nr_migrate; extern const_debug unsigned int sysctl_sched_migration_cost; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 2d9837c0aff4..f22f76b7a138 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -368,14 +368,6 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - { - .procname = "sched_time_avg_ms", - .data = &sysctl_sched_time_avg, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &one, - }, #ifdef CONFIG_SCHEDSTATS { .procname = "sched_schedstats", -- cgit v1.2.3 From 788faab70d5a882693286b8d5022779559c79904 Mon Sep 17 00:00:00 2001 From: Tobias Tefke Date: Mon, 9 Jul 2018 12:57:15 +0200 Subject: perf, tools: Use correct articles in comments Some of the comments in the perf events code use articles incorrectly, using 'a' for words beginning with a vowel sound, where 'an' should be used. Signed-off-by: Tobias Tefke Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: acme@kernel.org Cc: alexander.shishkin@linux.intel.com Cc: jolsa@redhat.com Cc: namhyung@kernel.org Link: http://lkml.kernel.org/r/20180709105715.22938-1-tobias.tefke@tutanota.com [ Fix a few more perf related 'a event' typo fixes from all around the kernel and tooling tree. ] Signed-off-by: Ingo Molnar --- arch/powerpc/perf/core-book3s.c | 6 +++--- include/linux/perf_event.h | 2 +- kernel/events/core.c | 16 ++++++++-------- kernel/events/uprobes.c | 6 +++--- tools/perf/Documentation/perf-list.txt | 2 +- tools/perf/Documentation/perf-record.txt | 4 ++-- 6 files changed, 18 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 3f66fcf8ad99..19d8ab49d1bd 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -1469,7 +1469,7 @@ static int collect_events(struct perf_event *group, int max_count, } /* - * Add a event to the PMU. + * Add an event to the PMU. * If all events are not already frozen, then we disable and * re-enable the PMU in order to get hw_perf_enable to do the * actual work of reconfiguring the PMU. @@ -1548,7 +1548,7 @@ nocheck: } /* - * Remove a event from the PMU. + * Remove an event from the PMU. */ static void power_pmu_del(struct perf_event *event, int ef_flags) { @@ -1742,7 +1742,7 @@ static int power_pmu_commit_txn(struct pmu *pmu) /* * Return 1 if we might be able to put event on a limited PMC, * or 0 if not. - * A event can only go on a limited PMC if it counts something + * An event can only go on a limited PMC if it counts something * that a limited PMC can count, doesn't require interrupts, and * doesn't exclude any processor mode. */ diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 1fa12887ec02..e6dd3a2f8ec4 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -490,7 +490,7 @@ struct perf_addr_filters_head { }; /** - * enum perf_event_state - the states of a event + * enum perf_event_state - the states of an event: */ enum perf_event_state { PERF_EVENT_STATE_DEAD = -4, diff --git a/kernel/events/core.c b/kernel/events/core.c index a4d5ac6d74af..86b31e5a5a9a 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1656,7 +1656,7 @@ perf_event_groups_next(struct perf_event *event) typeof(*event), group_node)) /* - * Add a event from the lists for its context. + * Add an event from the lists for its context. * Must be called with ctx->mutex and ctx->lock held. */ static void @@ -1844,7 +1844,7 @@ static void perf_group_attach(struct perf_event *event) } /* - * Remove a event from the lists for its context. + * Remove an event from the lists for its context. * Must be called with ctx->mutex and ctx->lock held. */ static void @@ -2148,7 +2148,7 @@ static void __perf_event_disable(struct perf_event *event, } /* - * Disable a event. + * Disable an event. * * If event->ctx is a cloned context, callers must make sure that * every task struct that event->ctx->task could possibly point to @@ -2677,7 +2677,7 @@ static void __perf_event_enable(struct perf_event *event, } /* - * Enable a event. + * Enable an event. * * If event->ctx is a cloned context, callers must make sure that * every task struct that event->ctx->task could possibly point to @@ -2755,7 +2755,7 @@ static int __perf_event_stop(void *info) * events will refuse to restart because of rb::aux_mmap_count==0, * see comments in perf_aux_output_begin(). * - * Since this is happening on a event-local CPU, no trace is lost + * Since this is happening on an event-local CPU, no trace is lost * while restarting. */ if (sd->restart) @@ -4827,7 +4827,7 @@ __perf_read(struct perf_event *event, char __user *buf, size_t count) int ret; /* - * Return end-of-file for a read on a event that is in + * Return end-of-file for a read on an event that is in * error state (i.e. because it was pinned but it couldn't be * scheduled on to the CPU at some point). */ @@ -9898,7 +9898,7 @@ enabled: } /* - * Allocate and initialize a event structure + * Allocate and initialize an event structure */ static struct perf_event * perf_event_alloc(struct perf_event_attr *attr, int cpu, @@ -11229,7 +11229,7 @@ const struct perf_event_attr *perf_event_attrs(struct perf_event *event) } /* - * Inherit a event from parent task to child task. + * Inherit an event from parent task to child task. * * Returns: * - valid pointer on success diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index ccc579a7d32e..aed1ba569954 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -918,7 +918,7 @@ int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer * EXPORT_SYMBOL_GPL(uprobe_register); /* - * uprobe_apply - unregister a already registered probe. + * uprobe_apply - unregister an already registered probe. * @inode: the file in which the probe has to be removed. * @offset: offset from the start of the file. * @uc: consumer which wants to add more or remove some breakpoints @@ -947,7 +947,7 @@ int uprobe_apply(struct inode *inode, loff_t offset, } /* - * uprobe_unregister - unregister a already registered probe. + * uprobe_unregister - unregister an already registered probe. * @inode: the file in which the probe has to be removed. * @offset: offset from the start of the file. * @uc: identify which probe if multiple probes are colocated. @@ -1403,7 +1403,7 @@ static struct return_instance *free_ret_instance(struct return_instance *ri) /* * Called with no locks held. - * Called in context of a exiting or a exec-ing thread. + * Called in context of an exiting or an exec-ing thread. */ void uprobe_free_utask(struct task_struct *t) { diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt index 11300dbe35c5..14e13512c05f 100644 --- a/tools/perf/Documentation/perf-list.txt +++ b/tools/perf/Documentation/perf-list.txt @@ -234,7 +234,7 @@ perf also supports group leader sampling using the :S specifier. perf record -e '{cycles,instructions}:S' ... perf report --group -Normally all events in a event group sample, but with :S only +Normally all events in an event group sample, but with :S only the first event (the leader) samples, and it only reads the values of the other events in the group. diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 04168da4268e..246dee081efd 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -94,7 +94,7 @@ OPTIONS "perf report" to view group events together. --filter=:: - Event filter. This option should follow a event selector (-e) which + Event filter. This option should follow an event selector (-e) which selects either tracepoint event(s) or a hardware trace PMU (e.g. Intel PT or CoreSight). @@ -153,7 +153,7 @@ OPTIONS --exclude-perf:: Don't record events issued by perf itself. This option should follow - a event selector (-e) which selects tracepoint event(s). It adds a + an event selector (-e) which selects tracepoint event(s). It adds a filter expression 'common_pid != $PERFPID' to filters. If other '--filter' exists, the new filter expression will be combined with them by '&&'. -- cgit v1.2.3 From 3eb420e70d879ce0e6bf752accf5cdedb0a59de8 Mon Sep 17 00:00:00 2001 From: Sai Praneeth Date: Wed, 11 Jul 2018 11:40:35 +0200 Subject: efi: Use a work queue to invoke EFI Runtime Services Presently, when a user process requests the kernel to execute any UEFI runtime service, the kernel temporarily switches to a separate set of page tables that describe the virtual mapping of the UEFI runtime services regions in memory. Since UEFI runtime services are typically invoked with interrupts enabled, any code that may be called during this time, will have an incorrect view of the process's address space. Although it is unusual for code running in interrupt context to make assumptions about the process context it runs in, there are cases (such as the perf subsystem taking samples) where this causes problems. So let's set up a work queue for calling UEFI runtime services, so that the actual calls are made when the work queue items are dispatched by a work queue worker running in a separate kernel thread. Such threads are not expected to have userland mappings in the first place, and so the additional mappings created for the UEFI runtime services can never clash with any. The ResetSystem() runtime service is not covered by the work queue handling, since it is not expected to return, and may be called at a time when the kernel is torn down to the point where we cannot expect work queues to still be operational. The non-blocking variants of SetVariable() and QueryVariableInfo() are also excluded: these are intended to be used from atomic context, which obviously rules out waiting for a completion to be signalled by another thread. Note that these variants are currently only used for UEFI runtime services calls that occur very early in the boot, and for ones that occur in critical conditions, e.g., to flush kernel logs to UEFI variables via efi-pstore. Suggested-by: Andy Lutomirski Signed-off-by: Sai Praneeth Prakhya [ardb: exclude ResetSystem() from the workqueue treatment merge from 2 separate patches and rewrite commit log] Signed-off-by: Ard Biesheuvel Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/20180711094040.12506-4-ard.biesheuvel@linaro.org Signed-off-by: Ingo Molnar --- drivers/firmware/efi/efi.c | 14 +++ drivers/firmware/efi/runtime-wrappers.c | 202 +++++++++++++++++++++++++++++--- include/linux/efi.h | 3 + 3 files changed, 204 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 232f4915223b..1379a375dfa8 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -84,6 +84,8 @@ struct mm_struct efi_mm = { .mmlist = LIST_HEAD_INIT(efi_mm.mmlist), }; +struct workqueue_struct *efi_rts_wq; + static bool disable_runtime; static int __init setup_noefi(char *arg) { @@ -337,6 +339,18 @@ static int __init efisubsys_init(void) if (!efi_enabled(EFI_BOOT)) return 0; + /* + * Since we process only one efi_runtime_service() at a time, an + * ordered workqueue (which creates only one execution context) + * should suffice all our needs. + */ + efi_rts_wq = alloc_ordered_workqueue("efi_rts_wq", 0); + if (!efi_rts_wq) { + pr_err("Creating efi_rts_wq failed, EFI runtime services disabled.\n"); + clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); + return 0; + } + /* We register the efi directory at /sys/firmware/efi */ efi_kobj = kobject_create_and_add("efi", firmware_kobj); if (!efi_kobj) { diff --git a/drivers/firmware/efi/runtime-wrappers.c b/drivers/firmware/efi/runtime-wrappers.c index ae54870b2788..aa66cbf23512 100644 --- a/drivers/firmware/efi/runtime-wrappers.c +++ b/drivers/firmware/efi/runtime-wrappers.c @@ -1,6 +1,15 @@ /* * runtime-wrappers.c - Runtime Services function call wrappers * + * Implementation summary: + * ----------------------- + * 1. When user/kernel thread requests to execute efi_runtime_service(), + * enqueue work to efi_rts_wq. + * 2. Caller thread waits for completion until the work is finished + * because it's dependent on the return status and execution of + * efi_runtime_service(). + * For instance, get_variable() and get_next_variable(). + * * Copyright (C) 2014 Linaro Ltd. * * Split off from arch/x86/platform/efi/efi.c @@ -22,6 +31,9 @@ #include #include #include +#include +#include + #include /* @@ -33,6 +45,76 @@ #define __efi_call_virt(f, args...) \ __efi_call_virt_pointer(efi.systab->runtime, f, args) +/* efi_runtime_service() function identifiers */ +enum efi_rts_ids { + GET_TIME, + SET_TIME, + GET_WAKEUP_TIME, + SET_WAKEUP_TIME, + GET_VARIABLE, + GET_NEXT_VARIABLE, + SET_VARIABLE, + QUERY_VARIABLE_INFO, + GET_NEXT_HIGH_MONO_COUNT, + UPDATE_CAPSULE, + QUERY_CAPSULE_CAPS, +}; + +/* + * efi_runtime_work: Details of EFI Runtime Service work + * @arg<1-5>: EFI Runtime Service function arguments + * @status: Status of executing EFI Runtime Service + * @efi_rts_id: EFI Runtime Service function identifier + * @efi_rts_comp: Struct used for handling completions + */ +struct efi_runtime_work { + void *arg1; + void *arg2; + void *arg3; + void *arg4; + void *arg5; + efi_status_t status; + struct work_struct work; + enum efi_rts_ids efi_rts_id; + struct completion efi_rts_comp; +}; + +/* + * efi_queue_work: Queue efi_runtime_service() and wait until it's done + * @rts: efi_runtime_service() function identifier + * @rts_arg<1-5>: efi_runtime_service() function arguments + * + * Accesses to efi_runtime_services() are serialized by a binary + * semaphore (efi_runtime_lock) and caller waits until the work is + * finished, hence _only_ one work is queued at a time and the caller + * thread waits for completion. + */ +#define efi_queue_work(_rts, _arg1, _arg2, _arg3, _arg4, _arg5) \ +({ \ + struct efi_runtime_work efi_rts_work; \ + efi_rts_work.status = EFI_ABORTED; \ + \ + init_completion(&efi_rts_work.efi_rts_comp); \ + INIT_WORK_ONSTACK(&efi_rts_work.work, efi_call_rts); \ + efi_rts_work.arg1 = _arg1; \ + efi_rts_work.arg2 = _arg2; \ + efi_rts_work.arg3 = _arg3; \ + efi_rts_work.arg4 = _arg4; \ + efi_rts_work.arg5 = _arg5; \ + efi_rts_work.efi_rts_id = _rts; \ + \ + /* \ + * queue_work() returns 0 if work was already on queue, \ + * _ideally_ this should never happen. \ + */ \ + if (queue_work(efi_rts_wq, &efi_rts_work.work)) \ + wait_for_completion(&efi_rts_work.efi_rts_comp); \ + else \ + pr_err("Failed to queue work to efi_rts_wq.\n"); \ + \ + efi_rts_work.status; \ +}) + void efi_call_virt_check_flags(unsigned long flags, const char *call) { unsigned long cur_flags, mismatch; @@ -90,13 +172,98 @@ void efi_call_virt_check_flags(unsigned long flags, const char *call) */ static DEFINE_SEMAPHORE(efi_runtime_lock); +/* + * Calls the appropriate efi_runtime_service() with the appropriate + * arguments. + * + * Semantics followed by efi_call_rts() to understand efi_runtime_work: + * 1. If argument was a pointer, recast it from void pointer to original + * pointer type. + * 2. If argument was a value, recast it from void pointer to original + * pointer type and dereference it. + */ +static void efi_call_rts(struct work_struct *work) +{ + struct efi_runtime_work *efi_rts_work; + void *arg1, *arg2, *arg3, *arg4, *arg5; + efi_status_t status = EFI_NOT_FOUND; + + efi_rts_work = container_of(work, struct efi_runtime_work, work); + arg1 = efi_rts_work->arg1; + arg2 = efi_rts_work->arg2; + arg3 = efi_rts_work->arg3; + arg4 = efi_rts_work->arg4; + arg5 = efi_rts_work->arg5; + + switch (efi_rts_work->efi_rts_id) { + case GET_TIME: + status = efi_call_virt(get_time, (efi_time_t *)arg1, + (efi_time_cap_t *)arg2); + break; + case SET_TIME: + status = efi_call_virt(set_time, (efi_time_t *)arg1); + break; + case GET_WAKEUP_TIME: + status = efi_call_virt(get_wakeup_time, (efi_bool_t *)arg1, + (efi_bool_t *)arg2, (efi_time_t *)arg3); + break; + case SET_WAKEUP_TIME: + status = efi_call_virt(set_wakeup_time, *(efi_bool_t *)arg1, + (efi_time_t *)arg2); + break; + case GET_VARIABLE: + status = efi_call_virt(get_variable, (efi_char16_t *)arg1, + (efi_guid_t *)arg2, (u32 *)arg3, + (unsigned long *)arg4, (void *)arg5); + break; + case GET_NEXT_VARIABLE: + status = efi_call_virt(get_next_variable, (unsigned long *)arg1, + (efi_char16_t *)arg2, + (efi_guid_t *)arg3); + break; + case SET_VARIABLE: + status = efi_call_virt(set_variable, (efi_char16_t *)arg1, + (efi_guid_t *)arg2, *(u32 *)arg3, + *(unsigned long *)arg4, (void *)arg5); + break; + case QUERY_VARIABLE_INFO: + status = efi_call_virt(query_variable_info, *(u32 *)arg1, + (u64 *)arg2, (u64 *)arg3, (u64 *)arg4); + break; + case GET_NEXT_HIGH_MONO_COUNT: + status = efi_call_virt(get_next_high_mono_count, (u32 *)arg1); + break; + case UPDATE_CAPSULE: + status = efi_call_virt(update_capsule, + (efi_capsule_header_t **)arg1, + *(unsigned long *)arg2, + *(unsigned long *)arg3); + break; + case QUERY_CAPSULE_CAPS: + status = efi_call_virt(query_capsule_caps, + (efi_capsule_header_t **)arg1, + *(unsigned long *)arg2, (u64 *)arg3, + (int *)arg4); + break; + default: + /* + * Ideally, we should never reach here because a caller of this + * function should have put the right efi_runtime_service() + * function identifier into efi_rts_work->efi_rts_id + */ + pr_err("Requested executing invalid EFI Runtime Service.\n"); + } + efi_rts_work->status = status; + complete(&efi_rts_work->efi_rts_comp); +} + static efi_status_t virt_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc) { efi_status_t status; if (down_interruptible(&efi_runtime_lock)) return EFI_ABORTED; - status = efi_call_virt(get_time, tm, tc); + status = efi_queue_work(GET_TIME, tm, tc, NULL, NULL, NULL); up(&efi_runtime_lock); return status; } @@ -107,7 +274,7 @@ static efi_status_t virt_efi_set_time(efi_time_t *tm) if (down_interruptible(&efi_runtime_lock)) return EFI_ABORTED; - status = efi_call_virt(set_time, tm); + status = efi_queue_work(SET_TIME, tm, NULL, NULL, NULL, NULL); up(&efi_runtime_lock); return status; } @@ -120,7 +287,8 @@ static efi_status_t virt_efi_get_wakeup_time(efi_bool_t *enabled, if (down_interruptible(&efi_runtime_lock)) return EFI_ABORTED; - status = efi_call_virt(get_wakeup_time, enabled, pending, tm); + status = efi_queue_work(GET_WAKEUP_TIME, enabled, pending, tm, NULL, + NULL); up(&efi_runtime_lock); return status; } @@ -131,7 +299,8 @@ static efi_status_t virt_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm) if (down_interruptible(&efi_runtime_lock)) return EFI_ABORTED; - status = efi_call_virt(set_wakeup_time, enabled, tm); + status = efi_queue_work(SET_WAKEUP_TIME, &enabled, tm, NULL, NULL, + NULL); up(&efi_runtime_lock); return status; } @@ -146,8 +315,8 @@ static efi_status_t virt_efi_get_variable(efi_char16_t *name, if (down_interruptible(&efi_runtime_lock)) return EFI_ABORTED; - status = efi_call_virt(get_variable, name, vendor, attr, data_size, - data); + status = efi_queue_work(GET_VARIABLE, name, vendor, attr, data_size, + data); up(&efi_runtime_lock); return status; } @@ -160,7 +329,8 @@ static efi_status_t virt_efi_get_next_variable(unsigned long *name_size, if (down_interruptible(&efi_runtime_lock)) return EFI_ABORTED; - status = efi_call_virt(get_next_variable, name_size, name, vendor); + status = efi_queue_work(GET_NEXT_VARIABLE, name_size, name, vendor, + NULL, NULL); up(&efi_runtime_lock); return status; } @@ -175,8 +345,8 @@ static efi_status_t virt_efi_set_variable(efi_char16_t *name, if (down_interruptible(&efi_runtime_lock)) return EFI_ABORTED; - status = efi_call_virt(set_variable, name, vendor, attr, data_size, - data); + status = efi_queue_work(SET_VARIABLE, name, vendor, &attr, &data_size, + data); up(&efi_runtime_lock); return status; } @@ -210,8 +380,8 @@ static efi_status_t virt_efi_query_variable_info(u32 attr, if (down_interruptible(&efi_runtime_lock)) return EFI_ABORTED; - status = efi_call_virt(query_variable_info, attr, storage_space, - remaining_space, max_variable_size); + status = efi_queue_work(QUERY_VARIABLE_INFO, &attr, storage_space, + remaining_space, max_variable_size, NULL); up(&efi_runtime_lock); return status; } @@ -242,7 +412,8 @@ static efi_status_t virt_efi_get_next_high_mono_count(u32 *count) if (down_interruptible(&efi_runtime_lock)) return EFI_ABORTED; - status = efi_call_virt(get_next_high_mono_count, count); + status = efi_queue_work(GET_NEXT_HIGH_MONO_COUNT, count, NULL, NULL, + NULL, NULL); up(&efi_runtime_lock); return status; } @@ -272,7 +443,8 @@ static efi_status_t virt_efi_update_capsule(efi_capsule_header_t **capsules, if (down_interruptible(&efi_runtime_lock)) return EFI_ABORTED; - status = efi_call_virt(update_capsule, capsules, count, sg_list); + status = efi_queue_work(UPDATE_CAPSULE, capsules, &count, &sg_list, + NULL, NULL); up(&efi_runtime_lock); return status; } @@ -289,8 +461,8 @@ static efi_status_t virt_efi_query_capsule_caps(efi_capsule_header_t **capsules, if (down_interruptible(&efi_runtime_lock)) return EFI_ABORTED; - status = efi_call_virt(query_capsule_caps, capsules, count, max_size, - reset_type); + status = efi_queue_work(QUERY_CAPSULE_CAPS, capsules, &count, + max_size, reset_type, NULL); up(&efi_runtime_lock); return status; } diff --git a/include/linux/efi.h b/include/linux/efi.h index 56add823f190..8ba0cdd244b2 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1651,4 +1651,7 @@ struct linux_efi_tpm_eventlog { extern int efi_tpm_eventlog_init(void); +/* Workqueue to queue EFI Runtime Services */ +extern struct workqueue_struct *efi_rts_wq; + #endif /* _LINUX_EFI_H */ -- cgit v1.2.3 From f5dcc214aae29a68b37b2b4183f7171724e7b02d Mon Sep 17 00:00:00 2001 From: Sai Praneeth Date: Wed, 11 Jul 2018 11:40:37 +0200 Subject: efi: Remove the declaration of efi_late_init() as the function is unused The following commit: 7b0a911478c74 ("efi/x86: Move the EFI BGRT init code to early init code") ... removed the implementation and all the references to efi_late_init() but the function is still declared at include/linux/efi.h. Hence, remove the unnecessary declaration. Signed-off-by: Sai Praneeth Prakhya Signed-off-by: Ard Biesheuvel Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/20180711094040.12506-6-ard.biesheuvel@linaro.org Signed-off-by: Ingo Molnar --- include/linux/efi.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/efi.h b/include/linux/efi.h index 8ba0cdd244b2..e190652f5ef9 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -988,14 +988,12 @@ extern void efi_memmap_walk (efi_freemem_callback_t callback, void *arg); extern void efi_gettimeofday (struct timespec64 *ts); extern void efi_enter_virtual_mode (void); /* switch EFI to virtual mode, if possible */ #ifdef CONFIG_X86 -extern void efi_late_init(void); extern void efi_free_boot_services(void); extern efi_status_t efi_query_variable_store(u32 attributes, unsigned long size, bool nonblocking); extern void efi_find_mirror(void); #else -static inline void efi_late_init(void) {} static inline void efi_free_boot_services(void) {} static inline efi_status_t efi_query_variable_store(u32 attributes, -- cgit v1.2.3 From 784abe24c903b093af04cf1a043140faa556cad7 Mon Sep 17 00:00:00 2001 From: Boris Pismenny Date: Fri, 13 Jul 2018 14:33:35 +0300 Subject: net: Add decrypted field to skb The decrypted bit is propogated to cloned/copied skbs. This will be used later by the inline crypto receive side offload of tls. Signed-off-by: Boris Pismenny Signed-off-by: Ilya Lesokhin Signed-off-by: David S. Miller --- include/linux/skbuff.h | 7 ++++++- net/core/skbuff.c | 6 ++++++ 2 files changed, 12 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 7601838c2513..3ceb8dcc54da 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -630,6 +630,7 @@ typedef unsigned char *sk_buff_data_t; * @hash: the packet hash * @queue_mapping: Queue mapping for multiqueue devices * @xmit_more: More SKBs are pending for this queue + * @decrypted: Decrypted SKB * @ndisc_nodetype: router type (from link layer) * @ooo_okay: allow the mapping of a socket to a queue to be changed * @l4_hash: indicate hash is a canonical 4-tuple hash over transport @@ -736,7 +737,11 @@ struct sk_buff { peeked:1, head_frag:1, xmit_more:1, - __unused:1; /* one bit hole */ +#ifdef CONFIG_TLS_DEVICE + decrypted:1; +#else + __unused:1; +#endif /* fields enclosed in headers_start/headers_end are copied * using a single memcpy() in __copy_skb_header() diff --git a/net/core/skbuff.c b/net/core/skbuff.c index c4e24ac27464..cfd6c6f35f9c 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -805,6 +805,9 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) * It is not yet because we do not want to have a 16 bit hole */ new->queue_mapping = old->queue_mapping; +#ifdef CONFIG_TLS_DEVICE + new->decrypted = old->decrypted; +#endif memcpy(&new->headers_start, &old->headers_start, offsetof(struct sk_buff, headers_end) - @@ -865,6 +868,9 @@ static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb) C(head_frag); C(data); C(truesize); +#ifdef CONFIG_TLS_DEVICE + C(decrypted); +#endif refcount_set(&n->users, 1); atomic_inc(&(skb_shinfo(skb)->dataref)); -- cgit v1.2.3 From 14136564c8ee94566945e85014019cbdb1716dca Mon Sep 17 00:00:00 2001 From: Ilya Lesokhin Date: Fri, 13 Jul 2018 14:33:36 +0300 Subject: net: Add TLS RX offload feature This patch adds a netdev feature to configure TLS RX inline crypto offload. Signed-off-by: Ilya Lesokhin Signed-off-by: Boris Pismenny Signed-off-by: David S. Miller --- include/linux/netdev_features.h | 2 ++ net/core/ethtool.c | 1 + 2 files changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 623bb8ced060..2b2a6dce1630 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -79,6 +79,7 @@ enum { NETIF_F_HW_ESP_TX_CSUM_BIT, /* ESP with TX checksum offload */ NETIF_F_RX_UDP_TUNNEL_PORT_BIT, /* Offload of RX port for UDP tunnels */ NETIF_F_HW_TLS_TX_BIT, /* Hardware TLS TX offload */ + NETIF_F_HW_TLS_RX_BIT, /* Hardware TLS RX offload */ NETIF_F_GRO_HW_BIT, /* Hardware Generic receive offload */ NETIF_F_HW_TLS_RECORD_BIT, /* Offload TLS record */ @@ -151,6 +152,7 @@ enum { #define NETIF_F_HW_TLS_RECORD __NETIF_F(HW_TLS_RECORD) #define NETIF_F_GSO_UDP_L4 __NETIF_F(GSO_UDP_L4) #define NETIF_F_HW_TLS_TX __NETIF_F(HW_TLS_TX) +#define NETIF_F_HW_TLS_RX __NETIF_F(HW_TLS_RX) #define for_each_netdev_feature(mask_addr, bit) \ for_each_set_bit(bit, (unsigned long *)mask_addr, NETDEV_FEATURE_COUNT) diff --git a/net/core/ethtool.c b/net/core/ethtool.c index e677a20180cf..c9993c6c2fd4 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -111,6 +111,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] [NETIF_F_RX_UDP_TUNNEL_PORT_BIT] = "rx-udp_tunnel-port-offload", [NETIF_F_HW_TLS_RECORD_BIT] = "tls-hw-record", [NETIF_F_HW_TLS_TX_BIT] = "tls-hw-tx-offload", + [NETIF_F_HW_TLS_RX_BIT] = "tls-hw-rx-offload", }; static const char -- cgit v1.2.3 From 16e4edc297ffc9b643b8dd3da6b0d579753ea2b3 Mon Sep 17 00:00:00 2001 From: Boris Pismenny Date: Fri, 13 Jul 2018 14:33:37 +0300 Subject: net: Add TLS rx resync NDO Add new netdev tls op for resynchronizing HW tls context Signed-off-by: Boris Pismenny Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 4fa7f7a3f8b3..3514d67112b3 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -903,6 +903,8 @@ struct tlsdev_ops { void (*tls_dev_del)(struct net_device *netdev, struct tls_context *ctx, enum tls_offload_ctx_dir direction); + void (*tls_dev_resync_rx)(struct net_device *netdev, + struct sock *sk, u32 seq, u64 rcd_sn); }; #endif -- cgit v1.2.3 From d80a1b9d186057ddb0d384ba601cf2b7d214539c Mon Sep 17 00:00:00 2001 From: Boris Pismenny Date: Fri, 13 Jul 2018 14:33:39 +0300 Subject: tls: Refactor tls_offload variable names For symmetry, we rename tls_offload_context to tls_offload_context_tx before we add tls_offload_context_rx. Signed-off-by: Boris Pismenny Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlx5/core/en_accel/tls.h | 6 +++--- include/net/tls.h | 16 +++++++------- net/tls/tls_device.c | 25 +++++++++++----------- net/tls/tls_device_fallback.c | 8 +++---- 4 files changed, 27 insertions(+), 28 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h index b6162178f621..b82f4deaa398 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h @@ -50,7 +50,7 @@ struct mlx5e_tls { }; struct mlx5e_tls_offload_context { - struct tls_offload_context base; + struct tls_offload_context_tx base; u32 expected_seq; __be32 swid; }; @@ -59,8 +59,8 @@ static inline struct mlx5e_tls_offload_context * mlx5e_get_tls_tx_context(struct tls_context *tls_ctx) { BUILD_BUG_ON(sizeof(struct mlx5e_tls_offload_context) > - TLS_OFFLOAD_CONTEXT_SIZE); - return container_of(tls_offload_ctx(tls_ctx), + TLS_OFFLOAD_CONTEXT_SIZE_TX); + return container_of(tls_offload_ctx_tx(tls_ctx), struct mlx5e_tls_offload_context, base); } diff --git a/include/net/tls.h b/include/net/tls.h index 70c273777fe9..5dcd808236a7 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -128,7 +128,7 @@ struct tls_record_info { skb_frag_t frags[MAX_SKB_FRAGS]; }; -struct tls_offload_context { +struct tls_offload_context_tx { struct crypto_aead *aead_send; spinlock_t lock; /* protects records list */ struct list_head records_list; @@ -147,8 +147,8 @@ struct tls_offload_context { #define TLS_DRIVER_STATE_SIZE (max_t(size_t, 8, sizeof(void *))) }; -#define TLS_OFFLOAD_CONTEXT_SIZE \ - (ALIGN(sizeof(struct tls_offload_context), sizeof(void *)) + \ +#define TLS_OFFLOAD_CONTEXT_SIZE_TX \ + (ALIGN(sizeof(struct tls_offload_context_tx), sizeof(void *)) + \ TLS_DRIVER_STATE_SIZE) enum { @@ -239,7 +239,7 @@ void tls_device_sk_destruct(struct sock *sk); void tls_device_init(void); void tls_device_cleanup(void); -struct tls_record_info *tls_get_record(struct tls_offload_context *context, +struct tls_record_info *tls_get_record(struct tls_offload_context_tx *context, u32 seq, u64 *p_record_sn); static inline bool tls_record_is_start_marker(struct tls_record_info *rec) @@ -380,10 +380,10 @@ static inline struct tls_sw_context_tx *tls_sw_ctx_tx( return (struct tls_sw_context_tx *)tls_ctx->priv_ctx_tx; } -static inline struct tls_offload_context *tls_offload_ctx( - const struct tls_context *tls_ctx) +static inline struct tls_offload_context_tx * +tls_offload_ctx_tx(const struct tls_context *tls_ctx) { - return (struct tls_offload_context *)tls_ctx->priv_ctx_tx; + return (struct tls_offload_context_tx *)tls_ctx->priv_ctx_tx; } int tls_proccess_cmsg(struct sock *sk, struct msghdr *msg, @@ -396,7 +396,7 @@ struct sk_buff *tls_validate_xmit_skb(struct sock *sk, struct sk_buff *skb); int tls_sw_fallback_init(struct sock *sk, - struct tls_offload_context *offload_ctx, + struct tls_offload_context_tx *offload_ctx, struct tls_crypto_info *crypto_info); #endif /* _TLS_OFFLOAD_H */ diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index a7a8f8e20ff3..332a5d1459b6 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -52,9 +52,8 @@ static DEFINE_SPINLOCK(tls_device_lock); static void tls_device_free_ctx(struct tls_context *ctx) { - struct tls_offload_context *offload_ctx = tls_offload_ctx(ctx); + kfree(tls_offload_ctx_tx(ctx)); - kfree(offload_ctx); kfree(ctx); } @@ -125,7 +124,7 @@ static void destroy_record(struct tls_record_info *record) kfree(record); } -static void delete_all_records(struct tls_offload_context *offload_ctx) +static void delete_all_records(struct tls_offload_context_tx *offload_ctx) { struct tls_record_info *info, *temp; @@ -141,14 +140,14 @@ static void tls_icsk_clean_acked(struct sock *sk, u32 acked_seq) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_record_info *info, *temp; - struct tls_offload_context *ctx; + struct tls_offload_context_tx *ctx; u64 deleted_records = 0; unsigned long flags; if (!tls_ctx) return; - ctx = tls_offload_ctx(tls_ctx); + ctx = tls_offload_ctx_tx(tls_ctx); spin_lock_irqsave(&ctx->lock, flags); info = ctx->retransmit_hint; @@ -179,7 +178,7 @@ static void tls_icsk_clean_acked(struct sock *sk, u32 acked_seq) void tls_device_sk_destruct(struct sock *sk) { struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_offload_context *ctx = tls_offload_ctx(tls_ctx); + struct tls_offload_context_tx *ctx = tls_offload_ctx_tx(tls_ctx); if (ctx->open_record) destroy_record(ctx->open_record); @@ -219,7 +218,7 @@ static void tls_append_frag(struct tls_record_info *record, static int tls_push_record(struct sock *sk, struct tls_context *ctx, - struct tls_offload_context *offload_ctx, + struct tls_offload_context_tx *offload_ctx, struct tls_record_info *record, struct page_frag *pfrag, int flags, @@ -264,7 +263,7 @@ static int tls_push_record(struct sock *sk, return tls_push_sg(sk, ctx, offload_ctx->sg_tx_data, 0, flags); } -static int tls_create_new_record(struct tls_offload_context *offload_ctx, +static int tls_create_new_record(struct tls_offload_context_tx *offload_ctx, struct page_frag *pfrag, size_t prepend_size) { @@ -290,7 +289,7 @@ static int tls_create_new_record(struct tls_offload_context *offload_ctx, } static int tls_do_allocation(struct sock *sk, - struct tls_offload_context *offload_ctx, + struct tls_offload_context_tx *offload_ctx, struct page_frag *pfrag, size_t prepend_size) { @@ -324,7 +323,7 @@ static int tls_push_data(struct sock *sk, unsigned char record_type) { struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_offload_context *ctx = tls_offload_ctx(tls_ctx); + struct tls_offload_context_tx *ctx = tls_offload_ctx_tx(tls_ctx); int tls_push_record_flags = flags | MSG_SENDPAGE_NOTLAST; int more = flags & (MSG_SENDPAGE_NOTLAST | MSG_MORE); struct tls_record_info *record = ctx->open_record; @@ -477,7 +476,7 @@ out: return rc; } -struct tls_record_info *tls_get_record(struct tls_offload_context *context, +struct tls_record_info *tls_get_record(struct tls_offload_context_tx *context, u32 seq, u64 *p_record_sn) { u64 record_sn = context->hint_record_sn; @@ -524,7 +523,7 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx) { u16 nonce_size, tag_size, iv_size, rec_seq_size; struct tls_record_info *start_marker_record; - struct tls_offload_context *offload_ctx; + struct tls_offload_context_tx *offload_ctx; struct tls_crypto_info *crypto_info; struct net_device *netdev; char *iv, *rec_seq; @@ -546,7 +545,7 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx) goto out; } - offload_ctx = kzalloc(TLS_OFFLOAD_CONTEXT_SIZE, GFP_KERNEL); + offload_ctx = kzalloc(TLS_OFFLOAD_CONTEXT_SIZE_TX, GFP_KERNEL); if (!offload_ctx) { rc = -ENOMEM; goto free_marker_record; diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c index 748914abdb60..d1d7dce38e0b 100644 --- a/net/tls/tls_device_fallback.c +++ b/net/tls/tls_device_fallback.c @@ -214,7 +214,7 @@ static void complete_skb(struct sk_buff *nskb, struct sk_buff *skb, int headln) static int fill_sg_in(struct scatterlist *sg_in, struct sk_buff *skb, - struct tls_offload_context *ctx, + struct tls_offload_context_tx *ctx, u64 *rcd_sn, s32 *sync_size, int *resync_sgs) @@ -299,7 +299,7 @@ static struct sk_buff *tls_enc_skb(struct tls_context *tls_ctx, s32 sync_size, u64 rcd_sn) { int tcp_payload_offset = skb_transport_offset(skb) + tcp_hdrlen(skb); - struct tls_offload_context *ctx = tls_offload_ctx(tls_ctx); + struct tls_offload_context_tx *ctx = tls_offload_ctx_tx(tls_ctx); int payload_len = skb->len - tcp_payload_offset; void *buf, *iv, *aad, *dummy_buf; struct aead_request *aead_req; @@ -361,7 +361,7 @@ static struct sk_buff *tls_sw_fallback(struct sock *sk, struct sk_buff *skb) { int tcp_payload_offset = skb_transport_offset(skb) + tcp_hdrlen(skb); struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_offload_context *ctx = tls_offload_ctx(tls_ctx); + struct tls_offload_context_tx *ctx = tls_offload_ctx_tx(tls_ctx); int payload_len = skb->len - tcp_payload_offset; struct scatterlist *sg_in, sg_out[3]; struct sk_buff *nskb = NULL; @@ -415,7 +415,7 @@ struct sk_buff *tls_validate_xmit_skb(struct sock *sk, } int tls_sw_fallback_init(struct sock *sk, - struct tls_offload_context *offload_ctx, + struct tls_offload_context_tx *offload_ctx, struct tls_crypto_info *crypto_info) { const u8 *key; -- cgit v1.2.3 From dafb67f3bb4a58a45fe92c1e362ea6429831688a Mon Sep 17 00:00:00 2001 From: Boris Pismenny Date: Fri, 13 Jul 2018 14:33:40 +0300 Subject: tls: Split decrypt_skb to two functions Previously, decrypt_skb also updated the TLS context. Now, decrypt_skb only decrypts the payload using the current context, while decrypt_skb_update also updates the state. Later, in the tls_device Rx flow, we will use decrypt_skb directly. Signed-off-by: Boris Pismenny Signed-off-by: David S. Miller --- include/net/tls.h | 2 ++ net/tls/tls_sw.c | 44 ++++++++++++++++++++++++++------------------ 2 files changed, 28 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/net/tls.h b/include/net/tls.h index 5dcd808236a7..49b89221db43 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -390,6 +390,8 @@ int tls_proccess_cmsg(struct sock *sk, struct msghdr *msg, unsigned char *record_type); void tls_register_device(struct tls_device *device); void tls_unregister_device(struct tls_device *device); +int decrypt_skb(struct sock *sk, struct sk_buff *skb, + struct scatterlist *sgout); struct sk_buff *tls_validate_xmit_skb(struct sock *sk, struct net_device *dev, diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 7453f5ae0819..1d2271736717 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -53,7 +53,6 @@ static int tls_do_decryption(struct sock *sk, { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); - struct strp_msg *rxm = strp_msg(skb); struct aead_request *aead_req; int ret; @@ -71,18 +70,6 @@ static int tls_do_decryption(struct sock *sk, ret = crypto_wait_req(crypto_aead_decrypt(aead_req), &ctx->async_wait); - if (ret < 0) - goto out; - - rxm->offset += tls_ctx->rx.prepend_size; - rxm->full_len -= tls_ctx->rx.overhead_size; - tls_advance_record_sn(sk, &tls_ctx->rx); - - ctx->decrypted = true; - - ctx->saved_data_ready(sk); - -out: aead_request_free(aead_req); return ret; } @@ -666,8 +653,29 @@ static struct sk_buff *tls_wait_data(struct sock *sk, int flags, return skb; } -static int decrypt_skb(struct sock *sk, struct sk_buff *skb, - struct scatterlist *sgout) +static int decrypt_skb_update(struct sock *sk, struct sk_buff *skb, + struct scatterlist *sgout) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); + struct strp_msg *rxm = strp_msg(skb); + int err = 0; + + err = decrypt_skb(sk, skb, sgout); + if (err < 0) + return err; + + rxm->offset += tls_ctx->rx.prepend_size; + rxm->full_len -= tls_ctx->rx.overhead_size; + tls_advance_record_sn(sk, &tls_ctx->rx); + ctx->decrypted = true; + ctx->saved_data_ready(sk); + + return err; +} + +int decrypt_skb(struct sock *sk, struct sk_buff *skb, + struct scatterlist *sgout) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); @@ -812,7 +820,7 @@ int tls_sw_recvmsg(struct sock *sk, if (err < 0) goto fallback_to_reg_recv; - err = decrypt_skb(sk, skb, sgin); + err = decrypt_skb_update(sk, skb, sgin); for (; pages > 0; pages--) put_page(sg_page(&sgin[pages])); if (err < 0) { @@ -821,7 +829,7 @@ int tls_sw_recvmsg(struct sock *sk, } } else { fallback_to_reg_recv: - err = decrypt_skb(sk, skb, NULL); + err = decrypt_skb_update(sk, skb, NULL); if (err < 0) { tls_err_abort(sk, EBADMSG); goto recv_end; @@ -892,7 +900,7 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, } if (!ctx->decrypted) { - err = decrypt_skb(sk, skb, NULL); + err = decrypt_skb_update(sk, skb, NULL); if (err < 0) { tls_err_abort(sk, EBADMSG); -- cgit v1.2.3 From 39f56e1a78d647316db330c3b6f4c5637a895e3b Mon Sep 17 00:00:00 2001 From: Boris Pismenny Date: Fri, 13 Jul 2018 14:33:41 +0300 Subject: tls: Split tls_sw_release_resources_rx This patch splits tls_sw_release_resources_rx into two functions one which releases all inner software tls structures and another that also frees the containing structure. In TLS_DEVICE we will need to release the software structures without freeeing the containing structure, which contains other information. Signed-off-by: Boris Pismenny Signed-off-by: David S. Miller --- include/net/tls.h | 1 + net/tls/tls_sw.c | 10 +++++++++- 2 files changed, 10 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/tls.h b/include/net/tls.h index 49b89221db43..7a485de25646 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -223,6 +223,7 @@ int tls_sw_sendpage(struct sock *sk, struct page *page, void tls_sw_close(struct sock *sk, long timeout); void tls_sw_free_resources_tx(struct sock *sk); void tls_sw_free_resources_rx(struct sock *sk); +void tls_sw_release_resources_rx(struct sock *sk); int tls_sw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len); unsigned int tls_sw_poll(struct file *file, struct socket *sock, diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 1d2271736717..694d26589dcc 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1030,7 +1030,7 @@ void tls_sw_free_resources_tx(struct sock *sk) kfree(ctx); } -void tls_sw_free_resources_rx(struct sock *sk) +void tls_sw_release_resources_rx(struct sock *sk) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); @@ -1049,6 +1049,14 @@ void tls_sw_free_resources_rx(struct sock *sk) strp_done(&ctx->strp); lock_sock(sk); } +} + +void tls_sw_free_resources_rx(struct sock *sk) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); + + tls_sw_release_resources_rx(sk); kfree(ctx); } -- cgit v1.2.3 From 4799ac81e52a72a6404827bf2738337bb581a174 Mon Sep 17 00:00:00 2001 From: Boris Pismenny Date: Fri, 13 Jul 2018 14:33:43 +0300 Subject: tls: Add rx inline crypto offload This patch completes the generic infrastructure to offload TLS crypto to a network device. It enables the kernel to skip decryption and authentication of some skbs marked as decrypted by the NIC. In the fast path, all packets received are decrypted by the NIC and the performance is comparable to plain TCP. This infrastructure doesn't require a TCP offload engine. Instead, the NIC only decrypts packets that contain the expected TCP sequence number. Out-Of-Order TCP packets are provided unmodified. As a result, at the worst case a received TLS record consists of both plaintext and ciphertext packets. These partially decrypted records must be reencrypted, only to be decrypted. The notable differences between SW KTLS Rx and this offload are as follows: 1. Partial decryption - Software must handle the case of a TLS record that was only partially decrypted by HW. This can happen due to packet reordering. 2. Resynchronization - tls_read_size calls the device driver to resynchronize HW after HW lost track of TLS record framing in the TCP stream. Signed-off-by: Boris Pismenny Signed-off-by: David S. Miller --- include/net/tls.h | 63 +++++++++- net/tls/tls_device.c | 278 ++++++++++++++++++++++++++++++++++++++---- net/tls/tls_device_fallback.c | 1 + net/tls/tls_main.c | 32 +++-- net/tls/tls_sw.c | 24 +++- 5 files changed, 355 insertions(+), 43 deletions(-) (limited to 'include') diff --git a/include/net/tls.h b/include/net/tls.h index 7a485de25646..d8b3b6578c01 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -83,6 +83,16 @@ struct tls_device { void (*unhash)(struct tls_device *device, struct sock *sk); }; +enum { + TLS_BASE, + TLS_SW, +#ifdef CONFIG_TLS_DEVICE + TLS_HW, +#endif + TLS_HW_RECORD, + TLS_NUM_CONFIG, +}; + struct tls_sw_context_tx { struct crypto_aead *aead_send; struct crypto_wait async_wait; @@ -197,6 +207,7 @@ struct tls_context { int (*push_pending_record)(struct sock *sk, int flags); void (*sk_write_space)(struct sock *sk); + void (*sk_destruct)(struct sock *sk); void (*sk_proto_close)(struct sock *sk, long timeout); int (*setsockopt)(struct sock *sk, int level, @@ -209,13 +220,27 @@ struct tls_context { void (*unhash)(struct sock *sk); }; +struct tls_offload_context_rx { + /* sw must be the first member of tls_offload_context_rx */ + struct tls_sw_context_rx sw; + atomic64_t resync_req; + u8 driver_state[]; + /* The TLS layer reserves room for driver specific state + * Currently the belief is that there is not enough + * driver specific state to justify another layer of indirection + */ +}; + +#define TLS_OFFLOAD_CONTEXT_SIZE_RX \ + (ALIGN(sizeof(struct tls_offload_context_rx), sizeof(void *)) + \ + TLS_DRIVER_STATE_SIZE) + int wait_on_pending_writer(struct sock *sk, long *timeo); int tls_sk_query(struct sock *sk, int optname, char __user *optval, int __user *optlen); int tls_sk_attach(struct sock *sk, int optname, char __user *optval, unsigned int optlen); - int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx); int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); int tls_sw_sendpage(struct sock *sk, struct page *page, @@ -290,11 +315,19 @@ static inline bool tls_is_pending_open_record(struct tls_context *tls_ctx) return tls_ctx->pending_open_record_frags; } +struct sk_buff * +tls_validate_xmit_skb(struct sock *sk, struct net_device *dev, + struct sk_buff *skb); + static inline bool tls_is_sk_tx_device_offloaded(struct sock *sk) { - return sk_fullsock(sk) && - /* matches smp_store_release in tls_set_device_offload */ - smp_load_acquire(&sk->sk_destruct) == &tls_device_sk_destruct; +#ifdef CONFIG_SOCK_VALIDATE_XMIT + return sk_fullsock(sk) & + (smp_load_acquire(&sk->sk_validate_xmit_skb) == + &tls_validate_xmit_skb); +#else + return false; +#endif } static inline void tls_err_abort(struct sock *sk, int err) @@ -387,10 +420,27 @@ tls_offload_ctx_tx(const struct tls_context *tls_ctx) return (struct tls_offload_context_tx *)tls_ctx->priv_ctx_tx; } +static inline struct tls_offload_context_rx * +tls_offload_ctx_rx(const struct tls_context *tls_ctx) +{ + return (struct tls_offload_context_rx *)tls_ctx->priv_ctx_rx; +} + +/* The TLS context is valid until sk_destruct is called */ +static inline void tls_offload_rx_resync_request(struct sock *sk, __be32 seq) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_offload_context_rx *rx_ctx = tls_offload_ctx_rx(tls_ctx); + + atomic64_set(&rx_ctx->resync_req, ((((uint64_t)seq) << 32) | 1)); +} + + int tls_proccess_cmsg(struct sock *sk, struct msghdr *msg, unsigned char *record_type); void tls_register_device(struct tls_device *device); void tls_unregister_device(struct tls_device *device); +int tls_device_decrypted(struct sock *sk, struct sk_buff *skb); int decrypt_skb(struct sock *sk, struct sk_buff *skb, struct scatterlist *sgout); @@ -402,4 +452,9 @@ int tls_sw_fallback_init(struct sock *sk, struct tls_offload_context_tx *offload_ctx, struct tls_crypto_info *crypto_info); +int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx); + +void tls_device_offload_cleanup_rx(struct sock *sk); +void handle_device_resync(struct sock *sk, u32 seq, u64 rcd_sn); + #endif /* _TLS_OFFLOAD_H */ diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 332a5d1459b6..4995d84d228d 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -52,7 +52,11 @@ static DEFINE_SPINLOCK(tls_device_lock); static void tls_device_free_ctx(struct tls_context *ctx) { - kfree(tls_offload_ctx_tx(ctx)); + if (ctx->tx_conf == TLS_HW) + kfree(tls_offload_ctx_tx(ctx)); + + if (ctx->rx_conf == TLS_HW) + kfree(tls_offload_ctx_rx(ctx)); kfree(ctx); } @@ -70,10 +74,11 @@ static void tls_device_gc_task(struct work_struct *work) list_for_each_entry_safe(ctx, tmp, &gc_list, list) { struct net_device *netdev = ctx->netdev; - if (netdev) { + if (netdev && ctx->tx_conf == TLS_HW) { netdev->tlsdev_ops->tls_dev_del(netdev, ctx, TLS_OFFLOAD_CTX_DIR_TX); dev_put(netdev); + ctx->netdev = NULL; } list_del(&ctx->list); @@ -81,6 +86,22 @@ static void tls_device_gc_task(struct work_struct *work) } } +static void tls_device_attach(struct tls_context *ctx, struct sock *sk, + struct net_device *netdev) +{ + if (sk->sk_destruct != tls_device_sk_destruct) { + refcount_set(&ctx->refcount, 1); + dev_hold(netdev); + ctx->netdev = netdev; + spin_lock_irq(&tls_device_lock); + list_add_tail(&ctx->list, &tls_device_list); + spin_unlock_irq(&tls_device_lock); + + ctx->sk_destruct = sk->sk_destruct; + sk->sk_destruct = tls_device_sk_destruct; + } +} + static void tls_device_queue_ctx_destruction(struct tls_context *ctx) { unsigned long flags; @@ -180,13 +201,15 @@ void tls_device_sk_destruct(struct sock *sk) struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_offload_context_tx *ctx = tls_offload_ctx_tx(tls_ctx); - if (ctx->open_record) - destroy_record(ctx->open_record); + tls_ctx->sk_destruct(sk); - delete_all_records(ctx); - crypto_free_aead(ctx->aead_send); - ctx->sk_destruct(sk); - clean_acked_data_disable(inet_csk(sk)); + if (tls_ctx->tx_conf == TLS_HW) { + if (ctx->open_record) + destroy_record(ctx->open_record); + delete_all_records(ctx); + crypto_free_aead(ctx->aead_send); + clean_acked_data_disable(inet_csk(sk)); + } if (refcount_dec_and_test(&tls_ctx->refcount)) tls_device_queue_ctx_destruction(tls_ctx); @@ -519,6 +542,118 @@ static int tls_device_push_pending_record(struct sock *sk, int flags) return tls_push_data(sk, &msg_iter, 0, flags, TLS_RECORD_TYPE_DATA); } +void handle_device_resync(struct sock *sk, u32 seq, u64 rcd_sn) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct net_device *netdev = tls_ctx->netdev; + struct tls_offload_context_rx *rx_ctx; + u32 is_req_pending; + s64 resync_req; + u32 req_seq; + + if (tls_ctx->rx_conf != TLS_HW) + return; + + rx_ctx = tls_offload_ctx_rx(tls_ctx); + resync_req = atomic64_read(&rx_ctx->resync_req); + req_seq = ntohl(resync_req >> 32) - ((u32)TLS_HEADER_SIZE - 1); + is_req_pending = resync_req; + + if (unlikely(is_req_pending) && req_seq == seq && + atomic64_try_cmpxchg(&rx_ctx->resync_req, &resync_req, 0)) + netdev->tlsdev_ops->tls_dev_resync_rx(netdev, sk, + seq + TLS_HEADER_SIZE - 1, + rcd_sn); +} + +static int tls_device_reencrypt(struct sock *sk, struct sk_buff *skb) +{ + struct strp_msg *rxm = strp_msg(skb); + int err = 0, offset = rxm->offset, copy, nsg; + struct sk_buff *skb_iter, *unused; + struct scatterlist sg[1]; + char *orig_buf, *buf; + + orig_buf = kmalloc(rxm->full_len + TLS_HEADER_SIZE + + TLS_CIPHER_AES_GCM_128_IV_SIZE, sk->sk_allocation); + if (!orig_buf) + return -ENOMEM; + buf = orig_buf; + + nsg = skb_cow_data(skb, 0, &unused); + if (unlikely(nsg < 0)) { + err = nsg; + goto free_buf; + } + + sg_init_table(sg, 1); + sg_set_buf(&sg[0], buf, + rxm->full_len + TLS_HEADER_SIZE + + TLS_CIPHER_AES_GCM_128_IV_SIZE); + skb_copy_bits(skb, offset, buf, + TLS_HEADER_SIZE + TLS_CIPHER_AES_GCM_128_IV_SIZE); + + /* We are interested only in the decrypted data not the auth */ + err = decrypt_skb(sk, skb, sg); + if (err != -EBADMSG) + goto free_buf; + else + err = 0; + + copy = min_t(int, skb_pagelen(skb) - offset, + rxm->full_len - TLS_CIPHER_AES_GCM_128_TAG_SIZE); + + if (skb->decrypted) + skb_store_bits(skb, offset, buf, copy); + + offset += copy; + buf += copy; + + skb_walk_frags(skb, skb_iter) { + copy = min_t(int, skb_iter->len, + rxm->full_len - offset + rxm->offset - + TLS_CIPHER_AES_GCM_128_TAG_SIZE); + + if (skb_iter->decrypted) + skb_store_bits(skb, offset, buf, copy); + + offset += copy; + buf += copy; + } + +free_buf: + kfree(orig_buf); + return err; +} + +int tls_device_decrypted(struct sock *sk, struct sk_buff *skb) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_offload_context_rx *ctx = tls_offload_ctx_rx(tls_ctx); + int is_decrypted = skb->decrypted; + int is_encrypted = !is_decrypted; + struct sk_buff *skb_iter; + + /* Skip if it is already decrypted */ + if (ctx->sw.decrypted) + return 0; + + /* Check if all the data is decrypted already */ + skb_walk_frags(skb, skb_iter) { + is_decrypted &= skb_iter->decrypted; + is_encrypted &= !skb_iter->decrypted; + } + + ctx->sw.decrypted |= is_decrypted; + + /* Return immedeatly if the record is either entirely plaintext or + * entirely ciphertext. Otherwise handle reencrypt partially decrypted + * record. + */ + return (is_encrypted || is_decrypted) ? 0 : + tls_device_reencrypt(sk, skb); +} + int tls_set_device_offload(struct sock *sk, struct tls_context *ctx) { u16 nonce_size, tag_size, iv_size, rec_seq_size; @@ -608,7 +743,6 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx) clean_acked_data_enable(inet_csk(sk), &tls_icsk_clean_acked); ctx->push_pending_record = tls_device_push_pending_record; - offload_ctx->sk_destruct = sk->sk_destruct; /* TLS offload is greatly simplified if we don't send * SKBs where only part of the payload needs to be encrypted. @@ -618,8 +752,6 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx) if (skb) TCP_SKB_CB(skb)->eor = 1; - refcount_set(&ctx->refcount, 1); - /* We support starting offload on multiple sockets * concurrently, so we only need a read lock here. * This lock must precede get_netdev_for_sock to prevent races between @@ -654,19 +786,14 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx) if (rc) goto release_netdev; - ctx->netdev = netdev; + tls_device_attach(ctx, sk, netdev); - spin_lock_irq(&tls_device_lock); - list_add_tail(&ctx->list, &tls_device_list); - spin_unlock_irq(&tls_device_lock); - - sk->sk_validate_xmit_skb = tls_validate_xmit_skb; /* following this assignment tls_is_sk_tx_device_offloaded * will return true and the context might be accessed * by the netdev's xmit function. */ - smp_store_release(&sk->sk_destruct, - &tls_device_sk_destruct); + smp_store_release(&sk->sk_validate_xmit_skb, tls_validate_xmit_skb); + dev_put(netdev); up_read(&device_offload_lock); goto out; @@ -689,6 +816,105 @@ out: return rc; } +int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx) +{ + struct tls_offload_context_rx *context; + struct net_device *netdev; + int rc = 0; + + /* We support starting offload on multiple sockets + * concurrently, so we only need a read lock here. + * This lock must precede get_netdev_for_sock to prevent races between + * NETDEV_DOWN and setsockopt. + */ + down_read(&device_offload_lock); + netdev = get_netdev_for_sock(sk); + if (!netdev) { + pr_err_ratelimited("%s: netdev not found\n", __func__); + rc = -EINVAL; + goto release_lock; + } + + if (!(netdev->features & NETIF_F_HW_TLS_RX)) { + pr_err_ratelimited("%s: netdev %s with no TLS offload\n", + __func__, netdev->name); + rc = -ENOTSUPP; + goto release_netdev; + } + + /* Avoid offloading if the device is down + * We don't want to offload new flows after + * the NETDEV_DOWN event + */ + if (!(netdev->flags & IFF_UP)) { + rc = -EINVAL; + goto release_netdev; + } + + context = kzalloc(TLS_OFFLOAD_CONTEXT_SIZE_RX, GFP_KERNEL); + if (!context) { + rc = -ENOMEM; + goto release_netdev; + } + + ctx->priv_ctx_rx = context; + rc = tls_set_sw_offload(sk, ctx, 0); + if (rc) + goto release_ctx; + + rc = netdev->tlsdev_ops->tls_dev_add(netdev, sk, TLS_OFFLOAD_CTX_DIR_RX, + &ctx->crypto_recv, + tcp_sk(sk)->copied_seq); + if (rc) { + pr_err_ratelimited("%s: The netdev has refused to offload this socket\n", + __func__); + goto free_sw_resources; + } + + tls_device_attach(ctx, sk, netdev); + goto release_netdev; + +free_sw_resources: + tls_sw_free_resources_rx(sk); +release_ctx: + ctx->priv_ctx_rx = NULL; +release_netdev: + dev_put(netdev); +release_lock: + up_read(&device_offload_lock); + return rc; +} + +void tls_device_offload_cleanup_rx(struct sock *sk) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct net_device *netdev; + + down_read(&device_offload_lock); + netdev = tls_ctx->netdev; + if (!netdev) + goto out; + + if (!(netdev->features & NETIF_F_HW_TLS_RX)) { + pr_err_ratelimited("%s: device is missing NETIF_F_HW_TLS_RX cap\n", + __func__); + goto out; + } + + netdev->tlsdev_ops->tls_dev_del(netdev, tls_ctx, + TLS_OFFLOAD_CTX_DIR_RX); + + if (tls_ctx->tx_conf != TLS_HW) { + dev_put(netdev); + tls_ctx->netdev = NULL; + } +out: + up_read(&device_offload_lock); + kfree(tls_ctx->rx.rec_seq); + kfree(tls_ctx->rx.iv); + tls_sw_release_resources_rx(sk); +} + static int tls_device_down(struct net_device *netdev) { struct tls_context *ctx, *tmp; @@ -709,8 +935,12 @@ static int tls_device_down(struct net_device *netdev) spin_unlock_irqrestore(&tls_device_lock, flags); list_for_each_entry_safe(ctx, tmp, &list, list) { - netdev->tlsdev_ops->tls_dev_del(netdev, ctx, - TLS_OFFLOAD_CTX_DIR_TX); + if (ctx->tx_conf == TLS_HW) + netdev->tlsdev_ops->tls_dev_del(netdev, ctx, + TLS_OFFLOAD_CTX_DIR_TX); + if (ctx->rx_conf == TLS_HW) + netdev->tlsdev_ops->tls_dev_del(netdev, ctx, + TLS_OFFLOAD_CTX_DIR_RX); ctx->netdev = NULL; dev_put(netdev); list_del_init(&ctx->list); @@ -731,12 +961,16 @@ static int tls_dev_event(struct notifier_block *this, unsigned long event, { struct net_device *dev = netdev_notifier_info_to_dev(ptr); - if (!(dev->features & NETIF_F_HW_TLS_TX)) + if (!(dev->features & (NETIF_F_HW_TLS_RX | NETIF_F_HW_TLS_TX))) return NOTIFY_DONE; switch (event) { case NETDEV_REGISTER: case NETDEV_FEAT_CHANGE: + if ((dev->features & NETIF_F_HW_TLS_RX) && + !dev->tlsdev_ops->tls_dev_resync_rx) + return NOTIFY_BAD; + if (dev->tlsdev_ops && dev->tlsdev_ops->tls_dev_add && dev->tlsdev_ops->tls_dev_del) diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c index d1d7dce38e0b..e3313c45663f 100644 --- a/net/tls/tls_device_fallback.c +++ b/net/tls/tls_device_fallback.c @@ -413,6 +413,7 @@ struct sk_buff *tls_validate_xmit_skb(struct sock *sk, return tls_sw_fallback(sk, skb); } +EXPORT_SYMBOL_GPL(tls_validate_xmit_skb); int tls_sw_fallback_init(struct sock *sk, struct tls_offload_context_tx *offload_ctx, diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 301f22430469..b09867c8b817 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -51,15 +51,6 @@ enum { TLSV6, TLS_NUM_PROTS, }; -enum { - TLS_BASE, - TLS_SW, -#ifdef CONFIG_TLS_DEVICE - TLS_HW, -#endif - TLS_HW_RECORD, - TLS_NUM_CONFIG, -}; static struct proto *saved_tcpv6_prot; static DEFINE_MUTEX(tcpv6_prot_mutex); @@ -290,7 +281,10 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) } #ifdef CONFIG_TLS_DEVICE - if (ctx->tx_conf != TLS_HW) { + if (ctx->rx_conf == TLS_HW) + tls_device_offload_cleanup_rx(sk); + + if (ctx->tx_conf != TLS_HW && ctx->rx_conf != TLS_HW) { #else { #endif @@ -470,8 +464,16 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval, conf = TLS_SW; } } else { - rc = tls_set_sw_offload(sk, ctx, 0); - conf = TLS_SW; +#ifdef CONFIG_TLS_DEVICE + rc = tls_set_device_offload_rx(sk, ctx); + conf = TLS_HW; + if (rc) { +#else + { +#endif + rc = tls_set_sw_offload(sk, ctx, 0); + conf = TLS_SW; + } } if (rc) @@ -629,6 +631,12 @@ static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG], prot[TLS_HW][TLS_SW] = prot[TLS_BASE][TLS_SW]; prot[TLS_HW][TLS_SW].sendmsg = tls_device_sendmsg; prot[TLS_HW][TLS_SW].sendpage = tls_device_sendpage; + + prot[TLS_BASE][TLS_HW] = prot[TLS_BASE][TLS_SW]; + + prot[TLS_SW][TLS_HW] = prot[TLS_SW][TLS_SW]; + + prot[TLS_HW][TLS_HW] = prot[TLS_HW][TLS_SW]; #endif prot[TLS_HW_RECORD][TLS_HW_RECORD] = *base; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 5f7d70b24be6..fe5735c57774 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -654,16 +654,25 @@ static struct sk_buff *tls_wait_data(struct sock *sk, int flags, } static int decrypt_skb_update(struct sock *sk, struct sk_buff *skb, - struct scatterlist *sgout) + struct scatterlist *sgout, bool *zc) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); struct strp_msg *rxm = strp_msg(skb); int err = 0; - err = decrypt_skb(sk, skb, sgout); +#ifdef CONFIG_TLS_DEVICE + err = tls_device_decrypted(sk, skb); if (err < 0) return err; +#endif + if (!ctx->decrypted) { + err = decrypt_skb(sk, skb, sgout); + if (err < 0) + return err; + } else { + *zc = false; + } rxm->offset += tls_ctx->rx.prepend_size; rxm->full_len -= tls_ctx->rx.overhead_size; @@ -820,7 +829,7 @@ int tls_sw_recvmsg(struct sock *sk, if (err < 0) goto fallback_to_reg_recv; - err = decrypt_skb_update(sk, skb, sgin); + err = decrypt_skb_update(sk, skb, sgin, &zc); for (; pages > 0; pages--) put_page(sg_page(&sgin[pages])); if (err < 0) { @@ -829,7 +838,7 @@ int tls_sw_recvmsg(struct sock *sk, } } else { fallback_to_reg_recv: - err = decrypt_skb_update(sk, skb, NULL); + err = decrypt_skb_update(sk, skb, NULL, &zc); if (err < 0) { tls_err_abort(sk, EBADMSG); goto recv_end; @@ -884,6 +893,7 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, int err = 0; long timeo; int chunk; + bool zc; lock_sock(sk); @@ -900,7 +910,7 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, } if (!ctx->decrypted) { - err = decrypt_skb_update(sk, skb, NULL); + err = decrypt_skb_update(sk, skb, NULL, &zc); if (err < 0) { tls_err_abort(sk, EBADMSG); @@ -989,6 +999,10 @@ static int tls_read_size(struct strparser *strp, struct sk_buff *skb) goto read_failure; } +#ifdef CONFIG_TLS_DEVICE + handle_device_resync(strp->sk, TCP_SKB_CB(skb)->seq + rxm->offset, + *(u64*)tls_ctx->rx.rec_seq); +#endif return data_len + TLS_HEADER_SIZE; read_failure: -- cgit v1.2.3 From ab412e1dd7db132c2abeb9385b4bf0dc8e6c5a65 Mon Sep 17 00:00:00 2001 From: Boris Pismenny Date: Fri, 13 Jul 2018 14:33:46 +0300 Subject: net/mlx5: Accel, add TLS rx offload routines In Innova TLS, TLS contexts are added or deleted via a command message over the SBU connection. The HW then sends a response message over the same connection. Complete the implementation for Innova TLS (FPGA-based) hardware by adding support for rx inline crypto offload. Signed-off-by: Boris Pismenny Signed-off-by: Ilya Lesokhin Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlx5/core/accel/tls.c | 23 +++-- .../net/ethernet/mellanox/mlx5/core/accel/tls.h | 26 +++-- drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c | 113 ++++++++++++++++----- drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.h | 18 ++-- include/linux/mlx5/mlx5_ifc_fpga.h | 1 + 5 files changed, 135 insertions(+), 46 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.c index 77ac19f38cbe..da7bd26368f9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.c @@ -37,17 +37,26 @@ #include "mlx5_core.h" #include "fpga/tls.h" -int mlx5_accel_tls_add_tx_flow(struct mlx5_core_dev *mdev, void *flow, - struct tls_crypto_info *crypto_info, - u32 start_offload_tcp_sn, u32 *p_swid) +int mlx5_accel_tls_add_flow(struct mlx5_core_dev *mdev, void *flow, + struct tls_crypto_info *crypto_info, + u32 start_offload_tcp_sn, u32 *p_swid, + bool direction_sx) { - return mlx5_fpga_tls_add_tx_flow(mdev, flow, crypto_info, - start_offload_tcp_sn, p_swid); + return mlx5_fpga_tls_add_flow(mdev, flow, crypto_info, + start_offload_tcp_sn, p_swid, + direction_sx); } -void mlx5_accel_tls_del_tx_flow(struct mlx5_core_dev *mdev, u32 swid) +void mlx5_accel_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid, + bool direction_sx) { - mlx5_fpga_tls_del_tx_flow(mdev, swid, GFP_KERNEL); + mlx5_fpga_tls_del_flow(mdev, swid, GFP_KERNEL, direction_sx); +} + +int mlx5_accel_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq, + u64 rcd_sn) +{ + return mlx5_fpga_tls_resync_rx(mdev, handle, seq, rcd_sn); } bool mlx5_accel_is_tls_device(struct mlx5_core_dev *mdev) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h index 6f9c9f446ecc..2228c1083528 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h @@ -60,10 +60,14 @@ struct mlx5_ifc_tls_flow_bits { u8 reserved_at_2[0x1e]; }; -int mlx5_accel_tls_add_tx_flow(struct mlx5_core_dev *mdev, void *flow, - struct tls_crypto_info *crypto_info, - u32 start_offload_tcp_sn, u32 *p_swid); -void mlx5_accel_tls_del_tx_flow(struct mlx5_core_dev *mdev, u32 swid); +int mlx5_accel_tls_add_flow(struct mlx5_core_dev *mdev, void *flow, + struct tls_crypto_info *crypto_info, + u32 start_offload_tcp_sn, u32 *p_swid, + bool direction_sx); +void mlx5_accel_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid, + bool direction_sx); +int mlx5_accel_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq, + u64 rcd_sn); bool mlx5_accel_is_tls_device(struct mlx5_core_dev *mdev); u32 mlx5_accel_tls_device_caps(struct mlx5_core_dev *mdev); int mlx5_accel_tls_init(struct mlx5_core_dev *mdev); @@ -71,11 +75,15 @@ void mlx5_accel_tls_cleanup(struct mlx5_core_dev *mdev); #else -static inline int -mlx5_accel_tls_add_tx_flow(struct mlx5_core_dev *mdev, void *flow, - struct tls_crypto_info *crypto_info, - u32 start_offload_tcp_sn, u32 *p_swid) { return 0; } -static inline void mlx5_accel_tls_del_tx_flow(struct mlx5_core_dev *mdev, u32 swid) { } +static int +mlx5_accel_tls_add_flow(struct mlx5_core_dev *mdev, void *flow, + struct tls_crypto_info *crypto_info, + u32 start_offload_tcp_sn, u32 *p_swid, + bool direction_sx) { return -ENOTSUPP; } +static inline void mlx5_accel_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid, + bool direction_sx) { } +static inline int mlx5_accel_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, + u32 seq, u64 rcd_sn) { return 0; } static inline bool mlx5_accel_is_tls_device(struct mlx5_core_dev *mdev) { return false; } static inline u32 mlx5_accel_tls_device_caps(struct mlx5_core_dev *mdev) { return 0; } static inline int mlx5_accel_tls_init(struct mlx5_core_dev *mdev) { return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c index c9736238604a..5cf5f2a9d51f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c @@ -129,6 +129,7 @@ static void mlx5_fpga_tls_cmd_send(struct mlx5_fpga_device *fdev, static int mlx5_fpga_tls_alloc_swid(struct idr *idr, spinlock_t *idr_spinlock, void *ptr) { + unsigned long flags; int ret; /* TLS metadata format is 1 byte for syndrome followed @@ -139,9 +140,9 @@ static int mlx5_fpga_tls_alloc_swid(struct idr *idr, spinlock_t *idr_spinlock, BUILD_BUG_ON((SWID_END - 1) & 0xFF000000); idr_preload(GFP_KERNEL); - spin_lock_irq(idr_spinlock); + spin_lock_irqsave(idr_spinlock, flags); ret = idr_alloc(idr, ptr, SWID_START, SWID_END, GFP_ATOMIC); - spin_unlock_irq(idr_spinlock); + spin_unlock_irqrestore(idr_spinlock, flags); idr_preload_end(); return ret; @@ -157,6 +158,13 @@ static void mlx5_fpga_tls_release_swid(struct idr *idr, spin_unlock_irqrestore(idr_spinlock, flags); } +static void mlx_tls_kfree_complete(struct mlx5_fpga_conn *conn, + struct mlx5_fpga_device *fdev, + struct mlx5_fpga_dma_buf *buf, u8 status) +{ + kfree(buf); +} + struct mlx5_teardown_stream_context { struct mlx5_fpga_tls_command_context cmd; u32 swid; @@ -178,9 +186,13 @@ mlx5_fpga_tls_teardown_completion(struct mlx5_fpga_conn *conn, mlx5_fpga_err(fdev, "Teardown stream failed with syndrome = %d", syndrome); - else + else if (MLX5_GET(tls_cmd, cmd->buf.sg[0].data, direction_sx)) mlx5_fpga_tls_release_swid(&fdev->tls->tx_idr, - &fdev->tls->idr_spinlock, + &fdev->tls->tx_idr_spinlock, + ctx->swid); + else + mlx5_fpga_tls_release_swid(&fdev->tls->rx_idr, + &fdev->tls->rx_idr_spinlock, ctx->swid); } mlx5_fpga_tls_put_command_ctx(cmd); @@ -196,6 +208,40 @@ static void mlx5_fpga_tls_flow_to_cmd(void *flow, void *cmd) MLX5_GET(tls_flow, flow, direction_sx)); } +int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq, + u64 rcd_sn) +{ + struct mlx5_fpga_dma_buf *buf; + int size = sizeof(*buf) + MLX5_TLS_COMMAND_SIZE; + void *flow; + void *cmd; + int ret; + + buf = kzalloc(size, GFP_ATOMIC); + if (!buf) + return -ENOMEM; + + cmd = (buf + 1); + + rcu_read_lock(); + flow = idr_find(&mdev->fpga->tls->rx_idr, ntohl(handle)); + rcu_read_unlock(); + mlx5_fpga_tls_flow_to_cmd(flow, cmd); + + MLX5_SET(tls_cmd, cmd, swid, ntohl(handle)); + MLX5_SET64(tls_cmd, cmd, tls_rcd_sn, be64_to_cpu(rcd_sn)); + MLX5_SET(tls_cmd, cmd, tcp_sn, seq); + MLX5_SET(tls_cmd, cmd, command_type, CMD_RESYNC_RX); + + buf->sg[0].data = cmd; + buf->sg[0].size = MLX5_TLS_COMMAND_SIZE; + buf->complete = mlx_tls_kfree_complete; + + ret = mlx5_fpga_sbu_conn_sendmsg(mdev->fpga->tls->conn, buf); + + return ret; +} + static void mlx5_fpga_tls_send_teardown_cmd(struct mlx5_core_dev *mdev, void *flow, u32 swid, gfp_t flags) { @@ -223,14 +269,18 @@ static void mlx5_fpga_tls_send_teardown_cmd(struct mlx5_core_dev *mdev, mlx5_fpga_tls_teardown_completion); } -void mlx5_fpga_tls_del_tx_flow(struct mlx5_core_dev *mdev, u32 swid, - gfp_t flags) +void mlx5_fpga_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid, + gfp_t flags, bool direction_sx) { struct mlx5_fpga_tls *tls = mdev->fpga->tls; void *flow; rcu_read_lock(); - flow = idr_find(&tls->tx_idr, swid); + if (direction_sx) + flow = idr_find(&tls->tx_idr, swid); + else + flow = idr_find(&tls->rx_idr, swid); + rcu_read_unlock(); if (!flow) { @@ -289,9 +339,11 @@ mlx5_fpga_tls_setup_completion(struct mlx5_fpga_conn *conn, * the command context because we might not have received * the tx completion yet. */ - mlx5_fpga_tls_del_tx_flow(fdev->mdev, - MLX5_GET(tls_cmd, tls_cmd, swid), - GFP_ATOMIC); + mlx5_fpga_tls_del_flow(fdev->mdev, + MLX5_GET(tls_cmd, tls_cmd, swid), + GFP_ATOMIC, + MLX5_GET(tls_cmd, tls_cmd, + direction_sx)); } mlx5_fpga_tls_put_command_ctx(cmd); @@ -415,8 +467,7 @@ int mlx5_fpga_tls_init(struct mlx5_core_dev *mdev) if (err) goto error; - if (!(tls->caps & (MLX5_ACCEL_TLS_TX | MLX5_ACCEL_TLS_V12 | - MLX5_ACCEL_TLS_AES_GCM128))) { + if (!(tls->caps & (MLX5_ACCEL_TLS_V12 | MLX5_ACCEL_TLS_AES_GCM128))) { err = -ENOTSUPP; goto error; } @@ -438,7 +489,9 @@ int mlx5_fpga_tls_init(struct mlx5_core_dev *mdev) INIT_LIST_HEAD(&tls->pending_cmds); idr_init(&tls->tx_idr); - spin_lock_init(&tls->idr_spinlock); + idr_init(&tls->rx_idr); + spin_lock_init(&tls->tx_idr_spinlock); + spin_lock_init(&tls->rx_idr_spinlock); fdev->tls = tls; return 0; @@ -500,9 +553,9 @@ static int mlx5_fpga_tls_set_key_material(void *cmd, u32 caps, return 0; } -static int mlx5_fpga_tls_add_flow(struct mlx5_core_dev *mdev, void *flow, - struct tls_crypto_info *crypto_info, u32 swid, - u32 tcp_sn) +static int _mlx5_fpga_tls_add_flow(struct mlx5_core_dev *mdev, void *flow, + struct tls_crypto_info *crypto_info, + u32 swid, u32 tcp_sn) { u32 caps = mlx5_fpga_tls_device_caps(mdev); struct mlx5_setup_stream_context *ctx; @@ -533,30 +586,42 @@ out: return ret; } -int mlx5_fpga_tls_add_tx_flow(struct mlx5_core_dev *mdev, void *flow, - struct tls_crypto_info *crypto_info, - u32 start_offload_tcp_sn, u32 *p_swid) +int mlx5_fpga_tls_add_flow(struct mlx5_core_dev *mdev, void *flow, + struct tls_crypto_info *crypto_info, + u32 start_offload_tcp_sn, u32 *p_swid, + bool direction_sx) { struct mlx5_fpga_tls *tls = mdev->fpga->tls; int ret = -ENOMEM; u32 swid; - ret = mlx5_fpga_tls_alloc_swid(&tls->tx_idr, &tls->idr_spinlock, flow); + if (direction_sx) + ret = mlx5_fpga_tls_alloc_swid(&tls->tx_idr, + &tls->tx_idr_spinlock, flow); + else + ret = mlx5_fpga_tls_alloc_swid(&tls->rx_idr, + &tls->rx_idr_spinlock, flow); + if (ret < 0) return ret; swid = ret; - MLX5_SET(tls_flow, flow, direction_sx, 1); + MLX5_SET(tls_flow, flow, direction_sx, direction_sx ? 1 : 0); - ret = mlx5_fpga_tls_add_flow(mdev, flow, crypto_info, swid, - start_offload_tcp_sn); + ret = _mlx5_fpga_tls_add_flow(mdev, flow, crypto_info, swid, + start_offload_tcp_sn); if (ret && ret != -EINTR) goto free_swid; *p_swid = swid; return 0; free_swid: - mlx5_fpga_tls_release_swid(&tls->tx_idr, &tls->idr_spinlock, swid); + if (direction_sx) + mlx5_fpga_tls_release_swid(&tls->tx_idr, + &tls->tx_idr_spinlock, swid); + else + mlx5_fpga_tls_release_swid(&tls->rx_idr, + &tls->rx_idr_spinlock, swid); return ret; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.h b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.h index 800a214e4e49..3b2e37bf76fe 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.h @@ -46,15 +46,18 @@ struct mlx5_fpga_tls { struct mlx5_fpga_conn *conn; struct idr tx_idr; - spinlock_t idr_spinlock; /* protects the IDR */ + struct idr rx_idr; + spinlock_t tx_idr_spinlock; /* protects the IDR */ + spinlock_t rx_idr_spinlock; /* protects the IDR */ }; -int mlx5_fpga_tls_add_tx_flow(struct mlx5_core_dev *mdev, void *flow, - struct tls_crypto_info *crypto_info, - u32 start_offload_tcp_sn, u32 *p_swid); +int mlx5_fpga_tls_add_flow(struct mlx5_core_dev *mdev, void *flow, + struct tls_crypto_info *crypto_info, + u32 start_offload_tcp_sn, u32 *p_swid, + bool direction_sx); -void mlx5_fpga_tls_del_tx_flow(struct mlx5_core_dev *mdev, u32 swid, - gfp_t flags); +void mlx5_fpga_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid, + gfp_t flags, bool direction_sx); bool mlx5_fpga_is_tls_device(struct mlx5_core_dev *mdev); int mlx5_fpga_tls_init(struct mlx5_core_dev *mdev); @@ -65,4 +68,7 @@ static inline u32 mlx5_fpga_tls_device_caps(struct mlx5_core_dev *mdev) return mdev->fpga->tls->caps; } +int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq, + u64 rcd_sn); + #endif /* __MLX5_FPGA_TLS_H__ */ diff --git a/include/linux/mlx5/mlx5_ifc_fpga.h b/include/linux/mlx5/mlx5_ifc_fpga.h index 64d0f40d4cc3..37e065a80a43 100644 --- a/include/linux/mlx5/mlx5_ifc_fpga.h +++ b/include/linux/mlx5/mlx5_ifc_fpga.h @@ -576,6 +576,7 @@ struct mlx5_ifc_fpga_ipsec_sa { enum fpga_tls_cmds { CMD_SETUP_STREAM = 0x1001, CMD_TEARDOWN_STREAM = 0x1002, + CMD_RESYNC_RX = 0x1003, }; #define MLX5_TLS_1_2 (0) -- cgit v1.2.3 From ff10e353a4c0c83a28c89c182462b3c8dc7f70cc Mon Sep 17 00:00:00 2001 From: Ludovic Desroches Date: Fri, 29 Jun 2018 10:15:33 +0200 Subject: pinctrl: at91-pio4: add support for drive strength Add support for the drive strength configuration. Usually, this value is expressed in mA. Since the numeric value depends on VDDIOP voltage, a value we can't retrieve at runtime, the controller uses low, medium and high to define the drive strength. The PIO controller accepts two values for the low drive configuration: 0 and 1. Most of the time, we don't care about the drive strength. So we keep the default value which is 0. The drive strength is advertised through the sysfs only when it has been explicitly set in the device tree i.e. if its value is different from 0. Signed-off-by: Ludovic Desroches Acked-by: Rob Herring Signed-off-by: Linus Walleij --- .../bindings/pinctrl/atmel,at91-pio4-pinctrl.txt | 3 ++ drivers/pinctrl/pinctrl-at91-pio4.c | 42 ++++++++++++++++++++++ include/dt-bindings/pinctrl/at91.h | 4 +++ 3 files changed, 49 insertions(+) (limited to 'include') diff --git a/Documentation/devicetree/bindings/pinctrl/atmel,at91-pio4-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/atmel,at91-pio4-pinctrl.txt index 61ac75706cc9..04d16fb69eb7 100644 --- a/Documentation/devicetree/bindings/pinctrl/atmel,at91-pio4-pinctrl.txt +++ b/Documentation/devicetree/bindings/pinctrl/atmel,at91-pio4-pinctrl.txt @@ -36,6 +36,8 @@ Optional properties: - GENERIC_PINCONFIG: generic pinconfig options to use, bias-disable, bias-pull-down, bias-pull-up, drive-open-drain, input-schmitt-enable, input-debounce, output-low, output-high. +- atmel,drive-strength: 0 or 1 for low drive, 2 for medium drive and 3 for +high drive. The default value is low drive. Example: @@ -66,6 +68,7 @@ Example: pinmux = , ; bias-pull-up; + atmel,drive-strength = ; }; pinctrl_sdmmc1_default: sdmmc1_default { diff --git a/drivers/pinctrl/pinctrl-at91-pio4.c b/drivers/pinctrl/pinctrl-at91-pio4.c index 67e4d9ffa6b1..8f061971a7d1 100644 --- a/drivers/pinctrl/pinctrl-at91-pio4.c +++ b/drivers/pinctrl/pinctrl-at91-pio4.c @@ -14,6 +14,7 @@ * GNU General Public License for more details. */ +#include #include #include /* FIXME: needed for gpio_to_irq(), get rid of this */ @@ -49,6 +50,8 @@ #define ATMEL_PIO_IFSCEN_MASK BIT(13) #define ATMEL_PIO_OPD_MASK BIT(14) #define ATMEL_PIO_SCHMITT_MASK BIT(15) +#define ATMEL_PIO_DRVSTR_MASK GENMASK(17, 16) +#define ATMEL_PIO_DRVSTR_OFFSET 16 #define ATMEL_PIO_CFGR_EVTSEL_MASK GENMASK(26, 24) #define ATMEL_PIO_CFGR_EVTSEL_FALLING (0 << 24) #define ATMEL_PIO_CFGR_EVTSEL_RISING (1 << 24) @@ -75,6 +78,9 @@ #define ATMEL_GET_PIN_FUNC(pinfunc) ((pinfunc >> 16) & 0xf) #define ATMEL_GET_PIN_IOSET(pinfunc) ((pinfunc >> 20) & 0xf) +/* Custom pinconf parameters */ +#define ATMEL_PIN_CONFIG_DRIVE_STRENGTH (PIN_CONFIG_END + 1) + struct atmel_pioctrl_data { unsigned nbanks; }; @@ -139,6 +145,10 @@ static const char * const atmel_functions[] = { "GPIO", "A", "B", "C", "D", "E", "F", "G" }; +static const struct pinconf_generic_params atmel_custom_bindings[] = { + {"atmel,drive-strength", ATMEL_PIN_CONFIG_DRIVE_STRENGTH, 0}, +}; + /* --- GPIO --- */ static unsigned int atmel_gpio_read(struct atmel_pioctrl *atmel_pioctrl, unsigned int bank, unsigned int reg) @@ -692,6 +702,11 @@ static int atmel_conf_pin_config_group_get(struct pinctrl_dev *pctldev, return -EINVAL; arg = 1; break; + case ATMEL_PIN_CONFIG_DRIVE_STRENGTH: + if (!(res & ATMEL_PIO_DRVSTR_MASK)) + return -EINVAL; + arg = (res & ATMEL_PIO_DRVSTR_MASK) >> ATMEL_PIO_DRVSTR_OFFSET; + break; default: return -ENOTSUPP; } @@ -777,6 +792,18 @@ static int atmel_conf_pin_config_group_set(struct pinctrl_dev *pctldev, ATMEL_PIO_SODR); } break; + case ATMEL_PIN_CONFIG_DRIVE_STRENGTH: + switch (arg) { + case ATMEL_PIO_DRVSTR_LO: + case ATMEL_PIO_DRVSTR_ME: + case ATMEL_PIO_DRVSTR_HI: + conf &= (~ATMEL_PIO_DRVSTR_MASK); + conf |= arg << ATMEL_PIO_DRVSTR_OFFSET; + break; + default: + dev_warn(pctldev->dev, "drive strength not updated (incorrect value)\n"); + } + break; default: dev_warn(pctldev->dev, "unsupported configuration parameter: %u\n", @@ -816,6 +843,19 @@ static void atmel_conf_pin_config_dbg_show(struct pinctrl_dev *pctldev, seq_printf(s, "%s ", "open-drain"); if (conf & ATMEL_PIO_SCHMITT_MASK) seq_printf(s, "%s ", "schmitt"); + if (conf & ATMEL_PIO_DRVSTR_MASK) { + switch ((conf & ATMEL_PIO_DRVSTR_MASK) >> ATMEL_PIO_DRVSTR_OFFSET) { + case ATMEL_PIO_DRVSTR_ME: + seq_printf(s, "%s ", "medium-drive"); + break; + case ATMEL_PIO_DRVSTR_HI: + seq_printf(s, "%s ", "high-drive"); + break; + /* ATMEL_PIO_DRVSTR_LO and 0 which is the default value at reset */ + default: + seq_printf(s, "%s ", "low-drive"); + } + } } static const struct pinconf_ops atmel_confops = { @@ -958,6 +998,8 @@ static int atmel_pinctrl_probe(struct platform_device *pdev) return -ENOMEM; atmel_pinctrl_desc.pins = pin_desc; atmel_pinctrl_desc.npins = atmel_pioctrl->npins; + atmel_pinctrl_desc.num_custom_params = ARRAY_SIZE(atmel_custom_bindings); + atmel_pinctrl_desc.custom_params = atmel_custom_bindings; /* One pin is one group since a pin can achieve all functions. */ group_names = devm_kcalloc(dev, diff --git a/include/dt-bindings/pinctrl/at91.h b/include/dt-bindings/pinctrl/at91.h index 2732d6c0fb39..eb81867eac77 100644 --- a/include/dt-bindings/pinctrl/at91.h +++ b/include/dt-bindings/pinctrl/at91.h @@ -39,4 +39,8 @@ #define AT91_PERIPH_C 3 #define AT91_PERIPH_D 4 +#define ATMEL_PIO_DRVSTR_LO 1 +#define ATMEL_PIO_DRVSTR_ME 2 +#define ATMEL_PIO_DRVSTR_HI 3 + #endif /* __DT_BINDINGS_AT91_PINCTRL_H__ */ -- cgit v1.2.3 From a4f9edb29d9c19f9f8dcd2df7ddfe4eb7ad58996 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 30 May 2018 17:29:52 +0100 Subject: irqchip/gic-v3: Expose GICD_TYPER in the rdist structure Instead of exposing the GIC distributor IntID field in the rdist structure that is passed to the ITS, let's replace it with a copy of the whole GICD_TYPER register. We are going to need some of this information at a later time. No functionnal change. Signed-off-by: Marc Zyngier --- drivers/irqchip/irq-gic-v3-its.c | 2 +- drivers/irqchip/irq-gic-v3.c | 4 ++-- include/linux/irqchip/arm-gic-v3.h | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 9c5b85577053..efe6d1a6c32e 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -1616,7 +1616,7 @@ static int __init its_alloc_lpi_tables(void) { phys_addr_t paddr; - lpi_id_bits = gic_rdists->id_bits; + lpi_id_bits = GICD_TYPER_ID_BITS(gic_rdists->gicd_typer); gic_rdists->prop_page = its_allocate_prop_table(GFP_NOWAIT); if (!gic_rdists->prop_page) { pr_err("Failed to allocate PROPBASE\n"); diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 76ea56d779a1..e214181b77b7 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -877,7 +877,7 @@ static struct irq_chip gic_eoimode1_chip = { .flags = IRQCHIP_SET_TYPE_MASKED, }; -#define GIC_ID_NR (1U << gic_data.rdists.id_bits) +#define GIC_ID_NR (1U << GICD_TYPER_ID_BITS(gic_data.rdists.gicd_typer)) static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hw) @@ -1091,7 +1091,7 @@ static int __init gic_init_bases(void __iomem *dist_base, * The GIC only supports up to 1020 interrupt sources (SGI+PPI+SPI) */ typer = readl_relaxed(gic_data.dist_base + GICD_TYPER); - gic_data.rdists.id_bits = GICD_TYPER_ID_BITS(typer); + gic_data.rdists.gicd_typer = typer; gic_irqs = GICD_TYPER_IRQS(typer); if (gic_irqs > 1020) gic_irqs = 1020; diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index cbb872c1b607..396cd99af02f 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -576,8 +576,8 @@ struct rdists { phys_addr_t phys_base; } __percpu *rdist; struct page *prop_page; - int id_bits; u64 flags; + u32 gicd_typer; bool has_vlpis; bool has_direct_lpi; }; -- cgit v1.2.3 From 12b2905af183c931bedcab4292c81d3a415e080f Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 31 May 2018 09:01:59 +0100 Subject: irqchip/gic-v3-its: Honor hypervisor enforced LPI range A recent extension to the GIC architecture allows a hypervisor to arbitrarily reduce the number of LPIs available to a guest, no matter what the GIC says about the valid range of IntIDs. Let's factor in this information when computing the number of available LPIs Signed-off-by: Marc Zyngier --- drivers/irqchip/irq-gic-v3-its.c | 9 +++++++++ include/linux/irqchip/arm-gic-v3.h | 1 + 2 files changed, 10 insertions(+) (limited to 'include') diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index efe6d1a6c32e..f56c84977241 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -1541,8 +1541,17 @@ out: static int __init its_lpi_init(u32 id_bits) { u32 lpis = (1UL << id_bits) - 8192; + u32 numlpis; int err; + numlpis = 1UL << GICD_TYPER_NUM_LPIS(gic_rdists->gicd_typer); + + if (numlpis > 2 && !WARN_ON(numlpis > lpis)) { + lpis = numlpis; + pr_info("ITS: Using hypervisor restricted LPI range [%u]\n", + lpis); + } + /* * Initializing the allocator is just the same as freeing the * full range of LPIs. diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 396cd99af02f..9d2ea3e907d0 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -73,6 +73,7 @@ #define GICD_TYPER_MBIS (1U << 16) #define GICD_TYPER_ID_BITS(typer) ((((typer) >> 19) & 0x1f) + 1) +#define GICD_TYPER_NUM_LPIS(typer) ((((typer) >> 11) & 0x1f) + 1) #define GICD_TYPER_IRQS(typer) ((((typer) & 0x1f) + 1) * 32) #define GICD_IROUTER_SPI_MODE_ONE (0U << 31) -- cgit v1.2.3 From 0f292f023ffcc67ec49d63dcb7fe388711cbb83a Mon Sep 17 00:00:00 2001 From: Jorge Sanjuan Date: Wed, 11 Jul 2018 13:37:53 +0100 Subject: ALSA: usb-audio: Add support for Processing Units in UAC3 This patch adds support for the Processig Units defined in the UAC3 spec. The main difference with the previous specs is the lack of on/off switches in the controls for these units and the addiction of the new Multi Function Processing Unit. The current version of the UAC3 spec doesn't define any useful controls for the new Multi Function Processing Unit so no control will get created once this unit is parsed. Signed-off-by: Jorge Sanjuan Signed-off-by: Takashi Iwai --- include/linux/usb/audio-v3.h | 15 +++++++++++++ include/uapi/linux/usb/audio.h | 49 ++++++++++++++++++++++++++++++++-------- sound/usb/mixer.c | 51 ++++++++++++++++++++++++++++++++++++++++-- 3 files changed, 104 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/usb/audio-v3.h b/include/linux/usb/audio-v3.h index a710e28b5215..334bfa6dfb47 100644 --- a/include/linux/usb/audio-v3.h +++ b/include/linux/usb/audio-v3.h @@ -387,6 +387,12 @@ struct uac3_interrupt_data_msg { #define UAC3_CONNECTORS 0x0f #define UAC3_POWER_DOMAIN 0x10 +/* A.20 PROCESSING UNIT PROCESS TYPES */ +#define UAC3_PROCESS_UNDEFINED 0x00 +#define UAC3_PROCESS_UP_DOWNMIX 0x01 +#define UAC3_PROCESS_STEREO_EXTENDER 0x02 +#define UAC3_PROCESS_MULTI_FUNCTION 0x03 + /* A.22 AUDIO CLASS-SPECIFIC REQUEST CODES */ /* see audio-v2.h for the rest, which is identical to v2 */ #define UAC3_CS_REQ_INTEN 0x04 @@ -406,6 +412,15 @@ struct uac3_interrupt_data_msg { #define UAC3_TE_OVERFLOW 0x04 #define UAC3_TE_LATENCY 0x05 +/* A.23.10 PROCESSING UNITS CONTROL SELECTROS */ + +/* Up/Down Mixer */ +#define UAC3_UD_MODE_SELECT 0x01 + +/* Stereo Extender */ +#define UAC3_EXT_WIDTH_CONTROL 0x01 + + /* BADD predefined Unit/Terminal values */ #define UAC3_BADD_IT_ID1 1 /* Input Terminal ID1: bTerminalID = 1 */ #define UAC3_BADD_FU_ID2 2 /* Feature Unit ID2: bUnitID = 2 */ diff --git a/include/uapi/linux/usb/audio.h b/include/uapi/linux/usb/audio.h index 74e520fb944f..ddc5396800aa 100644 --- a/include/uapi/linux/usb/audio.h +++ b/include/uapi/linux/usb/audio.h @@ -390,33 +390,64 @@ static inline __u8 uac_processing_unit_iChannelNames(struct uac_processing_unit_ static inline __u8 uac_processing_unit_bControlSize(struct uac_processing_unit_descriptor *desc, int protocol) { - return (protocol == UAC_VERSION_1) ? - desc->baSourceID[desc->bNrInPins + 4] : - 2; /* in UAC2, this value is constant */ + switch (protocol) { + case UAC_VERSION_1: + return desc->baSourceID[desc->bNrInPins + 4]; + case UAC_VERSION_2: + return 2; /* in UAC2, this value is constant */ + case UAC_VERSION_3: + return 4; /* in UAC3, this value is constant */ + default: + return 1; + } } static inline __u8 *uac_processing_unit_bmControls(struct uac_processing_unit_descriptor *desc, int protocol) { - return (protocol == UAC_VERSION_1) ? - &desc->baSourceID[desc->bNrInPins + 5] : - &desc->baSourceID[desc->bNrInPins + 6]; + switch (protocol) { + case UAC_VERSION_1: + return &desc->baSourceID[desc->bNrInPins + 5]; + case UAC_VERSION_2: + return &desc->baSourceID[desc->bNrInPins + 6]; + case UAC_VERSION_3: + return &desc->baSourceID[desc->bNrInPins + 2]; + default: + return NULL; + } } static inline __u8 uac_processing_unit_iProcessing(struct uac_processing_unit_descriptor *desc, int protocol) { __u8 control_size = uac_processing_unit_bControlSize(desc, protocol); - return *(uac_processing_unit_bmControls(desc, protocol) - + control_size); + + switch (protocol) { + case UAC_VERSION_1: + case UAC_VERSION_2: + default: + return *(uac_processing_unit_bmControls(desc, protocol) + + control_size); + case UAC_VERSION_3: + return 0; /* UAC3 does not have this field */ + } } static inline __u8 *uac_processing_unit_specific(struct uac_processing_unit_descriptor *desc, int protocol) { __u8 control_size = uac_processing_unit_bControlSize(desc, protocol); - return uac_processing_unit_bmControls(desc, protocol) + + switch (protocol) { + case UAC_VERSION_1: + case UAC_VERSION_2: + default: + return uac_processing_unit_bmControls(desc, protocol) + control_size + 1; + case UAC_VERSION_3: + return uac_processing_unit_bmControls(desc, protocol) + + control_size; + } } /* 4.5.2 Class-Specific AS Interface Descriptor */ diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index bfb3484096a6..39fde49e8749 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -953,6 +953,23 @@ static int check_input_term(struct mixer_build *state, int id, return 0; } + case UAC3_PROCESSING_UNIT: { + struct uac_processing_unit_descriptor *d = p1; + + if (!d->bNrInPins) + return -EINVAL; + + /* call recursively to retrieve the channel info */ + err = check_input_term(state, d->baSourceID[0], term); + if (err < 0) + return err; + + term->type = d->bDescriptorSubtype << 16; /* virtual type */ + term->id = id; + term->name = 0; /* TODO: UAC3 Class-specific strings */ + + return 0; + } default: return -ENODEV; } @@ -2180,6 +2197,11 @@ struct procunit_info { struct procunit_value_info *values; }; +static struct procunit_value_info undefined_proc_info[] = { + { 0x00, "Control Undefined", 0 }, + { 0 } +}; + static struct procunit_value_info updown_proc_info[] = { { UAC_UD_ENABLE, "Switch", USB_MIXER_BOOLEAN }, { UAC_UD_MODE_SELECT, "Mode Select", USB_MIXER_U8, 1 }, @@ -2228,6 +2250,23 @@ static struct procunit_info procunits[] = { { UAC_PROCESS_DYN_RANGE_COMP, "DCR", dcr_proc_info }, { 0 }, }; + +static struct procunit_value_info uac3_updown_proc_info[] = { + { UAC3_UD_MODE_SELECT, "Mode Select", USB_MIXER_U8, 1 }, + { 0 } +}; +static struct procunit_value_info uac3_stereo_ext_proc_info[] = { + { UAC3_EXT_WIDTH_CONTROL, "Width Control", USB_MIXER_U8 }, + { 0 } +}; + +static struct procunit_info uac3_procunits[] = { + { UAC3_PROCESS_UP_DOWNMIX, "Up Down", uac3_updown_proc_info }, + { UAC3_PROCESS_STEREO_EXTENDER, "3D Stereo Extender", uac3_stereo_ext_proc_info }, + { UAC3_PROCESS_MULTI_FUNCTION, "Multi-Function", undefined_proc_info }, + { 0 }, +}; + /* * predefined data for extension units */ @@ -2388,8 +2427,16 @@ static int build_audio_procunit(struct mixer_build *state, int unitid, static int parse_audio_processing_unit(struct mixer_build *state, int unitid, void *raw_desc) { - return build_audio_procunit(state, unitid, raw_desc, - procunits, "Processing Unit"); + switch (state->mixer->protocol) { + case UAC_VERSION_1: + case UAC_VERSION_2: + default: + return build_audio_procunit(state, unitid, raw_desc, + procunits, "Processing Unit"); + case UAC_VERSION_3: + return build_audio_procunit(state, unitid, raw_desc, + uac3_procunits, "Processing Unit"); + } } static int parse_audio_extension_unit(struct mixer_build *state, int unitid, -- cgit v1.2.3 From a18b21929453af70390e14f8dee40acf00d428cb Mon Sep 17 00:00:00 2001 From: Lyude Paul Date: Mon, 16 Jul 2018 11:44:32 -0400 Subject: drm/dp_helper: Add DP aux channel tracing This is something we've needed for a very long time now, as it makes debugging issues with faulty MST hubs along with debugging issues regarding us interfacing with hubs correctly vastly easier to debug. Currently this can actually be done if you trace the i2c devices for DP using ftrace but that's significantly less useful for a couple of reasons: - Tracing the i2c devices through ftrace means all of the traces are going to contain a lot of "garbage" output that we're sending over the i2c line. Most of this garbage comes from retrying transactions, DRM's helper library adding extra transactions to work around bad hubs, etc. - Having a user set up ftrace so that they can provide debugging information is a lot more difficult then being able to say "just boot with drm.debug=0x100" - We can potentially expand upon this tracing in the future to print debugging information in regards to other DP transactions like MST sideband transactions This is inspired by a patch Rob Clark sent to do this a long time back. Neither of us could find the patch however, so we both assumed it would probably just be easier to rewrite it anyway. Cc: Rob Clark Signed-off-by: Lyude Paul Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20180716154432.13433-1-lyude@redhat.com --- drivers/gpu/drm/drm_dp_helper.c | 32 +++++++++++++++++++++++++++----- drivers/gpu/drm/drm_drv.c | 15 ++++++++------- include/drm/drm_print.h | 6 ++++++ 3 files changed, 41 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c index f4a06b54aa7d..0cccbcb2d03e 100644 --- a/drivers/gpu/drm/drm_dp_helper.c +++ b/drivers/gpu/drm/drm_dp_helper.c @@ -185,6 +185,20 @@ EXPORT_SYMBOL(drm_dp_bw_code_to_link_rate); #define AUX_RETRY_INTERVAL 500 /* us */ +static inline void +drm_dp_dump_access(const struct drm_dp_aux *aux, + u8 request, uint offset, void *buffer, int ret) +{ + const char *arrow = request == DP_AUX_NATIVE_READ ? "->" : "<-"; + + if (ret > 0) + drm_dbg(DRM_UT_DP, "%s: 0x%05x AUX %s (ret=%3d) %*ph\n", + aux->name, offset, arrow, ret, min(ret, 20), buffer); + else + drm_dbg(DRM_UT_DP, "%s: 0x%05x AUX %s (ret=%3d)\n", + aux->name, offset, arrow, ret); +} + /** * DOC: dp helpers * @@ -288,10 +302,14 @@ ssize_t drm_dp_dpcd_read(struct drm_dp_aux *aux, unsigned int offset, ret = drm_dp_dpcd_access(aux, DP_AUX_NATIVE_READ, DP_DPCD_REV, buffer, 1); if (ret != 1) - return ret; + goto out; - return drm_dp_dpcd_access(aux, DP_AUX_NATIVE_READ, offset, buffer, - size); + ret = drm_dp_dpcd_access(aux, DP_AUX_NATIVE_READ, offset, buffer, + size); + +out: + drm_dp_dump_access(aux, DP_AUX_NATIVE_READ, offset, buffer, ret); + return ret; } EXPORT_SYMBOL(drm_dp_dpcd_read); @@ -312,8 +330,12 @@ EXPORT_SYMBOL(drm_dp_dpcd_read); ssize_t drm_dp_dpcd_write(struct drm_dp_aux *aux, unsigned int offset, void *buffer, size_t size) { - return drm_dp_dpcd_access(aux, DP_AUX_NATIVE_WRITE, offset, buffer, - size); + int ret; + + ret = drm_dp_dpcd_access(aux, DP_AUX_NATIVE_WRITE, offset, buffer, + size); + drm_dp_dump_access(aux, DP_AUX_NATIVE_WRITE, offset, buffer, ret); + return ret; } EXPORT_SYMBOL(drm_dp_dpcd_write); diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c index 6eb935bb2f92..ea4941da9b27 100644 --- a/drivers/gpu/drm/drm_drv.c +++ b/drivers/gpu/drm/drm_drv.c @@ -54,13 +54,14 @@ MODULE_AUTHOR("Gareth Hughes, Leif Delgass, José Fonseca, Jon Smirl"); MODULE_DESCRIPTION("DRM shared core routines"); MODULE_LICENSE("GPL and additional rights"); MODULE_PARM_DESC(debug, "Enable debug output, where each bit enables a debug category.\n" -"\t\tBit 0 (0x01) will enable CORE messages (drm core code)\n" -"\t\tBit 1 (0x02) will enable DRIVER messages (drm controller code)\n" -"\t\tBit 2 (0x04) will enable KMS messages (modesetting code)\n" -"\t\tBit 3 (0x08) will enable PRIME messages (prime code)\n" -"\t\tBit 4 (0x10) will enable ATOMIC messages (atomic code)\n" -"\t\tBit 5 (0x20) will enable VBL messages (vblank code)\n" -"\t\tBit 7 (0x80) will enable LEASE messages (leasing code)"); +"\t\tBit 0 (0x01) will enable CORE messages (drm core code)\n" +"\t\tBit 1 (0x02) will enable DRIVER messages (drm controller code)\n" +"\t\tBit 2 (0x04) will enable KMS messages (modesetting code)\n" +"\t\tBit 3 (0x08) will enable PRIME messages (prime code)\n" +"\t\tBit 4 (0x10) will enable ATOMIC messages (atomic code)\n" +"\t\tBit 5 (0x20) will enable VBL messages (vblank code)\n" +"\t\tBit 7 (0x80) will enable LEASE messages (leasing code)\n" +"\t\tBit 8 (0x100) will enable DP messages (displayport code)"); module_param_named(debug, drm_debug, int, 0600); static DEFINE_SPINLOCK(drm_minor_lock); diff --git a/include/drm/drm_print.h b/include/drm/drm_print.h index e1a46e9991cc..767c90b654c5 100644 --- a/include/drm/drm_print.h +++ b/include/drm/drm_print.h @@ -195,6 +195,7 @@ static inline struct drm_printer drm_debug_printer(const char *prefix) #define DRM_UT_VBL 0x20 #define DRM_UT_STATE 0x40 #define DRM_UT_LEASE 0x80 +#define DRM_UT_DP 0x100 __printf(3, 4) void drm_dev_printk(const struct device *dev, const char *level, @@ -307,6 +308,11 @@ void drm_err(const char *format, ...); #define DRM_DEBUG_LEASE(fmt, ...) \ drm_dbg(DRM_UT_LEASE, fmt, ##__VA_ARGS__) +#define DRM_DEV_DEBUG_DP(dev, fmt, ...) \ + drm_dev_dbg(dev, DRM_UT_DP, fmt, ## __VA_ARGS__) +#define DRM_DEBUG_DP(dev, fmt, ...) \ + drm_dbg(DRM_UT_DP, fmt, ## __VA_ARGS__) + #define _DRM_DEV_DEFINE_DEBUG_RATELIMITED(dev, category, fmt, ...) \ ({ \ static DEFINE_RATELIMIT_STATE(_rs, \ -- cgit v1.2.3 From f286586df68e7733a8e651098401f139dc2e17f4 Mon Sep 17 00:00:00 2001 From: Máté Eckl Date: Mon, 18 Jun 2018 15:12:52 +0200 Subject: netfilter: nft_tproxy: Move nf_tproxy_assign_sock() to nf_tproxy.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This function is also necessary to implement nft tproxy support Fixes: 45ca4e0cf273 ("netfilter: Libify xt_TPROXY") Signed-off-by: Máté Eckl Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tproxy.h | 8 ++++++++ net/netfilter/xt_TPROXY.c | 9 --------- 2 files changed, 8 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tproxy.h b/include/net/netfilter/nf_tproxy.h index 9754a50ecde9..d5a80888cbe4 100644 --- a/include/net/netfilter/nf_tproxy.h +++ b/include/net/netfilter/nf_tproxy.h @@ -17,6 +17,14 @@ static inline bool nf_tproxy_sk_is_transparent(struct sock *sk) return false; } +/* assign a socket to the skb -- consumes sk */ +static inline void nf_tproxy_assign_sock(struct sk_buff *skb, struct sock *sk) +{ + skb_orphan(skb); + skb->sk = sk; + skb->destructor = sock_edemux; +} + __be32 nf_tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr); /** diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c index 58fce4e749a9..35df0827e2ca 100644 --- a/net/netfilter/xt_TPROXY.c +++ b/net/netfilter/xt_TPROXY.c @@ -36,15 +36,6 @@ #include #include -/* assign a socket to the skb -- consumes sk */ -static void -nf_tproxy_assign_sock(struct sk_buff *skb, struct sock *sk) -{ - skb_orphan(skb); - skb->sk = sk; - skb->destructor = sock_edemux; -} - static unsigned int tproxy_tg4(struct net *net, struct sk_buff *skb, __be32 laddr, __be16 lport, u_int32_t mark_mask, u_int32_t mark_value) -- cgit v1.2.3 From d7e5a9a50245b91f016c814b0f076f7e55cbb980 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 25 Jun 2018 17:49:43 +0200 Subject: netfilter: utils: move nf_ip_checksum* from ipv4 to utils allows to make nf_ip_checksum_partial static, it no longer has an external caller. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_ipv4.h | 11 --------- net/ipv4/netfilter.c | 53 ---------------------------------------- net/netfilter/utils.c | 55 ++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 55 insertions(+), 64 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter_ipv4.h b/include/linux/netfilter_ipv4.h index b31dabfdb453..95ab5cc64422 100644 --- a/include/linux/netfilter_ipv4.h +++ b/include/linux/netfilter_ipv4.h @@ -23,9 +23,6 @@ struct nf_queue_entry; #ifdef CONFIG_INET __sum16 nf_ip_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, u_int8_t protocol); -__sum16 nf_ip_checksum_partial(struct sk_buff *skb, unsigned int hook, - unsigned int dataoff, unsigned int len, - u_int8_t protocol); int nf_ip_route(struct net *net, struct dst_entry **dst, struct flowi *fl, bool strict); int nf_ip_reroute(struct sk_buff *skb, const struct nf_queue_entry *entry); @@ -35,14 +32,6 @@ static inline __sum16 nf_ip_checksum(struct sk_buff *skb, unsigned int hook, { return 0; } -static inline __sum16 nf_ip_checksum_partial(struct sk_buff *skb, - unsigned int hook, - unsigned int dataoff, - unsigned int len, - u_int8_t protocol) -{ - return 0; -} static inline int nf_ip_route(struct net *net, struct dst_entry **dst, struct flowi *fl, bool strict) { diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index e6774ccb7731..8d2e5dc9a827 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -98,59 +98,6 @@ int nf_ip_reroute(struct sk_buff *skb, const struct nf_queue_entry *entry) } EXPORT_SYMBOL_GPL(nf_ip_reroute); -__sum16 nf_ip_checksum(struct sk_buff *skb, unsigned int hook, - unsigned int dataoff, u_int8_t protocol) -{ - const struct iphdr *iph = ip_hdr(skb); - __sum16 csum = 0; - - switch (skb->ip_summed) { - case CHECKSUM_COMPLETE: - if (hook != NF_INET_PRE_ROUTING && hook != NF_INET_LOCAL_IN) - break; - if ((protocol == 0 && !csum_fold(skb->csum)) || - !csum_tcpudp_magic(iph->saddr, iph->daddr, - skb->len - dataoff, protocol, - skb->csum)) { - skb->ip_summed = CHECKSUM_UNNECESSARY; - break; - } - /* fall through */ - case CHECKSUM_NONE: - if (protocol == 0) - skb->csum = 0; - else - skb->csum = csum_tcpudp_nofold(iph->saddr, iph->daddr, - skb->len - dataoff, - protocol, 0); - csum = __skb_checksum_complete(skb); - } - return csum; -} -EXPORT_SYMBOL(nf_ip_checksum); - -__sum16 nf_ip_checksum_partial(struct sk_buff *skb, unsigned int hook, - unsigned int dataoff, unsigned int len, - u_int8_t protocol) -{ - const struct iphdr *iph = ip_hdr(skb); - __sum16 csum = 0; - - switch (skb->ip_summed) { - case CHECKSUM_COMPLETE: - if (len == skb->len - dataoff) - return nf_ip_checksum(skb, hook, dataoff, protocol); - /* fall through */ - case CHECKSUM_NONE: - skb->csum = csum_tcpudp_nofold(iph->saddr, iph->daddr, protocol, - skb->len - dataoff, 0); - skb->ip_summed = CHECKSUM_NONE; - return __skb_checksum_complete_head(skb, dataoff + len); - } - return csum; -} -EXPORT_SYMBOL_GPL(nf_ip_checksum_partial); - int nf_ip_route(struct net *net, struct dst_entry **dst, struct flowi *fl, bool strict __always_unused) { diff --git a/net/netfilter/utils.c b/net/netfilter/utils.c index 0b660c568156..8980c8a0fe5c 100644 --- a/net/netfilter/utils.c +++ b/net/netfilter/utils.c @@ -1,9 +1,64 @@ +// SPDX-License-Identifier: GPL-2.0 #include #include #include #include #include +#ifdef CONFIG_INET +__sum16 nf_ip_checksum(struct sk_buff *skb, unsigned int hook, + unsigned int dataoff, u8 protocol) +{ + const struct iphdr *iph = ip_hdr(skb); + __sum16 csum = 0; + + switch (skb->ip_summed) { + case CHECKSUM_COMPLETE: + if (hook != NF_INET_PRE_ROUTING && hook != NF_INET_LOCAL_IN) + break; + if ((protocol == 0 && !csum_fold(skb->csum)) || + !csum_tcpudp_magic(iph->saddr, iph->daddr, + skb->len - dataoff, protocol, + skb->csum)) { + skb->ip_summed = CHECKSUM_UNNECESSARY; + break; + } + /* fall through */ + case CHECKSUM_NONE: + if (protocol == 0) + skb->csum = 0; + else + skb->csum = csum_tcpudp_nofold(iph->saddr, iph->daddr, + skb->len - dataoff, + protocol, 0); + csum = __skb_checksum_complete(skb); + } + return csum; +} +EXPORT_SYMBOL(nf_ip_checksum); +#endif + +static __sum16 nf_ip_checksum_partial(struct sk_buff *skb, unsigned int hook, + unsigned int dataoff, unsigned int len, + u8 protocol) +{ + const struct iphdr *iph = ip_hdr(skb); + __sum16 csum = 0; + + switch (skb->ip_summed) { + case CHECKSUM_COMPLETE: + if (len == skb->len - dataoff) + return nf_ip_checksum(skb, hook, dataoff, protocol); + /* fall through */ + case CHECKSUM_NONE: + skb->csum = csum_tcpudp_nofold(iph->saddr, iph->daddr, protocol, + skb->len - dataoff, 0); + skb->ip_summed = CHECKSUM_NONE; + return __skb_checksum_complete_head(skb, dataoff + len); + } + return csum; +} + __sum16 nf_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, u_int8_t protocol, unsigned short family) -- cgit v1.2.3 From ebee5a50d0b7cdc576aa8081f05b86971880054d Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 25 Jun 2018 17:49:59 +0200 Subject: netfilter: utils: move nf_ip6_checksum* from ipv6 to utils similar to previous change, this also allows to remove it from nf_ipv6_ops and avoid the indirection. It also removes the bogus dependency of nf_conntrack_ipv6 on ipv6 module: ipv6 checksum functions are built into kernel even if CONFIG_IPV6=m, but ipv6/netfilter.o isn't. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_ipv6.h | 5 --- net/ipv6/netfilter.c | 62 ---------------------------------- net/netfilter/utils.c | 76 ++++++++++++++++++++++++++++++++++++------ 3 files changed, 65 insertions(+), 78 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index 288c597e75b3..c0dc4dd78887 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -30,11 +30,6 @@ struct nf_ipv6_ops { void (*route_input)(struct sk_buff *skb); int (*fragment)(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)); - __sum16 (*checksum)(struct sk_buff *skb, unsigned int hook, - unsigned int dataoff, u_int8_t protocol); - __sum16 (*checksum_partial)(struct sk_buff *skb, unsigned int hook, - unsigned int dataoff, unsigned int len, - u_int8_t protocol); int (*route)(struct net *net, struct dst_entry **dst, struct flowi *fl, bool strict); int (*reroute)(struct sk_buff *skb, const struct nf_queue_entry *entry); diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 531d6957af36..5ae8e1c51079 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -15,7 +15,6 @@ #include #include #include -#include #include int ip6_route_me_harder(struct net *net, struct sk_buff *skb) @@ -106,71 +105,10 @@ static int nf_ip6_route(struct net *net, struct dst_entry **dst, return err; } -__sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook, - unsigned int dataoff, u_int8_t protocol) -{ - const struct ipv6hdr *ip6h = ipv6_hdr(skb); - __sum16 csum = 0; - - switch (skb->ip_summed) { - case CHECKSUM_COMPLETE: - if (hook != NF_INET_PRE_ROUTING && hook != NF_INET_LOCAL_IN) - break; - if (!csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, - skb->len - dataoff, protocol, - csum_sub(skb->csum, - skb_checksum(skb, 0, - dataoff, 0)))) { - skb->ip_summed = CHECKSUM_UNNECESSARY; - break; - } - /* fall through */ - case CHECKSUM_NONE: - skb->csum = ~csum_unfold( - csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, - skb->len - dataoff, - protocol, - csum_sub(0, - skb_checksum(skb, 0, - dataoff, 0)))); - csum = __skb_checksum_complete(skb); - } - return csum; -} -EXPORT_SYMBOL(nf_ip6_checksum); - -static __sum16 nf_ip6_checksum_partial(struct sk_buff *skb, unsigned int hook, - unsigned int dataoff, unsigned int len, - u_int8_t protocol) -{ - const struct ipv6hdr *ip6h = ipv6_hdr(skb); - __wsum hsum; - __sum16 csum = 0; - - switch (skb->ip_summed) { - case CHECKSUM_COMPLETE: - if (len == skb->len - dataoff) - return nf_ip6_checksum(skb, hook, dataoff, protocol); - /* fall through */ - case CHECKSUM_NONE: - hsum = skb_checksum(skb, 0, dataoff, 0); - skb->csum = ~csum_unfold(csum_ipv6_magic(&ip6h->saddr, - &ip6h->daddr, - skb->len - dataoff, - protocol, - csum_sub(0, hsum))); - skb->ip_summed = CHECKSUM_NONE; - return __skb_checksum_complete_head(skb, dataoff + len); - } - return csum; -}; - static const struct nf_ipv6_ops ipv6ops = { .chk_addr = ipv6_chk_addr, .route_input = ip6_route_input, .fragment = ip6_fragment, - .checksum = nf_ip6_checksum, - .checksum_partial = nf_ip6_checksum_partial, .route = nf_ip6_route, .reroute = nf_ip6_reroute, }; diff --git a/net/netfilter/utils.c b/net/netfilter/utils.c index 8980c8a0fe5c..e8da9a9bba73 100644 --- a/net/netfilter/utils.c +++ b/net/netfilter/utils.c @@ -4,6 +4,7 @@ #include #include #include +#include #ifdef CONFIG_INET __sum16 nf_ip_checksum(struct sk_buff *skb, unsigned int hook, @@ -59,11 +60,69 @@ static __sum16 nf_ip_checksum_partial(struct sk_buff *skb, unsigned int hook, return csum; } +__sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook, + unsigned int dataoff, u8 protocol) +{ + const struct ipv6hdr *ip6h = ipv6_hdr(skb); + __sum16 csum = 0; + + switch (skb->ip_summed) { + case CHECKSUM_COMPLETE: + if (hook != NF_INET_PRE_ROUTING && hook != NF_INET_LOCAL_IN) + break; + if (!csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, + skb->len - dataoff, protocol, + csum_sub(skb->csum, + skb_checksum(skb, 0, + dataoff, 0)))) { + skb->ip_summed = CHECKSUM_UNNECESSARY; + break; + } + /* fall through */ + case CHECKSUM_NONE: + skb->csum = ~csum_unfold( + csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, + skb->len - dataoff, + protocol, + csum_sub(0, + skb_checksum(skb, 0, + dataoff, 0)))); + csum = __skb_checksum_complete(skb); + } + return csum; +} +EXPORT_SYMBOL(nf_ip6_checksum); + +static __sum16 nf_ip6_checksum_partial(struct sk_buff *skb, unsigned int hook, + unsigned int dataoff, unsigned int len, + u8 protocol) +{ + const struct ipv6hdr *ip6h = ipv6_hdr(skb); + __wsum hsum; + __sum16 csum = 0; + + switch (skb->ip_summed) { + case CHECKSUM_COMPLETE: + if (len == skb->len - dataoff) + return nf_ip6_checksum(skb, hook, dataoff, protocol); + /* fall through */ + case CHECKSUM_NONE: + hsum = skb_checksum(skb, 0, dataoff, 0); + skb->csum = ~csum_unfold(csum_ipv6_magic(&ip6h->saddr, + &ip6h->daddr, + skb->len - dataoff, + protocol, + csum_sub(0, hsum))); + skb->ip_summed = CHECKSUM_NONE; + return __skb_checksum_complete_head(skb, dataoff + len); + } + return csum; +}; + __sum16 nf_checksum(struct sk_buff *skb, unsigned int hook, - unsigned int dataoff, u_int8_t protocol, + unsigned int dataoff, u8 protocol, unsigned short family) { - const struct nf_ipv6_ops *v6ops; __sum16 csum = 0; switch (family) { @@ -71,9 +130,7 @@ __sum16 nf_checksum(struct sk_buff *skb, unsigned int hook, csum = nf_ip_checksum(skb, hook, dataoff, protocol); break; case AF_INET6: - v6ops = rcu_dereference(nf_ipv6_ops); - if (v6ops) - csum = v6ops->checksum(skb, hook, dataoff, protocol); + csum = nf_ip6_checksum(skb, hook, dataoff, protocol); break; } @@ -83,9 +140,8 @@ EXPORT_SYMBOL_GPL(nf_checksum); __sum16 nf_checksum_partial(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, unsigned int len, - u_int8_t protocol, unsigned short family) + u8 protocol, unsigned short family) { - const struct nf_ipv6_ops *v6ops; __sum16 csum = 0; switch (family) { @@ -94,10 +150,8 @@ __sum16 nf_checksum_partial(struct sk_buff *skb, unsigned int hook, protocol); break; case AF_INET6: - v6ops = rcu_dereference(nf_ipv6_ops); - if (v6ops) - csum = v6ops->checksum_partial(skb, hook, dataoff, len, - protocol); + csum = nf_ip6_checksum_partial(skb, hook, dataoff, len, + protocol); break; } -- cgit v1.2.3 From 60e3be94e6a1c5162a0763c9aafb5190b2b1fdce Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 25 Jun 2018 17:55:32 +0200 Subject: openvswitch: use nf_ct_get_tuplepr, invert_tuplepr These versions deal with the l3proto/l4proto details internally. It removes only caller of nf_ct_get_tuple, so make it static. After this, l3proto->get_l4proto() can be removed in a followup patch. Signed-off-by: Florian Westphal Acked-by: Pravin B Shelar Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_core.h | 7 ------- net/netfilter/nf_conntrack_core.c | 3 +-- net/openvswitch/conntrack.c | 17 +++-------------- 3 files changed, 4 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index 9b5e7634713e..90df45022c51 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -40,13 +40,6 @@ void nf_conntrack_cleanup_start(void); void nf_conntrack_init_end(void); void nf_conntrack_cleanup_end(void); -bool nf_ct_get_tuple(const struct sk_buff *skb, unsigned int nhoff, - unsigned int dataoff, u_int16_t l3num, u_int8_t protonum, - struct net *net, - struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_l3proto *l3proto, - const struct nf_conntrack_l4proto *l4proto); - bool nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse, const struct nf_conntrack_tuple *orig, const struct nf_conntrack_l3proto *l3proto, diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 85ab2fd6a665..be0ab81e6b2c 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -222,7 +222,7 @@ static u32 hash_conntrack(const struct net *net, return scale_hash(hash_conntrack_raw(tuple, net)); } -bool +static bool nf_ct_get_tuple(const struct sk_buff *skb, unsigned int nhoff, unsigned int dataoff, @@ -244,7 +244,6 @@ nf_ct_get_tuple(const struct sk_buff *skb, return l4proto->pkt_to_tuple(skb, dataoff, net, tuple); } -EXPORT_SYMBOL_GPL(nf_ct_get_tuple); bool nf_ct_get_tuplepr(const struct sk_buff *skb, unsigned int nhoff, u_int16_t l3num, diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 284aca2a252d..e05bd3e53f0f 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -607,23 +607,12 @@ static struct nf_conn * ovs_ct_find_existing(struct net *net, const struct nf_conntrack_zone *zone, u8 l3num, struct sk_buff *skb, bool natted) { - const struct nf_conntrack_l3proto *l3proto; - const struct nf_conntrack_l4proto *l4proto; struct nf_conntrack_tuple tuple; struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; - unsigned int dataoff; - u8 protonum; - l3proto = __nf_ct_l3proto_find(l3num); - if (l3proto->get_l4proto(skb, skb_network_offset(skb), &dataoff, - &protonum) <= 0) { - pr_debug("ovs_ct_find_existing: Can't get protonum\n"); - return NULL; - } - l4proto = __nf_ct_l4proto_find(l3num, protonum); - if (!nf_ct_get_tuple(skb, skb_network_offset(skb), dataoff, l3num, - protonum, net, &tuple, l3proto, l4proto)) { + if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), l3num, + net, &tuple)) { pr_debug("ovs_ct_find_existing: Can't get tuple\n"); return NULL; } @@ -632,7 +621,7 @@ ovs_ct_find_existing(struct net *net, const struct nf_conntrack_zone *zone, if (natted) { struct nf_conntrack_tuple inverse; - if (!nf_ct_invert_tuple(&inverse, &tuple, l3proto, l4proto)) { + if (!nf_ct_invert_tuplepr(&inverse, &tuple)) { pr_debug("ovs_ct_find_existing: Inversion failed!\n"); return NULL; } -- cgit v1.2.3 From f957be9d349a3800940f823b16e12b0405cc305b Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 29 Jun 2018 07:46:44 +0200 Subject: netfilter: conntrack: remove ctnetlink callbacks from l3 protocol trackers handle everything from ctnetlink directly. After all these years we still only support ipv4 and ipv6, so it seems reasonable to remove l3 protocol tracker support and instead handle ipv4/ipv6 from a common, always builtin inet tracker. Step 1: Get rid of all the l3proto->func() calls. Start with ctnetlink, then move on to packet-path ones. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_core.h | 6 +- include/net/netfilter/nf_conntrack_l3proto.h | 8 --- net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c | 47 ------------- net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c | 48 ------------- net/ipv6/netfilter/nf_defrag_ipv6_hooks.c | 1 - net/netfilter/nf_conntrack_expect.c | 1 - net/netfilter/nf_conntrack_helper.c | 1 - net/netfilter/nf_conntrack_netlink.c | 96 +++++++++++++++++++------- net/netfilter/nf_conntrack_proto.c | 5 +- net/netfilter/nf_conntrack_standalone.c | 14 ++-- net/netfilter/nfnetlink_cttimeout.c | 1 - 11 files changed, 79 insertions(+), 149 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index 90df45022c51..d454a53ba646 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -68,10 +68,8 @@ static inline int nf_conntrack_confirm(struct sk_buff *skb) return ret; } -void -print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_l3proto *l3proto, - const struct nf_conntrack_l4proto *proto); +void print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple, + const struct nf_conntrack_l4proto *proto); #define CONNTRACK_LOCKS 1024 diff --git a/include/net/netfilter/nf_conntrack_l3proto.h b/include/net/netfilter/nf_conntrack_l3proto.h index d5808f3e2715..d07b5216a925 100644 --- a/include/net/netfilter/nf_conntrack_l3proto.h +++ b/include/net/netfilter/nf_conntrack_l3proto.h @@ -46,14 +46,6 @@ struct nf_conntrack_l3proto { int (*get_l4proto)(const struct sk_buff *skb, unsigned int nhoff, unsigned int *dataoff, u_int8_t *protonum); -#if IS_ENABLED(CONFIG_NF_CT_NETLINK) - int (*tuple_to_nlattr)(struct sk_buff *skb, - const struct nf_conntrack_tuple *t); - int (*nlattr_to_tuple)(struct nlattr *tb[], - struct nf_conntrack_tuple *t); - const struct nla_policy *nla_policy; -#endif - /* Called when netns wants to use connection tracking */ int (*net_ns_get)(struct net *); void (*net_ns_put)(struct net *); diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index 9db988f9a4d7..98ed12858c52 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -274,41 +274,6 @@ getorigdst(struct sock *sk, int optval, void __user *user, int *len) return -ENOENT; } -#if IS_ENABLED(CONFIG_NF_CT_NETLINK) - -#include -#include - -static int ipv4_tuple_to_nlattr(struct sk_buff *skb, - const struct nf_conntrack_tuple *tuple) -{ - if (nla_put_in_addr(skb, CTA_IP_V4_SRC, tuple->src.u3.ip) || - nla_put_in_addr(skb, CTA_IP_V4_DST, tuple->dst.u3.ip)) - goto nla_put_failure; - return 0; - -nla_put_failure: - return -1; -} - -static const struct nla_policy ipv4_nla_policy[CTA_IP_MAX+1] = { - [CTA_IP_V4_SRC] = { .type = NLA_U32 }, - [CTA_IP_V4_DST] = { .type = NLA_U32 }, -}; - -static int ipv4_nlattr_to_tuple(struct nlattr *tb[], - struct nf_conntrack_tuple *t) -{ - if (!tb[CTA_IP_V4_SRC] || !tb[CTA_IP_V4_DST]) - return -EINVAL; - - t->src.u3.ip = nla_get_in_addr(tb[CTA_IP_V4_SRC]); - t->dst.u3.ip = nla_get_in_addr(tb[CTA_IP_V4_DST]); - - return 0; -} -#endif - static struct nf_sockopt_ops so_getorigdst = { .pf = PF_INET, .get_optmin = SO_ORIGINAL_DST, @@ -360,13 +325,6 @@ const struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 = { .pkt_to_tuple = ipv4_pkt_to_tuple, .invert_tuple = ipv4_invert_tuple, .get_l4proto = ipv4_get_l4proto, -#if IS_ENABLED(CONFIG_NF_CT_NETLINK) - .tuple_to_nlattr = ipv4_tuple_to_nlattr, - .nlattr_to_tuple = ipv4_nlattr_to_tuple, - .nla_policy = ipv4_nla_policy, - .nla_size = NLA_ALIGN(NLA_HDRLEN + sizeof(u32)) + /* CTA_IP_V4_SRC */ - NLA_ALIGN(NLA_HDRLEN + sizeof(u32)), /* CTA_IP_V4_DST */ -#endif .net_ns_get = ipv4_hooks_register, .net_ns_put = ipv4_hooks_unregister, .me = THIS_MODULE, @@ -419,11 +377,6 @@ static int __init nf_conntrack_l3proto_ipv4_init(void) need_conntrack(); -#if IS_ENABLED(CONFIG_NF_CT_NETLINK) - if (WARN_ON(nla_policy_len(ipv4_nla_policy, CTA_IP_MAX + 1) != - nf_conntrack_l3proto_ipv4.nla_size)) - return -EINVAL; -#endif ret = nf_register_sockopt(&so_getorigdst); if (ret < 0) { pr_err("Unable to register netfilter socket option\n"); diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index 663827ee3cf8..13a660ae5799 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -269,41 +269,6 @@ ipv6_getorigdst(struct sock *sk, int optval, void __user *user, int *len) return copy_to_user(user, &sin6, sizeof(sin6)) ? -EFAULT : 0; } -#if IS_ENABLED(CONFIG_NF_CT_NETLINK) - -#include -#include - -static int ipv6_tuple_to_nlattr(struct sk_buff *skb, - const struct nf_conntrack_tuple *tuple) -{ - if (nla_put_in6_addr(skb, CTA_IP_V6_SRC, &tuple->src.u3.in6) || - nla_put_in6_addr(skb, CTA_IP_V6_DST, &tuple->dst.u3.in6)) - goto nla_put_failure; - return 0; - -nla_put_failure: - return -1; -} - -static const struct nla_policy ipv6_nla_policy[CTA_IP_MAX+1] = { - [CTA_IP_V6_SRC] = { .len = sizeof(u_int32_t)*4 }, - [CTA_IP_V6_DST] = { .len = sizeof(u_int32_t)*4 }, -}; - -static int ipv6_nlattr_to_tuple(struct nlattr *tb[], - struct nf_conntrack_tuple *t) -{ - if (!tb[CTA_IP_V6_SRC] || !tb[CTA_IP_V6_DST]) - return -EINVAL; - - t->src.u3.in6 = nla_get_in6_addr(tb[CTA_IP_V6_SRC]); - t->dst.u3.in6 = nla_get_in6_addr(tb[CTA_IP_V6_DST]); - - return 0; -} -#endif - static int ipv6_hooks_register(struct net *net) { struct conntrack6_net *cnet = net_generic(net, conntrack6_net_id); @@ -345,13 +310,6 @@ const struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6 = { .pkt_to_tuple = ipv6_pkt_to_tuple, .invert_tuple = ipv6_invert_tuple, .get_l4proto = ipv6_get_l4proto, -#if IS_ENABLED(CONFIG_NF_CT_NETLINK) - .tuple_to_nlattr = ipv6_tuple_to_nlattr, - .nlattr_to_tuple = ipv6_nlattr_to_tuple, - .nla_policy = ipv6_nla_policy, - .nla_size = NLA_ALIGN(NLA_HDRLEN + sizeof(u32[4])) + - NLA_ALIGN(NLA_HDRLEN + sizeof(u32[4])), -#endif .net_ns_get = ipv6_hooks_register, .net_ns_put = ipv6_hooks_unregister, .me = THIS_MODULE, @@ -409,12 +367,6 @@ static int __init nf_conntrack_l3proto_ipv6_init(void) need_conntrack(); -#if IS_ENABLED(CONFIG_NF_CT_NETLINK) - if (WARN_ON(nla_policy_len(ipv6_nla_policy, CTA_IP_MAX + 1) != - nf_conntrack_l3proto_ipv6.nla_size)) - return -EINVAL; -#endif - ret = nf_register_sockopt(&so_getorigdst6); if (ret < 0) { pr_err("Unable to register netfilter socket option\n"); diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c index c87b48359e8f..e631be25337e 100644 --- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c +++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c @@ -23,7 +23,6 @@ #include #include #include -#include #include #include #endif diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 853b23206bb7..3f586ba23d92 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -610,7 +610,6 @@ static int exp_seq_show(struct seq_file *s, void *v) expect->tuple.src.l3num, expect->tuple.dst.protonum); print_tuple(s, &expect->tuple, - __nf_ct_l3proto_find(expect->tuple.src.l3num), __nf_ct_l4proto_find(expect->tuple.src.l3num, expect->tuple.dst.protonum)); diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index a75b11c39312..a55a58c706a9 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -24,7 +24,6 @@ #include #include -#include #include #include #include diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 20a2e37c76d1..40152b9ad772 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -38,7 +38,6 @@ #include #include #include -#include #include #include #include @@ -81,9 +80,26 @@ nla_put_failure: return -1; } +static int ipv4_tuple_to_nlattr(struct sk_buff *skb, + const struct nf_conntrack_tuple *tuple) +{ + if (nla_put_in_addr(skb, CTA_IP_V4_SRC, tuple->src.u3.ip) || + nla_put_in_addr(skb, CTA_IP_V4_DST, tuple->dst.u3.ip)) + return -EMSGSIZE; + return 0; +} + +static int ipv6_tuple_to_nlattr(struct sk_buff *skb, + const struct nf_conntrack_tuple *tuple) +{ + if (nla_put_in6_addr(skb, CTA_IP_V6_SRC, &tuple->src.u3.in6) || + nla_put_in6_addr(skb, CTA_IP_V6_DST, &tuple->dst.u3.in6)) + return -EMSGSIZE; + return 0; +} + static int ctnetlink_dump_tuples_ip(struct sk_buff *skb, - const struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_l3proto *l3proto) + const struct nf_conntrack_tuple *tuple) { int ret = 0; struct nlattr *nest_parms; @@ -92,8 +108,14 @@ static int ctnetlink_dump_tuples_ip(struct sk_buff *skb, if (!nest_parms) goto nla_put_failure; - if (likely(l3proto->tuple_to_nlattr)) - ret = l3proto->tuple_to_nlattr(skb, tuple); + switch (tuple->src.l3num) { + case NFPROTO_IPV4: + ret = ipv4_tuple_to_nlattr(skb, tuple); + break; + case NFPROTO_IPV6: + ret = ipv6_tuple_to_nlattr(skb, tuple); + break; + } nla_nest_end(skb, nest_parms); @@ -106,13 +128,11 @@ nla_put_failure: static int ctnetlink_dump_tuples(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple) { - const struct nf_conntrack_l3proto *l3proto; const struct nf_conntrack_l4proto *l4proto; int ret; rcu_read_lock(); - l3proto = __nf_ct_l3proto_find(tuple->src.l3num); - ret = ctnetlink_dump_tuples_ip(skb, tuple, l3proto); + ret = ctnetlink_dump_tuples_ip(skb, tuple); if (ret >= 0) { l4proto = __nf_ct_l4proto_find(tuple->src.l3num, @@ -556,15 +576,20 @@ nla_put_failure: return -1; } +static const struct nla_policy cta_ip_nla_policy[CTA_IP_MAX + 1] = { + [CTA_IP_V4_SRC] = { .type = NLA_U32 }, + [CTA_IP_V4_DST] = { .type = NLA_U32 }, + [CTA_IP_V6_SRC] = { .len = sizeof(__be32) * 4 }, + [CTA_IP_V6_DST] = { .len = sizeof(__be32) * 4 }, +}; + #if defined(CONFIG_NETFILTER_NETLINK_GLUE_CT) || defined(CONFIG_NF_CONNTRACK_EVENTS) static size_t ctnetlink_proto_size(const struct nf_conn *ct) { - const struct nf_conntrack_l3proto *l3proto; const struct nf_conntrack_l4proto *l4proto; size_t len, len4 = 0; - l3proto = __nf_ct_l3proto_find(nf_ct_l3num(ct)); - len = l3proto->nla_size; + len = nla_policy_len(cta_ip_nla_policy, CTA_IP_MAX + 1); len *= 3u; /* ORIG, REPLY, MASTER */ l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct)); @@ -936,29 +961,54 @@ out: return skb->len; } +static int ipv4_nlattr_to_tuple(struct nlattr *tb[], + struct nf_conntrack_tuple *t) +{ + if (!tb[CTA_IP_V4_SRC] || !tb[CTA_IP_V4_DST]) + return -EINVAL; + + t->src.u3.ip = nla_get_in_addr(tb[CTA_IP_V4_SRC]); + t->dst.u3.ip = nla_get_in_addr(tb[CTA_IP_V4_DST]); + + return 0; +} + +static int ipv6_nlattr_to_tuple(struct nlattr *tb[], + struct nf_conntrack_tuple *t) +{ + if (!tb[CTA_IP_V6_SRC] || !tb[CTA_IP_V6_DST]) + return -EINVAL; + + t->src.u3.in6 = nla_get_in6_addr(tb[CTA_IP_V6_SRC]); + t->dst.u3.in6 = nla_get_in6_addr(tb[CTA_IP_V6_DST]); + + return 0; +} + static int ctnetlink_parse_tuple_ip(struct nlattr *attr, struct nf_conntrack_tuple *tuple) { struct nlattr *tb[CTA_IP_MAX+1]; - struct nf_conntrack_l3proto *l3proto; int ret = 0; ret = nla_parse_nested(tb, CTA_IP_MAX, attr, NULL, NULL); if (ret < 0) return ret; - rcu_read_lock(); - l3proto = __nf_ct_l3proto_find(tuple->src.l3num); + ret = nla_validate_nested(attr, CTA_IP_MAX, + cta_ip_nla_policy, NULL); + if (ret) + return ret; - if (likely(l3proto->nlattr_to_tuple)) { - ret = nla_validate_nested(attr, CTA_IP_MAX, - l3proto->nla_policy, NULL); - if (ret == 0) - ret = l3proto->nlattr_to_tuple(tb, tuple); + switch (tuple->src.l3num) { + case NFPROTO_IPV4: + ret = ipv4_nlattr_to_tuple(tb, tuple); + break; + case NFPROTO_IPV6: + ret = ipv6_nlattr_to_tuple(tb, tuple); + break; } - rcu_read_unlock(); - return ret; } @@ -2581,7 +2631,6 @@ static int ctnetlink_exp_dump_mask(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_tuple_mask *mask) { - const struct nf_conntrack_l3proto *l3proto; const struct nf_conntrack_l4proto *l4proto; struct nf_conntrack_tuple m; struct nlattr *nest_parms; @@ -2597,8 +2646,7 @@ static int ctnetlink_exp_dump_mask(struct sk_buff *skb, goto nla_put_failure; rcu_read_lock(); - l3proto = __nf_ct_l3proto_find(tuple->src.l3num); - ret = ctnetlink_dump_tuples_ip(skb, &m, l3proto); + ret = ctnetlink_dump_tuples_ip(skb, &m); if (ret >= 0) { l4proto = __nf_ct_l4proto_find(tuple->src.l3num, tuple->dst.protonum); diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index d88841fbc560..859cb303bb91 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -294,10 +294,7 @@ int nf_ct_l3proto_register(const struct nf_conntrack_l3proto *proto) if (proto->l3proto >= NFPROTO_NUMPROTO) return -EBUSY; -#if IS_ENABLED(CONFIG_NF_CT_NETLINK) - if (proto->tuple_to_nlattr && proto->nla_size == 0) - return -EINVAL; -#endif + mutex_lock(&nf_ct_proto_mutex); old = rcu_dereference_protected(nf_ct_l3protos[proto->l3proto], lockdep_is_held(&nf_ct_proto_mutex)); diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index b642c0b2495c..47b80fd0d2c3 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -24,7 +24,6 @@ #include #include -#include #include #include #include @@ -38,10 +37,9 @@ MODULE_LICENSE("GPL"); #ifdef CONFIG_NF_CONNTRACK_PROCFS void print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_l3proto *l3proto, const struct nf_conntrack_l4proto *l4proto) { - switch (l3proto->l3proto) { + switch (tuple->src.l3num) { case NFPROTO_IPV4: seq_printf(s, "src=%pI4 dst=%pI4 ", &tuple->src.u3.ip, &tuple->dst.u3.ip); @@ -282,7 +280,6 @@ static int ct_seq_show(struct seq_file *s, void *v) { struct nf_conntrack_tuple_hash *hash = v; struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(hash); - const struct nf_conntrack_l3proto *l3proto; const struct nf_conntrack_l4proto *l4proto; struct net *net = seq_file_net(s); int ret = 0; @@ -303,14 +300,12 @@ static int ct_seq_show(struct seq_file *s, void *v) if (!net_eq(nf_ct_net(ct), net)) goto release; - l3proto = __nf_ct_l3proto_find(nf_ct_l3num(ct)); - WARN_ON(!l3proto); l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct)); WARN_ON(!l4proto); ret = -ENOSPC; seq_printf(s, "%-8s %u %-8s %u ", - l3proto_name(l3proto->l3proto), nf_ct_l3num(ct), + l3proto_name(nf_ct_l3num(ct)), nf_ct_l3num(ct), l4proto_name(l4proto->l4proto), nf_ct_protonum(ct)); if (!test_bit(IPS_OFFLOAD_BIT, &ct->status)) @@ -320,7 +315,7 @@ static int ct_seq_show(struct seq_file *s, void *v) l4proto->print_conntrack(s, ct); print_tuple(s, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, - l3proto, l4proto); + l4proto); ct_show_zone(s, ct, NF_CT_ZONE_DIR_ORIG); @@ -333,8 +328,7 @@ static int ct_seq_show(struct seq_file *s, void *v) if (!(test_bit(IPS_SEEN_REPLY_BIT, &ct->status))) seq_puts(s, "[UNREPLIED] "); - print_tuple(s, &ct->tuplehash[IP_CT_DIR_REPLY].tuple, - l3proto, l4proto); + print_tuple(s, &ct->tuplehash[IP_CT_DIR_REPLY].tuple, l4proto); ct_show_zone(s, ct, NF_CT_ZONE_DIR_REPL); diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index 9ee5fa551fa6..9da4b8462004 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -26,7 +26,6 @@ #include #include #include -#include #include #include #include -- cgit v1.2.3 From 47a91b14de62e35d1466820cbb4c024b6c02dff1 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 29 Jun 2018 07:46:45 +0200 Subject: netfilter: conntrack: remove pkt_to_tuple indirection from l3 protocol trackers Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_l3proto.h | 7 ----- net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c | 17 ----------- net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c | 18 ------------ net/netfilter/nf_conntrack_core.c | 39 ++++++++++++++++++++++---- net/netfilter/nf_conntrack_l3proto_generic.c | 10 ------- 5 files changed, 33 insertions(+), 58 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_l3proto.h b/include/net/netfilter/nf_conntrack_l3proto.h index d07b5216a925..ece231450f30 100644 --- a/include/net/netfilter/nf_conntrack_l3proto.h +++ b/include/net/netfilter/nf_conntrack_l3proto.h @@ -24,13 +24,6 @@ struct nf_conntrack_l3proto { /* size of tuple nlattr, fills a hole */ u16 nla_size; - /* - * Try to fill in the third arg: nhoff is offset of l3 proto - * hdr. Return true if possible. - */ - bool (*pkt_to_tuple)(const struct sk_buff *skb, unsigned int nhoff, - struct nf_conntrack_tuple *tuple); - /* * Invert the per-proto part of the tuple: ie. turn xmit into reply. * Some packets can't be inverted: return 0 in that case. diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index 98ed12858c52..7ed56f61798b 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -38,22 +38,6 @@ struct conntrack4_net { unsigned int users; }; -static bool ipv4_pkt_to_tuple(const struct sk_buff *skb, unsigned int nhoff, - struct nf_conntrack_tuple *tuple) -{ - const __be32 *ap; - __be32 _addrs[2]; - ap = skb_header_pointer(skb, nhoff + offsetof(struct iphdr, saddr), - sizeof(u_int32_t) * 2, _addrs); - if (ap == NULL) - return false; - - tuple->src.u3.ip = ap[0]; - tuple->dst.u3.ip = ap[1]; - - return true; -} - static bool ipv4_invert_tuple(struct nf_conntrack_tuple *tuple, const struct nf_conntrack_tuple *orig) { @@ -322,7 +306,6 @@ static void ipv4_hooks_unregister(struct net *net) const struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 = { .l3proto = PF_INET, - .pkt_to_tuple = ipv4_pkt_to_tuple, .invert_tuple = ipv4_invert_tuple, .get_l4proto = ipv4_get_l4proto, .net_ns_get = ipv4_hooks_register, diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index 13a660ae5799..bdb1709bb951 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -41,23 +41,6 @@ struct conntrack6_net { unsigned int users; }; -static bool ipv6_pkt_to_tuple(const struct sk_buff *skb, unsigned int nhoff, - struct nf_conntrack_tuple *tuple) -{ - const u_int32_t *ap; - u_int32_t _addrs[8]; - - ap = skb_header_pointer(skb, nhoff + offsetof(struct ipv6hdr, saddr), - sizeof(_addrs), _addrs); - if (ap == NULL) - return false; - - memcpy(tuple->src.u3.ip6, ap, sizeof(tuple->src.u3.ip6)); - memcpy(tuple->dst.u3.ip6, ap + 4, sizeof(tuple->dst.u3.ip6)); - - return true; -} - static bool ipv6_invert_tuple(struct nf_conntrack_tuple *tuple, const struct nf_conntrack_tuple *orig) { @@ -307,7 +290,6 @@ static void ipv6_hooks_unregister(struct net *net) const struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6 = { .l3proto = PF_INET6, - .pkt_to_tuple = ipv6_pkt_to_tuple, .invert_tuple = ipv6_invert_tuple, .get_l4proto = ipv6_get_l4proto, .net_ns_get = ipv6_hooks_register, diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index be0ab81e6b2c..66b2ebae2747 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -230,15 +230,43 @@ nf_ct_get_tuple(const struct sk_buff *skb, u_int8_t protonum, struct net *net, struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_l3proto *l3proto, const struct nf_conntrack_l4proto *l4proto) { + unsigned int size; + const __be32 *ap; + __be32 _addrs[8]; + memset(tuple, 0, sizeof(*tuple)); tuple->src.l3num = l3num; - if (l3proto->pkt_to_tuple(skb, nhoff, tuple) == 0) + switch (l3num) { + case NFPROTO_IPV4: + nhoff += offsetof(struct iphdr, saddr); + size = 2 * sizeof(__be32); + break; + case NFPROTO_IPV6: + nhoff += offsetof(struct ipv6hdr, saddr); + size = sizeof(_addrs); + break; + default: + return true; + } + + ap = skb_header_pointer(skb, nhoff, size, _addrs); + if (!ap) return false; + switch (l3num) { + case NFPROTO_IPV4: + tuple->src.u3.ip = ap[0]; + tuple->dst.u3.ip = ap[1]; + break; + case NFPROTO_IPV6: + memcpy(tuple->src.u3.ip6, ap, sizeof(tuple->src.u3.ip6)); + memcpy(tuple->dst.u3.ip6, ap + 4, sizeof(tuple->dst.u3.ip6)); + break; + } + tuple->dst.protonum = protonum; tuple->dst.dir = IP_CT_DIR_ORIGINAL; @@ -267,7 +295,7 @@ bool nf_ct_get_tuplepr(const struct sk_buff *skb, unsigned int nhoff, l4proto = __nf_ct_l4proto_find(l3num, protonum); ret = nf_ct_get_tuple(skb, nhoff, protoff, l3num, protonum, net, tuple, - l3proto, l4proto); + l4proto); rcu_read_unlock(); return ret; @@ -1318,8 +1346,7 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl, u32 hash; if (!nf_ct_get_tuple(skb, skb_network_offset(skb), - dataoff, l3num, protonum, net, &tuple, l3proto, - l4proto)) { + dataoff, l3num, protonum, net, &tuple, l4proto)) { pr_debug("Can't get tuple\n"); return 0; } @@ -1633,7 +1660,7 @@ static int nf_conntrack_update(struct net *net, struct sk_buff *skb) l4proto = nf_ct_l4proto_find_get(l3num, l4num); if (!nf_ct_get_tuple(skb, skb_network_offset(skb), dataoff, l3num, - l4num, net, &tuple, l3proto, l4proto)) + l4num, net, &tuple, l4proto)) return -1; if (ct->status & IPS_SRC_NAT) { diff --git a/net/netfilter/nf_conntrack_l3proto_generic.c b/net/netfilter/nf_conntrack_l3proto_generic.c index 397e6911214f..0b01c9970e99 100644 --- a/net/netfilter/nf_conntrack_l3proto_generic.c +++ b/net/netfilter/nf_conntrack_l3proto_generic.c @@ -31,15 +31,6 @@ #include #include -static bool generic_pkt_to_tuple(const struct sk_buff *skb, unsigned int nhoff, - struct nf_conntrack_tuple *tuple) -{ - memset(&tuple->src.u3, 0, sizeof(tuple->src.u3)); - memset(&tuple->dst.u3, 0, sizeof(tuple->dst.u3)); - - return true; -} - static bool generic_invert_tuple(struct nf_conntrack_tuple *tuple, const struct nf_conntrack_tuple *orig) { @@ -59,7 +50,6 @@ static int generic_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, struct nf_conntrack_l3proto nf_conntrack_l3proto_generic __read_mostly = { .l3proto = PF_UNSPEC, - .pkt_to_tuple = generic_pkt_to_tuple, .invert_tuple = generic_invert_tuple, .get_l4proto = generic_get_l4proto, }; -- cgit v1.2.3 From d1b6fe94941f43e4743d5fea953d16b0a001c2c6 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 29 Jun 2018 07:46:46 +0200 Subject: netfilter: conntrack: remove invert_tuple indirection from l3 protocol trackers Its simpler to just handle it directly in nf_ct_invert_tuple(). Also gets rid of need to pass l3proto pointer to resolve_conntrack(). Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_core.h | 1 - include/net/netfilter/nf_conntrack_l3proto.h | 7 ------- net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c | 10 ---------- net/ipv4/netfilter/nf_conntrack_proto_icmp.c | 3 +-- net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c | 10 ---------- net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c | 3 +-- net/netfilter/nf_conntrack_core.c | 26 ++++++++++++++++---------- net/netfilter/nf_conntrack_l3proto_generic.c | 10 ---------- 8 files changed, 18 insertions(+), 52 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index d454a53ba646..35461b2d3462 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -42,7 +42,6 @@ void nf_conntrack_cleanup_end(void); bool nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse, const struct nf_conntrack_tuple *orig, - const struct nf_conntrack_l3proto *l3proto, const struct nf_conntrack_l4proto *l4proto); /* Find a connection corresponding to a tuple. */ diff --git a/include/net/netfilter/nf_conntrack_l3proto.h b/include/net/netfilter/nf_conntrack_l3proto.h index ece231450f30..164641c743a5 100644 --- a/include/net/netfilter/nf_conntrack_l3proto.h +++ b/include/net/netfilter/nf_conntrack_l3proto.h @@ -24,13 +24,6 @@ struct nf_conntrack_l3proto { /* size of tuple nlattr, fills a hole */ u16 nla_size; - /* - * Invert the per-proto part of the tuple: ie. turn xmit into reply. - * Some packets can't be inverted: return 0 in that case. - */ - bool (*invert_tuple)(struct nf_conntrack_tuple *inverse, - const struct nf_conntrack_tuple *orig); - /* * Called before tracking. * *dataoff: offset of protocol header (TCP, UDP,...) in skb diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index 7ed56f61798b..e10e38c443ab 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -38,15 +38,6 @@ struct conntrack4_net { unsigned int users; }; -static bool ipv4_invert_tuple(struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_tuple *orig) -{ - tuple->src.u3.ip = orig->dst.u3.ip; - tuple->dst.u3.ip = orig->src.u3.ip; - - return true; -} - static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, unsigned int *dataoff, u_int8_t *protonum) { @@ -306,7 +297,6 @@ static void ipv4_hooks_unregister(struct net *net) const struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 = { .l3proto = PF_INET, - .invert_tuple = ipv4_invert_tuple, .get_l4proto = ipv4_get_l4proto, .net_ns_get = ipv4_hooks_register, .net_ns_put = ipv4_hooks_unregister, diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c index 5c15beafa711..34095949a003 100644 --- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c +++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c @@ -142,8 +142,7 @@ icmp_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, /* Ordinarily, we'd expect the inverted tupleproto, but it's been preserved inside the ICMP. */ - if (!nf_ct_invert_tuple(&innertuple, &origtuple, - &nf_conntrack_l3proto_ipv4, innerproto)) { + if (!nf_ct_invert_tuple(&innertuple, &origtuple, innerproto)) { pr_debug("icmp_error_message: no match\n"); return -NF_ACCEPT; } diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index bdb1709bb951..f8051fe20489 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -41,15 +41,6 @@ struct conntrack6_net { unsigned int users; }; -static bool ipv6_invert_tuple(struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_tuple *orig) -{ - memcpy(tuple->src.u3.ip6, orig->dst.u3.ip6, sizeof(tuple->src.u3.ip6)); - memcpy(tuple->dst.u3.ip6, orig->src.u3.ip6, sizeof(tuple->dst.u3.ip6)); - - return true; -} - static int ipv6_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, unsigned int *dataoff, u_int8_t *protonum) { @@ -290,7 +281,6 @@ static void ipv6_hooks_unregister(struct net *net) const struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6 = { .l3proto = PF_INET6, - .invert_tuple = ipv6_invert_tuple, .get_l4proto = ipv6_get_l4proto, .net_ns_get = ipv6_hooks_register, .net_ns_put = ipv6_hooks_unregister, diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c index 2548e2c8aedd..8bcbc2f15bd5 100644 --- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c @@ -152,8 +152,7 @@ icmpv6_error_message(struct net *net, struct nf_conn *tmpl, /* Ordinarily, we'd expect the inverted tupleproto, but it's been preserved inside the ICMP. */ - if (!nf_ct_invert_tuple(&intuple, &origtuple, - &nf_conntrack_l3proto_ipv6, inproto)) { + if (!nf_ct_invert_tuple(&intuple, &origtuple, inproto)) { pr_debug("icmpv6_error: Can't invert tuple\n"); return -NF_ACCEPT; } diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 66b2ebae2747..14c040805b32 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -305,14 +305,24 @@ EXPORT_SYMBOL_GPL(nf_ct_get_tuplepr); bool nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse, const struct nf_conntrack_tuple *orig, - const struct nf_conntrack_l3proto *l3proto, const struct nf_conntrack_l4proto *l4proto) { memset(inverse, 0, sizeof(*inverse)); inverse->src.l3num = orig->src.l3num; - if (l3proto->invert_tuple(inverse, orig) == 0) - return false; + + switch (orig->src.l3num) { + case NFPROTO_IPV4: + inverse->src.u3.ip = orig->dst.u3.ip; + inverse->dst.u3.ip = orig->src.u3.ip; + break; + case NFPROTO_IPV6: + inverse->src.u3.in6 = orig->dst.u3.in6; + inverse->dst.u3.in6 = orig->src.u3.in6; + break; + default: + break; + } inverse->dst.dir = !orig->dst.dir; @@ -1222,7 +1232,6 @@ EXPORT_SYMBOL_GPL(nf_conntrack_free); static noinline struct nf_conntrack_tuple_hash * init_conntrack(struct net *net, struct nf_conn *tmpl, const struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_l3proto *l3proto, const struct nf_conntrack_l4proto *l4proto, struct sk_buff *skb, unsigned int dataoff, u32 hash) @@ -1237,7 +1246,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, struct nf_conntrack_zone tmp; unsigned int *timeouts; - if (!nf_ct_invert_tuple(&repl_tuple, tuple, l3proto, l4proto)) { + if (!nf_ct_invert_tuple(&repl_tuple, tuple, l4proto)) { pr_debug("Can't invert tuple.\n"); return NULL; } @@ -1334,7 +1343,6 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl, unsigned int dataoff, u_int16_t l3num, u_int8_t protonum, - const struct nf_conntrack_l3proto *l3proto, const struct nf_conntrack_l4proto *l4proto) { const struct nf_conntrack_zone *zone; @@ -1356,7 +1364,7 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl, hash = hash_conntrack_raw(&tuple, net); h = __nf_conntrack_find_get(net, zone, &tuple, hash); if (!h) { - h = init_conntrack(net, tmpl, &tuple, l3proto, l4proto, + h = init_conntrack(net, tmpl, &tuple, l4proto, skb, dataoff, hash); if (!h) return 0; @@ -1439,8 +1447,7 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum, goto out; } repeat: - ret = resolve_normal_ct(net, tmpl, skb, dataoff, pf, protonum, - l3proto, l4proto); + ret = resolve_normal_ct(net, tmpl, skb, dataoff, pf, protonum, l4proto); if (ret < 0) { /* Too stressed to deal. */ NF_CT_STAT_INC_ATOMIC(net, drop); @@ -1497,7 +1504,6 @@ bool nf_ct_invert_tuplepr(struct nf_conntrack_tuple *inverse, rcu_read_lock(); ret = nf_ct_invert_tuple(inverse, orig, - __nf_ct_l3proto_find(orig->src.l3num), __nf_ct_l4proto_find(orig->src.l3num, orig->dst.protonum)); rcu_read_unlock(); diff --git a/net/netfilter/nf_conntrack_l3proto_generic.c b/net/netfilter/nf_conntrack_l3proto_generic.c index 0b01c9970e99..d6a8fe591ccc 100644 --- a/net/netfilter/nf_conntrack_l3proto_generic.c +++ b/net/netfilter/nf_conntrack_l3proto_generic.c @@ -31,15 +31,6 @@ #include #include -static bool generic_invert_tuple(struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_tuple *orig) -{ - memset(&tuple->src.u3, 0, sizeof(tuple->src.u3)); - memset(&tuple->dst.u3, 0, sizeof(tuple->dst.u3)); - - return true; -} - static int generic_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, unsigned int *dataoff, u_int8_t *protonum) { @@ -50,7 +41,6 @@ static int generic_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, struct nf_conntrack_l3proto nf_conntrack_l3proto_generic __read_mostly = { .l3proto = PF_UNSPEC, - .invert_tuple = generic_invert_tuple, .get_l4proto = generic_get_l4proto, }; EXPORT_SYMBOL_GPL(nf_conntrack_l3proto_generic); -- cgit v1.2.3 From 6816d931cab009024b68c11c4cf752f8bf9a1e32 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 29 Jun 2018 07:46:47 +0200 Subject: netfilter: conntrack: remove get_l4proto indirection from l3 protocol trackers Handle it in the core instead. ipv6_skip_exthdr() is built-in even if ipv6 is a module, i.e. this doesn't create an ipv6 dependency. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_l3proto.h | 8 -- net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c | 30 ------- net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c | 29 ------- net/netfilter/Makefile | 2 +- net/netfilter/nf_conntrack_core.c | 108 ++++++++++++++++++++----- net/netfilter/nf_conntrack_l3proto_generic.c | 46 ----------- net/netfilter/nf_conntrack_proto.c | 5 ++ 7 files changed, 94 insertions(+), 134 deletions(-) delete mode 100644 net/netfilter/nf_conntrack_l3proto_generic.c (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_l3proto.h b/include/net/netfilter/nf_conntrack_l3proto.h index 164641c743a5..5f160375c93a 100644 --- a/include/net/netfilter/nf_conntrack_l3proto.h +++ b/include/net/netfilter/nf_conntrack_l3proto.h @@ -24,14 +24,6 @@ struct nf_conntrack_l3proto { /* size of tuple nlattr, fills a hole */ u16 nla_size; - /* - * Called before tracking. - * *dataoff: offset of protocol header (TCP, UDP,...) in skb - * *protonum: protocol number - */ - int (*get_l4proto)(const struct sk_buff *skb, unsigned int nhoff, - unsigned int *dataoff, u_int8_t *protonum); - /* Called when netns wants to use connection tracking */ int (*net_ns_get)(struct net *); void (*net_ns_put)(struct net *); diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index e10e38c443ab..9fbf6c7f8ece 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -38,35 +38,6 @@ struct conntrack4_net { unsigned int users; }; -static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, - unsigned int *dataoff, u_int8_t *protonum) -{ - const struct iphdr *iph; - struct iphdr _iph; - - iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph); - if (iph == NULL) - return -NF_ACCEPT; - - /* Conntrack defragments packets, we might still see fragments - * inside ICMP packets though. */ - if (iph->frag_off & htons(IP_OFFSET)) - return -NF_ACCEPT; - - *dataoff = nhoff + (iph->ihl << 2); - *protonum = iph->protocol; - - /* Check bogus IP headers */ - if (*dataoff > skb->len) { - pr_debug("nf_conntrack_ipv4: bogus IPv4 packet: " - "nhoff %u, ihl %u, skblen %u\n", - nhoff, iph->ihl << 2, skb->len); - return -NF_ACCEPT; - } - - return NF_ACCEPT; -} - static unsigned int ipv4_helper(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) @@ -297,7 +268,6 @@ static void ipv4_hooks_unregister(struct net *net) const struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 = { .l3proto = PF_INET, - .get_l4proto = ipv4_get_l4proto, .net_ns_get = ipv4_hooks_register, .net_ns_put = ipv4_hooks_unregister, .me = THIS_MODULE, diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index f8051fe20489..37ab25645cf2 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -41,34 +41,6 @@ struct conntrack6_net { unsigned int users; }; -static int ipv6_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, - unsigned int *dataoff, u_int8_t *protonum) -{ - unsigned int extoff = nhoff + sizeof(struct ipv6hdr); - __be16 frag_off; - int protoff; - u8 nexthdr; - - if (skb_copy_bits(skb, nhoff + offsetof(struct ipv6hdr, nexthdr), - &nexthdr, sizeof(nexthdr)) != 0) { - pr_debug("ip6_conntrack_core: can't get nexthdr\n"); - return -NF_ACCEPT; - } - protoff = ipv6_skip_exthdr(skb, extoff, &nexthdr, &frag_off); - /* - * (protoff == skb->len) means the packet has not data, just - * IPv6 and possibly extensions headers, but it is tracked anyway - */ - if (protoff < 0 || (frag_off & htons(~0x7)) != 0) { - pr_debug("ip6_conntrack_core: can't find proto in pkt\n"); - return -NF_ACCEPT; - } - - *dataoff = protoff; - *protonum = nexthdr; - return NF_ACCEPT; -} - static unsigned int ipv6_helper(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) @@ -281,7 +253,6 @@ static void ipv6_hooks_unregister(struct net *net) const struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6 = { .l3proto = PF_INET6, - .get_l4proto = ipv6_get_l4proto, .net_ns_get = ipv6_hooks_register, .net_ns_put = ipv6_hooks_unregister, .me = THIS_MODULE, diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 44449389e527..f132ea850778 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 netfilter-objs := core.o nf_log.o nf_queue.o nf_sockopt.o utils.o -nf_conntrack-y := nf_conntrack_core.o nf_conntrack_standalone.o nf_conntrack_expect.o nf_conntrack_helper.o nf_conntrack_proto.o nf_conntrack_l3proto_generic.o nf_conntrack_proto_generic.o nf_conntrack_proto_tcp.o nf_conntrack_proto_udp.o nf_conntrack_extend.o nf_conntrack_acct.o nf_conntrack_seqadj.o +nf_conntrack-y := nf_conntrack_core.o nf_conntrack_standalone.o nf_conntrack_expect.o nf_conntrack_helper.o nf_conntrack_proto.o nf_conntrack_proto_generic.o nf_conntrack_proto_tcp.o nf_conntrack_proto_udp.o nf_conntrack_extend.o nf_conntrack_acct.o nf_conntrack_seqadj.o nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMEOUT) += nf_conntrack_timeout.o nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMESTAMP) += nf_conntrack_timestamp.o nf_conntrack-$(CONFIG_NF_CONNTRACK_EVENTS) += nf_conntrack_ecache.o diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 14c040805b32..0674c6e5bfed 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -37,7 +37,6 @@ #include #include -#include #include #include #include @@ -55,6 +54,7 @@ #include #include #include +#include #include "nf_internals.h" @@ -273,21 +273,94 @@ nf_ct_get_tuple(const struct sk_buff *skb, return l4proto->pkt_to_tuple(skb, dataoff, net, tuple); } +static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, + u_int8_t *protonum) +{ + int dataoff = -1; +#if IS_ENABLED(CONFIG_NF_CONNTRACK_IPV4) + const struct iphdr *iph; + struct iphdr _iph; + + iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph); + if (!iph) + return -1; + + /* Conntrack defragments packets, we might still see fragments + * inside ICMP packets though. + */ + if (iph->frag_off & htons(IP_OFFSET)) + return -1; + + dataoff = nhoff + (iph->ihl << 2); + *protonum = iph->protocol; + + /* Check bogus IP headers */ + if (dataoff > skb->len) { + pr_debug("bogus IPv4 packet: nhoff %u, ihl %u, skblen %u\n", + nhoff, iph->ihl << 2, skb->len); + return -1; + } +#endif + return dataoff; +} + +static int ipv6_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, + u8 *protonum) +{ + int protoff = -1; +#if IS_ENABLED(CONFIG_NF_CONNTRACK_IPV6) + unsigned int extoff = nhoff + sizeof(struct ipv6hdr); + __be16 frag_off; + u8 nexthdr; + + if (skb_copy_bits(skb, nhoff + offsetof(struct ipv6hdr, nexthdr), + &nexthdr, sizeof(nexthdr)) != 0) { + pr_debug("can't get nexthdr\n"); + return -1; + } + protoff = ipv6_skip_exthdr(skb, extoff, &nexthdr, &frag_off); + /* + * (protoff == skb->len) means the packet has not data, just + * IPv6 and possibly extensions headers, but it is tracked anyway + */ + if (protoff < 0 || (frag_off & htons(~0x7)) != 0) { + pr_debug("can't find proto in pkt\n"); + return -1; + } + + *protonum = nexthdr; +#endif + return protoff; +} + +static int get_l4proto(const struct sk_buff *skb, + unsigned int nhoff, u8 pf, u8 *l4num) +{ + switch (pf) { + case NFPROTO_IPV4: + return ipv4_get_l4proto(skb, nhoff, l4num); + case NFPROTO_IPV6: + return ipv6_get_l4proto(skb, nhoff, l4num); + default: + *l4num = 0; + break; + } + return -1; +} + bool nf_ct_get_tuplepr(const struct sk_buff *skb, unsigned int nhoff, u_int16_t l3num, struct net *net, struct nf_conntrack_tuple *tuple) { - const struct nf_conntrack_l3proto *l3proto; const struct nf_conntrack_l4proto *l4proto; - unsigned int protoff; - u_int8_t protonum; + u8 protonum; + int protoff; int ret; rcu_read_lock(); - l3proto = __nf_ct_l3proto_find(l3num); - ret = l3proto->get_l4proto(skb, nhoff, &protoff, &protonum); - if (ret != NF_ACCEPT) { + protoff = get_l4proto(skb, nhoff, l3num, &protonum); + if (protoff <= 0) { rcu_read_unlock(); return false; } @@ -1397,14 +1470,12 @@ unsigned int nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum, struct sk_buff *skb) { - const struct nf_conntrack_l3proto *l3proto; const struct nf_conntrack_l4proto *l4proto; struct nf_conn *ct, *tmpl; enum ip_conntrack_info ctinfo; unsigned int *timeouts; - unsigned int dataoff; u_int8_t protonum; - int ret; + int dataoff, ret; tmpl = nf_ct_get(skb, &ctinfo); if (tmpl || ctinfo == IP_CT_UNTRACKED) { @@ -1418,14 +1489,12 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum, } /* rcu_read_lock()ed by nf_hook_thresh */ - l3proto = __nf_ct_l3proto_find(pf); - ret = l3proto->get_l4proto(skb, skb_network_offset(skb), - &dataoff, &protonum); - if (ret <= 0) { + dataoff = get_l4proto(skb, skb_network_offset(skb), pf, &protonum); + if (dataoff <= 0) { pr_debug("not prepared to track yet or error occurred\n"); NF_CT_STAT_INC_ATOMIC(net, error); NF_CT_STAT_INC_ATOMIC(net, invalid); - ret = -ret; + ret = NF_ACCEPT; goto out; } @@ -1641,14 +1710,14 @@ static void nf_conntrack_attach(struct sk_buff *nskb, const struct sk_buff *skb) static int nf_conntrack_update(struct net *net, struct sk_buff *skb) { - const struct nf_conntrack_l3proto *l3proto; const struct nf_conntrack_l4proto *l4proto; struct nf_conntrack_tuple_hash *h; struct nf_conntrack_tuple tuple; enum ip_conntrack_info ctinfo; struct nf_nat_hook *nat_hook; - unsigned int dataoff, status; + unsigned int status; struct nf_conn *ct; + int dataoff; u16 l3num; u8 l4num; @@ -1657,10 +1726,9 @@ static int nf_conntrack_update(struct net *net, struct sk_buff *skb) return 0; l3num = nf_ct_l3num(ct); - l3proto = nf_ct_l3proto_find_get(l3num); - if (l3proto->get_l4proto(skb, skb_network_offset(skb), &dataoff, - &l4num) <= 0) + dataoff = get_l4proto(skb, skb_network_offset(skb), l3num, &l4num); + if (dataoff <= 0) return -1; l4proto = nf_ct_l4proto_find_get(l3num, l4num); diff --git a/net/netfilter/nf_conntrack_l3proto_generic.c b/net/netfilter/nf_conntrack_l3proto_generic.c deleted file mode 100644 index d6a8fe591ccc..000000000000 --- a/net/netfilter/nf_conntrack_l3proto_generic.c +++ /dev/null @@ -1,46 +0,0 @@ -/* - * (C) 2003,2004 USAGI/WIDE Project - * - * Based largely upon the original ip_conntrack code which - * had the following copyright information: - * - * (C) 1999-2001 Paul `Rusty' Russell - * (C) 2002-2004 Netfilter Core Team - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * Author: - * Yasuyuki Kozakai @USAGI - */ - -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include -#include - -static int generic_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, - unsigned int *dataoff, u_int8_t *protonum) -{ - /* Never track !!! */ - return -NF_ACCEPT; -} - - -struct nf_conntrack_l3proto nf_conntrack_l3proto_generic __read_mostly = { - .l3proto = PF_UNSPEC, - .get_l4proto = generic_get_l4proto, -}; -EXPORT_SYMBOL_GPL(nf_conntrack_l3proto_generic); diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index 859cb303bb91..39df72bb9d56 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -35,6 +35,11 @@ EXPORT_SYMBOL_GPL(nf_ct_l3protos); static DEFINE_MUTEX(nf_ct_proto_mutex); +struct nf_conntrack_l3proto nf_conntrack_l3proto_generic __read_mostly = { + .l3proto = PF_UNSPEC, +}; +EXPORT_SYMBOL_GPL(nf_conntrack_l3proto_generic); + #ifdef CONFIG_SYSCTL static int nf_ct_register_sysctl(struct net *net, -- cgit v1.2.3 From 8b3892ea8718920d29432328fe9544d89a429614 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 29 Jun 2018 07:46:48 +0200 Subject: netfilter: conntrack: avoid calls to l4proto invert_tuple Handle the common cases (tcp, udp, etc). in the core and only do the indirect call for the protocols that need it (GRE for instance). Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_l4proto.h | 2 +- net/netfilter/nf_conntrack_core.c | 8 +++++++- net/netfilter/nf_conntrack_proto_dccp.c | 10 ---------- net/netfilter/nf_conntrack_proto_generic.c | 10 ---------- net/netfilter/nf_conntrack_proto_gre.c | 10 ---------- net/netfilter/nf_conntrack_proto_sctp.c | 10 ---------- net/netfilter/nf_conntrack_proto_tcp.c | 10 ---------- net/netfilter/nf_conntrack_proto_udp.c | 12 ------------ 8 files changed, 8 insertions(+), 64 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index a7220eef9aee..6a55e337a161 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -36,7 +36,7 @@ struct nf_conntrack_l4proto { struct net *net, struct nf_conntrack_tuple *tuple); /* Invert the per-proto part of the tuple: ie. turn xmit into reply. - * Some packets can't be inverted: return 0 in that case. + * Only used by icmp, most protocols use a generic version. */ bool (*invert_tuple)(struct nf_conntrack_tuple *inverse, const struct nf_conntrack_tuple *orig); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 0674c6e5bfed..92efce69b690 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -400,7 +400,13 @@ nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse, inverse->dst.dir = !orig->dst.dir; inverse->dst.protonum = orig->dst.protonum; - return l4proto->invert_tuple(inverse, orig); + + if (unlikely(l4proto->invert_tuple)) + return l4proto->invert_tuple(inverse, orig); + + inverse->src.u.all = orig->dst.u.all; + inverse->dst.u.all = orig->src.u.all; + return true; } EXPORT_SYMBOL_GPL(nf_ct_invert_tuple); diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index abe647d5b8c6..05620c03f138 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -403,14 +403,6 @@ static bool dccp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, return true; } -static bool dccp_invert_tuple(struct nf_conntrack_tuple *inv, - const struct nf_conntrack_tuple *tuple) -{ - inv->src.u.dccp.port = tuple->dst.u.dccp.port; - inv->dst.u.dccp.port = tuple->src.u.dccp.port; - return true; -} - static bool dccp_new(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, unsigned int *timeouts) { @@ -865,7 +857,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp4 = { .l3proto = AF_INET, .l4proto = IPPROTO_DCCP, .pkt_to_tuple = dccp_pkt_to_tuple, - .invert_tuple = dccp_invert_tuple, .new = dccp_new, .packet = dccp_packet, .get_timeouts = dccp_get_timeouts, @@ -901,7 +892,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp6 = { .l3proto = AF_INET6, .l4proto = IPPROTO_DCCP, .pkt_to_tuple = dccp_pkt_to_tuple, - .invert_tuple = dccp_invert_tuple, .new = dccp_new, .packet = dccp_packet, .get_timeouts = dccp_get_timeouts, diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c index 6c6896d21cd7..4dfe40aa9446 100644 --- a/net/netfilter/nf_conntrack_proto_generic.c +++ b/net/netfilter/nf_conntrack_proto_generic.c @@ -41,15 +41,6 @@ static bool generic_pkt_to_tuple(const struct sk_buff *skb, return true; } -static bool generic_invert_tuple(struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_tuple *orig) -{ - tuple->src.u.all = 0; - tuple->dst.u.all = 0; - - return true; -} - static unsigned int *generic_get_timeouts(struct net *net) { return &(generic_pernet(net)->timeout); @@ -168,7 +159,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_generic = .l3proto = PF_UNSPEC, .l4proto = 255, .pkt_to_tuple = generic_pkt_to_tuple, - .invert_tuple = generic_invert_tuple, .packet = generic_packet, .get_timeouts = generic_get_timeouts, .new = generic_new, diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index d049ea5a3770..0bd40eb06b55 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -179,15 +179,6 @@ EXPORT_SYMBOL_GPL(nf_ct_gre_keymap_destroy); /* PUBLIC CONNTRACK PROTO HELPER FUNCTIONS */ -/* invert gre part of tuple */ -static bool gre_invert_tuple(struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_tuple *orig) -{ - tuple->dst.u.gre.key = orig->src.u.gre.key; - tuple->src.u.gre.key = orig->dst.u.gre.key; - return true; -} - /* gre hdr info to tuple */ static bool gre_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, struct net *net, struct nf_conntrack_tuple *tuple) @@ -356,7 +347,6 @@ static const struct nf_conntrack_l4proto nf_conntrack_l4proto_gre4 = { .l3proto = AF_INET, .l4proto = IPPROTO_GRE, .pkt_to_tuple = gre_pkt_to_tuple, - .invert_tuple = gre_invert_tuple, #ifdef CONFIG_NF_CONNTRACK_PROCFS .print_conntrack = gre_print_conntrack, #endif diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index fb9a35d16069..148957a5cf3e 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -166,14 +166,6 @@ static bool sctp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, return true; } -static bool sctp_invert_tuple(struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_tuple *orig) -{ - tuple->src.u.sctp.port = orig->dst.u.sctp.port; - tuple->dst.u.sctp.port = orig->src.u.sctp.port; - return true; -} - #ifdef CONFIG_NF_CONNTRACK_PROCFS /* Print out the private part of the conntrack. */ static void sctp_print_conntrack(struct seq_file *s, struct nf_conn *ct) @@ -781,7 +773,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4 = { .l3proto = PF_INET, .l4proto = IPPROTO_SCTP, .pkt_to_tuple = sctp_pkt_to_tuple, - .invert_tuple = sctp_invert_tuple, #ifdef CONFIG_NF_CONNTRACK_PROCFS .print_conntrack = sctp_print_conntrack, #endif @@ -818,7 +809,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp6 = { .l3proto = PF_INET6, .l4proto = IPPROTO_SCTP, .pkt_to_tuple = sctp_pkt_to_tuple, - .invert_tuple = sctp_invert_tuple, #ifdef CONFIG_NF_CONNTRACK_PROCFS .print_conntrack = sctp_print_conntrack, #endif diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 8e67910185a0..03cff1e3066a 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -293,14 +293,6 @@ static bool tcp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, return true; } -static bool tcp_invert_tuple(struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_tuple *orig) -{ - tuple->src.u.tcp.port = orig->dst.u.tcp.port; - tuple->dst.u.tcp.port = orig->src.u.tcp.port; - return true; -} - #ifdef CONFIG_NF_CONNTRACK_PROCFS /* Print out the private part of the conntrack. */ static void tcp_print_conntrack(struct seq_file *s, struct nf_conn *ct) @@ -1560,7 +1552,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4 = .l3proto = PF_INET, .l4proto = IPPROTO_TCP, .pkt_to_tuple = tcp_pkt_to_tuple, - .invert_tuple = tcp_invert_tuple, #ifdef CONFIG_NF_CONNTRACK_PROCFS .print_conntrack = tcp_print_conntrack, #endif @@ -1598,7 +1589,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6 = .l3proto = PF_INET6, .l4proto = IPPROTO_TCP, .pkt_to_tuple = tcp_pkt_to_tuple, - .invert_tuple = tcp_invert_tuple, #ifdef CONFIG_NF_CONNTRACK_PROCFS .print_conntrack = tcp_print_conntrack, #endif diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index fe7243970aa4..6fe2233c323a 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -55,14 +55,6 @@ static bool udp_pkt_to_tuple(const struct sk_buff *skb, return true; } -static bool udp_invert_tuple(struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_tuple *orig) -{ - tuple->src.u.udp.port = orig->dst.u.udp.port; - tuple->dst.u.udp.port = orig->src.u.udp.port; - return true; -} - static unsigned int *udp_get_timeouts(struct net *net) { return udp_pernet(net)->timeouts; @@ -302,7 +294,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4 = .l4proto = IPPROTO_UDP, .allow_clash = true, .pkt_to_tuple = udp_pkt_to_tuple, - .invert_tuple = udp_invert_tuple, .packet = udp_packet, .get_timeouts = udp_get_timeouts, .new = udp_new, @@ -334,7 +325,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite4 = .l4proto = IPPROTO_UDPLITE, .allow_clash = true, .pkt_to_tuple = udp_pkt_to_tuple, - .invert_tuple = udp_invert_tuple, .packet = udp_packet, .get_timeouts = udp_get_timeouts, .new = udp_new, @@ -366,7 +356,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6 = .l4proto = IPPROTO_UDP, .allow_clash = true, .pkt_to_tuple = udp_pkt_to_tuple, - .invert_tuple = udp_invert_tuple, .packet = udp_packet, .get_timeouts = udp_get_timeouts, .new = udp_new, @@ -398,7 +387,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6 = .l4proto = IPPROTO_UDPLITE, .allow_clash = true, .pkt_to_tuple = udp_pkt_to_tuple, - .invert_tuple = udp_invert_tuple, .packet = udp_packet, .get_timeouts = udp_get_timeouts, .new = udp_new, -- cgit v1.2.3 From c779e849608a875448f6ffc2a5c2a15523bdcd00 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 29 Jun 2018 07:46:50 +0200 Subject: netfilter: conntrack: remove get_timeout() indirection Not needed, we can have the l4trackers fetch it themselvs. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_l4proto.h | 8 ++------ include/net/netfilter/nf_conntrack_timeout.h | 18 ++++-------------- net/ipv4/netfilter/nf_conntrack_proto_icmp.c | 16 +++++++++++----- net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c | 14 ++++++++++---- net/netfilter/nf_conntrack_core.c | 16 ++-------------- net/netfilter/nf_conntrack_proto_dccp.c | 17 +++++++---------- net/netfilter/nf_conntrack_proto_generic.c | 22 ++++++++++++---------- net/netfilter/nf_conntrack_proto_gre.c | 14 ++++++++++---- net/netfilter/nf_conntrack_proto_sctp.c | 18 ++++++++---------- net/netfilter/nf_conntrack_proto_tcp.c | 23 +++++++++++------------ net/netfilter/nf_conntrack_proto_udp.c | 20 +++++++++++++------- net/netfilter/nfnetlink_cttimeout.c | 12 ++++-------- 12 files changed, 94 insertions(+), 104 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index 6a55e337a161..c7a0075d96df 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -45,13 +45,12 @@ struct nf_conntrack_l4proto { int (*packet)(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, - enum ip_conntrack_info ctinfo, - unsigned int *timeouts); + enum ip_conntrack_info ctinfo); /* Called when a new connection for this protocol found; * returns TRUE if it's OK. If so, packet() called next. */ bool (*new)(struct nf_conn *ct, const struct sk_buff *skb, - unsigned int dataoff, unsigned int *timeouts); + unsigned int dataoff); /* Called when a conntrack entry is destroyed */ void (*destroy)(struct nf_conn *ct); @@ -63,9 +62,6 @@ struct nf_conntrack_l4proto { /* called by gc worker if table is full */ bool (*can_early_drop)(const struct nf_conn *ct); - /* Return the array of timeouts for this protocol. */ - unsigned int *(*get_timeouts)(struct net *net); - /* convert protoinfo to nfnetink attributes */ int (*to_nlattr)(struct sk_buff *skb, struct nlattr *nla, struct nf_conn *ct); diff --git a/include/net/netfilter/nf_conntrack_timeout.h b/include/net/netfilter/nf_conntrack_timeout.h index 9468ab4ad12d..80ceb3d0291d 100644 --- a/include/net/netfilter/nf_conntrack_timeout.h +++ b/include/net/netfilter/nf_conntrack_timeout.h @@ -67,27 +67,17 @@ struct nf_conn_timeout *nf_ct_timeout_ext_add(struct nf_conn *ct, #endif }; -static inline unsigned int * -nf_ct_timeout_lookup(struct net *net, struct nf_conn *ct, - const struct nf_conntrack_l4proto *l4proto) +static inline unsigned int *nf_ct_timeout_lookup(const struct nf_conn *ct) { + unsigned int *timeouts = NULL; #ifdef CONFIG_NF_CONNTRACK_TIMEOUT struct nf_conn_timeout *timeout_ext; - unsigned int *timeouts; timeout_ext = nf_ct_timeout_find(ct); - if (timeout_ext) { + if (timeout_ext) timeouts = nf_ct_timeout_data(timeout_ext); - if (unlikely(!timeouts)) - timeouts = l4proto->get_timeouts(net); - } else { - timeouts = l4proto->get_timeouts(net); - } - - return timeouts; -#else - return l4proto->get_timeouts(net); #endif + return timeouts; } #ifdef CONFIG_NF_CONNTRACK_TIMEOUT diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c index 34095949a003..036670b38282 100644 --- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c +++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include @@ -80,12 +81,16 @@ static unsigned int *icmp_get_timeouts(struct net *net) static int icmp_packet(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, - enum ip_conntrack_info ctinfo, - unsigned int *timeout) + enum ip_conntrack_info ctinfo) { /* Do not immediately delete the connection after the first successful reply to avoid excessive conntrackd traffic and also to handle correctly ICMP echo reply duplicates. */ + unsigned int *timeout = nf_ct_timeout_lookup(ct); + + if (!timeout) + timeout = icmp_get_timeouts(nf_ct_net(ct)); + nf_ct_refresh_acct(ct, ctinfo, skb, *timeout); return NF_ACCEPT; @@ -93,7 +98,7 @@ static int icmp_packet(struct nf_conn *ct, /* Called when a new connection for this protocol found. */ static bool icmp_new(struct nf_conn *ct, const struct sk_buff *skb, - unsigned int dataoff, unsigned int *timeouts) + unsigned int dataoff) { static const u_int8_t valid_new[] = { [ICMP_ECHO] = 1, @@ -280,9 +285,11 @@ static int icmp_timeout_nlattr_to_obj(struct nlattr *tb[], struct nf_icmp_net *in = icmp_pernet(net); if (tb[CTA_TIMEOUT_ICMP_TIMEOUT]) { + if (!timeout) + timeout = &in->timeout; *timeout = ntohl(nla_get_be32(tb[CTA_TIMEOUT_ICMP_TIMEOUT])) * HZ; - } else { + } else if (timeout) { /* Set default ICMP timeout. */ *timeout = in->timeout; } @@ -357,7 +364,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp = .pkt_to_tuple = icmp_pkt_to_tuple, .invert_tuple = icmp_invert_tuple, .packet = icmp_packet, - .get_timeouts = icmp_get_timeouts, .new = icmp_new, .error = icmp_error, .destroy = NULL, diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c index 8bcbc2f15bd5..bed07b998a10 100644 --- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include #include @@ -93,9 +94,13 @@ static unsigned int *icmpv6_get_timeouts(struct net *net) static int icmpv6_packet(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, - enum ip_conntrack_info ctinfo, - unsigned int *timeout) + enum ip_conntrack_info ctinfo) { + unsigned int *timeout = nf_ct_timeout_lookup(ct); + + if (!timeout) + timeout = icmpv6_get_timeouts(nf_ct_net(ct)); + /* Do not immediately delete the connection after the first successful reply to avoid excessive conntrackd traffic and also to handle correctly ICMP echo reply duplicates. */ @@ -106,7 +111,7 @@ static int icmpv6_packet(struct nf_conn *ct, /* Called when a new connection for this protocol found. */ static bool icmpv6_new(struct nf_conn *ct, const struct sk_buff *skb, - unsigned int dataoff, unsigned int *timeouts) + unsigned int dataoff) { static const u_int8_t valid_new[] = { [ICMPV6_ECHO_REQUEST - 128] = 1, @@ -280,6 +285,8 @@ static int icmpv6_timeout_nlattr_to_obj(struct nlattr *tb[], unsigned int *timeout = data; struct nf_icmp_net *in = icmpv6_pernet(net); + if (!timeout) + timeout = icmpv6_get_timeouts(net); if (tb[CTA_TIMEOUT_ICMPV6_TIMEOUT]) { *timeout = ntohl(nla_get_be32(tb[CTA_TIMEOUT_ICMPV6_TIMEOUT])) * HZ; @@ -358,7 +365,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 = .pkt_to_tuple = icmpv6_pkt_to_tuple, .invert_tuple = icmpv6_invert_tuple, .packet = icmpv6_packet, - .get_timeouts = icmpv6_get_timeouts, .new = icmpv6_new, .error = icmpv6_error, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 994591fd9b96..c069f2faff4c 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1337,7 +1337,6 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, const struct nf_conntrack_zone *zone; struct nf_conn_timeout *timeout_ext; struct nf_conntrack_zone tmp; - unsigned int *timeouts; if (!nf_ct_invert_tuple(&repl_tuple, tuple, l4proto)) { pr_debug("Can't invert tuple.\n"); @@ -1356,15 +1355,8 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, } timeout_ext = tmpl ? nf_ct_timeout_find(tmpl) : NULL; - if (timeout_ext) { - timeouts = nf_ct_timeout_data(timeout_ext); - if (unlikely(!timeouts)) - timeouts = l4proto->get_timeouts(net); - } else { - timeouts = l4proto->get_timeouts(net); - } - if (!l4proto->new(ct, skb, dataoff, timeouts)) { + if (!l4proto->new(ct, skb, dataoff)) { nf_conntrack_free(ct); pr_debug("can't track with proto module\n"); return NULL; @@ -1493,7 +1485,6 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum, const struct nf_conntrack_l4proto *l4proto; struct nf_conn *ct, *tmpl; enum ip_conntrack_info ctinfo; - unsigned int *timeouts; u_int8_t protonum; int dataoff, ret; @@ -1552,10 +1543,7 @@ repeat: goto out; } - /* Decide what timeout policy we want to apply to this flow. */ - timeouts = nf_ct_timeout_lookup(net, ct, l4proto); - - ret = l4proto->packet(ct, skb, dataoff, ctinfo, timeouts); + ret = l4proto->packet(ct, skb, dataoff, ctinfo); if (ret <= 0) { /* Invalid: inverse of the return code tells * the netfilter core what to do */ diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index abfdce7baed5..f476d116c816 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -23,6 +23,7 @@ #include #include #include +#include #include /* Timeouts are based on values from RFC4340: @@ -389,7 +390,7 @@ static inline struct nf_dccp_net *dccp_pernet(struct net *net) } static bool dccp_new(struct nf_conn *ct, const struct sk_buff *skb, - unsigned int dataoff, unsigned int *timeouts) + unsigned int dataoff) { struct net *net = nf_ct_net(ct); struct nf_dccp_net *dn; @@ -437,19 +438,14 @@ static u64 dccp_ack_seq(const struct dccp_hdr *dh) ntohl(dhack->dccph_ack_nr_low); } -static unsigned int *dccp_get_timeouts(struct net *net) -{ - return dccp_pernet(net)->dccp_timeout; -} - static int dccp_packet(struct nf_conn *ct, const struct sk_buff *skb, - unsigned int dataoff, enum ip_conntrack_info ctinfo, - unsigned int *timeouts) + unsigned int dataoff, enum ip_conntrack_info ctinfo) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); struct dccp_hdr _dh, *dh; u_int8_t type, old_state, new_state; enum ct_dccp_roles role; + unsigned int *timeouts; dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &_dh); BUG_ON(dh == NULL); @@ -523,6 +519,9 @@ static int dccp_packet(struct nf_conn *ct, const struct sk_buff *skb, if (new_state != old_state) nf_conntrack_event_cache(IPCT_PROTOINFO, ct); + timeouts = nf_ct_timeout_lookup(ct); + if (!timeouts) + timeouts = dccp_pernet(nf_ct_net(ct))->dccp_timeout; nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[new_state]); return NF_ACCEPT; @@ -843,7 +842,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp4 = { .l4proto = IPPROTO_DCCP, .new = dccp_new, .packet = dccp_packet, - .get_timeouts = dccp_get_timeouts, .error = dccp_error, .can_early_drop = dccp_can_early_drop, #ifdef CONFIG_NF_CONNTRACK_PROCFS @@ -877,7 +875,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp6 = { .l4proto = IPPROTO_DCCP, .new = dccp_new, .packet = dccp_packet, - .get_timeouts = dccp_get_timeouts, .error = dccp_error, .can_early_drop = dccp_can_early_drop, #ifdef CONFIG_NF_CONNTRACK_PROCFS diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c index 4dfe40aa9446..ac4a0b296dcd 100644 --- a/net/netfilter/nf_conntrack_proto_generic.c +++ b/net/netfilter/nf_conntrack_proto_generic.c @@ -11,6 +11,7 @@ #include #include #include +#include static const unsigned int nf_ct_generic_timeout = 600*HZ; @@ -41,25 +42,24 @@ static bool generic_pkt_to_tuple(const struct sk_buff *skb, return true; } -static unsigned int *generic_get_timeouts(struct net *net) -{ - return &(generic_pernet(net)->timeout); -} - /* Returns verdict for packet, or -1 for invalid. */ static int generic_packet(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, - enum ip_conntrack_info ctinfo, - unsigned int *timeout) + enum ip_conntrack_info ctinfo) { + const unsigned int *timeout = nf_ct_timeout_lookup(ct); + + if (!timeout) + timeout = &generic_pernet(nf_ct_net(ct))->timeout; + nf_ct_refresh_acct(ct, ctinfo, skb, *timeout); return NF_ACCEPT; } /* Called when a new connection for this protocol found. */ static bool generic_new(struct nf_conn *ct, const struct sk_buff *skb, - unsigned int dataoff, unsigned int *timeouts) + unsigned int dataoff) { bool ret; @@ -78,8 +78,11 @@ static bool generic_new(struct nf_conn *ct, const struct sk_buff *skb, static int generic_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { - unsigned int *timeout = data; struct nf_generic_net *gn = generic_pernet(net); + unsigned int *timeout = data; + + if (!timeout) + timeout = &gn->timeout; if (tb[CTA_TIMEOUT_GENERIC_TIMEOUT]) *timeout = @@ -160,7 +163,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_generic = .l4proto = 255, .pkt_to_tuple = generic_pkt_to_tuple, .packet = generic_packet, - .get_timeouts = generic_get_timeouts, .new = generic_new, #if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) .ctnl_timeout = { diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index 0bd40eb06b55..d1632252bf5b 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -39,6 +39,7 @@ #include #include #include +#include #include #include @@ -234,8 +235,7 @@ static unsigned int *gre_get_timeouts(struct net *net) static int gre_packet(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, - enum ip_conntrack_info ctinfo, - unsigned int *timeouts) + enum ip_conntrack_info ctinfo) { /* If we've seen traffic both ways, this is a GRE connection. * Extend timeout. */ @@ -254,8 +254,13 @@ static int gre_packet(struct nf_conn *ct, /* Called when a new connection for this protocol found. */ static bool gre_new(struct nf_conn *ct, const struct sk_buff *skb, - unsigned int dataoff, unsigned int *timeouts) + unsigned int dataoff) { + unsigned int *timeouts = nf_ct_timeout_lookup(ct); + + if (!timeouts) + timeouts = gre_get_timeouts(nf_ct_net(ct)); + pr_debug(": "); nf_ct_dump_tuple(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); @@ -291,6 +296,8 @@ static int gre_timeout_nlattr_to_obj(struct nlattr *tb[], unsigned int *timeouts = data; struct netns_proto_gre *net_gre = gre_pernet(net); + if (!timeouts) + timeouts = gre_get_timeouts(net); /* set default timeouts for GRE. */ timeouts[GRE_CT_UNREPLIED] = net_gre->gre_timeouts[GRE_CT_UNREPLIED]; timeouts[GRE_CT_REPLIED] = net_gre->gre_timeouts[GRE_CT_REPLIED]; @@ -350,7 +357,6 @@ static const struct nf_conntrack_l4proto nf_conntrack_l4proto_gre4 = { #ifdef CONFIG_NF_CONNTRACK_PROCFS .print_conntrack = gre_print_conntrack, #endif - .get_timeouts = gre_get_timeouts, .packet = gre_packet, .new = gre_new, .destroy = gre_destroy, diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index b4126a842bfd..8d1e085fc14a 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -28,6 +28,7 @@ #include #include #include +#include /* FIXME: Examine ipfilter's timeouts and conntrack transitions more closely. They're more complex. --RR @@ -272,17 +273,11 @@ static int sctp_new_state(enum ip_conntrack_dir dir, return sctp_conntracks[dir][i][cur_state]; } -static unsigned int *sctp_get_timeouts(struct net *net) -{ - return sctp_pernet(net)->timeouts; -} - /* Returns verdict for packet, or -NF_ACCEPT for invalid. */ static int sctp_packet(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, - enum ip_conntrack_info ctinfo, - unsigned int *timeouts) + enum ip_conntrack_info ctinfo) { enum sctp_conntrack new_state, old_state; enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); @@ -291,6 +286,7 @@ static int sctp_packet(struct nf_conn *ct, const struct sctp_chunkhdr *sch; struct sctp_chunkhdr _sch; u_int32_t offset, count; + unsigned int *timeouts; unsigned long map[256 / sizeof(unsigned long)] = { 0 }; sh = skb_header_pointer(skb, dataoff, sizeof(_sctph), &_sctph); @@ -379,6 +375,10 @@ static int sctp_packet(struct nf_conn *ct, } spin_unlock_bh(&ct->lock); + timeouts = nf_ct_timeout_lookup(ct); + if (!timeouts) + timeouts = sctp_pernet(nf_ct_net(ct))->timeouts; + nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[new_state]); if (old_state == SCTP_CONNTRACK_COOKIE_ECHOED && @@ -399,7 +399,7 @@ out: /* Called when a new connection for this protocol found. */ static bool sctp_new(struct nf_conn *ct, const struct sk_buff *skb, - unsigned int dataoff, unsigned int *timeouts) + unsigned int dataoff) { enum sctp_conntrack new_state; const struct sctphdr *sh; @@ -760,7 +760,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4 = { .print_conntrack = sctp_print_conntrack, #endif .packet = sctp_packet, - .get_timeouts = sctp_get_timeouts, .new = sctp_new, .error = sctp_error, .can_early_drop = sctp_can_early_drop, @@ -795,7 +794,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp6 = { .print_conntrack = sctp_print_conntrack, #endif .packet = sctp_packet, - .get_timeouts = sctp_get_timeouts, .new = sctp_new, .error = sctp_error, .can_early_drop = sctp_can_early_drop, diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 13c89fd107b2..d80d322b9d8b 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -29,6 +29,7 @@ #include #include #include +#include #include #include #include @@ -768,27 +769,21 @@ static int tcp_error(struct net *net, struct nf_conn *tmpl, return NF_ACCEPT; } -static unsigned int *tcp_get_timeouts(struct net *net) -{ - return tcp_pernet(net)->timeouts; -} - /* Returns verdict for packet, or -1 for invalid. */ static int tcp_packet(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, - enum ip_conntrack_info ctinfo, - unsigned int *timeouts) + enum ip_conntrack_info ctinfo) { struct net *net = nf_ct_net(ct); struct nf_tcp_net *tn = tcp_pernet(net); struct nf_conntrack_tuple *tuple; enum tcp_conntrack new_state, old_state; + unsigned int index, *timeouts; enum ip_conntrack_dir dir; const struct tcphdr *th; struct tcphdr _tcph; unsigned long timeout; - unsigned int index; th = skb_header_pointer(skb, dataoff, sizeof(_tcph), &_tcph); BUG_ON(th == NULL); @@ -1021,6 +1016,10 @@ static int tcp_packet(struct nf_conn *ct, && new_state == TCP_CONNTRACK_FIN_WAIT) ct->proto.tcp.seen[dir].flags |= IP_CT_TCP_FLAG_CLOSE_INIT; + timeouts = nf_ct_timeout_lookup(ct); + if (!timeouts) + timeouts = tn->timeouts; + if (ct->proto.tcp.retrans >= tn->tcp_max_retrans && timeouts[new_state] > timeouts[TCP_CONNTRACK_RETRANS]) timeout = timeouts[TCP_CONNTRACK_RETRANS]; @@ -1070,7 +1069,7 @@ static int tcp_packet(struct nf_conn *ct, /* Called when a new connection for this protocol found. */ static bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb, - unsigned int dataoff, unsigned int *timeouts) + unsigned int dataoff) { enum tcp_conntrack new_state; const struct tcphdr *th; @@ -1288,10 +1287,12 @@ static unsigned int tcp_nlattr_tuple_size(void) static int tcp_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { - unsigned int *timeouts = data; struct nf_tcp_net *tn = tcp_pernet(net); + unsigned int *timeouts = data; int i; + if (!timeouts) + timeouts = tn->timeouts; /* set default TCP timeouts. */ for (i=0; itimeouts[i]; @@ -1538,7 +1539,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4 = .print_conntrack = tcp_print_conntrack, #endif .packet = tcp_packet, - .get_timeouts = tcp_get_timeouts, .new = tcp_new, .error = tcp_error, .can_early_drop = tcp_can_early_drop, @@ -1574,7 +1574,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6 = .print_conntrack = tcp_print_conntrack, #endif .packet = tcp_packet, - .get_timeouts = tcp_get_timeouts, .new = tcp_new, .error = tcp_error, .can_early_drop = tcp_can_early_drop, diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index 8b435d70ffe3..7a1b8988a931 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include @@ -45,9 +46,14 @@ static unsigned int *udp_get_timeouts(struct net *net) static int udp_packet(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, - enum ip_conntrack_info ctinfo, - unsigned int *timeouts) + enum ip_conntrack_info ctinfo) { + unsigned int *timeouts; + + timeouts = nf_ct_timeout_lookup(ct); + if (!timeouts) + timeouts = udp_get_timeouts(nf_ct_net(ct)); + /* If we've seen traffic both ways, this is some kind of UDP stream. Extend timeout. */ if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) { @@ -65,7 +71,7 @@ static int udp_packet(struct nf_conn *ct, /* Called when a new connection for this protocol found. */ static bool udp_new(struct nf_conn *ct, const struct sk_buff *skb, - unsigned int dataoff, unsigned int *timeouts) + unsigned int dataoff) { return true; } @@ -176,6 +182,9 @@ static int udp_timeout_nlattr_to_obj(struct nlattr *tb[], unsigned int *timeouts = data; struct nf_udp_net *un = udp_pernet(net); + if (!timeouts) + timeouts = un->timeouts; + /* set default timeouts for UDP. */ timeouts[UDP_CT_UNREPLIED] = un->timeouts[UDP_CT_UNREPLIED]; timeouts[UDP_CT_REPLIED] = un->timeouts[UDP_CT_REPLIED]; @@ -275,7 +284,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4 = .l4proto = IPPROTO_UDP, .allow_clash = true, .packet = udp_packet, - .get_timeouts = udp_get_timeouts, .new = udp_new, .error = udp_error, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) @@ -305,7 +313,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite4 = .l4proto = IPPROTO_UDPLITE, .allow_clash = true, .packet = udp_packet, - .get_timeouts = udp_get_timeouts, .new = udp_new, .error = udplite_error, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) @@ -335,7 +342,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6 = .l4proto = IPPROTO_UDP, .allow_clash = true, .packet = udp_packet, - .get_timeouts = udp_get_timeouts, .new = udp_new, .error = udp_error, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) @@ -365,7 +371,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6 = .l4proto = IPPROTO_UDPLITE, .allow_clash = true, .packet = udp_packet, - .get_timeouts = udp_get_timeouts, .new = udp_new, .error = udplite_error, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) @@ -388,3 +393,4 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6 = }; EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_udplite6); #endif +#include diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index 9da4b8462004..d9d952fad3e0 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -46,7 +46,7 @@ static const struct nla_policy cttimeout_nla_policy[CTA_TIMEOUT_MAX+1] = { }; static int -ctnl_timeout_parse_policy(void *timeouts, +ctnl_timeout_parse_policy(void *timeout, const struct nf_conntrack_l4proto *l4proto, struct net *net, const struct nlattr *attr) { @@ -67,7 +67,7 @@ ctnl_timeout_parse_policy(void *timeouts, if (ret < 0) goto err; - ret = l4proto->ctnl_timeout.nlattr_to_obj(tb, net, timeouts); + ret = l4proto->ctnl_timeout.nlattr_to_obj(tb, net, timeout); err: kfree(tb); @@ -372,7 +372,6 @@ static int cttimeout_default_set(struct net *net, struct sock *ctnl, struct netlink_ext_ack *extack) { const struct nf_conntrack_l4proto *l4proto; - unsigned int *timeouts; __u16 l3num; __u8 l4num; int ret; @@ -392,9 +391,7 @@ static int cttimeout_default_set(struct net *net, struct sock *ctnl, goto err; } - timeouts = l4proto->get_timeouts(net); - - ret = ctnl_timeout_parse_policy(timeouts, l4proto, net, + ret = ctnl_timeout_parse_policy(NULL, l4proto, net, cda[CTA_TIMEOUT_DATA]); if (ret < 0) goto err; @@ -431,7 +428,6 @@ cttimeout_default_fill_info(struct net *net, struct sk_buff *skb, u32 portid, if (likely(l4proto->ctnl_timeout.obj_to_nlattr)) { struct nlattr *nest_parms; - unsigned int *timeouts = l4proto->get_timeouts(net); int ret; nest_parms = nla_nest_start(skb, @@ -439,7 +435,7 @@ cttimeout_default_fill_info(struct net *net, struct sk_buff *skb, u32 portid, if (!nest_parms) goto nla_put_failure; - ret = l4proto->ctnl_timeout.obj_to_nlattr(skb, timeouts); + ret = l4proto->ctnl_timeout.obj_to_nlattr(skb, NULL); if (ret < 0) goto nla_put_failure; -- cgit v1.2.3 From 377179cd28cd417dcfb4396edb824533431e607e Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Fri, 13 Jul 2018 14:05:56 -0400 Subject: security: define new LSM hook named security_kernel_load_data Differentiate between the kernel reading a file specified by userspace from the kernel loading a buffer containing data provided by userspace. This patch defines a new LSM hook named security_kernel_load_data(). Signed-off-by: Mimi Zohar Cc: Eric Biederman Cc: Luis R. Rodriguez Cc: Kees Cook Cc: Casey Schaufler Acked-by: Serge Hallyn Acked-by: Kees Cook Signed-off-by: James Morris --- include/linux/lsm_hooks.h | 6 ++++++ include/linux/security.h | 27 +++++++++++++++++++++++++++ security/security.c | 5 +++++ 3 files changed, 38 insertions(+) (limited to 'include') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 8f1131c8dd54..a08bc2587b96 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -576,6 +576,10 @@ * userspace to load a kernel module with the given name. * @kmod_name name of the module requested by the kernel * Return 0 if successful. + * @kernel_load_data: + * Load data provided by userspace. + * @id kernel load data identifier + * Return 0 if permission is granted. * @kernel_read_file: * Read a file specified by userspace. * @file contains the file structure pointing to the file being read @@ -1582,6 +1586,7 @@ union security_list_options { int (*kernel_act_as)(struct cred *new, u32 secid); int (*kernel_create_files_as)(struct cred *new, struct inode *inode); int (*kernel_module_request)(char *kmod_name); + int (*kernel_load_data)(enum kernel_load_data_id id); int (*kernel_read_file)(struct file *file, enum kernel_read_file_id id); int (*kernel_post_read_file)(struct file *file, char *buf, loff_t size, enum kernel_read_file_id id); @@ -1872,6 +1877,7 @@ struct security_hook_heads { struct hlist_head cred_getsecid; struct hlist_head kernel_act_as; struct hlist_head kernel_create_files_as; + struct hlist_head kernel_load_data; struct hlist_head kernel_read_file; struct hlist_head kernel_post_read_file; struct hlist_head kernel_module_request; diff --git a/include/linux/security.h b/include/linux/security.h index 63030c85ee19..3410acfe139c 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -159,6 +159,27 @@ extern int mmap_min_addr_handler(struct ctl_table *table, int write, typedef int (*initxattrs) (struct inode *inode, const struct xattr *xattr_array, void *fs_data); + +/* Keep the kernel_load_data_id enum in sync with kernel_read_file_id */ +#define __data_id_enumify(ENUM, dummy) LOADING_ ## ENUM, +#define __data_id_stringify(dummy, str) #str, + +enum kernel_load_data_id { + __kernel_read_file_id(__data_id_enumify) +}; + +static const char * const kernel_load_data_str[] = { + __kernel_read_file_id(__data_id_stringify) +}; + +static inline const char *kernel_load_data_id_str(enum kernel_load_data_id id) +{ + if ((unsigned)id >= LOADING_MAX_ID) + return kernel_load_data_str[LOADING_UNKNOWN]; + + return kernel_load_data_str[id]; +} + #ifdef CONFIG_SECURITY struct security_mnt_opts { @@ -320,6 +341,7 @@ void security_cred_getsecid(const struct cred *c, u32 *secid); int security_kernel_act_as(struct cred *new, u32 secid); int security_kernel_create_files_as(struct cred *new, struct inode *inode); int security_kernel_module_request(char *kmod_name); +int security_kernel_load_data(enum kernel_load_data_id id); int security_kernel_read_file(struct file *file, enum kernel_read_file_id id); int security_kernel_post_read_file(struct file *file, char *buf, loff_t size, enum kernel_read_file_id id); @@ -909,6 +931,11 @@ static inline int security_kernel_module_request(char *kmod_name) return 0; } +static inline int security_kernel_load_data(enum kernel_load_data_id id) +{ + return 0; +} + static inline int security_kernel_read_file(struct file *file, enum kernel_read_file_id id) { diff --git a/security/security.c b/security/security.c index 68f46d849abe..c2de2f134854 100644 --- a/security/security.c +++ b/security/security.c @@ -1056,6 +1056,11 @@ int security_kernel_post_read_file(struct file *file, char *buf, loff_t size, } EXPORT_SYMBOL_GPL(security_kernel_post_read_file); +int security_kernel_load_data(enum kernel_load_data_id id) +{ + return call_int_hook(kernel_load_data, 0, id); +} + int security_task_fix_setuid(struct cred *new, const struct cred *old, int flags) { -- cgit v1.2.3 From 16c267aac86b463b1fcccd43c89f4c8e5c5c86fa Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Fri, 13 Jul 2018 14:05:58 -0400 Subject: ima: based on policy require signed kexec kernel images The original kexec_load syscall can not verify file signatures, nor can the kexec image be measured. Based on policy, deny the kexec_load syscall. Signed-off-by: Mimi Zohar Cc: Eric Biederman Cc: Kees Cook Reviewed-by: Kees Cook Signed-off-by: James Morris --- include/linux/ima.h | 7 +++++++ security/integrity/ima/ima.h | 1 + security/integrity/ima/ima_main.c | 27 +++++++++++++++++++++++++++ security/integrity/ima/ima_policy.c | 2 ++ security/security.c | 7 ++++++- 5 files changed, 43 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ima.h b/include/linux/ima.h index 0e4647e0eb60..84806b54b50a 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -11,6 +11,7 @@ #define _LINUX_IMA_H #include +#include #include struct linux_binprm; @@ -19,6 +20,7 @@ extern int ima_bprm_check(struct linux_binprm *bprm); extern int ima_file_check(struct file *file, int mask, int opened); extern void ima_file_free(struct file *file); extern int ima_file_mmap(struct file *file, unsigned long prot); +extern int ima_load_data(enum kernel_load_data_id id); extern int ima_read_file(struct file *file, enum kernel_read_file_id id); extern int ima_post_read_file(struct file *file, void *buf, loff_t size, enum kernel_read_file_id id); @@ -49,6 +51,11 @@ static inline int ima_file_mmap(struct file *file, unsigned long prot) return 0; } +static inline int ima_load_data(enum kernel_load_data_id id) +{ + return 0; +} + static inline int ima_read_file(struct file *file, enum kernel_read_file_id id) { return 0; diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h index 354bb5716ce3..78c15264b17b 100644 --- a/security/integrity/ima/ima.h +++ b/security/integrity/ima/ima.h @@ -232,6 +232,7 @@ int ima_policy_show(struct seq_file *m, void *v); #define IMA_APPRAISE_MODULES 0x08 #define IMA_APPRAISE_FIRMWARE 0x10 #define IMA_APPRAISE_POLICY 0x20 +#define IMA_APPRAISE_KEXEC 0x40 #ifdef CONFIG_IMA_APPRAISE int ima_appraise_measurement(enum ima_hooks func, diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c index dca44cf7838e..71fecfef0939 100644 --- a/security/integrity/ima/ima_main.c +++ b/security/integrity/ima/ima_main.c @@ -496,6 +496,33 @@ int ima_post_read_file(struct file *file, void *buf, loff_t size, MAY_READ, func, 0); } +/** + * ima_load_data - appraise decision based on policy + * @id: kernel load data caller identifier + * + * Callers of this LSM hook can not measure, appraise, or audit the + * data provided by userspace. Enforce policy rules requring a file + * signature (eg. kexec'ed kernel image). + * + * For permission return 0, otherwise return -EACCES. + */ +int ima_load_data(enum kernel_load_data_id id) +{ + if ((ima_appraise & IMA_APPRAISE_ENFORCE) != IMA_APPRAISE_ENFORCE) + return 0; + + switch (id) { + case LOADING_KEXEC_IMAGE: + if (ima_appraise & IMA_APPRAISE_KEXEC) { + pr_err("impossible to appraise a kernel image without a file descriptor; try using kexec_file_load syscall.\n"); + return -EACCES; /* INTEGRITY_UNKNOWN */ + } + default: + break; + } + return 0; +} + static int __init init_ima(void) { int error; diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c index cdcc9a7b4e24..d5b4958decc5 100644 --- a/security/integrity/ima/ima_policy.c +++ b/security/integrity/ima/ima_policy.c @@ -448,6 +448,8 @@ static int ima_appraise_flag(enum ima_hooks func) return IMA_APPRAISE_FIRMWARE; else if (func == POLICY_CHECK) return IMA_APPRAISE_POLICY; + else if (func == KEXEC_KERNEL_CHECK) + return IMA_APPRAISE_KEXEC; return 0; } diff --git a/security/security.c b/security/security.c index c2de2f134854..4927e7cc7d96 100644 --- a/security/security.c +++ b/security/security.c @@ -1058,7 +1058,12 @@ EXPORT_SYMBOL_GPL(security_kernel_post_read_file); int security_kernel_load_data(enum kernel_load_data_id id) { - return call_int_hook(kernel_load_data, 0, id); + int ret; + + ret = call_int_hook(kernel_load_data, 0, id); + if (ret) + return ret; + return ima_load_data(id); } int security_task_fix_setuid(struct cred *new, const struct cred *old, -- cgit v1.2.3 From 964d0fbf6301d3dc8dfad19ffab5a06d002d27f1 Mon Sep 17 00:00:00 2001 From: Andrey Grodzovsky Date: Fri, 6 Jul 2018 14:16:54 -0400 Subject: drm/amdgpu: Allow to create BO lists in CS ioctl v3 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This change is to support MESA performace optimization. Modify CS IOCTL to allow its input as command buffer and an array of buffer handles to create a temporay bo list and then destroy it when IOCTL completes. This saves on calling for BO_LIST create and destry IOCTLs in MESA and by this improves performance. v2: Avoid inserting the temp list into idr struct. v3: Remove idr alloation from amdgpu_bo_list_create. Remove useless argument from amdgpu_cs_parser_fini Minor cosmetic stuff. v4: Revert amdgpu_bo_list_destroy back to static Signed-off-by: Andrey Grodzovsky Reviewed-by: Christian König Reviewed-by: Chunming Zhou Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu.h | 8 +++ drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c | 88 +++++++++++++++++------------ drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 48 +++++++++++++++- drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 3 +- include/uapi/drm/amdgpu_drm.h | 1 + 5 files changed, 108 insertions(+), 40 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 53435da158c2..c6c1e8dc919f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -732,6 +732,14 @@ void amdgpu_bo_list_get_list(struct amdgpu_bo_list *list, struct list_head *validated); void amdgpu_bo_list_put(struct amdgpu_bo_list *list); void amdgpu_bo_list_free(struct amdgpu_bo_list *list); +int amdgpu_bo_create_list_entry_array(struct drm_amdgpu_bo_list_in *in, + struct drm_amdgpu_bo_list_entry **info_param); + +int amdgpu_bo_list_create(struct amdgpu_device *adev, + struct drm_file *filp, + struct drm_amdgpu_bo_list_entry *info, + unsigned num_entries, + struct amdgpu_bo_list **list); /* * GFX stuff diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c index 92be7f6de197..7679c068c89a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c @@ -55,15 +55,15 @@ static void amdgpu_bo_list_release_rcu(struct kref *ref) kfree_rcu(list, rhead); } -static int amdgpu_bo_list_create(struct amdgpu_device *adev, +int amdgpu_bo_list_create(struct amdgpu_device *adev, struct drm_file *filp, struct drm_amdgpu_bo_list_entry *info, unsigned num_entries, - int *id) + struct amdgpu_bo_list **list_out) { - int r; - struct amdgpu_fpriv *fpriv = filp->driver_priv; struct amdgpu_bo_list *list; + int r; + list = kzalloc(sizeof(struct amdgpu_bo_list), GFP_KERNEL); if (!list) @@ -78,16 +78,7 @@ static int amdgpu_bo_list_create(struct amdgpu_device *adev, return r; } - /* idr alloc should be called only after initialization of bo list. */ - mutex_lock(&fpriv->bo_list_lock); - r = idr_alloc(&fpriv->bo_list_handles, list, 1, 0, GFP_KERNEL); - mutex_unlock(&fpriv->bo_list_lock); - if (r < 0) { - amdgpu_bo_list_free(list); - return r; - } - *id = r; - + *list_out = list; return 0; } @@ -263,55 +254,79 @@ void amdgpu_bo_list_free(struct amdgpu_bo_list *list) kfree(list); } -int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data, - struct drm_file *filp) +int amdgpu_bo_create_list_entry_array(struct drm_amdgpu_bo_list_in *in, + struct drm_amdgpu_bo_list_entry **info_param) { + const void __user *uptr = u64_to_user_ptr(in->bo_info_ptr); const uint32_t info_size = sizeof(struct drm_amdgpu_bo_list_entry); - - struct amdgpu_device *adev = dev->dev_private; - struct amdgpu_fpriv *fpriv = filp->driver_priv; - union drm_amdgpu_bo_list *args = data; - uint32_t handle = args->in.list_handle; - const void __user *uptr = u64_to_user_ptr(args->in.bo_info_ptr); - struct drm_amdgpu_bo_list_entry *info; - struct amdgpu_bo_list *list; - int r; - info = kvmalloc_array(args->in.bo_number, - sizeof(struct drm_amdgpu_bo_list_entry), GFP_KERNEL); + info = kvmalloc_array(in->bo_number, info_size, GFP_KERNEL); if (!info) return -ENOMEM; /* copy the handle array from userspace to a kernel buffer */ r = -EFAULT; - if (likely(info_size == args->in.bo_info_size)) { - unsigned long bytes = args->in.bo_number * - args->in.bo_info_size; + if (likely(info_size == in->bo_info_size)) { + unsigned long bytes = in->bo_number * + in->bo_info_size; if (copy_from_user(info, uptr, bytes)) goto error_free; } else { - unsigned long bytes = min(args->in.bo_info_size, info_size); + unsigned long bytes = min(in->bo_info_size, info_size); unsigned i; - memset(info, 0, args->in.bo_number * info_size); - for (i = 0; i < args->in.bo_number; ++i) { + memset(info, 0, in->bo_number * info_size); + for (i = 0; i < in->bo_number; ++i) { if (copy_from_user(&info[i], uptr, bytes)) goto error_free; - uptr += args->in.bo_info_size; + uptr += in->bo_info_size; } } + *info_param = info; + return 0; + +error_free: + kvfree(info); + return r; +} + +int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data, + struct drm_file *filp) +{ + struct amdgpu_device *adev = dev->dev_private; + struct amdgpu_fpriv *fpriv = filp->driver_priv; + union drm_amdgpu_bo_list *args = data; + uint32_t handle = args->in.list_handle; + struct drm_amdgpu_bo_list_entry *info = NULL; + struct amdgpu_bo_list *list; + int r; + + r = amdgpu_bo_create_list_entry_array(&args->in, &info); + if (r) + goto error_free; + switch (args->in.operation) { case AMDGPU_BO_LIST_OP_CREATE: r = amdgpu_bo_list_create(adev, filp, info, args->in.bo_number, - &handle); + &list); if (r) goto error_free; + + mutex_lock(&fpriv->bo_list_lock); + r = idr_alloc(&fpriv->bo_list_handles, list, 1, 0, GFP_KERNEL); + mutex_unlock(&fpriv->bo_list_lock); + if (r < 0) { + amdgpu_bo_list_free(list); + return r; + } + + handle = r; break; case AMDGPU_BO_LIST_OP_DESTROY: @@ -345,6 +360,7 @@ int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data, return 0; error_free: - kvfree(info); + if (info) + kvfree(info); return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 5a2a5ba29f9a..6d8df76b5a5d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -66,11 +66,35 @@ static int amdgpu_cs_user_fence_chunk(struct amdgpu_cs_parser *p, return 0; } -static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data) +static int amdgpu_cs_bo_handles_chunk(struct amdgpu_cs_parser *p, + struct drm_amdgpu_bo_list_in *data) +{ + int r; + struct drm_amdgpu_bo_list_entry *info = NULL; + + r = amdgpu_bo_create_list_entry_array(data, &info); + if (r) + return r; + + r = amdgpu_bo_list_create(p->adev, p->filp, info, data->bo_number, + &p->bo_list); + if (r) + goto error_free; + + kvfree(info); + return 0; + +error_free: + if (info) + kvfree(info); + + return r; +} + +static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, union drm_amdgpu_cs *cs) { struct amdgpu_fpriv *fpriv = p->filp->driver_priv; struct amdgpu_vm *vm = &fpriv->vm; - union drm_amdgpu_cs *cs = data; uint64_t *chunk_array_user; uint64_t *chunk_array; unsigned size, num_ibs = 0; @@ -164,6 +188,19 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data) break; + case AMDGPU_CHUNK_ID_BO_HANDLES: + size = sizeof(struct drm_amdgpu_bo_list_in); + if (p->chunks[i].length_dw * sizeof(uint32_t) < size) { + ret = -EINVAL; + goto free_partial_kdata; + } + + ret = amdgpu_cs_bo_handles_chunk(p, p->chunks[i].kdata); + if (ret) + goto free_partial_kdata; + + break; + case AMDGPU_CHUNK_ID_DEPENDENCIES: case AMDGPU_CHUNK_ID_SYNCOBJ_IN: case AMDGPU_CHUNK_ID_SYNCOBJ_OUT: @@ -534,7 +571,12 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p, INIT_LIST_HEAD(&p->validated); - p->bo_list = amdgpu_bo_list_get(fpriv, cs->in.bo_list_handle); + /* p->bo_list could already be assigned if AMDGPU_CHUNK_ID_BO_HANDLES is present */ + if (!p->bo_list) + p->bo_list = amdgpu_bo_list_get(fpriv, cs->in.bo_list_handle); + else + mutex_lock(&p->bo_list->lock); + if (p->bo_list) { amdgpu_bo_list_get_list(p->bo_list, &p->validated); if (p->bo_list->first_userptr != p->bo_list->num_entries) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 06aede194bf8..529500c94675 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -69,9 +69,10 @@ * - 3.24.0 - Add high priority compute support for gfx9 * - 3.25.0 - Add support for sensor query info (stable pstate sclk/mclk). * - 3.26.0 - GFX9: Process AMDGPU_IB_FLAG_TC_WB_NOT_INVALIDATE. + * - 3.27.0 - Add new chunk to to AMDGPU_CS to enable BO_LIST creation. */ #define KMS_DRIVER_MAJOR 3 -#define KMS_DRIVER_MINOR 26 +#define KMS_DRIVER_MINOR 27 #define KMS_DRIVER_PATCHLEVEL 0 int amdgpu_vram_limit = 0; diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index 784b0fe470ee..1ceec56de015 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -516,6 +516,7 @@ struct drm_amdgpu_gem_va { #define AMDGPU_CHUNK_ID_DEPENDENCIES 0x03 #define AMDGPU_CHUNK_ID_SYNCOBJ_IN 0x04 #define AMDGPU_CHUNK_ID_SYNCOBJ_OUT 0x05 +#define AMDGPU_CHUNK_ID_BO_HANDLES 0x06 struct drm_amdgpu_cs_chunk { __u32 chunk_id; -- cgit v1.2.3 From 2b9672ddb6f347467d7b33b86c5dfc4d5c0501a8 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Thu, 12 Jul 2018 21:32:53 +0200 Subject: net: phy: add phy_speed_down and phy_speed_up Some network drivers include functionality to speed down the PHY when suspending and just waiting for a WoL packet because this saves energy. This functionality is quite generic, therefore let's factor it out to phylib. Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- drivers/net/phy/phy.c | 78 +++++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/phy.h | 2 ++ 2 files changed, 80 insertions(+) (limited to 'include') diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index c4aa360dedff..d2baedc4ea91 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -551,6 +551,84 @@ int phy_start_aneg(struct phy_device *phydev) } EXPORT_SYMBOL(phy_start_aneg); +static int phy_poll_aneg_done(struct phy_device *phydev) +{ + unsigned int retries = 100; + int ret; + + do { + msleep(100); + ret = phy_aneg_done(phydev); + } while (!ret && --retries); + + if (!ret) + return -ETIMEDOUT; + + return ret < 0 ? ret : 0; +} + +/** + * phy_speed_down - set speed to lowest speed supported by both link partners + * @phydev: the phy_device struct + * @sync: perform action synchronously + * + * Description: Typically used to save energy when waiting for a WoL packet + * + * WARNING: Setting sync to false may cause the system being unable to suspend + * in case the PHY generates an interrupt when finishing the autonegotiation. + * This interrupt may wake up the system immediately after suspend. + * Therefore use sync = false only if you're sure it's safe with the respective + * network chip. + */ +int phy_speed_down(struct phy_device *phydev, bool sync) +{ + u32 adv = phydev->lp_advertising & phydev->supported; + u32 adv_old = phydev->advertising; + int ret; + + if (phydev->autoneg != AUTONEG_ENABLE) + return 0; + + if (adv & PHY_10BT_FEATURES) + phydev->advertising &= ~(PHY_100BT_FEATURES | + PHY_1000BT_FEATURES); + else if (adv & PHY_100BT_FEATURES) + phydev->advertising &= ~PHY_1000BT_FEATURES; + + if (phydev->advertising == adv_old) + return 0; + + ret = phy_config_aneg(phydev); + if (ret) + return ret; + + return sync ? phy_poll_aneg_done(phydev) : 0; +} +EXPORT_SYMBOL_GPL(phy_speed_down); + +/** + * phy_speed_up - (re)set advertised speeds to all supported speeds + * @phydev: the phy_device struct + * + * Description: Used to revert the effect of phy_speed_down + */ +int phy_speed_up(struct phy_device *phydev) +{ + u32 mask = PHY_10BT_FEATURES | PHY_100BT_FEATURES | PHY_1000BT_FEATURES; + u32 adv_old = phydev->advertising; + + if (phydev->autoneg != AUTONEG_ENABLE) + return 0; + + phydev->advertising = (adv_old & ~mask) | (phydev->supported & mask); + + if (phydev->advertising == adv_old) + return 0; + + return phy_config_aneg(phydev); +} +EXPORT_SYMBOL_GPL(phy_speed_up); + /** * phy_start_machine - start PHY state machine tracking * @phydev: the phy_device struct diff --git a/include/linux/phy.h b/include/linux/phy.h index 6cd09098427c..075c2f770d3e 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -942,6 +942,8 @@ void phy_start(struct phy_device *phydev); void phy_stop(struct phy_device *phydev); int phy_start_aneg(struct phy_device *phydev); int phy_aneg_done(struct phy_device *phydev); +int phy_speed_down(struct phy_device *phydev, bool sync); +int phy_speed_up(struct phy_device *phydev); int phy_stop_interrupts(struct phy_device *phydev); int phy_restart_aneg(struct phy_device *phydev); -- cgit v1.2.3 From d9f37d01e294e5338aa3e9d3b2eda61b59b619df Mon Sep 17 00:00:00 2001 From: Li RongQing Date: Fri, 13 Jul 2018 14:41:36 +0800 Subject: net: convert gro_count to bitmask gro_hash size is 192 bytes, and uses 3 cache lines, if there is few flows, gro_hash may be not fully used, so it is unnecessary to iterate all gro_hash in napi_gro_flush(), to occupy unnecessary cacheline. convert gro_count to a bitmask, and rename it as gro_bitmask, each bit represents a element of gro_hash, only flush a gro_hash element if the related bit is set, to speed up napi_gro_flush(). and update gro_bitmask only if it will be changed, to reduce cache update Suggested-by: Eric Dumazet Signed-off-by: Li RongQing Cc: Stefano Brivio Signed-off-by: David S. Miller --- include/linux/netdevice.h | 9 +++++++-- net/core/dev.c | 36 ++++++++++++++++++++++++------------ 2 files changed, 31 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3514d67112b3..c1295c7a452e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -308,9 +308,14 @@ struct gro_list { }; /* - * Structure for NAPI scheduling similar to tasklet but with weighting + * size of gro hash buckets, must less than bit number of + * napi_struct::gro_bitmask */ #define GRO_HASH_BUCKETS 8 + +/* + * Structure for NAPI scheduling similar to tasklet but with weighting + */ struct napi_struct { /* The poll_list must only be managed by the entity which * changes the state of the NAPI_STATE_SCHED bit. This means @@ -322,7 +327,7 @@ struct napi_struct { unsigned long state; int weight; - unsigned int gro_count; + unsigned long gro_bitmask; int (*poll)(struct napi_struct *, int); #ifdef CONFIG_NETPOLL int poll_owner; diff --git a/net/core/dev.c b/net/core/dev.c index 0df1771a12f9..c883b17ee0fe 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5282,9 +5282,11 @@ static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index, list_del(&skb->list); skb->next = NULL; napi_gro_complete(skb); - napi->gro_count--; napi->gro_hash[index].count--; } + + if (!napi->gro_hash[index].count) + __clear_bit(index, &napi->gro_bitmask); } /* napi->gro_hash[].list contains packets ordered by age. @@ -5295,8 +5297,10 @@ void napi_gro_flush(struct napi_struct *napi, bool flush_old) { u32 i; - for (i = 0; i < GRO_HASH_BUCKETS; i++) - __napi_gro_flush_chain(napi, i, flush_old); + for (i = 0; i < GRO_HASH_BUCKETS; i++) { + if (test_bit(i, &napi->gro_bitmask)) + __napi_gro_flush_chain(napi, i, flush_old); + } } EXPORT_SYMBOL(napi_gro_flush); @@ -5388,8 +5392,8 @@ static void gro_flush_oldest(struct list_head *head) if (WARN_ON_ONCE(!oldest)) return; - /* Do not adjust napi->gro_count, caller is adding a new SKB to - * the chain. + /* Do not adjust napi->gro_hash[].count, caller is adding a new + * SKB to the chain. */ list_del(&oldest->list); napi_gro_complete(oldest); @@ -5464,7 +5468,6 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff list_del(&pp->list); pp->next = NULL; napi_gro_complete(pp); - napi->gro_count--; napi->gro_hash[hash].count--; } @@ -5477,7 +5480,6 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff if (unlikely(napi->gro_hash[hash].count >= MAX_GRO_SKBS)) { gro_flush_oldest(gro_head); } else { - napi->gro_count++; napi->gro_hash[hash].count++; } NAPI_GRO_CB(skb)->count = 1; @@ -5492,6 +5494,13 @@ pull: if (grow > 0) gro_pull_from_frag0(skb, grow); ok: + if (napi->gro_hash[hash].count) { + if (!test_bit(hash, &napi->gro_bitmask)) + __set_bit(hash, &napi->gro_bitmask); + } else if (test_bit(hash, &napi->gro_bitmask)) { + __clear_bit(hash, &napi->gro_bitmask); + } + return ret; normal: @@ -5890,7 +5899,7 @@ bool napi_complete_done(struct napi_struct *n, int work_done) NAPIF_STATE_IN_BUSY_POLL))) return false; - if (n->gro_count) { + if (n->gro_bitmask) { unsigned long timeout = 0; if (work_done) @@ -6099,7 +6108,7 @@ static enum hrtimer_restart napi_watchdog(struct hrtimer *timer) /* Note : we use a relaxed variant of napi_schedule_prep() not setting * NAPI_STATE_MISSED, since we do not react to a device IRQ. */ - if (napi->gro_count && !napi_disable_pending(napi) && + if (napi->gro_bitmask && !napi_disable_pending(napi) && !test_and_set_bit(NAPI_STATE_SCHED, &napi->state)) __napi_schedule_irqoff(napi); @@ -6114,7 +6123,7 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi, INIT_LIST_HEAD(&napi->poll_list); hrtimer_init(&napi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED); napi->timer.function = napi_watchdog; - napi->gro_count = 0; + napi->gro_bitmask = 0; for (i = 0; i < GRO_HASH_BUCKETS; i++) { INIT_LIST_HEAD(&napi->gro_hash[i].list); napi->gro_hash[i].count = 0; @@ -6174,7 +6183,7 @@ void netif_napi_del(struct napi_struct *napi) napi_free_frags(napi); flush_gro_hash(napi); - napi->gro_count = 0; + napi->gro_bitmask = 0; } EXPORT_SYMBOL(netif_napi_del); @@ -6216,7 +6225,7 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll) goto out_unlock; } - if (n->gro_count) { + if (n->gro_bitmask) { /* flush too old packets * If HZ < 1000, flush all packets. */ @@ -9272,6 +9281,9 @@ static struct hlist_head * __net_init netdev_create_hash(void) /* Initialize per network namespace state */ static int __net_init netdev_init(struct net *net) { + BUILD_BUG_ON(GRO_HASH_BUCKETS > + FIELD_SIZEOF(struct napi_struct, gro_bitmask)); + if (net != &init_net) INIT_LIST_HEAD(&net->dev_base_head); -- cgit v1.2.3 From 3d85b2703783636366560c94842affd8608ec9d1 Mon Sep 17 00:00:00 2001 From: Andrea Parri Date: Mon, 16 Jul 2018 11:06:02 -0700 Subject: locking/spinlock, sched/core: Clarify requirements for smp_mb__after_spinlock() There are 11 interpretations of the requirements described in the header comment for smp_mb__after_spinlock(): one for each LKMM maintainer, and one currently encoded in the Cat file. Stick to the latter (until a more satisfactory solution is available). This also reworks some snippets related to the barrier to illustrate the requirements and to link them to the idioms which are relied upon at its call sites. Suggested-by: Boqun Feng Signed-off-by: Andrea Parri Signed-off-by: Paul E. McKenney Acked-by: Peter Zijlstra Cc: Linus Torvalds Cc: Thomas Gleixner Cc: Will Deacon Cc: akiyks@gmail.com Cc: dhowells@redhat.com Cc: j.alglave@ucl.ac.uk Cc: linux-arch@vger.kernel.org Cc: luc.maranget@inria.fr Cc: npiggin@gmail.com Cc: parri.andrea@gmail.com Cc: stern@rowland.harvard.edu Link: http://lkml.kernel.org/r/20180716180605.16115-11-paulmck@linux.vnet.ibm.com Signed-off-by: Ingo Molnar --- include/linux/spinlock.h | 53 ++++++++++++++++++++++++++++++++---------------- kernel/sched/core.c | 41 +++++++++++++++++++------------------ 2 files changed, 57 insertions(+), 37 deletions(-) (limited to 'include') diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index fd57888d4942..3190997df9ca 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -114,29 +114,48 @@ do { \ #endif /*arch_spin_is_contended*/ /* - * This barrier must provide two things: + * smp_mb__after_spinlock() provides the equivalent of a full memory barrier + * between program-order earlier lock acquisitions and program-order later + * memory accesses. * - * - it must guarantee a STORE before the spin_lock() is ordered against a - * LOAD after it, see the comments at its two usage sites. + * This guarantees that the following two properties hold: * - * - it must ensure the critical section is RCsc. + * 1) Given the snippet: * - * The latter is important for cases where we observe values written by other - * CPUs in spin-loops, without barriers, while being subject to scheduling. + * { X = 0; Y = 0; } * - * CPU0 CPU1 CPU2 + * CPU0 CPU1 * - * for (;;) { - * if (READ_ONCE(X)) - * break; - * } - * X=1 - * - * - * r = X; + * WRITE_ONCE(X, 1); WRITE_ONCE(Y, 1); + * spin_lock(S); smp_mb(); + * smp_mb__after_spinlock(); r1 = READ_ONCE(X); + * r0 = READ_ONCE(Y); + * spin_unlock(S); * - * without transitivity it could be that CPU1 observes X!=0 breaks the loop, - * we get migrated and CPU2 sees X==0. + * it is forbidden that CPU0 does not observe CPU1's store to Y (r0 = 0) + * and CPU1 does not observe CPU0's store to X (r1 = 0); see the comments + * preceding the call to smp_mb__after_spinlock() in __schedule() and in + * try_to_wake_up(). + * + * 2) Given the snippet: + * + * { X = 0; Y = 0; } + * + * CPU0 CPU1 CPU2 + * + * spin_lock(S); spin_lock(S); r1 = READ_ONCE(Y); + * WRITE_ONCE(X, 1); smp_mb__after_spinlock(); smp_rmb(); + * spin_unlock(S); r0 = READ_ONCE(X); r2 = READ_ONCE(X); + * WRITE_ONCE(Y, 1); + * spin_unlock(S); + * + * it is forbidden that CPU0's critical section executes before CPU1's + * critical section (r0 = 1), CPU2 observes CPU1's store to Y (r1 = 1) + * and CPU2 does not observe CPU0's store to X (r2 = 0); see the comments + * preceding the calls to smp_rmb() in try_to_wake_up() for similar + * snippets but "projected" onto two CPUs. + * + * Property (2) upgrades the lock to an RCsc lock. * * Since most load-store architectures implement ACQUIRE with an smp_mb() after * the LL/SC loop, they need no further barriers. Similarly all our TSO diff --git a/kernel/sched/core.c b/kernel/sched/core.c index fe365c9a08e9..0c5ec2abdf93 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1998,21 +1998,20 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) * be possible to, falsely, observe p->on_rq == 0 and get stuck * in smp_cond_load_acquire() below. * - * sched_ttwu_pending() try_to_wake_up() - * [S] p->on_rq = 1; [L] P->state - * UNLOCK rq->lock -----. - * \ - * +--- RMB - * schedule() / - * LOCK rq->lock -----' - * UNLOCK rq->lock + * sched_ttwu_pending() try_to_wake_up() + * STORE p->on_rq = 1 LOAD p->state + * UNLOCK rq->lock + * + * __schedule() (switch to task 'p') + * LOCK rq->lock smp_rmb(); + * smp_mb__after_spinlock(); + * UNLOCK rq->lock * * [task p] - * [S] p->state = UNINTERRUPTIBLE [L] p->on_rq + * STORE p->state = UNINTERRUPTIBLE LOAD p->on_rq * - * Pairs with the UNLOCK+LOCK on rq->lock from the - * last wakeup of our task and the schedule that got our task - * current. + * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in + * __schedule(). See the comment for smp_mb__after_spinlock(). */ smp_rmb(); if (p->on_rq && ttwu_remote(p, wake_flags)) @@ -2026,15 +2025,17 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) * One must be running (->on_cpu == 1) in order to remove oneself * from the runqueue. * - * [S] ->on_cpu = 1; [L] ->on_rq - * UNLOCK rq->lock - * RMB - * LOCK rq->lock - * [S] ->on_rq = 0; [L] ->on_cpu + * __schedule() (switch to task 'p') try_to_wake_up() + * STORE p->on_cpu = 1 LOAD p->on_rq + * UNLOCK rq->lock + * + * __schedule() (put 'p' to sleep) + * LOCK rq->lock smp_rmb(); + * smp_mb__after_spinlock(); + * STORE p->on_rq = 0 LOAD p->on_cpu * - * Pairs with the full barrier implied in the UNLOCK+LOCK on rq->lock - * from the consecutive calls to schedule(); the first switching to our - * task, the second putting it to sleep. + * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in + * __schedule(). See the comment for smp_mb__after_spinlock(). */ smp_rmb(); -- cgit v1.2.3 From 7696f9910a9a40b8a952f57d3428515fabd2d889 Mon Sep 17 00:00:00 2001 From: Andrea Parri Date: Mon, 16 Jul 2018 11:06:03 -0700 Subject: sched/Documentation: Update wake_up() & co. memory-barrier guarantees Both the implementation and the users' expectation [1] for the various wakeup primitives have evolved over time, but the documentation has not kept up with these changes: brings it into 2018. [1] http://lkml.kernel.org/r/20180424091510.GB4064@hirez.programming.kicks-ass.net Also applied feedback from Alan Stern. Suggested-by: Peter Zijlstra Signed-off-by: Andrea Parri Signed-off-by: Paul E. McKenney Acked-by: Peter Zijlstra (Intel) Cc: Akira Yokosawa Cc: Alan Stern Cc: Boqun Feng Cc: Daniel Lustig Cc: David Howells Cc: Jade Alglave Cc: Jonathan Corbet Cc: Linus Torvalds Cc: Luc Maranget Cc: Nicholas Piggin Cc: Thomas Gleixner Cc: Will Deacon Cc: linux-arch@vger.kernel.org Cc: parri.andrea@gmail.com Link: http://lkml.kernel.org/r/20180716180605.16115-12-paulmck@linux.vnet.ibm.com Signed-off-by: Ingo Molnar --- Documentation/memory-barriers.txt | 43 ++++++++++++++++++++++++--------------- include/linux/sched.h | 4 ++-- kernel/sched/completion.c | 8 ++++---- kernel/sched/core.c | 30 +++++++++++---------------- kernel/sched/wait.c | 8 ++++---- 5 files changed, 49 insertions(+), 44 deletions(-) (limited to 'include') diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt index a02d6bbfc9d0..0d8d7ef131e9 100644 --- a/Documentation/memory-barriers.txt +++ b/Documentation/memory-barriers.txt @@ -2179,32 +2179,41 @@ or: event_indicated = 1; wake_up_process(event_daemon); -A write memory barrier is implied by wake_up() and co. if and only if they -wake something up. The barrier occurs before the task state is cleared, and so -sits between the STORE to indicate the event and the STORE to set TASK_RUNNING: +A general memory barrier is executed by wake_up() if it wakes something up. +If it doesn't wake anything up then a memory barrier may or may not be +executed; you must not rely on it. The barrier occurs before the task state +is accessed, in particular, it sits between the STORE to indicate the event +and the STORE to set TASK_RUNNING: - CPU 1 CPU 2 + CPU 1 (Sleeper) CPU 2 (Waker) =============================== =============================== set_current_state(); STORE event_indicated smp_store_mb(); wake_up(); - STORE current->state - STORE current->state - LOAD event_indicated + STORE current->state ... + + LOAD event_indicated if ((LOAD task->state) & TASK_NORMAL) + STORE task->state -To repeat, this write memory barrier is present if and only if something -is actually awakened. To see this, consider the following sequence of -events, where X and Y are both initially zero: +where "task" is the thread being woken up and it equals CPU 1's "current". + +To repeat, a general memory barrier is guaranteed to be executed by wake_up() +if something is actually awakened, but otherwise there is no such guarantee. +To see this, consider the following sequence of events, where X and Y are both +initially zero: CPU 1 CPU 2 =============================== =============================== - X = 1; STORE event_indicated + X = 1; Y = 1; smp_mb(); wake_up(); - Y = 1; wait_event(wq, Y == 1); - wake_up(); load from Y sees 1, no memory barrier - load from X might see 0 + LOAD Y LOAD X + +If a wakeup does occur, one (at least) of the two loads must see 1. If, on +the other hand, a wakeup does not occur, both loads might see 0. -In contrast, if a wakeup does occur, CPU 2's load from X would be guaranteed -to see 1. +wake_up_process() always executes a general memory barrier. The barrier again +occurs before the task state is accessed. In particular, if the wake_up() in +the previous snippet were replaced by a call to wake_up_process() then one of +the two loads would be guaranteed to see 1. The available waker functions include: @@ -2224,6 +2233,8 @@ The available waker functions include: wake_up_poll(); wake_up_process(); +In terms of memory ordering, these functions all provide the same guarantees of +a wake_up() (or stronger). [!] Note that the memory barriers implied by the sleeper and the waker do _not_ order multiple stores before the wake-up with respect to loads of those stored diff --git a/include/linux/sched.h b/include/linux/sched.h index 43731fe51c97..05cd419f962d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -167,8 +167,8 @@ struct task_group; * need_sleep = false; * wake_up_state(p, TASK_UNINTERRUPTIBLE); * - * Where wake_up_state() (and all other wakeup primitives) imply enough - * barriers to order the store of the variable against wakeup. + * where wake_up_state() executes a full memory barrier before accessing the + * task state. * * Wakeup will do: if (@state & p->state) p->state = TASK_RUNNING, that is, * once it observes the TASK_UNINTERRUPTIBLE store the waking CPU can issue a diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c index e426b0cb9ac6..a1ad5b7d5521 100644 --- a/kernel/sched/completion.c +++ b/kernel/sched/completion.c @@ -22,8 +22,8 @@ * * See also complete_all(), wait_for_completion() and related routines. * - * It may be assumed that this function implies a write memory barrier before - * changing the task state if and only if any tasks are woken up. + * If this function wakes up a task, it executes a full memory barrier before + * accessing the task state. */ void complete(struct completion *x) { @@ -44,8 +44,8 @@ EXPORT_SYMBOL(complete); * * This will wake up all threads waiting on this particular completion event. * - * It may be assumed that this function implies a write memory barrier before - * changing the task state if and only if any tasks are woken up. + * If this function wakes up a task, it executes a full memory barrier before + * accessing the task state. * * Since complete_all() sets the completion of @x permanently to done * to allow multiple waiters to finish, a call to reinit_completion() diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 0c5ec2abdf93..a0065c84e73f 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -412,8 +412,8 @@ void wake_q_add(struct wake_q_head *head, struct task_struct *task) * its already queued (either by us or someone else) and will get the * wakeup due to that. * - * This cmpxchg() implies a full barrier, which pairs with the write - * barrier implied by the wakeup in wake_up_q(). + * This cmpxchg() executes a full barrier, which pairs with the full + * barrier executed by the wakeup in wake_up_q(). */ if (cmpxchg(&node->next, NULL, WAKE_Q_TAIL)) return; @@ -441,8 +441,8 @@ void wake_up_q(struct wake_q_head *head) task->wake_q.next = NULL; /* - * wake_up_process() implies a wmb() to pair with the queueing - * in wake_q_add() so as not to miss wakeups. + * wake_up_process() executes a full barrier, which pairs with + * the queueing in wake_q_add() so as not to miss wakeups. */ wake_up_process(task); put_task_struct(task); @@ -1879,8 +1879,7 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags) * rq(c1)->lock (if not at the same time, then in that order). * C) LOCK of the rq(c1)->lock scheduling in task * - * Transitivity guarantees that B happens after A and C after B. - * Note: we only require RCpc transitivity. + * Release/acquire chaining guarantees that B happens after A and C after B. * Note: the CPU doing B need not be c0 or c1 * * Example: @@ -1942,16 +1941,9 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags) * UNLOCK rq(0)->lock * * - * However; for wakeups there is a second guarantee we must provide, namely we - * must observe the state that lead to our wakeup. That is, not only must our - * task observe its own prior state, it must also observe the stores prior to - * its wakeup. - * - * This means that any means of doing remote wakeups must order the CPU doing - * the wakeup against the CPU the task is going to end up running on. This, - * however, is already required for the regular Program-Order guarantee above, - * since the waking CPU is the one issueing the ACQUIRE (smp_cond_load_acquire). - * + * However, for wakeups there is a second guarantee we must provide, namely we + * must ensure that CONDITION=1 done by the caller can not be reordered with + * accesses to the task state; see try_to_wake_up() and set_current_state(). */ /** @@ -1967,6 +1959,9 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags) * Atomic against schedule() which would dequeue a task, also see * set_current_state(). * + * This function executes a full memory barrier before accessing the task + * state; see set_current_state(). + * * Return: %true if @p->state changes (an actual wakeup was done), * %false otherwise. */ @@ -2141,8 +2136,7 @@ out: * * Return: 1 if the process was woken up, 0 if it was already running. * - * It may be assumed that this function implies a write memory barrier before - * changing the task state if and only if any tasks are woken up. + * This function executes a full memory barrier before accessing the task state. */ int wake_up_process(struct task_struct *p) { diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index a7a2aaa3026a..870f97b313e3 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -134,8 +134,8 @@ static void __wake_up_common_lock(struct wait_queue_head *wq_head, unsigned int * @nr_exclusive: how many wake-one or wake-many threads to wake up * @key: is directly passed to the wakeup function * - * It may be assumed that this function implies a write memory barrier before - * changing the task state if and only if any tasks are woken up. + * If this function wakes up a task, it executes a full memory barrier before + * accessing the task state. */ void __wake_up(struct wait_queue_head *wq_head, unsigned int mode, int nr_exclusive, void *key) @@ -180,8 +180,8 @@ EXPORT_SYMBOL_GPL(__wake_up_locked_key_bookmark); * * On UP it can prevent extra preemption. * - * It may be assumed that this function implies a write memory barrier before - * changing the task state if and only if any tasks are woken up. + * If this function wakes up a task, it executes a full memory barrier before + * accessing the task state. */ void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode, int nr_exclusive, void *key) -- cgit v1.2.3 From c1a2f7f0c06454387c2cd7b93ff1491c715a8c69 Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Mon, 16 Jul 2018 15:03:31 -0400 Subject: mm: Allocate the mm_cpumask (mm->cpu_bitmap[]) dynamically based on nr_cpu_ids The mm_struct always contains a cpumask bitmap, regardless of CONFIG_CPUMASK_OFFSTACK. That means the first step can be to simplify things, and simply have one bitmask at the end of the mm_struct for the mm_cpumask. This does necessitate moving everything else in mm_struct into an anonymous sub-structure, which can be randomized when struct randomization is enabled. The second step is to determine the correct size for the mm_struct slab object from the size of the mm_struct (excluding the CPU bitmap) and the size the cpumask. For init_mm we can simply allocate the maximum size this kernel is compiled for, since we only have one init_mm in the system, anyway. Pointer magic by Mike Galbraith, to evade -Wstringop-overflow getting confused by the dynamically sized array. Tested-by: Song Liu Signed-off-by: Rik van Riel Signed-off-by: Mike Galbraith Signed-off-by: Rik van Riel Acked-by: Dave Hansen Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: kernel-team@fb.com Cc: luto@kernel.org Link: http://lkml.kernel.org/r/20180716190337.26133-2-riel@surriel.com Signed-off-by: Ingo Molnar --- drivers/firmware/efi/efi.c | 1 + include/linux/mm_types.h | 241 +++++++++++++++++++++++---------------------- kernel/fork.c | 15 +-- mm/init-mm.c | 11 +++ 4 files changed, 145 insertions(+), 123 deletions(-) (limited to 'include') diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 232f4915223b..7f0b19410a95 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -82,6 +82,7 @@ struct mm_struct efi_mm = { .mmap_sem = __RWSEM_INITIALIZER(efi_mm.mmap_sem), .page_table_lock = __SPIN_LOCK_UNLOCKED(efi_mm.page_table_lock), .mmlist = LIST_HEAD_INIT(efi_mm.mmlist), + .cpu_bitmap = { [BITS_TO_LONGS(NR_CPUS)] = 0}, }; static bool disable_runtime; diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 99ce070e7dcb..efdc24dd9e97 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -335,176 +335,183 @@ struct core_state { struct kioctx_table; struct mm_struct { - struct vm_area_struct *mmap; /* list of VMAs */ - struct rb_root mm_rb; - u32 vmacache_seqnum; /* per-thread vmacache */ + struct { + struct vm_area_struct *mmap; /* list of VMAs */ + struct rb_root mm_rb; + u32 vmacache_seqnum; /* per-thread vmacache */ #ifdef CONFIG_MMU - unsigned long (*get_unmapped_area) (struct file *filp, + unsigned long (*get_unmapped_area) (struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); #endif - unsigned long mmap_base; /* base of mmap area */ - unsigned long mmap_legacy_base; /* base of mmap area in bottom-up allocations */ + unsigned long mmap_base; /* base of mmap area */ + unsigned long mmap_legacy_base; /* base of mmap area in bottom-up allocations */ #ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES - /* Base adresses for compatible mmap() */ - unsigned long mmap_compat_base; - unsigned long mmap_compat_legacy_base; + /* Base adresses for compatible mmap() */ + unsigned long mmap_compat_base; + unsigned long mmap_compat_legacy_base; #endif - unsigned long task_size; /* size of task vm space */ - unsigned long highest_vm_end; /* highest vma end address */ - pgd_t * pgd; - - /** - * @mm_users: The number of users including userspace. - * - * Use mmget()/mmget_not_zero()/mmput() to modify. When this drops - * to 0 (i.e. when the task exits and there are no other temporary - * reference holders), we also release a reference on @mm_count - * (which may then free the &struct mm_struct if @mm_count also - * drops to 0). - */ - atomic_t mm_users; - - /** - * @mm_count: The number of references to &struct mm_struct - * (@mm_users count as 1). - * - * Use mmgrab()/mmdrop() to modify. When this drops to 0, the - * &struct mm_struct is freed. - */ - atomic_t mm_count; + unsigned long task_size; /* size of task vm space */ + unsigned long highest_vm_end; /* highest vma end address */ + pgd_t * pgd; + + /** + * @mm_users: The number of users including userspace. + * + * Use mmget()/mmget_not_zero()/mmput() to modify. When this + * drops to 0 (i.e. when the task exits and there are no other + * temporary reference holders), we also release a reference on + * @mm_count (which may then free the &struct mm_struct if + * @mm_count also drops to 0). + */ + atomic_t mm_users; + + /** + * @mm_count: The number of references to &struct mm_struct + * (@mm_users count as 1). + * + * Use mmgrab()/mmdrop() to modify. When this drops to 0, the + * &struct mm_struct is freed. + */ + atomic_t mm_count; #ifdef CONFIG_MMU - atomic_long_t pgtables_bytes; /* PTE page table pages */ + atomic_long_t pgtables_bytes; /* PTE page table pages */ #endif - int map_count; /* number of VMAs */ + int map_count; /* number of VMAs */ - spinlock_t page_table_lock; /* Protects page tables and some counters */ - struct rw_semaphore mmap_sem; + spinlock_t page_table_lock; /* Protects page tables and some + * counters + */ + struct rw_semaphore mmap_sem; - struct list_head mmlist; /* List of maybe swapped mm's. These are globally strung - * together off init_mm.mmlist, and are protected - * by mmlist_lock - */ + struct list_head mmlist; /* List of maybe swapped mm's. These + * are globally strung together off + * init_mm.mmlist, and are protected + * by mmlist_lock + */ - unsigned long hiwater_rss; /* High-watermark of RSS usage */ - unsigned long hiwater_vm; /* High-water virtual memory usage */ + unsigned long hiwater_rss; /* High-watermark of RSS usage */ + unsigned long hiwater_vm; /* High-water virtual memory usage */ - unsigned long total_vm; /* Total pages mapped */ - unsigned long locked_vm; /* Pages that have PG_mlocked set */ - unsigned long pinned_vm; /* Refcount permanently increased */ - unsigned long data_vm; /* VM_WRITE & ~VM_SHARED & ~VM_STACK */ - unsigned long exec_vm; /* VM_EXEC & ~VM_WRITE & ~VM_STACK */ - unsigned long stack_vm; /* VM_STACK */ - unsigned long def_flags; + unsigned long total_vm; /* Total pages mapped */ + unsigned long locked_vm; /* Pages that have PG_mlocked set */ + unsigned long pinned_vm; /* Refcount permanently increased */ + unsigned long data_vm; /* VM_WRITE & ~VM_SHARED & ~VM_STACK */ + unsigned long exec_vm; /* VM_EXEC & ~VM_WRITE & ~VM_STACK */ + unsigned long stack_vm; /* VM_STACK */ + unsigned long def_flags; - spinlock_t arg_lock; /* protect the below fields */ - unsigned long start_code, end_code, start_data, end_data; - unsigned long start_brk, brk, start_stack; - unsigned long arg_start, arg_end, env_start, env_end; + spinlock_t arg_lock; /* protect the below fields */ + unsigned long start_code, end_code, start_data, end_data; + unsigned long start_brk, brk, start_stack; + unsigned long arg_start, arg_end, env_start, env_end; - unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */ + unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */ - /* - * Special counters, in some configurations protected by the - * page_table_lock, in other configurations by being atomic. - */ - struct mm_rss_stat rss_stat; - - struct linux_binfmt *binfmt; + /* + * Special counters, in some configurations protected by the + * page_table_lock, in other configurations by being atomic. + */ + struct mm_rss_stat rss_stat; - cpumask_var_t cpu_vm_mask_var; + struct linux_binfmt *binfmt; - /* Architecture-specific MM context */ - mm_context_t context; + /* Architecture-specific MM context */ + mm_context_t context; - unsigned long flags; /* Must use atomic bitops to access the bits */ + unsigned long flags; /* Must use atomic bitops to access */ - struct core_state *core_state; /* coredumping support */ + struct core_state *core_state; /* coredumping support */ #ifdef CONFIG_MEMBARRIER - atomic_t membarrier_state; + atomic_t membarrier_state; #endif #ifdef CONFIG_AIO - spinlock_t ioctx_lock; - struct kioctx_table __rcu *ioctx_table; + spinlock_t ioctx_lock; + struct kioctx_table __rcu *ioctx_table; #endif #ifdef CONFIG_MEMCG - /* - * "owner" points to a task that is regarded as the canonical - * user/owner of this mm. All of the following must be true in - * order for it to be changed: - * - * current == mm->owner - * current->mm != mm - * new_owner->mm == mm - * new_owner->alloc_lock is held - */ - struct task_struct __rcu *owner; + /* + * "owner" points to a task that is regarded as the canonical + * user/owner of this mm. All of the following must be true in + * order for it to be changed: + * + * current == mm->owner + * current->mm != mm + * new_owner->mm == mm + * new_owner->alloc_lock is held + */ + struct task_struct __rcu *owner; #endif - struct user_namespace *user_ns; + struct user_namespace *user_ns; - /* store ref to file /proc//exe symlink points to */ - struct file __rcu *exe_file; + /* store ref to file /proc//exe symlink points to */ + struct file __rcu *exe_file; #ifdef CONFIG_MMU_NOTIFIER - struct mmu_notifier_mm *mmu_notifier_mm; + struct mmu_notifier_mm *mmu_notifier_mm; #endif #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS - pgtable_t pmd_huge_pte; /* protected by page_table_lock */ -#endif -#ifdef CONFIG_CPUMASK_OFFSTACK - struct cpumask cpumask_allocation; + pgtable_t pmd_huge_pte; /* protected by page_table_lock */ #endif #ifdef CONFIG_NUMA_BALANCING - /* - * numa_next_scan is the next time that the PTEs will be marked - * pte_numa. NUMA hinting faults will gather statistics and migrate - * pages to new nodes if necessary. - */ - unsigned long numa_next_scan; + /* + * numa_next_scan is the next time that the PTEs will be marked + * pte_numa. NUMA hinting faults will gather statistics and + * migrate pages to new nodes if necessary. + */ + unsigned long numa_next_scan; - /* Restart point for scanning and setting pte_numa */ - unsigned long numa_scan_offset; + /* Restart point for scanning and setting pte_numa */ + unsigned long numa_scan_offset; - /* numa_scan_seq prevents two threads setting pte_numa */ - int numa_scan_seq; + /* numa_scan_seq prevents two threads setting pte_numa */ + int numa_scan_seq; #endif - /* - * An operation with batched TLB flushing is going on. Anything that - * can move process memory needs to flush the TLB when moving a - * PROT_NONE or PROT_NUMA mapped page. - */ - atomic_t tlb_flush_pending; + /* + * An operation with batched TLB flushing is going on. Anything + * that can move process memory needs to flush the TLB when + * moving a PROT_NONE or PROT_NUMA mapped page. + */ + atomic_t tlb_flush_pending; #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH - /* See flush_tlb_batched_pending() */ - bool tlb_flush_batched; + /* See flush_tlb_batched_pending() */ + bool tlb_flush_batched; #endif - struct uprobes_state uprobes_state; + struct uprobes_state uprobes_state; #ifdef CONFIG_HUGETLB_PAGE - atomic_long_t hugetlb_usage; + atomic_long_t hugetlb_usage; #endif - struct work_struct async_put_work; + struct work_struct async_put_work; #if IS_ENABLED(CONFIG_HMM) - /* HMM needs to track a few things per mm */ - struct hmm *hmm; + /* HMM needs to track a few things per mm */ + struct hmm *hmm; #endif -} __randomize_layout; + } __randomize_layout; + + /* + * The mm_cpumask needs to be at the end of mm_struct, because it + * is dynamically sized based on nr_cpu_ids. + */ + unsigned long cpu_bitmap[]; +}; extern struct mm_struct init_mm; +/* Pointer magic because the dynamic array size confuses some compilers. */ static inline void mm_init_cpumask(struct mm_struct *mm) { -#ifdef CONFIG_CPUMASK_OFFSTACK - mm->cpu_vm_mask_var = &mm->cpumask_allocation; -#endif - cpumask_clear(mm->cpu_vm_mask_var); + unsigned long cpu_bitmap = (unsigned long)mm; + + cpu_bitmap += offsetof(struct mm_struct, cpu_bitmap); + cpumask_clear((struct cpumask *)cpu_bitmap); } /* Future-safe accessor for struct mm_struct's cpu_vm_mask. */ static inline cpumask_t *mm_cpumask(struct mm_struct *mm) { - return mm->cpu_vm_mask_var; + return (struct cpumask *)&mm->cpu_bitmap; } struct mmu_gather; diff --git a/kernel/fork.c b/kernel/fork.c index 9440d61b925c..5b64c1b8461e 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2253,6 +2253,8 @@ static void sighand_ctor(void *data) void __init proc_caches_init(void) { + unsigned int mm_size; + sighand_cachep = kmem_cache_create("sighand_cache", sizeof(struct sighand_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU| @@ -2269,15 +2271,16 @@ void __init proc_caches_init(void) sizeof(struct fs_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); + /* - * FIXME! The "sizeof(struct mm_struct)" currently includes the - * whole struct cpumask for the OFFSTACK case. We could change - * this to *only* allocate as much of it as required by the - * maximum number of CPU's we can ever have. The cpumask_allocation - * is at the end of the structure, exactly for that reason. + * The mm_cpumask is located at the end of mm_struct, and is + * dynamically sized based on the maximum CPU number this system + * can have, taking hotplug into account (nr_cpu_ids). */ + mm_size = sizeof(struct mm_struct) + cpumask_size(); + mm_cachep = kmem_cache_create_usercopy("mm_struct", - sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN, + mm_size, ARCH_MIN_MMSTRUCT_ALIGN, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, offsetof(struct mm_struct, saved_auxv), sizeof_field(struct mm_struct, saved_auxv), diff --git a/mm/init-mm.c b/mm/init-mm.c index f0179c9c04c2..a787a319211e 100644 --- a/mm/init-mm.c +++ b/mm/init-mm.c @@ -15,6 +15,16 @@ #define INIT_MM_CONTEXT(name) #endif +/* + * For dynamically allocated mm_structs, there is a dynamically sized cpumask + * at the end of the structure, the size of which depends on the maximum CPU + * number the system can see. That way we allocate only as much memory for + * mm_cpumask() as needed for the hundreds, or thousands of processes that + * a system typically runs. + * + * Since there is only one init_mm in the entire system, keep it simple + * and size this cpu_bitmask to NR_CPUS. + */ struct mm_struct init_mm = { .mm_rb = RB_ROOT, .pgd = swapper_pg_dir, @@ -25,5 +35,6 @@ struct mm_struct init_mm = { .arg_lock = __SPIN_LOCK_UNLOCKED(init_mm.arg_lock), .mmlist = LIST_HEAD_INIT(init_mm.mmlist), .user_ns = &init_user_ns, + .cpu_bitmap = { [BITS_TO_LONGS(NR_CPUS)] = 0}, INIT_MM_CONTEXT(init_mm) }; -- cgit v1.2.3 From 2ff6ddf19c0ec40633bd14d8fe28a289816bd98d Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Mon, 16 Jul 2018 15:03:32 -0400 Subject: x86/mm/tlb: Leave lazy TLB mode at page table free time Andy discovered that speculative memory accesses while in lazy TLB mode can crash a system, when a CPU tries to dereference a speculative access using memory contents that used to be valid page table memory, but have since been reused for something else and point into la-la land. The latter problem can be prevented in two ways. The first is to always send a TLB shootdown IPI to CPUs in lazy TLB mode, while the second one is to only send the TLB shootdown at page table freeing time. The second should result in fewer IPIs, since operationgs like mprotect and madvise are very common with some workloads, but do not involve page table freeing. Also, on munmap, batching of page table freeing covers much larger ranges of virtual memory than the batching of unmapped user pages. Tested-by: Song Liu Signed-off-by: Rik van Riel Acked-by: Dave Hansen Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: efault@gmx.de Cc: kernel-team@fb.com Cc: luto@kernel.org Link: http://lkml.kernel.org/r/20180716190337.26133-3-riel@surriel.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/tlbflush.h | 5 +++++ arch/x86/mm/tlb.c | 27 +++++++++++++++++++++++++++ include/asm-generic/tlb.h | 10 ++++++++++ mm/memory.c | 22 ++++++++++++++-------- 4 files changed, 56 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 6690cd3fc8b1..3aa3204b5dc0 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -554,4 +554,9 @@ extern void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch); native_flush_tlb_others(mask, info) #endif +extern void tlb_flush_remove_tables(struct mm_struct *mm); +extern void tlb_flush_remove_tables_local(void *arg); + +#define HAVE_TLB_FLUSH_REMOVE_TABLES + #endif /* _ASM_X86_TLBFLUSH_H */ diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 6eb1f34c3c85..9a893673c56b 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -646,6 +646,33 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, put_cpu(); } +void tlb_flush_remove_tables_local(void *arg) +{ + struct mm_struct *mm = arg; + + if (this_cpu_read(cpu_tlbstate.loaded_mm) == mm && + this_cpu_read(cpu_tlbstate.is_lazy)) { + /* + * We're in lazy mode. We need to at least flush our + * paging-structure cache to avoid speculatively reading + * garbage into our TLB. Since switching to init_mm is barely + * slower than a minimal flush, just switch to init_mm. + */ + switch_mm_irqs_off(NULL, &init_mm, NULL); + } +} + +void tlb_flush_remove_tables(struct mm_struct *mm) +{ + int cpu = get_cpu(); + /* + * XXX: this really only needs to be called for CPUs in lazy TLB mode. + */ + if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids) + smp_call_function_many(mm_cpumask(mm), tlb_flush_remove_tables_local, (void *)mm, 1); + + put_cpu(); +} static void do_flush_tlb_all(void *info) { diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index 3063125197ad..e811ef7b8350 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -303,4 +303,14 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb, #define tlb_migrate_finish(mm) do {} while (0) +/* + * Used to flush the TLB when page tables are removed, when lazy + * TLB mode may cause a CPU to retain intermediate translations + * pointing to about-to-be-freed page table memory. + */ +#ifndef HAVE_TLB_FLUSH_REMOVE_TABLES +#define tlb_flush_remove_tables(mm) do {} while (0) +#define tlb_flush_remove_tables_local(mm) do {} while (0) +#endif + #endif /* _ASM_GENERIC__TLB_H */ diff --git a/mm/memory.c b/mm/memory.c index 7206a634270b..18355e0b971a 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -326,16 +326,20 @@ bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_ #ifdef CONFIG_HAVE_RCU_TABLE_FREE -/* - * See the comment near struct mmu_table_batch. - */ - static void tlb_remove_table_smp_sync(void *arg) { - /* Simply deliver the interrupt */ + struct mm_struct __maybe_unused *mm = arg; + /* + * On most architectures this does nothing. Simply delivering the + * interrupt is enough to prevent races with software page table + * walking like that done in get_user_pages_fast. + * + * See the comment near struct mmu_table_batch. + */ + tlb_flush_remove_tables_local(mm); } -static void tlb_remove_table_one(void *table) +static void tlb_remove_table_one(void *table, struct mmu_gather *tlb) { /* * This isn't an RCU grace period and hence the page-tables cannot be @@ -344,7 +348,7 @@ static void tlb_remove_table_one(void *table) * It is however sufficient for software page-table walkers that rely on * IRQ disabling. See the comment near struct mmu_table_batch. */ - smp_call_function(tlb_remove_table_smp_sync, NULL, 1); + smp_call_function(tlb_remove_table_smp_sync, tlb->mm, 1); __tlb_remove_table(table); } @@ -365,6 +369,8 @@ void tlb_table_flush(struct mmu_gather *tlb) { struct mmu_table_batch **batch = &tlb->batch; + tlb_flush_remove_tables(tlb->mm); + if (*batch) { call_rcu_sched(&(*batch)->rcu, tlb_remove_table_rcu); *batch = NULL; @@ -387,7 +393,7 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table) if (*batch == NULL) { *batch = (struct mmu_table_batch *)__get_free_page(GFP_NOWAIT | __GFP_NOWARN); if (*batch == NULL) { - tlb_remove_table_one(table); + tlb_remove_table_one(table, tlb); return; } (*batch)->nr = 0; -- cgit v1.2.3 From 4aaf448fa9754e2d5ee188d32327b24ffc15ca4d Mon Sep 17 00:00:00 2001 From: Jim Qu Date: Tue, 17 Jul 2018 16:20:50 +0800 Subject: vga_switcheroo: set audio client id according to bound GPU id On modern laptop, there are more and more platforms have two GPUs, and each of them maybe have audio codec for HDMP/DP output. For some dGPU which is no output, audio codec usually is disabled. In currect HDA audio driver, it will set all codec as VGA_SWITCHEROO_DIS, the audio which is binded to UMA will be suspended if user use debugfs to contorl power In HDA driver side, it is difficult to know which GPU the audio has binded to. So set the bound gpu pci dev to vga_switcheroo. if the audio client is not the third registration, audio id will set in vga_switcheroo enable function. if the audio client is the last registration when vga_switcheroo _ready() get true, we should get audio client id from bound GPU directly. Signed-off-by: Jim Qu Reviewed-by: Lukas Wunner Signed-off-by: Takashi Iwai --- drivers/gpu/vga/vga_switcheroo.c | 63 +++++++++++++++++++++++++++++++++------- include/linux/vga_switcheroo.h | 8 ++--- sound/pci/hda/hda_intel.c | 11 +++---- 3 files changed, 62 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/drivers/gpu/vga/vga_switcheroo.c b/drivers/gpu/vga/vga_switcheroo.c index fc4adf3d34e8..a96bf46bc483 100644 --- a/drivers/gpu/vga/vga_switcheroo.c +++ b/drivers/gpu/vga/vga_switcheroo.c @@ -103,9 +103,11 @@ * runtime pm. If true, writing ON and OFF to the vga_switcheroo debugfs * interface is a no-op so as not to interfere with runtime pm * @list: client list + * @vga_dev: pci device, indicate which GPU is bound to current audio client * * Registered client. A client can be either a GPU or an audio device on a GPU. - * For audio clients, the @fb_info and @active members are bogus. + * For audio clients, the @fb_info and @active members are bogus. For GPU + * clients, the @vga_dev is bogus. */ struct vga_switcheroo_client { struct pci_dev *pdev; @@ -116,6 +118,7 @@ struct vga_switcheroo_client { bool active; bool driver_power_control; struct list_head list; + struct pci_dev *vga_dev; }; /* @@ -161,9 +164,8 @@ struct vgasr_priv { }; #define ID_BIT_AUDIO 0x100 -#define client_is_audio(c) ((c)->id & ID_BIT_AUDIO) -#define client_is_vga(c) ((c)->id == VGA_SWITCHEROO_UNKNOWN_ID || \ - !client_is_audio(c)) +#define client_is_audio(c) ((c)->id & ID_BIT_AUDIO) +#define client_is_vga(c) (!client_is_audio(c)) #define client_id(c) ((c)->id & ~ID_BIT_AUDIO) static int vga_switcheroo_debugfs_init(struct vgasr_priv *priv); @@ -192,14 +194,29 @@ static void vga_switcheroo_enable(void) vgasr_priv.handler->init(); list_for_each_entry(client, &vgasr_priv.clients, list) { - if (client->id != VGA_SWITCHEROO_UNKNOWN_ID) + if (!client_is_vga(client) || + client_id(client) != VGA_SWITCHEROO_UNKNOWN_ID) continue; + ret = vgasr_priv.handler->get_client_id(client->pdev); if (ret < 0) return; client->id = ret; } + + list_for_each_entry(client, &vgasr_priv.clients, list) { + if (!client_is_audio(client) || + client_id(client) != VGA_SWITCHEROO_UNKNOWN_ID) + continue; + + ret = vgasr_priv.handler->get_client_id(client->vga_dev); + if (ret < 0) + return; + + client->id = ret | ID_BIT_AUDIO; + } + vga_switcheroo_debugfs_init(&vgasr_priv); vgasr_priv.active = true; } @@ -272,7 +289,9 @@ EXPORT_SYMBOL(vga_switcheroo_handler_flags); static int register_client(struct pci_dev *pdev, const struct vga_switcheroo_client_ops *ops, - enum vga_switcheroo_client_id id, bool active, + enum vga_switcheroo_client_id id, + struct pci_dev *vga_dev, + bool active, bool driver_power_control) { struct vga_switcheroo_client *client; @@ -287,6 +306,7 @@ static int register_client(struct pci_dev *pdev, client->id = id; client->active = active; client->driver_power_control = driver_power_control; + client->vga_dev = vga_dev; mutex_lock(&vgasr_mutex); list_add_tail(&client->list, &vgasr_priv.clients); @@ -319,7 +339,7 @@ int vga_switcheroo_register_client(struct pci_dev *pdev, const struct vga_switcheroo_client_ops *ops, bool driver_power_control) { - return register_client(pdev, ops, VGA_SWITCHEROO_UNKNOWN_ID, + return register_client(pdev, ops, VGA_SWITCHEROO_UNKNOWN_ID, NULL, pdev == vga_default_device(), driver_power_control); } @@ -329,19 +349,40 @@ EXPORT_SYMBOL(vga_switcheroo_register_client); * vga_switcheroo_register_audio_client - register audio client * @pdev: client pci device * @ops: client callbacks - * @id: client identifier + * @vga_dev: pci device which is bound to current audio client * * Register audio client (audio device on a GPU). The client is assumed * to use runtime PM. Beforehand, vga_switcheroo_client_probe_defer() * shall be called to ensure that all prerequisites are met. * - * Return: 0 on success, -ENOMEM on memory allocation error. + * Return: 0 on success, -ENOMEM on memory allocation error, -EINVAL on getting + * client id error. */ int vga_switcheroo_register_audio_client(struct pci_dev *pdev, const struct vga_switcheroo_client_ops *ops, - enum vga_switcheroo_client_id id) + struct pci_dev *vga_dev) { - return register_client(pdev, ops, id | ID_BIT_AUDIO, false, true); + enum vga_switcheroo_client_id id = VGA_SWITCHEROO_UNKNOWN_ID; + + /* + * if vga_switcheroo has enabled, that mean two GPU clients and also + * handler are registered. Get audio client id from bound GPU client + * id directly, otherwise, set it as VGA_SWITCHEROO_UNKNOWN_ID, + * it will set to correct id in later when vga_switcheroo_enable() + * is called. + */ + mutex_lock(&vgasr_mutex); + if (vgasr_priv.active) { + id = vgasr_priv.handler->get_client_id(vga_dev); + if (id < 0) { + mutex_unlock(&vgasr_mutex); + return -EINVAL; + } + } + mutex_unlock(&vgasr_mutex); + + return register_client(pdev, ops, id | ID_BIT_AUDIO, vga_dev, + false, true); } EXPORT_SYMBOL(vga_switcheroo_register_audio_client); diff --git a/include/linux/vga_switcheroo.h b/include/linux/vga_switcheroo.h index 77f0f0af3a71..a34539b7f750 100644 --- a/include/linux/vga_switcheroo.h +++ b/include/linux/vga_switcheroo.h @@ -84,8 +84,8 @@ enum vga_switcheroo_state { * Client identifier. Audio clients use the same identifier & 0x100. */ enum vga_switcheroo_client_id { - VGA_SWITCHEROO_UNKNOWN_ID = -1, - VGA_SWITCHEROO_IGD, + VGA_SWITCHEROO_UNKNOWN_ID = 0x1000, + VGA_SWITCHEROO_IGD = 0, VGA_SWITCHEROO_DIS, VGA_SWITCHEROO_MAX_CLIENTS, }; @@ -151,7 +151,7 @@ int vga_switcheroo_register_client(struct pci_dev *dev, bool driver_power_control); int vga_switcheroo_register_audio_client(struct pci_dev *pdev, const struct vga_switcheroo_client_ops *ops, - enum vga_switcheroo_client_id id); + struct pci_dev *vga_dev); void vga_switcheroo_client_fb_set(struct pci_dev *dev, struct fb_info *info); @@ -180,7 +180,7 @@ static inline int vga_switcheroo_register_handler(const struct vga_switcheroo_ha enum vga_switcheroo_handler_flags_t handler_flags) { return 0; } static inline int vga_switcheroo_register_audio_client(struct pci_dev *pdev, const struct vga_switcheroo_client_ops *ops, - enum vga_switcheroo_client_id id) { return 0; } + struct pci_dev *vga_dev) { return 0; } static inline void vga_switcheroo_unregister_handler(void) {} static inline enum vga_switcheroo_handler_flags_t vga_switcheroo_handler_flags(void) { return 0; } static inline int vga_switcheroo_lock_ddc(struct pci_dev *pdev) { return -ENODEV; } diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 1ae1850b3bfd..1967a5537d68 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -1319,15 +1319,16 @@ static const struct vga_switcheroo_client_ops azx_vs_ops = { static int register_vga_switcheroo(struct azx *chip) { struct hda_intel *hda = container_of(chip, struct hda_intel, chip); + struct pci_dev *p; int err; if (!hda->use_vga_switcheroo) return 0; - /* FIXME: currently only handling DIS controller - * is there any machine with two switchable HDMI audio controllers? - */ - err = vga_switcheroo_register_audio_client(chip->pci, &azx_vs_ops, - VGA_SWITCHEROO_DIS); + + p = get_bound_vga(chip->pci); + err = vga_switcheroo_register_audio_client(chip->pci, &azx_vs_ops, p); + pci_dev_put(p); + if (err < 0) return err; hda->vga_switcheroo_registered = 1; -- cgit v1.2.3 From a0ae2562c6c4b2721d9fddba63b7286c13517d9f Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 29 Jun 2018 07:46:51 +0200 Subject: netfilter: conntrack: remove l3proto abstraction This unifies ipv4 and ipv6 protocol trackers and removes the l3proto abstraction. This gets rid of all l3proto indirect calls and the need to do a lookup on the function to call for l3 demux. It increases module size by only a small amount (12kbyte), so this reduces size because nf_conntrack.ko is useless without either nf_conntrack_ipv4 or nf_conntrack_ipv6 module. before: text data bss dec hex filename 7357 1088 0 8445 20fd nf_conntrack_ipv4.ko 7405 1084 4 8493 212d nf_conntrack_ipv6.ko 72614 13689 236 86539 1520b nf_conntrack.ko 19K nf_conntrack_ipv4.ko 19K nf_conntrack_ipv6.ko 179K nf_conntrack.ko after: text data bss dec hex filename 79277 13937 236 93450 16d0a nf_conntrack.ko 191K nf_conntrack.ko Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/ipv4/nf_conntrack_ipv4.h | 3 - include/net/netfilter/nf_conntrack.h | 5 + include/net/netfilter/nf_conntrack_core.h | 1 - include/net/netfilter/nf_conntrack_l3proto.h | 54 -- include/net/netfilter/nf_conntrack_l4proto.h | 4 - net/ipv4/netfilter/Kconfig | 22 +- net/ipv4/netfilter/Makefile | 6 - net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c | 368 ----------- net/ipv4/netfilter/nf_conntrack_proto_icmp.c | 388 ----------- net/ipv6/netfilter/Kconfig | 27 +- net/ipv6/netfilter/Makefile | 6 - net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c | 355 ----------- net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c | 387 ----------- net/netfilter/Kconfig | 2 + net/netfilter/Makefile | 7 +- net/netfilter/nf_conntrack_core.c | 11 +- net/netfilter/nf_conntrack_proto.c | 847 ++++++++++++++++++------- net/netfilter/nf_conntrack_proto_icmp.c | 388 +++++++++++ net/netfilter/nf_conntrack_proto_icmpv6.c | 387 +++++++++++ net/netfilter/nf_conntrack_standalone.c | 14 +- net/netfilter/nf_nat_core.c | 8 - 21 files changed, 1420 insertions(+), 1870 deletions(-) delete mode 100644 include/net/netfilter/nf_conntrack_l3proto.h delete mode 100644 net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c delete mode 100644 net/ipv4/netfilter/nf_conntrack_proto_icmp.c delete mode 100644 net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c delete mode 100644 net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c create mode 100644 net/netfilter/nf_conntrack_proto_icmp.c create mode 100644 net/netfilter/nf_conntrack_proto_icmpv6.c (limited to 'include') diff --git a/include/net/netfilter/ipv4/nf_conntrack_ipv4.h b/include/net/netfilter/ipv4/nf_conntrack_ipv4.h index 73f825732326..c84b51682f08 100644 --- a/include/net/netfilter/ipv4/nf_conntrack_ipv4.h +++ b/include/net/netfilter/ipv4/nf_conntrack_ipv4.h @@ -10,9 +10,6 @@ #ifndef _NF_CONNTRACK_IPV4_H #define _NF_CONNTRACK_IPV4_H - -const extern struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4; - extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4; extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4; extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp; diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 062dc19b5840..a2b0ed025908 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -41,6 +41,11 @@ union nf_conntrack_expect_proto { /* insert expect proto private data here */ }; +struct nf_conntrack_net { + unsigned int users4; + unsigned int users6; +}; + #include #include diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index 35461b2d3462..2a3e0974a6af 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -14,7 +14,6 @@ #define _NF_CONNTRACK_CORE_H #include -#include #include #include diff --git a/include/net/netfilter/nf_conntrack_l3proto.h b/include/net/netfilter/nf_conntrack_l3proto.h deleted file mode 100644 index 5f160375c93a..000000000000 --- a/include/net/netfilter/nf_conntrack_l3proto.h +++ /dev/null @@ -1,54 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright (C)2003,2004 USAGI/WIDE Project - * - * Header for use in defining a given L3 protocol for connection tracking. - * - * Author: - * Yasuyuki Kozakai @USAGI - * - * Derived from include/netfilter_ipv4/ip_conntrack_protocol.h - */ - -#ifndef _NF_CONNTRACK_L3PROTO_H -#define _NF_CONNTRACK_L3PROTO_H -#include -#include -#include -#include - -struct nf_conntrack_l3proto { - /* L3 Protocol Family number. ex) PF_INET */ - u_int16_t l3proto; - - /* size of tuple nlattr, fills a hole */ - u16 nla_size; - - /* Called when netns wants to use connection tracking */ - int (*net_ns_get)(struct net *); - void (*net_ns_put)(struct net *); - - /* Module (if any) which this is connected to. */ - struct module *me; -}; - -extern struct nf_conntrack_l3proto __rcu *nf_ct_l3protos[NFPROTO_NUMPROTO]; - -/* Protocol global registration. */ -int nf_ct_l3proto_register(const struct nf_conntrack_l3proto *proto); -void nf_ct_l3proto_unregister(const struct nf_conntrack_l3proto *proto); - -const struct nf_conntrack_l3proto *nf_ct_l3proto_find_get(u_int16_t l3proto); - -/* Existing built-in protocols */ -extern struct nf_conntrack_l3proto nf_conntrack_l3proto_generic; - -static inline struct nf_conntrack_l3proto * -__nf_ct_l3proto_find(u_int16_t l3proto) -{ - if (unlikely(l3proto >= NFPROTO_NUMPROTO)) - return &nf_conntrack_l3proto_generic; - return rcu_dereference(nf_ct_l3protos[l3proto]); -} - -#endif /*_NF_CONNTRACK_L3PROTO_H*/ diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index c7a0075d96df..6068c6da3eac 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -130,10 +130,6 @@ void nf_ct_l4proto_pernet_unregister(struct net *net, /* Protocol global registration. */ int nf_ct_l4proto_register_one(const struct nf_conntrack_l4proto *proto); void nf_ct_l4proto_unregister_one(const struct nf_conntrack_l4proto *proto); -int nf_ct_l4proto_register(const struct nf_conntrack_l4proto * const proto[], - unsigned int num_proto); -void nf_ct_l4proto_unregister(const struct nf_conntrack_l4proto * const proto[], - unsigned int num_proto); /* Generic netlink helpers */ int nf_ct_port_tuple_to_nlattr(struct sk_buff *skb, diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index bbfc356cb1b5..d9504adc47b3 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -9,22 +9,6 @@ config NF_DEFRAG_IPV4 tristate default n -config NF_CONNTRACK_IPV4 - tristate "IPv4 connection tracking support (required for NAT)" - depends on NF_CONNTRACK - default m if NETFILTER_ADVANCED=n - select NF_DEFRAG_IPV4 - ---help--- - Connection tracking keeps a record of what packets have passed - through your machine, in order to figure out how they are related - into connections. - - This is IPv4 support on Layer 3 independent connection tracking. - Layer 3 independent connection tracking is experimental scheme - which generalize ip_conntrack to support other layer 3 protocols. - - To compile it as a module, choose M here. If unsure, say N. - config NF_SOCKET_IPV4 tristate "IPv4 socket lookup support" help @@ -112,7 +96,7 @@ config NF_REJECT_IPV4 config NF_NAT_IPV4 tristate "IPv4 NAT" - depends on NF_CONNTRACK_IPV4 + depends on NF_CONNTRACK default m if NETFILTER_ADVANCED=n select NF_NAT help @@ -279,7 +263,7 @@ config IP_NF_TARGET_SYNPROXY # NAT + specific targets: nf_conntrack config IP_NF_NAT tristate "iptables NAT support" - depends on NF_CONNTRACK_IPV4 + depends on NF_CONNTRACK default m if NETFILTER_ADVANCED=n select NF_NAT select NF_NAT_IPV4 @@ -340,7 +324,7 @@ config IP_NF_MANGLE config IP_NF_TARGET_CLUSTERIP tristate "CLUSTERIP target support" depends on IP_NF_MANGLE - depends on NF_CONNTRACK_IPV4 + depends on NF_CONNTRACK depends on NETFILTER_ADVANCED select NF_CONNTRACK_MARK select NETFILTER_FAMILY_ARP diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index 8394c17c269f..367993adf4d3 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -3,12 +3,6 @@ # Makefile for the netfilter modules on top of IPv4. # -# objects for l3 independent conntrack -nf_conntrack_ipv4-y := nf_conntrack_l3proto_ipv4.o nf_conntrack_proto_icmp.o - -# connection tracking -obj-$(CONFIG_NF_CONNTRACK_IPV4) += nf_conntrack_ipv4.o - nf_nat_ipv4-y := nf_nat_l3proto_ipv4.o nf_nat_proto_icmp.o nf_nat_ipv4-$(CONFIG_NF_NAT_MASQUERADE_IPV4) += nf_nat_masquerade_ipv4.o obj-$(CONFIG_NF_NAT_IPV4) += nf_nat_ipv4.o diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c deleted file mode 100644 index 9fbf6c7f8ece..000000000000 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ /dev/null @@ -1,368 +0,0 @@ - -/* (C) 1999-2001 Paul `Rusty' Russell - * (C) 2002-2004 Netfilter Core Team - * (C) 2006-2012 Patrick McHardy - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -static int conntrack4_net_id __read_mostly; -static DEFINE_MUTEX(register_ipv4_hooks); - -struct conntrack4_net { - unsigned int users; -}; - -static unsigned int ipv4_helper(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - struct nf_conn *ct; - enum ip_conntrack_info ctinfo; - const struct nf_conn_help *help; - const struct nf_conntrack_helper *helper; - - /* This is where we call the helper: as the packet goes out. */ - ct = nf_ct_get(skb, &ctinfo); - if (!ct || ctinfo == IP_CT_RELATED_REPLY) - return NF_ACCEPT; - - help = nfct_help(ct); - if (!help) - return NF_ACCEPT; - - /* rcu_read_lock()ed by nf_hook_thresh */ - helper = rcu_dereference(help->helper); - if (!helper) - return NF_ACCEPT; - - return helper->help(skb, skb_network_offset(skb) + ip_hdrlen(skb), - ct, ctinfo); -} - -static unsigned int ipv4_confirm(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - struct nf_conn *ct; - enum ip_conntrack_info ctinfo; - - ct = nf_ct_get(skb, &ctinfo); - if (!ct || ctinfo == IP_CT_RELATED_REPLY) - goto out; - - /* adjust seqs for loopback traffic only in outgoing direction */ - if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) && - !nf_is_loopback_packet(skb)) { - if (!nf_ct_seq_adjust(skb, ct, ctinfo, ip_hdrlen(skb))) { - NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop); - return NF_DROP; - } - } -out: - /* We've seen it coming out the other side: confirm it */ - return nf_conntrack_confirm(skb); -} - -static unsigned int ipv4_conntrack_in(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return nf_conntrack_in(state->net, PF_INET, state->hook, skb); -} - -static unsigned int ipv4_conntrack_local(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - if (ip_is_fragment(ip_hdr(skb))) { /* IP_NODEFRAG setsockopt set */ - enum ip_conntrack_info ctinfo; - struct nf_conn *tmpl; - - tmpl = nf_ct_get(skb, &ctinfo); - if (tmpl && nf_ct_is_template(tmpl)) { - /* when skipping ct, clear templates to avoid fooling - * later targets/matches - */ - skb->_nfct = 0; - nf_ct_put(tmpl); - } - return NF_ACCEPT; - } - - return nf_conntrack_in(state->net, PF_INET, state->hook, skb); -} - -/* Connection tracking may drop packets, but never alters them, so - make it the first hook. */ -static const struct nf_hook_ops ipv4_conntrack_ops[] = { - { - .hook = ipv4_conntrack_in, - .pf = NFPROTO_IPV4, - .hooknum = NF_INET_PRE_ROUTING, - .priority = NF_IP_PRI_CONNTRACK, - }, - { - .hook = ipv4_conntrack_local, - .pf = NFPROTO_IPV4, - .hooknum = NF_INET_LOCAL_OUT, - .priority = NF_IP_PRI_CONNTRACK, - }, - { - .hook = ipv4_helper, - .pf = NFPROTO_IPV4, - .hooknum = NF_INET_POST_ROUTING, - .priority = NF_IP_PRI_CONNTRACK_HELPER, - }, - { - .hook = ipv4_confirm, - .pf = NFPROTO_IPV4, - .hooknum = NF_INET_POST_ROUTING, - .priority = NF_IP_PRI_CONNTRACK_CONFIRM, - }, - { - .hook = ipv4_helper, - .pf = NFPROTO_IPV4, - .hooknum = NF_INET_LOCAL_IN, - .priority = NF_IP_PRI_CONNTRACK_HELPER, - }, - { - .hook = ipv4_confirm, - .pf = NFPROTO_IPV4, - .hooknum = NF_INET_LOCAL_IN, - .priority = NF_IP_PRI_CONNTRACK_CONFIRM, - }, -}; - -/* Fast function for those who don't want to parse /proc (and I don't - blame them). */ -/* Reversing the socket's dst/src point of view gives us the reply - mapping. */ -static int -getorigdst(struct sock *sk, int optval, void __user *user, int *len) -{ - const struct inet_sock *inet = inet_sk(sk); - const struct nf_conntrack_tuple_hash *h; - struct nf_conntrack_tuple tuple; - - memset(&tuple, 0, sizeof(tuple)); - - lock_sock(sk); - tuple.src.u3.ip = inet->inet_rcv_saddr; - tuple.src.u.tcp.port = inet->inet_sport; - tuple.dst.u3.ip = inet->inet_daddr; - tuple.dst.u.tcp.port = inet->inet_dport; - tuple.src.l3num = PF_INET; - tuple.dst.protonum = sk->sk_protocol; - release_sock(sk); - - /* We only do TCP and SCTP at the moment: is there a better way? */ - if (tuple.dst.protonum != IPPROTO_TCP && - tuple.dst.protonum != IPPROTO_SCTP) { - pr_debug("SO_ORIGINAL_DST: Not a TCP/SCTP socket\n"); - return -ENOPROTOOPT; - } - - if ((unsigned int) *len < sizeof(struct sockaddr_in)) { - pr_debug("SO_ORIGINAL_DST: len %d not %zu\n", - *len, sizeof(struct sockaddr_in)); - return -EINVAL; - } - - h = nf_conntrack_find_get(sock_net(sk), &nf_ct_zone_dflt, &tuple); - if (h) { - struct sockaddr_in sin; - struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h); - - sin.sin_family = AF_INET; - sin.sin_port = ct->tuplehash[IP_CT_DIR_ORIGINAL] - .tuple.dst.u.tcp.port; - sin.sin_addr.s_addr = ct->tuplehash[IP_CT_DIR_ORIGINAL] - .tuple.dst.u3.ip; - memset(sin.sin_zero, 0, sizeof(sin.sin_zero)); - - pr_debug("SO_ORIGINAL_DST: %pI4 %u\n", - &sin.sin_addr.s_addr, ntohs(sin.sin_port)); - nf_ct_put(ct); - if (copy_to_user(user, &sin, sizeof(sin)) != 0) - return -EFAULT; - else - return 0; - } - pr_debug("SO_ORIGINAL_DST: Can't find %pI4/%u-%pI4/%u.\n", - &tuple.src.u3.ip, ntohs(tuple.src.u.tcp.port), - &tuple.dst.u3.ip, ntohs(tuple.dst.u.tcp.port)); - return -ENOENT; -} - -static struct nf_sockopt_ops so_getorigdst = { - .pf = PF_INET, - .get_optmin = SO_ORIGINAL_DST, - .get_optmax = SO_ORIGINAL_DST+1, - .get = getorigdst, - .owner = THIS_MODULE, -}; - -static int ipv4_hooks_register(struct net *net) -{ - struct conntrack4_net *cnet = net_generic(net, conntrack4_net_id); - int err = 0; - - mutex_lock(®ister_ipv4_hooks); - - cnet->users++; - if (cnet->users > 1) - goto out_unlock; - - err = nf_defrag_ipv4_enable(net); - if (err) { - cnet->users = 0; - goto out_unlock; - } - - err = nf_register_net_hooks(net, ipv4_conntrack_ops, - ARRAY_SIZE(ipv4_conntrack_ops)); - - if (err) - cnet->users = 0; - out_unlock: - mutex_unlock(®ister_ipv4_hooks); - return err; -} - -static void ipv4_hooks_unregister(struct net *net) -{ - struct conntrack4_net *cnet = net_generic(net, conntrack4_net_id); - - mutex_lock(®ister_ipv4_hooks); - if (cnet->users && (--cnet->users == 0)) - nf_unregister_net_hooks(net, ipv4_conntrack_ops, - ARRAY_SIZE(ipv4_conntrack_ops)); - mutex_unlock(®ister_ipv4_hooks); -} - -const struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 = { - .l3proto = PF_INET, - .net_ns_get = ipv4_hooks_register, - .net_ns_put = ipv4_hooks_unregister, - .me = THIS_MODULE, -}; - -module_param_call(hashsize, nf_conntrack_set_hashsize, param_get_uint, - &nf_conntrack_htable_size, 0600); - -MODULE_ALIAS("nf_conntrack-" __stringify(AF_INET)); -MODULE_ALIAS("ip_conntrack"); -MODULE_LICENSE("GPL"); - -static const struct nf_conntrack_l4proto * const builtin_l4proto4[] = { - &nf_conntrack_l4proto_tcp4, - &nf_conntrack_l4proto_udp4, - &nf_conntrack_l4proto_icmp, -#ifdef CONFIG_NF_CT_PROTO_DCCP - &nf_conntrack_l4proto_dccp4, -#endif -#ifdef CONFIG_NF_CT_PROTO_SCTP - &nf_conntrack_l4proto_sctp4, -#endif -#ifdef CONFIG_NF_CT_PROTO_UDPLITE - &nf_conntrack_l4proto_udplite4, -#endif -}; - -static int ipv4_net_init(struct net *net) -{ - return nf_ct_l4proto_pernet_register(net, builtin_l4proto4, - ARRAY_SIZE(builtin_l4proto4)); -} - -static void ipv4_net_exit(struct net *net) -{ - nf_ct_l4proto_pernet_unregister(net, builtin_l4proto4, - ARRAY_SIZE(builtin_l4proto4)); -} - -static struct pernet_operations ipv4_net_ops = { - .init = ipv4_net_init, - .exit = ipv4_net_exit, - .id = &conntrack4_net_id, - .size = sizeof(struct conntrack4_net), -}; - -static int __init nf_conntrack_l3proto_ipv4_init(void) -{ - int ret = 0; - - need_conntrack(); - - ret = nf_register_sockopt(&so_getorigdst); - if (ret < 0) { - pr_err("Unable to register netfilter socket option\n"); - return ret; - } - - ret = register_pernet_subsys(&ipv4_net_ops); - if (ret < 0) { - pr_err("nf_conntrack_ipv4: can't register pernet ops\n"); - goto cleanup_sockopt; - } - - ret = nf_ct_l4proto_register(builtin_l4proto4, - ARRAY_SIZE(builtin_l4proto4)); - if (ret < 0) - goto cleanup_pernet; - - ret = nf_ct_l3proto_register(&nf_conntrack_l3proto_ipv4); - if (ret < 0) { - pr_err("nf_conntrack_ipv4: can't register ipv4 proto.\n"); - goto cleanup_l4proto; - } - - return ret; -cleanup_l4proto: - nf_ct_l4proto_unregister(builtin_l4proto4, - ARRAY_SIZE(builtin_l4proto4)); - cleanup_pernet: - unregister_pernet_subsys(&ipv4_net_ops); - cleanup_sockopt: - nf_unregister_sockopt(&so_getorigdst); - return ret; -} - -static void __exit nf_conntrack_l3proto_ipv4_fini(void) -{ - synchronize_net(); - nf_ct_l3proto_unregister(&nf_conntrack_l3proto_ipv4); - nf_ct_l4proto_unregister(builtin_l4proto4, - ARRAY_SIZE(builtin_l4proto4)); - unregister_pernet_subsys(&ipv4_net_ops); - nf_unregister_sockopt(&so_getorigdst); -} - -module_init(nf_conntrack_l3proto_ipv4_init); -module_exit(nf_conntrack_l3proto_ipv4_fini); diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c deleted file mode 100644 index 036670b38282..000000000000 --- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c +++ /dev/null @@ -1,388 +0,0 @@ -/* (C) 1999-2001 Paul `Rusty' Russell - * (C) 2002-2004 Netfilter Core Team - * (C) 2006-2010 Patrick McHardy - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -static const unsigned int nf_ct_icmp_timeout = 30*HZ; - -static inline struct nf_icmp_net *icmp_pernet(struct net *net) -{ - return &net->ct.nf_ct_proto.icmp; -} - -static bool icmp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, - struct net *net, struct nf_conntrack_tuple *tuple) -{ - const struct icmphdr *hp; - struct icmphdr _hdr; - - hp = skb_header_pointer(skb, dataoff, sizeof(_hdr), &_hdr); - if (hp == NULL) - return false; - - tuple->dst.u.icmp.type = hp->type; - tuple->src.u.icmp.id = hp->un.echo.id; - tuple->dst.u.icmp.code = hp->code; - - return true; -} - -/* Add 1; spaces filled with 0. */ -static const u_int8_t invmap[] = { - [ICMP_ECHO] = ICMP_ECHOREPLY + 1, - [ICMP_ECHOREPLY] = ICMP_ECHO + 1, - [ICMP_TIMESTAMP] = ICMP_TIMESTAMPREPLY + 1, - [ICMP_TIMESTAMPREPLY] = ICMP_TIMESTAMP + 1, - [ICMP_INFO_REQUEST] = ICMP_INFO_REPLY + 1, - [ICMP_INFO_REPLY] = ICMP_INFO_REQUEST + 1, - [ICMP_ADDRESS] = ICMP_ADDRESSREPLY + 1, - [ICMP_ADDRESSREPLY] = ICMP_ADDRESS + 1 -}; - -static bool icmp_invert_tuple(struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_tuple *orig) -{ - if (orig->dst.u.icmp.type >= sizeof(invmap) || - !invmap[orig->dst.u.icmp.type]) - return false; - - tuple->src.u.icmp.id = orig->src.u.icmp.id; - tuple->dst.u.icmp.type = invmap[orig->dst.u.icmp.type] - 1; - tuple->dst.u.icmp.code = orig->dst.u.icmp.code; - return true; -} - -static unsigned int *icmp_get_timeouts(struct net *net) -{ - return &icmp_pernet(net)->timeout; -} - -/* Returns verdict for packet, or -1 for invalid. */ -static int icmp_packet(struct nf_conn *ct, - const struct sk_buff *skb, - unsigned int dataoff, - enum ip_conntrack_info ctinfo) -{ - /* Do not immediately delete the connection after the first - successful reply to avoid excessive conntrackd traffic - and also to handle correctly ICMP echo reply duplicates. */ - unsigned int *timeout = nf_ct_timeout_lookup(ct); - - if (!timeout) - timeout = icmp_get_timeouts(nf_ct_net(ct)); - - nf_ct_refresh_acct(ct, ctinfo, skb, *timeout); - - return NF_ACCEPT; -} - -/* Called when a new connection for this protocol found. */ -static bool icmp_new(struct nf_conn *ct, const struct sk_buff *skb, - unsigned int dataoff) -{ - static const u_int8_t valid_new[] = { - [ICMP_ECHO] = 1, - [ICMP_TIMESTAMP] = 1, - [ICMP_INFO_REQUEST] = 1, - [ICMP_ADDRESS] = 1 - }; - - if (ct->tuplehash[0].tuple.dst.u.icmp.type >= sizeof(valid_new) || - !valid_new[ct->tuplehash[0].tuple.dst.u.icmp.type]) { - /* Can't create a new ICMP `conn' with this. */ - pr_debug("icmp: can't create new conn with type %u\n", - ct->tuplehash[0].tuple.dst.u.icmp.type); - nf_ct_dump_tuple_ip(&ct->tuplehash[0].tuple); - return false; - } - return true; -} - -/* Returns conntrack if it dealt with ICMP, and filled in skb fields */ -static int -icmp_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, - unsigned int hooknum) -{ - struct nf_conntrack_tuple innertuple, origtuple; - const struct nf_conntrack_l4proto *innerproto; - const struct nf_conntrack_tuple_hash *h; - const struct nf_conntrack_zone *zone; - enum ip_conntrack_info ctinfo; - struct nf_conntrack_zone tmp; - - WARN_ON(skb_nfct(skb)); - zone = nf_ct_zone_tmpl(tmpl, skb, &tmp); - - /* Are they talking about one of our connections? */ - if (!nf_ct_get_tuplepr(skb, - skb_network_offset(skb) + ip_hdrlen(skb) - + sizeof(struct icmphdr), - PF_INET, net, &origtuple)) { - pr_debug("icmp_error_message: failed to get tuple\n"); - return -NF_ACCEPT; - } - - /* rcu_read_lock()ed by nf_hook_thresh */ - innerproto = __nf_ct_l4proto_find(PF_INET, origtuple.dst.protonum); - - /* Ordinarily, we'd expect the inverted tupleproto, but it's - been preserved inside the ICMP. */ - if (!nf_ct_invert_tuple(&innertuple, &origtuple, innerproto)) { - pr_debug("icmp_error_message: no match\n"); - return -NF_ACCEPT; - } - - ctinfo = IP_CT_RELATED; - - h = nf_conntrack_find_get(net, zone, &innertuple); - if (!h) { - pr_debug("icmp_error_message: no match\n"); - return -NF_ACCEPT; - } - - if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY) - ctinfo += IP_CT_IS_REPLY; - - /* Update skb to refer to this connection */ - nf_ct_set(skb, nf_ct_tuplehash_to_ctrack(h), ctinfo); - return NF_ACCEPT; -} - -static void icmp_error_log(const struct sk_buff *skb, struct net *net, - u8 pf, const char *msg) -{ - nf_l4proto_log_invalid(skb, net, pf, IPPROTO_ICMP, "%s", msg); -} - -/* Small and modified version of icmp_rcv */ -static int -icmp_error(struct net *net, struct nf_conn *tmpl, - struct sk_buff *skb, unsigned int dataoff, - u8 pf, unsigned int hooknum) -{ - const struct icmphdr *icmph; - struct icmphdr _ih; - - /* Not enough header? */ - icmph = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_ih), &_ih); - if (icmph == NULL) { - icmp_error_log(skb, net, pf, "short packet"); - return -NF_ACCEPT; - } - - /* See ip_conntrack_proto_tcp.c */ - if (net->ct.sysctl_checksum && hooknum == NF_INET_PRE_ROUTING && - nf_ip_checksum(skb, hooknum, dataoff, 0)) { - icmp_error_log(skb, net, pf, "bad hw icmp checksum"); - return -NF_ACCEPT; - } - - /* - * 18 is the highest 'known' ICMP type. Anything else is a mystery - * - * RFC 1122: 3.2.2 Unknown ICMP messages types MUST be silently - * discarded. - */ - if (icmph->type > NR_ICMP_TYPES) { - icmp_error_log(skb, net, pf, "invalid icmp type"); - return -NF_ACCEPT; - } - - /* Need to track icmp error message? */ - if (icmph->type != ICMP_DEST_UNREACH && - icmph->type != ICMP_SOURCE_QUENCH && - icmph->type != ICMP_TIME_EXCEEDED && - icmph->type != ICMP_PARAMETERPROB && - icmph->type != ICMP_REDIRECT) - return NF_ACCEPT; - - return icmp_error_message(net, tmpl, skb, hooknum); -} - -#if IS_ENABLED(CONFIG_NF_CT_NETLINK) - -#include -#include - -static int icmp_tuple_to_nlattr(struct sk_buff *skb, - const struct nf_conntrack_tuple *t) -{ - if (nla_put_be16(skb, CTA_PROTO_ICMP_ID, t->src.u.icmp.id) || - nla_put_u8(skb, CTA_PROTO_ICMP_TYPE, t->dst.u.icmp.type) || - nla_put_u8(skb, CTA_PROTO_ICMP_CODE, t->dst.u.icmp.code)) - goto nla_put_failure; - return 0; - -nla_put_failure: - return -1; -} - -static const struct nla_policy icmp_nla_policy[CTA_PROTO_MAX+1] = { - [CTA_PROTO_ICMP_TYPE] = { .type = NLA_U8 }, - [CTA_PROTO_ICMP_CODE] = { .type = NLA_U8 }, - [CTA_PROTO_ICMP_ID] = { .type = NLA_U16 }, -}; - -static int icmp_nlattr_to_tuple(struct nlattr *tb[], - struct nf_conntrack_tuple *tuple) -{ - if (!tb[CTA_PROTO_ICMP_TYPE] || - !tb[CTA_PROTO_ICMP_CODE] || - !tb[CTA_PROTO_ICMP_ID]) - return -EINVAL; - - tuple->dst.u.icmp.type = nla_get_u8(tb[CTA_PROTO_ICMP_TYPE]); - tuple->dst.u.icmp.code = nla_get_u8(tb[CTA_PROTO_ICMP_CODE]); - tuple->src.u.icmp.id = nla_get_be16(tb[CTA_PROTO_ICMP_ID]); - - if (tuple->dst.u.icmp.type >= sizeof(invmap) || - !invmap[tuple->dst.u.icmp.type]) - return -EINVAL; - - return 0; -} - -static unsigned int icmp_nlattr_tuple_size(void) -{ - static unsigned int size __read_mostly; - - if (!size) - size = nla_policy_len(icmp_nla_policy, CTA_PROTO_MAX + 1); - - return size; -} -#endif - -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) - -#include -#include - -static int icmp_timeout_nlattr_to_obj(struct nlattr *tb[], - struct net *net, void *data) -{ - unsigned int *timeout = data; - struct nf_icmp_net *in = icmp_pernet(net); - - if (tb[CTA_TIMEOUT_ICMP_TIMEOUT]) { - if (!timeout) - timeout = &in->timeout; - *timeout = - ntohl(nla_get_be32(tb[CTA_TIMEOUT_ICMP_TIMEOUT])) * HZ; - } else if (timeout) { - /* Set default ICMP timeout. */ - *timeout = in->timeout; - } - return 0; -} - -static int -icmp_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) -{ - const unsigned int *timeout = data; - - if (nla_put_be32(skb, CTA_TIMEOUT_ICMP_TIMEOUT, htonl(*timeout / HZ))) - goto nla_put_failure; - return 0; - -nla_put_failure: - return -ENOSPC; -} - -static const struct nla_policy -icmp_timeout_nla_policy[CTA_TIMEOUT_ICMP_MAX+1] = { - [CTA_TIMEOUT_ICMP_TIMEOUT] = { .type = NLA_U32 }, -}; -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ - -#ifdef CONFIG_SYSCTL -static struct ctl_table icmp_sysctl_table[] = { - { - .procname = "nf_conntrack_icmp_timeout", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { } -}; -#endif /* CONFIG_SYSCTL */ - -static int icmp_kmemdup_sysctl_table(struct nf_proto_net *pn, - struct nf_icmp_net *in) -{ -#ifdef CONFIG_SYSCTL - pn->ctl_table = kmemdup(icmp_sysctl_table, - sizeof(icmp_sysctl_table), - GFP_KERNEL); - if (!pn->ctl_table) - return -ENOMEM; - - pn->ctl_table[0].data = &in->timeout; -#endif - return 0; -} - -static int icmp_init_net(struct net *net, u_int16_t proto) -{ - struct nf_icmp_net *in = icmp_pernet(net); - struct nf_proto_net *pn = &in->pn; - - in->timeout = nf_ct_icmp_timeout; - - return icmp_kmemdup_sysctl_table(pn, in); -} - -static struct nf_proto_net *icmp_get_net_proto(struct net *net) -{ - return &net->ct.nf_ct_proto.icmp.pn; -} - -const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp = -{ - .l3proto = PF_INET, - .l4proto = IPPROTO_ICMP, - .pkt_to_tuple = icmp_pkt_to_tuple, - .invert_tuple = icmp_invert_tuple, - .packet = icmp_packet, - .new = icmp_new, - .error = icmp_error, - .destroy = NULL, - .me = NULL, -#if IS_ENABLED(CONFIG_NF_CT_NETLINK) - .tuple_to_nlattr = icmp_tuple_to_nlattr, - .nlattr_tuple_size = icmp_nlattr_tuple_size, - .nlattr_to_tuple = icmp_nlattr_to_tuple, - .nla_policy = icmp_nla_policy, -#endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) - .ctnl_timeout = { - .nlattr_to_obj = icmp_timeout_nlattr_to_obj, - .obj_to_nlattr = icmp_timeout_obj_to_nlattr, - .nlattr_max = CTA_TIMEOUT_ICMP_MAX, - .obj_size = sizeof(unsigned int), - .nla_policy = icmp_timeout_nla_policy, - }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ - .init_net = icmp_init_net, - .get_net_proto = icmp_get_net_proto, -}; diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index 37b14dc9d863..339d0762b027 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -5,26 +5,6 @@ menu "IPv6: Netfilter Configuration" depends on INET && IPV6 && NETFILTER -config NF_DEFRAG_IPV6 - tristate - default n - -config NF_CONNTRACK_IPV6 - tristate "IPv6 connection tracking support" - depends on INET && IPV6 && NF_CONNTRACK - default m if NETFILTER_ADVANCED=n - select NF_DEFRAG_IPV6 - ---help--- - Connection tracking keeps a record of what packets have passed - through your machine, in order to figure out how they are related - into connections. - - This is IPv6 support on Layer 3 independent connection tracking. - Layer 3 independent connection tracking is experimental scheme - which generalize ip_conntrack to support other layer 3 protocols. - - To compile it as a module, choose M here. If unsure, say N. - config NF_SOCKET_IPV6 tristate "IPv6 socket lookup support" help @@ -128,7 +108,7 @@ config NF_LOG_IPV6 config NF_NAT_IPV6 tristate "IPv6 NAT" - depends on NF_CONNTRACK_IPV6 + depends on NF_CONNTRACK depends on NETFILTER_ADVANCED select NF_NAT help @@ -328,7 +308,7 @@ config IP6_NF_SECURITY config IP6_NF_NAT tristate "ip6tables NAT support" - depends on NF_CONNTRACK_IPV6 + depends on NF_CONNTRACK depends on NETFILTER_ADVANCED select NF_NAT select NF_NAT_IPV6 @@ -365,6 +345,7 @@ config IP6_NF_TARGET_NPT endif # IP6_NF_NAT endif # IP6_NF_IPTABLES - endmenu +config NF_DEFRAG_IPV6 + tristate diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile index 10a5a1c87320..200c0c235565 100644 --- a/net/ipv6/netfilter/Makefile +++ b/net/ipv6/netfilter/Makefile @@ -11,12 +11,6 @@ obj-$(CONFIG_IP6_NF_RAW) += ip6table_raw.o obj-$(CONFIG_IP6_NF_SECURITY) += ip6table_security.o obj-$(CONFIG_IP6_NF_NAT) += ip6table_nat.o -# objects for l3 independent conntrack -nf_conntrack_ipv6-y := nf_conntrack_l3proto_ipv6.o nf_conntrack_proto_icmpv6.o - -# l3 independent conntrack -obj-$(CONFIG_NF_CONNTRACK_IPV6) += nf_conntrack_ipv6.o - nf_nat_ipv6-y := nf_nat_l3proto_ipv6.o nf_nat_proto_icmpv6.o nf_nat_ipv6-$(CONFIG_NF_NAT_MASQUERADE_IPV6) += nf_nat_masquerade_ipv6.o obj-$(CONFIG_NF_NAT_IPV6) += nf_nat_ipv6.o diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c deleted file mode 100644 index 37ab25645cf2..000000000000 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ /dev/null @@ -1,355 +0,0 @@ -/* - * Copyright (C)2004 USAGI/WIDE Project - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * Author: - * Yasuyuki Kozakai @USAGI - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -static int conntrack6_net_id; -static DEFINE_MUTEX(register_ipv6_hooks); - -struct conntrack6_net { - unsigned int users; -}; - -static unsigned int ipv6_helper(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - struct nf_conn *ct; - const struct nf_conn_help *help; - const struct nf_conntrack_helper *helper; - enum ip_conntrack_info ctinfo; - __be16 frag_off; - int protoff; - u8 nexthdr; - - /* This is where we call the helper: as the packet goes out. */ - ct = nf_ct_get(skb, &ctinfo); - if (!ct || ctinfo == IP_CT_RELATED_REPLY) - return NF_ACCEPT; - - help = nfct_help(ct); - if (!help) - return NF_ACCEPT; - /* rcu_read_lock()ed by nf_hook_thresh */ - helper = rcu_dereference(help->helper); - if (!helper) - return NF_ACCEPT; - - nexthdr = ipv6_hdr(skb)->nexthdr; - protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, - &frag_off); - if (protoff < 0 || (frag_off & htons(~0x7)) != 0) { - pr_debug("proto header not found\n"); - return NF_ACCEPT; - } - - return helper->help(skb, protoff, ct, ctinfo); -} - -static unsigned int ipv6_confirm(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - struct nf_conn *ct; - enum ip_conntrack_info ctinfo; - unsigned char pnum = ipv6_hdr(skb)->nexthdr; - int protoff; - __be16 frag_off; - - ct = nf_ct_get(skb, &ctinfo); - if (!ct || ctinfo == IP_CT_RELATED_REPLY) - goto out; - - protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &pnum, - &frag_off); - if (protoff < 0 || (frag_off & htons(~0x7)) != 0) { - pr_debug("proto header not found\n"); - goto out; - } - - /* adjust seqs for loopback traffic only in outgoing direction */ - if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) && - !nf_is_loopback_packet(skb)) { - if (!nf_ct_seq_adjust(skb, ct, ctinfo, protoff)) { - NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop); - return NF_DROP; - } - } -out: - /* We've seen it coming out the other side: confirm it */ - return nf_conntrack_confirm(skb); -} - -static unsigned int ipv6_conntrack_in(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return nf_conntrack_in(state->net, PF_INET6, state->hook, skb); -} - -static unsigned int ipv6_conntrack_local(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return nf_conntrack_in(state->net, PF_INET6, state->hook, skb); -} - -static const struct nf_hook_ops ipv6_conntrack_ops[] = { - { - .hook = ipv6_conntrack_in, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_PRE_ROUTING, - .priority = NF_IP6_PRI_CONNTRACK, - }, - { - .hook = ipv6_conntrack_local, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_LOCAL_OUT, - .priority = NF_IP6_PRI_CONNTRACK, - }, - { - .hook = ipv6_helper, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_POST_ROUTING, - .priority = NF_IP6_PRI_CONNTRACK_HELPER, - }, - { - .hook = ipv6_confirm, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_POST_ROUTING, - .priority = NF_IP6_PRI_LAST, - }, - { - .hook = ipv6_helper, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_LOCAL_IN, - .priority = NF_IP6_PRI_CONNTRACK_HELPER, - }, - { - .hook = ipv6_confirm, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_LOCAL_IN, - .priority = NF_IP6_PRI_LAST-1, - }, -}; - -static int -ipv6_getorigdst(struct sock *sk, int optval, void __user *user, int *len) -{ - struct nf_conntrack_tuple tuple = { .src.l3num = NFPROTO_IPV6 }; - const struct ipv6_pinfo *inet6 = inet6_sk(sk); - const struct inet_sock *inet = inet_sk(sk); - const struct nf_conntrack_tuple_hash *h; - struct sockaddr_in6 sin6; - struct nf_conn *ct; - __be32 flow_label; - int bound_dev_if; - - lock_sock(sk); - tuple.src.u3.in6 = sk->sk_v6_rcv_saddr; - tuple.src.u.tcp.port = inet->inet_sport; - tuple.dst.u3.in6 = sk->sk_v6_daddr; - tuple.dst.u.tcp.port = inet->inet_dport; - tuple.dst.protonum = sk->sk_protocol; - bound_dev_if = sk->sk_bound_dev_if; - flow_label = inet6->flow_label; - release_sock(sk); - - if (tuple.dst.protonum != IPPROTO_TCP && - tuple.dst.protonum != IPPROTO_SCTP) - return -ENOPROTOOPT; - - if (*len < 0 || (unsigned int) *len < sizeof(sin6)) - return -EINVAL; - - h = nf_conntrack_find_get(sock_net(sk), &nf_ct_zone_dflt, &tuple); - if (!h) { - pr_debug("IP6T_SO_ORIGINAL_DST: Can't find %pI6c/%u-%pI6c/%u.\n", - &tuple.src.u3.ip6, ntohs(tuple.src.u.tcp.port), - &tuple.dst.u3.ip6, ntohs(tuple.dst.u.tcp.port)); - return -ENOENT; - } - - ct = nf_ct_tuplehash_to_ctrack(h); - - sin6.sin6_family = AF_INET6; - sin6.sin6_port = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u.tcp.port; - sin6.sin6_flowinfo = flow_label & IPV6_FLOWINFO_MASK; - memcpy(&sin6.sin6_addr, - &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.in6, - sizeof(sin6.sin6_addr)); - - nf_ct_put(ct); - sin6.sin6_scope_id = ipv6_iface_scope_id(&sin6.sin6_addr, bound_dev_if); - return copy_to_user(user, &sin6, sizeof(sin6)) ? -EFAULT : 0; -} - -static int ipv6_hooks_register(struct net *net) -{ - struct conntrack6_net *cnet = net_generic(net, conntrack6_net_id); - int err = 0; - - mutex_lock(®ister_ipv6_hooks); - cnet->users++; - if (cnet->users > 1) - goto out_unlock; - - err = nf_defrag_ipv6_enable(net); - if (err < 0) { - cnet->users = 0; - goto out_unlock; - } - - err = nf_register_net_hooks(net, ipv6_conntrack_ops, - ARRAY_SIZE(ipv6_conntrack_ops)); - if (err) - cnet->users = 0; - out_unlock: - mutex_unlock(®ister_ipv6_hooks); - return err; -} - -static void ipv6_hooks_unregister(struct net *net) -{ - struct conntrack6_net *cnet = net_generic(net, conntrack6_net_id); - - mutex_lock(®ister_ipv6_hooks); - if (cnet->users && (--cnet->users == 0)) - nf_unregister_net_hooks(net, ipv6_conntrack_ops, - ARRAY_SIZE(ipv6_conntrack_ops)); - mutex_unlock(®ister_ipv6_hooks); -} - -const struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6 = { - .l3proto = PF_INET6, - .net_ns_get = ipv6_hooks_register, - .net_ns_put = ipv6_hooks_unregister, - .me = THIS_MODULE, -}; - -MODULE_ALIAS("nf_conntrack-" __stringify(AF_INET6)); -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Yasuyuki KOZAKAI @USAGI "); - -static struct nf_sockopt_ops so_getorigdst6 = { - .pf = NFPROTO_IPV6, - .get_optmin = IP6T_SO_ORIGINAL_DST, - .get_optmax = IP6T_SO_ORIGINAL_DST + 1, - .get = ipv6_getorigdst, - .owner = THIS_MODULE, -}; - -static const struct nf_conntrack_l4proto * const builtin_l4proto6[] = { - &nf_conntrack_l4proto_tcp6, - &nf_conntrack_l4proto_udp6, - &nf_conntrack_l4proto_icmpv6, -#ifdef CONFIG_NF_CT_PROTO_DCCP - &nf_conntrack_l4proto_dccp6, -#endif -#ifdef CONFIG_NF_CT_PROTO_SCTP - &nf_conntrack_l4proto_sctp6, -#endif -#ifdef CONFIG_NF_CT_PROTO_UDPLITE - &nf_conntrack_l4proto_udplite6, -#endif -}; - -static int ipv6_net_init(struct net *net) -{ - return nf_ct_l4proto_pernet_register(net, builtin_l4proto6, - ARRAY_SIZE(builtin_l4proto6)); -} - -static void ipv6_net_exit(struct net *net) -{ - nf_ct_l4proto_pernet_unregister(net, builtin_l4proto6, - ARRAY_SIZE(builtin_l4proto6)); -} - -static struct pernet_operations ipv6_net_ops = { - .init = ipv6_net_init, - .exit = ipv6_net_exit, - .id = &conntrack6_net_id, - .size = sizeof(struct conntrack6_net), -}; - -static int __init nf_conntrack_l3proto_ipv6_init(void) -{ - int ret = 0; - - need_conntrack(); - - ret = nf_register_sockopt(&so_getorigdst6); - if (ret < 0) { - pr_err("Unable to register netfilter socket option\n"); - return ret; - } - - ret = register_pernet_subsys(&ipv6_net_ops); - if (ret < 0) - goto cleanup_sockopt; - - ret = nf_ct_l4proto_register(builtin_l4proto6, - ARRAY_SIZE(builtin_l4proto6)); - if (ret < 0) - goto cleanup_pernet; - - ret = nf_ct_l3proto_register(&nf_conntrack_l3proto_ipv6); - if (ret < 0) { - pr_err("nf_conntrack_ipv6: can't register ipv6 proto.\n"); - goto cleanup_l4proto; - } - return ret; -cleanup_l4proto: - nf_ct_l4proto_unregister(builtin_l4proto6, - ARRAY_SIZE(builtin_l4proto6)); - cleanup_pernet: - unregister_pernet_subsys(&ipv6_net_ops); - cleanup_sockopt: - nf_unregister_sockopt(&so_getorigdst6); - return ret; -} - -static void __exit nf_conntrack_l3proto_ipv6_fini(void) -{ - synchronize_net(); - nf_ct_l3proto_unregister(&nf_conntrack_l3proto_ipv6); - nf_ct_l4proto_unregister(builtin_l4proto6, - ARRAY_SIZE(builtin_l4proto6)); - unregister_pernet_subsys(&ipv6_net_ops); - nf_unregister_sockopt(&so_getorigdst6); -} - -module_init(nf_conntrack_l3proto_ipv6_init); -module_exit(nf_conntrack_l3proto_ipv6_fini); diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c deleted file mode 100644 index bed07b998a10..000000000000 --- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c +++ /dev/null @@ -1,387 +0,0 @@ -/* - * Copyright (C)2003,2004 USAGI/WIDE Project - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * Author: - * Yasuyuki Kozakai @USAGI - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -static const unsigned int nf_ct_icmpv6_timeout = 30*HZ; - -static inline struct nf_icmp_net *icmpv6_pernet(struct net *net) -{ - return &net->ct.nf_ct_proto.icmpv6; -} - -static bool icmpv6_pkt_to_tuple(const struct sk_buff *skb, - unsigned int dataoff, - struct net *net, - struct nf_conntrack_tuple *tuple) -{ - const struct icmp6hdr *hp; - struct icmp6hdr _hdr; - - hp = skb_header_pointer(skb, dataoff, sizeof(_hdr), &_hdr); - if (hp == NULL) - return false; - tuple->dst.u.icmp.type = hp->icmp6_type; - tuple->src.u.icmp.id = hp->icmp6_identifier; - tuple->dst.u.icmp.code = hp->icmp6_code; - - return true; -} - -/* Add 1; spaces filled with 0. */ -static const u_int8_t invmap[] = { - [ICMPV6_ECHO_REQUEST - 128] = ICMPV6_ECHO_REPLY + 1, - [ICMPV6_ECHO_REPLY - 128] = ICMPV6_ECHO_REQUEST + 1, - [ICMPV6_NI_QUERY - 128] = ICMPV6_NI_REPLY + 1, - [ICMPV6_NI_REPLY - 128] = ICMPV6_NI_QUERY + 1 -}; - -static const u_int8_t noct_valid_new[] = { - [ICMPV6_MGM_QUERY - 130] = 1, - [ICMPV6_MGM_REPORT - 130] = 1, - [ICMPV6_MGM_REDUCTION - 130] = 1, - [NDISC_ROUTER_SOLICITATION - 130] = 1, - [NDISC_ROUTER_ADVERTISEMENT - 130] = 1, - [NDISC_NEIGHBOUR_SOLICITATION - 130] = 1, - [NDISC_NEIGHBOUR_ADVERTISEMENT - 130] = 1, - [ICMPV6_MLD2_REPORT - 130] = 1 -}; - -static bool icmpv6_invert_tuple(struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_tuple *orig) -{ - int type = orig->dst.u.icmp.type - 128; - if (type < 0 || type >= sizeof(invmap) || !invmap[type]) - return false; - - tuple->src.u.icmp.id = orig->src.u.icmp.id; - tuple->dst.u.icmp.type = invmap[type] - 1; - tuple->dst.u.icmp.code = orig->dst.u.icmp.code; - return true; -} - -static unsigned int *icmpv6_get_timeouts(struct net *net) -{ - return &icmpv6_pernet(net)->timeout; -} - -/* Returns verdict for packet, or -1 for invalid. */ -static int icmpv6_packet(struct nf_conn *ct, - const struct sk_buff *skb, - unsigned int dataoff, - enum ip_conntrack_info ctinfo) -{ - unsigned int *timeout = nf_ct_timeout_lookup(ct); - - if (!timeout) - timeout = icmpv6_get_timeouts(nf_ct_net(ct)); - - /* Do not immediately delete the connection after the first - successful reply to avoid excessive conntrackd traffic - and also to handle correctly ICMP echo reply duplicates. */ - nf_ct_refresh_acct(ct, ctinfo, skb, *timeout); - - return NF_ACCEPT; -} - -/* Called when a new connection for this protocol found. */ -static bool icmpv6_new(struct nf_conn *ct, const struct sk_buff *skb, - unsigned int dataoff) -{ - static const u_int8_t valid_new[] = { - [ICMPV6_ECHO_REQUEST - 128] = 1, - [ICMPV6_NI_QUERY - 128] = 1 - }; - int type = ct->tuplehash[0].tuple.dst.u.icmp.type - 128; - - if (type < 0 || type >= sizeof(valid_new) || !valid_new[type]) { - /* Can't create a new ICMPv6 `conn' with this. */ - pr_debug("icmpv6: can't create new conn with type %u\n", - type + 128); - nf_ct_dump_tuple_ipv6(&ct->tuplehash[0].tuple); - return false; - } - return true; -} - -static int -icmpv6_error_message(struct net *net, struct nf_conn *tmpl, - struct sk_buff *skb, - unsigned int icmp6off) -{ - struct nf_conntrack_tuple intuple, origtuple; - const struct nf_conntrack_tuple_hash *h; - const struct nf_conntrack_l4proto *inproto; - enum ip_conntrack_info ctinfo; - struct nf_conntrack_zone tmp; - - WARN_ON(skb_nfct(skb)); - - /* Are they talking about one of our connections? */ - if (!nf_ct_get_tuplepr(skb, - skb_network_offset(skb) - + sizeof(struct ipv6hdr) - + sizeof(struct icmp6hdr), - PF_INET6, net, &origtuple)) { - pr_debug("icmpv6_error: Can't get tuple\n"); - return -NF_ACCEPT; - } - - /* rcu_read_lock()ed by nf_hook_thresh */ - inproto = __nf_ct_l4proto_find(PF_INET6, origtuple.dst.protonum); - - /* Ordinarily, we'd expect the inverted tupleproto, but it's - been preserved inside the ICMP. */ - if (!nf_ct_invert_tuple(&intuple, &origtuple, inproto)) { - pr_debug("icmpv6_error: Can't invert tuple\n"); - return -NF_ACCEPT; - } - - ctinfo = IP_CT_RELATED; - - h = nf_conntrack_find_get(net, nf_ct_zone_tmpl(tmpl, skb, &tmp), - &intuple); - if (!h) { - pr_debug("icmpv6_error: no match\n"); - return -NF_ACCEPT; - } else { - if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY) - ctinfo += IP_CT_IS_REPLY; - } - - /* Update skb to refer to this connection */ - nf_ct_set(skb, nf_ct_tuplehash_to_ctrack(h), ctinfo); - return NF_ACCEPT; -} - -static void icmpv6_error_log(const struct sk_buff *skb, struct net *net, - u8 pf, const char *msg) -{ - nf_l4proto_log_invalid(skb, net, pf, IPPROTO_ICMPV6, "%s", msg); -} - -static int -icmpv6_error(struct net *net, struct nf_conn *tmpl, - struct sk_buff *skb, unsigned int dataoff, - u8 pf, unsigned int hooknum) -{ - const struct icmp6hdr *icmp6h; - struct icmp6hdr _ih; - int type; - - icmp6h = skb_header_pointer(skb, dataoff, sizeof(_ih), &_ih); - if (icmp6h == NULL) { - icmpv6_error_log(skb, net, pf, "short packet"); - return -NF_ACCEPT; - } - - if (net->ct.sysctl_checksum && hooknum == NF_INET_PRE_ROUTING && - nf_ip6_checksum(skb, hooknum, dataoff, IPPROTO_ICMPV6)) { - icmpv6_error_log(skb, net, pf, "ICMPv6 checksum failed"); - return -NF_ACCEPT; - } - - type = icmp6h->icmp6_type - 130; - if (type >= 0 && type < sizeof(noct_valid_new) && - noct_valid_new[type]) { - nf_ct_set(skb, NULL, IP_CT_UNTRACKED); - return NF_ACCEPT; - } - - /* is not error message ? */ - if (icmp6h->icmp6_type >= 128) - return NF_ACCEPT; - - return icmpv6_error_message(net, tmpl, skb, dataoff); -} - -#if IS_ENABLED(CONFIG_NF_CT_NETLINK) - -#include -#include -static int icmpv6_tuple_to_nlattr(struct sk_buff *skb, - const struct nf_conntrack_tuple *t) -{ - if (nla_put_be16(skb, CTA_PROTO_ICMPV6_ID, t->src.u.icmp.id) || - nla_put_u8(skb, CTA_PROTO_ICMPV6_TYPE, t->dst.u.icmp.type) || - nla_put_u8(skb, CTA_PROTO_ICMPV6_CODE, t->dst.u.icmp.code)) - goto nla_put_failure; - return 0; - -nla_put_failure: - return -1; -} - -static const struct nla_policy icmpv6_nla_policy[CTA_PROTO_MAX+1] = { - [CTA_PROTO_ICMPV6_TYPE] = { .type = NLA_U8 }, - [CTA_PROTO_ICMPV6_CODE] = { .type = NLA_U8 }, - [CTA_PROTO_ICMPV6_ID] = { .type = NLA_U16 }, -}; - -static int icmpv6_nlattr_to_tuple(struct nlattr *tb[], - struct nf_conntrack_tuple *tuple) -{ - if (!tb[CTA_PROTO_ICMPV6_TYPE] || - !tb[CTA_PROTO_ICMPV6_CODE] || - !tb[CTA_PROTO_ICMPV6_ID]) - return -EINVAL; - - tuple->dst.u.icmp.type = nla_get_u8(tb[CTA_PROTO_ICMPV6_TYPE]); - tuple->dst.u.icmp.code = nla_get_u8(tb[CTA_PROTO_ICMPV6_CODE]); - tuple->src.u.icmp.id = nla_get_be16(tb[CTA_PROTO_ICMPV6_ID]); - - if (tuple->dst.u.icmp.type < 128 || - tuple->dst.u.icmp.type - 128 >= sizeof(invmap) || - !invmap[tuple->dst.u.icmp.type - 128]) - return -EINVAL; - - return 0; -} - -static unsigned int icmpv6_nlattr_tuple_size(void) -{ - static unsigned int size __read_mostly; - - if (!size) - size = nla_policy_len(icmpv6_nla_policy, CTA_PROTO_MAX + 1); - - return size; -} -#endif - -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) - -#include -#include - -static int icmpv6_timeout_nlattr_to_obj(struct nlattr *tb[], - struct net *net, void *data) -{ - unsigned int *timeout = data; - struct nf_icmp_net *in = icmpv6_pernet(net); - - if (!timeout) - timeout = icmpv6_get_timeouts(net); - if (tb[CTA_TIMEOUT_ICMPV6_TIMEOUT]) { - *timeout = - ntohl(nla_get_be32(tb[CTA_TIMEOUT_ICMPV6_TIMEOUT])) * HZ; - } else { - /* Set default ICMPv6 timeout. */ - *timeout = in->timeout; - } - return 0; -} - -static int -icmpv6_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) -{ - const unsigned int *timeout = data; - - if (nla_put_be32(skb, CTA_TIMEOUT_ICMPV6_TIMEOUT, htonl(*timeout / HZ))) - goto nla_put_failure; - return 0; - -nla_put_failure: - return -ENOSPC; -} - -static const struct nla_policy -icmpv6_timeout_nla_policy[CTA_TIMEOUT_ICMPV6_MAX+1] = { - [CTA_TIMEOUT_ICMPV6_TIMEOUT] = { .type = NLA_U32 }, -}; -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ - -#ifdef CONFIG_SYSCTL -static struct ctl_table icmpv6_sysctl_table[] = { - { - .procname = "nf_conntrack_icmpv6_timeout", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { } -}; -#endif /* CONFIG_SYSCTL */ - -static int icmpv6_kmemdup_sysctl_table(struct nf_proto_net *pn, - struct nf_icmp_net *in) -{ -#ifdef CONFIG_SYSCTL - pn->ctl_table = kmemdup(icmpv6_sysctl_table, - sizeof(icmpv6_sysctl_table), - GFP_KERNEL); - if (!pn->ctl_table) - return -ENOMEM; - - pn->ctl_table[0].data = &in->timeout; -#endif - return 0; -} - -static int icmpv6_init_net(struct net *net, u_int16_t proto) -{ - struct nf_icmp_net *in = icmpv6_pernet(net); - struct nf_proto_net *pn = &in->pn; - - in->timeout = nf_ct_icmpv6_timeout; - - return icmpv6_kmemdup_sysctl_table(pn, in); -} - -static struct nf_proto_net *icmpv6_get_net_proto(struct net *net) -{ - return &net->ct.nf_ct_proto.icmpv6.pn; -} - -const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 = -{ - .l3proto = PF_INET6, - .l4proto = IPPROTO_ICMPV6, - .pkt_to_tuple = icmpv6_pkt_to_tuple, - .invert_tuple = icmpv6_invert_tuple, - .packet = icmpv6_packet, - .new = icmpv6_new, - .error = icmpv6_error, -#if IS_ENABLED(CONFIG_NF_CT_NETLINK) - .tuple_to_nlattr = icmpv6_tuple_to_nlattr, - .nlattr_tuple_size = icmpv6_nlattr_tuple_size, - .nlattr_to_tuple = icmpv6_nlattr_to_tuple, - .nla_policy = icmpv6_nla_policy, -#endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) - .ctnl_timeout = { - .nlattr_to_obj = icmpv6_timeout_nlattr_to_obj, - .obj_to_nlattr = icmpv6_timeout_obj_to_nlattr, - .nlattr_max = CTA_TIMEOUT_ICMP_MAX, - .obj_size = sizeof(unsigned int), - .nla_policy = icmpv6_timeout_nla_policy, - }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ - .init_net = icmpv6_init_net, - .get_net_proto = icmpv6_get_net_proto, -}; diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 3ce657fbca67..9eab519b403a 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -49,6 +49,8 @@ config NETFILTER_NETLINK_LOG config NF_CONNTRACK tristate "Netfilter connection tracking support" default m if NETFILTER_ADVANCED=n + select NF_DEFRAG_IPV4 + select NF_DEFRAG_IPV6 if IPV6 != n help Connection tracking keeps a record of what packets have passed through your machine, in order to figure out how they are related diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index f132ea850778..53bd1ed1228a 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -1,7 +1,12 @@ # SPDX-License-Identifier: GPL-2.0 netfilter-objs := core.o nf_log.o nf_queue.o nf_sockopt.o utils.o -nf_conntrack-y := nf_conntrack_core.o nf_conntrack_standalone.o nf_conntrack_expect.o nf_conntrack_helper.o nf_conntrack_proto.o nf_conntrack_proto_generic.o nf_conntrack_proto_tcp.o nf_conntrack_proto_udp.o nf_conntrack_extend.o nf_conntrack_acct.o nf_conntrack_seqadj.o +nf_conntrack-y := nf_conntrack_core.o nf_conntrack_standalone.o nf_conntrack_expect.o nf_conntrack_helper.o \ + nf_conntrack_proto.o nf_conntrack_proto_generic.o nf_conntrack_proto_tcp.o nf_conntrack_proto_udp.o \ + nf_conntrack_proto_icmp.o \ + nf_conntrack_extend.o nf_conntrack_acct.o nf_conntrack_seqadj.o + +nf_conntrack-$(subst m,y,$(CONFIG_IPV6)) += nf_conntrack_proto_icmpv6.o nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMEOUT) += nf_conntrack_timeout.o nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMESTAMP) += nf_conntrack_timestamp.o nf_conntrack-$(CONFIG_NF_CONNTRACK_EVENTS) += nf_conntrack_ecache.o diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index c069f2faff4c..5123e91b1982 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -291,7 +291,6 @@ static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, u_int8_t *protonum) { int dataoff = -1; -#if IS_ENABLED(CONFIG_NF_CONNTRACK_IPV4) const struct iphdr *iph; struct iphdr _iph; @@ -314,15 +313,14 @@ static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, nhoff, iph->ihl << 2, skb->len); return -1; } -#endif return dataoff; } +#if IS_ENABLED(CONFIG_IPV6) static int ipv6_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, u8 *protonum) { int protoff = -1; -#if IS_ENABLED(CONFIG_NF_CONNTRACK_IPV6) unsigned int extoff = nhoff + sizeof(struct ipv6hdr); __be16 frag_off; u8 nexthdr; @@ -343,9 +341,9 @@ static int ipv6_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, } *protonum = nexthdr; -#endif return protoff; } +#endif static int get_l4proto(const struct sk_buff *skb, unsigned int nhoff, u8 pf, u8 *l4num) @@ -353,8 +351,10 @@ static int get_l4proto(const struct sk_buff *skb, switch (pf) { case NFPROTO_IPV4: return ipv4_get_l4proto(skb, nhoff, l4num); +#if IS_ENABLED(CONFIG_IPV6) case NFPROTO_IPV6: return ipv6_get_l4proto(skb, nhoff, l4num); +#endif default: *l4num = 0; break; @@ -2197,9 +2197,6 @@ int nf_conntrack_set_hashsize(const char *val, const struct kernel_param *kp) } EXPORT_SYMBOL_GPL(nf_conntrack_set_hashsize); -module_param_call(hashsize, nf_conntrack_set_hashsize, param_get_uint, - &nf_conntrack_htable_size, 0600); - static __always_inline unsigned int total_extension_size(void) { /* remember to add new extensions below */ diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index 39df72bb9d56..803607a90102 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -1,14 +1,4 @@ -/* L3/L4 protocol support for nf_conntrack. */ - -/* (C) 1999-2001 Paul `Rusty' Russell - * (C) 2002-2006 Netfilter Core Team - * (C) 2003,2004 USAGI/WIDE Project - * (C) 2006-2012 Patrick McHardy - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ +// SPDX-License-Identifier: GPL-2.0 #include #include @@ -24,22 +14,39 @@ #include #include -#include #include #include #include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include + +extern unsigned int nf_conntrack_net_id; + static struct nf_conntrack_l4proto __rcu **nf_ct_protos[NFPROTO_NUMPROTO] __read_mostly; -struct nf_conntrack_l3proto __rcu *nf_ct_l3protos[NFPROTO_NUMPROTO] __read_mostly; -EXPORT_SYMBOL_GPL(nf_ct_l3protos); static DEFINE_MUTEX(nf_ct_proto_mutex); -struct nf_conntrack_l3proto nf_conntrack_l3proto_generic __read_mostly = { - .l3proto = PF_UNSPEC, -}; -EXPORT_SYMBOL_GPL(nf_conntrack_l3proto_generic); - #ifdef CONFIG_SYSCTL static int nf_ct_register_sysctl(struct net *net, @@ -127,137 +134,6 @@ __nf_ct_l4proto_find(u_int16_t l3proto, u_int8_t l4proto) } EXPORT_SYMBOL_GPL(__nf_ct_l4proto_find); -/* this is guaranteed to always return a valid protocol helper, since - * it falls back to generic_protocol */ -const struct nf_conntrack_l3proto * -nf_ct_l3proto_find_get(u_int16_t l3proto) -{ - struct nf_conntrack_l3proto *p; - - rcu_read_lock(); - p = __nf_ct_l3proto_find(l3proto); - if (!try_module_get(p->me)) - p = &nf_conntrack_l3proto_generic; - rcu_read_unlock(); - - return p; -} -EXPORT_SYMBOL_GPL(nf_ct_l3proto_find_get); - -int -nf_ct_l3proto_try_module_get(unsigned short l3proto) -{ - const struct nf_conntrack_l3proto *p; - int ret; - -retry: p = nf_ct_l3proto_find_get(l3proto); - if (p == &nf_conntrack_l3proto_generic) { - ret = request_module("nf_conntrack-%d", l3proto); - if (!ret) - goto retry; - - return -EPROTOTYPE; - } - - return 0; -} -EXPORT_SYMBOL_GPL(nf_ct_l3proto_try_module_get); - -void nf_ct_l3proto_module_put(unsigned short l3proto) -{ - struct nf_conntrack_l3proto *p; - - /* rcu_read_lock not necessary since the caller holds a reference, but - * taken anyways to avoid lockdep warnings in __nf_ct_l3proto_find() - */ - rcu_read_lock(); - p = __nf_ct_l3proto_find(l3proto); - module_put(p->me); - rcu_read_unlock(); -} -EXPORT_SYMBOL_GPL(nf_ct_l3proto_module_put); - -static int nf_ct_netns_do_get(struct net *net, u8 nfproto) -{ - const struct nf_conntrack_l3proto *l3proto; - int ret; - - might_sleep(); - - ret = nf_ct_l3proto_try_module_get(nfproto); - if (ret < 0) - return ret; - - /* we already have a reference, can't fail */ - rcu_read_lock(); - l3proto = __nf_ct_l3proto_find(nfproto); - rcu_read_unlock(); - - if (!l3proto->net_ns_get) - return 0; - - ret = l3proto->net_ns_get(net); - if (ret < 0) - nf_ct_l3proto_module_put(nfproto); - - return ret; -} - -int nf_ct_netns_get(struct net *net, u8 nfproto) -{ - int err; - - if (nfproto == NFPROTO_INET) { - err = nf_ct_netns_do_get(net, NFPROTO_IPV4); - if (err < 0) - goto err1; - err = nf_ct_netns_do_get(net, NFPROTO_IPV6); - if (err < 0) - goto err2; - } else { - err = nf_ct_netns_do_get(net, nfproto); - if (err < 0) - goto err1; - } - return 0; - -err2: - nf_ct_netns_put(net, NFPROTO_IPV4); -err1: - return err; -} -EXPORT_SYMBOL_GPL(nf_ct_netns_get); - -static void nf_ct_netns_do_put(struct net *net, u8 nfproto) -{ - const struct nf_conntrack_l3proto *l3proto; - - might_sleep(); - - /* same as nf_conntrack_netns_get(), reference assumed */ - rcu_read_lock(); - l3proto = __nf_ct_l3proto_find(nfproto); - rcu_read_unlock(); - - if (WARN_ON(!l3proto)) - return; - - if (l3proto->net_ns_put) - l3proto->net_ns_put(net); - - nf_ct_l3proto_module_put(nfproto); -} - -void nf_ct_netns_put(struct net *net, uint8_t nfproto) -{ - if (nfproto == NFPROTO_INET) { - nf_ct_netns_do_put(net, NFPROTO_IPV4); - nf_ct_netns_do_put(net, NFPROTO_IPV6); - } else - nf_ct_netns_do_put(net, nfproto); -} -EXPORT_SYMBOL_GPL(nf_ct_netns_put); - const struct nf_conntrack_l4proto * nf_ct_l4proto_find_get(u_int16_t l3num, u_int8_t l4num) { @@ -279,11 +155,6 @@ void nf_ct_l4proto_put(const struct nf_conntrack_l4proto *p) } EXPORT_SYMBOL_GPL(nf_ct_l4proto_put); -static int kill_l3proto(struct nf_conn *i, void *data) -{ - return nf_ct_l3num(i) == ((const struct nf_conntrack_l3proto *)data)->l3proto; -} - static int kill_l4proto(struct nf_conn *i, void *data) { const struct nf_conntrack_l4proto *l4proto; @@ -292,49 +163,6 @@ static int kill_l4proto(struct nf_conn *i, void *data) nf_ct_l3num(i) == l4proto->l3proto; } -int nf_ct_l3proto_register(const struct nf_conntrack_l3proto *proto) -{ - int ret = 0; - struct nf_conntrack_l3proto *old; - - if (proto->l3proto >= NFPROTO_NUMPROTO) - return -EBUSY; - - mutex_lock(&nf_ct_proto_mutex); - old = rcu_dereference_protected(nf_ct_l3protos[proto->l3proto], - lockdep_is_held(&nf_ct_proto_mutex)); - if (old != &nf_conntrack_l3proto_generic) { - ret = -EBUSY; - goto out_unlock; - } - - rcu_assign_pointer(nf_ct_l3protos[proto->l3proto], proto); - -out_unlock: - mutex_unlock(&nf_ct_proto_mutex); - return ret; - -} -EXPORT_SYMBOL_GPL(nf_ct_l3proto_register); - -void nf_ct_l3proto_unregister(const struct nf_conntrack_l3proto *proto) -{ - BUG_ON(proto->l3proto >= NFPROTO_NUMPROTO); - - mutex_lock(&nf_ct_proto_mutex); - BUG_ON(rcu_dereference_protected(nf_ct_l3protos[proto->l3proto], - lockdep_is_held(&nf_ct_proto_mutex) - ) != proto); - rcu_assign_pointer(nf_ct_l3protos[proto->l3proto], - &nf_conntrack_l3proto_generic); - mutex_unlock(&nf_ct_proto_mutex); - - synchronize_rcu(); - /* Remove all contrack entries for this protocol */ - nf_ct_iterate_destroy(kill_l3proto, (void*)proto); -} -EXPORT_SYMBOL_GPL(nf_ct_l3proto_unregister); - static struct nf_proto_net *nf_ct_l4proto_net(struct net *net, const struct nf_conntrack_l4proto *l4proto) { @@ -501,8 +329,23 @@ void nf_ct_l4proto_pernet_unregister_one(struct net *net, } EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_unregister_one); -int nf_ct_l4proto_register(const struct nf_conntrack_l4proto * const l4proto[], - unsigned int num_proto) +static void +nf_ct_l4proto_unregister(const struct nf_conntrack_l4proto * const l4proto[], + unsigned int num_proto) +{ + mutex_lock(&nf_ct_proto_mutex); + while (num_proto-- != 0) + __nf_ct_l4proto_unregister_one(l4proto[num_proto]); + mutex_unlock(&nf_ct_proto_mutex); + + synchronize_net(); + /* Remove all contrack entries for this protocol */ + nf_ct_iterate_destroy(kill_l4proto, (void *)l4proto); +} + +static int +nf_ct_l4proto_register(const struct nf_conntrack_l4proto * const l4proto[], + unsigned int num_proto) { int ret = -EINVAL, ver; unsigned int i; @@ -520,7 +363,6 @@ int nf_ct_l4proto_register(const struct nf_conntrack_l4proto * const l4proto[], } return ret; } -EXPORT_SYMBOL_GPL(nf_ct_l4proto_register); int nf_ct_l4proto_pernet_register(struct net *net, const struct nf_conntrack_l4proto *const l4proto[], @@ -544,20 +386,6 @@ int nf_ct_l4proto_pernet_register(struct net *net, } EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_register); -void nf_ct_l4proto_unregister(const struct nf_conntrack_l4proto * const l4proto[], - unsigned int num_proto) -{ - mutex_lock(&nf_ct_proto_mutex); - while (num_proto-- != 0) - __nf_ct_l4proto_unregister_one(l4proto[num_proto]); - mutex_unlock(&nf_ct_proto_mutex); - - synchronize_net(); - /* Remove all contrack entries for this protocol */ - nf_ct_iterate_destroy(kill_l4proto, (void *)l4proto); -} -EXPORT_SYMBOL_GPL(nf_ct_l4proto_unregister); - void nf_ct_l4proto_pernet_unregister(struct net *net, const struct nf_conntrack_l4proto *const l4proto[], unsigned int num_proto) @@ -567,6 +395,563 @@ void nf_ct_l4proto_pernet_unregister(struct net *net, } EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_unregister); +static unsigned int ipv4_helper(void *priv, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ + struct nf_conn *ct; + enum ip_conntrack_info ctinfo; + const struct nf_conn_help *help; + const struct nf_conntrack_helper *helper; + + /* This is where we call the helper: as the packet goes out. */ + ct = nf_ct_get(skb, &ctinfo); + if (!ct || ctinfo == IP_CT_RELATED_REPLY) + return NF_ACCEPT; + + help = nfct_help(ct); + if (!help) + return NF_ACCEPT; + + /* rcu_read_lock()ed by nf_hook_thresh */ + helper = rcu_dereference(help->helper); + if (!helper) + return NF_ACCEPT; + + return helper->help(skb, skb_network_offset(skb) + ip_hdrlen(skb), + ct, ctinfo); +} + +static unsigned int ipv4_confirm(void *priv, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ + struct nf_conn *ct; + enum ip_conntrack_info ctinfo; + + ct = nf_ct_get(skb, &ctinfo); + if (!ct || ctinfo == IP_CT_RELATED_REPLY) + goto out; + + /* adjust seqs for loopback traffic only in outgoing direction */ + if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) && + !nf_is_loopback_packet(skb)) { + if (!nf_ct_seq_adjust(skb, ct, ctinfo, ip_hdrlen(skb))) { + NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop); + return NF_DROP; + } + } +out: + /* We've seen it coming out the other side: confirm it */ + return nf_conntrack_confirm(skb); +} + +static unsigned int ipv4_conntrack_in(void *priv, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ + return nf_conntrack_in(state->net, PF_INET, state->hook, skb); +} + +static unsigned int ipv4_conntrack_local(void *priv, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ + if (ip_is_fragment(ip_hdr(skb))) { /* IP_NODEFRAG setsockopt set */ + enum ip_conntrack_info ctinfo; + struct nf_conn *tmpl; + + tmpl = nf_ct_get(skb, &ctinfo); + if (tmpl && nf_ct_is_template(tmpl)) { + /* when skipping ct, clear templates to avoid fooling + * later targets/matches + */ + skb->_nfct = 0; + nf_ct_put(tmpl); + } + return NF_ACCEPT; + } + + return nf_conntrack_in(state->net, PF_INET, state->hook, skb); +} + +/* Connection tracking may drop packets, but never alters them, so + * make it the first hook. + */ +static const struct nf_hook_ops ipv4_conntrack_ops[] = { + { + .hook = ipv4_conntrack_in, + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_PRE_ROUTING, + .priority = NF_IP_PRI_CONNTRACK, + }, + { + .hook = ipv4_conntrack_local, + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_LOCAL_OUT, + .priority = NF_IP_PRI_CONNTRACK, + }, + { + .hook = ipv4_helper, + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_POST_ROUTING, + .priority = NF_IP_PRI_CONNTRACK_HELPER, + }, + { + .hook = ipv4_confirm, + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_POST_ROUTING, + .priority = NF_IP_PRI_CONNTRACK_CONFIRM, + }, + { + .hook = ipv4_helper, + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_LOCAL_IN, + .priority = NF_IP_PRI_CONNTRACK_HELPER, + }, + { + .hook = ipv4_confirm, + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_LOCAL_IN, + .priority = NF_IP_PRI_CONNTRACK_CONFIRM, + }, +}; + +/* Fast function for those who don't want to parse /proc (and I don't + * blame them). + * Reversing the socket's dst/src point of view gives us the reply + * mapping. + */ +static int +getorigdst(struct sock *sk, int optval, void __user *user, int *len) +{ + const struct inet_sock *inet = inet_sk(sk); + const struct nf_conntrack_tuple_hash *h; + struct nf_conntrack_tuple tuple; + + memset(&tuple, 0, sizeof(tuple)); + + lock_sock(sk); + tuple.src.u3.ip = inet->inet_rcv_saddr; + tuple.src.u.tcp.port = inet->inet_sport; + tuple.dst.u3.ip = inet->inet_daddr; + tuple.dst.u.tcp.port = inet->inet_dport; + tuple.src.l3num = PF_INET; + tuple.dst.protonum = sk->sk_protocol; + release_sock(sk); + + /* We only do TCP and SCTP at the moment: is there a better way? */ + if (tuple.dst.protonum != IPPROTO_TCP && + tuple.dst.protonum != IPPROTO_SCTP) { + pr_debug("SO_ORIGINAL_DST: Not a TCP/SCTP socket\n"); + return -ENOPROTOOPT; + } + + if ((unsigned int)*len < sizeof(struct sockaddr_in)) { + pr_debug("SO_ORIGINAL_DST: len %d not %zu\n", + *len, sizeof(struct sockaddr_in)); + return -EINVAL; + } + + h = nf_conntrack_find_get(sock_net(sk), &nf_ct_zone_dflt, &tuple); + if (h) { + struct sockaddr_in sin; + struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h); + + sin.sin_family = AF_INET; + sin.sin_port = ct->tuplehash[IP_CT_DIR_ORIGINAL] + .tuple.dst.u.tcp.port; + sin.sin_addr.s_addr = ct->tuplehash[IP_CT_DIR_ORIGINAL] + .tuple.dst.u3.ip; + memset(sin.sin_zero, 0, sizeof(sin.sin_zero)); + + pr_debug("SO_ORIGINAL_DST: %pI4 %u\n", + &sin.sin_addr.s_addr, ntohs(sin.sin_port)); + nf_ct_put(ct); + if (copy_to_user(user, &sin, sizeof(sin)) != 0) + return -EFAULT; + else + return 0; + } + pr_debug("SO_ORIGINAL_DST: Can't find %pI4/%u-%pI4/%u.\n", + &tuple.src.u3.ip, ntohs(tuple.src.u.tcp.port), + &tuple.dst.u3.ip, ntohs(tuple.dst.u.tcp.port)); + return -ENOENT; +} + +static struct nf_sockopt_ops so_getorigdst = { + .pf = PF_INET, + .get_optmin = SO_ORIGINAL_DST, + .get_optmax = SO_ORIGINAL_DST + 1, + .get = getorigdst, + .owner = THIS_MODULE, +}; + +#if IS_ENABLED(CONFIG_IPV6) +static int +ipv6_getorigdst(struct sock *sk, int optval, void __user *user, int *len) +{ + struct nf_conntrack_tuple tuple = { .src.l3num = NFPROTO_IPV6 }; + const struct ipv6_pinfo *inet6 = inet6_sk(sk); + const struct inet_sock *inet = inet_sk(sk); + const struct nf_conntrack_tuple_hash *h; + struct sockaddr_in6 sin6; + struct nf_conn *ct; + __be32 flow_label; + int bound_dev_if; + + lock_sock(sk); + tuple.src.u3.in6 = sk->sk_v6_rcv_saddr; + tuple.src.u.tcp.port = inet->inet_sport; + tuple.dst.u3.in6 = sk->sk_v6_daddr; + tuple.dst.u.tcp.port = inet->inet_dport; + tuple.dst.protonum = sk->sk_protocol; + bound_dev_if = sk->sk_bound_dev_if; + flow_label = inet6->flow_label; + release_sock(sk); + + if (tuple.dst.protonum != IPPROTO_TCP && + tuple.dst.protonum != IPPROTO_SCTP) + return -ENOPROTOOPT; + + if (*len < 0 || (unsigned int)*len < sizeof(sin6)) + return -EINVAL; + + h = nf_conntrack_find_get(sock_net(sk), &nf_ct_zone_dflt, &tuple); + if (!h) { + pr_debug("IP6T_SO_ORIGINAL_DST: Can't find %pI6c/%u-%pI6c/%u.\n", + &tuple.src.u3.ip6, ntohs(tuple.src.u.tcp.port), + &tuple.dst.u3.ip6, ntohs(tuple.dst.u.tcp.port)); + return -ENOENT; + } + + ct = nf_ct_tuplehash_to_ctrack(h); + + sin6.sin6_family = AF_INET6; + sin6.sin6_port = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u.tcp.port; + sin6.sin6_flowinfo = flow_label & IPV6_FLOWINFO_MASK; + memcpy(&sin6.sin6_addr, + &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.in6, + sizeof(sin6.sin6_addr)); + + nf_ct_put(ct); + sin6.sin6_scope_id = ipv6_iface_scope_id(&sin6.sin6_addr, bound_dev_if); + return copy_to_user(user, &sin6, sizeof(sin6)) ? -EFAULT : 0; +} + +static struct nf_sockopt_ops so_getorigdst6 = { + .pf = NFPROTO_IPV6, + .get_optmin = IP6T_SO_ORIGINAL_DST, + .get_optmax = IP6T_SO_ORIGINAL_DST + 1, + .get = ipv6_getorigdst, + .owner = THIS_MODULE, +}; + +static unsigned int ipv6_confirm(void *priv, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ + struct nf_conn *ct; + enum ip_conntrack_info ctinfo; + unsigned char pnum = ipv6_hdr(skb)->nexthdr; + int protoff; + __be16 frag_off; + + ct = nf_ct_get(skb, &ctinfo); + if (!ct || ctinfo == IP_CT_RELATED_REPLY) + goto out; + + protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &pnum, + &frag_off); + if (protoff < 0 || (frag_off & htons(~0x7)) != 0) { + pr_debug("proto header not found\n"); + goto out; + } + + /* adjust seqs for loopback traffic only in outgoing direction */ + if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) && + !nf_is_loopback_packet(skb)) { + if (!nf_ct_seq_adjust(skb, ct, ctinfo, protoff)) { + NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop); + return NF_DROP; + } + } +out: + /* We've seen it coming out the other side: confirm it */ + return nf_conntrack_confirm(skb); +} + +static unsigned int ipv6_conntrack_in(void *priv, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ + return nf_conntrack_in(state->net, PF_INET6, state->hook, skb); +} + +static unsigned int ipv6_conntrack_local(void *priv, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ + return nf_conntrack_in(state->net, PF_INET6, state->hook, skb); +} + +static unsigned int ipv6_helper(void *priv, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ + struct nf_conn *ct; + const struct nf_conn_help *help; + const struct nf_conntrack_helper *helper; + enum ip_conntrack_info ctinfo; + __be16 frag_off; + int protoff; + u8 nexthdr; + + /* This is where we call the helper: as the packet goes out. */ + ct = nf_ct_get(skb, &ctinfo); + if (!ct || ctinfo == IP_CT_RELATED_REPLY) + return NF_ACCEPT; + + help = nfct_help(ct); + if (!help) + return NF_ACCEPT; + /* rcu_read_lock()ed by nf_hook_thresh */ + helper = rcu_dereference(help->helper); + if (!helper) + return NF_ACCEPT; + + nexthdr = ipv6_hdr(skb)->nexthdr; + protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, + &frag_off); + if (protoff < 0 || (frag_off & htons(~0x7)) != 0) { + pr_debug("proto header not found\n"); + return NF_ACCEPT; + } + + return helper->help(skb, protoff, ct, ctinfo); +} + +static const struct nf_hook_ops ipv6_conntrack_ops[] = { + { + .hook = ipv6_conntrack_in, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_PRE_ROUTING, + .priority = NF_IP6_PRI_CONNTRACK, + }, + { + .hook = ipv6_conntrack_local, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_LOCAL_OUT, + .priority = NF_IP6_PRI_CONNTRACK, + }, + { + .hook = ipv6_helper, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_POST_ROUTING, + .priority = NF_IP6_PRI_CONNTRACK_HELPER, + }, + { + .hook = ipv6_confirm, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_POST_ROUTING, + .priority = NF_IP6_PRI_LAST, + }, + { + .hook = ipv6_helper, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_LOCAL_IN, + .priority = NF_IP6_PRI_CONNTRACK_HELPER, + }, + { + .hook = ipv6_confirm, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_LOCAL_IN, + .priority = NF_IP6_PRI_LAST - 1, + }, +}; +#endif + +static int nf_ct_netns_do_get(struct net *net, u8 nfproto) +{ + struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + int err = 0; + + mutex_lock(&nf_ct_proto_mutex); + + switch (nfproto) { + case NFPROTO_IPV4: + cnet->users4++; + if (cnet->users4 > 1) + goto out_unlock; + err = nf_defrag_ipv4_enable(net); + if (err) { + cnet->users4 = 0; + goto out_unlock; + } + + err = nf_register_net_hooks(net, ipv4_conntrack_ops, + ARRAY_SIZE(ipv4_conntrack_ops)); + if (err) + cnet->users4 = 0; + break; +#if IS_ENABLED(CONFIG_IPV6) + case NFPROTO_IPV6: + cnet->users6++; + if (cnet->users6 > 1) + goto out_unlock; + err = nf_defrag_ipv6_enable(net); + if (err < 0) { + cnet->users6 = 0; + goto out_unlock; + } + + err = nf_register_net_hooks(net, ipv6_conntrack_ops, + ARRAY_SIZE(ipv6_conntrack_ops)); + if (err) + cnet->users6 = 0; + break; +#endif + default: + err = -EPROTO; + break; + } + out_unlock: + mutex_unlock(&nf_ct_proto_mutex); + return err; +} + +static void nf_ct_netns_do_put(struct net *net, u8 nfproto) +{ + struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + + mutex_lock(&nf_ct_proto_mutex); + switch (nfproto) { + case NFPROTO_IPV4: + if (cnet->users4 && (--cnet->users4 == 0)) + nf_unregister_net_hooks(net, ipv4_conntrack_ops, + ARRAY_SIZE(ipv4_conntrack_ops)); + break; +#if IS_ENABLED(CONFIG_IPV6) + case NFPROTO_IPV6: + if (cnet->users6 && (--cnet->users6 == 0)) + nf_unregister_net_hooks(net, ipv6_conntrack_ops, + ARRAY_SIZE(ipv6_conntrack_ops)); + break; +#endif + } + + mutex_unlock(&nf_ct_proto_mutex); +} + +int nf_ct_netns_get(struct net *net, u8 nfproto) +{ + int err; + + if (nfproto == NFPROTO_INET) { + err = nf_ct_netns_do_get(net, NFPROTO_IPV4); + if (err < 0) + goto err1; + err = nf_ct_netns_do_get(net, NFPROTO_IPV6); + if (err < 0) + goto err2; + } else { + err = nf_ct_netns_do_get(net, nfproto); + if (err < 0) + goto err1; + } + return 0; + +err2: + nf_ct_netns_put(net, NFPROTO_IPV4); +err1: + return err; +} +EXPORT_SYMBOL_GPL(nf_ct_netns_get); + +void nf_ct_netns_put(struct net *net, uint8_t nfproto) +{ + if (nfproto == NFPROTO_INET) { + nf_ct_netns_do_put(net, NFPROTO_IPV4); + nf_ct_netns_do_put(net, NFPROTO_IPV6); + } else { + nf_ct_netns_do_put(net, nfproto); + } +} +EXPORT_SYMBOL_GPL(nf_ct_netns_put); + +static const struct nf_conntrack_l4proto * const builtin_l4proto[] = { + &nf_conntrack_l4proto_tcp4, + &nf_conntrack_l4proto_udp4, + &nf_conntrack_l4proto_icmp, +#ifdef CONFIG_NF_CT_PROTO_DCCP + &nf_conntrack_l4proto_dccp4, +#endif +#ifdef CONFIG_NF_CT_PROTO_SCTP + &nf_conntrack_l4proto_sctp4, +#endif +#ifdef CONFIG_NF_CT_PROTO_UDPLITE + &nf_conntrack_l4proto_udplite4, +#endif +#if IS_ENABLED(CONFIG_IPV6) + &nf_conntrack_l4proto_tcp6, + &nf_conntrack_l4proto_udp6, + &nf_conntrack_l4proto_icmpv6, +#ifdef CONFIG_NF_CT_PROTO_DCCP + &nf_conntrack_l4proto_dccp6, +#endif +#ifdef CONFIG_NF_CT_PROTO_SCTP + &nf_conntrack_l4proto_sctp6, +#endif +#ifdef CONFIG_NF_CT_PROTO_UDPLITE + &nf_conntrack_l4proto_udplite6, +#endif +#endif /* CONFIG_IPV6 */ +}; + +int nf_conntrack_proto_init(void) +{ + int ret = 0; + + ret = nf_register_sockopt(&so_getorigdst); + if (ret < 0) + return ret; + +#if IS_ENABLED(CONFIG_IPV6) + ret = nf_register_sockopt(&so_getorigdst6); + if (ret < 0) + goto cleanup_sockopt; +#endif + ret = nf_ct_l4proto_register(builtin_l4proto, + ARRAY_SIZE(builtin_l4proto)); + if (ret < 0) + goto cleanup_sockopt2; + + return ret; +cleanup_sockopt2: + nf_unregister_sockopt(&so_getorigdst); +#if IS_ENABLED(CONFIG_IPV6) +cleanup_sockopt: + nf_unregister_sockopt(&so_getorigdst6); +#endif + return ret; +} + +void nf_conntrack_proto_fini(void) +{ + unsigned int i; + + nf_ct_l4proto_unregister(builtin_l4proto, + ARRAY_SIZE(builtin_l4proto)); + nf_unregister_sockopt(&so_getorigdst); +#if IS_ENABLED(CONFIG_IPV6) + nf_unregister_sockopt(&so_getorigdst6); +#endif + + /* free l3proto protocol tables */ + for (i = 0; i < ARRAY_SIZE(nf_ct_protos); i++) + kfree(nf_ct_protos[i]); +} + int nf_conntrack_proto_pernet_init(struct net *net) { int err; @@ -583,6 +968,14 @@ int nf_conntrack_proto_pernet_init(struct net *net) if (err < 0) return err; + err = nf_ct_l4proto_pernet_register(net, builtin_l4proto, + ARRAY_SIZE(builtin_l4proto)); + if (err < 0) { + nf_ct_l4proto_unregister_sysctl(net, pn, + &nf_conntrack_l4proto_generic); + return err; + } + pn->users++; return 0; } @@ -592,25 +985,19 @@ void nf_conntrack_proto_pernet_fini(struct net *net) struct nf_proto_net *pn = nf_ct_l4proto_net(net, &nf_conntrack_l4proto_generic); + nf_ct_l4proto_pernet_unregister(net, builtin_l4proto, + ARRAY_SIZE(builtin_l4proto)); pn->users--; nf_ct_l4proto_unregister_sysctl(net, pn, &nf_conntrack_l4proto_generic); } -int nf_conntrack_proto_init(void) -{ - unsigned int i; - for (i = 0; i < NFPROTO_NUMPROTO; i++) - rcu_assign_pointer(nf_ct_l3protos[i], - &nf_conntrack_l3proto_generic); - return 0; -} -void nf_conntrack_proto_fini(void) -{ - unsigned int i; - /* free l3proto protocol tables */ - for (i = 0; i < ARRAY_SIZE(nf_ct_protos); i++) - kfree(nf_ct_protos[i]); -} +module_param_call(hashsize, nf_conntrack_set_hashsize, param_get_uint, + &nf_conntrack_htable_size, 0600); + +MODULE_ALIAS("ip_conntrack"); +MODULE_ALIAS("nf_conntrack-" __stringify(AF_INET)); +MODULE_ALIAS("nf_conntrack-" __stringify(AF_INET6)); +MODULE_LICENSE("GPL"); diff --git a/net/netfilter/nf_conntrack_proto_icmp.c b/net/netfilter/nf_conntrack_proto_icmp.c new file mode 100644 index 000000000000..036670b38282 --- /dev/null +++ b/net/netfilter/nf_conntrack_proto_icmp.c @@ -0,0 +1,388 @@ +/* (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2004 Netfilter Core Team + * (C) 2006-2010 Patrick McHardy + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static const unsigned int nf_ct_icmp_timeout = 30*HZ; + +static inline struct nf_icmp_net *icmp_pernet(struct net *net) +{ + return &net->ct.nf_ct_proto.icmp; +} + +static bool icmp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, + struct net *net, struct nf_conntrack_tuple *tuple) +{ + const struct icmphdr *hp; + struct icmphdr _hdr; + + hp = skb_header_pointer(skb, dataoff, sizeof(_hdr), &_hdr); + if (hp == NULL) + return false; + + tuple->dst.u.icmp.type = hp->type; + tuple->src.u.icmp.id = hp->un.echo.id; + tuple->dst.u.icmp.code = hp->code; + + return true; +} + +/* Add 1; spaces filled with 0. */ +static const u_int8_t invmap[] = { + [ICMP_ECHO] = ICMP_ECHOREPLY + 1, + [ICMP_ECHOREPLY] = ICMP_ECHO + 1, + [ICMP_TIMESTAMP] = ICMP_TIMESTAMPREPLY + 1, + [ICMP_TIMESTAMPREPLY] = ICMP_TIMESTAMP + 1, + [ICMP_INFO_REQUEST] = ICMP_INFO_REPLY + 1, + [ICMP_INFO_REPLY] = ICMP_INFO_REQUEST + 1, + [ICMP_ADDRESS] = ICMP_ADDRESSREPLY + 1, + [ICMP_ADDRESSREPLY] = ICMP_ADDRESS + 1 +}; + +static bool icmp_invert_tuple(struct nf_conntrack_tuple *tuple, + const struct nf_conntrack_tuple *orig) +{ + if (orig->dst.u.icmp.type >= sizeof(invmap) || + !invmap[orig->dst.u.icmp.type]) + return false; + + tuple->src.u.icmp.id = orig->src.u.icmp.id; + tuple->dst.u.icmp.type = invmap[orig->dst.u.icmp.type] - 1; + tuple->dst.u.icmp.code = orig->dst.u.icmp.code; + return true; +} + +static unsigned int *icmp_get_timeouts(struct net *net) +{ + return &icmp_pernet(net)->timeout; +} + +/* Returns verdict for packet, or -1 for invalid. */ +static int icmp_packet(struct nf_conn *ct, + const struct sk_buff *skb, + unsigned int dataoff, + enum ip_conntrack_info ctinfo) +{ + /* Do not immediately delete the connection after the first + successful reply to avoid excessive conntrackd traffic + and also to handle correctly ICMP echo reply duplicates. */ + unsigned int *timeout = nf_ct_timeout_lookup(ct); + + if (!timeout) + timeout = icmp_get_timeouts(nf_ct_net(ct)); + + nf_ct_refresh_acct(ct, ctinfo, skb, *timeout); + + return NF_ACCEPT; +} + +/* Called when a new connection for this protocol found. */ +static bool icmp_new(struct nf_conn *ct, const struct sk_buff *skb, + unsigned int dataoff) +{ + static const u_int8_t valid_new[] = { + [ICMP_ECHO] = 1, + [ICMP_TIMESTAMP] = 1, + [ICMP_INFO_REQUEST] = 1, + [ICMP_ADDRESS] = 1 + }; + + if (ct->tuplehash[0].tuple.dst.u.icmp.type >= sizeof(valid_new) || + !valid_new[ct->tuplehash[0].tuple.dst.u.icmp.type]) { + /* Can't create a new ICMP `conn' with this. */ + pr_debug("icmp: can't create new conn with type %u\n", + ct->tuplehash[0].tuple.dst.u.icmp.type); + nf_ct_dump_tuple_ip(&ct->tuplehash[0].tuple); + return false; + } + return true; +} + +/* Returns conntrack if it dealt with ICMP, and filled in skb fields */ +static int +icmp_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, + unsigned int hooknum) +{ + struct nf_conntrack_tuple innertuple, origtuple; + const struct nf_conntrack_l4proto *innerproto; + const struct nf_conntrack_tuple_hash *h; + const struct nf_conntrack_zone *zone; + enum ip_conntrack_info ctinfo; + struct nf_conntrack_zone tmp; + + WARN_ON(skb_nfct(skb)); + zone = nf_ct_zone_tmpl(tmpl, skb, &tmp); + + /* Are they talking about one of our connections? */ + if (!nf_ct_get_tuplepr(skb, + skb_network_offset(skb) + ip_hdrlen(skb) + + sizeof(struct icmphdr), + PF_INET, net, &origtuple)) { + pr_debug("icmp_error_message: failed to get tuple\n"); + return -NF_ACCEPT; + } + + /* rcu_read_lock()ed by nf_hook_thresh */ + innerproto = __nf_ct_l4proto_find(PF_INET, origtuple.dst.protonum); + + /* Ordinarily, we'd expect the inverted tupleproto, but it's + been preserved inside the ICMP. */ + if (!nf_ct_invert_tuple(&innertuple, &origtuple, innerproto)) { + pr_debug("icmp_error_message: no match\n"); + return -NF_ACCEPT; + } + + ctinfo = IP_CT_RELATED; + + h = nf_conntrack_find_get(net, zone, &innertuple); + if (!h) { + pr_debug("icmp_error_message: no match\n"); + return -NF_ACCEPT; + } + + if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY) + ctinfo += IP_CT_IS_REPLY; + + /* Update skb to refer to this connection */ + nf_ct_set(skb, nf_ct_tuplehash_to_ctrack(h), ctinfo); + return NF_ACCEPT; +} + +static void icmp_error_log(const struct sk_buff *skb, struct net *net, + u8 pf, const char *msg) +{ + nf_l4proto_log_invalid(skb, net, pf, IPPROTO_ICMP, "%s", msg); +} + +/* Small and modified version of icmp_rcv */ +static int +icmp_error(struct net *net, struct nf_conn *tmpl, + struct sk_buff *skb, unsigned int dataoff, + u8 pf, unsigned int hooknum) +{ + const struct icmphdr *icmph; + struct icmphdr _ih; + + /* Not enough header? */ + icmph = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_ih), &_ih); + if (icmph == NULL) { + icmp_error_log(skb, net, pf, "short packet"); + return -NF_ACCEPT; + } + + /* See ip_conntrack_proto_tcp.c */ + if (net->ct.sysctl_checksum && hooknum == NF_INET_PRE_ROUTING && + nf_ip_checksum(skb, hooknum, dataoff, 0)) { + icmp_error_log(skb, net, pf, "bad hw icmp checksum"); + return -NF_ACCEPT; + } + + /* + * 18 is the highest 'known' ICMP type. Anything else is a mystery + * + * RFC 1122: 3.2.2 Unknown ICMP messages types MUST be silently + * discarded. + */ + if (icmph->type > NR_ICMP_TYPES) { + icmp_error_log(skb, net, pf, "invalid icmp type"); + return -NF_ACCEPT; + } + + /* Need to track icmp error message? */ + if (icmph->type != ICMP_DEST_UNREACH && + icmph->type != ICMP_SOURCE_QUENCH && + icmph->type != ICMP_TIME_EXCEEDED && + icmph->type != ICMP_PARAMETERPROB && + icmph->type != ICMP_REDIRECT) + return NF_ACCEPT; + + return icmp_error_message(net, tmpl, skb, hooknum); +} + +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) + +#include +#include + +static int icmp_tuple_to_nlattr(struct sk_buff *skb, + const struct nf_conntrack_tuple *t) +{ + if (nla_put_be16(skb, CTA_PROTO_ICMP_ID, t->src.u.icmp.id) || + nla_put_u8(skb, CTA_PROTO_ICMP_TYPE, t->dst.u.icmp.type) || + nla_put_u8(skb, CTA_PROTO_ICMP_CODE, t->dst.u.icmp.code)) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -1; +} + +static const struct nla_policy icmp_nla_policy[CTA_PROTO_MAX+1] = { + [CTA_PROTO_ICMP_TYPE] = { .type = NLA_U8 }, + [CTA_PROTO_ICMP_CODE] = { .type = NLA_U8 }, + [CTA_PROTO_ICMP_ID] = { .type = NLA_U16 }, +}; + +static int icmp_nlattr_to_tuple(struct nlattr *tb[], + struct nf_conntrack_tuple *tuple) +{ + if (!tb[CTA_PROTO_ICMP_TYPE] || + !tb[CTA_PROTO_ICMP_CODE] || + !tb[CTA_PROTO_ICMP_ID]) + return -EINVAL; + + tuple->dst.u.icmp.type = nla_get_u8(tb[CTA_PROTO_ICMP_TYPE]); + tuple->dst.u.icmp.code = nla_get_u8(tb[CTA_PROTO_ICMP_CODE]); + tuple->src.u.icmp.id = nla_get_be16(tb[CTA_PROTO_ICMP_ID]); + + if (tuple->dst.u.icmp.type >= sizeof(invmap) || + !invmap[tuple->dst.u.icmp.type]) + return -EINVAL; + + return 0; +} + +static unsigned int icmp_nlattr_tuple_size(void) +{ + static unsigned int size __read_mostly; + + if (!size) + size = nla_policy_len(icmp_nla_policy, CTA_PROTO_MAX + 1); + + return size; +} +#endif + +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + +#include +#include + +static int icmp_timeout_nlattr_to_obj(struct nlattr *tb[], + struct net *net, void *data) +{ + unsigned int *timeout = data; + struct nf_icmp_net *in = icmp_pernet(net); + + if (tb[CTA_TIMEOUT_ICMP_TIMEOUT]) { + if (!timeout) + timeout = &in->timeout; + *timeout = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_ICMP_TIMEOUT])) * HZ; + } else if (timeout) { + /* Set default ICMP timeout. */ + *timeout = in->timeout; + } + return 0; +} + +static int +icmp_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) +{ + const unsigned int *timeout = data; + + if (nla_put_be32(skb, CTA_TIMEOUT_ICMP_TIMEOUT, htonl(*timeout / HZ))) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -ENOSPC; +} + +static const struct nla_policy +icmp_timeout_nla_policy[CTA_TIMEOUT_ICMP_MAX+1] = { + [CTA_TIMEOUT_ICMP_TIMEOUT] = { .type = NLA_U32 }, +}; +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ + +#ifdef CONFIG_SYSCTL +static struct ctl_table icmp_sysctl_table[] = { + { + .procname = "nf_conntrack_icmp_timeout", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + { } +}; +#endif /* CONFIG_SYSCTL */ + +static int icmp_kmemdup_sysctl_table(struct nf_proto_net *pn, + struct nf_icmp_net *in) +{ +#ifdef CONFIG_SYSCTL + pn->ctl_table = kmemdup(icmp_sysctl_table, + sizeof(icmp_sysctl_table), + GFP_KERNEL); + if (!pn->ctl_table) + return -ENOMEM; + + pn->ctl_table[0].data = &in->timeout; +#endif + return 0; +} + +static int icmp_init_net(struct net *net, u_int16_t proto) +{ + struct nf_icmp_net *in = icmp_pernet(net); + struct nf_proto_net *pn = &in->pn; + + in->timeout = nf_ct_icmp_timeout; + + return icmp_kmemdup_sysctl_table(pn, in); +} + +static struct nf_proto_net *icmp_get_net_proto(struct net *net) +{ + return &net->ct.nf_ct_proto.icmp.pn; +} + +const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp = +{ + .l3proto = PF_INET, + .l4proto = IPPROTO_ICMP, + .pkt_to_tuple = icmp_pkt_to_tuple, + .invert_tuple = icmp_invert_tuple, + .packet = icmp_packet, + .new = icmp_new, + .error = icmp_error, + .destroy = NULL, + .me = NULL, +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) + .tuple_to_nlattr = icmp_tuple_to_nlattr, + .nlattr_tuple_size = icmp_nlattr_tuple_size, + .nlattr_to_tuple = icmp_nlattr_to_tuple, + .nla_policy = icmp_nla_policy, +#endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + .ctnl_timeout = { + .nlattr_to_obj = icmp_timeout_nlattr_to_obj, + .obj_to_nlattr = icmp_timeout_obj_to_nlattr, + .nlattr_max = CTA_TIMEOUT_ICMP_MAX, + .obj_size = sizeof(unsigned int), + .nla_policy = icmp_timeout_nla_policy, + }, +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ + .init_net = icmp_init_net, + .get_net_proto = icmp_get_net_proto, +}; diff --git a/net/netfilter/nf_conntrack_proto_icmpv6.c b/net/netfilter/nf_conntrack_proto_icmpv6.c new file mode 100644 index 000000000000..bed07b998a10 --- /dev/null +++ b/net/netfilter/nf_conntrack_proto_icmpv6.c @@ -0,0 +1,387 @@ +/* + * Copyright (C)2003,2004 USAGI/WIDE Project + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Author: + * Yasuyuki Kozakai @USAGI + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static const unsigned int nf_ct_icmpv6_timeout = 30*HZ; + +static inline struct nf_icmp_net *icmpv6_pernet(struct net *net) +{ + return &net->ct.nf_ct_proto.icmpv6; +} + +static bool icmpv6_pkt_to_tuple(const struct sk_buff *skb, + unsigned int dataoff, + struct net *net, + struct nf_conntrack_tuple *tuple) +{ + const struct icmp6hdr *hp; + struct icmp6hdr _hdr; + + hp = skb_header_pointer(skb, dataoff, sizeof(_hdr), &_hdr); + if (hp == NULL) + return false; + tuple->dst.u.icmp.type = hp->icmp6_type; + tuple->src.u.icmp.id = hp->icmp6_identifier; + tuple->dst.u.icmp.code = hp->icmp6_code; + + return true; +} + +/* Add 1; spaces filled with 0. */ +static const u_int8_t invmap[] = { + [ICMPV6_ECHO_REQUEST - 128] = ICMPV6_ECHO_REPLY + 1, + [ICMPV6_ECHO_REPLY - 128] = ICMPV6_ECHO_REQUEST + 1, + [ICMPV6_NI_QUERY - 128] = ICMPV6_NI_REPLY + 1, + [ICMPV6_NI_REPLY - 128] = ICMPV6_NI_QUERY + 1 +}; + +static const u_int8_t noct_valid_new[] = { + [ICMPV6_MGM_QUERY - 130] = 1, + [ICMPV6_MGM_REPORT - 130] = 1, + [ICMPV6_MGM_REDUCTION - 130] = 1, + [NDISC_ROUTER_SOLICITATION - 130] = 1, + [NDISC_ROUTER_ADVERTISEMENT - 130] = 1, + [NDISC_NEIGHBOUR_SOLICITATION - 130] = 1, + [NDISC_NEIGHBOUR_ADVERTISEMENT - 130] = 1, + [ICMPV6_MLD2_REPORT - 130] = 1 +}; + +static bool icmpv6_invert_tuple(struct nf_conntrack_tuple *tuple, + const struct nf_conntrack_tuple *orig) +{ + int type = orig->dst.u.icmp.type - 128; + if (type < 0 || type >= sizeof(invmap) || !invmap[type]) + return false; + + tuple->src.u.icmp.id = orig->src.u.icmp.id; + tuple->dst.u.icmp.type = invmap[type] - 1; + tuple->dst.u.icmp.code = orig->dst.u.icmp.code; + return true; +} + +static unsigned int *icmpv6_get_timeouts(struct net *net) +{ + return &icmpv6_pernet(net)->timeout; +} + +/* Returns verdict for packet, or -1 for invalid. */ +static int icmpv6_packet(struct nf_conn *ct, + const struct sk_buff *skb, + unsigned int dataoff, + enum ip_conntrack_info ctinfo) +{ + unsigned int *timeout = nf_ct_timeout_lookup(ct); + + if (!timeout) + timeout = icmpv6_get_timeouts(nf_ct_net(ct)); + + /* Do not immediately delete the connection after the first + successful reply to avoid excessive conntrackd traffic + and also to handle correctly ICMP echo reply duplicates. */ + nf_ct_refresh_acct(ct, ctinfo, skb, *timeout); + + return NF_ACCEPT; +} + +/* Called when a new connection for this protocol found. */ +static bool icmpv6_new(struct nf_conn *ct, const struct sk_buff *skb, + unsigned int dataoff) +{ + static const u_int8_t valid_new[] = { + [ICMPV6_ECHO_REQUEST - 128] = 1, + [ICMPV6_NI_QUERY - 128] = 1 + }; + int type = ct->tuplehash[0].tuple.dst.u.icmp.type - 128; + + if (type < 0 || type >= sizeof(valid_new) || !valid_new[type]) { + /* Can't create a new ICMPv6 `conn' with this. */ + pr_debug("icmpv6: can't create new conn with type %u\n", + type + 128); + nf_ct_dump_tuple_ipv6(&ct->tuplehash[0].tuple); + return false; + } + return true; +} + +static int +icmpv6_error_message(struct net *net, struct nf_conn *tmpl, + struct sk_buff *skb, + unsigned int icmp6off) +{ + struct nf_conntrack_tuple intuple, origtuple; + const struct nf_conntrack_tuple_hash *h; + const struct nf_conntrack_l4proto *inproto; + enum ip_conntrack_info ctinfo; + struct nf_conntrack_zone tmp; + + WARN_ON(skb_nfct(skb)); + + /* Are they talking about one of our connections? */ + if (!nf_ct_get_tuplepr(skb, + skb_network_offset(skb) + + sizeof(struct ipv6hdr) + + sizeof(struct icmp6hdr), + PF_INET6, net, &origtuple)) { + pr_debug("icmpv6_error: Can't get tuple\n"); + return -NF_ACCEPT; + } + + /* rcu_read_lock()ed by nf_hook_thresh */ + inproto = __nf_ct_l4proto_find(PF_INET6, origtuple.dst.protonum); + + /* Ordinarily, we'd expect the inverted tupleproto, but it's + been preserved inside the ICMP. */ + if (!nf_ct_invert_tuple(&intuple, &origtuple, inproto)) { + pr_debug("icmpv6_error: Can't invert tuple\n"); + return -NF_ACCEPT; + } + + ctinfo = IP_CT_RELATED; + + h = nf_conntrack_find_get(net, nf_ct_zone_tmpl(tmpl, skb, &tmp), + &intuple); + if (!h) { + pr_debug("icmpv6_error: no match\n"); + return -NF_ACCEPT; + } else { + if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY) + ctinfo += IP_CT_IS_REPLY; + } + + /* Update skb to refer to this connection */ + nf_ct_set(skb, nf_ct_tuplehash_to_ctrack(h), ctinfo); + return NF_ACCEPT; +} + +static void icmpv6_error_log(const struct sk_buff *skb, struct net *net, + u8 pf, const char *msg) +{ + nf_l4proto_log_invalid(skb, net, pf, IPPROTO_ICMPV6, "%s", msg); +} + +static int +icmpv6_error(struct net *net, struct nf_conn *tmpl, + struct sk_buff *skb, unsigned int dataoff, + u8 pf, unsigned int hooknum) +{ + const struct icmp6hdr *icmp6h; + struct icmp6hdr _ih; + int type; + + icmp6h = skb_header_pointer(skb, dataoff, sizeof(_ih), &_ih); + if (icmp6h == NULL) { + icmpv6_error_log(skb, net, pf, "short packet"); + return -NF_ACCEPT; + } + + if (net->ct.sysctl_checksum && hooknum == NF_INET_PRE_ROUTING && + nf_ip6_checksum(skb, hooknum, dataoff, IPPROTO_ICMPV6)) { + icmpv6_error_log(skb, net, pf, "ICMPv6 checksum failed"); + return -NF_ACCEPT; + } + + type = icmp6h->icmp6_type - 130; + if (type >= 0 && type < sizeof(noct_valid_new) && + noct_valid_new[type]) { + nf_ct_set(skb, NULL, IP_CT_UNTRACKED); + return NF_ACCEPT; + } + + /* is not error message ? */ + if (icmp6h->icmp6_type >= 128) + return NF_ACCEPT; + + return icmpv6_error_message(net, tmpl, skb, dataoff); +} + +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) + +#include +#include +static int icmpv6_tuple_to_nlattr(struct sk_buff *skb, + const struct nf_conntrack_tuple *t) +{ + if (nla_put_be16(skb, CTA_PROTO_ICMPV6_ID, t->src.u.icmp.id) || + nla_put_u8(skb, CTA_PROTO_ICMPV6_TYPE, t->dst.u.icmp.type) || + nla_put_u8(skb, CTA_PROTO_ICMPV6_CODE, t->dst.u.icmp.code)) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -1; +} + +static const struct nla_policy icmpv6_nla_policy[CTA_PROTO_MAX+1] = { + [CTA_PROTO_ICMPV6_TYPE] = { .type = NLA_U8 }, + [CTA_PROTO_ICMPV6_CODE] = { .type = NLA_U8 }, + [CTA_PROTO_ICMPV6_ID] = { .type = NLA_U16 }, +}; + +static int icmpv6_nlattr_to_tuple(struct nlattr *tb[], + struct nf_conntrack_tuple *tuple) +{ + if (!tb[CTA_PROTO_ICMPV6_TYPE] || + !tb[CTA_PROTO_ICMPV6_CODE] || + !tb[CTA_PROTO_ICMPV6_ID]) + return -EINVAL; + + tuple->dst.u.icmp.type = nla_get_u8(tb[CTA_PROTO_ICMPV6_TYPE]); + tuple->dst.u.icmp.code = nla_get_u8(tb[CTA_PROTO_ICMPV6_CODE]); + tuple->src.u.icmp.id = nla_get_be16(tb[CTA_PROTO_ICMPV6_ID]); + + if (tuple->dst.u.icmp.type < 128 || + tuple->dst.u.icmp.type - 128 >= sizeof(invmap) || + !invmap[tuple->dst.u.icmp.type - 128]) + return -EINVAL; + + return 0; +} + +static unsigned int icmpv6_nlattr_tuple_size(void) +{ + static unsigned int size __read_mostly; + + if (!size) + size = nla_policy_len(icmpv6_nla_policy, CTA_PROTO_MAX + 1); + + return size; +} +#endif + +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + +#include +#include + +static int icmpv6_timeout_nlattr_to_obj(struct nlattr *tb[], + struct net *net, void *data) +{ + unsigned int *timeout = data; + struct nf_icmp_net *in = icmpv6_pernet(net); + + if (!timeout) + timeout = icmpv6_get_timeouts(net); + if (tb[CTA_TIMEOUT_ICMPV6_TIMEOUT]) { + *timeout = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_ICMPV6_TIMEOUT])) * HZ; + } else { + /* Set default ICMPv6 timeout. */ + *timeout = in->timeout; + } + return 0; +} + +static int +icmpv6_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) +{ + const unsigned int *timeout = data; + + if (nla_put_be32(skb, CTA_TIMEOUT_ICMPV6_TIMEOUT, htonl(*timeout / HZ))) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -ENOSPC; +} + +static const struct nla_policy +icmpv6_timeout_nla_policy[CTA_TIMEOUT_ICMPV6_MAX+1] = { + [CTA_TIMEOUT_ICMPV6_TIMEOUT] = { .type = NLA_U32 }, +}; +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ + +#ifdef CONFIG_SYSCTL +static struct ctl_table icmpv6_sysctl_table[] = { + { + .procname = "nf_conntrack_icmpv6_timeout", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + { } +}; +#endif /* CONFIG_SYSCTL */ + +static int icmpv6_kmemdup_sysctl_table(struct nf_proto_net *pn, + struct nf_icmp_net *in) +{ +#ifdef CONFIG_SYSCTL + pn->ctl_table = kmemdup(icmpv6_sysctl_table, + sizeof(icmpv6_sysctl_table), + GFP_KERNEL); + if (!pn->ctl_table) + return -ENOMEM; + + pn->ctl_table[0].data = &in->timeout; +#endif + return 0; +} + +static int icmpv6_init_net(struct net *net, u_int16_t proto) +{ + struct nf_icmp_net *in = icmpv6_pernet(net); + struct nf_proto_net *pn = &in->pn; + + in->timeout = nf_ct_icmpv6_timeout; + + return icmpv6_kmemdup_sysctl_table(pn, in); +} + +static struct nf_proto_net *icmpv6_get_net_proto(struct net *net) +{ + return &net->ct.nf_ct_proto.icmpv6.pn; +} + +const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 = +{ + .l3proto = PF_INET6, + .l4proto = IPPROTO_ICMPV6, + .pkt_to_tuple = icmpv6_pkt_to_tuple, + .invert_tuple = icmpv6_invert_tuple, + .packet = icmpv6_packet, + .new = icmpv6_new, + .error = icmpv6_error, +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) + .tuple_to_nlattr = icmpv6_tuple_to_nlattr, + .nlattr_tuple_size = icmpv6_nlattr_tuple_size, + .nlattr_to_tuple = icmpv6_nlattr_to_tuple, + .nla_policy = icmpv6_nla_policy, +#endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + .ctnl_timeout = { + .nlattr_to_obj = icmpv6_timeout_nlattr_to_obj, + .obj_to_nlattr = icmpv6_timeout_obj_to_nlattr, + .nlattr_max = CTA_TIMEOUT_ICMP_MAX, + .obj_size = sizeof(unsigned int), + .nla_policy = icmpv6_timeout_nla_policy, + }, +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ + .init_net = icmpv6_init_net, + .get_net_proto = icmpv6_get_net_proto, +}; diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 47b80fd0d2c3..13279f683da9 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -1,12 +1,4 @@ -/* (C) 1999-2001 Paul `Rusty' Russell - * (C) 2002-2004 Netfilter Core Team - * (C) 2005-2012 Patrick McHardy - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - +// SPDX-License-Identifier: GPL-2.0 #include #include #include @@ -32,7 +24,7 @@ #include #include -MODULE_LICENSE("GPL"); +unsigned int nf_conntrack_net_id __read_mostly; #ifdef CONFIG_NF_CONNTRACK_PROCFS void @@ -674,6 +666,8 @@ static void nf_conntrack_pernet_exit(struct list_head *net_exit_list) static struct pernet_operations nf_conntrack_net_ops = { .init = nf_conntrack_pernet_init, .exit_batch = nf_conntrack_pernet_exit, + .id = &nf_conntrack_net_id, + .size = sizeof(struct nf_conntrack_net), }; static int __init nf_conntrack_standalone_init(void) diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 86df2a1666fd..6366f0c0b8c1 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -28,7 +28,6 @@ #include #include #include -#include #include #include @@ -743,12 +742,6 @@ EXPORT_SYMBOL_GPL(nf_nat_l4proto_unregister); int nf_nat_l3proto_register(const struct nf_nat_l3proto *l3proto) { - int err; - - err = nf_ct_l3proto_try_module_get(l3proto->l3proto); - if (err < 0) - return err; - mutex_lock(&nf_nat_proto_mutex); RCU_INIT_POINTER(nf_nat_l4protos[l3proto->l3proto][IPPROTO_TCP], &nf_nat_l4proto_tcp); @@ -781,7 +774,6 @@ void nf_nat_l3proto_unregister(const struct nf_nat_l3proto *l3proto) synchronize_rcu(); nf_nat_l3proto_clean(l3proto->l3proto); - nf_ct_l3proto_module_put(l3proto->l3proto); } EXPORT_SYMBOL_GPL(nf_nat_l3proto_unregister); -- cgit v1.2.3 From 9afb719e7046c4f2462278862ab3db2961cc141c Mon Sep 17 00:00:00 2001 From: Laura Abbott Date: Thu, 5 Jul 2018 17:49:37 -0700 Subject: kbuild: Add build salt to the kernel and modules In Fedora, the debug information is packaged separately (foo-debuginfo) and can be installed separately. There's been a long standing issue where only one version of a debuginfo info package can be installed at a time. There's been an effort for Fedora for parallel debuginfo to rectify this problem. Part of the requirement to allow parallel debuginfo to work is that build ids are unique between builds. The existing upstream rpm implementation ensures this by re-calculating the build-id using the version and release as a seed. This doesn't work 100% for the kernel because of the vDSO which is its own binary and doesn't get updated when embedded. Fix this by adding some data in an ELF note for both the kernel and modules. The data is controlled via a Kconfig option so distributions can set it to an appropriate value to ensure uniqueness between builds. Suggested-by: Masahiro Yamada Signed-off-by: Laura Abbott Signed-off-by: Masahiro Yamada --- include/linux/build-salt.h | 20 ++++++++++++++++++++ init/Kconfig | 9 +++++++++ init/version.c | 3 +++ scripts/mod/modpost.c | 3 +++ 4 files changed, 35 insertions(+) create mode 100644 include/linux/build-salt.h (limited to 'include') diff --git a/include/linux/build-salt.h b/include/linux/build-salt.h new file mode 100644 index 000000000000..bb007bd05e7a --- /dev/null +++ b/include/linux/build-salt.h @@ -0,0 +1,20 @@ +#ifndef __BUILD_SALT_H +#define __BUILD_SALT_H + +#include + +#define LINUX_ELFNOTE_BUILD_SALT 0x100 + +#ifdef __ASSEMBLER__ + +#define BUILD_SALT \ + ELFNOTE(Linux, LINUX_ELFNOTE_BUILD_SALT, .asciz CONFIG_BUILD_SALT) + +#else + +#define BUILD_SALT \ + ELFNOTE32("Linux", LINUX_ELFNOTE_BUILD_SALT, CONFIG_BUILD_SALT) + +#endif + +#endif /* __BUILD_SALT_H */ diff --git a/init/Kconfig b/init/Kconfig index 041f3a022122..d39b31484c52 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -107,6 +107,15 @@ config LOCALVERSION_AUTO which is done within the script "scripts/setlocalversion".) +config BUILD_SALT + string "Build ID Salt" + default "" + help + The build ID is used to link binaries and their debug info. Setting + this option will use the value in the calculation of the build id. + This is mostly useful for distributions which want to ensure the + build is unique between builds. It's safe to leave the default. + config HAVE_KERNEL_GZIP bool diff --git a/init/version.c b/init/version.c index bfb4e3f4955e..ef4012ec4375 100644 --- a/init/version.c +++ b/init/version.c @@ -7,6 +7,7 @@ */ #include +#include #include #include #include @@ -49,3 +50,5 @@ const char linux_proc_banner[] = "%s version %s" " (" LINUX_COMPILE_BY "@" LINUX_COMPILE_HOST ")" " (" LINUX_COMPILER ") %s\n"; + +BUILD_SALT; diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 1663fb19343a..dc6d714e4dcb 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -2125,10 +2125,13 @@ static int check_modname_len(struct module *mod) **/ static void add_header(struct buffer *b, struct module *mod) { + buf_printf(b, "#include \n"); buf_printf(b, "#include \n"); buf_printf(b, "#include \n"); buf_printf(b, "#include \n"); buf_printf(b, "\n"); + buf_printf(b, "BUILD_SALT;\n"); + buf_printf(b, "\n"); buf_printf(b, "MODULE_INFO(vermagic, VERMAGIC_STRING);\n"); buf_printf(b, "MODULE_INFO(name, KBUILD_MODNAME);\n"); buf_printf(b, "\n"); -- cgit v1.2.3 From ae891abe7c2ccf75b69ca8330225e37ecc06924e Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 11 Jul 2018 15:17:22 +0200 Subject: drm/i915: Split audio component to a generic type For allowing other drivers to use the DRM audio component, rename the i915_audio_component_* with drm_audio_component_*, and split the generic part into drm_audio_component.h. The i915 specific stuff remains in struct i915_audio_component, which contains drm_audio_component as the base. The license of drm_audio_component.h is kept to MIT as same as the the original i915_component.h. This is a preliminary change for further development, and no functional changes by this patch itself, merely code-split and renames. v1->v2: Use SPDX for drm_audio_component.h, fix remaining i915 argument in drm_audio_component.h Reviewed-by: Rodrigo Vivi Signed-off-by: Takashi Iwai --- drivers/gpu/drm/i915/intel_audio.c | 22 +++++---- include/drm/drm_audio_component.h | 95 ++++++++++++++++++++++++++++++++++++++ include/drm/i915_component.h | 85 ++-------------------------------- include/sound/hda_i915.h | 6 +-- include/sound/hdaudio.h | 6 +-- sound/hda/hdac_i915.c | 40 ++++++++-------- sound/pci/hda/patch_hdmi.c | 8 ++-- sound/soc/codecs/hdac_hdmi.c | 2 +- 8 files changed, 144 insertions(+), 120 deletions(-) create mode 100644 include/drm/drm_audio_component.h (limited to 'include') diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c index 3ea566f99450..7dd5605d94ae 100644 --- a/drivers/gpu/drm/i915/intel_audio.c +++ b/drivers/gpu/drm/i915/intel_audio.c @@ -639,11 +639,12 @@ void intel_audio_codec_enable(struct intel_encoder *encoder, dev_priv->av_enc_map[pipe] = encoder; mutex_unlock(&dev_priv->av_mutex); - if (acomp && acomp->audio_ops && acomp->audio_ops->pin_eld_notify) { + if (acomp && acomp->base.audio_ops && + acomp->base.audio_ops->pin_eld_notify) { /* audio drivers expect pipe = -1 to indicate Non-MST cases */ if (!intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP_MST)) pipe = -1; - acomp->audio_ops->pin_eld_notify(acomp->audio_ops->audio_ptr, + acomp->base.audio_ops->pin_eld_notify(acomp->base.audio_ops->audio_ptr, (int) port, (int) pipe); } @@ -681,11 +682,12 @@ void intel_audio_codec_disable(struct intel_encoder *encoder, dev_priv->av_enc_map[pipe] = NULL; mutex_unlock(&dev_priv->av_mutex); - if (acomp && acomp->audio_ops && acomp->audio_ops->pin_eld_notify) { + if (acomp && acomp->base.audio_ops && + acomp->base.audio_ops->pin_eld_notify) { /* audio drivers expect pipe = -1 to indicate Non-MST cases */ if (!intel_crtc_has_type(old_crtc_state, INTEL_OUTPUT_DP_MST)) pipe = -1; - acomp->audio_ops->pin_eld_notify(acomp->audio_ops->audio_ptr, + acomp->base.audio_ops->pin_eld_notify(acomp->base.audio_ops->audio_ptr, (int) port, (int) pipe); } @@ -880,7 +882,7 @@ static int i915_audio_component_get_eld(struct device *kdev, int port, return ret; } -static const struct i915_audio_component_ops i915_audio_component_ops = { +static const struct drm_audio_component_ops i915_audio_component_ops = { .owner = THIS_MODULE, .get_power = i915_audio_component_get_power, .put_power = i915_audio_component_put_power, @@ -897,12 +899,12 @@ static int i915_audio_component_bind(struct device *i915_kdev, struct drm_i915_private *dev_priv = kdev_to_i915(i915_kdev); int i; - if (WARN_ON(acomp->ops || acomp->dev)) + if (WARN_ON(acomp->base.ops || acomp->base.dev)) return -EEXIST; drm_modeset_lock_all(&dev_priv->drm); - acomp->ops = &i915_audio_component_ops; - acomp->dev = i915_kdev; + acomp->base.ops = &i915_audio_component_ops; + acomp->base.dev = i915_kdev; BUILD_BUG_ON(MAX_PORTS != I915_MAX_PORTS); for (i = 0; i < ARRAY_SIZE(acomp->aud_sample_rate); i++) acomp->aud_sample_rate[i] = 0; @@ -919,8 +921,8 @@ static void i915_audio_component_unbind(struct device *i915_kdev, struct drm_i915_private *dev_priv = kdev_to_i915(i915_kdev); drm_modeset_lock_all(&dev_priv->drm); - acomp->ops = NULL; - acomp->dev = NULL; + acomp->base.ops = NULL; + acomp->base.dev = NULL; dev_priv->audio_component = NULL; drm_modeset_unlock_all(&dev_priv->drm); } diff --git a/include/drm/drm_audio_component.h b/include/drm/drm_audio_component.h new file mode 100644 index 000000000000..e85689f212c2 --- /dev/null +++ b/include/drm/drm_audio_component.h @@ -0,0 +1,95 @@ +// SPDX-License-Identifier: MIT +// Copyright © 2014 Intel Corporation + +#ifndef _DRM_AUDIO_COMPONENT_H_ +#define _DRM_AUDIO_COMPONENT_H_ + +/** + * struct drm_audio_component_ops - Ops implemented by DRM driver, called by hda driver + */ +struct drm_audio_component_ops { + /** + * @owner: drm module to pin down + */ + struct module *owner; + /** + * @get_power: get the POWER_DOMAIN_AUDIO power well + * + * Request the power well to be turned on. + */ + void (*get_power)(struct device *); + /** + * @put_power: put the POWER_DOMAIN_AUDIO power well + * + * Allow the power well to be turned off. + */ + void (*put_power)(struct device *); + /** + * @codec_wake_override: Enable/disable codec wake signal + */ + void (*codec_wake_override)(struct device *, bool enable); + /** + * @get_cdclk_freq: Get the Core Display Clock in kHz + */ + int (*get_cdclk_freq)(struct device *); + /** + * @sync_audio_rate: set n/cts based on the sample rate + * + * Called from audio driver. After audio driver sets the + * sample rate, it will call this function to set n/cts + */ + int (*sync_audio_rate)(struct device *, int port, int pipe, int rate); + /** + * @get_eld: fill the audio state and ELD bytes for the given port + * + * Called from audio driver to get the HDMI/DP audio state of the given + * digital port, and also fetch ELD bytes to the given pointer. + * + * It returns the byte size of the original ELD (not the actually + * copied size), zero for an invalid ELD, or a negative error code. + * + * Note that the returned size may be over @max_bytes. Then it + * implies that only a part of ELD has been copied to the buffer. + */ + int (*get_eld)(struct device *, int port, int pipe, bool *enabled, + unsigned char *buf, int max_bytes); +}; + +/** + * struct drm_audio_component_audio_ops - Ops implemented by hda driver, called by DRM driver + */ +struct drm_audio_component_audio_ops { + /** + * @audio_ptr: Pointer to be used in call to pin_eld_notify + */ + void *audio_ptr; + /** + * @pin_eld_notify: Notify the HDA driver that pin sense and/or ELD information has changed + * + * Called when the DRM driver has set up audio pipeline or has just + * begun to tear it down. This allows the HDA driver to update its + * status accordingly (even when the HDA controller is in power save + * mode). + */ + void (*pin_eld_notify)(void *audio_ptr, int port, int pipe); +}; + +/** + * struct drm_audio_component - Used for direct communication between DRM and hda drivers + */ +struct drm_audio_component { + /** + * @dev: DRM device, used as parameter for ops + */ + struct device *dev; + /** + * @ops: Ops implemented by DRM driver, called by hda driver + */ + const struct drm_audio_component_ops *ops; + /** + * @audio_ops: Ops implemented by hda driver, called by DRM driver + */ + const struct drm_audio_component_audio_ops *audio_ops; +}; + +#endif /* _DRM_AUDIO_COMPONENT_H_ */ diff --git a/include/drm/i915_component.h b/include/drm/i915_component.h index 346b1f5cb180..fca22d463e1b 100644 --- a/include/drm/i915_component.h +++ b/include/drm/i915_component.h @@ -24,101 +24,26 @@ #ifndef _I915_COMPONENT_H_ #define _I915_COMPONENT_H_ +#include "drm_audio_component.h" + /* MAX_PORT is the number of port * It must be sync with I915_MAX_PORTS defined i915_drv.h */ #define MAX_PORTS 6 -/** - * struct i915_audio_component_ops - Ops implemented by i915 driver, called by hda driver - */ -struct i915_audio_component_ops { - /** - * @owner: i915 module - */ - struct module *owner; - /** - * @get_power: get the POWER_DOMAIN_AUDIO power well - * - * Request the power well to be turned on. - */ - void (*get_power)(struct device *); - /** - * @put_power: put the POWER_DOMAIN_AUDIO power well - * - * Allow the power well to be turned off. - */ - void (*put_power)(struct device *); - /** - * @codec_wake_override: Enable/disable codec wake signal - */ - void (*codec_wake_override)(struct device *, bool enable); - /** - * @get_cdclk_freq: Get the Core Display Clock in kHz - */ - int (*get_cdclk_freq)(struct device *); - /** - * @sync_audio_rate: set n/cts based on the sample rate - * - * Called from audio driver. After audio driver sets the - * sample rate, it will call this function to set n/cts - */ - int (*sync_audio_rate)(struct device *, int port, int pipe, int rate); - /** - * @get_eld: fill the audio state and ELD bytes for the given port - * - * Called from audio driver to get the HDMI/DP audio state of the given - * digital port, and also fetch ELD bytes to the given pointer. - * - * It returns the byte size of the original ELD (not the actually - * copied size), zero for an invalid ELD, or a negative error code. - * - * Note that the returned size may be over @max_bytes. Then it - * implies that only a part of ELD has been copied to the buffer. - */ - int (*get_eld)(struct device *, int port, int pipe, bool *enabled, - unsigned char *buf, int max_bytes); -}; - -/** - * struct i915_audio_component_audio_ops - Ops implemented by hda driver, called by i915 driver - */ -struct i915_audio_component_audio_ops { - /** - * @audio_ptr: Pointer to be used in call to pin_eld_notify - */ - void *audio_ptr; - /** - * @pin_eld_notify: Notify the HDA driver that pin sense and/or ELD information has changed - * - * Called when the i915 driver has set up audio pipeline or has just - * begun to tear it down. This allows the HDA driver to update its - * status accordingly (even when the HDA controller is in power save - * mode). - */ - void (*pin_eld_notify)(void *audio_ptr, int port, int pipe); -}; - /** * struct i915_audio_component - Used for direct communication between i915 and hda drivers */ struct i915_audio_component { /** - * @dev: i915 device, used as parameter for ops + * @base: the drm_audio_component base class */ - struct device *dev; + struct drm_audio_component base; + /** * @aud_sample_rate: the array of audio sample rate per port */ int aud_sample_rate[MAX_PORTS]; - /** - * @ops: Ops implemented by i915 driver, called by hda driver - */ - const struct i915_audio_component_ops *ops; - /** - * @audio_ops: Ops implemented by hda driver, called by i915 driver - */ - const struct i915_audio_component_audio_ops *audio_ops; }; #endif /* _I915_COMPONENT_H_ */ diff --git a/include/sound/hda_i915.h b/include/sound/hda_i915.h index a94f5b6f92ac..f69ea84e7b65 100644 --- a/include/sound/hda_i915.h +++ b/include/sound/hda_i915.h @@ -5,7 +5,7 @@ #ifndef __SOUND_HDA_I915_H #define __SOUND_HDA_I915_H -#include +#include #ifdef CONFIG_SND_HDA_I915 int snd_hdac_set_codec_wakeup(struct hdac_bus *bus, bool enable); @@ -17,7 +17,7 @@ int snd_hdac_acomp_get_eld(struct hdac_device *codec, hda_nid_t nid, int dev_id, bool *audio_enabled, char *buffer, int max_bytes); int snd_hdac_i915_init(struct hdac_bus *bus); int snd_hdac_i915_exit(struct hdac_bus *bus); -int snd_hdac_i915_register_notifier(const struct i915_audio_component_audio_ops *); +int snd_hdac_i915_register_notifier(const struct drm_audio_component_audio_ops *); #else static inline int snd_hdac_set_codec_wakeup(struct hdac_bus *bus, bool enable) { @@ -49,7 +49,7 @@ static inline int snd_hdac_i915_exit(struct hdac_bus *bus) { return 0; } -static inline int snd_hdac_i915_register_notifier(const struct i915_audio_component_audio_ops *ops) +static inline int snd_hdac_i915_register_notifier(const struct drm_audio_component_audio_ops *ops) { return -ENODEV; } diff --git a/include/sound/hdaudio.h b/include/sound/hdaudio.h index f1baaa88e766..ab5ee3ef2198 100644 --- a/include/sound/hdaudio.h +++ b/include/sound/hdaudio.h @@ -333,9 +333,9 @@ struct hdac_bus { spinlock_t reg_lock; struct mutex cmd_mutex; - /* i915 component interface */ - struct i915_audio_component *audio_component; - int i915_power_refcount; + /* DRM component interface */ + struct drm_audio_component *audio_component; + int drm_power_refcount; /* parameters required for enhanced capabilities */ int num_streams; diff --git a/sound/hda/hdac_i915.c b/sound/hda/hdac_i915.c index cbe818eda336..1a88c1aaf9bb 100644 --- a/sound/hda/hdac_i915.c +++ b/sound/hda/hdac_i915.c @@ -16,13 +16,13 @@ #include #include #include -#include +#include #include #include #include #include -static struct i915_audio_component *hdac_acomp; +static struct drm_audio_component *hdac_acomp; /** * snd_hdac_set_codec_wakeup - Enable / disable HDMI/DP codec wakeup @@ -39,7 +39,7 @@ static struct i915_audio_component *hdac_acomp; */ int snd_hdac_set_codec_wakeup(struct hdac_bus *bus, bool enable) { - struct i915_audio_component *acomp = bus->audio_component; + struct drm_audio_component *acomp = bus->audio_component; if (!acomp || !acomp->ops) return -ENODEV; @@ -74,7 +74,7 @@ EXPORT_SYMBOL_GPL(snd_hdac_set_codec_wakeup); */ int snd_hdac_display_power(struct hdac_bus *bus, bool enable) { - struct i915_audio_component *acomp = bus->audio_component; + struct drm_audio_component *acomp = bus->audio_component; if (!acomp || !acomp->ops) return -ENODEV; @@ -83,14 +83,14 @@ int snd_hdac_display_power(struct hdac_bus *bus, bool enable) enable ? "enable" : "disable"); if (enable) { - if (!bus->i915_power_refcount++) { + if (!bus->drm_power_refcount++) { acomp->ops->get_power(acomp->dev); snd_hdac_set_codec_wakeup(bus, true); snd_hdac_set_codec_wakeup(bus, false); } } else { - WARN_ON(!bus->i915_power_refcount); - if (!--bus->i915_power_refcount) + WARN_ON(!bus->drm_power_refcount); + if (!--bus->drm_power_refcount) acomp->ops->put_power(acomp->dev); } @@ -119,7 +119,7 @@ EXPORT_SYMBOL_GPL(snd_hdac_display_power); */ void snd_hdac_i915_set_bclk(struct hdac_bus *bus) { - struct i915_audio_component *acomp = bus->audio_component; + struct drm_audio_component *acomp = bus->audio_component; struct pci_dev *pci = to_pci_dev(bus->dev); int cdclk_freq; unsigned int bclk_m, bclk_n; @@ -206,7 +206,7 @@ int snd_hdac_sync_audio_rate(struct hdac_device *codec, hda_nid_t nid, int dev_id, int rate) { struct hdac_bus *bus = codec->bus; - struct i915_audio_component *acomp = bus->audio_component; + struct drm_audio_component *acomp = bus->audio_component; int port, pipe; if (!acomp || !acomp->ops || !acomp->ops->sync_audio_rate) @@ -244,7 +244,7 @@ int snd_hdac_acomp_get_eld(struct hdac_device *codec, hda_nid_t nid, int dev_id, bool *audio_enabled, char *buffer, int max_bytes) { struct hdac_bus *bus = codec->bus; - struct i915_audio_component *acomp = bus->audio_component; + struct drm_audio_component *acomp = bus->audio_component; int port, pipe; if (!acomp || !acomp->ops || !acomp->ops->get_eld) @@ -262,7 +262,7 @@ EXPORT_SYMBOL_GPL(snd_hdac_acomp_get_eld); static int hdac_component_master_bind(struct device *dev) { - struct i915_audio_component *acomp = hdac_acomp; + struct drm_audio_component *acomp = hdac_acomp; int ret; ret = component_bind_all(dev, acomp); @@ -294,7 +294,7 @@ out_unbind: static void hdac_component_master_unbind(struct device *dev) { - struct i915_audio_component *acomp = hdac_acomp; + struct drm_audio_component *acomp = hdac_acomp; module_put(acomp->ops->owner); component_unbind_all(dev, acomp); @@ -323,7 +323,7 @@ static int hdac_component_master_match(struct device *dev, void *data) * * Returns zero for success or a negative error code. */ -int snd_hdac_i915_register_notifier(const struct i915_audio_component_audio_ops *aops) +int snd_hdac_i915_register_notifier(const struct drm_audio_component_audio_ops *aops) { if (!hdac_acomp) return -ENODEV; @@ -361,7 +361,8 @@ int snd_hdac_i915_init(struct hdac_bus *bus) { struct component_match *match = NULL; struct device *dev = bus->dev; - struct i915_audio_component *acomp; + struct i915_audio_component *i915_acomp; + struct drm_audio_component *acomp; int ret; if (WARN_ON(hdac_acomp)) @@ -370,9 +371,10 @@ int snd_hdac_i915_init(struct hdac_bus *bus) if (!i915_gfx_present()) return -ENODEV; - acomp = kzalloc(sizeof(*acomp), GFP_KERNEL); - if (!acomp) + i915_acomp = kzalloc(sizeof(*i915_acomp), GFP_KERNEL); + if (!i915_acomp) return -ENOMEM; + acomp = &i915_acomp->base; bus->audio_component = acomp; hdac_acomp = acomp; @@ -421,13 +423,13 @@ EXPORT_SYMBOL_GPL(snd_hdac_i915_init); int snd_hdac_i915_exit(struct hdac_bus *bus) { struct device *dev = bus->dev; - struct i915_audio_component *acomp = bus->audio_component; + struct drm_audio_component *acomp = bus->audio_component; if (!acomp) return 0; - WARN_ON(bus->i915_power_refcount); - if (bus->i915_power_refcount > 0 && acomp->ops) + WARN_ON(bus->drm_power_refcount); + if (bus->drm_power_refcount > 0 && acomp->ops) acomp->ops->put_power(acomp->dev); component_master_del(dev, &hdac_component_master_ops); diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 8a49415aebac..c0847017114c 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -177,7 +177,7 @@ struct hdmi_spec { /* i915/powerwell (Haswell+/Valleyview+) specific */ bool use_acomp_notifier; /* use i915 eld_notify callback for hotplug */ - struct i915_audio_component_audio_ops i915_audio_ops; + struct drm_audio_component_audio_ops drm_audio_ops; struct hdac_chmap chmap; hda_nid_t vendor_nid; @@ -2511,14 +2511,14 @@ static void register_i915_notifier(struct hda_codec *codec) struct hdmi_spec *spec = codec->spec; spec->use_acomp_notifier = true; - spec->i915_audio_ops.audio_ptr = codec; + spec->drm_audio_ops.audio_ptr = codec; /* intel_audio_codec_enable() or intel_audio_codec_disable() * will call pin_eld_notify with using audio_ptr pointer * We need make sure audio_ptr is really setup */ wmb(); - spec->i915_audio_ops.pin_eld_notify = intel_pin_eld_notify; - snd_hdac_i915_register_notifier(&spec->i915_audio_ops); + spec->drm_audio_ops.pin_eld_notify = intel_pin_eld_notify; + snd_hdac_i915_register_notifier(&spec->drm_audio_ops); } /* setup_stream ops override for HSW+ */ diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c index 3e3a2a9ef310..460075475f20 100644 --- a/sound/soc/codecs/hdac_hdmi.c +++ b/sound/soc/codecs/hdac_hdmi.c @@ -1583,7 +1583,7 @@ static void hdac_hdmi_eld_notify_cb(void *aptr, int port, int pipe) } -static struct i915_audio_component_audio_ops aops = { +static struct drm_audio_component_audio_ops aops = { .pin_eld_notify = hdac_hdmi_eld_notify_cb, }; -- cgit v1.2.3 From 82887c0beb1ee6b33eed8318d8e8d41c5b3eddae Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 11 Jul 2018 15:48:18 +0200 Subject: ALSA: hda/i915: Associate audio component with devres The HD-audio i915 binding code contains a single pointer, hdac_acomp, for allowing the access to audio component from the master bind/unbind callbacks. This was needed because the callbacks pass only the device pointer and we can't guarantee the object type assigned to the drvdata (which is free for each controller driver implementation). And this implementation will be a problem if we support multiple components for different DRM drivers, not only i915. As a solution, allocate the audio component object via devres and associate it with the given device, so that the component callbacks can refer to it via devres_find(). The removal of the object is still done half-manually via devres_destroy() to make the code consistent (although it may work without the explicit call). Also, the snd_hda_i915_register_notifier() had the reference to hdac_acomp as well. In this patch, the corresponding code is removed by passing hdac_bus object to the function, too. Signed-off-by: Takashi Iwai --- include/sound/hda_i915.h | 6 ++++-- sound/hda/hdac_i915.c | 34 +++++++++++++++++++++------------- sound/pci/hda/patch_hdmi.c | 5 +++-- sound/soc/codecs/hdac_hdmi.c | 2 +- 4 files changed, 29 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/sound/hda_i915.h b/include/sound/hda_i915.h index f69ea84e7b65..648263791559 100644 --- a/include/sound/hda_i915.h +++ b/include/sound/hda_i915.h @@ -17,7 +17,8 @@ int snd_hdac_acomp_get_eld(struct hdac_device *codec, hda_nid_t nid, int dev_id, bool *audio_enabled, char *buffer, int max_bytes); int snd_hdac_i915_init(struct hdac_bus *bus); int snd_hdac_i915_exit(struct hdac_bus *bus); -int snd_hdac_i915_register_notifier(const struct drm_audio_component_audio_ops *); +int snd_hdac_i915_register_notifier(struct hdac_bus *bus, + const struct drm_audio_component_audio_ops *ops); #else static inline int snd_hdac_set_codec_wakeup(struct hdac_bus *bus, bool enable) { @@ -49,7 +50,8 @@ static inline int snd_hdac_i915_exit(struct hdac_bus *bus) { return 0; } -static inline int snd_hdac_i915_register_notifier(const struct drm_audio_component_audio_ops *ops) +static inline int snd_hdac_i915_register_notifier(struct hdac_bus *bus, + const struct drm_audio_component_audio_ops *ops) { return -ENODEV; } diff --git a/sound/hda/hdac_i915.c b/sound/hda/hdac_i915.c index 1a88c1aaf9bb..861b77bbc7df 100644 --- a/sound/hda/hdac_i915.c +++ b/sound/hda/hdac_i915.c @@ -22,7 +22,14 @@ #include #include -static struct drm_audio_component *hdac_acomp; +static void hdac_acomp_release(struct device *dev, void *res) +{ +} + +static struct drm_audio_component *hdac_get_acomp(struct device *dev) +{ + return devres_find(dev, hdac_acomp_release, NULL, NULL); +} /** * snd_hdac_set_codec_wakeup - Enable / disable HDMI/DP codec wakeup @@ -262,7 +269,7 @@ EXPORT_SYMBOL_GPL(snd_hdac_acomp_get_eld); static int hdac_component_master_bind(struct device *dev) { - struct drm_audio_component *acomp = hdac_acomp; + struct drm_audio_component *acomp = hdac_get_acomp(dev); int ret; ret = component_bind_all(dev, acomp); @@ -294,7 +301,7 @@ out_unbind: static void hdac_component_master_unbind(struct device *dev) { - struct drm_audio_component *acomp = hdac_acomp; + struct drm_audio_component *acomp = hdac_get_acomp(dev); module_put(acomp->ops->owner); component_unbind_all(dev, acomp); @@ -314,6 +321,7 @@ static int hdac_component_master_match(struct device *dev, void *data) /** * snd_hdac_i915_register_notifier - Register i915 audio component ops + * @bus: HDA core bus * @aops: i915 audio component ops * * This function is supposed to be used only by a HD-audio controller @@ -323,12 +331,13 @@ static int hdac_component_master_match(struct device *dev, void *data) * * Returns zero for success or a negative error code. */ -int snd_hdac_i915_register_notifier(const struct drm_audio_component_audio_ops *aops) +int snd_hdac_i915_register_notifier(struct hdac_bus *bus, + const struct drm_audio_component_audio_ops *aops) { - if (!hdac_acomp) + if (!bus->audio_component) return -ENODEV; - hdac_acomp->audio_ops = aops; + bus->audio_component->audio_ops = aops; return 0; } EXPORT_SYMBOL_GPL(snd_hdac_i915_register_notifier); @@ -365,18 +374,19 @@ int snd_hdac_i915_init(struct hdac_bus *bus) struct drm_audio_component *acomp; int ret; - if (WARN_ON(hdac_acomp)) + if (WARN_ON(hdac_get_acomp(dev))) return -EBUSY; if (!i915_gfx_present()) return -ENODEV; - i915_acomp = kzalloc(sizeof(*i915_acomp), GFP_KERNEL); + i915_acomp = devres_alloc(hdac_acomp_release, sizeof(*i915_acomp), + GFP_KERNEL); if (!i915_acomp) return -ENOMEM; acomp = &i915_acomp->base; bus->audio_component = acomp; - hdac_acomp = acomp; + devres_add(dev, acomp); component_match_add(dev, &match, hdac_component_master_match, bus); ret = component_master_add_with_match(dev, &hdac_component_master_ops, @@ -400,9 +410,8 @@ int snd_hdac_i915_init(struct hdac_bus *bus) out_master_del: component_master_del(dev, &hdac_component_master_ops); out_err: - kfree(acomp); bus->audio_component = NULL; - hdac_acomp = NULL; + devres_destroy(dev, hdac_acomp_release, NULL, NULL); dev_info(dev, "failed to add i915 component master (%d)\n", ret); return ret; @@ -434,9 +443,8 @@ int snd_hdac_i915_exit(struct hdac_bus *bus) component_master_del(dev, &hdac_component_master_ops); - kfree(acomp); bus->audio_component = NULL; - hdac_acomp = NULL; + devres_destroy(dev, hdac_acomp_release, NULL, NULL); return 0; } diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index c0847017114c..bf174a013f2d 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -2288,7 +2288,7 @@ static void generic_hdmi_free(struct hda_codec *codec) int pin_idx, pcm_idx; if (codec_has_acomp(codec)) - snd_hdac_i915_register_notifier(NULL); + snd_hdac_i915_register_notifier(&codec->bus->core, NULL); for (pin_idx = 0; pin_idx < spec->num_pins; pin_idx++) { struct hdmi_spec_per_pin *per_pin = get_pin(spec, pin_idx); @@ -2518,7 +2518,8 @@ static void register_i915_notifier(struct hda_codec *codec) */ wmb(); spec->drm_audio_ops.pin_eld_notify = intel_pin_eld_notify; - snd_hdac_i915_register_notifier(&spec->drm_audio_ops); + snd_hdac_i915_register_notifier(&codec->bus->core, + &spec->drm_audio_ops); } /* setup_stream ops override for HSW+ */ diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c index 460075475f20..2b7c33db4ded 100644 --- a/sound/soc/codecs/hdac_hdmi.c +++ b/sound/soc/codecs/hdac_hdmi.c @@ -1812,7 +1812,7 @@ static int hdmi_codec_probe(struct snd_soc_component *component) return ret; aops.audio_ptr = hdev; - ret = snd_hdac_i915_register_notifier(&aops); + ret = snd_hdac_i915_register_notifier(hdev->bus, &aops); if (ret < 0) { dev_err(&hdev->dev, "notifier register failed: err: %d\n", ret); return ret; -- cgit v1.2.3 From a57942bfdd61b46df94021c9c33b8faaae5b65e1 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 11 Jul 2018 16:23:16 +0200 Subject: ALSA: hda: Make audio component support more generic This is the final step for more generic support of DRM audio component. The generic audio component code is now moved to its own file, and the symbols are renamed from snd_hac_i915_* to snd_hdac_acomp_*, respectively. The generic code is enabled via the new kconfig, CONFIG_SND_HDA_COMPONENT, while CONFIG_SND_HDA_I915 is kept as the super-class. Along with the split, three new callbacks are added to audio_ops: pin2port is for providing the conversion between the pin number and the widget id, and master_bind/master_unbin are called at binding / unbinding the master component, respectively. All these are optional, but used in i915 implementation and also other later implementations. A note about the new snd_hdac_acomp_init() function: there is a slight difference between this and the old snd_hdac_i915_init(). The latter (still) synchronizes with the master component binding, i.e. it assures that the relevant DRM component gets bound when it returns, or gives a negative error. Meanwhile the new function doesn't synchronize but just leaves as is. It's the responsibility by the caller's side to synchronize, or the caller may accept the asynchronous binding on the fly. v1->v2: Fix missing NULL check in master_bind/unbind Signed-off-by: Takashi Iwai --- drivers/gpu/drm/i915/Kconfig | 1 + include/drm/drm_audio_component.h | 23 +++ include/sound/hda_component.h | 61 +++++++ include/sound/hda_i915.h | 39 +---- sound/hda/Kconfig | 7 +- sound/hda/Makefile | 1 + sound/hda/hdac_component.c | 335 +++++++++++++++++++++++++++++++++++++ sound/hda/hdac_i915.c | 343 ++------------------------------------ sound/pci/hda/patch_hdmi.c | 50 ++++-- sound/soc/codecs/hdac_hdmi.c | 8 +- 10 files changed, 486 insertions(+), 382 deletions(-) create mode 100644 include/sound/hda_component.h create mode 100644 sound/hda/hdac_component.c (limited to 'include') diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig index dfd95889f4b7..5c607f2c707b 100644 --- a/drivers/gpu/drm/i915/Kconfig +++ b/drivers/gpu/drm/i915/Kconfig @@ -23,6 +23,7 @@ config DRM_I915 select SYNC_FILE select IOSF_MBI select CRC32 + select SND_HDA_I915 if SND_HDA_CORE help Choose this option if you have a system that has "Intel Graphics Media Accelerator" or "HD Graphics" integrated graphics, diff --git a/include/drm/drm_audio_component.h b/include/drm/drm_audio_component.h index e85689f212c2..4923b00328c1 100644 --- a/include/drm/drm_audio_component.h +++ b/include/drm/drm_audio_component.h @@ -4,6 +4,8 @@ #ifndef _DRM_AUDIO_COMPONENT_H_ #define _DRM_AUDIO_COMPONENT_H_ +struct drm_audio_component; + /** * struct drm_audio_component_ops - Ops implemented by DRM driver, called by hda driver */ @@ -72,6 +74,27 @@ struct drm_audio_component_audio_ops { * mode). */ void (*pin_eld_notify)(void *audio_ptr, int port, int pipe); + /** + * @pin2port: Check and convert from pin node to port number + * + * Called by HDA driver to check and convert from the pin widget node + * number to a port number in the graphics side. + */ + int (*pin2port)(void *audio_ptr, int pin); + /** + * @master_bind: (Optional) component master bind callback + * + * Called at binding master component, for HDA codec-specific + * handling of dynamic binding. + */ + int (*master_bind)(struct device *dev, struct drm_audio_component *); + /** + * @master_unbind: (Optional) component master unbind callback + * + * Called at unbinding master component, for HDA codec-specific + * handling of dynamic unbinding. + */ + void (*master_unbind)(struct device *dev, struct drm_audio_component *); }; /** diff --git a/include/sound/hda_component.h b/include/sound/hda_component.h new file mode 100644 index 000000000000..78626cde7081 --- /dev/null +++ b/include/sound/hda_component.h @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0 +// HD-Audio helpers to sync with DRM driver + +#ifndef __SOUND_HDA_COMPONENT_H +#define __SOUND_HDA_COMPONENT_H + +#include + +#ifdef CONFIG_SND_HDA_COMPONENT +int snd_hdac_set_codec_wakeup(struct hdac_bus *bus, bool enable); +int snd_hdac_display_power(struct hdac_bus *bus, bool enable); +int snd_hdac_sync_audio_rate(struct hdac_device *codec, hda_nid_t nid, + int dev_id, int rate); +int snd_hdac_acomp_get_eld(struct hdac_device *codec, hda_nid_t nid, int dev_id, + bool *audio_enabled, char *buffer, int max_bytes); +int snd_hdac_acomp_init(struct hdac_bus *bus, + const struct drm_audio_component_audio_ops *aops, + int (*match_master)(struct device *, void *), + size_t extra_size); +int snd_hdac_acomp_exit(struct hdac_bus *bus); +int snd_hdac_acomp_register_notifier(struct hdac_bus *bus, + const struct drm_audio_component_audio_ops *ops); +#else +static inline int snd_hdac_set_codec_wakeup(struct hdac_bus *bus, bool enable) +{ + return 0; +} +static inline int snd_hdac_display_power(struct hdac_bus *bus, bool enable) +{ + return 0; +} +static inline int snd_hdac_sync_audio_rate(struct hdac_device *codec, + hda_nid_t nid, int dev_id, int rate) +{ + return 0; +} +static inline int snd_hdac_acomp_get_eld(struct hdac_device *codec, hda_nid_t nid, + int dev_id, bool *audio_enabled, + char *buffer, int max_bytes) +{ + return -ENODEV; +} +static inline int snd_hdac_acomp_init(struct hdac_bus *bus, + const struct drm_audio_component_audio_ops *aops, + int (*match_master)(struct device *, void *), + size_t extra_size) +{ + return -ENODEV; +} +static inline int snd_hdac_acomp_exit(struct hdac_bus *bus) +{ + return 0; +} +static inline int snd_hdac_acomp_register_notifier(struct hdac_bus *bus, + const struct drm_audio_component_audio_ops *ops) +{ + return -ENODEV; +} +#endif + +#endif /* __SOUND_HDA_COMPONENT_H */ diff --git a/include/sound/hda_i915.h b/include/sound/hda_i915.h index 648263791559..6b79614a893b 100644 --- a/include/sound/hda_i915.h +++ b/include/sound/hda_i915.h @@ -5,56 +5,23 @@ #ifndef __SOUND_HDA_I915_H #define __SOUND_HDA_I915_H -#include +#include "hda_component.h" #ifdef CONFIG_SND_HDA_I915 -int snd_hdac_set_codec_wakeup(struct hdac_bus *bus, bool enable); -int snd_hdac_display_power(struct hdac_bus *bus, bool enable); void snd_hdac_i915_set_bclk(struct hdac_bus *bus); -int snd_hdac_sync_audio_rate(struct hdac_device *codec, hda_nid_t nid, - int dev_id, int rate); -int snd_hdac_acomp_get_eld(struct hdac_device *codec, hda_nid_t nid, int dev_id, - bool *audio_enabled, char *buffer, int max_bytes); int snd_hdac_i915_init(struct hdac_bus *bus); -int snd_hdac_i915_exit(struct hdac_bus *bus); -int snd_hdac_i915_register_notifier(struct hdac_bus *bus, - const struct drm_audio_component_audio_ops *ops); #else -static inline int snd_hdac_set_codec_wakeup(struct hdac_bus *bus, bool enable) -{ - return 0; -} -static inline int snd_hdac_display_power(struct hdac_bus *bus, bool enable) -{ - return 0; -} static inline void snd_hdac_i915_set_bclk(struct hdac_bus *bus) { } -static inline int snd_hdac_sync_audio_rate(struct hdac_device *codec, - hda_nid_t nid, int dev_id, int rate) -{ - return 0; -} -static inline int snd_hdac_acomp_get_eld(struct hdac_device *codec, hda_nid_t nid, - int dev_id, bool *audio_enabled, - char *buffer, int max_bytes) -{ - return -ENODEV; -} static inline int snd_hdac_i915_init(struct hdac_bus *bus) { return -ENODEV; } +#endif static inline int snd_hdac_i915_exit(struct hdac_bus *bus) { - return 0; + return snd_hdac_acomp_exit(bus); } -static inline int snd_hdac_i915_register_notifier(struct hdac_bus *bus, - const struct drm_audio_component_audio_ops *ops) -{ - return -ENODEV; -} -#endif #endif /* __SOUND_HDA_I915_H */ diff --git a/sound/hda/Kconfig b/sound/hda/Kconfig index 3129546398d0..2d90e11b3eaa 100644 --- a/sound/hda/Kconfig +++ b/sound/hda/Kconfig @@ -5,11 +5,12 @@ config SND_HDA_CORE config SND_HDA_DSP_LOADER bool +config SND_HDA_COMPONENT + bool + config SND_HDA_I915 bool - default y - depends on DRM_I915 - depends on SND_HDA_CORE + select SND_HDA_COMPONENT config SND_HDA_EXT_CORE tristate diff --git a/sound/hda/Makefile b/sound/hda/Makefile index e4e726f2ce98..2160202e2dc1 100644 --- a/sound/hda/Makefile +++ b/sound/hda/Makefile @@ -6,6 +6,7 @@ snd-hda-core-objs += trace.o CFLAGS_trace.o := -I$(src) # for sync with i915 gfx driver +snd-hda-core-$(CONFIG_SND_HDA_COMPONENT) += hdac_component.o snd-hda-core-$(CONFIG_SND_HDA_I915) += hdac_i915.o obj-$(CONFIG_SND_HDA_CORE) += snd-hda-core.o diff --git a/sound/hda/hdac_component.c b/sound/hda/hdac_component.c new file mode 100644 index 000000000000..6e46a9c73aed --- /dev/null +++ b/sound/hda/hdac_component.c @@ -0,0 +1,335 @@ +// SPDX-License-Identifier: GPL-2.0 +// hdac_component.c - routines for sync between HD-A core and DRM driver + +#include +#include +#include +#include +#include +#include +#include +#include + +static void hdac_acomp_release(struct device *dev, void *res) +{ +} + +static struct drm_audio_component *hdac_get_acomp(struct device *dev) +{ + return devres_find(dev, hdac_acomp_release, NULL, NULL); +} + +/** + * snd_hdac_set_codec_wakeup - Enable / disable HDMI/DP codec wakeup + * @bus: HDA core bus + * @enable: enable or disable the wakeup + * + * This function is supposed to be used only by a HD-audio controller + * driver that needs the interaction with graphics driver. + * + * This function should be called during the chip reset, also called at + * resume for updating STATESTS register read. + * + * Returns zero for success or a negative error code. + */ +int snd_hdac_set_codec_wakeup(struct hdac_bus *bus, bool enable) +{ + struct drm_audio_component *acomp = bus->audio_component; + + if (!acomp || !acomp->ops) + return -ENODEV; + + if (!acomp->ops->codec_wake_override) + return 0; + + dev_dbg(bus->dev, "%s codec wakeup\n", + enable ? "enable" : "disable"); + + acomp->ops->codec_wake_override(acomp->dev, enable); + + return 0; +} +EXPORT_SYMBOL_GPL(snd_hdac_set_codec_wakeup); + +/** + * snd_hdac_display_power - Power up / down the power refcount + * @bus: HDA core bus + * @enable: power up or down + * + * This function is supposed to be used only by a HD-audio controller + * driver that needs the interaction with graphics driver. + * + * This function manages a refcount and calls the get_power() and + * put_power() ops accordingly, toggling the codec wakeup, too. + * + * Returns zero for success or a negative error code. + */ +int snd_hdac_display_power(struct hdac_bus *bus, bool enable) +{ + struct drm_audio_component *acomp = bus->audio_component; + + if (!acomp || !acomp->ops) + return -ENODEV; + + dev_dbg(bus->dev, "display power %s\n", + enable ? "enable" : "disable"); + + if (enable) { + if (!bus->drm_power_refcount++) { + if (acomp->ops->get_power) + acomp->ops->get_power(acomp->dev); + snd_hdac_set_codec_wakeup(bus, true); + snd_hdac_set_codec_wakeup(bus, false); + } + } else { + WARN_ON(!bus->drm_power_refcount); + if (!--bus->drm_power_refcount) + if (acomp->ops->put_power) + acomp->ops->put_power(acomp->dev); + } + + return 0; +} +EXPORT_SYMBOL_GPL(snd_hdac_display_power); + +/** + * snd_hdac_sync_audio_rate - Set N/CTS based on the sample rate + * @codec: HDA codec + * @nid: the pin widget NID + * @dev_id: device identifier + * @rate: the sample rate to set + * + * This function is supposed to be used only by a HD-audio controller + * driver that needs the interaction with graphics driver. + * + * This function sets N/CTS value based on the given sample rate. + * Returns zero for success, or a negative error code. + */ +int snd_hdac_sync_audio_rate(struct hdac_device *codec, hda_nid_t nid, + int dev_id, int rate) +{ + struct hdac_bus *bus = codec->bus; + struct drm_audio_component *acomp = bus->audio_component; + int port, pipe; + + if (!acomp || !acomp->ops || !acomp->ops->sync_audio_rate) + return -ENODEV; + port = nid; + if (acomp->audio_ops && acomp->audio_ops->pin2port) { + port = acomp->audio_ops->pin2port(codec, nid); + if (port < 0) + return -EINVAL; + } + pipe = dev_id; + return acomp->ops->sync_audio_rate(acomp->dev, port, pipe, rate); +} +EXPORT_SYMBOL_GPL(snd_hdac_sync_audio_rate); + +/** + * snd_hdac_acomp_get_eld - Get the audio state and ELD via component + * @codec: HDA codec + * @nid: the pin widget NID + * @dev_id: device identifier + * @audio_enabled: the pointer to store the current audio state + * @buffer: the buffer pointer to store ELD bytes + * @max_bytes: the max bytes to be stored on @buffer + * + * This function is supposed to be used only by a HD-audio controller + * driver that needs the interaction with graphics driver. + * + * This function queries the current state of the audio on the given + * digital port and fetches the ELD bytes onto the given buffer. + * It returns the number of bytes for the total ELD data, zero for + * invalid ELD, or a negative error code. + * + * The return size is the total bytes required for the whole ELD bytes, + * thus it may be over @max_bytes. If it's over @max_bytes, it implies + * that only a part of ELD bytes have been fetched. + */ +int snd_hdac_acomp_get_eld(struct hdac_device *codec, hda_nid_t nid, int dev_id, + bool *audio_enabled, char *buffer, int max_bytes) +{ + struct hdac_bus *bus = codec->bus; + struct drm_audio_component *acomp = bus->audio_component; + int port, pipe; + + if (!acomp || !acomp->ops || !acomp->ops->get_eld) + return -ENODEV; + + port = nid; + if (acomp->audio_ops && acomp->audio_ops->pin2port) { + port = acomp->audio_ops->pin2port(codec, nid); + if (port < 0) + return -EINVAL; + } + pipe = dev_id; + return acomp->ops->get_eld(acomp->dev, port, pipe, audio_enabled, + buffer, max_bytes); +} +EXPORT_SYMBOL_GPL(snd_hdac_acomp_get_eld); + +static int hdac_component_master_bind(struct device *dev) +{ + struct drm_audio_component *acomp = hdac_get_acomp(dev); + int ret; + + if (WARN_ON(!acomp)) + return -EINVAL; + + ret = component_bind_all(dev, acomp); + if (ret < 0) + return ret; + + if (WARN_ON(!(acomp->dev && acomp->ops))) { + ret = -EINVAL; + goto out_unbind; + } + + /* pin the module to avoid dynamic unbinding, but only if given */ + if (!try_module_get(acomp->ops->owner)) { + ret = -ENODEV; + goto out_unbind; + } + + if (acomp->audio_ops && acomp->audio_ops->master_bind) { + ret = acomp->audio_ops->master_bind(dev, acomp); + if (ret < 0) + goto module_put; + } + + return 0; + + module_put: + module_put(acomp->ops->owner); +out_unbind: + component_unbind_all(dev, acomp); + + return ret; +} + +static void hdac_component_master_unbind(struct device *dev) +{ + struct drm_audio_component *acomp = hdac_get_acomp(dev); + + if (acomp->audio_ops && acomp->audio_ops->master_unbind) + acomp->audio_ops->master_unbind(dev, acomp); + module_put(acomp->ops->owner); + component_unbind_all(dev, acomp); + WARN_ON(acomp->ops || acomp->dev); +} + +static const struct component_master_ops hdac_component_master_ops = { + .bind = hdac_component_master_bind, + .unbind = hdac_component_master_unbind, +}; + +/** + * snd_hdac_acomp_register_notifier - Register audio component ops + * @bus: HDA core bus + * @aops: audio component ops + * + * This function is supposed to be used only by a HD-audio controller + * driver that needs the interaction with graphics driver. + * + * This function sets the given ops to be called by the graphics driver. + * + * Returns zero for success or a negative error code. + */ +int snd_hdac_acomp_register_notifier(struct hdac_bus *bus, + const struct drm_audio_component_audio_ops *aops) +{ + if (!bus->audio_component) + return -ENODEV; + + bus->audio_component->audio_ops = aops; + return 0; +} +EXPORT_SYMBOL_GPL(snd_hdac_acomp_register_notifier); + +/** + * snd_hdac_acomp_init - Initialize audio component + * @bus: HDA core bus + * @match_master: match function for finding components + * @extra_size: Extra bytes to allocate + * + * This function is supposed to be used only by a HD-audio controller + * driver that needs the interaction with graphics driver. + * + * This function initializes and sets up the audio component to communicate + * with graphics driver. + * + * Unlike snd_hdac_i915_init(), this function doesn't synchronize with the + * binding with the DRM component. Each caller needs to sync via master_bind + * audio_ops. + * + * Returns zero for success or a negative error code. + */ +int snd_hdac_acomp_init(struct hdac_bus *bus, + const struct drm_audio_component_audio_ops *aops, + int (*match_master)(struct device *, void *), + size_t extra_size) +{ + struct component_match *match = NULL; + struct device *dev = bus->dev; + struct drm_audio_component *acomp; + int ret; + + if (WARN_ON(hdac_get_acomp(dev))) + return -EBUSY; + + acomp = devres_alloc(hdac_acomp_release, sizeof(*acomp) + extra_size, + GFP_KERNEL); + if (!acomp) + return -ENOMEM; + acomp->audio_ops = aops; + bus->audio_component = acomp; + devres_add(dev, acomp); + + component_match_add(dev, &match, match_master, bus); + ret = component_master_add_with_match(dev, &hdac_component_master_ops, + match); + if (ret < 0) + goto out_err; + + return 0; + +out_err: + bus->audio_component = NULL; + devres_destroy(dev, hdac_acomp_release, NULL, NULL); + dev_info(dev, "failed to add audio component master (%d)\n", ret); + + return ret; +} +EXPORT_SYMBOL_GPL(snd_hdac_acomp_init); + +/** + * snd_hdac_acomp_exit - Finalize audio component + * @bus: HDA core bus + * + * This function is supposed to be used only by a HD-audio controller + * driver that needs the interaction with graphics driver. + * + * This function releases the audio component that has been used. + * + * Returns zero for success or a negative error code. + */ +int snd_hdac_acomp_exit(struct hdac_bus *bus) +{ + struct device *dev = bus->dev; + struct drm_audio_component *acomp = bus->audio_component; + + if (!acomp) + return 0; + + WARN_ON(bus->drm_power_refcount); + if (bus->drm_power_refcount > 0 && acomp->ops) + acomp->ops->put_power(acomp->dev); + + component_master_del(dev, &hdac_component_master_ops); + + bus->audio_component = NULL; + devres_destroy(dev, hdac_acomp_release, NULL, NULL); + + return 0; +} +EXPORT_SYMBOL_GPL(snd_hdac_acomp_exit); diff --git a/sound/hda/hdac_i915.c b/sound/hda/hdac_i915.c index 861b77bbc7df..8f2aa8bc1185 100644 --- a/sound/hda/hdac_i915.c +++ b/sound/hda/hdac_i915.c @@ -15,96 +15,11 @@ #include #include #include -#include -#include #include #include #include #include -static void hdac_acomp_release(struct device *dev, void *res) -{ -} - -static struct drm_audio_component *hdac_get_acomp(struct device *dev) -{ - return devres_find(dev, hdac_acomp_release, NULL, NULL); -} - -/** - * snd_hdac_set_codec_wakeup - Enable / disable HDMI/DP codec wakeup - * @bus: HDA core bus - * @enable: enable or disable the wakeup - * - * This function is supposed to be used only by a HD-audio controller - * driver that needs the interaction with i915 graphics. - * - * This function should be called during the chip reset, also called at - * resume for updating STATESTS register read. - * - * Returns zero for success or a negative error code. - */ -int snd_hdac_set_codec_wakeup(struct hdac_bus *bus, bool enable) -{ - struct drm_audio_component *acomp = bus->audio_component; - - if (!acomp || !acomp->ops) - return -ENODEV; - - if (!acomp->ops->codec_wake_override) { - dev_warn(bus->dev, - "Invalid codec wake callback\n"); - return 0; - } - - dev_dbg(bus->dev, "%s codec wakeup\n", - enable ? "enable" : "disable"); - - acomp->ops->codec_wake_override(acomp->dev, enable); - - return 0; -} -EXPORT_SYMBOL_GPL(snd_hdac_set_codec_wakeup); - -/** - * snd_hdac_display_power - Power up / down the power refcount - * @bus: HDA core bus - * @enable: power up or down - * - * This function is supposed to be used only by a HD-audio controller - * driver that needs the interaction with i915 graphics. - * - * This function manages a refcount and calls the i915 get_power() and - * put_power() ops accordingly, toggling the codec wakeup, too. - * - * Returns zero for success or a negative error code. - */ -int snd_hdac_display_power(struct hdac_bus *bus, bool enable) -{ - struct drm_audio_component *acomp = bus->audio_component; - - if (!acomp || !acomp->ops) - return -ENODEV; - - dev_dbg(bus->dev, "display power %s\n", - enable ? "enable" : "disable"); - - if (enable) { - if (!bus->drm_power_refcount++) { - acomp->ops->get_power(acomp->dev); - snd_hdac_set_codec_wakeup(bus, true); - snd_hdac_set_codec_wakeup(bus, false); - } - } else { - WARN_ON(!bus->drm_power_refcount); - if (!--bus->drm_power_refcount) - acomp->ops->put_power(acomp->dev); - } - - return 0; -} -EXPORT_SYMBOL_GPL(snd_hdac_display_power); - #define CONTROLLER_IN_GPU(pci) (((pci)->device == 0x0a0c) || \ ((pci)->device == 0x0c0c) || \ ((pci)->device == 0x0d0c) || \ @@ -165,183 +80,11 @@ void snd_hdac_i915_set_bclk(struct hdac_bus *bus) } EXPORT_SYMBOL_GPL(snd_hdac_i915_set_bclk); -/* There is a fixed mapping between audio pin node and display port. - * on SNB, IVY, HSW, BSW, SKL, BXT, KBL: - * Pin Widget 5 - PORT B (port = 1 in i915 driver) - * Pin Widget 6 - PORT C (port = 2 in i915 driver) - * Pin Widget 7 - PORT D (port = 3 in i915 driver) - * - * on VLV, ILK: - * Pin Widget 4 - PORT B (port = 1 in i915 driver) - * Pin Widget 5 - PORT C (port = 2 in i915 driver) - * Pin Widget 6 - PORT D (port = 3 in i915 driver) - */ -static int pin2port(struct hdac_device *codec, hda_nid_t pin_nid) -{ - int base_nid; - - switch (codec->vendor_id) { - case 0x80860054: /* ILK */ - case 0x80862804: /* ILK */ - case 0x80862882: /* VLV */ - base_nid = 3; - break; - default: - base_nid = 4; - break; - } - - if (WARN_ON(pin_nid <= base_nid || pin_nid > base_nid + 3)) - return -1; - return pin_nid - base_nid; -} - -/** - * snd_hdac_sync_audio_rate - Set N/CTS based on the sample rate - * @codec: HDA codec - * @nid: the pin widget NID - * @dev_id: device identifier - * @rate: the sample rate to set - * - * This function is supposed to be used only by a HD-audio controller - * driver that needs the interaction with i915 graphics. - * - * This function sets N/CTS value based on the given sample rate. - * Returns zero for success, or a negative error code. - */ -int snd_hdac_sync_audio_rate(struct hdac_device *codec, hda_nid_t nid, - int dev_id, int rate) +static int i915_component_master_match(struct device *dev, void *data) { - struct hdac_bus *bus = codec->bus; - struct drm_audio_component *acomp = bus->audio_component; - int port, pipe; - - if (!acomp || !acomp->ops || !acomp->ops->sync_audio_rate) - return -ENODEV; - port = pin2port(codec, nid); - if (port < 0) - return -EINVAL; - pipe = dev_id; - return acomp->ops->sync_audio_rate(acomp->dev, port, pipe, rate); -} -EXPORT_SYMBOL_GPL(snd_hdac_sync_audio_rate); - -/** - * snd_hdac_acomp_get_eld - Get the audio state and ELD via component - * @codec: HDA codec - * @nid: the pin widget NID - * @dev_id: device identifier - * @audio_enabled: the pointer to store the current audio state - * @buffer: the buffer pointer to store ELD bytes - * @max_bytes: the max bytes to be stored on @buffer - * - * This function is supposed to be used only by a HD-audio controller - * driver that needs the interaction with i915 graphics. - * - * This function queries the current state of the audio on the given - * digital port and fetches the ELD bytes onto the given buffer. - * It returns the number of bytes for the total ELD data, zero for - * invalid ELD, or a negative error code. - * - * The return size is the total bytes required for the whole ELD bytes, - * thus it may be over @max_bytes. If it's over @max_bytes, it implies - * that only a part of ELD bytes have been fetched. - */ -int snd_hdac_acomp_get_eld(struct hdac_device *codec, hda_nid_t nid, int dev_id, - bool *audio_enabled, char *buffer, int max_bytes) -{ - struct hdac_bus *bus = codec->bus; - struct drm_audio_component *acomp = bus->audio_component; - int port, pipe; - - if (!acomp || !acomp->ops || !acomp->ops->get_eld) - return -ENODEV; - - port = pin2port(codec, nid); - if (port < 0) - return -EINVAL; - - pipe = dev_id; - return acomp->ops->get_eld(acomp->dev, port, pipe, audio_enabled, - buffer, max_bytes); -} -EXPORT_SYMBOL_GPL(snd_hdac_acomp_get_eld); - -static int hdac_component_master_bind(struct device *dev) -{ - struct drm_audio_component *acomp = hdac_get_acomp(dev); - int ret; - - ret = component_bind_all(dev, acomp); - if (ret < 0) - return ret; - - if (WARN_ON(!(acomp->dev && acomp->ops && acomp->ops->get_power && - acomp->ops->put_power && acomp->ops->get_cdclk_freq))) { - ret = -EINVAL; - goto out_unbind; - } - - /* - * Atm, we don't support dynamic unbinding initiated by the child - * component, so pin its containing module until we unbind. - */ - if (!try_module_get(acomp->ops->owner)) { - ret = -ENODEV; - goto out_unbind; - } - - return 0; - -out_unbind: - component_unbind_all(dev, acomp); - - return ret; -} - -static void hdac_component_master_unbind(struct device *dev) -{ - struct drm_audio_component *acomp = hdac_get_acomp(dev); - - module_put(acomp->ops->owner); - component_unbind_all(dev, acomp); - WARN_ON(acomp->ops || acomp->dev); -} - -static const struct component_master_ops hdac_component_master_ops = { - .bind = hdac_component_master_bind, - .unbind = hdac_component_master_unbind, -}; - -static int hdac_component_master_match(struct device *dev, void *data) -{ - /* i915 is the only supported component */ return !strcmp(dev->driver->name, "i915"); } -/** - * snd_hdac_i915_register_notifier - Register i915 audio component ops - * @bus: HDA core bus - * @aops: i915 audio component ops - * - * This function is supposed to be used only by a HD-audio controller - * driver that needs the interaction with i915 graphics. - * - * This function sets the given ops to be called by the i915 graphics driver. - * - * Returns zero for success or a negative error code. - */ -int snd_hdac_i915_register_notifier(struct hdac_bus *bus, - const struct drm_audio_component_audio_ops *aops) -{ - if (!bus->audio_component) - return -ENODEV; - - bus->audio_component->audio_ops = aops; - return 0; -} -EXPORT_SYMBOL_GPL(snd_hdac_i915_register_notifier); - /* check whether intel graphics is present */ static bool i915_gfx_present(void) { @@ -368,84 +111,26 @@ static bool i915_gfx_present(void) */ int snd_hdac_i915_init(struct hdac_bus *bus) { - struct component_match *match = NULL; - struct device *dev = bus->dev; - struct i915_audio_component *i915_acomp; struct drm_audio_component *acomp; - int ret; - - if (WARN_ON(hdac_get_acomp(dev))) - return -EBUSY; + int err; if (!i915_gfx_present()) return -ENODEV; - i915_acomp = devres_alloc(hdac_acomp_release, sizeof(*i915_acomp), - GFP_KERNEL); - if (!i915_acomp) - return -ENOMEM; - acomp = &i915_acomp->base; - bus->audio_component = acomp; - devres_add(dev, acomp); - - component_match_add(dev, &match, hdac_component_master_match, bus); - ret = component_master_add_with_match(dev, &hdac_component_master_ops, - match); - if (ret < 0) - goto out_err; - - /* - * Atm, we don't support deferring the component binding, so make sure - * i915 is loaded and that the binding successfully completes. - */ - request_module("i915"); - + err = snd_hdac_acomp_init(bus, NULL, + i915_component_master_match, + sizeof(struct i915_audio_component) - sizeof(*acomp)); + if (err < 0) + return err; + acomp = bus->audio_component; + if (!acomp) + return -ENODEV; + if (!acomp->ops) + request_module("i915"); if (!acomp->ops) { - ret = -ENODEV; - goto out_master_del; + snd_hdac_acomp_exit(bus); + return -ENODEV; } - dev_dbg(dev, "bound to i915 component master\n"); - return 0; -out_master_del: - component_master_del(dev, &hdac_component_master_ops); -out_err: - bus->audio_component = NULL; - devres_destroy(dev, hdac_acomp_release, NULL, NULL); - dev_info(dev, "failed to add i915 component master (%d)\n", ret); - - return ret; } EXPORT_SYMBOL_GPL(snd_hdac_i915_init); - -/** - * snd_hdac_i915_exit - Finalize i915 audio component - * @bus: HDA core bus - * - * This function is supposed to be used only by a HD-audio controller - * driver that needs the interaction with i915 graphics. - * - * This function releases the i915 audio component that has been used. - * - * Returns zero for success or a negative error code. - */ -int snd_hdac_i915_exit(struct hdac_bus *bus) -{ - struct device *dev = bus->dev; - struct drm_audio_component *acomp = bus->audio_component; - - if (!acomp) - return 0; - - WARN_ON(bus->drm_power_refcount); - if (bus->drm_power_refcount > 0 && acomp->ops) - acomp->ops->put_power(acomp->dev); - - component_master_del(dev, &hdac_component_master_ops); - - bus->audio_component = NULL; - devres_destroy(dev, hdac_acomp_release, NULL, NULL); - - return 0; -} -EXPORT_SYMBOL_GPL(snd_hdac_i915_exit); diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index bf174a013f2d..1de5491fb9bf 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -183,7 +183,7 @@ struct hdmi_spec { hda_nid_t vendor_nid; }; -#ifdef CONFIG_SND_HDA_I915 +#ifdef CONFIG_SND_HDA_COMPONENT static inline bool codec_has_acomp(struct hda_codec *codec) { struct hdmi_spec *spec = codec->spec; @@ -2288,7 +2288,7 @@ static void generic_hdmi_free(struct hda_codec *codec) int pin_idx, pcm_idx; if (codec_has_acomp(codec)) - snd_hdac_i915_register_notifier(&codec->bus->core, NULL); + snd_hdac_acomp_register_notifier(&codec->bus->core, NULL); for (pin_idx = 0; pin_idx < spec->num_pins; pin_idx++) { struct hdmi_spec_per_pin *per_pin = get_pin(spec, pin_idx); @@ -2471,6 +2471,38 @@ static void haswell_set_power_state(struct hda_codec *codec, hda_nid_t fg, snd_hda_codec_set_power_to_all(codec, fg, power_state); } +/* There is a fixed mapping between audio pin node and display port. + * on SNB, IVY, HSW, BSW, SKL, BXT, KBL: + * Pin Widget 5 - PORT B (port = 1 in i915 driver) + * Pin Widget 6 - PORT C (port = 2 in i915 driver) + * Pin Widget 7 - PORT D (port = 3 in i915 driver) + * + * on VLV, ILK: + * Pin Widget 4 - PORT B (port = 1 in i915 driver) + * Pin Widget 5 - PORT C (port = 2 in i915 driver) + * Pin Widget 6 - PORT D (port = 3 in i915 driver) + */ +static int intel_base_nid(struct hda_codec *codec) +{ + switch (codec->core.vendor_id) { + case 0x80860054: /* ILK */ + case 0x80862804: /* ILK */ + case 0x80862882: /* VLV */ + return 4; + default: + return 5; + } +} + +static int intel_pin2port(void *audio_ptr, int pin_nid) +{ + int base_nid = intel_base_nid(audio_ptr); + + if (WARN_ON(pin_nid < base_nid || pin_nid >= base_nid + 3)) + return -1; + return pin_nid - base_nid + 1; /* intel port is 1-based */ +} + static void intel_pin_eld_notify(void *audio_ptr, int port, int pipe) { struct hda_codec *codec = audio_ptr; @@ -2481,16 +2513,7 @@ static void intel_pin_eld_notify(void *audio_ptr, int port, int pipe) if (port < 1 || port > 3) return; - switch (codec->core.vendor_id) { - case 0x80860054: /* ILK */ - case 0x80862804: /* ILK */ - case 0x80862882: /* VLV */ - pin_nid = port + 0x03; - break; - default: - pin_nid = port + 0x04; - break; - } + pin_nid = port + intel_base_nid(codec) - 1; /* intel port is 1-based */ /* skip notification during system suspend (but not in runtime PM); * the state will be updated at resume @@ -2517,8 +2540,9 @@ static void register_i915_notifier(struct hda_codec *codec) * We need make sure audio_ptr is really setup */ wmb(); + spec->drm_audio_ops.pin2port = intel_pin2port; spec->drm_audio_ops.pin_eld_notify = intel_pin_eld_notify; - snd_hdac_i915_register_notifier(&codec->bus->core, + snd_hdac_acomp_register_notifier(&codec->bus->core, &spec->drm_audio_ops); } diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c index 2b7c33db4ded..4748a9d5de3b 100644 --- a/sound/soc/codecs/hdac_hdmi.c +++ b/sound/soc/codecs/hdac_hdmi.c @@ -1530,6 +1530,11 @@ free_widgets: return ret; } +static int hdac_hdmi_pin2port(void *aptr, int pin) +{ + return pin - 4; /* map NID 0x05 -> port #1 */ +} + static void hdac_hdmi_eld_notify_cb(void *aptr, int port, int pipe) { struct hdac_device *hdev = aptr; @@ -1584,6 +1589,7 @@ static void hdac_hdmi_eld_notify_cb(void *aptr, int port, int pipe) } static struct drm_audio_component_audio_ops aops = { + .pin2port = hdac_hdmi_pin2port, .pin_eld_notify = hdac_hdmi_eld_notify_cb, }; @@ -1812,7 +1818,7 @@ static int hdmi_codec_probe(struct snd_soc_component *component) return ret; aops.audio_ptr = hdev; - ret = snd_hdac_i915_register_notifier(hdev->bus, &aops); + ret = snd_hdac_acomp_register_notifier(hdev->bus, &aops); if (ret < 0) { dev_err(&hdev->dev, "notifier register failed: err: %d\n", ret); return ret; -- cgit v1.2.3 From 2fe31e43124040a67495fa81f7ac67bc4c09ebc8 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Tue, 17 Jul 2018 21:48:10 +0200 Subject: hwmon: Add missing HWMON_T_LCRIT_ALARM define The enum hwmon_temp_lcrit_alarm exists, but the BIT definition is missing. Signed-off-by: Andrew Lunn Acked-by: Guenter Roeck Signed-off-by: David S. Miller --- include/linux/hwmon.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h index e5fd2707b6df..1b74ad11a5a4 100644 --- a/include/linux/hwmon.h +++ b/include/linux/hwmon.h @@ -93,6 +93,7 @@ enum hwmon_temp_attributes { #define HWMON_T_MIN_ALARM BIT(hwmon_temp_min_alarm) #define HWMON_T_MAX_ALARM BIT(hwmon_temp_max_alarm) #define HWMON_T_CRIT_ALARM BIT(hwmon_temp_crit_alarm) +#define HWMON_T_LCRIT_ALARM BIT(hwmon_temp_lcrit_alarm) #define HWMON_T_EMERGENCY_ALARM BIT(hwmon_temp_emergency_alarm) #define HWMON_T_FAULT BIT(hwmon_temp_fault) #define HWMON_T_OFFSET BIT(hwmon_temp_offset) -- cgit v1.2.3 From aa7f29b07c8702127124d0522e3cd46850cdbc41 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Tue, 17 Jul 2018 21:48:11 +0200 Subject: hwmon: Add support for power min, lcrit, min_alarm and lcrit_alarm Some sensors support reporting minimal and lower critical power, as well as alarms when these thresholds are reached. Add support for these attributes to the hwmon core. Signed-off-by: Andrew Lunn Acked-by: Guenter Roeck Signed-off-by: David S. Miller --- drivers/hwmon/hwmon.c | 4 ++++ include/linux/hwmon.h | 8 ++++++++ 2 files changed, 12 insertions(+) (limited to 'include') diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c index e88c01961948..33d51281272b 100644 --- a/drivers/hwmon/hwmon.c +++ b/drivers/hwmon/hwmon.c @@ -394,12 +394,16 @@ static const char * const hwmon_power_attr_templates[] = { [hwmon_power_cap_hyst] = "power%d_cap_hyst", [hwmon_power_cap_max] = "power%d_cap_max", [hwmon_power_cap_min] = "power%d_cap_min", + [hwmon_power_min] = "power%d_min", [hwmon_power_max] = "power%d_max", + [hwmon_power_lcrit] = "power%d_lcrit", [hwmon_power_crit] = "power%d_crit", [hwmon_power_label] = "power%d_label", [hwmon_power_alarm] = "power%d_alarm", [hwmon_power_cap_alarm] = "power%d_cap_alarm", + [hwmon_power_min_alarm] = "power%d_min_alarm", [hwmon_power_max_alarm] = "power%d_max_alarm", + [hwmon_power_lcrit_alarm] = "power%d_lcrit_alarm", [hwmon_power_crit_alarm] = "power%d_crit_alarm", }; diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h index 1b74ad11a5a4..b217101ca76e 100644 --- a/include/linux/hwmon.h +++ b/include/linux/hwmon.h @@ -188,12 +188,16 @@ enum hwmon_power_attributes { hwmon_power_cap_hyst, hwmon_power_cap_max, hwmon_power_cap_min, + hwmon_power_min, hwmon_power_max, hwmon_power_crit, + hwmon_power_lcrit, hwmon_power_label, hwmon_power_alarm, hwmon_power_cap_alarm, + hwmon_power_min_alarm, hwmon_power_max_alarm, + hwmon_power_lcrit_alarm, hwmon_power_crit_alarm, }; @@ -214,12 +218,16 @@ enum hwmon_power_attributes { #define HWMON_P_CAP_HYST BIT(hwmon_power_cap_hyst) #define HWMON_P_CAP_MAX BIT(hwmon_power_cap_max) #define HWMON_P_CAP_MIN BIT(hwmon_power_cap_min) +#define HWMON_P_MIN BIT(hwmon_power_min) #define HWMON_P_MAX BIT(hwmon_power_max) +#define HWMON_P_LCRIT BIT(hwmon_power_lcrit) #define HWMON_P_CRIT BIT(hwmon_power_crit) #define HWMON_P_LABEL BIT(hwmon_power_label) #define HWMON_P_ALARM BIT(hwmon_power_alarm) #define HWMON_P_CAP_ALARM BIT(hwmon_power_cap_alarm) +#define HWMON_P_MIN_ALARM BIT(hwmon_power_max_alarm) #define HWMON_P_MAX_ALARM BIT(hwmon_power_max_alarm) +#define HWMON_P_LCRIT_ALARM BIT(hwmon_power_lcrit_alarm) #define HWMON_P_CRIT_ALARM BIT(hwmon_power_crit_alarm) enum hwmon_energy_attributes { -- cgit v1.2.3 From dcb5d0fcaa1ddd0af9c18ef51e6b05e38a6cec71 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Tue, 17 Jul 2018 21:48:12 +0200 Subject: hwmon: Add helper to tell if a char is invalid in a name HWMON device names are not allowed to contain "-* \t\n". Add a helper which will return true if passed an invalid character. It can be used to massage a string into a hwmon compatible name by replacing invalid characters with '_'. Signed-off-by: Andrew Lunn Acked-by: Guenter Roeck Signed-off-by: David S. Miller --- include/linux/hwmon.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include') diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h index b217101ca76e..9493d4a388db 100644 --- a/include/linux/hwmon.h +++ b/include/linux/hwmon.h @@ -398,4 +398,27 @@ devm_hwmon_device_register_with_info(struct device *dev, void hwmon_device_unregister(struct device *dev); void devm_hwmon_device_unregister(struct device *dev); +/** + * hwmon_is_bad_char - Is the char invalid in a hwmon name + * @ch: the char to be considered + * + * hwmon_is_bad_char() can be used to determine if the given character + * may not be used in a hwmon name. + * + * Returns true if the char is invalid, false otherwise. + */ +static inline bool hwmon_is_bad_char(const char ch) +{ + switch (ch) { + case '-': + case '*': + case ' ': + case '\t': + case '\n': + return true; + default: + return false; + } +} + #endif -- cgit v1.2.3 From 1323061a018a7514287894a552c4ec2a5f0cb0cd Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Tue, 17 Jul 2018 21:48:13 +0200 Subject: net: phy: sfp: Add HWMON support for module sensors MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit SFP modules can contain a number of sensors. The EEPROM also contains recommended alarm and critical values for each sensor, and indications of if these have been exceeded. Export this information via HWMON. Currently temperature, VCC, bias current, transmit power, and possibly receiver power is supported. The sensors in the modules can either return calibrate or uncalibrated values. Uncalibrated values need to be manipulated, using coefficients provided in the SFP EEPROM. Uncalibrated receive power values require floating point maths in order to calibrate them. Performing this in the kernel is hard. So if the SFP module indicates it uses uncalibrated values, RX power is not made available. With this hwmon device, it is possible to view the sensor values using lm-sensors programs: in0: +3.29 V (crit min = +2.90 V, min = +3.00 V) (max = +3.60 V, crit max = +3.70 V) temp1: +33.0°C (low = -5.0°C, high = +80.0°C) (crit low = -10.0°C, crit = +85.0°C) power1: 1000.00 nW (max = 794.00 uW, min = 50.00 uW) ALARM (LCRIT) (lcrit = 40.00 uW, crit = 1000.00 uW) curr1: +0.00 A (crit min = +0.00 A, min = +0.00 A) ALARM (LCRIT, MIN) (max = +0.01 A, crit max = +0.01 A) The scaling sensors performs on the bias current is not particularly good. The raw values are more useful: curr1: curr1_input: 0.000 curr1_min: 0.002 curr1_max: 0.010 curr1_lcrit: 0.000 curr1_crit: 0.011 curr1_min_alarm: 1.000 curr1_max_alarm: 0.000 curr1_lcrit_alarm: 1.000 curr1_crit_alarm: 0.000 In order to keep the I2C overhead to a minimum, the constant values, such as limits and calibration coefficients are read once at module insertion time. Thus only reading *_input and *_alarm properties requires i2c read operations. Signed-off-by: Andrew Lunn Acked-by: Guenter Roeck Signed-off-by: David S. Miller --- drivers/net/phy/Kconfig | 1 + drivers/net/phy/sfp.c | 727 ++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/sfp.h | 72 ++++- 3 files changed, 799 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index ceede09a2845..9beac427f9e8 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -215,6 +215,7 @@ config SFP tristate "SFP cage support" depends on I2C && PHYLINK select MDIO_I2C + imply HWMON config AMD_PHY tristate "AMD PHYs" diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index c4c92db86dfa..5661226cf75b 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -1,5 +1,7 @@ +#include #include #include +#include #include #include #include @@ -131,6 +133,12 @@ struct sfp { unsigned int sm_retries; struct sfp_eeprom_id id; +#if IS_ENABLED(CONFIG_HWMON) + struct sfp_diag diag; + struct device *hwmon_dev; + char *hwmon_name; +#endif + }; static bool sff_module_supported(const struct sfp_eeprom_id *id) @@ -316,6 +324,719 @@ static unsigned int sfp_check(void *buf, size_t len) return check; } +/* hwmon */ +#if IS_ENABLED(CONFIG_HWMON) +static umode_t sfp_hwmon_is_visible(const void *data, + enum hwmon_sensor_types type, + u32 attr, int channel) +{ + const struct sfp *sfp = data; + + switch (type) { + case hwmon_temp: + switch (attr) { + case hwmon_temp_input: + case hwmon_temp_min_alarm: + case hwmon_temp_max_alarm: + case hwmon_temp_lcrit_alarm: + case hwmon_temp_crit_alarm: + case hwmon_temp_min: + case hwmon_temp_max: + case hwmon_temp_lcrit: + case hwmon_temp_crit: + return 0444; + default: + return 0; + } + case hwmon_in: + switch (attr) { + case hwmon_in_input: + case hwmon_in_min_alarm: + case hwmon_in_max_alarm: + case hwmon_in_lcrit_alarm: + case hwmon_in_crit_alarm: + case hwmon_in_min: + case hwmon_in_max: + case hwmon_in_lcrit: + case hwmon_in_crit: + return 0444; + default: + return 0; + } + case hwmon_curr: + switch (attr) { + case hwmon_curr_input: + case hwmon_curr_min_alarm: + case hwmon_curr_max_alarm: + case hwmon_curr_lcrit_alarm: + case hwmon_curr_crit_alarm: + case hwmon_curr_min: + case hwmon_curr_max: + case hwmon_curr_lcrit: + case hwmon_curr_crit: + return 0444; + default: + return 0; + } + case hwmon_power: + /* External calibration of receive power requires + * floating point arithmetic. Doing that in the kernel + * is not easy, so just skip it. If the module does + * not require external calibration, we can however + * show receiver power, since FP is then not needed. + */ + if (sfp->id.ext.diagmon & SFP_DIAGMON_EXT_CAL && + channel == 1) + return 0; + switch (attr) { + case hwmon_power_input: + case hwmon_power_min_alarm: + case hwmon_power_max_alarm: + case hwmon_power_lcrit_alarm: + case hwmon_power_crit_alarm: + case hwmon_power_min: + case hwmon_power_max: + case hwmon_power_lcrit: + case hwmon_power_crit: + return 0444; + default: + return 0; + } + default: + return 0; + } +} + +static int sfp_hwmon_read_sensor(struct sfp *sfp, int reg, long *value) +{ + __be16 val; + int err; + + err = sfp_read(sfp, true, reg, &val, sizeof(val)); + if (err < 0) + return err; + + *value = be16_to_cpu(val); + + return 0; +} + +static void sfp_hwmon_to_rx_power(long *value) +{ + *value = DIV_ROUND_CLOSEST(*value, 100); +} + +static void sfp_hwmon_calibrate(struct sfp *sfp, unsigned int slope, int offset, + long *value) +{ + if (sfp->id.ext.diagmon & SFP_DIAGMON_EXT_CAL) + *value = DIV_ROUND_CLOSEST(*value * slope, 256) + offset; +} + +static void sfp_hwmon_calibrate_temp(struct sfp *sfp, long *value) +{ + sfp_hwmon_calibrate(sfp, be16_to_cpu(sfp->diag.cal_t_slope), + be16_to_cpu(sfp->diag.cal_t_offset), value); + + if (*value >= 0x8000) + *value -= 0x10000; + + *value = DIV_ROUND_CLOSEST(*value * 1000, 256); +} + +static void sfp_hwmon_calibrate_vcc(struct sfp *sfp, long *value) +{ + sfp_hwmon_calibrate(sfp, be16_to_cpu(sfp->diag.cal_v_slope), + be16_to_cpu(sfp->diag.cal_v_offset), value); + + *value = DIV_ROUND_CLOSEST(*value, 10); +} + +static void sfp_hwmon_calibrate_bias(struct sfp *sfp, long *value) +{ + sfp_hwmon_calibrate(sfp, be16_to_cpu(sfp->diag.cal_txi_slope), + be16_to_cpu(sfp->diag.cal_txi_offset), value); + + *value = DIV_ROUND_CLOSEST(*value, 500); +} + +static void sfp_hwmon_calibrate_tx_power(struct sfp *sfp, long *value) +{ + sfp_hwmon_calibrate(sfp, be16_to_cpu(sfp->diag.cal_txpwr_slope), + be16_to_cpu(sfp->diag.cal_txpwr_offset), value); + + *value = DIV_ROUND_CLOSEST(*value, 10); +} + +static int sfp_hwmon_read_temp(struct sfp *sfp, int reg, long *value) +{ + int err; + + err = sfp_hwmon_read_sensor(sfp, reg, value); + if (err < 0) + return err; + + sfp_hwmon_calibrate_temp(sfp, value); + + return 0; +} + +static int sfp_hwmon_read_vcc(struct sfp *sfp, int reg, long *value) +{ + int err; + + err = sfp_hwmon_read_sensor(sfp, reg, value); + if (err < 0) + return err; + + sfp_hwmon_calibrate_vcc(sfp, value); + + return 0; +} + +static int sfp_hwmon_read_bias(struct sfp *sfp, int reg, long *value) +{ + int err; + + err = sfp_hwmon_read_sensor(sfp, reg, value); + if (err < 0) + return err; + + sfp_hwmon_calibrate_bias(sfp, value); + + return 0; +} + +static int sfp_hwmon_read_tx_power(struct sfp *sfp, int reg, long *value) +{ + int err; + + err = sfp_hwmon_read_sensor(sfp, reg, value); + if (err < 0) + return err; + + sfp_hwmon_calibrate_tx_power(sfp, value); + + return 0; +} + +static int sfp_hwmon_read_rx_power(struct sfp *sfp, int reg, long *value) +{ + int err; + + err = sfp_hwmon_read_sensor(sfp, reg, value); + if (err < 0) + return err; + + sfp_hwmon_to_rx_power(value); + + return 0; +} + +static int sfp_hwmon_temp(struct sfp *sfp, u32 attr, long *value) +{ + u8 status; + int err; + + switch (attr) { + case hwmon_temp_input: + return sfp_hwmon_read_temp(sfp, SFP_TEMP, value); + + case hwmon_temp_lcrit: + *value = be16_to_cpu(sfp->diag.temp_low_alarm); + sfp_hwmon_calibrate_temp(sfp, value); + return 0; + + case hwmon_temp_min: + *value = be16_to_cpu(sfp->diag.temp_low_warn); + sfp_hwmon_calibrate_temp(sfp, value); + return 0; + case hwmon_temp_max: + *value = be16_to_cpu(sfp->diag.temp_high_warn); + sfp_hwmon_calibrate_temp(sfp, value); + return 0; + + case hwmon_temp_crit: + *value = be16_to_cpu(sfp->diag.temp_high_alarm); + sfp_hwmon_calibrate_temp(sfp, value); + return 0; + + case hwmon_temp_lcrit_alarm: + err = sfp_read(sfp, true, SFP_ALARM0, &status, sizeof(status)); + if (err < 0) + return err; + + *value = !!(status & SFP_ALARM0_TEMP_LOW); + return 0; + + case hwmon_temp_min_alarm: + err = sfp_read(sfp, true, SFP_WARN0, &status, sizeof(status)); + if (err < 0) + return err; + + *value = !!(status & SFP_WARN0_TEMP_LOW); + return 0; + + case hwmon_temp_max_alarm: + err = sfp_read(sfp, true, SFP_WARN0, &status, sizeof(status)); + if (err < 0) + return err; + + *value = !!(status & SFP_WARN0_TEMP_HIGH); + return 0; + + case hwmon_temp_crit_alarm: + err = sfp_read(sfp, true, SFP_ALARM0, &status, sizeof(status)); + if (err < 0) + return err; + + *value = !!(status & SFP_ALARM0_TEMP_HIGH); + return 0; + default: + return -EOPNOTSUPP; + } + + return -EOPNOTSUPP; +} + +static int sfp_hwmon_vcc(struct sfp *sfp, u32 attr, long *value) +{ + u8 status; + int err; + + switch (attr) { + case hwmon_in_input: + return sfp_hwmon_read_vcc(sfp, SFP_VCC, value); + + case hwmon_in_lcrit: + *value = be16_to_cpu(sfp->diag.volt_low_alarm); + sfp_hwmon_calibrate_vcc(sfp, value); + return 0; + + case hwmon_in_min: + *value = be16_to_cpu(sfp->diag.volt_low_warn); + sfp_hwmon_calibrate_vcc(sfp, value); + return 0; + + case hwmon_in_max: + *value = be16_to_cpu(sfp->diag.volt_high_warn); + sfp_hwmon_calibrate_vcc(sfp, value); + return 0; + + case hwmon_in_crit: + *value = be16_to_cpu(sfp->diag.volt_high_alarm); + sfp_hwmon_calibrate_vcc(sfp, value); + return 0; + + case hwmon_in_lcrit_alarm: + err = sfp_read(sfp, true, SFP_ALARM0, &status, sizeof(status)); + if (err < 0) + return err; + + *value = !!(status & SFP_ALARM0_VCC_LOW); + return 0; + + case hwmon_in_min_alarm: + err = sfp_read(sfp, true, SFP_WARN0, &status, sizeof(status)); + if (err < 0) + return err; + + *value = !!(status & SFP_WARN0_VCC_LOW); + return 0; + + case hwmon_in_max_alarm: + err = sfp_read(sfp, true, SFP_WARN0, &status, sizeof(status)); + if (err < 0) + return err; + + *value = !!(status & SFP_WARN0_VCC_HIGH); + return 0; + + case hwmon_in_crit_alarm: + err = sfp_read(sfp, true, SFP_ALARM0, &status, sizeof(status)); + if (err < 0) + return err; + + *value = !!(status & SFP_ALARM0_VCC_HIGH); + return 0; + default: + return -EOPNOTSUPP; + } + + return -EOPNOTSUPP; +} + +static int sfp_hwmon_bias(struct sfp *sfp, u32 attr, long *value) +{ + u8 status; + int err; + + switch (attr) { + case hwmon_curr_input: + return sfp_hwmon_read_bias(sfp, SFP_TX_BIAS, value); + + case hwmon_curr_lcrit: + *value = be16_to_cpu(sfp->diag.bias_low_alarm); + sfp_hwmon_calibrate_bias(sfp, value); + return 0; + + case hwmon_curr_min: + *value = be16_to_cpu(sfp->diag.bias_low_warn); + sfp_hwmon_calibrate_bias(sfp, value); + return 0; + + case hwmon_curr_max: + *value = be16_to_cpu(sfp->diag.bias_high_warn); + sfp_hwmon_calibrate_bias(sfp, value); + return 0; + + case hwmon_curr_crit: + *value = be16_to_cpu(sfp->diag.bias_high_alarm); + sfp_hwmon_calibrate_bias(sfp, value); + return 0; + + case hwmon_curr_lcrit_alarm: + err = sfp_read(sfp, true, SFP_ALARM0, &status, sizeof(status)); + if (err < 0) + return err; + + *value = !!(status & SFP_ALARM0_TX_BIAS_LOW); + return 0; + + case hwmon_curr_min_alarm: + err = sfp_read(sfp, true, SFP_WARN0, &status, sizeof(status)); + if (err < 0) + return err; + + *value = !!(status & SFP_WARN0_TX_BIAS_LOW); + return 0; + + case hwmon_curr_max_alarm: + err = sfp_read(sfp, true, SFP_WARN0, &status, sizeof(status)); + if (err < 0) + return err; + + *value = !!(status & SFP_WARN0_TX_BIAS_HIGH); + return 0; + + case hwmon_curr_crit_alarm: + err = sfp_read(sfp, true, SFP_ALARM0, &status, sizeof(status)); + if (err < 0) + return err; + + *value = !!(status & SFP_ALARM0_TX_BIAS_HIGH); + return 0; + default: + return -EOPNOTSUPP; + } + + return -EOPNOTSUPP; +} + +static int sfp_hwmon_tx_power(struct sfp *sfp, u32 attr, long *value) +{ + u8 status; + int err; + + switch (attr) { + case hwmon_power_input: + return sfp_hwmon_read_tx_power(sfp, SFP_TX_POWER, value); + + case hwmon_power_lcrit: + *value = be16_to_cpu(sfp->diag.txpwr_low_alarm); + sfp_hwmon_calibrate_tx_power(sfp, value); + return 0; + + case hwmon_power_min: + *value = be16_to_cpu(sfp->diag.txpwr_low_warn); + sfp_hwmon_calibrate_tx_power(sfp, value); + return 0; + + case hwmon_power_max: + *value = be16_to_cpu(sfp->diag.txpwr_high_warn); + sfp_hwmon_calibrate_tx_power(sfp, value); + return 0; + + case hwmon_power_crit: + *value = be16_to_cpu(sfp->diag.txpwr_high_alarm); + sfp_hwmon_calibrate_tx_power(sfp, value); + return 0; + + case hwmon_power_lcrit_alarm: + err = sfp_read(sfp, true, SFP_ALARM0, &status, sizeof(status)); + if (err < 0) + return err; + + *value = !!(status & SFP_ALARM0_TXPWR_LOW); + return 0; + + case hwmon_power_min_alarm: + err = sfp_read(sfp, true, SFP_WARN0, &status, sizeof(status)); + if (err < 0) + return err; + + *value = !!(status & SFP_WARN0_TXPWR_LOW); + return 0; + + case hwmon_power_max_alarm: + err = sfp_read(sfp, true, SFP_WARN0, &status, sizeof(status)); + if (err < 0) + return err; + + *value = !!(status & SFP_WARN0_TXPWR_HIGH); + return 0; + + case hwmon_power_crit_alarm: + err = sfp_read(sfp, true, SFP_ALARM0, &status, sizeof(status)); + if (err < 0) + return err; + + *value = !!(status & SFP_ALARM0_TXPWR_HIGH); + return 0; + default: + return -EOPNOTSUPP; + } + + return -EOPNOTSUPP; +} + +static int sfp_hwmon_rx_power(struct sfp *sfp, u32 attr, long *value) +{ + u8 status; + int err; + + switch (attr) { + case hwmon_power_input: + return sfp_hwmon_read_rx_power(sfp, SFP_RX_POWER, value); + + case hwmon_power_lcrit: + *value = be16_to_cpu(sfp->diag.rxpwr_low_alarm); + sfp_hwmon_to_rx_power(value); + return 0; + + case hwmon_power_min: + *value = be16_to_cpu(sfp->diag.rxpwr_low_warn); + sfp_hwmon_to_rx_power(value); + return 0; + + case hwmon_power_max: + *value = be16_to_cpu(sfp->diag.rxpwr_high_warn); + sfp_hwmon_to_rx_power(value); + return 0; + + case hwmon_power_crit: + *value = be16_to_cpu(sfp->diag.rxpwr_high_alarm); + sfp_hwmon_to_rx_power(value); + return 0; + + case hwmon_power_lcrit_alarm: + err = sfp_read(sfp, true, SFP_ALARM1, &status, sizeof(status)); + if (err < 0) + return err; + + *value = !!(status & SFP_ALARM1_RXPWR_LOW); + return 0; + + case hwmon_power_min_alarm: + err = sfp_read(sfp, true, SFP_WARN1, &status, sizeof(status)); + if (err < 0) + return err; + + *value = !!(status & SFP_WARN1_RXPWR_LOW); + return 0; + + case hwmon_power_max_alarm: + err = sfp_read(sfp, true, SFP_WARN1, &status, sizeof(status)); + if (err < 0) + return err; + + *value = !!(status & SFP_WARN1_RXPWR_HIGH); + return 0; + + case hwmon_power_crit_alarm: + err = sfp_read(sfp, true, SFP_ALARM1, &status, sizeof(status)); + if (err < 0) + return err; + + *value = !!(status & SFP_ALARM1_RXPWR_HIGH); + return 0; + default: + return -EOPNOTSUPP; + } + + return -EOPNOTSUPP; +} + +static int sfp_hwmon_read(struct device *dev, enum hwmon_sensor_types type, + u32 attr, int channel, long *value) +{ + struct sfp *sfp = dev_get_drvdata(dev); + + switch (type) { + case hwmon_temp: + return sfp_hwmon_temp(sfp, attr, value); + case hwmon_in: + return sfp_hwmon_vcc(sfp, attr, value); + case hwmon_curr: + return sfp_hwmon_bias(sfp, attr, value); + case hwmon_power: + switch (channel) { + case 0: + return sfp_hwmon_tx_power(sfp, attr, value); + case 1: + return sfp_hwmon_rx_power(sfp, attr, value); + default: + return -EOPNOTSUPP; + } + default: + return -EOPNOTSUPP; + } +} + +static const struct hwmon_ops sfp_hwmon_ops = { + .is_visible = sfp_hwmon_is_visible, + .read = sfp_hwmon_read, +}; + +static u32 sfp_hwmon_chip_config[] = { + HWMON_C_REGISTER_TZ, + 0, +}; + +static const struct hwmon_channel_info sfp_hwmon_chip = { + .type = hwmon_chip, + .config = sfp_hwmon_chip_config, +}; + +static u32 sfp_hwmon_temp_config[] = { + HWMON_T_INPUT | + HWMON_T_MAX | HWMON_T_MIN | + HWMON_T_MAX_ALARM | HWMON_T_MIN_ALARM | + HWMON_T_CRIT | HWMON_T_LCRIT | + HWMON_T_CRIT_ALARM | HWMON_T_LCRIT_ALARM, + 0, +}; + +static const struct hwmon_channel_info sfp_hwmon_temp_channel_info = { + .type = hwmon_temp, + .config = sfp_hwmon_temp_config, +}; + +static u32 sfp_hwmon_vcc_config[] = { + HWMON_I_INPUT | + HWMON_I_MAX | HWMON_I_MIN | + HWMON_I_MAX_ALARM | HWMON_I_MIN_ALARM | + HWMON_I_CRIT | HWMON_I_LCRIT | + HWMON_I_CRIT_ALARM | HWMON_I_LCRIT_ALARM, + 0, +}; + +static const struct hwmon_channel_info sfp_hwmon_vcc_channel_info = { + .type = hwmon_in, + .config = sfp_hwmon_vcc_config, +}; + +static u32 sfp_hwmon_bias_config[] = { + HWMON_C_INPUT | + HWMON_C_MAX | HWMON_C_MIN | + HWMON_C_MAX_ALARM | HWMON_C_MIN_ALARM | + HWMON_C_CRIT | HWMON_C_LCRIT | + HWMON_C_CRIT_ALARM | HWMON_C_LCRIT_ALARM, + 0, +}; + +static const struct hwmon_channel_info sfp_hwmon_bias_channel_info = { + .type = hwmon_curr, + .config = sfp_hwmon_bias_config, +}; + +static u32 sfp_hwmon_power_config[] = { + /* Transmit power */ + HWMON_P_INPUT | + HWMON_P_MAX | HWMON_P_MIN | + HWMON_P_MAX_ALARM | HWMON_P_MIN_ALARM | + HWMON_P_CRIT | HWMON_P_LCRIT | + HWMON_P_CRIT_ALARM | HWMON_P_LCRIT_ALARM, + /* Receive power */ + HWMON_P_INPUT | + HWMON_P_MAX | HWMON_P_MIN | + HWMON_P_MAX_ALARM | HWMON_P_MIN_ALARM | + HWMON_P_CRIT | HWMON_P_LCRIT | + HWMON_P_CRIT_ALARM | HWMON_P_LCRIT_ALARM, + 0, +}; + +static const struct hwmon_channel_info sfp_hwmon_power_channel_info = { + .type = hwmon_power, + .config = sfp_hwmon_power_config, +}; + +static const struct hwmon_channel_info *sfp_hwmon_info[] = { + &sfp_hwmon_chip, + &sfp_hwmon_vcc_channel_info, + &sfp_hwmon_temp_channel_info, + &sfp_hwmon_bias_channel_info, + &sfp_hwmon_power_channel_info, + NULL, +}; + +static const struct hwmon_chip_info sfp_hwmon_chip_info = { + .ops = &sfp_hwmon_ops, + .info = sfp_hwmon_info, +}; + +static int sfp_hwmon_insert(struct sfp *sfp) +{ + int err, i; + + if (sfp->id.ext.sff8472_compliance == SFP_SFF8472_COMPLIANCE_NONE) + return 0; + + if (!(sfp->id.ext.diagmon & SFP_DIAGMON_DDM)) + return 0; + + if (sfp->id.ext.diagmon & SFP_DIAGMON_ADDRMODE) + /* This driver in general does not support address + * change. + */ + return 0; + + err = sfp_read(sfp, true, 0, &sfp->diag, sizeof(sfp->diag)); + if (err < 0) + return err; + + sfp->hwmon_name = kstrdup(dev_name(sfp->dev), GFP_KERNEL); + if (!sfp->hwmon_name) + return -ENODEV; + + for (i = 0; sfp->hwmon_name[i]; i++) + if (hwmon_is_bad_char(sfp->hwmon_name[i])) + sfp->hwmon_name[i] = '_'; + + sfp->hwmon_dev = hwmon_device_register_with_info(sfp->dev, + sfp->hwmon_name, sfp, + &sfp_hwmon_chip_info, + NULL); + + return PTR_ERR_OR_ZERO(sfp->hwmon_dev); +} + +static void sfp_hwmon_remove(struct sfp *sfp) +{ + hwmon_device_unregister(sfp->hwmon_dev); + kfree(sfp->hwmon_name); +} +#else +static int sfp_hwmon_insert(struct sfp *sfp) +{ + return 0; +} + +static void sfp_hwmon_remove(struct sfp *sfp) +{ +} +#endif + /* Helpers */ static void sfp_module_tx_disable(struct sfp *sfp) { @@ -636,6 +1357,10 @@ static int sfp_sm_mod_probe(struct sfp *sfp) dev_warn(sfp->dev, "module address swap to access page 0xA2 is not supported.\n"); + ret = sfp_hwmon_insert(sfp); + if (ret < 0) + return ret; + ret = sfp_module_insert(sfp->sfp_bus, &sfp->id); if (ret < 0) return ret; @@ -647,6 +1372,8 @@ static void sfp_sm_mod_remove(struct sfp *sfp) { sfp_module_remove(sfp->sfp_bus); + sfp_hwmon_remove(sfp); + if (sfp->mod_phy) sfp_sm_phy_detach(sfp); diff --git a/include/linux/sfp.h b/include/linux/sfp.h index ebce9e24906a..d37518e89db2 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -231,6 +231,50 @@ struct sfp_eeprom_id { struct sfp_eeprom_ext ext; } __packed; +struct sfp_diag { + __be16 temp_high_alarm; + __be16 temp_low_alarm; + __be16 temp_high_warn; + __be16 temp_low_warn; + __be16 volt_high_alarm; + __be16 volt_low_alarm; + __be16 volt_high_warn; + __be16 volt_low_warn; + __be16 bias_high_alarm; + __be16 bias_low_alarm; + __be16 bias_high_warn; + __be16 bias_low_warn; + __be16 txpwr_high_alarm; + __be16 txpwr_low_alarm; + __be16 txpwr_high_warn; + __be16 txpwr_low_warn; + __be16 rxpwr_high_alarm; + __be16 rxpwr_low_alarm; + __be16 rxpwr_high_warn; + __be16 rxpwr_low_warn; + __be16 laser_temp_high_alarm; + __be16 laser_temp_low_alarm; + __be16 laser_temp_high_warn; + __be16 laser_temp_low_warn; + __be16 tec_cur_high_alarm; + __be16 tec_cur_low_alarm; + __be16 tec_cur_high_warn; + __be16 tec_cur_low_warn; + __be32 cal_rxpwr4; + __be32 cal_rxpwr3; + __be32 cal_rxpwr2; + __be32 cal_rxpwr1; + __be32 cal_rxpwr0; + __be16 cal_txi_slope; + __be16 cal_txi_offset; + __be16 cal_txpwr_slope; + __be16 cal_txpwr_offset; + __be16 cal_t_slope; + __be16 cal_t_offset; + __be16 cal_v_slope; + __be16 cal_v_offset; +} __packed; + /* SFP EEPROM registers */ enum { SFP_PHYS_ID = 0x00, @@ -384,7 +428,33 @@ enum { SFP_TEC_CUR = 0x6c, SFP_STATUS = 0x6e, - SFP_ALARM = 0x70, + SFP_ALARM0 = 0x70, + SFP_ALARM0_TEMP_HIGH = BIT(7), + SFP_ALARM0_TEMP_LOW = BIT(6), + SFP_ALARM0_VCC_HIGH = BIT(5), + SFP_ALARM0_VCC_LOW = BIT(4), + SFP_ALARM0_TX_BIAS_HIGH = BIT(3), + SFP_ALARM0_TX_BIAS_LOW = BIT(2), + SFP_ALARM0_TXPWR_HIGH = BIT(1), + SFP_ALARM0_TXPWR_LOW = BIT(0), + + SFP_ALARM1 = 0x71, + SFP_ALARM1_RXPWR_HIGH = BIT(7), + SFP_ALARM1_RXPWR_LOW = BIT(6), + + SFP_WARN0 = 0x74, + SFP_WARN0_TEMP_HIGH = BIT(7), + SFP_WARN0_TEMP_LOW = BIT(6), + SFP_WARN0_VCC_HIGH = BIT(5), + SFP_WARN0_VCC_LOW = BIT(4), + SFP_WARN0_TX_BIAS_HIGH = BIT(3), + SFP_WARN0_TX_BIAS_LOW = BIT(2), + SFP_WARN0_TXPWR_HIGH = BIT(1), + SFP_WARN0_TXPWR_LOW = BIT(0), + + SFP_WARN1 = 0x75, + SFP_WARN1_RXPWR_HIGH = BIT(7), + SFP_WARN1_RXPWR_LOW = BIT(6), SFP_EXT_STATUS = 0x76, SFP_VSL = 0x78, -- cgit v1.2.3 From 753d433b586d1d43c487e3d660f5778c7c8d58ea Mon Sep 17 00:00:00 2001 From: "Tobin C. Harding" Date: Fri, 22 Jun 2018 09:15:32 +1000 Subject: random: Return nbytes filled from hw RNG Currently the function get_random_bytes_arch() has return value 'void'. If the hw RNG fails we currently fall back to using get_random_bytes(). This defeats the purpose of requesting random material from the hw RNG in the first place. There are currently no intree users of get_random_bytes_arch(). Only get random bytes from the hw RNG, make function return the number of bytes retrieved from the hw RNG. Acked-by: Theodore Ts'o Reviewed-by: Steven Rostedt (VMware) Signed-off-by: Tobin C. Harding Signed-off-by: Theodore Ts'o --- drivers/char/random.c | 16 +++++++++------- include/linux/random.h | 2 +- 2 files changed, 10 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/drivers/char/random.c b/drivers/char/random.c index 8e53e9515a1d..34ddfd57419b 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1725,26 +1725,28 @@ EXPORT_SYMBOL(del_random_ready_callback); * key known by the NSA). So it's useful if we need the speed, but * only if we're willing to trust the hardware manufacturer not to * have put in a back door. + * + * Return number of bytes filled in. */ -void get_random_bytes_arch(void *buf, int nbytes) +int __must_check get_random_bytes_arch(void *buf, int nbytes) { + int left = nbytes; char *p = buf; - trace_get_random_bytes_arch(nbytes, _RET_IP_); - while (nbytes) { + trace_get_random_bytes_arch(left, _RET_IP_); + while (left) { unsigned long v; - int chunk = min(nbytes, (int)sizeof(unsigned long)); + int chunk = min_t(int, left, sizeof(unsigned long)); if (!arch_get_random_long(&v)) break; memcpy(p, &v, chunk); p += chunk; - nbytes -= chunk; + left -= chunk; } - if (nbytes) - get_random_bytes(p, nbytes); + return nbytes - left; } EXPORT_SYMBOL(get_random_bytes_arch); diff --git a/include/linux/random.h b/include/linux/random.h index 2ddf13b4281e..f1c9bc5cd231 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -38,7 +38,7 @@ extern void get_random_bytes(void *buf, int nbytes); extern int wait_for_random_bytes(void); extern int add_random_ready_callback(struct random_ready_callback *rdy); extern void del_random_ready_callback(struct random_ready_callback *rdy); -extern void get_random_bytes_arch(void *buf, int nbytes); +extern int __must_check get_random_bytes_arch(void *buf, int nbytes); #ifndef MODULE extern const struct file_operations random_fops, urandom_fops; -- cgit v1.2.3 From 49502b23e0e45b57b776490cfdfd95ea7fecd7c7 Mon Sep 17 00:00:00 2001 From: Enric Balletbo i Serra Date: Wed, 9 May 2018 14:57:44 +0200 Subject: dt-bindings: clock: add rk3399 DDR3 standard speed bins. DDR3 SDRAM Standard (JESD79-3F) defines some standard speed bins for DDR3 memories. The rk3399_dmc driver allows you to pass these values via the device tree. For that purpose the devfreq/rk3399_dmc.txt binding refers to a ddr.h file which does not exist. This patch adds the missing defines in a include file called rk3399-ddr.h with the definition of standard speed bins according to the ARM Trusted Firmware (ATF). Fixes: c1ceb8f7c167 (Documentation: bindings: add dt documentation for rk3399 dmc) Signed-off-by: Enric Balletbo i Serra Reviewed-by: Rob Herring Signed-off-by: MyungJoo Ham --- .../devicetree/bindings/devfreq/rk3399_dmc.txt | 2 +- include/dt-bindings/clock/rk3399-ddr.h | 56 ++++++++++++++++++++++ 2 files changed, 57 insertions(+), 1 deletion(-) create mode 100644 include/dt-bindings/clock/rk3399-ddr.h (limited to 'include') diff --git a/Documentation/devicetree/bindings/devfreq/rk3399_dmc.txt b/Documentation/devicetree/bindings/devfreq/rk3399_dmc.txt index 1b93b33c7d38..e0030a139383 100644 --- a/Documentation/devicetree/bindings/devfreq/rk3399_dmc.txt +++ b/Documentation/devicetree/bindings/devfreq/rk3399_dmc.txt @@ -19,7 +19,7 @@ Required properties: Following properties relate to DDR timing: -- rockchip,dram_speed_bin : Value reference include/dt-bindings/clock/ddr.h, +- rockchip,dram_speed_bin : Value reference include/dt-bindings/clock/rk3399-ddr.h, it selects the DDR3 cl-trp-trcd type. It must be set according to "Speed Bin" in DDR3 datasheet, DO NOT use a smaller "Speed Bin" than specified diff --git a/include/dt-bindings/clock/rk3399-ddr.h b/include/dt-bindings/clock/rk3399-ddr.h new file mode 100644 index 000000000000..ed2280844963 --- /dev/null +++ b/include/dt-bindings/clock/rk3399-ddr.h @@ -0,0 +1,56 @@ +/* SPDX-License-Identifier: (GPL-2.0+ OR MIT) */ + +#ifndef DT_BINDINGS_DDR_H +#define DT_BINDINGS_DDR_H + +/* + * DDR3 SDRAM Standard Speed Bins include tCK, tRCD, tRP, tRAS and tRC for + * each corresponding bin. + */ + +/* DDR3-800 (5-5-5) */ +#define DDR3_800D 0 +/* DDR3-800 (6-6-6) */ +#define DDR3_800E 1 +/* DDR3-1066 (6-6-6) */ +#define DDR3_1066E 2 +/* DDR3-1066 (7-7-7) */ +#define DDR3_1066F 3 +/* DDR3-1066 (8-8-8) */ +#define DDR3_1066G 4 +/* DDR3-1333 (7-7-7) */ +#define DDR3_1333F 5 +/* DDR3-1333 (8-8-8) */ +#define DDR3_1333G 6 +/* DDR3-1333 (9-9-9) */ +#define DDR3_1333H 7 +/* DDR3-1333 (10-10-10) */ +#define DDR3_1333J 8 +/* DDR3-1600 (8-8-8) */ +#define DDR3_1600G 9 +/* DDR3-1600 (9-9-9) */ +#define DDR3_1600H 10 +/* DDR3-1600 (10-10-10) */ +#define DDR3_1600J 11 +/* DDR3-1600 (11-11-11) */ +#define DDR3_1600K 12 +/* DDR3-1600 (10-10-10) */ +#define DDR3_1866J 13 +/* DDR3-1866 (11-11-11) */ +#define DDR3_1866K 14 +/* DDR3-1866 (12-12-12) */ +#define DDR3_1866L 15 +/* DDR3-1866 (13-13-13) */ +#define DDR3_1866M 16 +/* DDR3-2133 (11-11-11) */ +#define DDR3_2133K 17 +/* DDR3-2133 (12-12-12) */ +#define DDR3_2133L 18 +/* DDR3-2133 (13-13-13) */ +#define DDR3_2133M 19 +/* DDR3-2133 (14-14-14) */ +#define DDR3_2133N 20 +/* DDR3 ATF default */ +#define DDR3_DEFAULT 21 + +#endif -- cgit v1.2.3 From fa84cf094ef9667e2b91c104b0a788fd1896f482 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 18 Jul 2018 07:40:53 +0200 Subject: ALSA: pcm: Nuke snd_pcm_lib_mmap_vmalloc() snd_pcm_lib_mmap_vmalloc() was supposed to be implemented with somewhat special for vmalloc handling, but in the end, this turned to just the default handler, i.e. NULL. As the situation has never changed over decades, let's rip it off. Reviewed-by: Takashi Sakamoto Signed-off-by: Takashi Iwai --- drivers/staging/most/sound/sound.c | 1 - include/sound/pcm.h | 2 -- sound/drivers/aloop.c | 1 - sound/drivers/vx/vx_pcm.c | 2 -- sound/firewire/bebob/bebob_pcm.c | 1 - sound/firewire/dice/dice-pcm.c | 2 -- sound/firewire/digi00x/digi00x-pcm.c | 1 - sound/firewire/fireface/ff-pcm.c | 1 - sound/firewire/fireworks/fireworks_pcm.c | 1 - sound/firewire/isight.c | 1 - sound/firewire/motu/motu-pcm.c | 2 -- sound/firewire/oxfw/oxfw-pcm.c | 2 -- sound/firewire/tascam/tascam-pcm.c | 1 - sound/mips/sgio2audio.c | 3 --- sound/pcmcia/pdaudiocf/pdaudiocf_pcm.c | 1 - sound/soc/codecs/rt5514-spi.c | 1 - sound/usb/6fire/pcm.c | 1 - sound/usb/caiaq/audio.c | 1 - sound/usb/hiface/pcm.c | 1 - sound/usb/misc/ua101.c | 2 -- sound/usb/pcm.c | 2 -- 21 files changed, 30 deletions(-) (limited to 'include') diff --git a/drivers/staging/most/sound/sound.c b/drivers/staging/most/sound/sound.c index 04c18323c2ea..89b02fc305b8 100644 --- a/drivers/staging/most/sound/sound.c +++ b/drivers/staging/most/sound/sound.c @@ -457,7 +457,6 @@ static const struct snd_pcm_ops pcm_ops = { .trigger = pcm_trigger, .pointer = pcm_pointer, .page = snd_pcm_lib_get_vmalloc_page, - .mmap = snd_pcm_lib_mmap_vmalloc, }; static int split_arg_list(char *buf, char **card_name, u16 *ch_num, diff --git a/include/sound/pcm.h b/include/sound/pcm.h index fcdf358a25f0..1206045ccf03 100644 --- a/include/sound/pcm.h +++ b/include/sound/pcm.h @@ -1342,8 +1342,6 @@ int snd_pcm_lib_mmap_iomem(struct snd_pcm_substream *substream, struct vm_area_s #define snd_pcm_lib_mmap_iomem NULL #endif -#define snd_pcm_lib_mmap_vmalloc NULL - /** * snd_pcm_limit_isa_dma_size - Get the max size fitting with ISA DMA transfer * @dma: DMA number diff --git a/sound/drivers/aloop.c b/sound/drivers/aloop.c index 78a2fdc38531..1e34e6381baa 100644 --- a/sound/drivers/aloop.c +++ b/sound/drivers/aloop.c @@ -778,7 +778,6 @@ static const struct snd_pcm_ops loopback_pcm_ops = { .trigger = loopback_trigger, .pointer = loopback_pointer, .page = snd_pcm_lib_get_vmalloc_page, - .mmap = snd_pcm_lib_mmap_vmalloc, }; static int loopback_pcm_new(struct loopback *loopback, diff --git a/sound/drivers/vx/vx_pcm.c b/sound/drivers/vx/vx_pcm.c index 380a028469c4..ba80f459bdc5 100644 --- a/sound/drivers/vx/vx_pcm.c +++ b/sound/drivers/vx/vx_pcm.c @@ -883,7 +883,6 @@ static const struct snd_pcm_ops vx_pcm_playback_ops = { .trigger = vx_pcm_trigger, .pointer = vx_pcm_playback_pointer, .page = snd_pcm_lib_get_vmalloc_page, - .mmap = snd_pcm_lib_mmap_vmalloc, }; @@ -1105,7 +1104,6 @@ static const struct snd_pcm_ops vx_pcm_capture_ops = { .trigger = vx_pcm_trigger, .pointer = vx_pcm_capture_pointer, .page = snd_pcm_lib_get_vmalloc_page, - .mmap = snd_pcm_lib_mmap_vmalloc, }; diff --git a/sound/firewire/bebob/bebob_pcm.c b/sound/firewire/bebob/bebob_pcm.c index e6adab3ef42e..ea9b86450580 100644 --- a/sound/firewire/bebob/bebob_pcm.c +++ b/sound/firewire/bebob/bebob_pcm.c @@ -373,7 +373,6 @@ int snd_bebob_create_pcm_devices(struct snd_bebob *bebob) .pointer = pcm_playback_pointer, .ack = pcm_playback_ack, .page = snd_pcm_lib_get_vmalloc_page, - .mmap = snd_pcm_lib_mmap_vmalloc, }; struct snd_pcm *pcm; int err; diff --git a/sound/firewire/dice/dice-pcm.c b/sound/firewire/dice/dice-pcm.c index 80351b29fe0d..bb3ef5ff3488 100644 --- a/sound/firewire/dice/dice-pcm.c +++ b/sound/firewire/dice/dice-pcm.c @@ -412,7 +412,6 @@ int snd_dice_create_pcm(struct snd_dice *dice) .pointer = capture_pointer, .ack = capture_ack, .page = snd_pcm_lib_get_vmalloc_page, - .mmap = snd_pcm_lib_mmap_vmalloc, }; static const struct snd_pcm_ops playback_ops = { .open = pcm_open, @@ -425,7 +424,6 @@ int snd_dice_create_pcm(struct snd_dice *dice) .pointer = playback_pointer, .ack = playback_ack, .page = snd_pcm_lib_get_vmalloc_page, - .mmap = snd_pcm_lib_mmap_vmalloc, }; struct snd_pcm *pcm; unsigned int capture, playback; diff --git a/sound/firewire/digi00x/digi00x-pcm.c b/sound/firewire/digi00x/digi00x-pcm.c index 796f4b4645f5..fdcff0460c53 100644 --- a/sound/firewire/digi00x/digi00x-pcm.c +++ b/sound/firewire/digi00x/digi00x-pcm.c @@ -352,7 +352,6 @@ int snd_dg00x_create_pcm_devices(struct snd_dg00x *dg00x) .pointer = pcm_playback_pointer, .ack = pcm_playback_ack, .page = snd_pcm_lib_get_vmalloc_page, - .mmap = snd_pcm_lib_mmap_vmalloc, }; struct snd_pcm *pcm; int err; diff --git a/sound/firewire/fireface/ff-pcm.c b/sound/firewire/fireface/ff-pcm.c index e3c16308363d..bf47f9ec8703 100644 --- a/sound/firewire/fireface/ff-pcm.c +++ b/sound/firewire/fireface/ff-pcm.c @@ -383,7 +383,6 @@ int snd_ff_create_pcm_devices(struct snd_ff *ff) .pointer = pcm_playback_pointer, .ack = pcm_playback_ack, .page = snd_pcm_lib_get_vmalloc_page, - .mmap = snd_pcm_lib_mmap_vmalloc, }; struct snd_pcm *pcm; int err; diff --git a/sound/firewire/fireworks/fireworks_pcm.c b/sound/firewire/fireworks/fireworks_pcm.c index 40faed5e6968..aed566d82726 100644 --- a/sound/firewire/fireworks/fireworks_pcm.c +++ b/sound/firewire/fireworks/fireworks_pcm.c @@ -397,7 +397,6 @@ int snd_efw_create_pcm_devices(struct snd_efw *efw) .pointer = pcm_playback_pointer, .ack = pcm_playback_ack, .page = snd_pcm_lib_get_vmalloc_page, - .mmap = snd_pcm_lib_mmap_vmalloc, }; struct snd_pcm *pcm; int err; diff --git a/sound/firewire/isight.c b/sound/firewire/isight.c index 3919e186a30b..30957477e005 100644 --- a/sound/firewire/isight.c +++ b/sound/firewire/isight.c @@ -454,7 +454,6 @@ static int isight_create_pcm(struct isight *isight) .trigger = isight_trigger, .pointer = isight_pointer, .page = snd_pcm_lib_get_vmalloc_page, - .mmap = snd_pcm_lib_mmap_vmalloc, }; struct snd_pcm *pcm; int err; diff --git a/sound/firewire/motu/motu-pcm.c b/sound/firewire/motu/motu-pcm.c index 4330220890e8..ab69d7e6ac05 100644 --- a/sound/firewire/motu/motu-pcm.c +++ b/sound/firewire/motu/motu-pcm.c @@ -363,7 +363,6 @@ int snd_motu_create_pcm_devices(struct snd_motu *motu) .pointer = capture_pointer, .ack = capture_ack, .page = snd_pcm_lib_get_vmalloc_page, - .mmap = snd_pcm_lib_mmap_vmalloc, }; static const struct snd_pcm_ops playback_ops = { .open = pcm_open, @@ -376,7 +375,6 @@ int snd_motu_create_pcm_devices(struct snd_motu *motu) .pointer = playback_pointer, .ack = playback_ack, .page = snd_pcm_lib_get_vmalloc_page, - .mmap = snd_pcm_lib_mmap_vmalloc, }; struct snd_pcm *pcm; int err; diff --git a/sound/firewire/oxfw/oxfw-pcm.c b/sound/firewire/oxfw/oxfw-pcm.c index 3dd46285c0e2..b3f6503dd34d 100644 --- a/sound/firewire/oxfw/oxfw-pcm.c +++ b/sound/firewire/oxfw/oxfw-pcm.c @@ -389,7 +389,6 @@ int snd_oxfw_create_pcm(struct snd_oxfw *oxfw) .pointer = pcm_capture_pointer, .ack = pcm_capture_ack, .page = snd_pcm_lib_get_vmalloc_page, - .mmap = snd_pcm_lib_mmap_vmalloc, }; static const struct snd_pcm_ops playback_ops = { .open = pcm_open, @@ -402,7 +401,6 @@ int snd_oxfw_create_pcm(struct snd_oxfw *oxfw) .pointer = pcm_playback_pointer, .ack = pcm_playback_ack, .page = snd_pcm_lib_get_vmalloc_page, - .mmap = snd_pcm_lib_mmap_vmalloc, }; struct snd_pcm *pcm; unsigned int cap = 0; diff --git a/sound/firewire/tascam/tascam-pcm.c b/sound/firewire/tascam/tascam-pcm.c index 6ec8ec634d4d..e4cc8990e195 100644 --- a/sound/firewire/tascam/tascam-pcm.c +++ b/sound/firewire/tascam/tascam-pcm.c @@ -279,7 +279,6 @@ int snd_tscm_create_pcm_devices(struct snd_tscm *tscm) .pointer = pcm_playback_pointer, .ack = pcm_playback_ack, .page = snd_pcm_lib_get_vmalloc_page, - .mmap = snd_pcm_lib_mmap_vmalloc, }; struct snd_pcm *pcm; int err; diff --git a/sound/mips/sgio2audio.c b/sound/mips/sgio2audio.c index 9fb68b35de5a..3ec9391a4736 100644 --- a/sound/mips/sgio2audio.c +++ b/sound/mips/sgio2audio.c @@ -685,7 +685,6 @@ static const struct snd_pcm_ops snd_sgio2audio_playback1_ops = { .trigger = snd_sgio2audio_pcm_trigger, .pointer = snd_sgio2audio_pcm_pointer, .page = snd_pcm_lib_get_vmalloc_page, - .mmap = snd_pcm_lib_mmap_vmalloc, }; static const struct snd_pcm_ops snd_sgio2audio_playback2_ops = { @@ -698,7 +697,6 @@ static const struct snd_pcm_ops snd_sgio2audio_playback2_ops = { .trigger = snd_sgio2audio_pcm_trigger, .pointer = snd_sgio2audio_pcm_pointer, .page = snd_pcm_lib_get_vmalloc_page, - .mmap = snd_pcm_lib_mmap_vmalloc, }; static const struct snd_pcm_ops snd_sgio2audio_capture_ops = { @@ -711,7 +709,6 @@ static const struct snd_pcm_ops snd_sgio2audio_capture_ops = { .trigger = snd_sgio2audio_pcm_trigger, .pointer = snd_sgio2audio_pcm_pointer, .page = snd_pcm_lib_get_vmalloc_page, - .mmap = snd_pcm_lib_mmap_vmalloc, }; /* diff --git a/sound/pcmcia/pdaudiocf/pdaudiocf_pcm.c b/sound/pcmcia/pdaudiocf/pdaudiocf_pcm.c index 4a2354b5ae00..98a6863e933c 100644 --- a/sound/pcmcia/pdaudiocf/pdaudiocf_pcm.c +++ b/sound/pcmcia/pdaudiocf/pdaudiocf_pcm.c @@ -276,7 +276,6 @@ static const struct snd_pcm_ops pdacf_pcm_capture_ops = { .trigger = pdacf_pcm_trigger, .pointer = pdacf_pcm_capture_pointer, .page = snd_pcm_lib_get_vmalloc_page, - .mmap = snd_pcm_lib_mmap_vmalloc, }; diff --git a/sound/soc/codecs/rt5514-spi.c b/sound/soc/codecs/rt5514-spi.c index 18686ffb0cd5..6478d10c4f4a 100644 --- a/sound/soc/codecs/rt5514-spi.c +++ b/sound/soc/codecs/rt5514-spi.c @@ -268,7 +268,6 @@ static const struct snd_pcm_ops rt5514_spi_pcm_ops = { .hw_params = rt5514_spi_hw_params, .hw_free = rt5514_spi_hw_free, .pointer = rt5514_spi_pcm_pointer, - .mmap = snd_pcm_lib_mmap_vmalloc, .page = snd_pcm_lib_get_vmalloc_page, }; diff --git a/sound/usb/6fire/pcm.c b/sound/usb/6fire/pcm.c index 2dd2518a71d3..f8ef3e2a8ca0 100644 --- a/sound/usb/6fire/pcm.c +++ b/sound/usb/6fire/pcm.c @@ -565,7 +565,6 @@ static const struct snd_pcm_ops pcm_ops = { .trigger = usb6fire_pcm_trigger, .pointer = usb6fire_pcm_pointer, .page = snd_pcm_lib_get_vmalloc_page, - .mmap = snd_pcm_lib_mmap_vmalloc, }; static void usb6fire_pcm_init_urb(struct pcm_urb *urb, diff --git a/sound/usb/caiaq/audio.c b/sound/usb/caiaq/audio.c index 15344d39a6cd..c6108a3d7f8f 100644 --- a/sound/usb/caiaq/audio.c +++ b/sound/usb/caiaq/audio.c @@ -348,7 +348,6 @@ static const struct snd_pcm_ops snd_usb_caiaq_ops = { .trigger = snd_usb_caiaq_pcm_trigger, .pointer = snd_usb_caiaq_pcm_pointer, .page = snd_pcm_lib_get_vmalloc_page, - .mmap = snd_pcm_lib_mmap_vmalloc, }; static void check_for_elapsed_periods(struct snd_usb_caiaqdev *cdev, diff --git a/sound/usb/hiface/pcm.c b/sound/usb/hiface/pcm.c index 396c317115b1..e1fbb9cc9ea7 100644 --- a/sound/usb/hiface/pcm.c +++ b/sound/usb/hiface/pcm.c @@ -523,7 +523,6 @@ static const struct snd_pcm_ops pcm_ops = { .trigger = hiface_pcm_trigger, .pointer = hiface_pcm_pointer, .page = snd_pcm_lib_get_vmalloc_page, - .mmap = snd_pcm_lib_mmap_vmalloc, }; static int hiface_pcm_init_urb(struct pcm_urb *urb, diff --git a/sound/usb/misc/ua101.c b/sound/usb/misc/ua101.c index 386fbfd5c617..a0b6d039017f 100644 --- a/sound/usb/misc/ua101.c +++ b/sound/usb/misc/ua101.c @@ -900,7 +900,6 @@ static const struct snd_pcm_ops capture_pcm_ops = { .trigger = capture_pcm_trigger, .pointer = capture_pcm_pointer, .page = snd_pcm_lib_get_vmalloc_page, - .mmap = snd_pcm_lib_mmap_vmalloc, }; static const struct snd_pcm_ops playback_pcm_ops = { @@ -913,7 +912,6 @@ static const struct snd_pcm_ops playback_pcm_ops = { .trigger = playback_pcm_trigger, .pointer = playback_pcm_pointer, .page = snd_pcm_lib_get_vmalloc_page, - .mmap = snd_pcm_lib_mmap_vmalloc, }; static const struct uac_format_type_i_discrete_descriptor * diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c index 160f52c4871b..4b930fa47277 100644 --- a/sound/usb/pcm.c +++ b/sound/usb/pcm.c @@ -1694,7 +1694,6 @@ static const struct snd_pcm_ops snd_usb_playback_ops = { .trigger = snd_usb_substream_playback_trigger, .pointer = snd_usb_pcm_pointer, .page = snd_pcm_lib_get_vmalloc_page, - .mmap = snd_pcm_lib_mmap_vmalloc, }; static const struct snd_pcm_ops snd_usb_capture_ops = { @@ -1707,7 +1706,6 @@ static const struct snd_pcm_ops snd_usb_capture_ops = { .trigger = snd_usb_substream_capture_trigger, .pointer = snd_usb_pcm_pointer, .page = snd_pcm_lib_get_vmalloc_page, - .mmap = snd_pcm_lib_mmap_vmalloc, }; static const struct snd_pcm_ops snd_usb_playback_dev_ops = { -- cgit v1.2.3 From 181ace9e1b2e1c5c2be590bc9603baa65f3a16d8 Mon Sep 17 00:00:00 2001 From: Abhishek Sahu Date: Wed, 20 Jun 2018 12:57:28 +0530 Subject: mtd: rawnand: helper function for setting up ECC configuration commit 2c8f8afa7f92 ("mtd: nand: add generic helpers to check, match, maximize ECC settings") provides generic helpers which drivers can use for setting up ECC parameters. Since same board can have different ECC strength nand chips so following is the logic for setting up ECC strength and ECC step size, which can be used by most of the drivers. 1. If both ECC step size and ECC strength are already set (usually by DT) then just check whether this setting is supported by NAND controller. 2. If NAND_ECC_MAXIMIZE is set, then select maximum ECC strength supported by NAND controller. 3. Otherwise, try to match the ECC step size and ECC strength closest to the chip's requirement. If available OOB size can't fit the chip requirement then select maximum ECC strength which can be fit with available OOB size. This patch introduces nand_ecc_choose_conf function which calls the required helper functions for the above logic. The drivers can use this single function instead of calling the 3 helper functions individually. Signed-off-by: Abhishek Sahu Reviewed-by: Masahiro Yamada Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/nand_base.c | 33 +++++++++++++++++++++++++++++++++ include/linux/mtd/rawnand.h | 3 +++ 2 files changed, 36 insertions(+) (limited to 'include') diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index dbf6e80e9ab5..2858d0b09c1d 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -6295,6 +6295,39 @@ int nand_maximize_ecc(struct nand_chip *chip, } EXPORT_SYMBOL_GPL(nand_maximize_ecc); +/** + * nand_ecc_choose_conf - Set the ECC strength and ECC step size + * @chip: nand chip info structure + * @caps: ECC engine caps info structure + * @oobavail: OOB size that the ECC engine can use + * + * Choose the ECC configuration according to following logic + * + * 1. If both ECC step size and ECC strength are already set (usually by DT) + * then check if it is supported by this controller. + * 2. If NAND_ECC_MAXIMIZE is set, then select maximum ECC strength. + * 3. Otherwise, try to match the ECC step size and ECC strength closest + * to the chip's requirement. If available OOB size can't fit the chip + * requirement then fallback to the maximum ECC step size and ECC strength. + * + * On success, the chosen ECC settings are set. + */ +int nand_ecc_choose_conf(struct nand_chip *chip, + const struct nand_ecc_caps *caps, int oobavail) +{ + if (chip->ecc.size && chip->ecc.strength) + return nand_check_ecc_caps(chip, caps, oobavail); + + if (chip->ecc.options & NAND_ECC_MAXIMIZE) + return nand_maximize_ecc(chip, caps, oobavail); + + if (!nand_match_ecc_req(chip, caps, oobavail)) + return 0; + + return nand_maximize_ecc(chip, caps, oobavail); +} +EXPORT_SYMBOL_GPL(nand_ecc_choose_conf); + /* * Check if the chip configuration meet the datasheet requirements. diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index fbac4741da52..2ce305388471 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1672,6 +1672,9 @@ int nand_match_ecc_req(struct nand_chip *chip, int nand_maximize_ecc(struct nand_chip *chip, const struct nand_ecc_caps *caps, int oobavail); +int nand_ecc_choose_conf(struct nand_chip *chip, + const struct nand_ecc_caps *caps, int oobavail); + /* Default write_oob implementation */ int nand_write_oob_std(struct mtd_info *mtd, struct nand_chip *chip, int page); -- cgit v1.2.3 From 0cf5c7dbaa392d11cfae532cedeaad0ac48b2165 Mon Sep 17 00:00:00 2001 From: Abhishek Sahu Date: Wed, 20 Jun 2018 12:57:42 +0530 Subject: mtd: rawnand: provide only single helper function for ECC conf Function nand_ecc_choose_conf() will be help for all the cases, so other helper functions can be made static. nand_check_ecc_caps(): Invoke nand_ecc_choose_conf() with both chip->ecc.size and chip->ecc.strength value set. nand_maximize_ecc(): Invoke nand_ecc_choose_conf() with NAND_ECC_MAXIMIZE flag. nand_match_ecc_req(): Invoke nand_ecc_choose_conf() with either chip->ecc.size or chip->ecc.strength value set and without NAND_ECC_MAXIMIZE flag. CC: Masahiro Yamada Signed-off-by: Abhishek Sahu Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/nand_base.c | 39 +++++++++++++++------------------------ include/linux/mtd/rawnand.h | 9 --------- 2 files changed, 15 insertions(+), 33 deletions(-) (limited to 'include') diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index 2858d0b09c1d..faac82b1e058 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -6085,24 +6085,17 @@ static int nand_set_ecc_soft_ops(struct mtd_info *mtd) * by the controller and the calculated ECC bytes fit within the chip's OOB. * On success, the calculated ECC bytes is set. */ -int nand_check_ecc_caps(struct nand_chip *chip, - const struct nand_ecc_caps *caps, int oobavail) +static int +nand_check_ecc_caps(struct nand_chip *chip, + const struct nand_ecc_caps *caps, int oobavail) { struct mtd_info *mtd = nand_to_mtd(chip); const struct nand_ecc_step_info *stepinfo; int preset_step = chip->ecc.size; int preset_strength = chip->ecc.strength; - int nsteps, ecc_bytes; + int ecc_bytes, nsteps = mtd->writesize / preset_step; int i, j; - if (WARN_ON(oobavail < 0)) - return -EINVAL; - - if (!preset_step || !preset_strength) - return -ENODATA; - - nsteps = mtd->writesize / preset_step; - for (i = 0; i < caps->nstepinfos; i++) { stepinfo = &caps->stepinfos[i]; @@ -6135,7 +6128,6 @@ int nand_check_ecc_caps(struct nand_chip *chip, return -ENOTSUPP; } -EXPORT_SYMBOL_GPL(nand_check_ecc_caps); /** * nand_match_ecc_req - meet the chip's requirement with least ECC bytes @@ -6147,8 +6139,9 @@ EXPORT_SYMBOL_GPL(nand_check_ecc_caps); * number of ECC bytes (i.e. with the largest number of OOB-free bytes). * On success, the chosen ECC settings are set. */ -int nand_match_ecc_req(struct nand_chip *chip, - const struct nand_ecc_caps *caps, int oobavail) +static int +nand_match_ecc_req(struct nand_chip *chip, + const struct nand_ecc_caps *caps, int oobavail) { struct mtd_info *mtd = nand_to_mtd(chip); const struct nand_ecc_step_info *stepinfo; @@ -6159,9 +6152,6 @@ int nand_match_ecc_req(struct nand_chip *chip, int best_ecc_bytes_total = INT_MAX; int i, j; - if (WARN_ON(oobavail < 0)) - return -EINVAL; - /* No information provided by the NAND chip */ if (!req_step || !req_strength) return -ENOTSUPP; @@ -6220,7 +6210,6 @@ int nand_match_ecc_req(struct nand_chip *chip, return 0; } -EXPORT_SYMBOL_GPL(nand_match_ecc_req); /** * nand_maximize_ecc - choose the max ECC strength available @@ -6231,8 +6220,9 @@ EXPORT_SYMBOL_GPL(nand_match_ecc_req); * Choose the max ECC strength that is supported on the controller, and can fit * within the chip's OOB. On success, the chosen ECC settings are set. */ -int nand_maximize_ecc(struct nand_chip *chip, - const struct nand_ecc_caps *caps, int oobavail) +static int +nand_maximize_ecc(struct nand_chip *chip, + const struct nand_ecc_caps *caps, int oobavail) { struct mtd_info *mtd = nand_to_mtd(chip); const struct nand_ecc_step_info *stepinfo; @@ -6242,9 +6232,6 @@ int nand_maximize_ecc(struct nand_chip *chip, int best_strength, best_ecc_bytes; int i, j; - if (WARN_ON(oobavail < 0)) - return -EINVAL; - for (i = 0; i < caps->nstepinfos; i++) { stepinfo = &caps->stepinfos[i]; step_size = stepinfo->stepsize; @@ -6293,7 +6280,6 @@ int nand_maximize_ecc(struct nand_chip *chip, return 0; } -EXPORT_SYMBOL_GPL(nand_maximize_ecc); /** * nand_ecc_choose_conf - Set the ECC strength and ECC step size @@ -6315,6 +6301,11 @@ EXPORT_SYMBOL_GPL(nand_maximize_ecc); int nand_ecc_choose_conf(struct nand_chip *chip, const struct nand_ecc_caps *caps, int oobavail) { + struct mtd_info *mtd = nand_to_mtd(chip); + + if (WARN_ON(oobavail < 0 || oobavail > mtd->oobsize)) + return -EINVAL; + if (chip->ecc.size && chip->ecc.strength) return nand_check_ecc_caps(chip, caps, oobavail); diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 2ce305388471..0c6fb316b409 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1663,15 +1663,6 @@ int nand_check_erased_ecc_chunk(void *data, int datalen, void *extraoob, int extraooblen, int threshold); -int nand_check_ecc_caps(struct nand_chip *chip, - const struct nand_ecc_caps *caps, int oobavail); - -int nand_match_ecc_req(struct nand_chip *chip, - const struct nand_ecc_caps *caps, int oobavail); - -int nand_maximize_ecc(struct nand_chip *chip, - const struct nand_ecc_caps *caps, int oobavail); - int nand_ecc_choose_conf(struct nand_chip *chip, const struct nand_ecc_caps *caps, int oobavail); -- cgit v1.2.3 From 7529df4652482c33ae1a99ee8189401146f13cb7 Mon Sep 17 00:00:00 2001 From: Peter Pan Date: Fri, 22 Jun 2018 14:28:23 +0200 Subject: mtd: nand: Add core infrastructure to support SPI NANDs Add a SPI NAND framework based on the generic NAND framework and the spi-mem infrastructure. In its current state, this framework supports the following features: - single/dual/quad IO modes - on-die ECC Signed-off-by: Peter Pan Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- drivers/mtd/nand/Kconfig | 1 + drivers/mtd/nand/Makefile | 1 + drivers/mtd/nand/spi/Kconfig | 7 + drivers/mtd/nand/spi/Makefile | 3 + drivers/mtd/nand/spi/core.c | 1136 +++++++++++++++++++++++++++++++++++++++++ include/linux/mtd/spinand.h | 416 +++++++++++++++ include/linux/spi/spi-mem.h | 4 +- 7 files changed, 1567 insertions(+), 1 deletion(-) create mode 100644 drivers/mtd/nand/spi/Kconfig create mode 100644 drivers/mtd/nand/spi/Makefile create mode 100644 drivers/mtd/nand/spi/core.c create mode 100644 include/linux/mtd/spinand.h (limited to 'include') diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig index 88c7d3b4ff8b..9033215e62ea 100644 --- a/drivers/mtd/nand/Kconfig +++ b/drivers/mtd/nand/Kconfig @@ -4,3 +4,4 @@ config MTD_NAND_CORE source "drivers/mtd/nand/onenand/Kconfig" source "drivers/mtd/nand/raw/Kconfig" +source "drivers/mtd/nand/spi/Kconfig" diff --git a/drivers/mtd/nand/Makefile b/drivers/mtd/nand/Makefile index 3f0cb87f1a57..7ecd80c0a66e 100644 --- a/drivers/mtd/nand/Makefile +++ b/drivers/mtd/nand/Makefile @@ -5,3 +5,4 @@ obj-$(CONFIG_MTD_NAND_CORE) += nandcore.o obj-y += onenand/ obj-y += raw/ +obj-y += spi/ diff --git a/drivers/mtd/nand/spi/Kconfig b/drivers/mtd/nand/spi/Kconfig new file mode 100644 index 000000000000..7c37d2929b68 --- /dev/null +++ b/drivers/mtd/nand/spi/Kconfig @@ -0,0 +1,7 @@ +menuconfig MTD_SPI_NAND + tristate "SPI NAND device Support" + select MTD_NAND_CORE + depends on SPI_MASTER + select SPI_MEM + help + This is the framework for the SPI NAND device drivers. diff --git a/drivers/mtd/nand/spi/Makefile b/drivers/mtd/nand/spi/Makefile new file mode 100644 index 000000000000..2c473b765027 --- /dev/null +++ b/drivers/mtd/nand/spi/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 +spinand-objs := core.o +obj-$(CONFIG_MTD_SPI_NAND) += spinand.o diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c new file mode 100644 index 000000000000..4efbeb0d85b4 --- /dev/null +++ b/drivers/mtd/nand/spi/core.c @@ -0,0 +1,1136 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2016-2017 Micron Technology, Inc. + * + * Authors: + * Peter Pan + * Boris Brezillon + */ + +#define pr_fmt(fmt) "spi-nand: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static void spinand_cache_op_adjust_colum(struct spinand_device *spinand, + const struct nand_page_io_req *req, + u16 *column) +{ + struct nand_device *nand = spinand_to_nand(spinand); + unsigned int shift; + + if (nand->memorg.planes_per_lun < 2) + return; + + /* The plane number is passed in MSB just above the column address */ + shift = fls(nand->memorg.pagesize); + *column |= req->pos.plane << shift; +} + +static int spinand_read_reg_op(struct spinand_device *spinand, u8 reg, u8 *val) +{ + struct spi_mem_op op = SPINAND_GET_FEATURE_OP(reg, + spinand->scratchbuf); + int ret; + + ret = spi_mem_exec_op(spinand->spimem, &op); + if (ret) + return ret; + + *val = *spinand->scratchbuf; + return 0; +} + +static int spinand_write_reg_op(struct spinand_device *spinand, u8 reg, u8 val) +{ + struct spi_mem_op op = SPINAND_SET_FEATURE_OP(reg, + spinand->scratchbuf); + + *spinand->scratchbuf = val; + return spi_mem_exec_op(spinand->spimem, &op); +} + +static int spinand_read_status(struct spinand_device *spinand, u8 *status) +{ + return spinand_read_reg_op(spinand, REG_STATUS, status); +} + +static int spinand_get_cfg(struct spinand_device *spinand, u8 *cfg) +{ + struct nand_device *nand = spinand_to_nand(spinand); + + if (WARN_ON(spinand->cur_target < 0 || + spinand->cur_target >= nand->memorg.ntargets)) + return -EINVAL; + + *cfg = spinand->cfg_cache[spinand->cur_target]; + return 0; +} + +static int spinand_set_cfg(struct spinand_device *spinand, u8 cfg) +{ + struct nand_device *nand = spinand_to_nand(spinand); + int ret; + + if (WARN_ON(spinand->cur_target < 0 || + spinand->cur_target >= nand->memorg.ntargets)) + return -EINVAL; + + if (spinand->cfg_cache[spinand->cur_target] == cfg) + return 0; + + ret = spinand_write_reg_op(spinand, REG_CFG, cfg); + if (ret) + return ret; + + spinand->cfg_cache[spinand->cur_target] = cfg; + return 0; +} + +/** + * spinand_upd_cfg() - Update the configuration register + * @spinand: the spinand device + * @mask: the mask encoding the bits to update in the config reg + * @val: the new value to apply + * + * Update the configuration register. + * + * Return: 0 on success, a negative error code otherwise. + */ +int spinand_upd_cfg(struct spinand_device *spinand, u8 mask, u8 val) +{ + int ret; + u8 cfg; + + ret = spinand_get_cfg(spinand, &cfg); + if (ret) + return ret; + + cfg &= ~mask; + cfg |= val; + + return spinand_set_cfg(spinand, cfg); +} + +/** + * spinand_select_target() - Select a specific NAND target/die + * @spinand: the spinand device + * @target: the target/die to select + * + * Select a new target/die. If chip only has one die, this function is a NOOP. + * + * Return: 0 on success, a negative error code otherwise. + */ +int spinand_select_target(struct spinand_device *spinand, unsigned int target) +{ + struct nand_device *nand = spinand_to_nand(spinand); + int ret; + + if (WARN_ON(target >= nand->memorg.ntargets)) + return -EINVAL; + + if (spinand->cur_target == target) + return 0; + + if (nand->memorg.ntargets == 1) { + spinand->cur_target = target; + return 0; + } + + ret = spinand->select_target(spinand, target); + if (ret) + return ret; + + spinand->cur_target = target; + return 0; +} + +static int spinand_init_cfg_cache(struct spinand_device *spinand) +{ + struct nand_device *nand = spinand_to_nand(spinand); + struct device *dev = &spinand->spimem->spi->dev; + unsigned int target; + int ret; + + spinand->cfg_cache = devm_kcalloc(dev, + nand->memorg.ntargets, + sizeof(*spinand->cfg_cache), + GFP_KERNEL); + if (!spinand->cfg_cache) + return -ENOMEM; + + for (target = 0; target < nand->memorg.ntargets; target++) { + ret = spinand_select_target(spinand, target); + if (ret) + return ret; + + /* + * We use spinand_read_reg_op() instead of spinand_get_cfg() + * here to bypass the config cache. + */ + ret = spinand_read_reg_op(spinand, REG_CFG, + &spinand->cfg_cache[target]); + if (ret) + return ret; + } + + return 0; +} + +static int spinand_init_quad_enable(struct spinand_device *spinand) +{ + bool enable = false; + + if (!(spinand->flags & SPINAND_HAS_QE_BIT)) + return 0; + + if (spinand->op_templates.read_cache->data.buswidth == 4 || + spinand->op_templates.write_cache->data.buswidth == 4 || + spinand->op_templates.update_cache->data.buswidth == 4) + enable = true; + + return spinand_upd_cfg(spinand, CFG_QUAD_ENABLE, + enable ? CFG_QUAD_ENABLE : 0); +} + +static int spinand_ecc_enable(struct spinand_device *spinand, + bool enable) +{ + return spinand_upd_cfg(spinand, CFG_ECC_ENABLE, + enable ? CFG_ECC_ENABLE : 0); +} + +static int spinand_write_enable_op(struct spinand_device *spinand) +{ + struct spi_mem_op op = SPINAND_WR_EN_DIS_OP(true); + + return spi_mem_exec_op(spinand->spimem, &op); +} + +static int spinand_load_page_op(struct spinand_device *spinand, + const struct nand_page_io_req *req) +{ + struct nand_device *nand = spinand_to_nand(spinand); + unsigned int row = nanddev_pos_to_row(nand, &req->pos); + struct spi_mem_op op = SPINAND_PAGE_READ_OP(row); + + return spi_mem_exec_op(spinand->spimem, &op); +} + +static int spinand_read_from_cache_op(struct spinand_device *spinand, + const struct nand_page_io_req *req) +{ + struct spi_mem_op op = *spinand->op_templates.read_cache; + struct nand_device *nand = spinand_to_nand(spinand); + struct mtd_info *mtd = nanddev_to_mtd(nand); + struct nand_page_io_req adjreq = *req; + unsigned int nbytes = 0; + void *buf = NULL; + u16 column = 0; + int ret; + + if (req->datalen) { + adjreq.datalen = nanddev_page_size(nand); + adjreq.dataoffs = 0; + adjreq.databuf.in = spinand->databuf; + buf = spinand->databuf; + nbytes = adjreq.datalen; + } + + if (req->ooblen) { + adjreq.ooblen = nanddev_per_page_oobsize(nand); + adjreq.ooboffs = 0; + adjreq.oobbuf.in = spinand->oobbuf; + nbytes += nanddev_per_page_oobsize(nand); + if (!buf) { + buf = spinand->oobbuf; + column = nanddev_page_size(nand); + } + } + + spinand_cache_op_adjust_colum(spinand, &adjreq, &column); + op.addr.val = column; + + /* + * Some controllers are limited in term of max RX data size. In this + * case, just repeat the READ_CACHE operation after updating the + * column. + */ + while (nbytes) { + op.data.buf.in = buf; + op.data.nbytes = nbytes; + ret = spi_mem_adjust_op_size(spinand->spimem, &op); + if (ret) + return ret; + + ret = spi_mem_exec_op(spinand->spimem, &op); + if (ret) + return ret; + + buf += op.data.nbytes; + nbytes -= op.data.nbytes; + op.addr.val += op.data.nbytes; + } + + if (req->datalen) + memcpy(req->databuf.in, spinand->databuf + req->dataoffs, + req->datalen); + + if (req->ooblen) { + if (req->mode == MTD_OPS_AUTO_OOB) + mtd_ooblayout_get_databytes(mtd, req->oobbuf.in, + spinand->oobbuf, + req->ooboffs, + req->ooblen); + else + memcpy(req->oobbuf.in, spinand->oobbuf + req->ooboffs, + req->ooblen); + } + + return 0; +} + +static int spinand_write_to_cache_op(struct spinand_device *spinand, + const struct nand_page_io_req *req) +{ + struct spi_mem_op op = *spinand->op_templates.write_cache; + struct nand_device *nand = spinand_to_nand(spinand); + struct mtd_info *mtd = nanddev_to_mtd(nand); + struct nand_page_io_req adjreq = *req; + unsigned int nbytes = 0; + void *buf = NULL; + u16 column = 0; + int ret; + + memset(spinand->databuf, 0xff, + nanddev_page_size(nand) + + nanddev_per_page_oobsize(nand)); + + if (req->datalen) { + memcpy(spinand->databuf + req->dataoffs, req->databuf.out, + req->datalen); + adjreq.dataoffs = 0; + adjreq.datalen = nanddev_page_size(nand); + adjreq.databuf.out = spinand->databuf; + nbytes = adjreq.datalen; + buf = spinand->databuf; + } + + if (req->ooblen) { + if (req->mode == MTD_OPS_AUTO_OOB) + mtd_ooblayout_set_databytes(mtd, req->oobbuf.out, + spinand->oobbuf, + req->ooboffs, + req->ooblen); + else + memcpy(spinand->oobbuf + req->ooboffs, req->oobbuf.out, + req->ooblen); + + adjreq.ooblen = nanddev_per_page_oobsize(nand); + adjreq.ooboffs = 0; + nbytes += nanddev_per_page_oobsize(nand); + if (!buf) { + buf = spinand->oobbuf; + column = nanddev_page_size(nand); + } + } + + spinand_cache_op_adjust_colum(spinand, &adjreq, &column); + + op = *spinand->op_templates.write_cache; + op.addr.val = column; + + /* + * Some controllers are limited in term of max TX data size. In this + * case, split the operation into one LOAD CACHE and one or more + * LOAD RANDOM CACHE. + */ + while (nbytes) { + op.data.buf.out = buf; + op.data.nbytes = nbytes; + + ret = spi_mem_adjust_op_size(spinand->spimem, &op); + if (ret) + return ret; + + ret = spi_mem_exec_op(spinand->spimem, &op); + if (ret) + return ret; + + buf += op.data.nbytes; + nbytes -= op.data.nbytes; + op.addr.val += op.data.nbytes; + + /* + * We need to use the RANDOM LOAD CACHE operation if there's + * more than one iteration, because the LOAD operation resets + * the cache to 0xff. + */ + if (nbytes) { + column = op.addr.val; + op = *spinand->op_templates.update_cache; + op.addr.val = column; + } + } + + return 0; +} + +static int spinand_program_op(struct spinand_device *spinand, + const struct nand_page_io_req *req) +{ + struct nand_device *nand = spinand_to_nand(spinand); + unsigned int row = nanddev_pos_to_row(nand, &req->pos); + struct spi_mem_op op = SPINAND_PROG_EXEC_OP(row); + + return spi_mem_exec_op(spinand->spimem, &op); +} + +static int spinand_erase_op(struct spinand_device *spinand, + const struct nand_pos *pos) +{ + struct nand_device *nand = spinand_to_nand(spinand); + unsigned int row = nanddev_pos_to_row(nand, pos); + struct spi_mem_op op = SPINAND_BLK_ERASE_OP(row); + + return spi_mem_exec_op(spinand->spimem, &op); +} + +static int spinand_wait(struct spinand_device *spinand, u8 *s) +{ + unsigned long timeo = jiffies + msecs_to_jiffies(400); + u8 status; + int ret; + + do { + ret = spinand_read_status(spinand, &status); + if (ret) + return ret; + + if (!(status & STATUS_BUSY)) + goto out; + } while (time_before(jiffies, timeo)); + + /* + * Extra read, just in case the STATUS_READY bit has changed + * since our last check + */ + ret = spinand_read_status(spinand, &status); + if (ret) + return ret; + +out: + if (s) + *s = status; + + return status & STATUS_BUSY ? -ETIMEDOUT : 0; +} + +static int spinand_read_id_op(struct spinand_device *spinand, u8 *buf) +{ + struct spi_mem_op op = SPINAND_READID_OP(0, spinand->scratchbuf, + SPINAND_MAX_ID_LEN); + int ret; + + ret = spi_mem_exec_op(spinand->spimem, &op); + if (!ret) + memcpy(buf, spinand->scratchbuf, SPINAND_MAX_ID_LEN); + + return ret; +} + +static int spinand_reset_op(struct spinand_device *spinand) +{ + struct spi_mem_op op = SPINAND_RESET_OP; + int ret; + + ret = spi_mem_exec_op(spinand->spimem, &op); + if (ret) + return ret; + + return spinand_wait(spinand, NULL); +} + +static int spinand_lock_block(struct spinand_device *spinand, u8 lock) +{ + return spinand_write_reg_op(spinand, REG_BLOCK_LOCK, lock); +} + +static int spinand_check_ecc_status(struct spinand_device *spinand, u8 status) +{ + struct nand_device *nand = spinand_to_nand(spinand); + + if (spinand->eccinfo.get_status) + return spinand->eccinfo.get_status(spinand, status); + + switch (status & STATUS_ECC_MASK) { + case STATUS_ECC_NO_BITFLIPS: + return 0; + + case STATUS_ECC_HAS_BITFLIPS: + /* + * We have no way to know exactly how many bitflips have been + * fixed, so let's return the maximum possible value so that + * wear-leveling layers move the data immediately. + */ + return nand->eccreq.strength; + + case STATUS_ECC_UNCOR_ERROR: + return -EBADMSG; + + default: + break; + } + + return -EINVAL; +} + +static int spinand_read_page(struct spinand_device *spinand, + const struct nand_page_io_req *req, + bool ecc_enabled) +{ + u8 status; + int ret; + + ret = spinand_load_page_op(spinand, req); + if (ret) + return ret; + + ret = spinand_wait(spinand, &status); + if (ret < 0) + return ret; + + ret = spinand_read_from_cache_op(spinand, req); + if (ret) + return ret; + + if (!ecc_enabled) + return 0; + + return spinand_check_ecc_status(spinand, status); +} + +static int spinand_write_page(struct spinand_device *spinand, + const struct nand_page_io_req *req) +{ + u8 status; + int ret; + + ret = spinand_write_enable_op(spinand); + if (ret) + return ret; + + ret = spinand_write_to_cache_op(spinand, req); + if (ret) + return ret; + + ret = spinand_program_op(spinand, req); + if (ret) + return ret; + + ret = spinand_wait(spinand, &status); + if (!ret && (status & STATUS_PROG_FAILED)) + ret = -EIO; + + return ret; +} + +static int spinand_mtd_read(struct mtd_info *mtd, loff_t from, + struct mtd_oob_ops *ops) +{ + struct spinand_device *spinand = mtd_to_spinand(mtd); + struct nand_device *nand = mtd_to_nanddev(mtd); + unsigned int max_bitflips = 0; + struct nand_io_iter iter; + bool enable_ecc = false; + bool ecc_failed = false; + int ret = 0; + + if (ops->mode != MTD_OPS_RAW && spinand->eccinfo.ooblayout) + enable_ecc = true; + + mutex_lock(&spinand->lock); + + nanddev_io_for_each_page(nand, from, ops, &iter) { + ret = spinand_select_target(spinand, iter.req.pos.target); + if (ret) + break; + + ret = spinand_ecc_enable(spinand, enable_ecc); + if (ret) + break; + + ret = spinand_read_page(spinand, &iter.req, enable_ecc); + if (ret < 0 && ret != -EBADMSG) + break; + + if (ret == -EBADMSG) { + ecc_failed = true; + mtd->ecc_stats.failed++; + ret = 0; + } else { + mtd->ecc_stats.corrected += ret; + max_bitflips = max_t(unsigned int, max_bitflips, ret); + } + + ops->retlen += iter.req.datalen; + ops->oobretlen += iter.req.ooblen; + } + + mutex_unlock(&spinand->lock); + + if (ecc_failed && !ret) + ret = -EBADMSG; + + return ret ? ret : max_bitflips; +} + +static int spinand_mtd_write(struct mtd_info *mtd, loff_t to, + struct mtd_oob_ops *ops) +{ + struct spinand_device *spinand = mtd_to_spinand(mtd); + struct nand_device *nand = mtd_to_nanddev(mtd); + struct nand_io_iter iter; + bool enable_ecc = false; + int ret = 0; + + if (ops->mode != MTD_OPS_RAW && mtd->ooblayout) + enable_ecc = true; + + mutex_lock(&spinand->lock); + + nanddev_io_for_each_page(nand, to, ops, &iter) { + ret = spinand_select_target(spinand, iter.req.pos.target); + if (ret) + break; + + ret = spinand_ecc_enable(spinand, enable_ecc); + if (ret) + break; + + ret = spinand_write_page(spinand, &iter.req); + if (ret) + break; + + ops->retlen += iter.req.datalen; + ops->oobretlen += iter.req.ooblen; + } + + mutex_unlock(&spinand->lock); + + return ret; +} + +static bool spinand_isbad(struct nand_device *nand, const struct nand_pos *pos) +{ + struct spinand_device *spinand = nand_to_spinand(nand); + struct nand_page_io_req req = { + .pos = *pos, + .ooblen = 2, + .ooboffs = 0, + .oobbuf.in = spinand->oobbuf, + .mode = MTD_OPS_RAW, + }; + + memset(spinand->oobbuf, 0, 2); + spinand_select_target(spinand, pos->target); + spinand_read_page(spinand, &req, false); + if (spinand->oobbuf[0] != 0xff || spinand->oobbuf[1] != 0xff) + return true; + + return false; +} + +static int spinand_mtd_block_isbad(struct mtd_info *mtd, loff_t offs) +{ + struct nand_device *nand = mtd_to_nanddev(mtd); + struct spinand_device *spinand = nand_to_spinand(nand); + struct nand_pos pos; + int ret; + + nanddev_offs_to_pos(nand, offs, &pos); + mutex_lock(&spinand->lock); + ret = nanddev_isbad(nand, &pos); + mutex_unlock(&spinand->lock); + + return ret; +} + +static int spinand_markbad(struct nand_device *nand, const struct nand_pos *pos) +{ + struct spinand_device *spinand = nand_to_spinand(nand); + struct nand_page_io_req req = { + .pos = *pos, + .ooboffs = 0, + .ooblen = 2, + .oobbuf.out = spinand->oobbuf, + }; + int ret; + + /* Erase block before marking it bad. */ + ret = spinand_select_target(spinand, pos->target); + if (ret) + return ret; + + ret = spinand_write_enable_op(spinand); + if (ret) + return ret; + + spinand_erase_op(spinand, pos); + + memset(spinand->oobbuf, 0, 2); + return spinand_write_page(spinand, &req); +} + +static int spinand_mtd_block_markbad(struct mtd_info *mtd, loff_t offs) +{ + struct nand_device *nand = mtd_to_nanddev(mtd); + struct spinand_device *spinand = nand_to_spinand(nand); + struct nand_pos pos; + int ret; + + nanddev_offs_to_pos(nand, offs, &pos); + mutex_lock(&spinand->lock); + ret = nanddev_markbad(nand, &pos); + mutex_unlock(&spinand->lock); + + return ret; +} + +static int spinand_erase(struct nand_device *nand, const struct nand_pos *pos) +{ + struct spinand_device *spinand = nand_to_spinand(nand); + u8 status; + int ret; + + ret = spinand_select_target(spinand, pos->target); + if (ret) + return ret; + + ret = spinand_write_enable_op(spinand); + if (ret) + return ret; + + ret = spinand_erase_op(spinand, pos); + if (ret) + return ret; + + ret = spinand_wait(spinand, &status); + if (!ret && (status & STATUS_ERASE_FAILED)) + ret = -EIO; + + return ret; +} + +static int spinand_mtd_erase(struct mtd_info *mtd, + struct erase_info *einfo) +{ + struct spinand_device *spinand = mtd_to_spinand(mtd); + int ret; + + mutex_lock(&spinand->lock); + ret = nanddev_mtd_erase(mtd, einfo); + mutex_unlock(&spinand->lock); + + return ret; +} + +static int spinand_mtd_block_isreserved(struct mtd_info *mtd, loff_t offs) +{ + struct spinand_device *spinand = mtd_to_spinand(mtd); + struct nand_device *nand = mtd_to_nanddev(mtd); + struct nand_pos pos; + int ret; + + nanddev_offs_to_pos(nand, offs, &pos); + mutex_lock(&spinand->lock); + ret = nanddev_isreserved(nand, &pos); + mutex_unlock(&spinand->lock); + + return ret; +} + +static const struct nand_ops spinand_ops = { + .erase = spinand_erase, + .markbad = spinand_markbad, + .isbad = spinand_isbad, +}; + +static int spinand_manufacturer_detect(struct spinand_device *spinand) +{ + return -ENOTSUPP; +} + +static int spinand_manufacturer_init(struct spinand_device *spinand) +{ + if (spinand->manufacturer->ops->init) + return spinand->manufacturer->ops->init(spinand); + + return 0; +} + +static void spinand_manufacturer_cleanup(struct spinand_device *spinand) +{ + /* Release manufacturer private data */ + if (spinand->manufacturer->ops->cleanup) + return spinand->manufacturer->ops->cleanup(spinand); +} + +static const struct spi_mem_op * +spinand_select_op_variant(struct spinand_device *spinand, + const struct spinand_op_variants *variants) +{ + struct nand_device *nand = spinand_to_nand(spinand); + unsigned int i; + + for (i = 0; i < variants->nops; i++) { + struct spi_mem_op op = variants->ops[i]; + unsigned int nbytes; + int ret; + + nbytes = nanddev_per_page_oobsize(nand) + + nanddev_page_size(nand); + + while (nbytes) { + op.data.nbytes = nbytes; + ret = spi_mem_adjust_op_size(spinand->spimem, &op); + if (ret) + break; + + if (!spi_mem_supports_op(spinand->spimem, &op)) + break; + + nbytes -= op.data.nbytes; + } + + if (!nbytes) + return &variants->ops[i]; + } + + return NULL; +} + +/** + * spinand_match_and_init() - Try to find a match between a device ID and an + * entry in a spinand_info table + * @spinand: SPI NAND object + * @table: SPI NAND device description table + * @table_size: size of the device description table + * + * Should be used by SPI NAND manufacturer drivers when they want to find a + * match between a device ID retrieved through the READ_ID command and an + * entry in the SPI NAND description table. If a match is found, the spinand + * object will be initialized with information provided by the matching + * spinand_info entry. + * + * Return: 0 on success, a negative error code otherwise. + */ +int spinand_match_and_init(struct spinand_device *spinand, + const struct spinand_info *table, + unsigned int table_size, u8 devid) +{ + struct nand_device *nand = spinand_to_nand(spinand); + unsigned int i; + + for (i = 0; i < table_size; i++) { + const struct spinand_info *info = &table[i]; + const struct spi_mem_op *op; + + if (devid != info->devid) + continue; + + nand->memorg = table[i].memorg; + nand->eccreq = table[i].eccreq; + spinand->eccinfo = table[i].eccinfo; + spinand->flags = table[i].flags; + spinand->select_target = table[i].select_target; + + op = spinand_select_op_variant(spinand, + info->op_variants.read_cache); + if (!op) + return -ENOTSUPP; + + spinand->op_templates.read_cache = op; + + op = spinand_select_op_variant(spinand, + info->op_variants.write_cache); + if (!op) + return -ENOTSUPP; + + spinand->op_templates.write_cache = op; + + op = spinand_select_op_variant(spinand, + info->op_variants.update_cache); + spinand->op_templates.update_cache = op; + + return 0; + } + + return -ENOTSUPP; +} + +static int spinand_detect(struct spinand_device *spinand) +{ + struct device *dev = &spinand->spimem->spi->dev; + struct nand_device *nand = spinand_to_nand(spinand); + int ret; + + ret = spinand_reset_op(spinand); + if (ret) + return ret; + + ret = spinand_read_id_op(spinand, spinand->id.data); + if (ret) + return ret; + + spinand->id.len = SPINAND_MAX_ID_LEN; + + ret = spinand_manufacturer_detect(spinand); + if (ret) { + dev_err(dev, "unknown raw ID %*phN\n", SPINAND_MAX_ID_LEN, + spinand->id.data); + return ret; + } + + if (nand->memorg.ntargets > 1 && !spinand->select_target) { + dev_err(dev, + "SPI NANDs with more than one die must implement ->select_target()\n"); + return -EINVAL; + } + + dev_info(&spinand->spimem->spi->dev, + "%s SPI NAND was found.\n", spinand->manufacturer->name); + dev_info(&spinand->spimem->spi->dev, + "%llu MiB, block size: %zu KiB, page size: %zu, OOB size: %u\n", + nanddev_size(nand) >> 20, nanddev_eraseblock_size(nand) >> 10, + nanddev_page_size(nand), nanddev_per_page_oobsize(nand)); + + return 0; +} + +static int spinand_noecc_ooblayout_ecc(struct mtd_info *mtd, int section, + struct mtd_oob_region *region) +{ + return -ERANGE; +} + +static int spinand_noecc_ooblayout_free(struct mtd_info *mtd, int section, + struct mtd_oob_region *region) +{ + if (section) + return -ERANGE; + + /* Reserve 2 bytes for the BBM. */ + region->offset = 2; + region->length = 62; + + return 0; +} + +static const struct mtd_ooblayout_ops spinand_noecc_ooblayout = { + .ecc = spinand_noecc_ooblayout_ecc, + .free = spinand_noecc_ooblayout_free, +}; + +static int spinand_init(struct spinand_device *spinand) +{ + struct device *dev = &spinand->spimem->spi->dev; + struct mtd_info *mtd = spinand_to_mtd(spinand); + struct nand_device *nand = mtd_to_nanddev(mtd); + int ret, i; + + /* + * We need a scratch buffer because the spi_mem interface requires that + * buf passed in spi_mem_op->data.buf be DMA-able. + */ + spinand->scratchbuf = kzalloc(SPINAND_MAX_ID_LEN, GFP_KERNEL); + if (!spinand->scratchbuf) + return -ENOMEM; + + ret = spinand_detect(spinand); + if (ret) + goto err_free_bufs; + + /* + * Use kzalloc() instead of devm_kzalloc() here, because some drivers + * may use this buffer for DMA access. + * Memory allocated by devm_ does not guarantee DMA-safe alignment. + */ + spinand->databuf = kzalloc(nanddev_page_size(nand) + + nanddev_per_page_oobsize(nand), + GFP_KERNEL); + if (!spinand->databuf) { + ret = -ENOMEM; + goto err_free_bufs; + } + + spinand->oobbuf = spinand->databuf + nanddev_page_size(nand); + + ret = spinand_init_cfg_cache(spinand); + if (ret) + goto err_free_bufs; + + ret = spinand_init_quad_enable(spinand); + if (ret) + goto err_free_bufs; + + ret = spinand_upd_cfg(spinand, CFG_OTP_ENABLE, 0); + if (ret) + goto err_free_bufs; + + ret = spinand_manufacturer_init(spinand); + if (ret) { + dev_err(dev, + "Failed to initialize the SPI NAND chip (err = %d)\n", + ret); + goto err_free_bufs; + } + + /* After power up, all blocks are locked, so unlock them here. */ + for (i = 0; i < nand->memorg.ntargets; i++) { + ret = spinand_select_target(spinand, i); + if (ret) + goto err_free_bufs; + + ret = spinand_lock_block(spinand, BL_ALL_UNLOCKED); + if (ret) + goto err_free_bufs; + } + + ret = nanddev_init(nand, &spinand_ops, THIS_MODULE); + if (ret) + goto err_manuf_cleanup; + + /* + * Right now, we don't support ECC, so let the whole oob + * area is available for user. + */ + mtd->_read_oob = spinand_mtd_read; + mtd->_write_oob = spinand_mtd_write; + mtd->_block_isbad = spinand_mtd_block_isbad; + mtd->_block_markbad = spinand_mtd_block_markbad; + mtd->_block_isreserved = spinand_mtd_block_isreserved; + mtd->_erase = spinand_mtd_erase; + + if (spinand->eccinfo.ooblayout) + mtd_set_ooblayout(mtd, spinand->eccinfo.ooblayout); + else + mtd_set_ooblayout(mtd, &spinand_noecc_ooblayout); + + ret = mtd_ooblayout_count_freebytes(mtd); + if (ret < 0) + goto err_cleanup_nanddev; + + mtd->oobavail = ret; + + return 0; + +err_cleanup_nanddev: + nanddev_cleanup(nand); + +err_manuf_cleanup: + spinand_manufacturer_cleanup(spinand); + +err_free_bufs: + kfree(spinand->databuf); + kfree(spinand->scratchbuf); + return ret; +} + +static void spinand_cleanup(struct spinand_device *spinand) +{ + struct nand_device *nand = spinand_to_nand(spinand); + + nanddev_cleanup(nand); + spinand_manufacturer_cleanup(spinand); + kfree(spinand->databuf); + kfree(spinand->scratchbuf); +} + +static int spinand_probe(struct spi_mem *mem) +{ + struct spinand_device *spinand; + struct mtd_info *mtd; + int ret; + + spinand = devm_kzalloc(&mem->spi->dev, sizeof(*spinand), + GFP_KERNEL); + if (!spinand) + return -ENOMEM; + + spinand->spimem = mem; + spi_mem_set_drvdata(mem, spinand); + spinand_set_of_node(spinand, mem->spi->dev.of_node); + mutex_init(&spinand->lock); + mtd = spinand_to_mtd(spinand); + mtd->dev.parent = &mem->spi->dev; + + ret = spinand_init(spinand); + if (ret) + return ret; + + ret = mtd_device_register(mtd, NULL, 0); + if (ret) + goto err_spinand_cleanup; + + return 0; + +err_spinand_cleanup: + spinand_cleanup(spinand); + + return ret; +} + +static int spinand_remove(struct spi_mem *mem) +{ + struct spinand_device *spinand; + struct mtd_info *mtd; + int ret; + + spinand = spi_mem_get_drvdata(mem); + mtd = spinand_to_mtd(spinand); + + ret = mtd_device_unregister(mtd); + if (ret) + return ret; + + spinand_cleanup(spinand); + + return 0; +} + +static const struct spi_device_id spinand_ids[] = { + { .name = "spi-nand" }, + { /* sentinel */ }, +}; + +#ifdef CONFIG_OF +static const struct of_device_id spinand_of_ids[] = { + { .compatible = "spi-nand" }, + { /* sentinel */ }, +}; +#endif + +static struct spi_mem_driver spinand_drv = { + .spidrv = { + .id_table = spinand_ids, + .driver = { + .name = "spi-nand", + .of_match_table = of_match_ptr(spinand_of_ids), + }, + }, + .probe = spinand_probe, + .remove = spinand_remove, +}; +module_spi_mem_driver(spinand_drv); + +MODULE_DESCRIPTION("SPI NAND framework"); +MODULE_AUTHOR("Peter Pan"); +MODULE_LICENSE("GPL v2"); diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h new file mode 100644 index 000000000000..d3efe62dc9de --- /dev/null +++ b/include/linux/mtd/spinand.h @@ -0,0 +1,416 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2016-2017 Micron Technology, Inc. + * + * Authors: + * Peter Pan + */ +#ifndef __LINUX_MTD_SPINAND_H +#define __LINUX_MTD_SPINAND_H + +#include +#include +#include +#include +#include +#include +#include + +/** + * Standard SPI NAND flash operations + */ + +#define SPINAND_RESET_OP \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0xff, 1), \ + SPI_MEM_OP_NO_ADDR, \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_NO_DATA) + +#define SPINAND_WR_EN_DIS_OP(enable) \ + SPI_MEM_OP(SPI_MEM_OP_CMD((enable) ? 0x06 : 0x04, 1), \ + SPI_MEM_OP_NO_ADDR, \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_NO_DATA) + +#define SPINAND_READID_OP(ndummy, buf, len) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0x9f, 1), \ + SPI_MEM_OP_NO_ADDR, \ + SPI_MEM_OP_DUMMY(ndummy, 1), \ + SPI_MEM_OP_DATA_IN(len, buf, 1)) + +#define SPINAND_SET_FEATURE_OP(reg, valptr) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0x1f, 1), \ + SPI_MEM_OP_ADDR(1, reg, 1), \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_DATA_OUT(1, valptr, 1)) + +#define SPINAND_GET_FEATURE_OP(reg, valptr) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0x0f, 1), \ + SPI_MEM_OP_ADDR(1, reg, 1), \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_DATA_IN(1, valptr, 1)) + +#define SPINAND_BLK_ERASE_OP(addr) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0xd8, 1), \ + SPI_MEM_OP_ADDR(3, addr, 1), \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_NO_DATA) + +#define SPINAND_PAGE_READ_OP(addr) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0x13, 1), \ + SPI_MEM_OP_ADDR(3, addr, 1), \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_NO_DATA) + +#define SPINAND_PAGE_READ_FROM_CACHE_OP(fast, addr, ndummy, buf, len) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(fast ? 0x0b : 0x03, 1), \ + SPI_MEM_OP_ADDR(2, addr, 1), \ + SPI_MEM_OP_DUMMY(ndummy, 1), \ + SPI_MEM_OP_DATA_IN(len, buf, 1)) + +#define SPINAND_PAGE_READ_FROM_CACHE_X2_OP(addr, ndummy, buf, len) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0x3b, 1), \ + SPI_MEM_OP_ADDR(2, addr, 1), \ + SPI_MEM_OP_DUMMY(ndummy, 1), \ + SPI_MEM_OP_DATA_IN(len, buf, 2)) + +#define SPINAND_PAGE_READ_FROM_CACHE_X4_OP(addr, ndummy, buf, len) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0x6b, 1), \ + SPI_MEM_OP_ADDR(2, addr, 1), \ + SPI_MEM_OP_DUMMY(ndummy, 1), \ + SPI_MEM_OP_DATA_IN(len, buf, 4)) + +#define SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP(addr, ndummy, buf, len) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0xbb, 1), \ + SPI_MEM_OP_ADDR(2, addr, 2), \ + SPI_MEM_OP_DUMMY(ndummy, 2), \ + SPI_MEM_OP_DATA_IN(len, buf, 2)) + +#define SPINAND_PAGE_READ_FROM_CACHE_QUADIO_OP(addr, ndummy, buf, len) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0xeb, 1), \ + SPI_MEM_OP_ADDR(2, addr, 4), \ + SPI_MEM_OP_DUMMY(ndummy, 4), \ + SPI_MEM_OP_DATA_IN(len, buf, 4)) + +#define SPINAND_PROG_EXEC_OP(addr) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0x10, 1), \ + SPI_MEM_OP_ADDR(3, addr, 1), \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_NO_DATA) + +#define SPINAND_PROG_LOAD(reset, addr, buf, len) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(reset ? 0x02 : 0x84, 1), \ + SPI_MEM_OP_ADDR(2, addr, 1), \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_DATA_OUT(len, buf, 1)) + +#define SPINAND_PROG_LOAD_X4(reset, addr, buf, len) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(reset ? 0x32 : 0x34, 1), \ + SPI_MEM_OP_ADDR(2, addr, 1), \ + SPI_MEM_OP_NO_DUMMY, \ + SPI_MEM_OP_DATA_OUT(len, buf, 4)) + +/** + * Standard SPI NAND flash commands + */ +#define SPINAND_CMD_PROG_LOAD_X4 0x32 +#define SPINAND_CMD_PROG_LOAD_RDM_DATA_X4 0x34 + +/* feature register */ +#define REG_BLOCK_LOCK 0xa0 +#define BL_ALL_UNLOCKED 0x00 + +/* configuration register */ +#define REG_CFG 0xb0 +#define CFG_OTP_ENABLE BIT(6) +#define CFG_ECC_ENABLE BIT(4) +#define CFG_QUAD_ENABLE BIT(0) + +/* status register */ +#define REG_STATUS 0xc0 +#define STATUS_BUSY BIT(0) +#define STATUS_ERASE_FAILED BIT(2) +#define STATUS_PROG_FAILED BIT(3) +#define STATUS_ECC_MASK GENMASK(5, 4) +#define STATUS_ECC_NO_BITFLIPS (0 << 4) +#define STATUS_ECC_HAS_BITFLIPS (1 << 4) +#define STATUS_ECC_UNCOR_ERROR (2 << 4) + +struct spinand_op; +struct spinand_device; + +#define SPINAND_MAX_ID_LEN 4 + +/** + * struct spinand_id - SPI NAND id structure + * @data: buffer containing the id bytes. Currently 4 bytes large, but can + * be extended if required + * @len: ID length + * + * struct_spinand_id->data contains all bytes returned after a READ_ID command, + * including dummy bytes if the chip does not emit ID bytes right after the + * READ_ID command. The responsibility to extract real ID bytes is left to + * struct_manufacurer_ops->detect(). + */ +struct spinand_id { + u8 data[SPINAND_MAX_ID_LEN]; + int len; +}; + +/** + * struct manufacurer_ops - SPI NAND manufacturer specific operations + * @detect: detect a SPI NAND device. Every time a SPI NAND device is probed + * the core calls the struct_manufacurer_ops->detect() hook of each + * registered manufacturer until one of them return 1. Note that + * the first thing to check in this hook is that the manufacturer ID + * in struct_spinand_device->id matches the manufacturer whose + * ->detect() hook has been called. Should return 1 if there's a + * match, 0 if the manufacturer ID does not match and a negative + * error code otherwise. When true is returned, the core assumes + * that properties of the NAND chip (spinand->base.memorg and + * spinand->base.eccreq) have been filled + * @init: initialize a SPI NAND device + * @cleanup: cleanup a SPI NAND device + * + * Each SPI NAND manufacturer driver should implement this interface so that + * NAND chips coming from this vendor can be detected and initialized properly. + */ +struct spinand_manufacturer_ops { + int (*detect)(struct spinand_device *spinand); + int (*init)(struct spinand_device *spinand); + void (*cleanup)(struct spinand_device *spinand); +}; + +/** + * struct spinand_manufacturer - SPI NAND manufacturer instance + * @id: manufacturer ID + * @name: manufacturer name + * @ops: manufacturer operations + */ +struct spinand_manufacturer { + u8 id; + char *name; + const struct spinand_manufacturer_ops *ops; +}; + +/** + * struct spinand_op_variants - SPI NAND operation variants + * @ops: the list of variants for a given operation + * @nops: the number of variants + * + * Some operations like read-from-cache/write-to-cache have several variants + * depending on the number of IO lines you use to transfer data or address + * cycles. This structure is a way to describe the different variants supported + * by a chip and let the core pick the best one based on the SPI mem controller + * capabilities. + */ +struct spinand_op_variants { + const struct spi_mem_op *ops; + unsigned int nops; +}; + +#define SPINAND_OP_VARIANTS(name, ...) \ + const struct spinand_op_variants name = { \ + .ops = (struct spi_mem_op[]) { __VA_ARGS__ }, \ + .nops = sizeof((struct spi_mem_op[]){ __VA_ARGS__ }) / \ + sizeof(struct spi_mem_op), \ + } + +/** + * spinand_ecc_info - description of the on-die ECC implemented by a SPI NAND + * chip + * @get_status: get the ECC status. Should return a positive number encoding + * the number of corrected bitflips if correction was possible or + * -EBADMSG if there are uncorrectable errors. I can also return + * other negative error codes if the error is not caused by + * uncorrectable bitflips + * @ooblayout: the OOB layout used by the on-die ECC implementation + */ +struct spinand_ecc_info { + int (*get_status)(struct spinand_device *spinand, u8 status); + const struct mtd_ooblayout_ops *ooblayout; +}; + +#define SPINAND_HAS_QE_BIT BIT(0) + +/** + * struct spinand_info - Structure used to describe SPI NAND chips + * @model: model name + * @devid: device ID + * @flags: OR-ing of the SPINAND_XXX flags + * @memorg: memory organization + * @eccreq: ECC requirements + * @eccinfo: on-die ECC info + * @op_variants: operations variants + * @op_variants.read_cache: variants of the read-cache operation + * @op_variants.write_cache: variants of the write-cache operation + * @op_variants.update_cache: variants of the update-cache operation + * @select_target: function used to select a target/die. Required only for + * multi-die chips + * + * Each SPI NAND manufacturer driver should have a spinand_info table + * describing all the chips supported by the driver. + */ +struct spinand_info { + const char *model; + u8 devid; + u32 flags; + struct nand_memory_organization memorg; + struct nand_ecc_req eccreq; + struct spinand_ecc_info eccinfo; + struct { + const struct spinand_op_variants *read_cache; + const struct spinand_op_variants *write_cache; + const struct spinand_op_variants *update_cache; + } op_variants; + int (*select_target)(struct spinand_device *spinand, + unsigned int target); +}; + +#define SPINAND_INFO_OP_VARIANTS(__read, __write, __update) \ + { \ + .read_cache = __read, \ + .write_cache = __write, \ + .update_cache = __update, \ + } + +#define SPINAND_ECCINFO(__ooblayout, __get_status) \ + .eccinfo = { \ + .ooblayout = __ooblayout, \ + .get_status = __get_status, \ + } + +#define SPINAND_SELECT_TARGET(__func) \ + .select_target = __func, + +#define SPINAND_INFO(__model, __id, __memorg, __eccreq, __op_variants, \ + __flags, ...) \ + { \ + .model = __model, \ + .devid = __id, \ + .memorg = __memorg, \ + .eccreq = __eccreq, \ + .op_variants = __op_variants, \ + .flags = __flags, \ + __VA_ARGS__ \ + } + +/** + * struct spinand_device - SPI NAND device instance + * @base: NAND device instance + * @spimem: pointer to the SPI mem object + * @lock: lock used to serialize accesses to the NAND + * @id: NAND ID as returned by READ_ID + * @flags: NAND flags + * @op_templates: various SPI mem op templates + * @op_templates.read_cache: read cache op template + * @op_templates.write_cache: write cache op template + * @op_templates.update_cache: update cache op template + * @select_target: select a specific target/die. Usually called before sending + * a command addressing a page or an eraseblock embedded in + * this die. Only required if your chip exposes several dies + * @cur_target: currently selected target/die + * @eccinfo: on-die ECC information + * @cfg_cache: config register cache. One entry per die + * @databuf: bounce buffer for data + * @oobbuf: bounce buffer for OOB data + * @scratchbuf: buffer used for everything but page accesses. This is needed + * because the spi-mem interface explicitly requests that buffers + * passed in spi_mem_op be DMA-able, so we can't based the bufs on + * the stack + * @manufacturer: SPI NAND manufacturer information + * @priv: manufacturer private data + */ +struct spinand_device { + struct nand_device base; + struct spi_mem *spimem; + struct mutex lock; + struct spinand_id id; + u32 flags; + + struct { + const struct spi_mem_op *read_cache; + const struct spi_mem_op *write_cache; + const struct spi_mem_op *update_cache; + } op_templates; + + int (*select_target)(struct spinand_device *spinand, + unsigned int target); + unsigned int cur_target; + + struct spinand_ecc_info eccinfo; + + u8 *cfg_cache; + u8 *databuf; + u8 *oobbuf; + u8 *scratchbuf; + const struct spinand_manufacturer *manufacturer; + void *priv; +}; + +/** + * mtd_to_spinand() - Get the SPI NAND device attached to an MTD instance + * @mtd: MTD instance + * + * Return: the SPI NAND device attached to @mtd. + */ +static inline struct spinand_device *mtd_to_spinand(struct mtd_info *mtd) +{ + return container_of(mtd_to_nanddev(mtd), struct spinand_device, base); +} + +/** + * spinand_to_mtd() - Get the MTD device embedded in a SPI NAND device + * @spinand: SPI NAND device + * + * Return: the MTD device embedded in @spinand. + */ +static inline struct mtd_info *spinand_to_mtd(struct spinand_device *spinand) +{ + return nanddev_to_mtd(&spinand->base); +} + +/** + * nand_to_spinand() - Get the SPI NAND device embedding an NAND object + * @nand: NAND object + * + * Return: the SPI NAND device embedding @nand. + */ +static inline struct spinand_device *nand_to_spinand(struct nand_device *nand) +{ + return container_of(nand, struct spinand_device, base); +} + +/** + * spinand_to_nand() - Get the NAND device embedded in a SPI NAND object + * @spinand: SPI NAND device + * + * Return: the NAND device embedded in @spinand. + */ +static inline struct nand_device * +spinand_to_nand(struct spinand_device *spinand) +{ + return &spinand->base; +} + +/** + * spinand_set_of_node - Attach a DT node to a SPI NAND device + * @spinand: SPI NAND device + * @np: DT node + * + * Attach a DT node to a SPI NAND device. + */ +static inline void spinand_set_of_node(struct spinand_device *spinand, + struct device_node *np) +{ + nanddev_set_of_node(&spinand->base, np); +} + +int spinand_match_and_init(struct spinand_device *dev, + const struct spinand_info *table, + unsigned int table_size, u8 devid); + +int spinand_upd_cfg(struct spinand_device *spinand, u8 mask, u8 val); +int spinand_select_target(struct spinand_device *spinand, unsigned int target); + +#endif /* __LINUX_MTD_SPINAND_H */ diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h index bb4bd15ae1f6..4fa34a227a0f 100644 --- a/include/linux/spi/spi-mem.h +++ b/include/linux/spi/spi-mem.h @@ -3,7 +3,9 @@ * Copyright (C) 2018 Exceet Electronics GmbH * Copyright (C) 2018 Bootlin * - * Author: Boris Brezillon + * Author: + * Peter Pan + * Boris Brezillon */ #ifndef __LINUX_SPI_MEM_H -- cgit v1.2.3 From a508e8875e135d7a1df26d8131b5443cb07005ff Mon Sep 17 00:00:00 2001 From: Peter Pan Date: Fri, 22 Jun 2018 14:28:25 +0200 Subject: mtd: spinand: Add initial support for Micron MT29F2G01ABAGD Add a basic driver for Micron SPI NANDs. Only one device is supported right now, but the driver will be extended to support more devices afterwards. Signed-off-by: Peter Pan Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- drivers/mtd/nand/spi/Makefile | 2 +- drivers/mtd/nand/spi/core.c | 17 ++++++ drivers/mtd/nand/spi/micron.c | 133 ++++++++++++++++++++++++++++++++++++++++++ include/linux/mtd/spinand.h | 3 + 4 files changed, 154 insertions(+), 1 deletion(-) create mode 100644 drivers/mtd/nand/spi/micron.c (limited to 'include') diff --git a/drivers/mtd/nand/spi/Makefile b/drivers/mtd/nand/spi/Makefile index 2c473b765027..a1df25398f20 100644 --- a/drivers/mtd/nand/spi/Makefile +++ b/drivers/mtd/nand/spi/Makefile @@ -1,3 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 -spinand-objs := core.o +spinand-objs := core.o micron.o obj-$(CONFIG_MTD_SPI_NAND) += spinand.o diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c index 4efbeb0d85b4..9cc502d7e745 100644 --- a/drivers/mtd/nand/spi/core.c +++ b/drivers/mtd/nand/spi/core.c @@ -763,8 +763,25 @@ static const struct nand_ops spinand_ops = { .isbad = spinand_isbad, }; +static const struct spinand_manufacturer *spinand_manufacturers[] = { + µn_spinand_manufacturer, +}; + static int spinand_manufacturer_detect(struct spinand_device *spinand) { + unsigned int i; + int ret; + + for (i = 0; i < ARRAY_SIZE(spinand_manufacturers); i++) { + ret = spinand_manufacturers[i]->ops->detect(spinand); + if (ret > 0) { + spinand->manufacturer = spinand_manufacturers[i]; + return 0; + } else if (ret < 0) { + return ret; + } + } + return -ENOTSUPP; } diff --git a/drivers/mtd/nand/spi/micron.c b/drivers/mtd/nand/spi/micron.c new file mode 100644 index 000000000000..9c4381d6847b --- /dev/null +++ b/drivers/mtd/nand/spi/micron.c @@ -0,0 +1,133 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2016-2017 Micron Technology, Inc. + * + * Authors: + * Peter Pan + */ + +#include +#include +#include + +#define SPINAND_MFR_MICRON 0x2c + +#define MICRON_STATUS_ECC_MASK GENMASK(7, 4) +#define MICRON_STATUS_ECC_NO_BITFLIPS (0 << 4) +#define MICRON_STATUS_ECC_1TO3_BITFLIPS (1 << 4) +#define MICRON_STATUS_ECC_4TO6_BITFLIPS (3 << 4) +#define MICRON_STATUS_ECC_7TO8_BITFLIPS (5 << 4) + +static SPINAND_OP_VARIANTS(read_cache_variants, + SPINAND_PAGE_READ_FROM_CACHE_QUADIO_OP(0, 2, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_X4_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_X2_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_OP(true, 0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_OP(false, 0, 1, NULL, 0)); + +static SPINAND_OP_VARIANTS(write_cache_variants, + SPINAND_PROG_LOAD_X4(true, 0, NULL, 0), + SPINAND_PROG_LOAD(true, 0, NULL, 0)); + +static SPINAND_OP_VARIANTS(update_cache_variants, + SPINAND_PROG_LOAD_X4(false, 0, NULL, 0), + SPINAND_PROG_LOAD(false, 0, NULL, 0)); + +static int mt29f2g01abagd_ooblayout_ecc(struct mtd_info *mtd, int section, + struct mtd_oob_region *region) +{ + if (section) + return -ERANGE; + + region->offset = 64; + region->length = 64; + + return 0; +} + +static int mt29f2g01abagd_ooblayout_free(struct mtd_info *mtd, int section, + struct mtd_oob_region *region) +{ + if (section) + return -ERANGE; + + /* Reserve 2 bytes for the BBM. */ + region->offset = 2; + region->length = 62; + + return 0; +} + +static const struct mtd_ooblayout_ops mt29f2g01abagd_ooblayout = { + .ecc = mt29f2g01abagd_ooblayout_ecc, + .free = mt29f2g01abagd_ooblayout_free, +}; + +static int mt29f2g01abagd_ecc_get_status(struct spinand_device *spinand, + u8 status) +{ + switch (status & MICRON_STATUS_ECC_MASK) { + case STATUS_ECC_NO_BITFLIPS: + return 0; + + case STATUS_ECC_UNCOR_ERROR: + return -EBADMSG; + + case MICRON_STATUS_ECC_1TO3_BITFLIPS: + return 3; + + case MICRON_STATUS_ECC_4TO6_BITFLIPS: + return 6; + + case MICRON_STATUS_ECC_7TO8_BITFLIPS: + return 8; + + default: + break; + } + + return -EINVAL; +} + +static const struct spinand_info micron_spinand_table[] = { + SPINAND_INFO("MT29F2G01ABAGD", 0x24, + NAND_MEMORG(1, 2048, 128, 64, 2048, 2, 1, 1), + NAND_ECCREQ(8, 512), + SPINAND_INFO_OP_VARIANTS(&read_cache_variants, + &write_cache_variants, + &update_cache_variants), + 0, + SPINAND_ECCINFO(&mt29f2g01abagd_ooblayout, + mt29f2g01abagd_ecc_get_status)), +}; + +static int micron_spinand_detect(struct spinand_device *spinand) +{ + u8 *id = spinand->id.data; + int ret; + + /* + * Micron SPI NAND read ID need a dummy byte, + * so the first byte in raw_id is dummy. + */ + if (id[1] != SPINAND_MFR_MICRON) + return 0; + + ret = spinand_match_and_init(spinand, micron_spinand_table, + ARRAY_SIZE(micron_spinand_table), id[2]); + if (ret) + return ret; + + return 1; +} + +static const struct spinand_manufacturer_ops micron_spinand_manuf_ops = { + .detect = micron_spinand_detect, +}; + +const struct spinand_manufacturer micron_spinand_manufacturer = { + .id = SPINAND_MFR_MICRON, + .name = "Micron", + .ops = µn_spinand_manuf_ops, +}; diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h index d3efe62dc9de..717b272940f1 100644 --- a/include/linux/mtd/spinand.h +++ b/include/linux/mtd/spinand.h @@ -193,6 +193,9 @@ struct spinand_manufacturer { const struct spinand_manufacturer_ops *ops; }; +/* SPI NAND manufacturers */ +extern const struct spinand_manufacturer micron_spinand_manufacturer; + /** * struct spinand_op_variants - SPI NAND operation variants * @ops: the list of variants for a given operation -- cgit v1.2.3 From 1075492bb9e26312bc8ddeec1a93e2de5f9c76b4 Mon Sep 17 00:00:00 2001 From: Frieder Schrempf Date: Fri, 22 Jun 2018 14:28:26 +0200 Subject: mtd: spinand: Add initial support for Winbond W25M02GV Add support for the W25M02GV chip. Signed-off-by: Frieder Schrempf Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- drivers/mtd/nand/spi/Makefile | 2 +- drivers/mtd/nand/spi/core.c | 1 + drivers/mtd/nand/spi/winbond.c | 141 +++++++++++++++++++++++++++++++++++++++++ include/linux/mtd/spinand.h | 1 + 4 files changed, 144 insertions(+), 1 deletion(-) create mode 100644 drivers/mtd/nand/spi/winbond.c (limited to 'include') diff --git a/drivers/mtd/nand/spi/Makefile b/drivers/mtd/nand/spi/Makefile index a1df25398f20..100008d202ed 100644 --- a/drivers/mtd/nand/spi/Makefile +++ b/drivers/mtd/nand/spi/Makefile @@ -1,3 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 -spinand-objs := core.o micron.o +spinand-objs := core.o micron.o winbond.o obj-$(CONFIG_MTD_SPI_NAND) += spinand.o diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c index 9cc502d7e745..4803a6bfe8ec 100644 --- a/drivers/mtd/nand/spi/core.c +++ b/drivers/mtd/nand/spi/core.c @@ -765,6 +765,7 @@ static const struct nand_ops spinand_ops = { static const struct spinand_manufacturer *spinand_manufacturers[] = { µn_spinand_manufacturer, + &winbond_spinand_manufacturer, }; static int spinand_manufacturer_detect(struct spinand_device *spinand) diff --git a/drivers/mtd/nand/spi/winbond.c b/drivers/mtd/nand/spi/winbond.c new file mode 100644 index 000000000000..67baa1b32c00 --- /dev/null +++ b/drivers/mtd/nand/spi/winbond.c @@ -0,0 +1,141 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2017 exceet electronics GmbH + * + * Authors: + * Frieder Schrempf + * Boris Brezillon + */ + +#include +#include +#include + +#define SPINAND_MFR_WINBOND 0xEF + +#define WINBOND_CFG_BUF_READ BIT(3) + +static SPINAND_OP_VARIANTS(read_cache_variants, + SPINAND_PAGE_READ_FROM_CACHE_QUADIO_OP(0, 2, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_X4_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_X2_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_OP(true, 0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_OP(false, 0, 1, NULL, 0)); + +static SPINAND_OP_VARIANTS(write_cache_variants, + SPINAND_PROG_LOAD_X4(true, 0, NULL, 0), + SPINAND_PROG_LOAD(true, 0, NULL, 0)); + +static SPINAND_OP_VARIANTS(update_cache_variants, + SPINAND_PROG_LOAD_X4(false, 0, NULL, 0), + SPINAND_PROG_LOAD(false, 0, NULL, 0)); + +static int w25m02gv_ooblayout_ecc(struct mtd_info *mtd, int section, + struct mtd_oob_region *region) +{ + if (section > 3) + return -ERANGE; + + region->offset = (16 * section) + 8; + region->length = 8; + + return 0; +} + +static int w25m02gv_ooblayout_free(struct mtd_info *mtd, int section, + struct mtd_oob_region *region) +{ + if (section > 3) + return -ERANGE; + + region->offset = (16 * section) + 2; + region->length = 6; + + return 0; +} + +static const struct mtd_ooblayout_ops w25m02gv_ooblayout = { + .ecc = w25m02gv_ooblayout_ecc, + .free = w25m02gv_ooblayout_free, +}; + +static int w25m02gv_select_target(struct spinand_device *spinand, + unsigned int target) +{ + struct spi_mem_op op = SPI_MEM_OP(SPI_MEM_OP_CMD(0xc2, 1), + SPI_MEM_OP_NO_ADDR, + SPI_MEM_OP_NO_DUMMY, + SPI_MEM_OP_DATA_OUT(1, + spinand->scratchbuf, + 1)); + + *spinand->scratchbuf = target; + return spi_mem_exec_op(spinand->spimem, &op); +} + +static const struct spinand_info winbond_spinand_table[] = { + SPINAND_INFO("W25M02GV", 0xAB, + NAND_MEMORG(1, 2048, 64, 64, 1024, 1, 1, 2), + NAND_ECCREQ(1, 512), + SPINAND_INFO_OP_VARIANTS(&read_cache_variants, + &write_cache_variants, + &update_cache_variants), + 0, + SPINAND_ECCINFO(&w25m02gv_ooblayout, NULL), + SPINAND_SELECT_TARGET(w25m02gv_select_target)), +}; + +/** + * winbond_spinand_detect - initialize device related part in spinand_device + * struct if it is a Winbond device. + * @spinand: SPI NAND device structure + */ +static int winbond_spinand_detect(struct spinand_device *spinand) +{ + u8 *id = spinand->id.data; + int ret; + + /* + * Winbond SPI NAND read ID need a dummy byte, + * so the first byte in raw_id is dummy. + */ + if (id[1] != SPINAND_MFR_WINBOND) + return 0; + + ret = spinand_match_and_init(spinand, winbond_spinand_table, + ARRAY_SIZE(winbond_spinand_table), id[2]); + if (ret) + return ret; + + return 1; +} + +static int winbond_spinand_init(struct spinand_device *spinand) +{ + struct nand_device *nand = spinand_to_nand(spinand); + unsigned int i; + + /* + * Make sure all dies are in buffer read mode and not continuous read + * mode. + */ + for (i = 0; i < nand->memorg.ntargets; i++) { + spinand_select_target(spinand, i); + spinand_upd_cfg(spinand, WINBOND_CFG_BUF_READ, + WINBOND_CFG_BUF_READ); + } + + return 0; +} + +static const struct spinand_manufacturer_ops winbond_spinand_manuf_ops = { + .detect = winbond_spinand_detect, + .init = winbond_spinand_init, +}; + +const struct spinand_manufacturer winbond_spinand_manufacturer = { + .id = SPINAND_MFR_WINBOND, + .name = "Winbond", + .ops = &winbond_spinand_manuf_ops, +}; diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h index 717b272940f1..f0f16b9029e7 100644 --- a/include/linux/mtd/spinand.h +++ b/include/linux/mtd/spinand.h @@ -195,6 +195,7 @@ struct spinand_manufacturer { /* SPI NAND manufacturers */ extern const struct spinand_manufacturer micron_spinand_manufacturer; +extern const struct spinand_manufacturer winbond_spinand_manufacturer; /** * struct spinand_op_variants - SPI NAND operation variants -- cgit v1.2.3 From b02308af05e62c7d995f4fc75b0bc2ae3c3026f7 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 22 Jun 2018 14:28:27 +0200 Subject: mtd: spinand: Add initial support for the MX35LF1GE4AB chip Add minimal support for the MX35LF1GE4AB SPI NAND chip. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- drivers/mtd/nand/spi/Makefile | 2 +- drivers/mtd/nand/spi/core.c | 1 + drivers/mtd/nand/spi/macronix.c | 136 ++++++++++++++++++++++++++++++++++++++++ include/linux/mtd/spinand.h | 1 + 4 files changed, 139 insertions(+), 1 deletion(-) create mode 100644 drivers/mtd/nand/spi/macronix.c (limited to 'include') diff --git a/drivers/mtd/nand/spi/Makefile b/drivers/mtd/nand/spi/Makefile index 100008d202ed..b74e074b363a 100644 --- a/drivers/mtd/nand/spi/Makefile +++ b/drivers/mtd/nand/spi/Makefile @@ -1,3 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 -spinand-objs := core.o micron.o winbond.o +spinand-objs := core.o macronix.o micron.o winbond.o obj-$(CONFIG_MTD_SPI_NAND) += spinand.o diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c index 4803a6bfe8ec..30f83649c481 100644 --- a/drivers/mtd/nand/spi/core.c +++ b/drivers/mtd/nand/spi/core.c @@ -764,6 +764,7 @@ static const struct nand_ops spinand_ops = { }; static const struct spinand_manufacturer *spinand_manufacturers[] = { + ¯onix_spinand_manufacturer, µn_spinand_manufacturer, &winbond_spinand_manufacturer, }; diff --git a/drivers/mtd/nand/spi/macronix.c b/drivers/mtd/nand/spi/macronix.c new file mode 100644 index 000000000000..8ba3489d332a --- /dev/null +++ b/drivers/mtd/nand/spi/macronix.c @@ -0,0 +1,136 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2018 Macronix + * + * Author: Boris Brezillon + */ + +#include +#include +#include + +#define SPINAND_MFR_MACRONIX 0xC2 + +static SPINAND_OP_VARIANTS(read_cache_variants, + SPINAND_PAGE_READ_FROM_CACHE_X4_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_X2_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_OP(true, 0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_OP(false, 0, 1, NULL, 0)); + +static SPINAND_OP_VARIANTS(write_cache_variants, + SPINAND_PROG_LOAD_X4(true, 0, NULL, 0), + SPINAND_PROG_LOAD(true, 0, NULL, 0)); + +static SPINAND_OP_VARIANTS(update_cache_variants, + SPINAND_PROG_LOAD_X4(false, 0, NULL, 0), + SPINAND_PROG_LOAD(false, 0, NULL, 0)); + +static int mx35lfxge4ab_ooblayout_ecc(struct mtd_info *mtd, int section, + struct mtd_oob_region *region) +{ + return -ERANGE; +} + +static int mx35lfxge4ab_ooblayout_free(struct mtd_info *mtd, int section, + struct mtd_oob_region *region) +{ + if (section) + return -ERANGE; + + region->offset = 2; + region->length = mtd->oobsize - 2; + + return 0; +} + +static const struct mtd_ooblayout_ops mx35lfxge4ab_ooblayout = { + .ecc = mx35lfxge4ab_ooblayout_ecc, + .free = mx35lfxge4ab_ooblayout_free, +}; + +static int mx35lf1ge4ab_get_eccsr(struct spinand_device *spinand, u8 *eccsr) +{ + struct spi_mem_op op = SPI_MEM_OP(SPI_MEM_OP_CMD(0x7c, 1), + SPI_MEM_OP_NO_ADDR, + SPI_MEM_OP_DUMMY(1, 1), + SPI_MEM_OP_DATA_IN(1, eccsr, 1)); + + return spi_mem_exec_op(spinand->spimem, &op); +} + +static int mx35lf1ge4ab_ecc_get_status(struct spinand_device *spinand, + u8 status) +{ + struct nand_device *nand = spinand_to_nand(spinand); + u8 eccsr; + + switch (status & STATUS_ECC_MASK) { + case STATUS_ECC_NO_BITFLIPS: + return 0; + + case STATUS_ECC_UNCOR_ERROR: + return -EBADMSG; + + case STATUS_ECC_HAS_BITFLIPS: + /* + * Let's try to retrieve the real maximum number of bitflips + * in order to avoid forcing the wear-leveling layer to move + * data around if it's not necessary. + */ + if (mx35lf1ge4ab_get_eccsr(spinand, &eccsr)) + return nand->eccreq.strength; + + if (WARN_ON(eccsr > nand->eccreq.strength || !eccsr)) + return nand->eccreq.strength; + + return eccsr; + + default: + break; + } + + return -EINVAL; +} + +static const struct spinand_info macronix_spinand_table[] = { + SPINAND_INFO("MX35LF1GE4AB", 0x12, + NAND_MEMORG(1, 2048, 64, 64, 1024, 1, 1, 1), + NAND_ECCREQ(4, 512), + SPINAND_INFO_OP_VARIANTS(&read_cache_variants, + &write_cache_variants, + &update_cache_variants), + SPINAND_HAS_QE_BIT, + SPINAND_ECCINFO(&mx35lfxge4ab_ooblayout, + mx35lf1ge4ab_ecc_get_status)), +}; + +static int macronix_spinand_detect(struct spinand_device *spinand) +{ + u8 *id = spinand->id.data; + int ret; + + /* + * Macronix SPI NAND read ID needs a dummy byte, so the first byte in + * raw_id is garbage. + */ + if (id[1] != SPINAND_MFR_MACRONIX) + return 0; + + ret = spinand_match_and_init(spinand, macronix_spinand_table, + ARRAY_SIZE(macronix_spinand_table), + id[2]); + if (ret) + return ret; + + return 1; +} + +static const struct spinand_manufacturer_ops macronix_spinand_manuf_ops = { + .detect = macronix_spinand_detect, +}; + +const struct spinand_manufacturer macronix_spinand_manufacturer = { + .id = SPINAND_MFR_MACRONIX, + .name = "Macronix", + .ops = ¯onix_spinand_manuf_ops, +}; diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h index f0f16b9029e7..088ff96c3eb6 100644 --- a/include/linux/mtd/spinand.h +++ b/include/linux/mtd/spinand.h @@ -194,6 +194,7 @@ struct spinand_manufacturer { }; /* SPI NAND manufacturers */ +extern const struct spinand_manufacturer macronix_spinand_manufacturer; extern const struct spinand_manufacturer micron_spinand_manufacturer; extern const struct spinand_manufacturer winbond_spinand_manufacturer; -- cgit v1.2.3 From a4c025372d9d4756e7be98a98f5dde302c6df562 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 5 Jul 2018 12:27:27 +0200 Subject: mtd: rawnand: Remove nand_do_read() prototype from rawnand.h nand_do_read() is a static function implemented in nand_base.c. There's no good reason to expose its prototype in rawnand.h. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 0c6fb316b409..4d7a46c42900 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1545,8 +1545,6 @@ int nand_isreserved_bbt(struct mtd_info *mtd, loff_t offs); int nand_isbad_bbt(struct mtd_info *mtd, loff_t offs, int allowbbt); int nand_erase_nand(struct mtd_info *mtd, struct erase_info *instr, int allowbbt); -int nand_do_read(struct mtd_info *mtd, loff_t from, size_t len, - size_t *retlen, uint8_t *buf); /** * struct platform_nand_chip - chip level device structure -- cgit v1.2.3 From 707329aca6e0cf5781ca7f62c39bdcb5f87e9c23 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 5 Jul 2018 12:27:28 +0200 Subject: mtd: rawnand: Remove forward declaration of mtd_info struct mtd_info is defined in linux/mtd/mtd.h which is included at the beginning of nand_base.c, there's thus no need for the forward declaration of mtd_info. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 4d7a46c42900..32145b302585 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -23,7 +23,6 @@ #include #include -struct mtd_info; struct nand_flash_dev; struct device_node; -- cgit v1.2.3 From 1c3ab61ebcf8cfb5308d2e68e03fd4b4df484e62 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 5 Jul 2018 12:27:29 +0200 Subject: mtd: rawnand: Remove forward declaration of device_node struct device_node is defined in linux/of.h. Let's include this file instead of having a forward declaration of this struct. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 32145b302585..83ab6779144e 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -21,10 +21,10 @@ #include #include #include +#include #include struct nand_flash_dev; -struct device_node; /* Scan and identify a NAND device */ int nand_scan_with_ids(struct mtd_info *mtd, int max_chips, -- cgit v1.2.3 From 44b07b921dea5ec997fb929ceaa82582a7415816 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 5 Jul 2018 12:27:30 +0200 Subject: mtd: rawnand: Rename nand_default_bbt() into nand_create_bbt() Rename nand_default_bbt() into nand_create_bbt() and pass it a nand_chip object to prepare removal of the chip->scan_bbt() hook. We add a temporary nand_default_bbt() wrapper which will be dropped after the removal of ->scan_bbt(). Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/nand_base.c | 5 +++++ drivers/mtd/nand/raw/nand_bbt.c | 10 +++++----- include/linux/mtd/rawnand.h | 2 +- 3 files changed, 11 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index faac82b1e058..0476e13d47b1 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -4924,6 +4924,11 @@ static void nand_shutdown(struct mtd_info *mtd) nand_get_device(mtd, FL_PM_SUSPENDED); } +static int nand_default_bbt(struct mtd_info *mtd) +{ + return nand_create_bbt(mtd_to_nand(mtd)); +} + /* Set default functions */ static void nand_set_defaults(struct nand_chip *chip) { diff --git a/drivers/mtd/nand/raw/nand_bbt.c b/drivers/mtd/nand/raw/nand_bbt.c index d9f4ceff2568..39db352f8757 100644 --- a/drivers/mtd/nand/raw/nand_bbt.c +++ b/drivers/mtd/nand/raw/nand_bbt.c @@ -1349,15 +1349,14 @@ static int nand_create_badblock_pattern(struct nand_chip *this) } /** - * nand_default_bbt - [NAND Interface] Select a default bad block table for the device - * @mtd: MTD device structure + * nand_create_bbt - [NAND Interface] Select a default bad block table for the device + * @this: NAND chip object * * This function selects the default bad block table support for the device and * calls the nand_scan_bbt function. */ -int nand_default_bbt(struct mtd_info *mtd) +int nand_create_bbt(struct nand_chip *this) { - struct nand_chip *this = mtd_to_nand(mtd); int ret; /* Is a flash based bad block table requested? */ @@ -1383,8 +1382,9 @@ int nand_default_bbt(struct mtd_info *mtd) return ret; } - return nand_scan_bbt(mtd, this->badblock_pattern); + return nand_scan_bbt(nand_to_mtd(this), this->badblock_pattern); } +EXPORT_SYMBOL(nand_create_bbt); /** * nand_isreserved_bbt - [NAND Interface] Check if a block is reserved diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 83ab6779144e..186f9fb1e7eb 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1538,7 +1538,7 @@ extern const struct nand_manufacturer_ops micron_nand_manuf_ops; extern const struct nand_manufacturer_ops amd_nand_manuf_ops; extern const struct nand_manufacturer_ops macronix_nand_manuf_ops; -int nand_default_bbt(struct mtd_info *mtd); +int nand_create_bbt(struct nand_chip *chip); int nand_markbad_bbt(struct mtd_info *mtd, loff_t offs); int nand_isreserved_bbt(struct mtd_info *mtd, loff_t offs); int nand_isbad_bbt(struct mtd_info *mtd, loff_t offs, int allowbbt); -- cgit v1.2.3 From e80eba7581512625083ba540f120479b935425de Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 5 Jul 2018 12:27:31 +0200 Subject: mtd: rawnand: Kill the chip->scan_bbt() hook None of the existing drivers are overloading the ->scan_bbt() method, let's get rid of it and replace calls to ->scan_bbt() by nand_create_bbt() ones. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/diskonchip.c | 4 ++-- drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c | 2 +- drivers/mtd/nand/raw/nand_base.c | 9 +-------- drivers/mtd/nand/raw/nandsim.c | 2 +- include/linux/mtd/rawnand.h | 2 -- 5 files changed, 5 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/drivers/mtd/nand/raw/diskonchip.c b/drivers/mtd/nand/raw/diskonchip.c index 8d10061abb4b..3c46188dd6d2 100644 --- a/drivers/mtd/nand/raw/diskonchip.c +++ b/drivers/mtd/nand/raw/diskonchip.c @@ -1291,7 +1291,7 @@ static int __init nftl_scan_bbt(struct mtd_info *mtd) this->bbt_md = NULL; } - ret = this->scan_bbt(mtd); + ret = nand_create_bbt(this); if (ret) return ret; @@ -1338,7 +1338,7 @@ static int __init inftl_scan_bbt(struct mtd_info *mtd) this->bbt_md->pattern = "TBB_SYSM"; } - ret = this->scan_bbt(mtd); + ret = nand_create_bbt(this); if (ret) return ret; diff --git a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c index 58d4e4a93a93..599513321e71 100644 --- a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c +++ b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c @@ -1944,7 +1944,7 @@ static int gpmi_nand_init(struct gpmi_nand_data *this) ret = nand_boot_init(this); if (ret) goto err_nand_cleanup; - ret = chip->scan_bbt(mtd); + ret = nand_create_bbt(chip); if (ret) goto err_nand_cleanup; diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index 0476e13d47b1..4fa5e20d9690 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -4924,11 +4924,6 @@ static void nand_shutdown(struct mtd_info *mtd) nand_get_device(mtd, FL_PM_SUSPENDED); } -static int nand_default_bbt(struct mtd_info *mtd) -{ - return nand_create_bbt(mtd_to_nand(mtd)); -} - /* Set default functions */ static void nand_set_defaults(struct nand_chip *chip) { @@ -4970,8 +4965,6 @@ static void nand_set_defaults(struct nand_chip *chip) chip->write_byte = busw ? nand_write_byte16 : nand_write_byte; if (!chip->read_buf || chip->read_buf == nand_read_buf) chip->read_buf = busw ? nand_read_buf16 : nand_read_buf; - if (!chip->scan_bbt) - chip->scan_bbt = nand_default_bbt; if (!chip->controller) { chip->controller = &chip->hwcontrol; @@ -6673,7 +6666,7 @@ int nand_scan_tail(struct mtd_info *mtd) return 0; /* Build bad block table */ - ret = chip->scan_bbt(mtd); + ret = nand_create_bbt(chip); if (ret) goto err_nand_manuf_cleanup; diff --git a/drivers/mtd/nand/raw/nandsim.c b/drivers/mtd/nand/raw/nandsim.c index f8edacde49ab..8a3b36cfe5ea 100644 --- a/drivers/mtd/nand/raw/nandsim.c +++ b/drivers/mtd/nand/raw/nandsim.c @@ -2337,7 +2337,7 @@ static int __init ns_init_module(void) if ((retval = init_nandsim(nsmtd)) != 0) goto err_exit; - if ((retval = chip->scan_bbt(nsmtd)) != 0) + if ((retval = nand_create_bbt(chip)) != 0) goto err_exit; if ((retval = parse_badblocks(nand, nsmtd)) != 0) diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 186f9fb1e7eb..ac0007ddadf2 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1199,7 +1199,6 @@ int nand_op_parser_exec_op(struct nand_chip *chip, * @buf_align: minimum buffer alignment required by a platform * @hwcontrol: platform-specific hardware control structure * @erase: [REPLACEABLE] erase function - * @scan_bbt: [REPLACEABLE] function to scan bad block table * @chip_delay: [BOARDSPECIFIC] chip dependent delay for transferring * data from array to read regs (tR). * @state: [INTERN] the current state of the NAND device @@ -1292,7 +1291,6 @@ struct nand_chip { const struct nand_operation *op, bool check_only); int (*erase)(struct mtd_info *mtd, int page); - int (*scan_bbt)(struct mtd_info *mtd); int (*set_features)(struct mtd_info *mtd, struct nand_chip *chip, int feature_addr, uint8_t *subfeature_para); int (*get_features)(struct mtd_info *mtd, struct nand_chip *chip, -- cgit v1.2.3 From f0f01838f76420988b50b23f315704c9a5cd2fa9 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 5 Jul 2018 12:27:32 +0200 Subject: mtd: rawnand: orion_nand: Kill orion_nand_data.dev_ready() None of the boards seem to overload the ->dev_ready() hook, just drop this field from orion_nand_data. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/orion_nand.c | 3 --- include/linux/platform_data/mtd-orion_nand.h | 1 - 2 files changed, 4 deletions(-) (limited to 'include') diff --git a/drivers/mtd/nand/raw/orion_nand.c b/drivers/mtd/nand/raw/orion_nand.c index 7825fd3ce66b..1a4828442675 100644 --- a/drivers/mtd/nand/raw/orion_nand.c +++ b/drivers/mtd/nand/raw/orion_nand.c @@ -153,9 +153,6 @@ static int __init orion_nand_probe(struct platform_device *pdev) if (board->width == 16) nc->options |= NAND_BUSWIDTH_16; - if (board->dev_ready) - nc->dev_ready = board->dev_ready; - platform_set_drvdata(pdev, info); /* Not all platforms can gate the clock, so it is not diff --git a/include/linux/platform_data/mtd-orion_nand.h b/include/linux/platform_data/mtd-orion_nand.h index a7ce77c7c1a8..34828eb85982 100644 --- a/include/linux/platform_data/mtd-orion_nand.h +++ b/include/linux/platform_data/mtd-orion_nand.h @@ -12,7 +12,6 @@ */ struct orion_nand_data { struct mtd_partition *parts; - int (*dev_ready)(struct mtd_info *mtd); u32 nr_parts; u8 ale; /* address line number connected to ALE */ u8 cle; /* address line number connected to CLE */ -- cgit v1.2.3 From dc2d8856a758627d4f126d17bc113eedd72b2d60 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 5 Jul 2018 12:27:33 +0200 Subject: mtd: rawnand: plat_nand: Kill pdata->ctrl.{hwcontrol, read_byte}() None of the board files are overloading those hooks, so let's drop them from struct platform_nand_ctrl. Signed-off-by: Boris Brezillon Acked-by: Robert Jarzmik Signed-off-by: Miquel Raynal --- arch/arm/mach-pxa/balloon3.c | 1 - arch/arm/mach-pxa/em-x270.c | 1 - drivers/mtd/nand/raw/plat_nand.c | 2 -- include/linux/mtd/rawnand.h | 4 ---- 4 files changed, 8 deletions(-) (limited to 'include') diff --git a/arch/arm/mach-pxa/balloon3.c b/arch/arm/mach-pxa/balloon3.c index f4f8f23bda8c..af46d2182533 100644 --- a/arch/arm/mach-pxa/balloon3.c +++ b/arch/arm/mach-pxa/balloon3.c @@ -688,7 +688,6 @@ struct platform_nand_data balloon3_nand_pdata = { .chip_delay = 50, }, .ctrl = { - .hwcontrol = 0, .dev_ready = balloon3_nand_dev_ready, .select_chip = balloon3_nand_select_chip, .cmd_ctrl = balloon3_nand_cmd_ctl, diff --git a/arch/arm/mach-pxa/em-x270.c b/arch/arm/mach-pxa/em-x270.c index 49022ad338e9..29be04c6cc48 100644 --- a/arch/arm/mach-pxa/em-x270.c +++ b/arch/arm/mach-pxa/em-x270.c @@ -346,7 +346,6 @@ struct platform_nand_data em_x270_nand_platdata = { .chip_delay = 20, }, .ctrl = { - .hwcontrol = 0, .dev_ready = em_x270_nand_device_ready, .select_chip = 0, .cmd_ctrl = em_x270_nand_cmd_ctl, diff --git a/drivers/mtd/nand/raw/plat_nand.c b/drivers/mtd/nand/raw/plat_nand.c index 925a1323604d..222626df4b96 100644 --- a/drivers/mtd/nand/raw/plat_nand.c +++ b/drivers/mtd/nand/raw/plat_nand.c @@ -67,12 +67,10 @@ static int plat_nand_probe(struct platform_device *pdev) data->chip.select_chip = pdata->ctrl.select_chip; data->chip.write_buf = pdata->ctrl.write_buf; data->chip.read_buf = pdata->ctrl.read_buf; - data->chip.read_byte = pdata->ctrl.read_byte; data->chip.chip_delay = pdata->chip.chip_delay; data->chip.options |= pdata->chip.options; data->chip.bbt_options |= pdata->chip.bbt_options; - data->chip.ecc.hwctl = pdata->ctrl.hwcontrol; data->chip.ecc.mode = NAND_ECC_SOFT; data->chip.ecc.algo = NAND_ECC_HAMMING; diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index ac0007ddadf2..11c2426fc363 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1572,14 +1572,12 @@ struct platform_device; * struct platform_nand_ctrl - controller level device structure * @probe: platform specific function to probe/setup hardware * @remove: platform specific function to remove/teardown hardware - * @hwcontrol: platform specific hardware control structure * @dev_ready: platform specific function to read ready/busy pin * @select_chip: platform specific chip select function * @cmd_ctrl: platform specific function for controlling * ALE/CLE/nCE. Also used to write command and address * @write_buf: platform specific function for write buffer * @read_buf: platform specific function for read buffer - * @read_byte: platform specific function to read one byte from chip * @priv: private data to transport driver specific settings * * All fields are optional and depend on the hardware driver requirements @@ -1587,13 +1585,11 @@ struct platform_device; struct platform_nand_ctrl { int (*probe)(struct platform_device *pdev); void (*remove)(struct platform_device *pdev); - void (*hwcontrol)(struct mtd_info *mtd, int cmd); int (*dev_ready)(struct mtd_info *mtd); void (*select_chip)(struct mtd_info *mtd, int chip); void (*cmd_ctrl)(struct mtd_info *mtd, int dat, unsigned int ctrl); void (*write_buf)(struct mtd_info *mtd, const uint8_t *buf, int len); void (*read_buf)(struct mtd_info *mtd, uint8_t *buf, int len); - unsigned char (*read_byte)(struct mtd_info *mtd); void *priv; }; -- cgit v1.2.3 From dc2865ac3527d76fe04ee1f1a3ffc101a60faba0 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Mon, 9 Jul 2018 22:09:40 +0200 Subject: MIPS: txx9: Move the ndfc.h header to include/linux/platform_data/txx9 This way we will be able to compile the ndfmc driver when COMPILE_TEST=y. Signed-off-by: Boris Brezillon Acked-by: Paul Burton Signed-off-by: Miquel Raynal --- arch/mips/include/asm/txx9/ndfmc.h | 30 ------------------------------ arch/mips/txx9/generic/setup.c | 2 +- arch/mips/txx9/generic/setup_tx4938.c | 2 +- arch/mips/txx9/generic/setup_tx4939.c | 2 +- drivers/mtd/nand/raw/txx9ndfmc.c | 2 +- include/linux/platform_data/txx9/ndfmc.h | 30 ++++++++++++++++++++++++++++++ 6 files changed, 34 insertions(+), 34 deletions(-) delete mode 100644 arch/mips/include/asm/txx9/ndfmc.h create mode 100644 include/linux/platform_data/txx9/ndfmc.h (limited to 'include') diff --git a/arch/mips/include/asm/txx9/ndfmc.h b/arch/mips/include/asm/txx9/ndfmc.h deleted file mode 100644 index fa67f3df78fc..000000000000 --- a/arch/mips/include/asm/txx9/ndfmc.h +++ /dev/null @@ -1,30 +0,0 @@ -/* - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * (C) Copyright TOSHIBA CORPORATION 2007 - */ -#ifndef __ASM_TXX9_NDFMC_H -#define __ASM_TXX9_NDFMC_H - -#define NDFMC_PLAT_FLAG_USE_BSPRT 0x01 -#define NDFMC_PLAT_FLAG_NO_RSTR 0x02 -#define NDFMC_PLAT_FLAG_HOLDADD 0x04 -#define NDFMC_PLAT_FLAG_DUMMYWRITE 0x08 - -struct txx9ndfmc_platform_data { - unsigned int shift; - unsigned int gbus_clock; - unsigned int hold; /* hold time in nanosecond */ - unsigned int spw; /* strobe pulse width in nanosecond */ - unsigned int flags; - unsigned char ch_mask; /* available channel bitmask */ - unsigned char wp_mask; /* write-protect bitmask */ - unsigned char wide_mask; /* 16bit-nand bitmask */ -}; - -void txx9_ndfmc_init(unsigned long baseaddr, - const struct txx9ndfmc_platform_data *plat_data); - -#endif /* __ASM_TXX9_NDFMC_H */ diff --git a/arch/mips/txx9/generic/setup.c b/arch/mips/txx9/generic/setup.c index 1791a44ee570..aa47932abd28 100644 --- a/arch/mips/txx9/generic/setup.c +++ b/arch/mips/txx9/generic/setup.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include @@ -35,7 +36,6 @@ #include #include #include -#include #include #ifdef CONFIG_CPU_TX49XX #include diff --git a/arch/mips/txx9/generic/setup_tx4938.c b/arch/mips/txx9/generic/setup_tx4938.c index 85d1795652da..17395d5d15ca 100644 --- a/arch/mips/txx9/generic/setup_tx4938.c +++ b/arch/mips/txx9/generic/setup_tx4938.c @@ -17,13 +17,13 @@ #include #include #include +#include #include #include #include #include #include #include -#include #include #include diff --git a/arch/mips/txx9/generic/setup_tx4939.c b/arch/mips/txx9/generic/setup_tx4939.c index 274928987a21..360c388f4c82 100644 --- a/arch/mips/txx9/generic/setup_tx4939.c +++ b/arch/mips/txx9/generic/setup_tx4939.c @@ -21,13 +21,13 @@ #include #include #include +#include #include #include #include #include #include #include -#include #include #include diff --git a/drivers/mtd/nand/raw/txx9ndfmc.c b/drivers/mtd/nand/raw/txx9ndfmc.c index b567d212fe7d..04d57474ef97 100644 --- a/drivers/mtd/nand/raw/txx9ndfmc.c +++ b/drivers/mtd/nand/raw/txx9ndfmc.c @@ -20,7 +20,7 @@ #include #include #include -#include +#include /* TXX9 NDFMC Registers */ #define TXX9_NDFDTR 0x00 diff --git a/include/linux/platform_data/txx9/ndfmc.h b/include/linux/platform_data/txx9/ndfmc.h new file mode 100644 index 000000000000..fc172627d54e --- /dev/null +++ b/include/linux/platform_data/txx9/ndfmc.h @@ -0,0 +1,30 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * (C) Copyright TOSHIBA CORPORATION 2007 + */ +#ifndef __TXX9_NDFMC_H +#define __TXX9_NDFMC_H + +#define NDFMC_PLAT_FLAG_USE_BSPRT 0x01 +#define NDFMC_PLAT_FLAG_NO_RSTR 0x02 +#define NDFMC_PLAT_FLAG_HOLDADD 0x04 +#define NDFMC_PLAT_FLAG_DUMMYWRITE 0x08 + +struct txx9ndfmc_platform_data { + unsigned int shift; + unsigned int gbus_clock; + unsigned int hold; /* hold time in nanosecond */ + unsigned int spw; /* strobe pulse width in nanosecond */ + unsigned int flags; + unsigned char ch_mask; /* available channel bitmask */ + unsigned char wp_mask; /* write-protect bitmask */ + unsigned char wide_mask; /* 16bit-nand bitmask */ +}; + +void txx9_ndfmc_init(unsigned long baseaddr, + const struct txx9ndfmc_platform_data *plat_data); + +#endif /* __TXX9_NDFMC_H */ -- cgit v1.2.3 From e65e3a50702f4e7a01c0b36ff08d6ed8dde7ee7b Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Mon, 9 Jul 2018 22:09:42 +0200 Subject: MIPS: jz4740: Move jz4740_nand.h header to include/linux/platform_data/jz4740 This way we will be able to compile the jz4740_nand driver when COMPILE_TEST=y. Signed-off-by: Boris Brezillon Acked-by: Paul Burton Signed-off-by: Miquel Raynal --- arch/mips/include/asm/mach-jz4740/jz4740_nand.h | 34 ------------------------ arch/mips/jz4740/board-qi_lb60.c | 3 ++- drivers/mtd/nand/raw/jz4740_nand.c | 2 +- include/linux/platform_data/jz4740/jz4740_nand.h | 34 ++++++++++++++++++++++++ 4 files changed, 37 insertions(+), 36 deletions(-) delete mode 100644 arch/mips/include/asm/mach-jz4740/jz4740_nand.h create mode 100644 include/linux/platform_data/jz4740/jz4740_nand.h (limited to 'include') diff --git a/arch/mips/include/asm/mach-jz4740/jz4740_nand.h b/arch/mips/include/asm/mach-jz4740/jz4740_nand.h deleted file mode 100644 index f381d465e768..000000000000 --- a/arch/mips/include/asm/mach-jz4740/jz4740_nand.h +++ /dev/null @@ -1,34 +0,0 @@ -/* - * Copyright (C) 2009-2010, Lars-Peter Clausen - * JZ4740 SoC NAND controller driver - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 675 Mass Ave, Cambridge, MA 02139, USA. - * - */ - -#ifndef __ASM_MACH_JZ4740_JZ4740_NAND_H__ -#define __ASM_MACH_JZ4740_JZ4740_NAND_H__ - -#include -#include - -#define JZ_NAND_NUM_BANKS 4 - -struct jz_nand_platform_data { - int num_partitions; - struct mtd_partition *partitions; - - unsigned char banks[JZ_NAND_NUM_BANKS]; - - void (*ident_callback)(struct platform_device *, struct mtd_info *, - struct mtd_partition **, int *num_partitions); -}; - -#endif diff --git a/arch/mips/jz4740/board-qi_lb60.c b/arch/mips/jz4740/board-qi_lb60.c index 60f0767507c6..af0c8ace0141 100644 --- a/arch/mips/jz4740/board-qi_lb60.c +++ b/arch/mips/jz4740/board-qi_lb60.c @@ -29,10 +29,11 @@ #include #include +#include + #include #include #include -#include #include #include diff --git a/drivers/mtd/nand/raw/jz4740_nand.c b/drivers/mtd/nand/raw/jz4740_nand.c index 613b00a9604b..a0254461812d 100644 --- a/drivers/mtd/nand/raw/jz4740_nand.c +++ b/drivers/mtd/nand/raw/jz4740_nand.c @@ -25,7 +25,7 @@ #include -#include +#include #define JZ_REG_NAND_CTRL 0x50 #define JZ_REG_NAND_ECC_CTRL 0x100 diff --git a/include/linux/platform_data/jz4740/jz4740_nand.h b/include/linux/platform_data/jz4740/jz4740_nand.h new file mode 100644 index 000000000000..bc571f6d5ced --- /dev/null +++ b/include/linux/platform_data/jz4740/jz4740_nand.h @@ -0,0 +1,34 @@ +/* + * Copyright (C) 2009-2010, Lars-Peter Clausen + * JZ4740 SoC NAND controller driver + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, write to the Free Software Foundation, Inc., + * 675 Mass Ave, Cambridge, MA 02139, USA. + * + */ + +#ifndef __JZ4740_NAND_H__ +#define __JZ4740_NAND_H__ + +#include +#include + +#define JZ_NAND_NUM_BANKS 4 + +struct jz_nand_platform_data { + int num_partitions; + struct mtd_partition *partitions; + + unsigned char banks[JZ_NAND_NUM_BANKS]; + + void (*ident_callback)(struct platform_device *, struct mtd_info *, + struct mtd_partition **, int *num_partitions); +}; + +#endif -- cgit v1.2.3 From cb2b36f5a97df76f547fcc4ab444a02522fb6c96 Mon Sep 17 00:00:00 2001 From: Yi-Hung Wei Date: Mon, 2 Jul 2018 17:33:40 -0700 Subject: netfilter: nf_conncount: Switch to plain list Original patch is from Florian Westphal. This patch switches from hlist to plain list to store the list of connections with the same filtering key in nf_conncount. With the plain list, we can insert new connections at the tail, so over time the beginning of list holds long-running connections and those are expired, while the newly creates ones are at the end. Later on, we could probably move checked ones to the end of the list, so the next run has higher chance to reclaim stale entries in the front. Signed-off-by: Yi-Hung Wei Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_count.h | 15 ++++-- net/netfilter/nf_conncount.c | 83 ++++++++++++++++++------------ net/netfilter/nft_connlimit.c | 24 ++++----- 3 files changed, 75 insertions(+), 47 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_count.h b/include/net/netfilter/nf_conntrack_count.h index 3a188a0923a3..e4884e0e4f69 100644 --- a/include/net/netfilter/nf_conntrack_count.h +++ b/include/net/netfilter/nf_conntrack_count.h @@ -1,8 +1,15 @@ #ifndef _NF_CONNTRACK_COUNT_H #define _NF_CONNTRACK_COUNT_H +#include + struct nf_conncount_data; +struct nf_conncount_list { + struct list_head head; /* connections with the same filtering key */ + unsigned int count; /* length of list */ +}; + struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int family, unsigned int keylen); void nf_conncount_destroy(struct net *net, unsigned int family, @@ -14,15 +21,17 @@ unsigned int nf_conncount_count(struct net *net, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_zone *zone); -unsigned int nf_conncount_lookup(struct net *net, struct hlist_head *head, +unsigned int nf_conncount_lookup(struct net *net, struct nf_conncount_list *list, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_zone *zone, bool *addit); -bool nf_conncount_add(struct hlist_head *head, +void nf_conncount_list_init(struct nf_conncount_list *list); + +bool nf_conncount_add(struct nf_conncount_list *list, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_zone *zone); -void nf_conncount_cache_free(struct hlist_head *hhead); +void nf_conncount_cache_free(struct nf_conncount_list *list); #endif diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c index 81c02185b2e8..81b060adefef 100644 --- a/net/netfilter/nf_conncount.c +++ b/net/netfilter/nf_conncount.c @@ -44,7 +44,7 @@ /* we will save the tuples of all connections we care about */ struct nf_conncount_tuple { - struct hlist_node node; + struct list_head node; struct nf_conntrack_tuple tuple; struct nf_conntrack_zone zone; int cpu; @@ -53,7 +53,7 @@ struct nf_conncount_tuple { struct nf_conncount_rb { struct rb_node node; - struct hlist_head hhead; /* connections/hosts in same subnet */ + struct nf_conncount_list list; u32 key[MAX_KEYLEN]; }; @@ -82,12 +82,15 @@ static int key_diff(const u32 *a, const u32 *b, unsigned int klen) return memcmp(a, b, klen * sizeof(u32)); } -bool nf_conncount_add(struct hlist_head *head, +bool nf_conncount_add(struct nf_conncount_list *list, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_zone *zone) { struct nf_conncount_tuple *conn; + if (WARN_ON_ONCE(list->count > INT_MAX)) + return false; + conn = kmem_cache_alloc(conncount_conn_cachep, GFP_ATOMIC); if (conn == NULL) return false; @@ -95,13 +98,26 @@ bool nf_conncount_add(struct hlist_head *head, conn->zone = *zone; conn->cpu = raw_smp_processor_id(); conn->jiffies32 = (u32)jiffies; - hlist_add_head(&conn->node, head); + list_add_tail(&conn->node, &list->head); + list->count++; return true; } EXPORT_SYMBOL_GPL(nf_conncount_add); +static void conn_free(struct nf_conncount_list *list, + struct nf_conncount_tuple *conn) +{ + if (WARN_ON_ONCE(list->count == 0)) + return; + + list->count--; + list_del(&conn->node); + kmem_cache_free(conncount_conn_cachep, conn); +} + static const struct nf_conntrack_tuple_hash * -find_or_evict(struct net *net, struct nf_conncount_tuple *conn) +find_or_evict(struct net *net, struct nf_conncount_list *list, + struct nf_conncount_tuple *conn) { const struct nf_conntrack_tuple_hash *found; unsigned long a, b; @@ -121,30 +137,29 @@ find_or_evict(struct net *net, struct nf_conncount_tuple *conn) */ age = a - b; if (conn->cpu == cpu || age >= 2) { - hlist_del(&conn->node); - kmem_cache_free(conncount_conn_cachep, conn); + conn_free(list, conn); return ERR_PTR(-ENOENT); } return ERR_PTR(-EAGAIN); } -unsigned int nf_conncount_lookup(struct net *net, struct hlist_head *head, +unsigned int nf_conncount_lookup(struct net *net, + struct nf_conncount_list *list, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_zone *zone, bool *addit) { const struct nf_conntrack_tuple_hash *found; - struct nf_conncount_tuple *conn; + struct nf_conncount_tuple *conn, *conn_n; struct nf_conn *found_ct; - struct hlist_node *n; unsigned int length = 0; *addit = tuple ? true : false; /* check the saved connections */ - hlist_for_each_entry_safe(conn, n, head, node) { - found = find_or_evict(net, conn); + list_for_each_entry_safe(conn, conn_n, &list->head, node) { + found = find_or_evict(net, list, conn); if (IS_ERR(found)) { /* Not found, but might be about to be confirmed */ if (PTR_ERR(found) == -EAGAIN) { @@ -157,6 +172,7 @@ unsigned int nf_conncount_lookup(struct net *net, struct hlist_head *head, nf_ct_zone_id(zone, zone->dir)) *addit = false; } + continue; } @@ -176,8 +192,7 @@ unsigned int nf_conncount_lookup(struct net *net, struct hlist_head *head, * closed already -> ditch it */ nf_ct_put(found_ct); - hlist_del(&conn->node); - kmem_cache_free(conncount_conn_cachep, conn); + conn_free(list, conn); continue; } @@ -189,17 +204,23 @@ unsigned int nf_conncount_lookup(struct net *net, struct hlist_head *head, } EXPORT_SYMBOL_GPL(nf_conncount_lookup); +void nf_conncount_list_init(struct nf_conncount_list *list) +{ + INIT_LIST_HEAD(&list->head); + list->count = 1; +} +EXPORT_SYMBOL_GPL(nf_conncount_list_init); + static void nf_conncount_gc_list(struct net *net, - struct nf_conncount_rb *rbconn) + struct nf_conncount_list *list) { const struct nf_conntrack_tuple_hash *found; - struct nf_conncount_tuple *conn; - struct hlist_node *n; + struct nf_conncount_tuple *conn, *conn_n; struct nf_conn *found_ct; unsigned int collected = 0; - hlist_for_each_entry_safe(conn, n, &rbconn->hhead, node) { - found = find_or_evict(net, conn); + list_for_each_entry_safe(conn, conn_n, &list->head, node) { + found = find_or_evict(net, list, conn); if (IS_ERR(found)) { if (PTR_ERR(found) == -ENOENT) collected++; @@ -213,8 +234,7 @@ static void nf_conncount_gc_list(struct net *net, * closed already -> ditch it */ nf_ct_put(found_ct); - hlist_del(&conn->node); - kmem_cache_free(conncount_conn_cachep, conn); + conn_free(list, conn); collected++; continue; } @@ -271,14 +291,14 @@ count_tree(struct net *net, struct rb_root *root, /* same source network -> be counted! */ unsigned int count; - count = nf_conncount_lookup(net, &rbconn->hhead, tuple, + count = nf_conncount_lookup(net, &rbconn->list, tuple, zone, &addit); tree_nodes_free(root, gc_nodes, gc_count); if (!addit) return count; - if (!nf_conncount_add(&rbconn->hhead, tuple, zone)) + if (!nf_conncount_add(&rbconn->list, tuple, zone)) return 0; /* hotdrop */ return count + 1; @@ -287,8 +307,8 @@ count_tree(struct net *net, struct rb_root *root, if (no_gc || gc_count >= ARRAY_SIZE(gc_nodes)) continue; - nf_conncount_gc_list(net, rbconn); - if (hlist_empty(&rbconn->hhead)) + nf_conncount_gc_list(net, &rbconn->list); + if (list_empty(&rbconn->list.head)) gc_nodes[gc_count++] = rbconn; } @@ -322,8 +342,8 @@ count_tree(struct net *net, struct rb_root *root, conn->zone = *zone; memcpy(rbconn->key, key, sizeof(u32) * keylen); - INIT_HLIST_HEAD(&rbconn->hhead); - hlist_add_head(&conn->node, &rbconn->hhead); + nf_conncount_list_init(&rbconn->list); + list_add(&conn->node, &rbconn->list.head); rb_link_node(&rbconn->node, parent, rbnode); rb_insert_color(&rbconn->node, root); @@ -388,12 +408,11 @@ struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int family } EXPORT_SYMBOL_GPL(nf_conncount_init); -void nf_conncount_cache_free(struct hlist_head *hhead) +void nf_conncount_cache_free(struct nf_conncount_list *list) { - struct nf_conncount_tuple *conn; - struct hlist_node *n; + struct nf_conncount_tuple *conn, *conn_n; - hlist_for_each_entry_safe(conn, n, hhead, node) + list_for_each_entry_safe(conn, conn_n, &list->head, node) kmem_cache_free(conncount_conn_cachep, conn); } EXPORT_SYMBOL_GPL(nf_conncount_cache_free); @@ -408,7 +427,7 @@ static void destroy_tree(struct rb_root *r) rb_erase(node, r); - nf_conncount_cache_free(&rbconn->hhead); + nf_conncount_cache_free(&rbconn->list); kmem_cache_free(conncount_rb_cachep, rbconn); } diff --git a/net/netfilter/nft_connlimit.c b/net/netfilter/nft_connlimit.c index a832c59f0a9c..4f0491a36a1d 100644 --- a/net/netfilter/nft_connlimit.c +++ b/net/netfilter/nft_connlimit.c @@ -14,10 +14,10 @@ #include struct nft_connlimit { - spinlock_t lock; - struct hlist_head hhead; - u32 limit; - bool invert; + spinlock_t lock; + struct nf_conncount_list list; + u32 limit; + bool invert; }; static inline void nft_connlimit_do_eval(struct nft_connlimit *priv, @@ -46,13 +46,13 @@ static inline void nft_connlimit_do_eval(struct nft_connlimit *priv, } spin_lock_bh(&priv->lock); - count = nf_conncount_lookup(nft_net(pkt), &priv->hhead, tuple_ptr, zone, + count = nf_conncount_lookup(nft_net(pkt), &priv->list, tuple_ptr, zone, &addit); if (!addit) goto out; - if (!nf_conncount_add(&priv->hhead, tuple_ptr, zone)) { + if (!nf_conncount_add(&priv->list, tuple_ptr, zone)) { regs->verdict.code = NF_DROP; spin_unlock_bh(&priv->lock); return; @@ -88,7 +88,7 @@ static int nft_connlimit_do_init(const struct nft_ctx *ctx, } spin_lock_init(&priv->lock); - INIT_HLIST_HEAD(&priv->hhead); + nf_conncount_list_init(&priv->list); priv->limit = limit; priv->invert = invert; @@ -99,7 +99,7 @@ static void nft_connlimit_do_destroy(const struct nft_ctx *ctx, struct nft_connlimit *priv) { nf_ct_netns_put(ctx->net, ctx->family); - nf_conncount_cache_free(&priv->hhead); + nf_conncount_cache_free(&priv->list); } static int nft_connlimit_do_dump(struct sk_buff *skb, @@ -213,7 +213,7 @@ static int nft_connlimit_clone(struct nft_expr *dst, const struct nft_expr *src) struct nft_connlimit *priv_src = nft_expr_priv(src); spin_lock_init(&priv_dst->lock); - INIT_HLIST_HEAD(&priv_dst->hhead); + nf_conncount_list_init(&priv_dst->list); priv_dst->limit = priv_src->limit; priv_dst->invert = priv_src->invert; @@ -225,7 +225,7 @@ static void nft_connlimit_destroy_clone(const struct nft_ctx *ctx, { struct nft_connlimit *priv = nft_expr_priv(expr); - nf_conncount_cache_free(&priv->hhead); + nf_conncount_cache_free(&priv->list); } static bool nft_connlimit_gc(struct net *net, const struct nft_expr *expr) @@ -234,9 +234,9 @@ static bool nft_connlimit_gc(struct net *net, const struct nft_expr *expr) bool addit, ret; spin_lock_bh(&priv->lock); - nf_conncount_lookup(net, &priv->hhead, NULL, &nf_ct_zone_dflt, &addit); + nf_conncount_lookup(net, &priv->list, NULL, &nf_ct_zone_dflt, &addit); - ret = hlist_empty(&priv->hhead); + ret = list_empty(&priv->list.head); spin_unlock_bh(&priv->lock); return ret; -- cgit v1.2.3 From 976afca1ceba53df6f4a543014e15d1c7a962571 Mon Sep 17 00:00:00 2001 From: Yi-Hung Wei Date: Mon, 2 Jul 2018 17:33:41 -0700 Subject: netfilter: nf_conncount: Early exit in nf_conncount_lookup() and cleanup This patch is originally from Florian Westphal. This patch does the following three tasks. It applies the same early exit technique for nf_conncount_lookup(). Since now we keep the number of connections in 'struct nf_conncount_list', we no longer need to return the count in nf_conncount_lookup(). Moreover, we expose the garbage collection function nf_conncount_gc_list() for nft_connlimit. Signed-off-by: Yi-Hung Wei Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_count.h | 11 +++++---- net/netfilter/nf_conncount.c | 38 +++++++++++++++++------------- net/netfilter/nft_connlimit.c | 9 +++---- 3 files changed, 33 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_count.h b/include/net/netfilter/nf_conntrack_count.h index e4884e0e4f69..dbec17f674b7 100644 --- a/include/net/netfilter/nf_conntrack_count.h +++ b/include/net/netfilter/nf_conntrack_count.h @@ -21,10 +21,10 @@ unsigned int nf_conncount_count(struct net *net, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_zone *zone); -unsigned int nf_conncount_lookup(struct net *net, struct nf_conncount_list *list, - const struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_zone *zone, - bool *addit); +void nf_conncount_lookup(struct net *net, struct nf_conncount_list *list, + const struct nf_conntrack_tuple *tuple, + const struct nf_conntrack_zone *zone, + bool *addit); void nf_conncount_list_init(struct nf_conncount_list *list); @@ -32,6 +32,9 @@ bool nf_conncount_add(struct nf_conncount_list *list, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_zone *zone); +void nf_conncount_gc_list(struct net *net, + struct nf_conncount_list *list); + void nf_conncount_cache_free(struct nf_conncount_list *list); #endif diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c index 81b060adefef..7dfd9d5e6a3e 100644 --- a/net/netfilter/nf_conncount.c +++ b/net/netfilter/nf_conncount.c @@ -144,26 +144,29 @@ find_or_evict(struct net *net, struct nf_conncount_list *list, return ERR_PTR(-EAGAIN); } -unsigned int nf_conncount_lookup(struct net *net, - struct nf_conncount_list *list, - const struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_zone *zone, - bool *addit) +void nf_conncount_lookup(struct net *net, + struct nf_conncount_list *list, + const struct nf_conntrack_tuple *tuple, + const struct nf_conntrack_zone *zone, + bool *addit) { const struct nf_conntrack_tuple_hash *found; struct nf_conncount_tuple *conn, *conn_n; struct nf_conn *found_ct; - unsigned int length = 0; + unsigned int collect = 0; + /* best effort only */ *addit = tuple ? true : false; /* check the saved connections */ list_for_each_entry_safe(conn, conn_n, &list->head, node) { + if (collect > CONNCOUNT_GC_MAX_NODES) + break; + found = find_or_evict(net, list, conn); if (IS_ERR(found)) { /* Not found, but might be about to be confirmed */ if (PTR_ERR(found) == -EAGAIN) { - length++; if (!tuple) continue; @@ -171,8 +174,8 @@ unsigned int nf_conncount_lookup(struct net *net, nf_ct_zone_id(&conn->zone, conn->zone.dir) == nf_ct_zone_id(zone, zone->dir)) *addit = false; - } - + } else if (PTR_ERR(found) == -ENOENT) + collect++; continue; } @@ -181,9 +184,10 @@ unsigned int nf_conncount_lookup(struct net *net, if (tuple && nf_ct_tuple_equal(&conn->tuple, tuple) && nf_ct_zone_equal(found_ct, zone, zone->dir)) { /* - * Just to be sure we have it only once in the list. * We should not see tuples twice unless someone hooks * this into a table without "-p tcp --syn". + * + * Attempt to avoid a re-add in this case. */ *addit = false; } else if (already_closed(found_ct)) { @@ -193,14 +197,12 @@ unsigned int nf_conncount_lookup(struct net *net, */ nf_ct_put(found_ct); conn_free(list, conn); + collect++; continue; } nf_ct_put(found_ct); - length++; } - - return length; } EXPORT_SYMBOL_GPL(nf_conncount_lookup); @@ -211,8 +213,8 @@ void nf_conncount_list_init(struct nf_conncount_list *list) } EXPORT_SYMBOL_GPL(nf_conncount_list_init); -static void nf_conncount_gc_list(struct net *net, - struct nf_conncount_list *list) +void nf_conncount_gc_list(struct net *net, + struct nf_conncount_list *list) { const struct nf_conntrack_tuple_hash *found; struct nf_conncount_tuple *conn, *conn_n; @@ -244,6 +246,7 @@ static void nf_conncount_gc_list(struct net *net, return; } } +EXPORT_SYMBOL_GPL(nf_conncount_gc_list); static void tree_nodes_free(struct rb_root *root, struct nf_conncount_rb *gc_nodes[], @@ -291,8 +294,9 @@ count_tree(struct net *net, struct rb_root *root, /* same source network -> be counted! */ unsigned int count; - count = nf_conncount_lookup(net, &rbconn->list, tuple, - zone, &addit); + nf_conncount_lookup(net, &rbconn->list, tuple, zone, + &addit); + count = rbconn->list.count; tree_nodes_free(root, gc_nodes, gc_count); if (!addit) diff --git a/net/netfilter/nft_connlimit.c b/net/netfilter/nft_connlimit.c index 4f0491a36a1d..37c52ae06741 100644 --- a/net/netfilter/nft_connlimit.c +++ b/net/netfilter/nft_connlimit.c @@ -46,8 +46,9 @@ static inline void nft_connlimit_do_eval(struct nft_connlimit *priv, } spin_lock_bh(&priv->lock); - count = nf_conncount_lookup(nft_net(pkt), &priv->list, tuple_ptr, zone, - &addit); + nf_conncount_lookup(nft_net(pkt), &priv->list, tuple_ptr, zone, + &addit); + count = priv->list.count; if (!addit) goto out; @@ -231,10 +232,10 @@ static void nft_connlimit_destroy_clone(const struct nft_ctx *ctx, static bool nft_connlimit_gc(struct net *net, const struct nft_expr *expr) { struct nft_connlimit *priv = nft_expr_priv(expr); - bool addit, ret; + bool ret; spin_lock_bh(&priv->lock); - nf_conncount_lookup(net, &priv->list, NULL, &nf_ct_zone_dflt, &addit); + nf_conncount_gc_list(net, &priv->list); ret = list_empty(&priv->list.head); spin_unlock_bh(&priv->lock); -- cgit v1.2.3 From 5c789e131cbb997a528451564ea4613e812fc718 Mon Sep 17 00:00:00 2001 From: Yi-Hung Wei Date: Mon, 2 Jul 2018 17:33:44 -0700 Subject: netfilter: nf_conncount: Add list lock and gc worker, and RCU for init tree search This patch is originally from Florian Westphal. This patch does the following 3 main tasks. 1) Add list lock to 'struct nf_conncount_list' so that we can alter the lists containing the individual connections without holding the main tree lock. It would be useful when we only need to add/remove to/from a list without allocate/remove a node in the tree. With this change, we update nft_connlimit accordingly since we longer need to maintain a list lock in nft_connlimit now. 2) Use RCU for the initial tree search to improve tree look up performance. 3) Add a garbage collection worker. This worker is schedule when there are excessive tree node that needed to be recycled. Moreover,the rbnode reclaim logic is moved from search tree to insert tree to avoid race condition. Signed-off-by: Yi-Hung Wei Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_count.h | 17 +- net/netfilter/nf_conncount.c | 253 +++++++++++++++++++++-------- net/netfilter/nft_connlimit.c | 17 +- 3 files changed, 196 insertions(+), 91 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_count.h b/include/net/netfilter/nf_conntrack_count.h index dbec17f674b7..4b2b2baf8ab4 100644 --- a/include/net/netfilter/nf_conntrack_count.h +++ b/include/net/netfilter/nf_conntrack_count.h @@ -5,9 +5,17 @@ struct nf_conncount_data; +enum nf_conncount_list_add { + NF_CONNCOUNT_ADDED, /* list add was ok */ + NF_CONNCOUNT_ERR, /* -ENOMEM, must drop skb */ + NF_CONNCOUNT_SKIP, /* list is already reclaimed by gc */ +}; + struct nf_conncount_list { + spinlock_t list_lock; struct list_head head; /* connections with the same filtering key */ unsigned int count; /* length of list */ + bool dead; }; struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int family, @@ -28,11 +36,12 @@ void nf_conncount_lookup(struct net *net, struct nf_conncount_list *list, void nf_conncount_list_init(struct nf_conncount_list *list); -bool nf_conncount_add(struct nf_conncount_list *list, - const struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_zone *zone); +enum nf_conncount_list_add +nf_conncount_add(struct nf_conncount_list *list, + const struct nf_conntrack_tuple *tuple, + const struct nf_conntrack_zone *zone); -void nf_conncount_gc_list(struct net *net, +bool nf_conncount_gc_list(struct net *net, struct nf_conncount_list *list); void nf_conncount_cache_free(struct nf_conncount_list *list); diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c index 3f14806b7271..02ca7df793f5 100644 --- a/net/netfilter/nf_conncount.c +++ b/net/netfilter/nf_conncount.c @@ -49,12 +49,14 @@ struct nf_conncount_tuple { struct nf_conntrack_zone zone; int cpu; u32 jiffies32; + struct rcu_head rcu_head; }; struct nf_conncount_rb { struct rb_node node; struct nf_conncount_list list; u32 key[MAX_KEYLEN]; + struct rcu_head rcu_head; }; static spinlock_t nf_conncount_locks[CONNCOUNT_LOCK_SLOTS] __cacheline_aligned_in_smp; @@ -62,6 +64,10 @@ static spinlock_t nf_conncount_locks[CONNCOUNT_LOCK_SLOTS] __cacheline_aligned_i struct nf_conncount_data { unsigned int keylen; struct rb_root root[CONNCOUNT_SLOTS]; + struct net *net; + struct work_struct gc_work; + unsigned long pending_trees[BITS_TO_LONGS(CONNCOUNT_SLOTS)]; + unsigned int gc_tree; }; static u_int32_t conncount_rnd __read_mostly; @@ -82,42 +88,70 @@ static int key_diff(const u32 *a, const u32 *b, unsigned int klen) return memcmp(a, b, klen * sizeof(u32)); } -bool nf_conncount_add(struct nf_conncount_list *list, - const struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_zone *zone) +enum nf_conncount_list_add +nf_conncount_add(struct nf_conncount_list *list, + const struct nf_conntrack_tuple *tuple, + const struct nf_conntrack_zone *zone) { struct nf_conncount_tuple *conn; if (WARN_ON_ONCE(list->count > INT_MAX)) - return false; + return NF_CONNCOUNT_ERR; conn = kmem_cache_alloc(conncount_conn_cachep, GFP_ATOMIC); if (conn == NULL) - return false; + return NF_CONNCOUNT_ERR; + conn->tuple = *tuple; conn->zone = *zone; conn->cpu = raw_smp_processor_id(); conn->jiffies32 = (u32)jiffies; + spin_lock(&list->list_lock); + if (list->dead == true) { + kmem_cache_free(conncount_conn_cachep, conn); + spin_unlock(&list->list_lock); + return NF_CONNCOUNT_SKIP; + } list_add_tail(&conn->node, &list->head); list->count++; - return true; + spin_unlock(&list->list_lock); + return NF_CONNCOUNT_ADDED; } EXPORT_SYMBOL_GPL(nf_conncount_add); -static void conn_free(struct nf_conncount_list *list, +static void __conn_free(struct rcu_head *h) +{ + struct nf_conncount_tuple *conn; + + conn = container_of(h, struct nf_conncount_tuple, rcu_head); + kmem_cache_free(conncount_conn_cachep, conn); +} + +static bool conn_free(struct nf_conncount_list *list, struct nf_conncount_tuple *conn) { - if (WARN_ON_ONCE(list->count == 0)) - return; + bool free_entry = false; + + spin_lock(&list->list_lock); + + if (list->count == 0) { + spin_unlock(&list->list_lock); + return free_entry; + } list->count--; - list_del(&conn->node); - kmem_cache_free(conncount_conn_cachep, conn); + list_del_rcu(&conn->node); + if (list->count == 0) + free_entry = true; + + spin_unlock(&list->list_lock); + call_rcu(&conn->rcu_head, __conn_free); + return free_entry; } static const struct nf_conntrack_tuple_hash * find_or_evict(struct net *net, struct nf_conncount_list *list, - struct nf_conncount_tuple *conn) + struct nf_conncount_tuple *conn, bool *free_entry) { const struct nf_conntrack_tuple_hash *found; unsigned long a, b; @@ -137,7 +171,7 @@ find_or_evict(struct net *net, struct nf_conncount_list *list, */ age = a - b; if (conn->cpu == cpu || age >= 2) { - conn_free(list, conn); + *free_entry = conn_free(list, conn); return ERR_PTR(-ENOENT); } @@ -154,6 +188,7 @@ void nf_conncount_lookup(struct net *net, struct nf_conncount_tuple *conn, *conn_n; struct nf_conn *found_ct; unsigned int collect = 0; + bool free_entry = false; /* best effort only */ *addit = tuple ? true : false; @@ -163,7 +198,7 @@ void nf_conncount_lookup(struct net *net, if (collect > CONNCOUNT_GC_MAX_NODES) break; - found = find_or_evict(net, list, conn); + found = find_or_evict(net, list, conn, &free_entry); if (IS_ERR(found)) { /* Not found, but might be about to be confirmed */ if (PTR_ERR(found) == -EAGAIN) { @@ -208,24 +243,31 @@ EXPORT_SYMBOL_GPL(nf_conncount_lookup); void nf_conncount_list_init(struct nf_conncount_list *list) { + spin_lock_init(&list->list_lock); INIT_LIST_HEAD(&list->head); list->count = 1; + list->dead = false; } EXPORT_SYMBOL_GPL(nf_conncount_list_init); -void nf_conncount_gc_list(struct net *net, +/* Return true if the list is empty */ +bool nf_conncount_gc_list(struct net *net, struct nf_conncount_list *list) { const struct nf_conntrack_tuple_hash *found; struct nf_conncount_tuple *conn, *conn_n; struct nf_conn *found_ct; unsigned int collected = 0; + bool free_entry = false; list_for_each_entry_safe(conn, conn_n, &list->head, node) { - found = find_or_evict(net, list, conn); + found = find_or_evict(net, list, conn, &free_entry); if (IS_ERR(found)) { - if (PTR_ERR(found) == -ENOENT) + if (PTR_ERR(found) == -ENOENT) { + if (free_entry) + return true; collected++; + } continue; } @@ -236,18 +278,28 @@ void nf_conncount_gc_list(struct net *net, * closed already -> ditch it */ nf_ct_put(found_ct); - conn_free(list, conn); + if (conn_free(list, conn)) + return true; collected++; continue; } nf_ct_put(found_ct); if (collected > CONNCOUNT_GC_MAX_NODES) - return; + return false; } + return false; } EXPORT_SYMBOL_GPL(nf_conncount_gc_list); +static void __tree_nodes_free(struct rcu_head *h) +{ + struct nf_conncount_rb *rbconn; + + rbconn = container_of(h, struct nf_conncount_rb, rcu_head); + kmem_cache_free(conncount_rb_cachep, rbconn); +} + static void tree_nodes_free(struct rb_root *root, struct nf_conncount_rb *gc_nodes[], unsigned int gc_count) @@ -256,23 +308,39 @@ static void tree_nodes_free(struct rb_root *root, while (gc_count) { rbconn = gc_nodes[--gc_count]; - rb_erase(&rbconn->node, root); - kmem_cache_free(conncount_rb_cachep, rbconn); + spin_lock(&rbconn->list.list_lock); + if (rbconn->list.count == 0 && rbconn->list.dead == false) { + rbconn->list.dead = true; + rb_erase(&rbconn->node, root); + call_rcu(&rbconn->rcu_head, __tree_nodes_free); + } + spin_unlock(&rbconn->list.list_lock); } } +static void schedule_gc_worker(struct nf_conncount_data *data, int tree) +{ + set_bit(tree, data->pending_trees); + schedule_work(&data->gc_work); +} + static unsigned int -insert_tree(struct rb_root *root, +insert_tree(struct net *net, + struct nf_conncount_data *data, + struct rb_root *root, unsigned int hash, const u32 *key, u8 keylen, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_zone *zone) { + enum nf_conncount_list_add ret; + struct nf_conncount_rb *gc_nodes[CONNCOUNT_GC_MAX_NODES]; struct rb_node **rbnode, *parent; struct nf_conncount_rb *rbconn; struct nf_conncount_tuple *conn; - unsigned int count = 0; + unsigned int count = 0, gc_count = 0; + bool node_found = false; spin_lock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]); @@ -290,16 +358,44 @@ insert_tree(struct rb_root *root, rbnode = &((*rbnode)->rb_right); } else { /* unlikely: other cpu added node already */ - if (!nf_conncount_add(&rbconn->list, tuple, zone)) { + node_found = true; + ret = nf_conncount_add(&rbconn->list, tuple, zone); + if (ret == NF_CONNCOUNT_ERR) { count = 0; /* hotdrop */ - goto out_unlock; + } else if (ret == NF_CONNCOUNT_ADDED) { + count = rbconn->list.count; + } else { + /* NF_CONNCOUNT_SKIP, rbconn is already + * reclaimed by gc, insert a new tree node + */ + node_found = false; } - - count = rbconn->list.count; - goto out_unlock; + break; } + + if (gc_count >= ARRAY_SIZE(gc_nodes)) + continue; + + if (nf_conncount_gc_list(net, &rbconn->list)) + gc_nodes[gc_count++] = rbconn; + } + + if (gc_count) { + tree_nodes_free(root, gc_nodes, gc_count); + /* tree_node_free before new allocation permits + * allocator to re-use newly free'd object. + * + * This is a rare event; in most cases we will find + * existing node to re-use. (or gc_count is 0). + */ + + if (gc_count >= ARRAY_SIZE(gc_nodes)) + schedule_gc_worker(data, hash); } + if (node_found) + goto out_unlock; + /* expected case: match, insert new node */ rbconn = kmem_cache_alloc(conncount_rb_cachep, GFP_ATOMIC); if (rbconn == NULL) @@ -333,87 +429,97 @@ count_tree(struct net *net, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_zone *zone) { - struct nf_conncount_rb *gc_nodes[CONNCOUNT_GC_MAX_NODES]; + enum nf_conncount_list_add ret; struct rb_root *root; - struct rb_node **rbnode, *parent; + struct rb_node *parent; struct nf_conncount_rb *rbconn; - unsigned int gc_count, hash; - bool no_gc = false; - unsigned int count = 0; + unsigned int hash; u8 keylen = data->keylen; hash = jhash2(key, data->keylen, conncount_rnd) % CONNCOUNT_SLOTS; root = &data->root[hash]; - spin_lock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]); - restart: - gc_count = 0; - parent = NULL; - rbnode = &(root->rb_node); - while (*rbnode) { + parent = rcu_dereference_raw(root->rb_node); + while (parent) { int diff; bool addit; - rbconn = rb_entry(*rbnode, struct nf_conncount_rb, node); + rbconn = rb_entry(parent, struct nf_conncount_rb, node); - parent = *rbnode; diff = key_diff(key, rbconn->key, keylen); if (diff < 0) { - rbnode = &((*rbnode)->rb_left); + parent = rcu_dereference_raw(parent->rb_left); } else if (diff > 0) { - rbnode = &((*rbnode)->rb_right); + parent = rcu_dereference_raw(parent->rb_right); } else { /* same source network -> be counted! */ nf_conncount_lookup(net, &rbconn->list, tuple, zone, &addit); - count = rbconn->list.count; - tree_nodes_free(root, gc_nodes, gc_count); if (!addit) - goto out_unlock; + return rbconn->list.count; + + ret = nf_conncount_add(&rbconn->list, tuple, zone); + if (ret == NF_CONNCOUNT_ERR) { + return 0; /* hotdrop */ + } else if (ret == NF_CONNCOUNT_ADDED) { + return rbconn->list.count; + } else { + /* NF_CONNCOUNT_SKIP, rbconn is already + * reclaimed by gc, insert a new tree node + */ + break; + } + } + } - if (!nf_conncount_add(&rbconn->list, tuple, zone)) - count = 0; /* hotdrop */ - goto out_unlock; + if (!tuple) + return 0; - count++; - goto out_unlock; - } + return insert_tree(net, data, root, hash, key, keylen, tuple, zone); +} - if (no_gc || gc_count >= ARRAY_SIZE(gc_nodes)) - continue; +static void tree_gc_worker(struct work_struct *work) +{ + struct nf_conncount_data *data = container_of(work, struct nf_conncount_data, gc_work); + struct nf_conncount_rb *gc_nodes[CONNCOUNT_GC_MAX_NODES], *rbconn; + struct rb_root *root; + struct rb_node *node; + unsigned int tree, next_tree, gc_count = 0; + + tree = data->gc_tree % CONNCOUNT_LOCK_SLOTS; + root = &data->root[tree]; - nf_conncount_gc_list(net, &rbconn->list); - if (list_empty(&rbconn->list.head)) + rcu_read_lock(); + for (node = rb_first(root); node != NULL; node = rb_next(node)) { + rbconn = rb_entry(node, struct nf_conncount_rb, node); + if (nf_conncount_gc_list(data->net, &rbconn->list)) gc_nodes[gc_count++] = rbconn; } + rcu_read_unlock(); + + spin_lock_bh(&nf_conncount_locks[tree]); if (gc_count) { - no_gc = true; tree_nodes_free(root, gc_nodes, gc_count); - /* tree_node_free before new allocation permits - * allocator to re-use newly free'd object. - * - * This is a rare event; in most cases we will find - * existing node to re-use. (or gc_count is 0). - */ - goto restart; } - count = 0; - if (!tuple) - goto out_unlock; + clear_bit(tree, data->pending_trees); - spin_unlock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]); - return insert_tree(root, hash, key, keylen, tuple, zone); + next_tree = (tree + 1) % CONNCOUNT_SLOTS; + next_tree = find_next_bit(data->pending_trees, next_tree, CONNCOUNT_SLOTS); -out_unlock: - spin_unlock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]); - return count; + if (next_tree < CONNCOUNT_SLOTS) { + data->gc_tree = next_tree; + schedule_work(work); + } + + spin_unlock_bh(&nf_conncount_locks[tree]); } /* Count and return number of conntrack entries in 'net' with particular 'key'. * If 'tuple' is not null, insert it into the accounting data structure. + * Call with RCU read lock. */ unsigned int nf_conncount_count(struct net *net, struct nf_conncount_data *data, @@ -452,6 +558,8 @@ struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int family data->root[i] = RB_ROOT; data->keylen = keylen / sizeof(u32); + data->net = net; + INIT_WORK(&data->gc_work, tree_gc_worker); return data; } @@ -487,6 +595,7 @@ void nf_conncount_destroy(struct net *net, unsigned int family, { unsigned int i; + cancel_work_sync(&data->gc_work); nf_ct_netns_put(net, family); for (i = 0; i < ARRAY_SIZE(data->root); ++i) diff --git a/net/netfilter/nft_connlimit.c b/net/netfilter/nft_connlimit.c index 37c52ae06741..b90d96ba4a12 100644 --- a/net/netfilter/nft_connlimit.c +++ b/net/netfilter/nft_connlimit.c @@ -14,7 +14,6 @@ #include struct nft_connlimit { - spinlock_t lock; struct nf_conncount_list list; u32 limit; bool invert; @@ -45,7 +44,6 @@ static inline void nft_connlimit_do_eval(struct nft_connlimit *priv, return; } - spin_lock_bh(&priv->lock); nf_conncount_lookup(nft_net(pkt), &priv->list, tuple_ptr, zone, &addit); count = priv->list.count; @@ -53,14 +51,12 @@ static inline void nft_connlimit_do_eval(struct nft_connlimit *priv, if (!addit) goto out; - if (!nf_conncount_add(&priv->list, tuple_ptr, zone)) { + if (nf_conncount_add(&priv->list, tuple_ptr, zone) == NF_CONNCOUNT_ERR) { regs->verdict.code = NF_DROP; - spin_unlock_bh(&priv->lock); return; } count++; out: - spin_unlock_bh(&priv->lock); if ((count > priv->limit) ^ priv->invert) { regs->verdict.code = NFT_BREAK; @@ -88,7 +84,6 @@ static int nft_connlimit_do_init(const struct nft_ctx *ctx, invert = true; } - spin_lock_init(&priv->lock); nf_conncount_list_init(&priv->list); priv->limit = limit; priv->invert = invert; @@ -213,7 +208,6 @@ static int nft_connlimit_clone(struct nft_expr *dst, const struct nft_expr *src) struct nft_connlimit *priv_dst = nft_expr_priv(dst); struct nft_connlimit *priv_src = nft_expr_priv(src); - spin_lock_init(&priv_dst->lock); nf_conncount_list_init(&priv_dst->list); priv_dst->limit = priv_src->limit; priv_dst->invert = priv_src->invert; @@ -232,15 +226,8 @@ static void nft_connlimit_destroy_clone(const struct nft_ctx *ctx, static bool nft_connlimit_gc(struct net *net, const struct nft_expr *expr) { struct nft_connlimit *priv = nft_expr_priv(expr); - bool ret; - spin_lock_bh(&priv->lock); - nf_conncount_gc_list(net, &priv->list); - - ret = list_empty(&priv->list.head); - spin_unlock_bh(&priv->lock); - - return ret; + return nf_conncount_gc_list(net, &priv->list); } static struct nft_expr_type nft_connlimit_type; -- cgit v1.2.3 From ec1b28ca9674def4a158808a6493bdb87b993d81 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Fri, 6 Jul 2018 08:25:52 +0300 Subject: ipvs: provide just conn to ip_vs_state_name In preparation for followup patches, provide just the cp ptr to ip_vs_state_name. Signed-off-by: Julian Anastasov Signed-off-by: Pablo Neira Ayuso --- include/net/ip_vs.h | 2 +- net/netfilter/ipvs/ip_vs_conn.c | 8 ++++---- net/netfilter/ipvs/ip_vs_proto.c | 8 ++++---- 3 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index a0bec23c6d5e..4d76abcf1c41 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1221,7 +1221,7 @@ struct ip_vs_conn *ip_vs_conn_new(const struct ip_vs_conn_param *p, int dest_af, struct ip_vs_dest *dest, __u32 fwmark); void ip_vs_conn_expire_now(struct ip_vs_conn *cp); -const char *ip_vs_state_name(__u16 proto, int state); +const char *ip_vs_state_name(const struct ip_vs_conn *cp); void ip_vs_tcp_conn_listen(struct ip_vs_conn *cp); int ip_vs_check_template(struct ip_vs_conn *ct, struct ip_vs_dest *cdest); diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 99e0aa350dc5..de5a64e42ebd 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1107,7 +1107,7 @@ static int ip_vs_conn_seq_show(struct seq_file *seq, void *v) &cp->caddr.in6, ntohs(cp->cport), &cp->vaddr.in6, ntohs(cp->vport), dbuf, ntohs(cp->dport), - ip_vs_state_name(cp->protocol, cp->state), + ip_vs_state_name(cp), (cp->timer.expires-jiffies)/HZ, pe_data); else #endif @@ -1118,7 +1118,7 @@ static int ip_vs_conn_seq_show(struct seq_file *seq, void *v) ntohl(cp->caddr.ip), ntohs(cp->cport), ntohl(cp->vaddr.ip), ntohs(cp->vport), dbuf, ntohs(cp->dport), - ip_vs_state_name(cp->protocol, cp->state), + ip_vs_state_name(cp), (cp->timer.expires-jiffies)/HZ, pe_data); } return 0; @@ -1169,7 +1169,7 @@ static int ip_vs_conn_sync_seq_show(struct seq_file *seq, void *v) &cp->caddr.in6, ntohs(cp->cport), &cp->vaddr.in6, ntohs(cp->vport), dbuf, ntohs(cp->dport), - ip_vs_state_name(cp->protocol, cp->state), + ip_vs_state_name(cp), ip_vs_origin_name(cp->flags), (cp->timer.expires-jiffies)/HZ); else @@ -1181,7 +1181,7 @@ static int ip_vs_conn_sync_seq_show(struct seq_file *seq, void *v) ntohl(cp->caddr.ip), ntohs(cp->cport), ntohl(cp->vaddr.ip), ntohs(cp->vport), dbuf, ntohs(cp->dport), - ip_vs_state_name(cp->protocol, cp->state), + ip_vs_state_name(cp), ip_vs_origin_name(cp->flags), (cp->timer.expires-jiffies)/HZ); } diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c index ca880a3ad033..85c446621758 100644 --- a/net/netfilter/ipvs/ip_vs_proto.c +++ b/net/netfilter/ipvs/ip_vs_proto.c @@ -193,13 +193,13 @@ ip_vs_create_timeout_table(int *table, int size) } -const char * ip_vs_state_name(__u16 proto, int state) +const char *ip_vs_state_name(const struct ip_vs_conn *cp) { - struct ip_vs_protocol *pp = ip_vs_proto_get(proto); + struct ip_vs_protocol *pp = ip_vs_proto_get(cp->protocol); if (pp == NULL || pp->state_name == NULL) - return (IPPROTO_IP == proto) ? "NONE" : "ERR!"; - return pp->state_name(state); + return (cp->protocol == IPPROTO_IP) ? "NONE" : "ERR!"; + return pp->state_name(cp->state); } -- cgit v1.2.3 From 275411430f892407b885be1de2548b2e632892c3 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Fri, 6 Jul 2018 08:25:53 +0300 Subject: ipvs: add assured state for conn templates cp->state was not used for templates. Add support for state bits and for the first "assured" bit which indicates that some connection controlled by this template was established or assured by the real server. In a followup patch we will use it to drop templates under SYN attack. Signed-off-by: Julian Anastasov Signed-off-by: Pablo Neira Ayuso --- include/net/ip_vs.h | 16 ++++++++++++++++ net/netfilter/ipvs/ip_vs_proto.c | 17 +++++++++++++++-- net/netfilter/ipvs/ip_vs_proto_sctp.c | 2 ++ net/netfilter/ipvs/ip_vs_proto_tcp.c | 2 ++ net/netfilter/ipvs/ip_vs_proto_udp.c | 2 ++ net/netfilter/ipvs/ip_vs_sync.c | 18 ++++++------------ 6 files changed, 43 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 4d76abcf1c41..a0d2e0bb9a94 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -335,6 +335,11 @@ enum ip_vs_sctp_states { IP_VS_SCTP_S_LAST }; +/* Connection templates use bits from state */ +#define IP_VS_CTPL_S_NONE 0x0000 +#define IP_VS_CTPL_S_ASSURED 0x0001 +#define IP_VS_CTPL_S_LAST 0x0002 + /* Delta sequence info structure * Each ip_vs_conn has 2 (output AND input seq. changes). * Only used in the VS/NAT. @@ -1289,6 +1294,17 @@ ip_vs_control_add(struct ip_vs_conn *cp, struct ip_vs_conn *ctl_cp) atomic_inc(&ctl_cp->n_control); } +/* Mark our template as assured */ +static inline void +ip_vs_control_assure_ct(struct ip_vs_conn *cp) +{ + struct ip_vs_conn *ct = cp->control; + + if (ct && !(ct->state & IP_VS_CTPL_S_ASSURED) && + (ct->flags & IP_VS_CONN_F_TEMPLATE)) + ct->state |= IP_VS_CTPL_S_ASSURED; +} + /* IPVS netns init & cleanup functions */ int ip_vs_estimator_net_init(struct netns_ipvs *ipvs); int ip_vs_control_net_init(struct netns_ipvs *ipvs); diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c index 85c446621758..54ee84adf0bd 100644 --- a/net/netfilter/ipvs/ip_vs_proto.c +++ b/net/netfilter/ipvs/ip_vs_proto.c @@ -42,6 +42,11 @@ static struct ip_vs_protocol *ip_vs_proto_table[IP_VS_PROTO_TAB_SIZE]; +/* States for conn templates: NONE or words separated with ",", max 15 chars */ +static const char *ip_vs_ctpl_state_name_table[IP_VS_CTPL_S_LAST] = { + [IP_VS_CTPL_S_NONE] = "NONE", + [IP_VS_CTPL_S_ASSURED] = "ASSURED", +}; /* * register an ipvs protocol @@ -195,11 +200,19 @@ ip_vs_create_timeout_table(int *table, int size) const char *ip_vs_state_name(const struct ip_vs_conn *cp) { - struct ip_vs_protocol *pp = ip_vs_proto_get(cp->protocol); + unsigned int state = cp->state; + struct ip_vs_protocol *pp; + + if (cp->flags & IP_VS_CONN_F_TEMPLATE) { + if (state >= IP_VS_CTPL_S_LAST) + return "ERR!"; + return ip_vs_ctpl_state_name_table[state] ? : "?"; + } + pp = ip_vs_proto_get(cp->protocol); if (pp == NULL || pp->state_name == NULL) return (cp->protocol == IPPROTO_IP) ? "NONE" : "ERR!"; - return pp->state_name(cp->state); + return pp->state_name(state); } diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index 3250c4a1111e..b0cd7d08f2a7 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -461,6 +461,8 @@ set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, cp->flags &= ~IP_VS_CONN_F_INACTIVE; } } + if (next_state == IP_VS_SCTP_S_ESTABLISHED) + ip_vs_control_assure_ct(cp); } if (likely(pd)) cp->timeout = pd->timeout_table[cp->state = next_state]; diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index 80d10ad12a15..1770fc6ce960 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -569,6 +569,8 @@ set_tcp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, cp->flags &= ~IP_VS_CONN_F_INACTIVE; } } + if (new_state == IP_VS_TCP_S_ESTABLISHED) + ip_vs_control_assure_ct(cp); } if (likely(pd)) diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c index e0ef11c3691e..0f53c49025f8 100644 --- a/net/netfilter/ipvs/ip_vs_proto_udp.c +++ b/net/netfilter/ipvs/ip_vs_proto_udp.c @@ -460,6 +460,8 @@ udp_state_transition(struct ip_vs_conn *cp, int direction, } cp->timeout = pd->timeout_table[IP_VS_UDP_S_NORMAL]; + if (direction == IP_VS_DIR_OUTPUT) + ip_vs_control_assure_ct(cp); } static int __udp_init(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd) diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 001501e25625..d4020c5e831d 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1003,12 +1003,9 @@ static void ip_vs_process_message_v0(struct netns_ipvs *ipvs, const char *buffer continue; } } else { - /* protocol in templates is not used for state/timeout */ - if (state > 0) { - IP_VS_DBG(2, "BACKUP v0, Invalid template state %u\n", - state); - state = 0; - } + if (state >= IP_VS_CTPL_S_LAST) + IP_VS_DBG(7, "BACKUP v0, Invalid tpl state %u\n", + state); } ip_vs_conn_fill_param(ipvs, AF_INET, s->protocol, @@ -1166,12 +1163,9 @@ static inline int ip_vs_proc_sync_conn(struct netns_ipvs *ipvs, __u8 *p, __u8 *m goto out; } } else { - /* protocol in templates is not used for state/timeout */ - if (state > 0) { - IP_VS_DBG(3, "BACKUP, Invalid template state %u\n", - state); - state = 0; - } + if (state >= IP_VS_CTPL_S_LAST) + IP_VS_DBG(7, "BACKUP, Invalid tpl state %u\n", + state); } if (ip_vs_conn_fill_param_sync(ipvs, af, s, ¶m, pe_data, pe_data_len, pe_name, pe_name_len)) { -- cgit v1.2.3 From 440534d3c56be04abfb26850ee882d19d223557a Mon Sep 17 00:00:00 2001 From: Gao Feng Date: Mon, 9 Jul 2018 18:06:33 +0800 Subject: netfilter: Remove useless param helper of nf_ct_helper_ext_add The param helper of nf_ct_helper_ext_add is useless now, then remove it now. Signed-off-by: Gao Feng Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_helper.h | 4 +--- net/netfilter/nf_conntrack_core.c | 3 +-- net/netfilter/nf_conntrack_helper.c | 5 ++--- net/netfilter/nf_conntrack_netlink.c | 2 +- net/netfilter/nft_ct.c | 2 +- net/netfilter/xt_CT.c | 2 +- net/openvswitch/conntrack.c | 2 +- 7 files changed, 8 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h index 32c2a94a219d..2492120b8097 100644 --- a/include/net/netfilter/nf_conntrack_helper.h +++ b/include/net/netfilter/nf_conntrack_helper.h @@ -103,9 +103,7 @@ int nf_conntrack_helpers_register(struct nf_conntrack_helper *, unsigned int); void nf_conntrack_helpers_unregister(struct nf_conntrack_helper *, unsigned int); -struct nf_conn_help *nf_ct_helper_ext_add(struct nf_conn *ct, - struct nf_conntrack_helper *helper, - gfp_t gfp); +struct nf_conn_help *nf_ct_helper_ext_add(struct nf_conn *ct, gfp_t gfp); int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl, gfp_t flags); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 4ced7c7102b6..d97d7e9a9ee7 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1401,8 +1401,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, /* exp->master safe, refcnt bumped in nf_ct_find_expectation */ ct->master = exp->master; if (exp->helper) { - help = nf_ct_helper_ext_add(ct, exp->helper, - GFP_ATOMIC); + help = nf_ct_helper_ext_add(ct, GFP_ATOMIC); if (help) rcu_assign_pointer(help->helper, exp->helper); } diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index a55a58c706a9..d557a425289d 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -192,8 +192,7 @@ void nf_conntrack_helper_put(struct nf_conntrack_helper *helper) EXPORT_SYMBOL_GPL(nf_conntrack_helper_put); struct nf_conn_help * -nf_ct_helper_ext_add(struct nf_conn *ct, - struct nf_conntrack_helper *helper, gfp_t gfp) +nf_ct_helper_ext_add(struct nf_conn *ct, gfp_t gfp) { struct nf_conn_help *help; @@ -262,7 +261,7 @@ int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl, } if (help == NULL) { - help = nf_ct_helper_ext_add(ct, helper, flags); + help = nf_ct_helper_ext_add(ct, flags); if (help == NULL) return -ENOMEM; } else { diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 40152b9ad772..f981bfa8db72 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1947,7 +1947,7 @@ ctnetlink_create_conntrack(struct net *net, } else { struct nf_conn_help *help; - help = nf_ct_helper_ext_add(ct, helper, GFP_ATOMIC); + help = nf_ct_helper_ext_add(ct, GFP_ATOMIC); if (help == NULL) { err = -ENOMEM; goto err2; diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 1435ffc5f57e..3bc82ee5464d 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -870,7 +870,7 @@ static void nft_ct_helper_obj_eval(struct nft_object *obj, if (test_bit(IPS_HELPER_BIT, &ct->status)) return; - help = nf_ct_helper_ext_add(ct, to_assign, GFP_ATOMIC); + help = nf_ct_helper_ext_add(ct, GFP_ATOMIC); if (help) { rcu_assign_pointer(help->helper, to_assign); set_bit(IPS_HELPER_BIT, &ct->status); diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index 03b9a50ec93b..7ba454e9e3fa 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -93,7 +93,7 @@ xt_ct_set_helper(struct nf_conn *ct, const char *helper_name, return -ENOENT; } - help = nf_ct_helper_ext_add(ct, helper, GFP_KERNEL); + help = nf_ct_helper_ext_add(ct, GFP_KERNEL); if (help == NULL) { nf_conntrack_helper_put(helper); return -ENOMEM; diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index e05bd3e53f0f..3e33c382367f 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1303,7 +1303,7 @@ static int ovs_ct_add_helper(struct ovs_conntrack_info *info, const char *name, return -EINVAL; } - help = nf_ct_helper_ext_add(info->ct, helper, GFP_KERNEL); + help = nf_ct_helper_ext_add(info->ct, GFP_KERNEL); if (!help) { nf_conntrack_helper_put(helper); return -ENOMEM; -- cgit v1.2.3 From be2ab5b4d5c0bf041a34ec2e1397d50afbfb095e Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 11 Jul 2018 13:45:12 +0200 Subject: netfilter: nf_tables: take module reference when starting a batch Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nfnetlink.h | 1 + net/netfilter/nf_tables_api.c | 1 + net/netfilter/nfnetlink.c | 9 +++++++++ 3 files changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 3ecc3050be0e..4a520d3304a2 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -29,6 +29,7 @@ struct nfnetlink_subsystem { __u8 subsys_id; /* nfnetlink subsystem ID */ __u8 cb_count; /* number of callbacks */ const struct nfnl_callback *cb; /* callback for individual types */ + struct module *owner; int (*commit)(struct net *net, struct sk_buff *skb); int (*abort)(struct net *net, struct sk_buff *skb); void (*cleanup)(struct net *net); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 594b395442d6..c16c481fc52a 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -6603,6 +6603,7 @@ static const struct nfnetlink_subsystem nf_tables_subsys = { .abort = nf_tables_abort, .cleanup = nf_tables_cleanup, .valid_genid = nf_tables_valid_genid, + .owner = THIS_MODULE, }; int nft_chain_validate_dependency(const struct nft_chain *chain, diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 94f9bcaa0799..dd1d7bc23b03 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -337,7 +337,14 @@ replay: return kfree_skb(skb); } + if (!try_module_get(ss->owner)) { + nfnl_unlock(subsys_id); + netlink_ack(oskb, nlh, -EOPNOTSUPP, NULL); + return kfree_skb(skb); + } + if (!ss->valid_genid(net, genid)) { + module_put(ss->owner); nfnl_unlock(subsys_id); netlink_ack(oskb, nlh, -ERESTART, NULL); return kfree_skb(skb); @@ -472,6 +479,7 @@ done: nfnl_err_reset(&err_list); nfnl_unlock(subsys_id); kfree_skb(skb); + module_put(ss->owner); goto replay; } else if (status == NFNL_BATCH_DONE) { err = ss->commit(net, oskb); @@ -491,6 +499,7 @@ done: nfnl_err_deliver(&err_list, oskb); nfnl_unlock(subsys_id); kfree_skb(skb); + module_put(ss->owner); } static const struct nla_policy nfnl_batch_policy[NFNL_BATCH_MAX + 1] = { -- cgit v1.2.3 From f102d66b335a417d4848da9441f585695a838934 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 11 Jul 2018 13:45:14 +0200 Subject: netfilter: nf_tables: use dedicated mutex to guard transactions Continue to use nftnl subsys mutex to protect (un)registration of hook types, expressions and so on, but force batch operations to do their own locking. This allows distinct net namespaces to perform transactions in parallel. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netns/nftables.h | 1 + net/netfilter/nf_tables_api.c | 88 +++++++++++++++++++++++++++++++--------- net/netfilter/nfnetlink.c | 10 ++--- net/netfilter/nft_chain_filter.c | 4 +- net/netfilter/nft_dynset.c | 2 + 5 files changed, 77 insertions(+), 28 deletions(-) (limited to 'include') diff --git a/include/net/netns/nftables.h b/include/net/netns/nftables.h index 94767ea3a490..286fd960896f 100644 --- a/include/net/netns/nftables.h +++ b/include/net/netns/nftables.h @@ -7,6 +7,7 @@ struct netns_nftables { struct list_head tables; struct list_head commit_list; + struct mutex commit_mutex; unsigned int base_seq; u8 gencursor; u8 validate_state; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 68436edd9cdf..c0fb2bcd30fe 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -480,12 +480,19 @@ static void nft_request_module(struct net *net, const char *fmt, ...) if (WARN(ret >= MODULE_NAME_LEN, "truncated: '%s' (len %d)", module_name, ret)) return; - nfnl_unlock(NFNL_SUBSYS_NFTABLES); + mutex_unlock(&net->nft.commit_mutex); request_module("%s", module_name); - nfnl_lock(NFNL_SUBSYS_NFTABLES); + mutex_lock(&net->nft.commit_mutex); } #endif +static void lockdep_nfnl_nft_mutex_not_held(void) +{ +#ifdef CONFIG_PROVE_LOCKING + WARN_ON_ONCE(lockdep_nfnl_is_held(NFNL_SUBSYS_NFTABLES)); +#endif +} + static const struct nft_chain_type * nf_tables_chain_type_lookup(struct net *net, const struct nlattr *nla, u8 family, bool autoload) @@ -495,6 +502,8 @@ nf_tables_chain_type_lookup(struct net *net, const struct nlattr *nla, type = __nf_tables_chain_type_lookup(nla, family); if (type != NULL) return type; + + lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES if (autoload) { nft_request_module(net, "nft-chain-%u-%.*s", family, @@ -802,6 +811,7 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk, struct nft_ctx ctx; int err; + lockdep_assert_held(&net->nft.commit_mutex); attr = nla[NFTA_TABLE_NAME]; table = nft_table_lookup(net, attr, family, genmask); if (IS_ERR(table)) { @@ -1042,7 +1052,17 @@ nft_chain_lookup_byhandle(const struct nft_table *table, u64 handle, u8 genmask) return ERR_PTR(-ENOENT); } -static struct nft_chain *nft_chain_lookup(struct nft_table *table, +static bool lockdep_commit_lock_is_held(struct net *net) +{ +#ifdef CONFIG_PROVE_LOCKING + return lockdep_is_held(&net->nft.commit_mutex); +#else + return true; +#endif +} + +static struct nft_chain *nft_chain_lookup(struct net *net, + struct nft_table *table, const struct nlattr *nla, u8 genmask) { char search[NFT_CHAIN_MAXNAMELEN + 1]; @@ -1055,7 +1075,7 @@ static struct nft_chain *nft_chain_lookup(struct nft_table *table, nla_strlcpy(search, nla, sizeof(search)); WARN_ON(!rcu_read_lock_held() && - !lockdep_nfnl_is_held(NFNL_SUBSYS_NFTABLES)); + !lockdep_commit_lock_is_held(net)); chain = ERR_PTR(-ENOENT); rcu_read_lock(); @@ -1295,7 +1315,7 @@ static int nf_tables_getchain(struct net *net, struct sock *nlsk, return PTR_ERR(table); } - chain = nft_chain_lookup(table, nla[NFTA_CHAIN_NAME], genmask); + chain = nft_chain_lookup(net, table, nla[NFTA_CHAIN_NAME], genmask); if (IS_ERR(chain)) { NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_NAME]); return PTR_ERR(chain); @@ -1428,6 +1448,9 @@ static int nft_chain_parse_hook(struct net *net, struct net_device *dev; int err; + lockdep_assert_held(&net->nft.commit_mutex); + lockdep_nfnl_nft_mutex_not_held(); + err = nla_parse_nested(ha, NFTA_HOOK_MAX, nla[NFTA_CHAIN_HOOK], nft_hook_policy, NULL); if (err < 0) @@ -1662,7 +1685,8 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, nla[NFTA_CHAIN_NAME]) { struct nft_chain *chain2; - chain2 = nft_chain_lookup(table, nla[NFTA_CHAIN_NAME], genmask); + chain2 = nft_chain_lookup(ctx->net, table, + nla[NFTA_CHAIN_NAME], genmask); if (!IS_ERR(chain2)) return -EEXIST; } @@ -1724,6 +1748,8 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false; + lockdep_assert_held(&net->nft.commit_mutex); + table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TABLE]); @@ -1742,7 +1768,7 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, } attr = nla[NFTA_CHAIN_HANDLE]; } else { - chain = nft_chain_lookup(table, attr, genmask); + chain = nft_chain_lookup(net, table, attr, genmask); if (IS_ERR(chain)) { if (PTR_ERR(chain) != -ENOENT) { NL_SET_BAD_ATTR(extack, attr); @@ -1820,7 +1846,7 @@ static int nf_tables_delchain(struct net *net, struct sock *nlsk, chain = nft_chain_lookup_byhandle(table, handle, genmask); } else { attr = nla[NFTA_CHAIN_NAME]; - chain = nft_chain_lookup(table, attr, genmask); + chain = nft_chain_lookup(net, table, attr, genmask); } if (IS_ERR(chain)) { NL_SET_BAD_ATTR(extack, attr); @@ -1918,6 +1944,7 @@ static const struct nft_expr_type *nft_expr_type_get(struct net *net, if (type != NULL && try_module_get(type->owner)) return type; + lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES if (type == NULL) { nft_request_module(net, "nft-expr-%u-%.*s", family, @@ -2352,7 +2379,7 @@ static int nf_tables_getrule(struct net *net, struct sock *nlsk, return PTR_ERR(table); } - chain = nft_chain_lookup(table, nla[NFTA_RULE_CHAIN], genmask); + chain = nft_chain_lookup(net, table, nla[NFTA_RULE_CHAIN], genmask); if (IS_ERR(chain)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]); return PTR_ERR(chain); @@ -2386,6 +2413,7 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx, { struct nft_expr *expr; + lockdep_assert_held(&ctx->net->nft.commit_mutex); /* * Careful: some expressions might not be initialized in case this * is called on error from nf_tables_newrule(). @@ -2476,6 +2504,8 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, bool create; u64 handle, pos_handle; + lockdep_assert_held(&net->nft.commit_mutex); + create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false; table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask); @@ -2484,7 +2514,7 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, return PTR_ERR(table); } - chain = nft_chain_lookup(table, nla[NFTA_RULE_CHAIN], genmask); + chain = nft_chain_lookup(net, table, nla[NFTA_RULE_CHAIN], genmask); if (IS_ERR(chain)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]); return PTR_ERR(chain); @@ -2684,7 +2714,8 @@ static int nf_tables_delrule(struct net *net, struct sock *nlsk, } if (nla[NFTA_RULE_CHAIN]) { - chain = nft_chain_lookup(table, nla[NFTA_RULE_CHAIN], genmask); + chain = nft_chain_lookup(net, table, nla[NFTA_RULE_CHAIN], + genmask); if (IS_ERR(chain)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]); return PTR_ERR(chain); @@ -2776,6 +2807,8 @@ nft_select_set_ops(const struct nft_ctx *ctx, const struct nft_set_type *type; u32 flags = 0; + lockdep_assert_held(&ctx->net->nft.commit_mutex); + lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES if (list_empty(&nf_tables_set_types)) { nft_request_module(ctx->net, "nft-set"); @@ -4820,6 +4853,7 @@ nft_obj_type_get(struct net *net, u32 objtype) if (type != NULL && try_module_get(type->owner)) return type; + lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES if (type == NULL) { nft_request_module(net, "nft-obj-%u", objtype); @@ -5379,6 +5413,7 @@ nft_flowtable_type_get(struct net *net, u8 family) if (type != NULL && try_module_get(type->owner)) return type; + lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES if (type == NULL) { nft_request_module(net, "nf-flowtable-%u", family); @@ -6232,9 +6267,9 @@ static void nf_tables_commit_chain_active(struct net *net, struct nft_chain *cha next_genbit = nft_gencursor_next(net); g0 = rcu_dereference_protected(chain->rules_gen_0, - lockdep_nfnl_is_held(NFNL_SUBSYS_NFTABLES)); + lockdep_commit_lock_is_held(net)); g1 = rcu_dereference_protected(chain->rules_gen_1, - lockdep_nfnl_is_held(NFNL_SUBSYS_NFTABLES)); + lockdep_commit_lock_is_held(net)); /* No changes to this chain? */ if (chain->rules_next == NULL) { @@ -6442,6 +6477,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nf_tables_commit_release(net); nf_tables_gen_notify(net, skb, NFT_MSG_NEWGEN); + mutex_unlock(&net->nft.commit_mutex); return 0; } @@ -6593,12 +6629,25 @@ static void nf_tables_cleanup(struct net *net) static int nf_tables_abort(struct net *net, struct sk_buff *skb) { - return __nf_tables_abort(net); + int ret = __nf_tables_abort(net); + + mutex_unlock(&net->nft.commit_mutex); + + return ret; } static bool nf_tables_valid_genid(struct net *net, u32 genid) { - return genid == 0 || net->nft.base_seq == genid; + bool genid_ok; + + mutex_lock(&net->nft.commit_mutex); + + genid_ok = genid == 0 || net->nft.base_seq == genid; + if (!genid_ok) + mutex_unlock(&net->nft.commit_mutex); + + /* else, commit mutex has to be released by commit or abort function */ + return genid_ok; } static const struct nfnetlink_subsystem nf_tables_subsys = { @@ -6937,8 +6986,8 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, case NFT_GOTO: if (!tb[NFTA_VERDICT_CHAIN]) return -EINVAL; - chain = nft_chain_lookup(ctx->table, tb[NFTA_VERDICT_CHAIN], - genmask); + chain = nft_chain_lookup(ctx->net, ctx->table, + tb[NFTA_VERDICT_CHAIN], genmask); if (IS_ERR(chain)) return PTR_ERR(chain); if (nft_is_base_chain(chain)) @@ -7183,6 +7232,7 @@ static int __net_init nf_tables_init_net(struct net *net) { INIT_LIST_HEAD(&net->nft.tables); INIT_LIST_HEAD(&net->nft.commit_list); + mutex_init(&net->nft.commit_mutex); net->nft.base_seq = 1; net->nft.validate_state = NFT_VALIDATE_SKIP; @@ -7191,11 +7241,11 @@ static int __net_init nf_tables_init_net(struct net *net) static void __net_exit nf_tables_exit_net(struct net *net) { - nfnl_lock(NFNL_SUBSYS_NFTABLES); + mutex_lock(&net->nft.commit_mutex); if (!list_empty(&net->nft.commit_list)) __nf_tables_abort(net); __nft_release_tables(net); - nfnl_unlock(NFNL_SUBSYS_NFTABLES); + mutex_unlock(&net->nft.commit_mutex); WARN_ON_ONCE(!list_empty(&net->nft.tables)); } diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index dd1d7bc23b03..916913454624 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -350,6 +350,8 @@ replay: return kfree_skb(skb); } + nfnl_unlock(subsys_id); + while (skb->len >= nlmsg_total_size(0)) { int msglen, type; @@ -471,13 +473,8 @@ ack: } done: if (status & NFNL_BATCH_REPLAY) { - const struct nfnetlink_subsystem *ss2; - - ss2 = nfnl_dereference_protected(subsys_id); - if (ss2 == ss) - ss->abort(net, oskb); + ss->abort(net, oskb); nfnl_err_reset(&err_list); - nfnl_unlock(subsys_id); kfree_skb(skb); module_put(ss->owner); goto replay; @@ -497,7 +494,6 @@ done: ss->cleanup(net); nfnl_err_deliver(&err_list, oskb); - nfnl_unlock(subsys_id); kfree_skb(skb); module_put(ss->owner); } diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c index d21834bed805..ea5b7c4944f6 100644 --- a/net/netfilter/nft_chain_filter.c +++ b/net/netfilter/nft_chain_filter.c @@ -322,7 +322,7 @@ static int nf_tables_netdev_event(struct notifier_block *this, if (!ctx.net) return NOTIFY_DONE; - nfnl_lock(NFNL_SUBSYS_NFTABLES); + mutex_lock(&ctx.net->nft.commit_mutex); list_for_each_entry(table, &ctx.net->nft.tables, list) { if (table->family != NFPROTO_NETDEV) continue; @@ -337,7 +337,7 @@ static int nf_tables_netdev_event(struct notifier_block *this, nft_netdev_event(event, dev, &ctx); } } - nfnl_unlock(NFNL_SUBSYS_NFTABLES); + mutex_unlock(&ctx.net->nft.commit_mutex); put_net(ctx.net); return NOTIFY_DONE; diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 27d7e4598ab6..81184c244d1a 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -118,6 +118,8 @@ static int nft_dynset_init(const struct nft_ctx *ctx, u64 timeout; int err; + lockdep_assert_held(&ctx->net->nft.commit_mutex); + if (tb[NFTA_DYNSET_SET_NAME] == NULL || tb[NFTA_DYNSET_OP] == NULL || tb[NFTA_DYNSET_SREG_KEY] == NULL) -- cgit v1.2.3 From 7d25f8851a2c03319bfa8e56bb40bde2c4621392 Mon Sep 17 00:00:00 2001 From: Máté Eckl Date: Thu, 12 Jul 2018 17:48:06 +0200 Subject: netfilter: nft_socket: Expose socket mark MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Máté Eckl Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 4 +++- net/netfilter/nft_socket.c | 11 +++++++++++ 2 files changed, 14 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 89438e68dc03..f466860bcf75 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -921,10 +921,12 @@ enum nft_socket_attributes { /* * enum nft_socket_keys - nf_tables socket expression keys * - * @NFT_SOCKET_TRANSPARENT: Value of the IP(V6)_TRANSPARENT socket option_ + * @NFT_SOCKET_TRANSPARENT: Value of the IP(V6)_TRANSPARENT socket option + * @NFT_SOCKET_MARK: Value of the socket mark */ enum nft_socket_keys { NFT_SOCKET_TRANSPARENT, + NFT_SOCKET_MARK, __NFT_SOCKET_MAX }; #define NFT_SOCKET_MAX (__NFT_SOCKET_MAX - 1) diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c index 622ac2012a40..d7f3776dfd71 100644 --- a/net/netfilter/nft_socket.c +++ b/net/netfilter/nft_socket.c @@ -54,6 +54,14 @@ static void nft_socket_eval(const struct nft_expr *expr, case NFT_SOCKET_TRANSPARENT: nft_reg_store8(dest, inet_sk_transparent(sk)); break; + case NFT_SOCKET_MARK: + if (sk_fullsock(sk)) { + *dest = sk->sk_mark; + } else { + regs->verdict.code = NFT_BREAK; + return; + } + break; default: WARN_ON(1); regs->verdict.code = NFT_BREAK; @@ -91,6 +99,9 @@ static int nft_socket_init(const struct nft_ctx *ctx, case NFT_SOCKET_TRANSPARENT: len = sizeof(u8); break; + case NFT_SOCKET_MARK: + len = sizeof(u32); + break; default: return -EOPNOTSUPP; } -- cgit v1.2.3 From 70b095c84326640eeacfd69a411db8fc36e8ab1a Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sat, 14 Jul 2018 01:14:01 +0200 Subject: ipv6: remove dependency of nf_defrag_ipv6 on ipv6 module IPV6=m DEFRAG_IPV6=m CONNTRACK=y yields: net/netfilter/nf_conntrack_proto.o: In function `nf_ct_netns_do_get': net/netfilter/nf_conntrack_proto.c:802: undefined reference to `nf_defrag_ipv6_enable' net/netfilter/nf_conntrack_proto.o:(.rodata+0x640): undefined reference to `nf_conntrack_l4proto_icmpv6' Setting DEFRAG_IPV6=y causes undefined references to ip6_rhash_params ip6_frag_init and ip6_expire_frag_queue so it would be needed to force IPV6=y too. This patch gets rid of the 'followup linker error' by removing the dependency of ipv6.ko symbols from netfilter ipv6 defrag. Shared code is placed into a header, then used from both. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/ipv6.h | 28 -------- include/net/ipv6_frag.h | 104 ++++++++++++++++++++++++++++++ net/ieee802154/6lowpan/reassembly.c | 2 +- net/ipv6/netfilter/nf_conntrack_reasm.c | 17 +++-- net/ipv6/netfilter/nf_defrag_ipv6_hooks.c | 3 +- net/ipv6/reassembly.c | 92 ++------------------------ net/openvswitch/conntrack.c | 1 + 7 files changed, 126 insertions(+), 121 deletions(-) create mode 100644 include/net/ipv6_frag.h (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index aa6fd11a887c..3720958cd4e1 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -581,34 +581,6 @@ static inline bool ipv6_prefix_equal(const struct in6_addr *addr1, } #endif -struct inet_frag_queue; - -enum ip6_defrag_users { - IP6_DEFRAG_LOCAL_DELIVER, - IP6_DEFRAG_CONNTRACK_IN, - __IP6_DEFRAG_CONNTRACK_IN = IP6_DEFRAG_CONNTRACK_IN + USHRT_MAX, - IP6_DEFRAG_CONNTRACK_OUT, - __IP6_DEFRAG_CONNTRACK_OUT = IP6_DEFRAG_CONNTRACK_OUT + USHRT_MAX, - IP6_DEFRAG_CONNTRACK_BRIDGE_IN, - __IP6_DEFRAG_CONNTRACK_BRIDGE_IN = IP6_DEFRAG_CONNTRACK_BRIDGE_IN + USHRT_MAX, -}; - -void ip6_frag_init(struct inet_frag_queue *q, const void *a); -extern const struct rhashtable_params ip6_rhash_params; - -/* - * Equivalent of ipv4 struct ip - */ -struct frag_queue { - struct inet_frag_queue q; - - int iif; - __u16 nhoffset; - u8 ecn; -}; - -void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq); - static inline bool ipv6_addr_any(const struct in6_addr *a) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 diff --git a/include/net/ipv6_frag.h b/include/net/ipv6_frag.h new file mode 100644 index 000000000000..6ced1e6899b6 --- /dev/null +++ b/include/net/ipv6_frag.h @@ -0,0 +1,104 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _IPV6_FRAG_H +#define _IPV6_FRAG_H +#include +#include +#include +#include + +enum ip6_defrag_users { + IP6_DEFRAG_LOCAL_DELIVER, + IP6_DEFRAG_CONNTRACK_IN, + __IP6_DEFRAG_CONNTRACK_IN = IP6_DEFRAG_CONNTRACK_IN + USHRT_MAX, + IP6_DEFRAG_CONNTRACK_OUT, + __IP6_DEFRAG_CONNTRACK_OUT = IP6_DEFRAG_CONNTRACK_OUT + USHRT_MAX, + IP6_DEFRAG_CONNTRACK_BRIDGE_IN, + __IP6_DEFRAG_CONNTRACK_BRIDGE_IN = IP6_DEFRAG_CONNTRACK_BRIDGE_IN + USHRT_MAX, +}; + +/* + * Equivalent of ipv4 struct ip + */ +struct frag_queue { + struct inet_frag_queue q; + + int iif; + __u16 nhoffset; + u8 ecn; +}; + +#if IS_ENABLED(CONFIG_IPV6) +static inline void ip6frag_init(struct inet_frag_queue *q, const void *a) +{ + struct frag_queue *fq = container_of(q, struct frag_queue, q); + const struct frag_v6_compare_key *key = a; + + q->key.v6 = *key; + fq->ecn = 0; +} + +static inline u32 ip6frag_key_hashfn(const void *data, u32 len, u32 seed) +{ + return jhash2(data, + sizeof(struct frag_v6_compare_key) / sizeof(u32), seed); +} + +static inline u32 ip6frag_obj_hashfn(const void *data, u32 len, u32 seed) +{ + const struct inet_frag_queue *fq = data; + + return jhash2((const u32 *)&fq->key.v6, + sizeof(struct frag_v6_compare_key) / sizeof(u32), seed); +} + +static inline int +ip6frag_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr) +{ + const struct frag_v6_compare_key *key = arg->key; + const struct inet_frag_queue *fq = ptr; + + return !!memcmp(&fq->key, key, sizeof(*key)); +} + +static inline void +ip6frag_expire_frag_queue(struct net *net, struct frag_queue *fq) +{ + struct net_device *dev = NULL; + struct sk_buff *head; + + rcu_read_lock(); + spin_lock(&fq->q.lock); + + if (fq->q.flags & INET_FRAG_COMPLETE) + goto out; + + inet_frag_kill(&fq->q); + + dev = dev_get_by_index_rcu(net, fq->iif); + if (!dev) + goto out; + + __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS); + __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT); + + /* Don't send error if the first segment did not arrive. */ + head = fq->q.fragments; + if (!(fq->q.flags & INET_FRAG_FIRST_IN) || !head) + goto out; + + head->dev = dev; + skb_get(head); + spin_unlock(&fq->q.lock); + + icmpv6_send(head, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0); + kfree_skb(head); + goto out_rcu_unlock; + +out: + spin_unlock(&fq->q.lock); +out_rcu_unlock: + rcu_read_unlock(); + inet_frag_put(&fq->q); +} +#endif +#endif diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c index 2cc224106b69..ec7a5da56129 100644 --- a/net/ieee802154/6lowpan/reassembly.c +++ b/net/ieee802154/6lowpan/reassembly.c @@ -25,7 +25,7 @@ #include #include -#include +#include #include #include "6lowpan_i.h" diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index a452d99c9f52..333ee3256964 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -33,9 +33,8 @@ #include #include -#include +#include -#include #include #include #include @@ -151,7 +150,7 @@ static void nf_ct_frag6_expire(struct timer_list *t) fq = container_of(frag, struct frag_queue, q); net = container_of(fq->q.net, struct net, nf_frag.frags); - ip6_expire_frag_queue(net, fq); + ip6frag_expire_frag_queue(net, fq); } /* Creation primitives. */ @@ -622,16 +621,24 @@ static struct pernet_operations nf_ct_net_ops = { .exit = nf_ct_net_exit, }; +static const struct rhashtable_params nfct_rhash_params = { + .head_offset = offsetof(struct inet_frag_queue, node), + .hashfn = ip6frag_key_hashfn, + .obj_hashfn = ip6frag_obj_hashfn, + .obj_cmpfn = ip6frag_obj_cmpfn, + .automatic_shrinking = true, +}; + int nf_ct_frag6_init(void) { int ret = 0; - nf_frags.constructor = ip6_frag_init; + nf_frags.constructor = ip6frag_init; nf_frags.destructor = NULL; nf_frags.qsize = sizeof(struct frag_queue); nf_frags.frag_expire = nf_ct_frag6_expire; nf_frags.frags_cache_name = nf_frags_cache_name; - nf_frags.rhash_params = ip6_rhash_params; + nf_frags.rhash_params = nfct_rhash_params; ret = inet_frags_init(&nf_frags); if (ret) goto out; diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c index e631be25337e..72dd3e202375 100644 --- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c +++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c @@ -14,8 +14,7 @@ #include #include #include -#include -#include +#include #include #include diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index b939b94e7e91..6edd2ac8ae4b 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -57,7 +57,7 @@ #include #include #include -#include +#include #include static const char ip6_frag_cache_name[] = "ip6-frags"; @@ -72,61 +72,6 @@ static struct inet_frags ip6_frags; static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, struct net_device *dev); -void ip6_frag_init(struct inet_frag_queue *q, const void *a) -{ - struct frag_queue *fq = container_of(q, struct frag_queue, q); - const struct frag_v6_compare_key *key = a; - - q->key.v6 = *key; - fq->ecn = 0; -} -EXPORT_SYMBOL(ip6_frag_init); - -void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq) -{ - struct net_device *dev = NULL; - struct sk_buff *head; - - rcu_read_lock(); - spin_lock(&fq->q.lock); - - if (fq->q.flags & INET_FRAG_COMPLETE) - goto out; - - inet_frag_kill(&fq->q); - - dev = dev_get_by_index_rcu(net, fq->iif); - if (!dev) - goto out; - - __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS); - __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT); - - /* Don't send error if the first segment did not arrive. */ - head = fq->q.fragments; - if (!(fq->q.flags & INET_FRAG_FIRST_IN) || !head) - goto out; - - /* But use as source device on which LAST ARRIVED - * segment was received. And do not use fq->dev - * pointer directly, device might already disappeared. - */ - head->dev = dev; - skb_get(head); - spin_unlock(&fq->q.lock); - - icmpv6_send(head, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0); - kfree_skb(head); - goto out_rcu_unlock; - -out: - spin_unlock(&fq->q.lock); -out_rcu_unlock: - rcu_read_unlock(); - inet_frag_put(&fq->q); -} -EXPORT_SYMBOL(ip6_expire_frag_queue); - static void ip6_frag_expire(struct timer_list *t) { struct inet_frag_queue *frag = from_timer(frag, t, timer); @@ -136,7 +81,7 @@ static void ip6_frag_expire(struct timer_list *t) fq = container_of(frag, struct frag_queue, q); net = container_of(fq->q.net, struct net, ipv6.frags); - ip6_expire_frag_queue(net, fq); + ip6frag_expire_frag_queue(net, fq); } static struct frag_queue * @@ -696,42 +641,19 @@ static struct pernet_operations ip6_frags_ops = { .exit = ipv6_frags_exit_net, }; -static u32 ip6_key_hashfn(const void *data, u32 len, u32 seed) -{ - return jhash2(data, - sizeof(struct frag_v6_compare_key) / sizeof(u32), seed); -} - -static u32 ip6_obj_hashfn(const void *data, u32 len, u32 seed) -{ - const struct inet_frag_queue *fq = data; - - return jhash2((const u32 *)&fq->key.v6, - sizeof(struct frag_v6_compare_key) / sizeof(u32), seed); -} - -static int ip6_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr) -{ - const struct frag_v6_compare_key *key = arg->key; - const struct inet_frag_queue *fq = ptr; - - return !!memcmp(&fq->key, key, sizeof(*key)); -} - -const struct rhashtable_params ip6_rhash_params = { +static const struct rhashtable_params ip6_rhash_params = { .head_offset = offsetof(struct inet_frag_queue, node), - .hashfn = ip6_key_hashfn, - .obj_hashfn = ip6_obj_hashfn, - .obj_cmpfn = ip6_obj_cmpfn, + .hashfn = ip6frag_key_hashfn, + .obj_hashfn = ip6frag_obj_hashfn, + .obj_cmpfn = ip6frag_obj_cmpfn, .automatic_shrinking = true, }; -EXPORT_SYMBOL(ip6_rhash_params); int __init ipv6_frag_init(void) { int ret; - ip6_frags.constructor = ip6_frag_init; + ip6_frags.constructor = ip6frag_init; ip6_frags.destructor = NULL; ip6_frags.qsize = sizeof(struct frag_queue); ip6_frags.frag_expire = ip6_frag_expire; diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 3e33c382367f..86a75105af1a 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -26,6 +26,7 @@ #include #include #include +#include #ifdef CONFIG_NF_NAT_NEEDED #include -- cgit v1.2.3 From 24c458c485c87eef97e91d2e180f222555528b11 Mon Sep 17 00:00:00 2001 From: Fernando Fernandez Mancera Date: Sat, 14 Jul 2018 16:50:59 +0200 Subject: netfilter: nf_osf: add missing definitions to header file Add missing definitions from nf_osf.h in order to extract Passive OS fingerprint infrastructure from xt_osf. Signed-off-by: Fernando Fernandez Mancera Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_osf.h | 11 +++++++++++ include/uapi/linux/netfilter/xt_osf.h | 10 ++-------- 2 files changed, 13 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/netfilter/nf_osf.h b/include/uapi/linux/netfilter/nf_osf.h index 8f2f2f403183..3738116b2bbe 100644 --- a/include/uapi/linux/netfilter/nf_osf.h +++ b/include/uapi/linux/netfilter/nf_osf.h @@ -16,9 +16,14 @@ #define NF_OSF_TTL_TRUE 0 /* True ip and fingerprint TTL comparison */ +/* Check if ip TTL is less than fingerprint one */ +#define NF_OSF_TTL_LESS 1 + /* Do not compare ip and fingerprint TTL at all */ #define NF_OSF_TTL_NOCHECK 2 +#define NF_OSF_FLAGMASK (NF_OSF_GENRE | NF_OSF_TTL | \ + NF_OSF_LOG | NF_OSF_INVERT) /* Wildcard MSS (kind of). * It is used to implement a state machine for the different wildcard values * of the MSS and window sizes. @@ -83,4 +88,10 @@ enum iana_options { OSFOPT_EMPTY = 255, }; +enum nf_osf_attr_type { + OSF_ATTR_UNSPEC, + OSF_ATTR_FINGER, + OSF_ATTR_MAX, +}; + #endif /* _NF_OSF_H */ diff --git a/include/uapi/linux/netfilter/xt_osf.h b/include/uapi/linux/netfilter/xt_osf.h index 72956eceeb09..b189007f4f28 100644 --- a/include/uapi/linux/netfilter/xt_osf.h +++ b/include/uapi/linux/netfilter/xt_osf.h @@ -37,8 +37,7 @@ #define XT_OSF_TTL_TRUE NF_OSF_TTL_TRUE #define XT_OSF_TTL_NOCHECK NF_OSF_TTL_NOCHECK - -#define XT_OSF_TTL_LESS 1 /* Check if ip TTL is less than fingerprint one */ +#define XT_OSF_TTL_LESS NF_OSF_TTL_LESS #define xt_osf_wc nf_osf_wc #define xt_osf_opt nf_osf_opt @@ -47,6 +46,7 @@ #define xt_osf_finger nf_osf_finger #define xt_osf_nlmsg nf_osf_nlmsg +#define xt_osf_attr_type nf_osf_attr_type /* * Add/remove fingerprint from the kernel. */ @@ -56,10 +56,4 @@ enum xt_osf_msg_types { OSF_MSG_MAX, }; -enum xt_osf_attr_type { - OSF_ATTR_UNSPEC, - OSF_ATTR_FINGER, - OSF_ATTR_MAX, -}; - #endif /* _XT_OSF_H */ -- cgit v1.2.3 From dba31ee759417ef1a952e929524b0cca1751c036 Mon Sep 17 00:00:00 2001 From: Stefan Berger Date: Mon, 4 Jun 2018 16:54:55 -0400 Subject: ima: Differentiate auditing policy rules from "audit" actions The AUDIT_INTEGRITY_RULE is used for auditing IMA policy rules and the IMA "audit" policy action. This patch defines AUDIT_INTEGRITY_POLICY_RULE to reflect the IMA policy rules. Since we defined a new message type we can now also pass the audit_context and get an associated SYSCALL record. This now produces the following records when parsing IMA policy's rules: type=UNKNOWN[1807] msg=audit(1527888965.738:320): action=audit \ func=MMAP_CHECK mask=MAY_EXEC res=1 type=UNKNOWN[1807] msg=audit(1527888965.738:320): action=audit \ func=FILE_CHECK mask=MAY_READ res=1 type=SYSCALL msg=audit(1527888965.738:320): arch=c000003e syscall=1 \ success=yes exit=17 a0=1 a1=55bcfcca9030 a2=11 a3=7fcc1b55fb38 \ items=0 ppid=1567 pid=1601 auid=0 uid=0 gid=0 euid=0 suid=0 \ fsuid=0 egid=0 sgid=0 fsgid=0 tty=tty2 ses=2 comm="echo" \ exe="/usr/bin/echo" \ subj=unconfined_u:unconfined_r:unconfined_t:s0-s0:c0.c1023 key=(null) Signed-off-by: Stefan Berger Acked-by: Paul Moore Signed-off-by: Mimi Zohar --- include/uapi/linux/audit.h | 1 + security/integrity/ima/ima_policy.c | 4 ++-- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index c35aee9ad4a6..cf2bad8d7873 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -148,6 +148,7 @@ #define AUDIT_INTEGRITY_PCR 1804 /* PCR invalidation msgs */ #define AUDIT_INTEGRITY_RULE 1805 /* policy rule */ #define AUDIT_INTEGRITY_EVM_XATTR 1806 /* New EVM-covered xattr */ +#define AUDIT_INTEGRITY_POLICY_RULE 1807 /* IMA policy rules */ #define AUDIT_KERNEL 2000 /* Asynchronous audit record. NOT A REQUEST. */ diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c index 0178bdaa40aa..8c9499867c91 100644 --- a/security/integrity/ima/ima_policy.c +++ b/security/integrity/ima/ima_policy.c @@ -681,8 +681,8 @@ static int ima_parse_rule(char *rule, struct ima_rule_entry *entry) bool uid_token; int result = 0; - ab = integrity_audit_log_start(NULL, GFP_KERNEL, - AUDIT_INTEGRITY_RULE); + ab = integrity_audit_log_start(audit_context(), GFP_KERNEL, + AUDIT_INTEGRITY_POLICY_RULE); entry->uid = INVALID_UID; entry->fowner = INVALID_UID; -- cgit v1.2.3 From e2861fa71641c6414831d628a1f4f793b6562580 Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Fri, 8 Jun 2018 14:57:42 -0700 Subject: evm: Don't deadlock if a crypto algorithm is unavailable When EVM attempts to appraise a file signed with a crypto algorithm the kernel doesn't have support for, it will cause the kernel to trigger a module load. If the EVM policy includes appraisal of kernel modules this will in turn call back into EVM - since EVM is holding a lock until the crypto initialisation is complete, this triggers a deadlock. Add a CRYPTO_NOLOAD flag and skip module loading if it's set, and add that flag in the EVM case in order to fail gracefully with an error message instead of deadlocking. Signed-off-by: Matthew Garrett Acked-by: Herbert Xu Signed-off-by: Mimi Zohar --- crypto/api.c | 2 +- include/linux/crypto.h | 5 +++++ security/integrity/evm/evm_crypto.c | 3 ++- 3 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/crypto/api.c b/crypto/api.c index 0ee632bba064..7aca9f86c5f3 100644 --- a/crypto/api.c +++ b/crypto/api.c @@ -229,7 +229,7 @@ static struct crypto_alg *crypto_larval_lookup(const char *name, u32 type, mask &= ~(CRYPTO_ALG_LARVAL | CRYPTO_ALG_DEAD); alg = crypto_alg_lookup(name, type, mask); - if (!alg) { + if (!alg && !(mask & CRYPTO_NOLOAD)) { request_module("crypto-%s", name); if (!((type ^ CRYPTO_ALG_NEED_FALLBACK) & mask & diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 6eb06101089f..e8839d3a7559 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -112,6 +112,11 @@ */ #define CRYPTO_ALG_OPTIONAL_KEY 0x00004000 +/* + * Don't trigger module loading + */ +#define CRYPTO_NOLOAD 0x00008000 + /* * Transform masks and values (for crt_flags). */ diff --git a/security/integrity/evm/evm_crypto.c b/security/integrity/evm/evm_crypto.c index b60524310855..c20e3142b541 100644 --- a/security/integrity/evm/evm_crypto.c +++ b/security/integrity/evm/evm_crypto.c @@ -97,7 +97,8 @@ static struct shash_desc *init_desc(char type) mutex_lock(&mutex); if (*tfm) goto out; - *tfm = crypto_alloc_shash(algo, 0, CRYPTO_ALG_ASYNC); + *tfm = crypto_alloc_shash(algo, 0, + CRYPTO_ALG_ASYNC | CRYPTO_NOLOAD); if (IS_ERR(*tfm)) { rc = PTR_ERR(*tfm); pr_err("Can not allocate %s (reason: %ld)\n", algo, rc); -- cgit v1.2.3 From 6eb864c1d9dd1ef32b88e03c3f49d8be0dab7dcf Mon Sep 17 00:00:00 2001 From: Mikhail Kurinnoi Date: Wed, 27 Jun 2018 16:33:42 +0300 Subject: integrity: prevent deadlock during digsig verification. This patch aimed to prevent deadlock during digsig verification.The point of issue - user space utility modprobe and/or it's dependencies (ld-*.so, libz.so.*, libc-*.so and /lib/modules/ files) that could be used for kernel modules load during digsig verification and could be signed by digsig in the same time. First at all, look at crypto_alloc_tfm() work algorithm: crypto_alloc_tfm() will first attempt to locate an already loaded algorithm. If that fails and the kernel supports dynamically loadable modules, it will then attempt to load a module of the same name or alias. If that fails it will send a query to any loaded crypto manager to construct an algorithm on the fly. We have situation, when public_key_verify_signature() in case of RSA algorithm use alg_name to store internal information in order to construct an algorithm on the fly, but crypto_larval_lookup() will try to use alg_name in order to load kernel module with same name. 1) we can't do anything with crypto module work, since it designed to work exactly in this way; 2) we can't globally filter module requests for modprobe, since it designed to work with any requests. In this patch, I propose add an exception for "crypto-pkcs1pad(rsa,*)" module requests only in case of enabled integrity asymmetric keys support. Since we don't have any real "crypto-pkcs1pad(rsa,*)" kernel modules for sure, we are safe to fail such module request from crypto_larval_lookup(). In this way we prevent modprobe execution during digsig verification and avoid possible deadlock if modprobe and/or it's dependencies also signed with digsig. Requested "crypto-pkcs1pad(rsa,*)" kernel module name formed by: 1) "pkcs1pad(rsa,%s)" in public_key_verify_signature(); 2) "crypto-%s" / "crypto-%s-all" in crypto_larval_lookup(). "crypto-pkcs1pad(rsa," part of request is a constant and unique and could be used as filter. Signed-off-by: Mikhail Kurinnoi Signed-off-by: Mimi Zohar include/linux/integrity.h | 13 +++++++++++++ security/integrity/digsig_asymmetric.c | 23 +++++++++++++++++++++++ security/security.c | 7 ++++++- 3 files changed, 42 insertions(+), 1 deletion(-) --- include/linux/integrity.h | 13 +++++++++++++ security/integrity/digsig_asymmetric.c | 23 +++++++++++++++++++++++ security/security.c | 7 ++++++- 3 files changed, 42 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/integrity.h b/include/linux/integrity.h index 858d3f4a2241..54c853ec2fd1 100644 --- a/include/linux/integrity.h +++ b/include/linux/integrity.h @@ -44,4 +44,17 @@ static inline void integrity_load_keys(void) } #endif /* CONFIG_INTEGRITY */ +#ifdef CONFIG_INTEGRITY_ASYMMETRIC_KEYS + +extern int integrity_kernel_module_request(char *kmod_name); + +#else + +static inline int integrity_kernel_module_request(char *kmod_name) +{ + return 0; +} + +#endif /* CONFIG_INTEGRITY_ASYMMETRIC_KEYS */ + #endif /* _LINUX_INTEGRITY_H */ diff --git a/security/integrity/digsig_asymmetric.c b/security/integrity/digsig_asymmetric.c index ab6a029062a1..6dc075144508 100644 --- a/security/integrity/digsig_asymmetric.c +++ b/security/integrity/digsig_asymmetric.c @@ -115,3 +115,26 @@ int asymmetric_verify(struct key *keyring, const char *sig, pr_debug("%s() = %d\n", __func__, ret); return ret; } + +/** + * integrity_kernel_module_request - prevent crypto-pkcs1pad(rsa,*) requests + * @kmod_name: kernel module name + * + * We have situation, when public_key_verify_signature() in case of RSA + * algorithm use alg_name to store internal information in order to + * construct an algorithm on the fly, but crypto_larval_lookup() will try + * to use alg_name in order to load kernel module with same name. + * Since we don't have any real "crypto-pkcs1pad(rsa,*)" kernel modules, + * we are safe to fail such module request from crypto_larval_lookup(). + * + * In this way we prevent modprobe execution during digsig verification + * and avoid possible deadlock if modprobe and/or it's dependencies + * also signed with digsig. + */ +int integrity_kernel_module_request(char *kmod_name) +{ + if (strncmp(kmod_name, "crypto-pkcs1pad(rsa,", 20) == 0) + return -EINVAL; + + return 0; +} diff --git a/security/security.c b/security/security.c index b49ee810371b..dbca03d3629b 100644 --- a/security/security.c +++ b/security/security.c @@ -1032,7 +1032,12 @@ int security_kernel_create_files_as(struct cred *new, struct inode *inode) int security_kernel_module_request(char *kmod_name) { - return call_int_hook(kernel_module_request, 0, kmod_name); + int ret; + + ret = call_int_hook(kernel_module_request, 0, kmod_name); + if (ret) + return ret; + return integrity_kernel_module_request(kmod_name); } int security_kernel_read_file(struct file *file, enum kernel_read_file_id id) -- cgit v1.2.3 From bb4b894addb09a069c072a0a032f644cc470d17f Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Fri, 13 Jul 2018 16:36:28 +0100 Subject: ASoC: core: add support to card re-bind using component framework This patch aims at achieving dynamic behaviour of audio card when the dependent components disappear and reappear. With this patch the card is removed if any of the dependent component is removed and card is added back if the dependent component comes back. All this is done using component framework and matching based on component name. Signed-off-by: Srinivas Kandagatla Reviewed-by: Vinod Koul Signed-off-by: Mark Brown --- include/sound/soc.h | 7 ++++++ sound/soc/soc-core.c | 62 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 69 insertions(+) (limited to 'include') diff --git a/include/sound/soc.h b/include/sound/soc.h index a4915148f739..a23ecdf3eff1 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include @@ -1090,6 +1091,12 @@ struct snd_soc_card { struct work_struct deferred_resume_work; + /* component framework related */ + bool components_added; + /* set in machine driver to enable/disable auto re-binding */ + bool auto_bind; + struct component_match *match; + /* lists of probed devices belonging to this card */ struct list_head component_dev_list; diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index 3be0310d5c81..08e189485009 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -279,11 +279,28 @@ static inline void snd_soc_debugfs_exit(void) #endif +static int snd_soc_card_comp_compare(struct device *dev, void *data) +{ + struct snd_soc_component *component; + + lockdep_assert_held(&client_mutex); + list_for_each_entry(component, &component_list, list) { + if (dev == component->dev) { + if (!strcmp(component->name, data)) + return 1; + break; + } + } + + return 0; +} + static int snd_soc_rtdcom_add(struct snd_soc_pcm_runtime *rtd, struct snd_soc_component *component) { struct snd_soc_rtdcom_list *rtdcom; struct snd_soc_rtdcom_list *new_rtdcom; + char *cname; for_each_rtdcom(rtd, rtdcom) { /* already connected */ @@ -300,6 +317,13 @@ static int snd_soc_rtdcom_add(struct snd_soc_pcm_runtime *rtd, list_add_tail(&new_rtdcom->list, &rtd->component_list); + if (rtd->card->auto_bind && !rtd->card->components_added) { + cname = devm_kasprintf(rtd->card->dev, GFP_KERNEL, + "%s", component->name); + component_match_add(rtd->card->dev, &rtd->card->match, + snd_soc_card_comp_compare, cname); + } + return 0; } @@ -835,6 +859,25 @@ static bool soc_is_dai_link_bound(struct snd_soc_card *card, return false; } +static int snd_soc_card_comp_bind(struct device *dev) +{ + struct snd_soc_card *card = dev_get_drvdata(dev); + + if (card->instantiated) + return 0; + + return snd_soc_register_card(card); +} + +static void snd_soc_card_comp_unbind(struct device *dev) +{ +} + +static const struct component_master_ops snd_soc_card_comp_ops = { + .bind = snd_soc_card_comp_bind, + .unbind = snd_soc_card_comp_unbind, +}; + static int soc_bind_dai_link(struct snd_soc_card *card, struct snd_soc_dai_link *dai_link) { @@ -2126,6 +2169,12 @@ static int snd_soc_instantiate_card(struct snd_soc_card *card) card->instantiated = 1; snd_soc_dapm_sync(&card->dapm); + if (card->auto_bind && !card->components_added) { + component_master_add_with_match(card->dev, + &snd_soc_card_comp_ops, + card->match); + card->components_added = true; + } mutex_unlock(&card->mutex); mutex_unlock(&client_mutex); @@ -2749,6 +2798,9 @@ int snd_soc_unregister_card(struct snd_soc_card *card) dev_dbg(card->dev, "ASoC: Unregistered card '%s'\n", card->name); } + if (!card->auto_bind && card->components_added) + component_master_del(card->dev, &snd_soc_card_comp_ops); + return 0; } EXPORT_SYMBOL_GPL(snd_soc_unregister_card); @@ -3161,8 +3213,17 @@ int snd_soc_add_component(struct device *dev, snd_soc_component_add(component); + ret = component_add(dev, NULL); + if (ret < 0) { + dev_err(dev, "ASoC: Failed to add Component: %d\n", ret); + goto err_comp; + } + return 0; +err_comp: + soc_remove_component(component); + snd_soc_unregister_dais(component); err_cleanup: snd_soc_component_cleanup(component); err_free: @@ -3210,6 +3271,7 @@ static int __snd_soc_unregister_component(struct device *dev) mutex_unlock(&client_mutex); if (found) { + component_del(dev, NULL); snd_soc_component_cleanup(component); } -- cgit v1.2.3 From d29ab6e1fa21ebc2a8a771015dd9e0e5d4e28dc1 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 13 Jul 2018 12:41:10 -0700 Subject: bpf: bpf_prog_array_alloc() should return a generic non-rcu pointer Currently the return type of the bpf_prog_array_alloc() is struct bpf_prog_array __rcu *, which is not quite correct. Obviously, the returned pointer is a generic pointer, which is valid for an indefinite amount of time and it's not shared with anyone else, so there is no sense in marking it as __rcu. This change eliminate the following sparse warnings: kernel/bpf/core.c:1544:31: warning: incorrect type in return expression (different address spaces) kernel/bpf/core.c:1544:31: expected struct bpf_prog_array [noderef] * kernel/bpf/core.c:1544:31: got void * kernel/bpf/core.c:1548:17: warning: incorrect type in return expression (different address spaces) kernel/bpf/core.c:1548:17: expected struct bpf_prog_array [noderef] * kernel/bpf/core.c:1548:17: got struct bpf_prog_array * kernel/bpf/core.c:1681:15: warning: incorrect type in assignment (different address spaces) kernel/bpf/core.c:1681:15: expected struct bpf_prog_array *array kernel/bpf/core.c:1681:15: got struct bpf_prog_array [noderef] * Fixes: 324bda9e6c5a ("bpf: multi program support for cgroup+bpf") Signed-off-by: Roman Gushchin Cc: Alexei Starovoitov Cc: Daniel Borkmann Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 2 +- kernel/bpf/core.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8827e797ff97..943fb08d8287 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -352,7 +352,7 @@ struct bpf_prog_array { struct bpf_prog *progs[0]; }; -struct bpf_prog_array __rcu *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags); +struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags); void bpf_prog_array_free(struct bpf_prog_array __rcu *progs); int bpf_prog_array_length(struct bpf_prog_array __rcu *progs); int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs, diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 1e5625d46414..253aa8e79c7b 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1538,7 +1538,7 @@ static struct { .null_prog = NULL, }; -struct bpf_prog_array __rcu *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags) +struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags) { if (prog_cnt) return kzalloc(sizeof(struct bpf_prog_array) + -- cgit v1.2.3 From 09728266b6f99ab57cd4f84f3eead65b7b65dbf7 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 17 Jul 2018 10:53:23 -0700 Subject: bpf: offload: rename bpf_offload_dev_match() to bpf_offload_prog_map_match() A set of new API functions exported for the drivers will soon use 'bpf_offload_dev_' as a prefix. Rename the bpf_offload_dev_match() which is internal to the core (used by the verifier) to avoid any confusion. Signed-off-by: Jakub Kicinski Reviewed-by: Quentin Monnet Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 2 +- kernel/bpf/offload.c | 2 +- kernel/bpf/verifier.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 943fb08d8287..9b010d9129f3 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -648,7 +648,7 @@ int bpf_map_offload_delete_elem(struct bpf_map *map, void *key); int bpf_map_offload_get_next_key(struct bpf_map *map, void *key, void *next_key); -bool bpf_offload_dev_match(struct bpf_prog *prog, struct bpf_map *map); +bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map); #if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL) int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr); diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index ac747d5cf7c6..6184e48703f4 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -468,7 +468,7 @@ int bpf_map_offload_info_fill(struct bpf_map_info *info, struct bpf_map *map) return 0; } -bool bpf_offload_dev_match(struct bpf_prog *prog, struct bpf_map *map) +bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map) { struct bpf_offloaded_map *offmap; struct bpf_prog_offload *offload; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 9e2bf834f13a..15d69b278277 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5054,7 +5054,7 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, } if ((bpf_prog_is_dev_bound(prog->aux) || bpf_map_is_dev_bound(map)) && - !bpf_offload_dev_match(prog, map)) { + !bpf_offload_prog_map_match(prog, map)) { verbose(env, "offload device mismatch between prog and map\n"); return -EINVAL; } -- cgit v1.2.3 From 9fd7c5559165f4c679b40c5e6ad442955832dfad Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 17 Jul 2018 10:53:24 -0700 Subject: bpf: offload: aggregate offloads per-device Currently we have two lists of offloaded objects - programs and maps. Netdevice unregister notifier scans those lists to orphan objects associated with device being unregistered. This puts unnecessary (even if negligible) burden on all netdev unregister calls in BPF- -enabled kernel. The lists of objects may potentially get long making the linear scan even more problematic. There haven't been complaints about this mechanisms so far, but it is suboptimal. Instead of relying on notifiers, make the few BPF-capable drivers register explicitly for BPF offloads. The programs and maps will now be collected per-device not on a global list, and only scanned for removal when driver unregisters from BPF offloads. Signed-off-by: Jakub Kicinski Reviewed-by: Quentin Monnet Signed-off-by: Daniel Borkmann --- drivers/net/ethernet/netronome/nfp/bpf/main.c | 13 +++ drivers/net/netdevsim/bpf.c | 7 ++ include/linux/bpf.h | 3 + kernel/bpf/offload.c | 142 +++++++++++++++++--------- 4 files changed, 119 insertions(+), 46 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c index b95b94d008cf..dee039ada75c 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c @@ -404,6 +404,16 @@ err_release_free: return -EINVAL; } +static int nfp_bpf_ndo_init(struct nfp_app *app, struct net_device *netdev) +{ + return bpf_offload_dev_netdev_register(netdev); +} + +static void nfp_bpf_ndo_uninit(struct nfp_app *app, struct net_device *netdev) +{ + bpf_offload_dev_netdev_unregister(netdev); +} + static int nfp_bpf_init(struct nfp_app *app) { struct nfp_app_bpf *bpf; @@ -466,6 +476,9 @@ const struct nfp_app_type app_bpf = { .extra_cap = nfp_bpf_extra_cap, + .ndo_init = nfp_bpf_ndo_init, + .ndo_uninit = nfp_bpf_ndo_uninit, + .vnic_alloc = nfp_bpf_vnic_alloc, .vnic_free = nfp_bpf_vnic_free, diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c index 357f9e62f306..c4a2829e0e1f 100644 --- a/drivers/net/netdevsim/bpf.c +++ b/drivers/net/netdevsim/bpf.c @@ -582,6 +582,8 @@ int nsim_bpf(struct net_device *dev, struct netdev_bpf *bpf) int nsim_bpf_init(struct netdevsim *ns) { + int err; + if (ns->sdev->refcnt == 1) { INIT_LIST_HEAD(&ns->sdev->bpf_bound_progs); INIT_LIST_HEAD(&ns->sdev->bpf_bound_maps); @@ -592,6 +594,10 @@ int nsim_bpf_init(struct netdevsim *ns) return -ENOMEM; } + err = bpf_offload_dev_netdev_register(ns->netdev); + if (err) + return err; + debugfs_create_u32("bpf_offloaded_id", 0400, ns->ddir, &ns->bpf_offloaded_id); @@ -625,6 +631,7 @@ void nsim_bpf_uninit(struct netdevsim *ns) WARN_ON(ns->xdp.prog); WARN_ON(ns->xdp_hw.prog); WARN_ON(ns->bpf_offloaded); + bpf_offload_dev_netdev_unregister(ns->netdev); if (ns->sdev->refcnt == 1) { WARN_ON(!list_empty(&ns->sdev->bpf_bound_progs)); diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 9b010d9129f3..aa2e834a122b 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -650,6 +650,9 @@ int bpf_map_offload_get_next_key(struct bpf_map *map, bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map); +int bpf_offload_dev_netdev_register(struct net_device *netdev); +void bpf_offload_dev_netdev_unregister(struct net_device *netdev); + #if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL) int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr); diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index 6184e48703f4..cd64a26807aa 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -18,19 +18,37 @@ #include #include #include +#include #include #include #include +#include #include #include -/* Protects bpf_prog_offload_devs, bpf_map_offload_devs and offload members +/* Protects offdevs, members of bpf_offload_netdev and offload members * of all progs. * RTNL lock cannot be taken when holding this lock. */ static DECLARE_RWSEM(bpf_devs_lock); -static LIST_HEAD(bpf_prog_offload_devs); -static LIST_HEAD(bpf_map_offload_devs); + +struct bpf_offload_netdev { + struct rhash_head l; + struct net_device *netdev; + struct list_head progs; + struct list_head maps; +}; + +static const struct rhashtable_params offdevs_params = { + .nelem_hint = 4, + .key_len = sizeof(struct net_device *), + .key_offset = offsetof(struct bpf_offload_netdev, netdev), + .head_offset = offsetof(struct bpf_offload_netdev, l), + .automatic_shrinking = true, +}; + +static struct rhashtable offdevs; +static bool offdevs_inited; static int bpf_dev_offload_check(struct net_device *netdev) { @@ -41,8 +59,19 @@ static int bpf_dev_offload_check(struct net_device *netdev) return 0; } +static struct bpf_offload_netdev * +bpf_offload_find_netdev(struct net_device *netdev) +{ + lockdep_assert_held(&bpf_devs_lock); + + if (!offdevs_inited) + return NULL; + return rhashtable_lookup_fast(&offdevs, &netdev, offdevs_params); +} + int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr) { + struct bpf_offload_netdev *ondev; struct bpf_prog_offload *offload; int err; @@ -66,12 +95,13 @@ int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr) goto err_maybe_put; down_write(&bpf_devs_lock); - if (offload->netdev->reg_state != NETREG_REGISTERED) { + ondev = bpf_offload_find_netdev(offload->netdev); + if (!ondev) { err = -EINVAL; goto err_unlock; } prog->aux->offload = offload; - list_add_tail(&offload->offloads, &bpf_prog_offload_devs); + list_add_tail(&offload->offloads, &ondev->progs); dev_put(offload->netdev); up_write(&bpf_devs_lock); @@ -294,6 +324,7 @@ static int bpf_map_offload_ndo(struct bpf_offloaded_map *offmap, struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr) { struct net *net = current->nsproxy->net_ns; + struct bpf_offload_netdev *ondev; struct bpf_offloaded_map *offmap; int err; @@ -316,11 +347,17 @@ struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr) if (err) goto err_unlock; + ondev = bpf_offload_find_netdev(offmap->netdev); + if (!ondev) { + err = -EINVAL; + goto err_unlock; + } + err = bpf_map_offload_ndo(offmap, BPF_OFFLOAD_MAP_ALLOC); if (err) goto err_unlock; - list_add_tail(&offmap->offloads, &bpf_map_offload_devs); + list_add_tail(&offmap->offloads, &ondev->maps); up_write(&bpf_devs_lock); rtnl_unlock(); @@ -489,56 +526,69 @@ bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map) return ret; } -static void bpf_offload_orphan_all_progs(struct net_device *netdev) +int bpf_offload_dev_netdev_register(struct net_device *netdev) { - struct bpf_prog_offload *offload, *tmp; + struct bpf_offload_netdev *ondev; + int err; - list_for_each_entry_safe(offload, tmp, &bpf_prog_offload_devs, offloads) - if (offload->netdev == netdev) - __bpf_prog_offload_destroy(offload->prog); -} + down_write(&bpf_devs_lock); + if (!offdevs_inited) { + err = rhashtable_init(&offdevs, &offdevs_params); + if (err) + return err; + offdevs_inited = true; + } + up_write(&bpf_devs_lock); -static void bpf_offload_orphan_all_maps(struct net_device *netdev) -{ - struct bpf_offloaded_map *offmap, *tmp; + ondev = kzalloc(sizeof(*ondev), GFP_KERNEL); + if (!ondev) + return -ENOMEM; + + ondev->netdev = netdev; + INIT_LIST_HEAD(&ondev->progs); + INIT_LIST_HEAD(&ondev->maps); + + down_write(&bpf_devs_lock); + err = rhashtable_insert_fast(&offdevs, &ondev->l, offdevs_params); + if (err) { + netdev_warn(netdev, "failed to register for BPF offload\n"); + goto err_unlock_free; + } - list_for_each_entry_safe(offmap, tmp, &bpf_map_offload_devs, offloads) - if (offmap->netdev == netdev) - __bpf_map_offload_destroy(offmap); + up_write(&bpf_devs_lock); + return 0; + +err_unlock_free: + up_write(&bpf_devs_lock); + kfree(ondev); + return err; } +EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_register); -static int bpf_offload_notification(struct notifier_block *notifier, - ulong event, void *ptr) +void bpf_offload_dev_netdev_unregister(struct net_device *netdev) { - struct net_device *netdev = netdev_notifier_info_to_dev(ptr); + struct bpf_offloaded_map *offmap, *mtmp; + struct bpf_prog_offload *offload, *ptmp; + struct bpf_offload_netdev *ondev; ASSERT_RTNL(); - switch (event) { - case NETDEV_UNREGISTER: - /* ignore namespace changes */ - if (netdev->reg_state != NETREG_UNREGISTERING) - break; - - down_write(&bpf_devs_lock); - bpf_offload_orphan_all_progs(netdev); - bpf_offload_orphan_all_maps(netdev); - up_write(&bpf_devs_lock); - break; - default: - break; - } - return NOTIFY_OK; -} + down_write(&bpf_devs_lock); + ondev = rhashtable_lookup_fast(&offdevs, &netdev, offdevs_params); + if (WARN_ON(!ondev)) + goto unlock; -static struct notifier_block bpf_offload_notifier = { - .notifier_call = bpf_offload_notification, -}; + WARN_ON(rhashtable_remove_fast(&offdevs, &ondev->l, offdevs_params)); -static int __init bpf_offload_init(void) -{ - register_netdevice_notifier(&bpf_offload_notifier); - return 0; -} + list_for_each_entry_safe(offload, ptmp, &ondev->progs, offloads) + __bpf_prog_offload_destroy(offload->prog); + list_for_each_entry_safe(offmap, mtmp, &ondev->maps, offloads) + __bpf_map_offload_destroy(offmap); -subsys_initcall(bpf_offload_init); + WARN_ON(!list_empty(&ondev->progs)); + WARN_ON(!list_empty(&ondev->maps)); + kfree(ondev); +unlock: + up_write(&bpf_devs_lock); +} +EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_unregister); -- cgit v1.2.3 From 602144c224604f1cbff02ee2d1cf46825269ecbd Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 17 Jul 2018 10:53:25 -0700 Subject: bpf: offload: keep the offload state per-ASIC Create a higher-level entity to represent a device/ASIC to allow programs and maps to be shared between device ports. The extra work is required to make sure we don't destroy BPF objects as soon as the netdev for which they were loaded gets destroyed, as other ports may still be using them. When netdev goes away all of its BPF objects will be moved to other netdevs of the device, and only destroyed when last netdev is unregistered. Signed-off-by: Jakub Kicinski Reviewed-by: Quentin Monnet Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- drivers/net/ethernet/netronome/nfp/bpf/main.c | 14 ++++- drivers/net/ethernet/netronome/nfp/bpf/main.h | 4 ++ drivers/net/netdevsim/bpf.c | 17 +++++- drivers/net/netdevsim/netdevsim.h | 3 + include/linux/bpf.h | 9 ++- kernel/bpf/offload.c | 81 +++++++++++++++++++++------ 6 files changed, 104 insertions(+), 24 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c index dee039ada75c..458f49235d06 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c @@ -406,12 +406,16 @@ err_release_free: static int nfp_bpf_ndo_init(struct nfp_app *app, struct net_device *netdev) { - return bpf_offload_dev_netdev_register(netdev); + struct nfp_app_bpf *bpf = app->priv; + + return bpf_offload_dev_netdev_register(bpf->bpf_dev, netdev); } static void nfp_bpf_ndo_uninit(struct nfp_app *app, struct net_device *netdev) { - bpf_offload_dev_netdev_unregister(netdev); + struct nfp_app_bpf *bpf = app->priv; + + bpf_offload_dev_netdev_unregister(bpf->bpf_dev, netdev); } static int nfp_bpf_init(struct nfp_app *app) @@ -437,6 +441,11 @@ static int nfp_bpf_init(struct nfp_app *app) if (err) goto err_free_neutral_maps; + bpf->bpf_dev = bpf_offload_dev_create(); + err = PTR_ERR_OR_ZERO(bpf->bpf_dev); + if (err) + goto err_free_neutral_maps; + return 0; err_free_neutral_maps: @@ -455,6 +464,7 @@ static void nfp_bpf_clean(struct nfp_app *app) { struct nfp_app_bpf *bpf = app->priv; + bpf_offload_dev_destroy(bpf->bpf_dev); WARN_ON(!skb_queue_empty(&bpf->cmsg_replies)); WARN_ON(!list_empty(&bpf->map_list)); WARN_ON(bpf->maps_in_use || bpf->map_elems_in_use); diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h index 9845c1a2d4c2..bec935468f90 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.h +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h @@ -110,6 +110,8 @@ enum pkt_vec { * struct nfp_app_bpf - bpf app priv structure * @app: backpointer to the app * + * @bpf_dev: BPF offload device handle + * * @tag_allocator: bitmap of control message tags in use * @tag_alloc_next: next tag bit to allocate * @tag_alloc_last: next tag bit to be freed @@ -150,6 +152,8 @@ enum pkt_vec { struct nfp_app_bpf { struct nfp_app *app; + struct bpf_offload_dev *bpf_dev; + DECLARE_BITMAP(tag_allocator, U16_MAX + 1); u16 tag_alloc_next; u16 tag_alloc_last; diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c index c4a2829e0e1f..9eab29f67a0e 100644 --- a/drivers/net/netdevsim/bpf.c +++ b/drivers/net/netdevsim/bpf.c @@ -592,11 +592,16 @@ int nsim_bpf_init(struct netdevsim *ns) debugfs_create_dir("bpf_bound_progs", ns->sdev->ddir); if (IS_ERR_OR_NULL(ns->sdev->ddir_bpf_bound_progs)) return -ENOMEM; + + ns->sdev->bpf_dev = bpf_offload_dev_create(); + err = PTR_ERR_OR_ZERO(ns->sdev->bpf_dev); + if (err) + return err; } - err = bpf_offload_dev_netdev_register(ns->netdev); + err = bpf_offload_dev_netdev_register(ns->sdev->bpf_dev, ns->netdev); if (err) - return err; + goto err_destroy_bdev; debugfs_create_u32("bpf_offloaded_id", 0400, ns->ddir, &ns->bpf_offloaded_id); @@ -624,6 +629,11 @@ int nsim_bpf_init(struct netdevsim *ns) &ns->bpf_map_accept); return 0; + +err_destroy_bdev: + if (ns->sdev->refcnt == 1) + bpf_offload_dev_destroy(ns->sdev->bpf_dev); + return err; } void nsim_bpf_uninit(struct netdevsim *ns) @@ -631,10 +641,11 @@ void nsim_bpf_uninit(struct netdevsim *ns) WARN_ON(ns->xdp.prog); WARN_ON(ns->xdp_hw.prog); WARN_ON(ns->bpf_offloaded); - bpf_offload_dev_netdev_unregister(ns->netdev); + bpf_offload_dev_netdev_unregister(ns->sdev->bpf_dev, ns->netdev); if (ns->sdev->refcnt == 1) { WARN_ON(!list_empty(&ns->sdev->bpf_bound_progs)); WARN_ON(!list_empty(&ns->sdev->bpf_bound_maps)); + bpf_offload_dev_destroy(ns->sdev->bpf_dev); } } diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h index 98f26fa1e671..02be199eb005 100644 --- a/drivers/net/netdevsim/netdevsim.h +++ b/drivers/net/netdevsim/netdevsim.h @@ -27,6 +27,7 @@ #define NSIM_EA(extack, msg) NL_SET_ERR_MSG_MOD((extack), msg) struct bpf_prog; +struct bpf_offload_dev; struct dentry; struct nsim_vf_config; @@ -36,6 +37,8 @@ struct netdevsim_shared_dev { struct dentry *ddir; + struct bpf_offload_dev *bpf_dev; + struct dentry *ddir_bpf_bound_progs; u32 prog_id_gen; diff --git a/include/linux/bpf.h b/include/linux/bpf.h index aa2e834a122b..913465e45062 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -85,6 +85,7 @@ struct bpf_map { char name[BPF_OBJ_NAME_LEN]; }; +struct bpf_offload_dev; struct bpf_offloaded_map; struct bpf_map_dev_ops { @@ -650,8 +651,12 @@ int bpf_map_offload_get_next_key(struct bpf_map *map, bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map); -int bpf_offload_dev_netdev_register(struct net_device *netdev); -void bpf_offload_dev_netdev_unregister(struct net_device *netdev); +struct bpf_offload_dev *bpf_offload_dev_create(void); +void bpf_offload_dev_destroy(struct bpf_offload_dev *offdev); +int bpf_offload_dev_netdev_register(struct bpf_offload_dev *offdev, + struct net_device *netdev); +void bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev, + struct net_device *netdev); #if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL) int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr); diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index cd64a26807aa..925575f64ff1 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -32,11 +32,17 @@ */ static DECLARE_RWSEM(bpf_devs_lock); +struct bpf_offload_dev { + struct list_head netdevs; +}; + struct bpf_offload_netdev { struct rhash_head l; struct net_device *netdev; + struct bpf_offload_dev *offdev; struct list_head progs; struct list_head maps; + struct list_head offdev_netdevs; }; static const struct rhashtable_params offdevs_params = { @@ -526,25 +532,18 @@ bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map) return ret; } -int bpf_offload_dev_netdev_register(struct net_device *netdev) +int bpf_offload_dev_netdev_register(struct bpf_offload_dev *offdev, + struct net_device *netdev) { struct bpf_offload_netdev *ondev; int err; - down_write(&bpf_devs_lock); - if (!offdevs_inited) { - err = rhashtable_init(&offdevs, &offdevs_params); - if (err) - return err; - offdevs_inited = true; - } - up_write(&bpf_devs_lock); - ondev = kzalloc(sizeof(*ondev), GFP_KERNEL); if (!ondev) return -ENOMEM; ondev->netdev = netdev; + ondev->offdev = offdev; INIT_LIST_HEAD(&ondev->progs); INIT_LIST_HEAD(&ondev->maps); @@ -555,6 +554,7 @@ int bpf_offload_dev_netdev_register(struct net_device *netdev) goto err_unlock_free; } + list_add(&ondev->offdev_netdevs, &offdev->netdevs); up_write(&bpf_devs_lock); return 0; @@ -565,11 +565,12 @@ err_unlock_free: } EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_register); -void bpf_offload_dev_netdev_unregister(struct net_device *netdev) +void bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev, + struct net_device *netdev) { + struct bpf_offload_netdev *ondev, *altdev; struct bpf_offloaded_map *offmap, *mtmp; struct bpf_prog_offload *offload, *ptmp; - struct bpf_offload_netdev *ondev; ASSERT_RTNL(); @@ -579,11 +580,26 @@ void bpf_offload_dev_netdev_unregister(struct net_device *netdev) goto unlock; WARN_ON(rhashtable_remove_fast(&offdevs, &ondev->l, offdevs_params)); - - list_for_each_entry_safe(offload, ptmp, &ondev->progs, offloads) - __bpf_prog_offload_destroy(offload->prog); - list_for_each_entry_safe(offmap, mtmp, &ondev->maps, offloads) - __bpf_map_offload_destroy(offmap); + list_del(&ondev->offdev_netdevs); + + /* Try to move the objects to another netdev of the device */ + altdev = list_first_entry_or_null(&offdev->netdevs, + struct bpf_offload_netdev, + offdev_netdevs); + if (altdev) { + list_for_each_entry(offload, &ondev->progs, offloads) + offload->netdev = altdev->netdev; + list_splice_init(&ondev->progs, &altdev->progs); + + list_for_each_entry(offmap, &ondev->maps, offloads) + offmap->netdev = altdev->netdev; + list_splice_init(&ondev->maps, &altdev->maps); + } else { + list_for_each_entry_safe(offload, ptmp, &ondev->progs, offloads) + __bpf_prog_offload_destroy(offload->prog); + list_for_each_entry_safe(offmap, mtmp, &ondev->maps, offloads) + __bpf_map_offload_destroy(offmap); + } WARN_ON(!list_empty(&ondev->progs)); WARN_ON(!list_empty(&ondev->maps)); @@ -592,3 +608,34 @@ unlock: up_write(&bpf_devs_lock); } EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_unregister); + +struct bpf_offload_dev *bpf_offload_dev_create(void) +{ + struct bpf_offload_dev *offdev; + int err; + + down_write(&bpf_devs_lock); + if (!offdevs_inited) { + err = rhashtable_init(&offdevs, &offdevs_params); + if (err) + return ERR_PTR(err); + offdevs_inited = true; + } + up_write(&bpf_devs_lock); + + offdev = kzalloc(sizeof(*offdev), GFP_KERNEL); + if (!offdev) + return ERR_PTR(-ENOMEM); + + INIT_LIST_HEAD(&offdev->netdevs); + + return offdev; +} +EXPORT_SYMBOL_GPL(bpf_offload_dev_create); + +void bpf_offload_dev_destroy(struct bpf_offload_dev *offdev) +{ + WARN_ON(!list_empty(&offdev->netdevs)); + kfree(offdev); +} +EXPORT_SYMBOL_GPL(bpf_offload_dev_destroy); -- cgit v1.2.3 From fd4f227dea0f24d89f52f7c4eb3207f84ddcbcbd Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 17 Jul 2018 10:53:26 -0700 Subject: bpf: offload: allow program and map sharing per-ASIC Allow programs and maps to be re-used across different netdevs, as long as they belong to the same struct bpf_offload_dev. Update the bpf_offload_prog_map_match() helper for the verifier and export a new helper for the drivers to use when checking programs at attachment time. Signed-off-by: Jakub Kicinski Reviewed-by: Quentin Monnet Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 1 + kernel/bpf/offload.c | 42 +++++++++++++++++++++++++++++++++++------- 2 files changed, 36 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 913465e45062..5b5ad95cf339 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -657,6 +657,7 @@ int bpf_offload_dev_netdev_register(struct bpf_offload_dev *offdev, struct net_device *netdev); void bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev, struct net_device *netdev); +bool bpf_offload_dev_match(struct bpf_prog *prog, struct net_device *netdev); #if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL) int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr); diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index 925575f64ff1..177a52436394 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -511,22 +511,50 @@ int bpf_map_offload_info_fill(struct bpf_map_info *info, struct bpf_map *map) return 0; } -bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map) +static bool __bpf_offload_dev_match(struct bpf_prog *prog, + struct net_device *netdev) { - struct bpf_offloaded_map *offmap; + struct bpf_offload_netdev *ondev1, *ondev2; struct bpf_prog_offload *offload; - bool ret; if (!bpf_prog_is_dev_bound(prog->aux)) return false; - if (!bpf_map_is_dev_bound(map)) - return bpf_map_offload_neutral(map); - down_read(&bpf_devs_lock); offload = prog->aux->offload; + if (!offload) + return false; + if (offload->netdev == netdev) + return true; + + ondev1 = bpf_offload_find_netdev(offload->netdev); + ondev2 = bpf_offload_find_netdev(netdev); + + return ondev1 && ondev2 && ondev1->offdev == ondev2->offdev; +} + +bool bpf_offload_dev_match(struct bpf_prog *prog, struct net_device *netdev) +{ + bool ret; + + down_read(&bpf_devs_lock); + ret = __bpf_offload_dev_match(prog, netdev); + up_read(&bpf_devs_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(bpf_offload_dev_match); + +bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map) +{ + struct bpf_offloaded_map *offmap; + bool ret; + + if (!bpf_map_is_dev_bound(map)) + return bpf_map_offload_neutral(map); offmap = map_to_offmap(map); - ret = offload && offload->netdev == offmap->netdev; + down_read(&bpf_devs_lock); + ret = __bpf_offload_dev_match(prog, offmap->netdev); up_read(&bpf_devs_lock); return ret; -- cgit v1.2.3 From 3f289dcb4b265416a57ca79cf4a324060bb09060 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 18 Jul 2018 04:47:36 -0700 Subject: block: make bdev_ops->rw_page() take a REQ_OP instead of bool c11f0c0b5bb9 ("block/mm: make bdev_ops->rw_page() take a bool for read/write") replaced @op with boolean @is_write, which limited the amount of information going into ->rw_page() and more importantly page_endio(), which removed the need to expose block internals to mm. Unfortunately, we want to track discards separately and @is_write isn't enough information. This patch updates bdev_ops->rw_page() to take REQ_OP instead but leaves page_endio() to take bool @is_write. This allows the block part of operations to have enough information while not leaking it to mm. Signed-off-by: Tejun Heo Cc: Mike Christie Cc: Minchan Kim Cc: Dan Williams Signed-off-by: Jens Axboe --- drivers/block/brd.c | 14 +++++++------- drivers/block/zram/zram_drv.c | 16 ++++++++-------- drivers/nvdimm/btt.c | 12 ++++++------ drivers/nvdimm/pmem.c | 13 ++++++------- fs/block_dev.c | 6 ++++-- fs/mpage.c | 4 ++-- include/linux/blkdev.h | 2 +- 7 files changed, 34 insertions(+), 33 deletions(-) (limited to 'include') diff --git a/drivers/block/brd.c b/drivers/block/brd.c index bb976598ee43..df8103dd40ac 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -254,20 +254,20 @@ static void copy_from_brd(void *dst, struct brd_device *brd, * Process a single bvec of a bio. */ static int brd_do_bvec(struct brd_device *brd, struct page *page, - unsigned int len, unsigned int off, bool is_write, + unsigned int len, unsigned int off, unsigned int op, sector_t sector) { void *mem; int err = 0; - if (is_write) { + if (op_is_write(op)) { err = copy_to_brd_setup(brd, sector, len); if (err) goto out; } mem = kmap_atomic(page); - if (!is_write) { + if (!op_is_write(op)) { copy_from_brd(mem + off, brd, sector, len); flush_dcache_page(page); } else { @@ -296,7 +296,7 @@ static blk_qc_t brd_make_request(struct request_queue *q, struct bio *bio) int err; err = brd_do_bvec(brd, bvec.bv_page, len, bvec.bv_offset, - op_is_write(bio_op(bio)), sector); + bio_op(bio), sector); if (err) goto io_error; sector += len >> SECTOR_SHIFT; @@ -310,15 +310,15 @@ io_error: } static int brd_rw_page(struct block_device *bdev, sector_t sector, - struct page *page, bool is_write) + struct page *page, unsigned int op) { struct brd_device *brd = bdev->bd_disk->private_data; int err; if (PageTransHuge(page)) return -ENOTSUPP; - err = brd_do_bvec(brd, page, PAGE_SIZE, 0, is_write, sector); - page_endio(page, is_write, err); + err = brd_do_bvec(brd, page, PAGE_SIZE, 0, op, sector); + page_endio(page, op_is_write(op), err); return err; } diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 7436b2d27fa3..78c29044684a 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1274,17 +1274,17 @@ static void zram_bio_discard(struct zram *zram, u32 index, * Returns 1 if IO request was successfully submitted. */ static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index, - int offset, bool is_write, struct bio *bio) + int offset, unsigned int op, struct bio *bio) { unsigned long start_time = jiffies; - int rw_acct = is_write ? REQ_OP_WRITE : REQ_OP_READ; + int rw_acct = op_is_write(op) ? REQ_OP_WRITE : REQ_OP_READ; struct request_queue *q = zram->disk->queue; int ret; generic_start_io_acct(q, rw_acct, bvec->bv_len >> SECTOR_SHIFT, &zram->disk->part0); - if (!is_write) { + if (!op_is_write(op)) { atomic64_inc(&zram->stats.num_reads); ret = zram_bvec_read(zram, bvec, index, offset, bio); flush_dcache_page(bvec->bv_page); @@ -1300,7 +1300,7 @@ static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index, zram_slot_unlock(zram, index); if (unlikely(ret < 0)) { - if (!is_write) + if (!op_is_write(op)) atomic64_inc(&zram->stats.failed_reads); else atomic64_inc(&zram->stats.failed_writes); @@ -1338,7 +1338,7 @@ static void __zram_make_request(struct zram *zram, struct bio *bio) bv.bv_len = min_t(unsigned int, PAGE_SIZE - offset, unwritten); if (zram_bvec_rw(zram, &bv, index, offset, - op_is_write(bio_op(bio)), bio) < 0) + bio_op(bio), bio) < 0) goto out; bv.bv_offset += bv.bv_len; @@ -1390,7 +1390,7 @@ static void zram_slot_free_notify(struct block_device *bdev, } static int zram_rw_page(struct block_device *bdev, sector_t sector, - struct page *page, bool is_write) + struct page *page, unsigned int op) { int offset, ret; u32 index; @@ -1414,7 +1414,7 @@ static int zram_rw_page(struct block_device *bdev, sector_t sector, bv.bv_len = PAGE_SIZE; bv.bv_offset = 0; - ret = zram_bvec_rw(zram, &bv, index, offset, is_write, NULL); + ret = zram_bvec_rw(zram, &bv, index, offset, op, NULL); out: /* * If I/O fails, just return error(ie, non-zero) without @@ -1429,7 +1429,7 @@ out: switch (ret) { case 0: - page_endio(page, is_write, 0); + page_endio(page, op_is_write(op), 0); break; case 1: ret = 0; diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c index 85de8053aa34..0360c015f658 100644 --- a/drivers/nvdimm/btt.c +++ b/drivers/nvdimm/btt.c @@ -1423,11 +1423,11 @@ static int btt_write_pg(struct btt *btt, struct bio_integrity_payload *bip, static int btt_do_bvec(struct btt *btt, struct bio_integrity_payload *bip, struct page *page, unsigned int len, unsigned int off, - bool is_write, sector_t sector) + unsigned int op, sector_t sector) { int ret; - if (!is_write) { + if (!op_is_write(op)) { ret = btt_read_pg(btt, bip, page, off, sector, len); flush_dcache_page(page); } else { @@ -1464,7 +1464,7 @@ static blk_qc_t btt_make_request(struct request_queue *q, struct bio *bio) } err = btt_do_bvec(btt, bip, bvec.bv_page, len, bvec.bv_offset, - op_is_write(bio_op(bio)), iter.bi_sector); + bio_op(bio), iter.bi_sector); if (err) { dev_err(&btt->nd_btt->dev, "io error in %s sector %lld, len %d,\n", @@ -1483,16 +1483,16 @@ static blk_qc_t btt_make_request(struct request_queue *q, struct bio *bio) } static int btt_rw_page(struct block_device *bdev, sector_t sector, - struct page *page, bool is_write) + struct page *page, unsigned int op) { struct btt *btt = bdev->bd_disk->private_data; int rc; unsigned int len; len = hpage_nr_pages(page) * PAGE_SIZE; - rc = btt_do_bvec(btt, NULL, page, len, 0, is_write, sector); + rc = btt_do_bvec(btt, NULL, page, len, 0, op, sector); if (rc == 0) - page_endio(page, is_write, 0); + page_endio(page, op_is_write(op), 0); return rc; } diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 8b1fd7f1a224..dd17acd8fe68 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -120,7 +120,7 @@ static blk_status_t read_pmem(struct page *page, unsigned int off, } static blk_status_t pmem_do_bvec(struct pmem_device *pmem, struct page *page, - unsigned int len, unsigned int off, bool is_write, + unsigned int len, unsigned int off, unsigned int op, sector_t sector) { blk_status_t rc = BLK_STS_OK; @@ -131,7 +131,7 @@ static blk_status_t pmem_do_bvec(struct pmem_device *pmem, struct page *page, if (unlikely(is_bad_pmem(&pmem->bb, sector, len))) bad_pmem = true; - if (!is_write) { + if (!op_is_write(op)) { if (unlikely(bad_pmem)) rc = BLK_STS_IOERR; else { @@ -180,8 +180,7 @@ static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio) do_acct = nd_iostat_start(bio, &start); bio_for_each_segment(bvec, bio, iter) { rc = pmem_do_bvec(pmem, bvec.bv_page, bvec.bv_len, - bvec.bv_offset, op_is_write(bio_op(bio)), - iter.bi_sector); + bvec.bv_offset, bio_op(bio), iter.bi_sector); if (rc) { bio->bi_status = rc; break; @@ -198,13 +197,13 @@ static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio) } static int pmem_rw_page(struct block_device *bdev, sector_t sector, - struct page *page, bool is_write) + struct page *page, unsigned int op) { struct pmem_device *pmem = bdev->bd_queue->queuedata; blk_status_t rc; rc = pmem_do_bvec(pmem, page, hpage_nr_pages(page) * PAGE_SIZE, - 0, is_write, sector); + 0, op, sector); /* * The ->rw_page interface is subtle and tricky. The core @@ -213,7 +212,7 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector, * caused by double completion. */ if (rc == 0) - page_endio(page, is_write, 0); + page_endio(page, op_is_write(op), 0); return blk_status_to_errno(rc); } diff --git a/fs/block_dev.c b/fs/block_dev.c index 0dd87aaeb39a..496fb51a1e1a 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -665,7 +665,8 @@ int bdev_read_page(struct block_device *bdev, sector_t sector, result = blk_queue_enter(bdev->bd_queue, 0); if (result) return result; - result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, false); + result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, + REQ_OP_READ); blk_queue_exit(bdev->bd_queue); return result; } @@ -703,7 +704,8 @@ int bdev_write_page(struct block_device *bdev, sector_t sector, return result; set_page_writeback(page); - result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, true); + result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, + REQ_OP_WRITE); if (result) { end_page_writeback(page); } else { diff --git a/fs/mpage.c b/fs/mpage.c index b7e7f570733a..b73638db9866 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -51,8 +51,8 @@ static void mpage_end_io(struct bio *bio) bio_for_each_segment_all(bv, bio, i) { struct page *page = bv->bv_page; - page_endio(page, op_is_write(bio_op(bio)), - blk_status_to_errno(bio->bi_status)); + page_endio(page, bio_op(bio), + blk_status_to_errno(bio->bi_status)); } bio_put(bio); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 1939ed95f936..331a6cb8805f 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1943,7 +1943,7 @@ static inline bool integrity_req_gap_front_merge(struct request *req, struct block_device_operations { int (*open) (struct block_device *, fmode_t); void (*release) (struct gendisk *, fmode_t); - int (*rw_page)(struct block_device *, sector_t, struct page *, bool); + int (*rw_page)(struct block_device *, sector_t, struct page *, unsigned int); int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); unsigned int (*check_events) (struct gendisk *disk, -- cgit v1.2.3 From 59767fbd49d794b4499d30b314df6c0d4aca584b Mon Sep 17 00:00:00 2001 From: Michael Callahan Date: Wed, 18 Jul 2018 04:47:37 -0700 Subject: block: Add part_stat_read_accum to read across field entries. Add a part_stat_read_accum macro to genhd.h to read and sum across field entries. For example to sum up the number read and write sectors completed. In addition to being ar reasonable cleanup by itself this will make it easier to add new stat fields in the future. tj: Refreshed on top of v4.17. Signed-off-by: Michael Callahan Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- drivers/block/drbd/drbd_receiver.c | 3 +-- drivers/block/drbd/drbd_worker.c | 4 +--- drivers/md/md.c | 3 +-- include/linux/genhd.h | 4 ++++ 4 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index a36a30795c43..75f6b47169e6 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -2674,8 +2674,7 @@ bool drbd_rs_c_min_rate_throttle(struct drbd_device *device) if (c_min_rate == 0) return false; - curr_events = (int)part_stat_read(&disk->part0, sectors[0]) + - (int)part_stat_read(&disk->part0, sectors[1]) - + curr_events = (int)part_stat_read_accum(&disk->part0, sectors) - atomic_read(&device->rs_sect_ev); if (atomic_read(&device->ap_actlog_cnt) diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c index 5e793dd7adfb..b8f77e83d456 100644 --- a/drivers/block/drbd/drbd_worker.c +++ b/drivers/block/drbd/drbd_worker.c @@ -1690,9 +1690,7 @@ void drbd_rs_controller_reset(struct drbd_device *device) atomic_set(&device->rs_sect_in, 0); atomic_set(&device->rs_sect_ev, 0); device->rs_in_flight = 0; - device->rs_last_events = - (int)part_stat_read(&disk->part0, sectors[0]) + - (int)part_stat_read(&disk->part0, sectors[1]); + device->rs_last_events = (int)part_stat_read_accum(&disk->part0, sectors); /* Updating the RCU protected object in place is necessary since this function gets called from atomic context. diff --git a/drivers/md/md.c b/drivers/md/md.c index 994aed2f9dff..dabe36723d60 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -8046,8 +8046,7 @@ static int is_mddev_idle(struct mddev *mddev, int init) rcu_read_lock(); rdev_for_each_rcu(rdev, mddev) { struct gendisk *disk = rdev->bdev->bd_contains->bd_disk; - curr_events = (int)part_stat_read(&disk->part0, sectors[0]) + - (int)part_stat_read(&disk->part0, sectors[1]) - + curr_events = (int)part_stat_read_accum(&disk->part0, sectors) - atomic_read(&disk->sync_io); /* sync IO will cause sync_io to increase before the disk_stats * as sync_io is counted when a request starts, and diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 6cb8a5789668..19f36fa10995 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -353,6 +353,10 @@ static inline void free_part_stats(struct hd_struct *part) #endif /* CONFIG_SMP */ +#define part_stat_read_accum(part, field) \ + (part_stat_read(part, field[0]) + \ + part_stat_read(part, field[1])) + #define part_stat_add(cpu, part, field, addnd) do { \ __part_stat_add((cpu), (part), field, addnd); \ if ((part)->partno) \ -- cgit v1.2.3 From dbae2c551377b6533a00c11fc7ede370100ab404 Mon Sep 17 00:00:00 2001 From: Michael Callahan Date: Wed, 18 Jul 2018 04:47:38 -0700 Subject: block: Define and use STAT_READ and STAT_WRITE Add defines for STAT_READ and STAT_WRITE for indexing the partition stat entries. This clarifies some fs/ code which has hardcoded 1 for STAT_WRITE and will make it easier to extend the stats with additional fields. tj: Refreshed on top of v4.17. Signed-off-by: Michael Callahan Signed-off-by: Tejun Heo Cc: "Theodore Ts'o" Cc: Jaegeuk Kim Signed-off-by: Jens Axboe --- block/genhd.c | 16 ++++++++-------- block/partition-generic.c | 16 ++++++++-------- fs/ext4/super.c | 5 +++-- fs/ext4/sysfs.c | 6 ++++-- fs/f2fs/f2fs.h | 2 +- fs/f2fs/super.c | 3 ++- include/linux/blk_types.h | 7 +++++++ include/linux/genhd.h | 13 +++++++------ 8 files changed, 40 insertions(+), 28 deletions(-) (limited to 'include') diff --git a/block/genhd.c b/block/genhd.c index f1543a45e73b..0711a800d0d4 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1337,14 +1337,14 @@ static int diskstats_show(struct seq_file *seqf, void *v) "%u %lu %lu %lu %u %u %u %u\n", MAJOR(part_devt(hd)), MINOR(part_devt(hd)), disk_name(gp, hd->partno, buf), - part_stat_read(hd, ios[READ]), - part_stat_read(hd, merges[READ]), - part_stat_read(hd, sectors[READ]), - jiffies_to_msecs(part_stat_read(hd, ticks[READ])), - part_stat_read(hd, ios[WRITE]), - part_stat_read(hd, merges[WRITE]), - part_stat_read(hd, sectors[WRITE]), - jiffies_to_msecs(part_stat_read(hd, ticks[WRITE])), + part_stat_read(hd, ios[STAT_READ]), + part_stat_read(hd, merges[STAT_READ]), + part_stat_read(hd, sectors[STAT_READ]), + jiffies_to_msecs(part_stat_read(hd, ticks[STAT_READ])), + part_stat_read(hd, ios[STAT_WRITE]), + part_stat_read(hd, merges[STAT_WRITE]), + part_stat_read(hd, sectors[STAT_WRITE]), + jiffies_to_msecs(part_stat_read(hd, ticks[STAT_WRITE])), inflight[0], jiffies_to_msecs(part_stat_read(hd, io_ticks)), jiffies_to_msecs(part_stat_read(hd, time_in_queue)) diff --git a/block/partition-generic.c b/block/partition-generic.c index 3dcfd4ec0e11..0ddb06722162 100644 --- a/block/partition-generic.c +++ b/block/partition-generic.c @@ -132,14 +132,14 @@ ssize_t part_stat_show(struct device *dev, "%8lu %8lu %8llu %8u " "%8u %8u %8u" "\n", - part_stat_read(p, ios[READ]), - part_stat_read(p, merges[READ]), - (unsigned long long)part_stat_read(p, sectors[READ]), - jiffies_to_msecs(part_stat_read(p, ticks[READ])), - part_stat_read(p, ios[WRITE]), - part_stat_read(p, merges[WRITE]), - (unsigned long long)part_stat_read(p, sectors[WRITE]), - jiffies_to_msecs(part_stat_read(p, ticks[WRITE])), + part_stat_read(p, ios[STAT_READ]), + part_stat_read(p, merges[STAT_READ]), + (unsigned long long)part_stat_read(p, sectors[STAT_READ]), + jiffies_to_msecs(part_stat_read(p, ticks[STAT_READ])), + part_stat_read(p, ios[STAT_WRITE]), + part_stat_read(p, merges[STAT_WRITE]), + (unsigned long long)part_stat_read(p, sectors[STAT_WRITE]), + jiffies_to_msecs(part_stat_read(p, ticks[STAT_WRITE])), inflight[0], jiffies_to_msecs(part_stat_read(p, io_ticks)), jiffies_to_msecs(part_stat_read(p, time_in_queue))); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index ba2396a7bd04..4b8aef989552 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -3514,7 +3514,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_sb_block = sb_block; if (sb->s_bdev->bd_part) sbi->s_sectors_written_start = - part_stat_read(sb->s_bdev->bd_part, sectors[1]); + part_stat_read(sb->s_bdev->bd_part, sectors[STAT_WRITE]); /* Cleanup superblock name */ strreplace(sb->s_id, '/', '!'); @@ -4824,7 +4824,8 @@ static int ext4_commit_super(struct super_block *sb, int sync) if (sb->s_bdev->bd_part) es->s_kbytes_written = cpu_to_le64(EXT4_SB(sb)->s_kbytes_written + - ((part_stat_read(sb->s_bdev->bd_part, sectors[1]) - + ((part_stat_read(sb->s_bdev->bd_part, + sectors[STAT_WRITE]) - EXT4_SB(sb)->s_sectors_written_start) >> 1)); else es->s_kbytes_written = diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c index f34da0bb8f17..2be9ad790017 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -56,7 +56,8 @@ static ssize_t session_write_kbytes_show(struct ext4_sb_info *sbi, char *buf) if (!sb->s_bdev->bd_part) return snprintf(buf, PAGE_SIZE, "0\n"); return snprintf(buf, PAGE_SIZE, "%lu\n", - (part_stat_read(sb->s_bdev->bd_part, sectors[1]) - + (part_stat_read(sb->s_bdev->bd_part, + sectors[STAT_WRITE]) - sbi->s_sectors_written_start) >> 1); } @@ -68,7 +69,8 @@ static ssize_t lifetime_write_kbytes_show(struct ext4_sb_info *sbi, char *buf) return snprintf(buf, PAGE_SIZE, "0\n"); return snprintf(buf, PAGE_SIZE, "%llu\n", (unsigned long long)(sbi->s_kbytes_written + - ((part_stat_read(sb->s_bdev->bd_part, sectors[1]) - + ((part_stat_read(sb->s_bdev->bd_part, + sectors[STAT_WRITE]) - EXT4_SB(sb)->s_sectors_written_start) >> 1))); } diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 4d8b1de83143..6799c3fc44e3 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1304,7 +1304,7 @@ static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type) * and the return value is in kbytes. s is of struct f2fs_sb_info. */ #define BD_PART_WRITTEN(s) \ -(((u64)part_stat_read((s)->sb->s_bdev->bd_part, sectors[1]) - \ +(((u64)part_stat_read((s)->sb->s_bdev->bd_part, sectors[STAT_WRITE]) - \ (s)->sectors_written_start) >> 1) static inline void f2fs_update_time(struct f2fs_sb_info *sbi, int type) diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 3995e926ba3a..17bcff789c08 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -2882,7 +2882,8 @@ try_onemore: /* For write statistics */ if (sb->s_bdev->bd_part) sbi->sectors_written_start = - (u64)part_stat_read(sb->s_bdev->bd_part, sectors[1]); + (u64)part_stat_read(sb->s_bdev->bd_part, + sectors[STAT_WRITE]); /* Read accumulated write IO statistics if exists */ seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index e13449a379a1..d2b44de56bc1 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -357,6 +357,13 @@ enum req_flag_bits { #define REQ_NOMERGE_FLAGS \ (REQ_NOMERGE | REQ_PREFLUSH | REQ_FUA) +enum stat_group { + STAT_READ, + STAT_WRITE, + + NR_STAT_GROUPS +}; + #define bio_op(bio) \ ((bio)->bi_opf & REQ_OP_MASK) #define req_op(req) \ diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 19f36fa10995..a75445446974 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -16,6 +16,7 @@ #include #include #include +#include #ifdef CONFIG_BLOCK @@ -82,10 +83,10 @@ struct partition { } __attribute__((packed)); struct disk_stats { - unsigned long sectors[2]; /* READs and WRITEs */ - unsigned long ios[2]; - unsigned long merges[2]; - unsigned long ticks[2]; + unsigned long sectors[NR_STAT_GROUPS]; + unsigned long ios[NR_STAT_GROUPS]; + unsigned long merges[NR_STAT_GROUPS]; + unsigned long ticks[NR_STAT_GROUPS]; unsigned long io_ticks; unsigned long time_in_queue; }; @@ -354,8 +355,8 @@ static inline void free_part_stats(struct hd_struct *part) #endif /* CONFIG_SMP */ #define part_stat_read_accum(part, field) \ - (part_stat_read(part, field[0]) + \ - part_stat_read(part, field[1])) + (part_stat_read(part, field[STAT_READ]) + \ + part_stat_read(part, field[STAT_WRITE])) #define part_stat_add(cpu, part, field, addnd) do { \ __part_stat_add((cpu), (part), field, addnd); \ -- cgit v1.2.3 From ddcf35d397976421a4ec1d0d00fbcc027a8cb034 Mon Sep 17 00:00:00 2001 From: Michael Callahan Date: Wed, 18 Jul 2018 04:47:39 -0700 Subject: block: Add and use op_stat_group() for indexing disk_stat fields. Add and use a new op_stat_group() function for indexing partition stat fields rather than indexing them by rq_data_dir() or bio_data_dir(). This function works similarly to op_is_sync() in that it takes the request::cmd_flags or bio::bi_opf flags and determines which stats should et updated. In addition, the second parameter to generic_start_io_acct() and generic_end_io_acct() is now a REQ_OP rather than simply a read or write bit and it uses op_stat_group() on the parameter to determine the stat group. Note that the partition in_flight counts are not part of the per-cpu statistics and as such are not indexed via this function. It's now indexed by op_is_write(). tj: Refreshed on top of v4.17. Updated to pass around REQ_OP. Signed-off-by: Michael Callahan Signed-off-by: Tejun Heo Cc: Minchan Kim Cc: Dan Williams Cc: Joshua Morris Cc: Philipp Reisner Cc: Matias Bjorling Cc: Kent Overstreet Cc: Alasdair Kergon Signed-off-by: Jens Axboe --- block/bio.c | 16 +++++++++------- block/blk-core.c | 12 ++++++------ drivers/block/drbd/drbd_req.c | 4 ++-- drivers/block/rsxx/dev.c | 6 +++--- drivers/block/zram/zram_drv.c | 5 ++--- drivers/lightnvm/pblk-cache.c | 5 +++-- drivers/lightnvm/pblk-read.c | 5 +++-- drivers/md/bcache/request.c | 13 +++++-------- drivers/md/dm.c | 6 ++++-- drivers/md/md.c | 5 +++-- drivers/nvdimm/nd.h | 7 +++---- include/linux/bio.h | 4 ++-- include/linux/blk_types.h | 5 +++++ 13 files changed, 50 insertions(+), 43 deletions(-) (limited to 'include') diff --git a/block/bio.c b/block/bio.c index f3536bfc8298..8ecc95615941 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1728,29 +1728,31 @@ void bio_check_pages_dirty(struct bio *bio) } EXPORT_SYMBOL_GPL(bio_check_pages_dirty); -void generic_start_io_acct(struct request_queue *q, int rw, +void generic_start_io_acct(struct request_queue *q, int op, unsigned long sectors, struct hd_struct *part) { + const int sgrp = op_stat_group(op); int cpu = part_stat_lock(); part_round_stats(q, cpu, part); - part_stat_inc(cpu, part, ios[rw]); - part_stat_add(cpu, part, sectors[rw], sectors); - part_inc_in_flight(q, part, rw); + part_stat_inc(cpu, part, ios[sgrp]); + part_stat_add(cpu, part, sectors[sgrp], sectors); + part_inc_in_flight(q, part, op_is_write(op)); part_stat_unlock(); } EXPORT_SYMBOL(generic_start_io_acct); -void generic_end_io_acct(struct request_queue *q, int rw, +void generic_end_io_acct(struct request_queue *q, int req_op, struct hd_struct *part, unsigned long start_time) { unsigned long duration = jiffies - start_time; + const int sgrp = op_stat_group(req_op); int cpu = part_stat_lock(); - part_stat_add(cpu, part, ticks[rw], duration); + part_stat_add(cpu, part, ticks[sgrp], duration); part_round_stats(q, cpu, part); - part_dec_in_flight(q, part, rw); + part_dec_in_flight(q, part, op_is_write(req_op)); part_stat_unlock(); } diff --git a/block/blk-core.c b/block/blk-core.c index c4b57d8806fe..03a4ea93a5f3 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -2702,13 +2702,13 @@ EXPORT_SYMBOL_GPL(blk_rq_err_bytes); void blk_account_io_completion(struct request *req, unsigned int bytes) { if (blk_do_io_stat(req)) { - const int rw = rq_data_dir(req); + const int sgrp = op_stat_group(req_op(req)); struct hd_struct *part; int cpu; cpu = part_stat_lock(); part = req->part; - part_stat_add(cpu, part, sectors[rw], bytes >> 9); + part_stat_add(cpu, part, sectors[sgrp], bytes >> 9); part_stat_unlock(); } } @@ -2722,7 +2722,7 @@ void blk_account_io_done(struct request *req, u64 now) */ if (blk_do_io_stat(req) && !(req->rq_flags & RQF_FLUSH_SEQ)) { unsigned long duration; - const int rw = rq_data_dir(req); + const int sgrp = op_stat_group(req_op(req)); struct hd_struct *part; int cpu; @@ -2730,10 +2730,10 @@ void blk_account_io_done(struct request *req, u64 now) cpu = part_stat_lock(); part = req->part; - part_stat_inc(cpu, part, ios[rw]); - part_stat_add(cpu, part, ticks[rw], duration); + part_stat_inc(cpu, part, ios[sgrp]); + part_stat_add(cpu, part, ticks[sgrp], duration); part_round_stats(req->q, cpu, part); - part_dec_in_flight(req->q, part, rw); + part_dec_in_flight(req->q, part, rq_data_dir(req)); hd_struct_put(part); part_stat_unlock(); diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c index d146fedc38bb..19cac36e9737 100644 --- a/drivers/block/drbd/drbd_req.c +++ b/drivers/block/drbd/drbd_req.c @@ -38,7 +38,7 @@ static void _drbd_start_io_acct(struct drbd_device *device, struct drbd_request { struct request_queue *q = device->rq_queue; - generic_start_io_acct(q, bio_data_dir(req->master_bio), + generic_start_io_acct(q, bio_op(req->master_bio), req->i.size >> 9, &device->vdisk->part0); } @@ -47,7 +47,7 @@ static void _drbd_end_io_acct(struct drbd_device *device, struct drbd_request *r { struct request_queue *q = device->rq_queue; - generic_end_io_acct(q, bio_data_dir(req->master_bio), + generic_end_io_acct(q, bio_op(req->master_bio), &device->vdisk->part0, req->start_jif); } diff --git a/drivers/block/rsxx/dev.c b/drivers/block/rsxx/dev.c index dddb3f2490b6..1a92f9e65937 100644 --- a/drivers/block/rsxx/dev.c +++ b/drivers/block/rsxx/dev.c @@ -112,7 +112,7 @@ static const struct block_device_operations rsxx_fops = { static void disk_stats_start(struct rsxx_cardinfo *card, struct bio *bio) { - generic_start_io_acct(card->queue, bio_data_dir(bio), bio_sectors(bio), + generic_start_io_acct(card->queue, bio_op(bio), bio_sectors(bio), &card->gendisk->part0); } @@ -120,8 +120,8 @@ static void disk_stats_complete(struct rsxx_cardinfo *card, struct bio *bio, unsigned long start_time) { - generic_end_io_acct(card->queue, bio_data_dir(bio), - &card->gendisk->part0, start_time); + generic_end_io_acct(card->queue, bio_op(bio), + &card->gendisk->part0, start_time); } static void bio_dma_done_cb(struct rsxx_cardinfo *card, diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 78c29044684a..2907a8156aaf 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1277,11 +1277,10 @@ static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index, int offset, unsigned int op, struct bio *bio) { unsigned long start_time = jiffies; - int rw_acct = op_is_write(op) ? REQ_OP_WRITE : REQ_OP_READ; struct request_queue *q = zram->disk->queue; int ret; - generic_start_io_acct(q, rw_acct, bvec->bv_len >> SECTOR_SHIFT, + generic_start_io_acct(q, op, bvec->bv_len >> SECTOR_SHIFT, &zram->disk->part0); if (!op_is_write(op)) { @@ -1293,7 +1292,7 @@ static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index, ret = zram_bvec_write(zram, bvec, index, offset, bio); } - generic_end_io_acct(q, rw_acct, &zram->disk->part0, start_time); + generic_end_io_acct(q, op, &zram->disk->part0, start_time); zram_slot_lock(zram, index); zram_accessed(zram, index); diff --git a/drivers/lightnvm/pblk-cache.c b/drivers/lightnvm/pblk-cache.c index 77d811962818..f565a56b898a 100644 --- a/drivers/lightnvm/pblk-cache.c +++ b/drivers/lightnvm/pblk-cache.c @@ -27,7 +27,8 @@ int pblk_write_to_cache(struct pblk *pblk, struct bio *bio, unsigned long flags) int nr_entries = pblk_get_secs(bio); int i, ret; - generic_start_io_acct(q, WRITE, bio_sectors(bio), &pblk->disk->part0); + generic_start_io_acct(q, REQ_OP_WRITE, bio_sectors(bio), + &pblk->disk->part0); /* Update the write buffer head (mem) with the entries that we can * write. The write in itself cannot fail, so there is no need to @@ -75,7 +76,7 @@ retry: pblk_rl_inserted(&pblk->rl, nr_entries); out: - generic_end_io_acct(q, WRITE, &pblk->disk->part0, start_time); + generic_end_io_acct(q, REQ_OP_WRITE, &pblk->disk->part0, start_time); pblk_write_should_kick(pblk); return ret; } diff --git a/drivers/lightnvm/pblk-read.c b/drivers/lightnvm/pblk-read.c index 26d414ae25b6..5a46d7f9302f 100644 --- a/drivers/lightnvm/pblk-read.c +++ b/drivers/lightnvm/pblk-read.c @@ -199,7 +199,7 @@ static void __pblk_end_io_read(struct pblk *pblk, struct nvm_rq *rqd, struct bio *int_bio = rqd->bio; unsigned long start_time = r_ctx->start_time; - generic_end_io_acct(dev->q, READ, &pblk->disk->part0, start_time); + generic_end_io_acct(dev->q, REQ_OP_READ, &pblk->disk->part0, start_time); if (rqd->error) pblk_log_read_err(pblk, rqd); @@ -461,7 +461,8 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio) return NVM_IO_ERR; } - generic_start_io_acct(q, READ, bio_sectors(bio), &pblk->disk->part0); + generic_start_io_acct(q, REQ_OP_READ, bio_sectors(bio), + &pblk->disk->part0); bitmap_zero(read_bitmap, nr_secs); diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index ae67f5fa8047..97707b0c54ce 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -667,8 +667,7 @@ static void backing_request_endio(struct bio *bio) static void bio_complete(struct search *s) { if (s->orig_bio) { - generic_end_io_acct(s->d->disk->queue, - bio_data_dir(s->orig_bio), + generic_end_io_acct(s->d->disk->queue, bio_op(s->orig_bio), &s->d->disk->part0, s->start_time); trace_bcache_request_end(s->d, s->orig_bio); @@ -1062,8 +1061,7 @@ static void detached_dev_end_io(struct bio *bio) bio->bi_end_io = ddip->bi_end_io; bio->bi_private = ddip->bi_private; - generic_end_io_acct(ddip->d->disk->queue, - bio_data_dir(bio), + generic_end_io_acct(ddip->d->disk->queue, bio_op(bio), &ddip->d->disk->part0, ddip->start_time); if (bio->bi_status) { @@ -1120,7 +1118,7 @@ static blk_qc_t cached_dev_make_request(struct request_queue *q, } atomic_set(&dc->backing_idle, 0); - generic_start_io_acct(q, rw, bio_sectors(bio), &d->disk->part0); + generic_start_io_acct(q, bio_op(bio), bio_sectors(bio), &d->disk->part0); bio_set_dev(bio, dc->bdev); bio->bi_iter.bi_sector += dc->sb.data_offset; @@ -1229,7 +1227,6 @@ static blk_qc_t flash_dev_make_request(struct request_queue *q, struct search *s; struct closure *cl; struct bcache_device *d = bio->bi_disk->private_data; - int rw = bio_data_dir(bio); if (unlikely(d->c && test_bit(CACHE_SET_IO_DISABLE, &d->c->flags))) { bio->bi_status = BLK_STS_IOERR; @@ -1237,7 +1234,7 @@ static blk_qc_t flash_dev_make_request(struct request_queue *q, return BLK_QC_T_NONE; } - generic_start_io_acct(q, rw, bio_sectors(bio), &d->disk->part0); + generic_start_io_acct(q, bio_op(bio), bio_sectors(bio), &d->disk->part0); s = search_alloc(bio, d); cl = &s->cl; @@ -1254,7 +1251,7 @@ static blk_qc_t flash_dev_make_request(struct request_queue *q, flash_dev_nodata, bcache_wq); return BLK_QC_T_NONE; - } else if (rw) { + } else if (bio_data_dir(bio)) { bch_keybuf_check_overlapping(&s->iop.c->moving_gc_keys, &KEY(d->id, bio->bi_iter.bi_sector, 0), &KEY(d->id, bio_end_sector(bio), 0)); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index b0dd7027848b..20f7e4ef5342 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -609,7 +609,8 @@ static void start_io_acct(struct dm_io *io) io->start_time = jiffies; - generic_start_io_acct(md->queue, rw, bio_sectors(bio), &dm_disk(md)->part0); + generic_start_io_acct(md->queue, bio_op(bio), bio_sectors(bio), + &dm_disk(md)->part0); atomic_set(&dm_disk(md)->part0.in_flight[rw], atomic_inc_return(&md->pending[rw])); @@ -628,7 +629,8 @@ static void end_io_acct(struct dm_io *io) int pending; int rw = bio_data_dir(bio); - generic_end_io_acct(md->queue, rw, &dm_disk(md)->part0, io->start_time); + generic_end_io_acct(md->queue, bio_op(bio), &dm_disk(md)->part0, + io->start_time); if (unlikely(dm_stats_used(&md->stats))) dm_stats_account_io(&md->stats, bio_data_dir(bio), diff --git a/drivers/md/md.c b/drivers/md/md.c index dabe36723d60..f6e58dbca0d4 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -335,6 +335,7 @@ EXPORT_SYMBOL(md_handle_request); static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio) { const int rw = bio_data_dir(bio); + const int sgrp = op_stat_group(bio_op(bio)); struct mddev *mddev = q->queuedata; unsigned int sectors; int cpu; @@ -363,8 +364,8 @@ static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio) md_handle_request(mddev, bio); cpu = part_stat_lock(); - part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]); - part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw], sectors); + part_stat_inc(cpu, &mddev->gendisk->part0, ios[sgrp]); + part_stat_add(cpu, &mddev->gendisk->part0, sectors[sgrp], sectors); part_stat_unlock(); return BLK_QC_T_NONE; diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h index 32e0364b48b9..6ee7fd7e4bbd 100644 --- a/drivers/nvdimm/nd.h +++ b/drivers/nvdimm/nd.h @@ -396,16 +396,15 @@ static inline bool nd_iostat_start(struct bio *bio, unsigned long *start) return false; *start = jiffies; - generic_start_io_acct(disk->queue, bio_data_dir(bio), - bio_sectors(bio), &disk->part0); + generic_start_io_acct(disk->queue, bio_op(bio), bio_sectors(bio), + &disk->part0); return true; } static inline void nd_iostat_end(struct bio *bio, unsigned long start) { struct gendisk *disk = bio->bi_disk; - generic_end_io_acct(disk->queue, bio_data_dir(bio), &disk->part0, - start); + generic_end_io_acct(disk->queue, bio_op(bio), &disk->part0, start); } static inline bool is_bad_pmem(struct badblocks *bb, sector_t sector, unsigned int len) diff --git a/include/linux/bio.h b/include/linux/bio.h index a00dfff51aa5..ab221c517f4e 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -496,9 +496,9 @@ extern struct bio *bio_copy_kern(struct request_queue *, void *, unsigned int, extern void bio_set_pages_dirty(struct bio *bio); extern void bio_check_pages_dirty(struct bio *bio); -void generic_start_io_acct(struct request_queue *q, int rw, +void generic_start_io_acct(struct request_queue *q, int op, unsigned long sectors, struct hd_struct *part); -void generic_end_io_acct(struct request_queue *q, int rw, +void generic_end_io_acct(struct request_queue *q, int op, struct hd_struct *part, unsigned long start_time); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index d2b44de56bc1..2960a96d833c 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -401,6 +401,11 @@ static inline bool op_is_sync(unsigned int op) (op & (REQ_SYNC | REQ_FUA | REQ_PREFLUSH)); } +static inline int op_stat_group(unsigned int op) +{ + return op_is_write(op); +} + typedef unsigned int blk_qc_t; #define BLK_QC_T_NONE -1U #define BLK_QC_T_SHIFT 16 -- cgit v1.2.3 From bdca3c87fb7ad1cc61d231d37eb0d8f90d001e0c Mon Sep 17 00:00:00 2001 From: Michael Callahan Date: Wed, 18 Jul 2018 04:47:40 -0700 Subject: block: Track DISCARD statistics and output them in stat and diskstat Add tracking of REQ_OP_DISCARD ios to the partition statistics and append them to the various stat files in /sys as well as /proc/diskstats. These are tracked with the same four stats as reads and writes: Number of discard ios completed. Number of discard ios merged Number of discard sectors completed Milliseconds spent on discard requests This is done via adding a new STAT_DISCARD define to genhd.h and then using it to index that stat field for discard requests. tj: Refreshed on top of v4.17 and other previous updates. Signed-off-by: Michael Callahan Signed-off-by: Tejun Heo Cc: Andy Newell Signed-off-by: Jens Axboe --- Documentation/ABI/testing/procfs-diskstats | 10 ++++++++++ Documentation/block/stat.txt | 28 ++++++++++++++++------------ Documentation/iostats.txt | 15 +++++++++++++++ block/genhd.c | 13 ++++++++++--- block/partition-generic.c | 9 +++++++-- include/linux/blk_types.h | 8 ++++++++ include/linux/genhd.h | 3 ++- 7 files changed, 68 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/Documentation/ABI/testing/procfs-diskstats b/Documentation/ABI/testing/procfs-diskstats index f91a973a37fe..abac31d216de 100644 --- a/Documentation/ABI/testing/procfs-diskstats +++ b/Documentation/ABI/testing/procfs-diskstats @@ -5,6 +5,7 @@ Description: The /proc/diskstats file displays the I/O statistics of block devices. Each line contains the following 14 fields: + 1 - major number 2 - minor mumber 3 - device name @@ -19,4 +20,13 @@ Description: 12 - I/Os currently in progress 13 - time spent doing I/Os (ms) 14 - weighted time spent doing I/Os (ms) + + Kernel 4.18+ appends four more fields for discard + tracking putting the total at 18: + + 15 - discards completed successfully + 16 - discards merged + 17 - sectors discarded + 18 - time spent discarding + For more details refer to Documentation/iostats.txt diff --git a/Documentation/block/stat.txt b/Documentation/block/stat.txt index 0dbc946de2ea..0aace9cc536c 100644 --- a/Documentation/block/stat.txt +++ b/Documentation/block/stat.txt @@ -31,28 +31,32 @@ write ticks milliseconds total wait time for write requests in_flight requests number of I/Os currently in flight io_ticks milliseconds total time this block device has been active time_in_queue milliseconds total wait time for all requests +discard I/Os requests number of discard I/Os processed +discard merges requests number of discard I/Os merged with in-queue I/O +discard sectors sectors number of sectors discarded +discard ticks milliseconds total wait time for discard requests -read I/Os, write I/Os -===================== +read I/Os, write I/Os, discard I/0s +=================================== These values increment when an I/O request completes. -read merges, write merges -========================= +read merges, write merges, discard merges +========================================= These values increment when an I/O request is merged with an already-queued I/O request. -read sectors, write sectors -=========================== +read sectors, write sectors, discard_sectors +============================================ -These values count the number of sectors read from or written to this -block device. The "sectors" in question are the standard UNIX 512-byte -sectors, not any device- or filesystem-specific block size. The -counters are incremented when the I/O completes. +These values count the number of sectors read from, written to, or +discarded from this block device. The "sectors" in question are the +standard UNIX 512-byte sectors, not any device- or filesystem-specific +block size. The counters are incremented when the I/O completes. -read ticks, write ticks -======================= +read ticks, write ticks, discard ticks +====================================== These values count the number of milliseconds that I/O requests have waited on this block device. If there are multiple I/O requests waiting, diff --git a/Documentation/iostats.txt b/Documentation/iostats.txt index 04d394a2e06c..49df45f90e8a 100644 --- a/Documentation/iostats.txt +++ b/Documentation/iostats.txt @@ -31,6 +31,9 @@ Here are examples of these different formats:: 3 0 hda 446216 784926 9550688 4382310 424847 312726 5922052 19310380 0 3376340 23705160 3 1 hda1 35486 38030 38030 38030 + 4.18+ diskstats: + 3 0 hda 446216 784926 9550688 4382310 424847 312726 5922052 19310380 0 3376340 23705160 0 0 0 0 + On 2.4 you might execute ``grep 'hda ' /proc/partitions``. On 2.6+, you have a choice of ``cat /sys/block/hda/stat`` or ``grep 'hda ' /proc/diskstats``. @@ -101,6 +104,18 @@ Field 11 -- weighted # of milliseconds spent doing I/Os last update of this field. This can provide an easy measure of both I/O completion time and the backlog that may be accumulating. +Field 12 -- # of discards completed + This is the total number of discards completed successfully. + +Field 13 -- # of discards merged + See the description of field 2 + +Field 14 -- # of sectors discarded + This is the total number of sectors discarded successfully. + +Field 15 -- # of milliseconds spent discarding + This is the total number of milliseconds spent by all discards (as + measured from __make_request() to end_that_request_last()). To avoid introducing performance bottlenecks, no locks are held while modifying these counters. This implies that minor inaccuracies may be diff --git a/block/genhd.c b/block/genhd.c index 0711a800d0d4..8cc719a37b32 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1333,8 +1333,11 @@ static int diskstats_show(struct seq_file *seqf, void *v) part_round_stats(gp->queue, cpu, hd); part_stat_unlock(); part_in_flight(gp->queue, hd, inflight); - seq_printf(seqf, "%4d %7d %s %lu %lu %lu " - "%u %lu %lu %lu %u %u %u %u\n", + seq_printf(seqf, "%4d %7d %s " + "%lu %lu %lu %u " + "%lu %lu %lu %u " + "%u %u %u " + "%lu %lu %lu %u\n", MAJOR(part_devt(hd)), MINOR(part_devt(hd)), disk_name(gp, hd->partno, buf), part_stat_read(hd, ios[STAT_READ]), @@ -1347,7 +1350,11 @@ static int diskstats_show(struct seq_file *seqf, void *v) jiffies_to_msecs(part_stat_read(hd, ticks[STAT_WRITE])), inflight[0], jiffies_to_msecs(part_stat_read(hd, io_ticks)), - jiffies_to_msecs(part_stat_read(hd, time_in_queue)) + jiffies_to_msecs(part_stat_read(hd, time_in_queue)), + part_stat_read(hd, ios[STAT_DISCARD]), + part_stat_read(hd, merges[STAT_DISCARD]), + part_stat_read(hd, sectors[STAT_DISCARD]), + jiffies_to_msecs(part_stat_read(hd, ticks[STAT_DISCARD])) ); } disk_part_iter_exit(&piter); diff --git a/block/partition-generic.c b/block/partition-generic.c index 0ddb06722162..5a8975a1201c 100644 --- a/block/partition-generic.c +++ b/block/partition-generic.c @@ -130,7 +130,8 @@ ssize_t part_stat_show(struct device *dev, return sprintf(buf, "%8lu %8lu %8llu %8u " "%8lu %8lu %8llu %8u " - "%8u %8u %8u" + "%8u %8u %8u " + "%8lu %8lu %8llu %8u" "\n", part_stat_read(p, ios[STAT_READ]), part_stat_read(p, merges[STAT_READ]), @@ -142,7 +143,11 @@ ssize_t part_stat_show(struct device *dev, jiffies_to_msecs(part_stat_read(p, ticks[STAT_WRITE])), inflight[0], jiffies_to_msecs(part_stat_read(p, io_ticks)), - jiffies_to_msecs(part_stat_read(p, time_in_queue))); + jiffies_to_msecs(part_stat_read(p, time_in_queue)), + part_stat_read(p, ios[STAT_DISCARD]), + part_stat_read(p, merges[STAT_DISCARD]), + (unsigned long long)part_stat_read(p, sectors[STAT_DISCARD]), + jiffies_to_msecs(part_stat_read(p, ticks[STAT_DISCARD]))); } ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr, diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 2960a96d833c..f6dfb30737d8 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -360,6 +360,7 @@ enum req_flag_bits { enum stat_group { STAT_READ, STAT_WRITE, + STAT_DISCARD, NR_STAT_GROUPS }; @@ -401,8 +402,15 @@ static inline bool op_is_sync(unsigned int op) (op & (REQ_SYNC | REQ_FUA | REQ_PREFLUSH)); } +static inline bool op_is_discard(unsigned int op) +{ + return (op & REQ_OP_MASK) == REQ_OP_DISCARD; +} + static inline int op_stat_group(unsigned int op) { + if (op_is_discard(op)) + return STAT_DISCARD; return op_is_write(op); } diff --git a/include/linux/genhd.h b/include/linux/genhd.h index a75445446974..57864422a2c8 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -356,7 +356,8 @@ static inline void free_part_stats(struct hd_struct *part) #define part_stat_read_accum(part, field) \ (part_stat_read(part, field[STAT_READ]) + \ - part_stat_read(part, field[STAT_WRITE])) + part_stat_read(part, field[STAT_WRITE]) + \ + part_stat_read(part, field[STAT_DISCARD])) #define part_stat_add(cpu, part, field, addnd) do { \ __part_stat_add((cpu), (part), field, addnd); \ -- cgit v1.2.3 From 636620b66d5d4012c4a9c86206013964d3986c4f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 18 Jul 2018 04:47:41 -0700 Subject: blkcg: Track DISCARD statistics and output them in cgroup io.stat Add tracking of REQ_OP_DISCARD ios to the per-cgroup io.stat. Two fields, dbytes and dios, to respectively count the total bytes and number of discards are added. Signed-off-by: Tejun Heo Cc: Andy Newell Cc: Michael Callahan Signed-off-by: Jens Axboe --- Documentation/admin-guide/cgroup-v2.rst | 10 ++++++---- block/blk-cgroup.c | 13 +++++++++---- include/linux/blk-cgroup.h | 5 ++++- 3 files changed, 19 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 569ce27b85e5..3afe10fa82bc 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1317,17 +1317,19 @@ IO Interface Files Lines are keyed by $MAJ:$MIN device numbers and not ordered. The following nested keys are defined. - ====== =================== + ====== ===================== rbytes Bytes read wbytes Bytes written rios Number of read IOs wios Number of write IOs - ====== =================== + dbytes Bytes discarded + dios Number of discard IOs + ====== ===================== An example read output follows: - 8:16 rbytes=1459200 wbytes=314773504 rios=192 wios=353 - 8:0 rbytes=90430464 wbytes=299008000 rios=8950 wios=1252 + 8:16 rbytes=1459200 wbytes=314773504 rios=192 wios=353 dbytes=0 dios=0 + 8:0 rbytes=90430464 wbytes=299008000 rios=8950 wios=1252 dbytes=50331648 dios=3021 io.weight A read-write flat-keyed file which exists on non-root cgroups. diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 7e2c19ce1a08..1942357d7165 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -567,6 +567,7 @@ u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd, [BLKG_RWSTAT_WRITE] = "Write", [BLKG_RWSTAT_SYNC] = "Sync", [BLKG_RWSTAT_ASYNC] = "Async", + [BLKG_RWSTAT_DISCARD] = "Discard", }; const char *dname = blkg_dev_name(pd->blkg); u64 v; @@ -580,7 +581,8 @@ u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd, (unsigned long long)atomic64_read(&rwstat->aux_cnt[i])); v = atomic64_read(&rwstat->aux_cnt[BLKG_RWSTAT_READ]) + - atomic64_read(&rwstat->aux_cnt[BLKG_RWSTAT_WRITE]); + atomic64_read(&rwstat->aux_cnt[BLKG_RWSTAT_WRITE]) + + atomic64_read(&rwstat->aux_cnt[BLKG_RWSTAT_DISCARD]); seq_printf(sf, "%s Total %llu\n", dname, (unsigned long long)v); return v; } @@ -959,7 +961,7 @@ static int blkcg_print_stat(struct seq_file *sf, void *v) const char *dname; char *buf; struct blkg_rwstat rwstat; - u64 rbytes, wbytes, rios, wios; + u64 rbytes, wbytes, rios, wios, dbytes, dios; size_t size = seq_get_buf(sf, &buf), off = 0; int i; bool has_stats = false; @@ -982,19 +984,22 @@ static int blkcg_print_stat(struct seq_file *sf, void *v) offsetof(struct blkcg_gq, stat_bytes)); rbytes = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_READ]); wbytes = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_WRITE]); + dbytes = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_DISCARD]); rwstat = blkg_rwstat_recursive_sum(blkg, NULL, offsetof(struct blkcg_gq, stat_ios)); rios = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_READ]); wios = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_WRITE]); + dios = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_DISCARD]); spin_unlock_irq(blkg->q->queue_lock); if (rbytes || wbytes || rios || wios) { has_stats = true; off += scnprintf(buf+off, size-off, - "rbytes=%llu wbytes=%llu rios=%llu wios=%llu", - rbytes, wbytes, rios, wios); + "rbytes=%llu wbytes=%llu rios=%llu wios=%llu dbytes=%llu dios=%llu", + rbytes, wbytes, rios, wios, + dbytes, dios); } if (!blkcg_debug_stats) diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index de57de4831d5..3bed5e02a873 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -35,6 +35,7 @@ enum blkg_rwstat_type { BLKG_RWSTAT_WRITE, BLKG_RWSTAT_SYNC, BLKG_RWSTAT_ASYNC, + BLKG_RWSTAT_DISCARD, BLKG_RWSTAT_NR, BLKG_RWSTAT_TOTAL = BLKG_RWSTAT_NR, @@ -649,7 +650,9 @@ static inline void blkg_rwstat_add(struct blkg_rwstat *rwstat, { struct percpu_counter *cnt; - if (op_is_write(op)) + if (op_is_discard(op)) + cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_DISCARD]; + else if (op_is_write(op)) cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_WRITE]; else cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_READ]; -- cgit v1.2.3 From bcf7eac3d97f49d8400ba52c71bee5934bf20093 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Tue, 17 Jul 2018 00:47:48 +0900 Subject: regmap: add SCCB support This adds Serial Camera Control Bus (SCCB) support for regmap API that is intended to be used by some of Omnivision sensor drivers. The ov772x and ov9650 drivers are going to use this SCCB regmap API. The ov772x driver was previously only worked with the i2c controller drivers that support I2C_FUNC_PROTOCOL_MANGLING, because the ov772x device doesn't support repeated starts. After commit 0b964d183cbf ("media: ov772x: allow i2c controllers without I2C_FUNC_PROTOCOL_MANGLING"), reading ov772x register is replaced with issuing two separated i2c messages in order to avoid repeated start. Using this SCCB regmap hides the implementation detail. The ov9650 driver also issues two separated i2c messages to read the registers as the device doesn't support repeated start. So it can make use of this SCCB regmap. Cc: Mark Brown Cc: Peter Rosin Cc: Sebastian Reichel Cc: Wolfram Sang Cc: Sylwester Nawrocki Cc: Jacopo Mondi Cc: Laurent Pinchart Cc: Hans Verkuil Cc: Sakari Ailus Cc: Mauro Carvalho Chehab Signed-off-by: Akinobu Mita Signed-off-by: Mark Brown --- drivers/base/regmap/Kconfig | 4 ++ drivers/base/regmap/Makefile | 1 + drivers/base/regmap/regmap-sccb.c | 128 ++++++++++++++++++++++++++++++++++++++ include/linux/regmap.h | 35 +++++++++++ 4 files changed, 168 insertions(+) create mode 100644 drivers/base/regmap/regmap-sccb.c (limited to 'include') diff --git a/drivers/base/regmap/Kconfig b/drivers/base/regmap/Kconfig index aff34c0c2a3e..6ad5ef48b61e 100644 --- a/drivers/base/regmap/Kconfig +++ b/drivers/base/regmap/Kconfig @@ -45,3 +45,7 @@ config REGMAP_IRQ config REGMAP_SOUNDWIRE tristate depends on SOUNDWIRE_BUS + +config REGMAP_SCCB + tristate + depends on I2C diff --git a/drivers/base/regmap/Makefile b/drivers/base/regmap/Makefile index 5ed0023fabda..f5b4e8851d00 100644 --- a/drivers/base/regmap/Makefile +++ b/drivers/base/regmap/Makefile @@ -15,3 +15,4 @@ obj-$(CONFIG_REGMAP_MMIO) += regmap-mmio.o obj-$(CONFIG_REGMAP_IRQ) += regmap-irq.o obj-$(CONFIG_REGMAP_W1) += regmap-w1.o obj-$(CONFIG_REGMAP_SOUNDWIRE) += regmap-sdw.o +obj-$(CONFIG_REGMAP_SCCB) += regmap-sccb.o diff --git a/drivers/base/regmap/regmap-sccb.c b/drivers/base/regmap/regmap-sccb.c new file mode 100644 index 000000000000..b6eb876ea819 --- /dev/null +++ b/drivers/base/regmap/regmap-sccb.c @@ -0,0 +1,128 @@ +// SPDX-License-Identifier: GPL-2.0 +// Register map access API - SCCB support + +#include +#include +#include + +#include "internal.h" + +/** + * sccb_is_available - Check if the adapter supports SCCB protocol + * @adap: I2C adapter + * + * Return true if the I2C adapter is capable of using SCCB helper functions, + * false otherwise. + */ +static bool sccb_is_available(struct i2c_adapter *adap) +{ + u32 needed_funcs = I2C_FUNC_SMBUS_BYTE | I2C_FUNC_SMBUS_WRITE_BYTE_DATA; + + /* + * If we ever want support for hardware doing SCCB natively, we will + * introduce a sccb_xfer() callback to struct i2c_algorithm and check + * for it here. + */ + + return (i2c_get_functionality(adap) & needed_funcs) == needed_funcs; +} + +/** + * regmap_sccb_read - Read data from SCCB slave device + * @context: Device that will be interacted wit + * @reg: Register to be read from + * @val: Pointer to store read value + * + * This executes the 2-phase write transmission cycle that is followed by a + * 2-phase read transmission cycle, returning negative errno else zero on + * success. + */ +static int regmap_sccb_read(void *context, unsigned int reg, unsigned int *val) +{ + struct device *dev = context; + struct i2c_client *i2c = to_i2c_client(dev); + int ret; + union i2c_smbus_data data; + + i2c_lock_bus(i2c->adapter, I2C_LOCK_SEGMENT); + + ret = __i2c_smbus_xfer(i2c->adapter, i2c->addr, i2c->flags, + I2C_SMBUS_WRITE, reg, I2C_SMBUS_BYTE, NULL); + if (ret < 0) + goto out; + + ret = __i2c_smbus_xfer(i2c->adapter, i2c->addr, i2c->flags, + I2C_SMBUS_READ, 0, I2C_SMBUS_BYTE, &data); + if (ret < 0) + goto out; + + *val = data.byte; +out: + i2c_unlock_bus(i2c->adapter, I2C_LOCK_SEGMENT); + + return ret; +} + +/** + * regmap_sccb_write - Write data to SCCB slave device + * @context: Device that will be interacted wit + * @reg: Register to write to + * @val: Value to be written + * + * This executes the SCCB 3-phase write transmission cycle, returning negative + * errno else zero on success. + */ +static int regmap_sccb_write(void *context, unsigned int reg, unsigned int val) +{ + struct device *dev = context; + struct i2c_client *i2c = to_i2c_client(dev); + + return i2c_smbus_write_byte_data(i2c, reg, val); +} + +static struct regmap_bus regmap_sccb_bus = { + .reg_write = regmap_sccb_write, + .reg_read = regmap_sccb_read, +}; + +static const struct regmap_bus *regmap_get_sccb_bus(struct i2c_client *i2c, + const struct regmap_config *config) +{ + if (config->val_bits == 8 && config->reg_bits == 8 && + sccb_is_available(i2c->adapter)) + return ®map_sccb_bus; + + return ERR_PTR(-ENOTSUPP); +} + +struct regmap *__regmap_init_sccb(struct i2c_client *i2c, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name) +{ + const struct regmap_bus *bus = regmap_get_sccb_bus(i2c, config); + + if (IS_ERR(bus)) + return ERR_CAST(bus); + + return __regmap_init(&i2c->dev, bus, &i2c->dev, config, + lock_key, lock_name); +} +EXPORT_SYMBOL_GPL(__regmap_init_sccb); + +struct regmap *__devm_regmap_init_sccb(struct i2c_client *i2c, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name) +{ + const struct regmap_bus *bus = regmap_get_sccb_bus(i2c, config); + + if (IS_ERR(bus)) + return ERR_CAST(bus); + + return __devm_regmap_init(&i2c->dev, bus, &i2c->dev, config, + lock_key, lock_name); +} +EXPORT_SYMBOL_GPL(__devm_regmap_init_sccb); + +MODULE_LICENSE("GPL v2"); diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 4f38068ffb71..52bf358e2c73 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -514,6 +514,10 @@ struct regmap *__regmap_init_i2c(struct i2c_client *i2c, const struct regmap_config *config, struct lock_class_key *lock_key, const char *lock_name); +struct regmap *__regmap_init_sccb(struct i2c_client *i2c, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); struct regmap *__regmap_init_slimbus(struct slim_device *slimbus, const struct regmap_config *config, struct lock_class_key *lock_key, @@ -558,6 +562,10 @@ struct regmap *__devm_regmap_init_i2c(struct i2c_client *i2c, const struct regmap_config *config, struct lock_class_key *lock_key, const char *lock_name); +struct regmap *__devm_regmap_init_sccb(struct i2c_client *i2c, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); struct regmap *__devm_regmap_init_spi(struct spi_device *dev, const struct regmap_config *config, struct lock_class_key *lock_key, @@ -645,6 +653,19 @@ int regmap_attach_dev(struct device *dev, struct regmap *map, __regmap_lockdep_wrapper(__regmap_init_i2c, #config, \ i2c, config) +/** + * regmap_init_sccb() - Initialise register map + * + * @i2c: Device that will be interacted with + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer to + * a struct regmap. + */ +#define regmap_init_sccb(i2c, config) \ + __regmap_lockdep_wrapper(__regmap_init_sccb, #config, \ + i2c, config) + /** * regmap_init_slimbus() - Initialise register map * @@ -797,6 +818,20 @@ bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg); __regmap_lockdep_wrapper(__devm_regmap_init_i2c, #config, \ i2c, config) +/** + * devm_regmap_init_sccb() - Initialise managed register map + * + * @i2c: Device that will be interacted with + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer + * to a struct regmap. The regmap will be automatically freed by the + * device management code. + */ +#define devm_regmap_init_sccb(i2c, config) \ + __regmap_lockdep_wrapper(__devm_regmap_init_sccb, #config, \ + i2c, config) + /** * devm_regmap_init_spi() - Initialise register map * -- cgit v1.2.3 From 7c201ead1bfd19935f689fca69100c335028c047 Mon Sep 17 00:00:00 2001 From: David Lechner Date: Mon, 16 Jul 2018 22:20:49 -0500 Subject: spi: spi-bitbang: change flags from u8 to u16 This changes the data type of the flags field in struct spi_bitbang from u8 to u16. This matches the size of the mode field of struct spi_device where these flags are also used. This is done in preparation of adding a new SPI mode flag that will be used with this field that would otherwise not fit in 8 bits. Signed-off-by: David Lechner Signed-off-by: Mark Brown --- include/linux/spi/spi_bitbang.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/spi/spi_bitbang.h b/include/linux/spi/spi_bitbang.h index 51d8c060e513..c1e61641a7f1 100644 --- a/include/linux/spi/spi_bitbang.h +++ b/include/linux/spi/spi_bitbang.h @@ -8,7 +8,7 @@ struct spi_bitbang { struct mutex lock; u8 busy; u8 use_dma; - u8 flags; /* extra spi->mode support */ + u16 flags; /* extra spi->mode support */ struct spi_master *master; -- cgit v1.2.3 From ce2d54619a10780a0d354e10d4c83ae4fad46f41 Mon Sep 17 00:00:00 2001 From: Ayan Kumar Halder Date: Tue, 17 Jul 2018 18:13:42 +0100 Subject: drm/fourcc: Add is_yuv field to drm_format_info to denote if the format is yuv A lot of drivers duplicate the function to check if a format is yuv or not. If we add a field (to denote whether the format is yuv or not) in the drm_format_info table, all the drivers can use this field and it will prevent duplication of similar logic. Signed-off-by: Ayan Kumar halder Reviewed-by: Ville Syrjala Link: https://patchwork.freedesktop.org/patch/msgid/1531847626-22248-1-git-send-email-ayan.halder@arm.com --- drivers/gpu/drm/drm_fourcc.c | 42 +++++++++++++++++++++--------------------- include/drm/drm_fourcc.h | 2 ++ 2 files changed, 23 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_fourcc.c b/drivers/gpu/drm/drm_fourcc.c index 5ca6395cd4d3..35c1e2742c27 100644 --- a/drivers/gpu/drm/drm_fourcc.c +++ b/drivers/gpu/drm/drm_fourcc.c @@ -152,27 +152,27 @@ const struct drm_format_info *__drm_format_info(u32 format) { .format = DRM_FORMAT_XBGR8888_A8, .depth = 32, .num_planes = 2, .cpp = { 4, 1, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true }, { .format = DRM_FORMAT_RGBX8888_A8, .depth = 32, .num_planes = 2, .cpp = { 4, 1, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true }, { .format = DRM_FORMAT_BGRX8888_A8, .depth = 32, .num_planes = 2, .cpp = { 4, 1, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true }, - { .format = DRM_FORMAT_YUV410, .depth = 0, .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 4, .vsub = 4 }, - { .format = DRM_FORMAT_YVU410, .depth = 0, .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 4, .vsub = 4 }, - { .format = DRM_FORMAT_YUV411, .depth = 0, .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 4, .vsub = 1 }, - { .format = DRM_FORMAT_YVU411, .depth = 0, .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 4, .vsub = 1 }, - { .format = DRM_FORMAT_YUV420, .depth = 0, .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 2, .vsub = 2 }, - { .format = DRM_FORMAT_YVU420, .depth = 0, .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 2, .vsub = 2 }, - { .format = DRM_FORMAT_YUV422, .depth = 0, .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 2, .vsub = 1 }, - { .format = DRM_FORMAT_YVU422, .depth = 0, .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 2, .vsub = 1 }, - { .format = DRM_FORMAT_YUV444, .depth = 0, .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 1, .vsub = 1 }, - { .format = DRM_FORMAT_YVU444, .depth = 0, .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 1, .vsub = 1 }, - { .format = DRM_FORMAT_NV12, .depth = 0, .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 2, .vsub = 2 }, - { .format = DRM_FORMAT_NV21, .depth = 0, .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 2, .vsub = 2 }, - { .format = DRM_FORMAT_NV16, .depth = 0, .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 2, .vsub = 1 }, - { .format = DRM_FORMAT_NV61, .depth = 0, .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 2, .vsub = 1 }, - { .format = DRM_FORMAT_NV24, .depth = 0, .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 1, .vsub = 1 }, - { .format = DRM_FORMAT_NV42, .depth = 0, .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 1, .vsub = 1 }, - { .format = DRM_FORMAT_YUYV, .depth = 0, .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 2, .vsub = 1 }, - { .format = DRM_FORMAT_YVYU, .depth = 0, .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 2, .vsub = 1 }, - { .format = DRM_FORMAT_UYVY, .depth = 0, .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 2, .vsub = 1 }, - { .format = DRM_FORMAT_VYUY, .depth = 0, .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 2, .vsub = 1 }, - { .format = DRM_FORMAT_AYUV, .depth = 0, .num_planes = 1, .cpp = { 4, 0, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true }, + { .format = DRM_FORMAT_YUV410, .depth = 0, .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 4, .vsub = 4, .is_yuv = true }, + { .format = DRM_FORMAT_YVU410, .depth = 0, .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 4, .vsub = 4, .is_yuv = true }, + { .format = DRM_FORMAT_YUV411, .depth = 0, .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 4, .vsub = 1, .is_yuv = true }, + { .format = DRM_FORMAT_YVU411, .depth = 0, .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 4, .vsub = 1, .is_yuv = true }, + { .format = DRM_FORMAT_YUV420, .depth = 0, .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 2, .vsub = 2, .is_yuv = true }, + { .format = DRM_FORMAT_YVU420, .depth = 0, .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 2, .vsub = 2, .is_yuv = true }, + { .format = DRM_FORMAT_YUV422, .depth = 0, .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 2, .vsub = 1, .is_yuv = true }, + { .format = DRM_FORMAT_YVU422, .depth = 0, .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 2, .vsub = 1, .is_yuv = true }, + { .format = DRM_FORMAT_YUV444, .depth = 0, .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 1, .vsub = 1, .is_yuv = true }, + { .format = DRM_FORMAT_YVU444, .depth = 0, .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 1, .vsub = 1, .is_yuv = true }, + { .format = DRM_FORMAT_NV12, .depth = 0, .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 2, .vsub = 2, .is_yuv = true }, + { .format = DRM_FORMAT_NV21, .depth = 0, .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 2, .vsub = 2, .is_yuv = true }, + { .format = DRM_FORMAT_NV16, .depth = 0, .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 2, .vsub = 1, .is_yuv = true }, + { .format = DRM_FORMAT_NV61, .depth = 0, .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 2, .vsub = 1, .is_yuv = true }, + { .format = DRM_FORMAT_NV24, .depth = 0, .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 1, .vsub = 1, .is_yuv = true }, + { .format = DRM_FORMAT_NV42, .depth = 0, .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 1, .vsub = 1, .is_yuv = true }, + { .format = DRM_FORMAT_YUYV, .depth = 0, .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 2, .vsub = 1, .is_yuv = true }, + { .format = DRM_FORMAT_YVYU, .depth = 0, .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 2, .vsub = 1, .is_yuv = true }, + { .format = DRM_FORMAT_UYVY, .depth = 0, .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 2, .vsub = 1, .is_yuv = true }, + { .format = DRM_FORMAT_VYUY, .depth = 0, .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 2, .vsub = 1, .is_yuv = true }, + { .format = DRM_FORMAT_AYUV, .depth = 0, .num_planes = 1, .cpp = { 4, 0, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true, .is_yuv = true }, }; unsigned int i; diff --git a/include/drm/drm_fourcc.h b/include/drm/drm_fourcc.h index 3e86408dac9f..f9c15845f465 100644 --- a/include/drm/drm_fourcc.h +++ b/include/drm/drm_fourcc.h @@ -39,6 +39,7 @@ struct drm_mode_fb_cmd2; * @hsub: Horizontal chroma subsampling factor * @vsub: Vertical chroma subsampling factor * @has_alpha: Does the format embeds an alpha component? + * @is_yuv: Is it a YUV format? */ struct drm_format_info { u32 format; @@ -48,6 +49,7 @@ struct drm_format_info { u8 hsub; u8 vsub; bool has_alpha; + bool is_yuv; }; /** -- cgit v1.2.3 From a48d189ef53146a8df132a327a637c4182f50a16 Mon Sep 17 00:00:00 2001 From: Stefano Brivio Date: Tue, 17 Jul 2018 11:52:57 +0200 Subject: net: Move skb decrypted field, avoid explicity copy Commit 784abe24c903 ("net: Add decrypted field to skb") introduced a 'decrypted' field that is explicitly copied on skb copy and clone. Move it between headers_start[0] and headers_end[0], so that we don't need to copy it explicitly as it's copied by the memcpy() in __copy_skb_header(). While at it, drop the assignment in __skb_clone(), it was already redundant. This doesn't change the size of sk_buff or cacheline boundaries. The 15-bits hole before tc_index becomes a 14-bits hole, and will be again a 15-bits hole when this change is merged with commit 8b7008620b84 ("net: Don't copy pfmemalloc flag in __copy_skb_header()"). v2: as reported by kbuild test robot (oops, I forgot to build with CONFIG_TLS_DEVICE it seems), we can't use CHECK_SKB_FIELD() on a bit-field member. Just drop the check for the moment being, perhaps we could think of some magic to also check bit-field members one day. Fixes: 784abe24c903 ("net: Add decrypted field to skb") Signed-off-by: Stefano Brivio Signed-off-by: David S. Miller --- include/linux/skbuff.h | 9 ++++----- net/core/skbuff.c | 6 ------ 2 files changed, 4 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 3ceb8dcc54da..14bc9ebe30f2 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -630,7 +630,6 @@ typedef unsigned char *sk_buff_data_t; * @hash: the packet hash * @queue_mapping: Queue mapping for multiqueue devices * @xmit_more: More SKBs are pending for this queue - * @decrypted: Decrypted SKB * @ndisc_nodetype: router type (from link layer) * @ooo_okay: allow the mapping of a socket to a queue to be changed * @l4_hash: indicate hash is a canonical 4-tuple hash over transport @@ -641,6 +640,7 @@ typedef unsigned char *sk_buff_data_t; * @no_fcs: Request NIC to treat last 4 bytes as Ethernet FCS * @csum_not_inet: use CRC32c to resolve CHECKSUM_PARTIAL * @dst_pending_confirm: need to confirm neighbour + * @decrypted: Decrypted SKB * @napi_id: id of the NAPI struct this skb came from * @secmark: security marking * @mark: Generic packet mark @@ -737,11 +737,7 @@ struct sk_buff { peeked:1, head_frag:1, xmit_more:1, -#ifdef CONFIG_TLS_DEVICE - decrypted:1; -#else __unused:1; -#endif /* fields enclosed in headers_start/headers_end are copied * using a single memcpy() in __copy_skb_header() @@ -797,6 +793,9 @@ struct sk_buff { __u8 tc_redirected:1; __u8 tc_from_ingress:1; #endif +#ifdef CONFIG_TLS_DEVICE + __u8 decrypted:1; +#endif #ifdef CONFIG_NET_SCHED __u16 tc_index; /* traffic control index */ diff --git a/net/core/skbuff.c b/net/core/skbuff.c index cfd6c6f35f9c..c4e24ac27464 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -805,9 +805,6 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) * It is not yet because we do not want to have a 16 bit hole */ new->queue_mapping = old->queue_mapping; -#ifdef CONFIG_TLS_DEVICE - new->decrypted = old->decrypted; -#endif memcpy(&new->headers_start, &old->headers_start, offsetof(struct sk_buff, headers_end) - @@ -868,9 +865,6 @@ static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb) C(head_frag); C(data); C(truesize); -#ifdef CONFIG_TLS_DEVICE - C(decrypted); -#endif refcount_set(&n->users, 1); atomic_inc(&(skb_shinfo(skb)->dataref)); -- cgit v1.2.3 From 0015b80abccecca82622d9e9d48eb210572a0c3b Mon Sep 17 00:00:00 2001 From: Salvatore Mesoraca Date: Mon, 16 Jul 2018 21:10:34 -0700 Subject: net: dsa: Remove VLA usage We avoid 2 VLAs by using a pre-allocated field in dsa_switch. We also try to avoid dynamic allocation whenever possible (when using fewer than bits-per-long ports, which is the common case). Link: http://lkml.kernel.org/r/CA+55aFzCG-zNmZwX4A2FQpadafLfEzK6CC=qPXydAacU1RqZWA@mail.gmail.com Link: http://lkml.kernel.org/r/20180505185145.GB32630@lunn.ch Signed-off-by: Salvatore Mesoraca [kees: tweak commit subject and message slightly] Signed-off-by: Kees Cook Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/net/dsa.h | 3 +++ net/dsa/dsa2.c | 14 ++++++++++++++ net/dsa/switch.c | 22 ++++++++++------------ 3 files changed, 27 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index fdbd6082945d..461e8a7661b7 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -259,6 +259,9 @@ struct dsa_switch { /* Number of switch port queues */ unsigned int num_tx_queues; + unsigned long *bitmap; + unsigned long _bitmap; + /* Dynamically allocated ports, keep last */ size_t num_ports; struct dsa_port ports[]; diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index dc5d9af3dc80..a1917025e155 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -775,6 +775,20 @@ struct dsa_switch *dsa_switch_alloc(struct device *dev, size_t n) if (!ds) return NULL; + /* We avoid allocating memory outside dsa_switch + * if it is not needed. + */ + if (n <= sizeof(ds->_bitmap) * 8) { + ds->bitmap = &ds->_bitmap; + } else { + ds->bitmap = devm_kcalloc(dev, + BITS_TO_LONGS(n), + sizeof(unsigned long), + GFP_KERNEL); + if (unlikely(!ds->bitmap)) + return NULL; + } + ds->dev = dev; ds->num_ports = n; diff --git a/net/dsa/switch.c b/net/dsa/switch.c index b93511726069..142b294d3446 100644 --- a/net/dsa/switch.c +++ b/net/dsa/switch.c @@ -136,21 +136,20 @@ static int dsa_switch_mdb_add(struct dsa_switch *ds, { const struct switchdev_obj_port_mdb *mdb = info->mdb; struct switchdev_trans *trans = info->trans; - DECLARE_BITMAP(group, ds->num_ports); int port; /* Build a mask of Multicast group members */ - bitmap_zero(group, ds->num_ports); + bitmap_zero(ds->bitmap, ds->num_ports); if (ds->index == info->sw_index) - set_bit(info->port, group); + set_bit(info->port, ds->bitmap); for (port = 0; port < ds->num_ports; port++) if (dsa_is_dsa_port(ds, port)) - set_bit(port, group); + set_bit(port, ds->bitmap); if (switchdev_trans_ph_prepare(trans)) - return dsa_switch_mdb_prepare_bitmap(ds, mdb, group); + return dsa_switch_mdb_prepare_bitmap(ds, mdb, ds->bitmap); - dsa_switch_mdb_add_bitmap(ds, mdb, group); + dsa_switch_mdb_add_bitmap(ds, mdb, ds->bitmap); return 0; } @@ -204,21 +203,20 @@ static int dsa_switch_vlan_add(struct dsa_switch *ds, { const struct switchdev_obj_port_vlan *vlan = info->vlan; struct switchdev_trans *trans = info->trans; - DECLARE_BITMAP(members, ds->num_ports); int port; /* Build a mask of VLAN members */ - bitmap_zero(members, ds->num_ports); + bitmap_zero(ds->bitmap, ds->num_ports); if (ds->index == info->sw_index) - set_bit(info->port, members); + set_bit(info->port, ds->bitmap); for (port = 0; port < ds->num_ports; port++) if (dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port)) - set_bit(port, members); + set_bit(port, ds->bitmap); if (switchdev_trans_ph_prepare(trans)) - return dsa_switch_vlan_prepare_bitmap(ds, vlan, members); + return dsa_switch_vlan_prepare_bitmap(ds, vlan, ds->bitmap); - dsa_switch_vlan_add_bitmap(ds, vlan, members); + dsa_switch_vlan_add_bitmap(ds, vlan, ds->bitmap); return 0; } -- cgit v1.2.3 From 8963106eabdc56911e9b65258eb5e9a6b7b3dfda Mon Sep 17 00:00:00 2001 From: Gustavo Pimentel Date: Thu, 19 Jul 2018 10:32:12 +0200 Subject: PCI: endpoint: Add MSI-X interfaces Add PCI_EPC_IRQ_MSIX type. Add MSI-X callbacks signatures to the ops structure. Add sysfs interface for set/get MSI-X capability maximum number. Update documentation accordingly. Signed-off-by: Gustavo Pimentel Signed-off-by: Lorenzo Pieralisi Acked-by: Kishon Vijay Abraham I --- .../PCI/endpoint/function/binding/pci-test.txt | 2 + drivers/pci/endpoint/pci-ep-cfs.c | 24 +++++++++ drivers/pci/endpoint/pci-epc-core.c | 57 ++++++++++++++++++++++ include/linux/pci-epc.h | 9 ++++ include/linux/pci-epf.h | 1 + 5 files changed, 93 insertions(+) (limited to 'include') diff --git a/Documentation/PCI/endpoint/function/binding/pci-test.txt b/Documentation/PCI/endpoint/function/binding/pci-test.txt index 3b68b955fb50..cd76ba47394b 100644 --- a/Documentation/PCI/endpoint/function/binding/pci-test.txt +++ b/Documentation/PCI/endpoint/function/binding/pci-test.txt @@ -15,3 +15,5 @@ subsys_id : don't care interrupt_pin : Should be 1 - INTA, 2 - INTB, 3 - INTC, 4 -INTD msi_interrupts : Should be 1 to 32 depending on the number of MSI interrupts to test +msix_interrupts : Should be 1 to 2048 depending on the number of MSI-X + interrupts to test diff --git a/drivers/pci/endpoint/pci-ep-cfs.c b/drivers/pci/endpoint/pci-ep-cfs.c index 018ea3433cb5..d1288a0bd530 100644 --- a/drivers/pci/endpoint/pci-ep-cfs.c +++ b/drivers/pci/endpoint/pci-ep-cfs.c @@ -286,6 +286,28 @@ static ssize_t pci_epf_msi_interrupts_show(struct config_item *item, to_pci_epf_group(item)->epf->msi_interrupts); } +static ssize_t pci_epf_msix_interrupts_store(struct config_item *item, + const char *page, size_t len) +{ + u16 val; + int ret; + + ret = kstrtou16(page, 0, &val); + if (ret) + return ret; + + to_pci_epf_group(item)->epf->msix_interrupts = val; + + return len; +} + +static ssize_t pci_epf_msix_interrupts_show(struct config_item *item, + char *page) +{ + return sprintf(page, "%d\n", + to_pci_epf_group(item)->epf->msix_interrupts); +} + PCI_EPF_HEADER_R(vendorid) PCI_EPF_HEADER_W_u16(vendorid) @@ -327,6 +349,7 @@ CONFIGFS_ATTR(pci_epf_, subsys_vendor_id); CONFIGFS_ATTR(pci_epf_, subsys_id); CONFIGFS_ATTR(pci_epf_, interrupt_pin); CONFIGFS_ATTR(pci_epf_, msi_interrupts); +CONFIGFS_ATTR(pci_epf_, msix_interrupts); static struct configfs_attribute *pci_epf_attrs[] = { &pci_epf_attr_vendorid, @@ -340,6 +363,7 @@ static struct configfs_attribute *pci_epf_attrs[] = { &pci_epf_attr_subsys_id, &pci_epf_attr_interrupt_pin, &pci_epf_attr_msi_interrupts, + &pci_epf_attr_msix_interrupts, NULL, }; diff --git a/drivers/pci/endpoint/pci-epc-core.c b/drivers/pci/endpoint/pci-epc-core.c index b0ee42739c3c..7d77bd0e5d4a 100644 --- a/drivers/pci/endpoint/pci-epc-core.c +++ b/drivers/pci/endpoint/pci-epc-core.c @@ -217,6 +217,63 @@ int pci_epc_set_msi(struct pci_epc *epc, u8 func_no, u8 interrupts) } EXPORT_SYMBOL_GPL(pci_epc_set_msi); +/** + * pci_epc_get_msix() - get the number of MSI-X interrupt numbers allocated + * @epc: the EPC device to which MSI-X interrupts was requested + * @func_no: the endpoint function number in the EPC device + * + * Invoke to get the number of MSI-X interrupts allocated by the RC + */ +int pci_epc_get_msix(struct pci_epc *epc, u8 func_no) +{ + int interrupt; + unsigned long flags; + + if (IS_ERR_OR_NULL(epc) || func_no >= epc->max_functions) + return 0; + + if (!epc->ops->get_msix) + return 0; + + spin_lock_irqsave(&epc->lock, flags); + interrupt = epc->ops->get_msix(epc, func_no); + spin_unlock_irqrestore(&epc->lock, flags); + + if (interrupt < 0) + return 0; + + return interrupt + 1; +} +EXPORT_SYMBOL_GPL(pci_epc_get_msix); + +/** + * pci_epc_set_msix() - set the number of MSI-X interrupt numbers required + * @epc: the EPC device on which MSI-X has to be configured + * @func_no: the endpoint function number in the EPC device + * @interrupts: number of MSI-X interrupts required by the EPF + * + * Invoke to set the required number of MSI-X interrupts. + */ +int pci_epc_set_msix(struct pci_epc *epc, u8 func_no, u16 interrupts) +{ + int ret; + unsigned long flags; + + if (IS_ERR_OR_NULL(epc) || func_no >= epc->max_functions || + interrupts < 1 || interrupts > 2048) + return -EINVAL; + + if (!epc->ops->set_msix) + return 0; + + spin_lock_irqsave(&epc->lock, flags); + ret = epc->ops->set_msix(epc, func_no, interrupts - 1); + spin_unlock_irqrestore(&epc->lock, flags); + + return ret; +} +EXPORT_SYMBOL_GPL(pci_epc_set_msix); + /** * pci_epc_unmap_addr() - unmap CPU address from PCI address * @epc: the EPC device on which address is allocated diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h index 243eaa5a66ff..89f079f582df 100644 --- a/include/linux/pci-epc.h +++ b/include/linux/pci-epc.h @@ -17,6 +17,7 @@ enum pci_epc_irq_type { PCI_EPC_IRQ_UNKNOWN, PCI_EPC_IRQ_LEGACY, PCI_EPC_IRQ_MSI, + PCI_EPC_IRQ_MSIX, }; /** @@ -30,6 +31,10 @@ enum pci_epc_irq_type { * capability register * @get_msi: ops to get the number of MSI interrupts allocated by the RC from * the MSI capability register + * @set_msix: ops to set the requested number of MSI-X interrupts in the + * MSI-X capability register + * @get_msix: ops to get the number of MSI-X interrupts allocated by the RC + * from the MSI-X capability register * @raise_irq: ops to raise a legacy or MSI interrupt * @start: ops to start the PCI link * @stop: ops to stop the PCI link @@ -48,6 +53,8 @@ struct pci_epc_ops { phys_addr_t addr); int (*set_msi)(struct pci_epc *epc, u8 func_no, u8 interrupts); int (*get_msi)(struct pci_epc *epc, u8 func_no); + int (*set_msix)(struct pci_epc *epc, u8 func_no, u16 interrupts); + int (*get_msix)(struct pci_epc *epc, u8 func_no); int (*raise_irq)(struct pci_epc *epc, u8 func_no, enum pci_epc_irq_type type, u8 interrupt_num); int (*start)(struct pci_epc *epc); @@ -144,6 +151,8 @@ void pci_epc_unmap_addr(struct pci_epc *epc, u8 func_no, phys_addr_t phys_addr); int pci_epc_set_msi(struct pci_epc *epc, u8 func_no, u8 interrupts); int pci_epc_get_msi(struct pci_epc *epc, u8 func_no); +int pci_epc_set_msix(struct pci_epc *epc, u8 func_no, u16 interrupts); +int pci_epc_get_msix(struct pci_epc *epc, u8 func_no); int pci_epc_raise_irq(struct pci_epc *epc, u8 func_no, enum pci_epc_irq_type type, u8 interrupt_num); int pci_epc_start(struct pci_epc *epc); diff --git a/include/linux/pci-epf.h b/include/linux/pci-epf.h index 4e7764935fa8..ec02f58758c8 100644 --- a/include/linux/pci-epf.h +++ b/include/linux/pci-epf.h @@ -119,6 +119,7 @@ struct pci_epf { struct pci_epf_header *header; struct pci_epf_bar bar[6]; u8 msi_interrupts; + u16 msix_interrupts; u8 func_no; struct pci_epc *epc; -- cgit v1.2.3 From d3c70a98d7d63cae02d50ebfafea04264a767401 Mon Sep 17 00:00:00 2001 From: Gustavo Pimentel Date: Thu, 19 Jul 2018 10:32:13 +0200 Subject: PCI: Update xxx_pcie_ep_raise_irq() and pci_epc_raise_irq() signatures Change {cdns, dra7xx, artpec6, dw, rockchip}_pcie_ep_raise_irq() and pci_epc_raise_irq() signature, namely the interrupt_num variable type from u8 to u16 to accommodate 2048 maximum MSI-X interrupts. Signed-off-by: Gustavo Pimentel Signed-off-by: Lorenzo Pieralisi Acked-by: Alan Douglas Acked-by: Shawn Lin Acked-by: Jesper Nilsson Acked-by: Joao Pinto Acked-by: Kishon Vijay Abraham I --- drivers/pci/controller/dwc/pci-dra7xx.c | 2 +- drivers/pci/controller/dwc/pcie-artpec6.c | 2 +- drivers/pci/controller/dwc/pcie-designware-ep.c | 2 +- drivers/pci/controller/dwc/pcie-designware-plat.c | 2 +- drivers/pci/controller/dwc/pcie-designware.h | 2 +- drivers/pci/controller/pcie-cadence-ep.c | 3 ++- drivers/pci/controller/pcie-rockchip-ep.c | 2 +- drivers/pci/endpoint/pci-epc-core.c | 8 ++++---- include/linux/pci-epc.h | 6 +++--- 9 files changed, 15 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/drivers/pci/controller/dwc/pci-dra7xx.c b/drivers/pci/controller/dwc/pci-dra7xx.c index 345aab56ce8b..ce9224a36f62 100644 --- a/drivers/pci/controller/dwc/pci-dra7xx.c +++ b/drivers/pci/controller/dwc/pci-dra7xx.c @@ -370,7 +370,7 @@ static void dra7xx_pcie_raise_msi_irq(struct dra7xx_pcie *dra7xx, } static int dra7xx_pcie_raise_irq(struct dw_pcie_ep *ep, u8 func_no, - enum pci_epc_irq_type type, u8 interrupt_num) + enum pci_epc_irq_type type, u16 interrupt_num) { struct dw_pcie *pci = to_dw_pcie_from_ep(ep); struct dra7xx_pcie *dra7xx = to_dra7xx_pcie(pci); diff --git a/drivers/pci/controller/dwc/pcie-artpec6.c b/drivers/pci/controller/dwc/pcie-artpec6.c index 128b182648b3..dba83abfe764 100644 --- a/drivers/pci/controller/dwc/pcie-artpec6.c +++ b/drivers/pci/controller/dwc/pcie-artpec6.c @@ -427,7 +427,7 @@ static void artpec6_pcie_ep_init(struct dw_pcie_ep *ep) } static int artpec6_pcie_raise_irq(struct dw_pcie_ep *ep, u8 func_no, - enum pci_epc_irq_type type, u8 interrupt_num) + enum pci_epc_irq_type type, u16 interrupt_num) { struct dw_pcie *pci = to_dw_pcie_from_ep(ep); diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c index 04092a7aba89..69d039de2af6 100644 --- a/drivers/pci/controller/dwc/pcie-designware-ep.c +++ b/drivers/pci/controller/dwc/pcie-designware-ep.c @@ -242,7 +242,7 @@ static int dw_pcie_ep_set_msi(struct pci_epc *epc, u8 func_no, u8 encode_int) } static int dw_pcie_ep_raise_irq(struct pci_epc *epc, u8 func_no, - enum pci_epc_irq_type type, u8 interrupt_num) + enum pci_epc_irq_type type, u16 interrupt_num) { struct dw_pcie_ep *ep = epc_get_drvdata(epc); diff --git a/drivers/pci/controller/dwc/pcie-designware-plat.c b/drivers/pci/controller/dwc/pcie-designware-plat.c index a37dc92a03c7..cca69ac63319 100644 --- a/drivers/pci/controller/dwc/pcie-designware-plat.c +++ b/drivers/pci/controller/dwc/pcie-designware-plat.c @@ -81,7 +81,7 @@ static void dw_plat_pcie_ep_init(struct dw_pcie_ep *ep) static int dw_plat_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no, enum pci_epc_irq_type type, - u8 interrupt_num) + u16 interrupt_num) { struct dw_pcie *pci = to_dw_pcie_from_ep(ep); diff --git a/drivers/pci/controller/dwc/pcie-designware.h b/drivers/pci/controller/dwc/pcie-designware.h index bee4e2535a61..9d581c077329 100644 --- a/drivers/pci/controller/dwc/pcie-designware.h +++ b/drivers/pci/controller/dwc/pcie-designware.h @@ -191,7 +191,7 @@ enum dw_pcie_as_type { struct dw_pcie_ep_ops { void (*ep_init)(struct dw_pcie_ep *ep); int (*raise_irq)(struct dw_pcie_ep *ep, u8 func_no, - enum pci_epc_irq_type type, u8 interrupt_num); + enum pci_epc_irq_type type, u16 interrupt_num); }; struct dw_pcie_ep { diff --git a/drivers/pci/controller/pcie-cadence-ep.c b/drivers/pci/controller/pcie-cadence-ep.c index e3fe4124e3af..208d11f27d5d 100644 --- a/drivers/pci/controller/pcie-cadence-ep.c +++ b/drivers/pci/controller/pcie-cadence-ep.c @@ -363,7 +363,8 @@ static int cdns_pcie_ep_send_msi_irq(struct cdns_pcie_ep *ep, u8 fn, } static int cdns_pcie_ep_raise_irq(struct pci_epc *epc, u8 fn, - enum pci_epc_irq_type type, u8 interrupt_num) + enum pci_epc_irq_type type, + u16 interrupt_num) { struct cdns_pcie_ep *ep = epc_get_drvdata(epc); diff --git a/drivers/pci/controller/pcie-rockchip-ep.c b/drivers/pci/controller/pcie-rockchip-ep.c index 6beba8ed7b84..b8163c56a142 100644 --- a/drivers/pci/controller/pcie-rockchip-ep.c +++ b/drivers/pci/controller/pcie-rockchip-ep.c @@ -472,7 +472,7 @@ static int rockchip_pcie_ep_send_msi_irq(struct rockchip_pcie_ep *ep, u8 fn, static int rockchip_pcie_ep_raise_irq(struct pci_epc *epc, u8 fn, enum pci_epc_irq_type type, - u8 interrupt_num) + u16 interrupt_num) { struct rockchip_pcie_ep *ep = epc_get_drvdata(epc); diff --git a/drivers/pci/endpoint/pci-epc-core.c b/drivers/pci/endpoint/pci-epc-core.c index 7d77bd0e5d4a..c72e656e7e29 100644 --- a/drivers/pci/endpoint/pci-epc-core.c +++ b/drivers/pci/endpoint/pci-epc-core.c @@ -131,13 +131,13 @@ EXPORT_SYMBOL_GPL(pci_epc_start); * pci_epc_raise_irq() - interrupt the host system * @epc: the EPC device which has to interrupt the host * @func_no: the endpoint function number in the EPC device - * @type: specify the type of interrupt; legacy or MSI - * @interrupt_num: the MSI interrupt number + * @type: specify the type of interrupt; legacy, MSI or MSI-X + * @interrupt_num: the MSI or MSI-X interrupt number * - * Invoke to raise an MSI or legacy interrupt + * Invoke to raise an legacy, MSI or MSI-X interrupt */ int pci_epc_raise_irq(struct pci_epc *epc, u8 func_no, - enum pci_epc_irq_type type, u8 interrupt_num) + enum pci_epc_irq_type type, u16 interrupt_num) { int ret; unsigned long flags; diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h index 89f079f582df..bb2395b56f13 100644 --- a/include/linux/pci-epc.h +++ b/include/linux/pci-epc.h @@ -35,7 +35,7 @@ enum pci_epc_irq_type { * MSI-X capability register * @get_msix: ops to get the number of MSI-X interrupts allocated by the RC * from the MSI-X capability register - * @raise_irq: ops to raise a legacy or MSI interrupt + * @raise_irq: ops to raise a legacy, MSI or MSI-X interrupt * @start: ops to start the PCI link * @stop: ops to stop the PCI link * @owner: the module owner containing the ops @@ -56,7 +56,7 @@ struct pci_epc_ops { int (*set_msix)(struct pci_epc *epc, u8 func_no, u16 interrupts); int (*get_msix)(struct pci_epc *epc, u8 func_no); int (*raise_irq)(struct pci_epc *epc, u8 func_no, - enum pci_epc_irq_type type, u8 interrupt_num); + enum pci_epc_irq_type type, u16 interrupt_num); int (*start)(struct pci_epc *epc); void (*stop)(struct pci_epc *epc); struct module *owner; @@ -154,7 +154,7 @@ int pci_epc_get_msi(struct pci_epc *epc, u8 func_no); int pci_epc_set_msix(struct pci_epc *epc, u8 func_no, u16 interrupts); int pci_epc_get_msix(struct pci_epc *epc, u8 func_no); int pci_epc_raise_irq(struct pci_epc *epc, u8 func_no, - enum pci_epc_irq_type type, u8 interrupt_num); + enum pci_epc_irq_type type, u16 interrupt_num); int pci_epc_start(struct pci_epc *epc); void pci_epc_stop(struct pci_epc *epc); struct pci_epc *pci_epc_get(const char *epc_name); -- cgit v1.2.3 From c2e00e31087e58f6c49b90b4702fc3df4fad6a83 Mon Sep 17 00:00:00 2001 From: Gustavo Pimentel Date: Thu, 19 Jul 2018 10:32:19 +0200 Subject: pci-epf-test/pci_endpoint_test: Add MSI-X support Add MSI-X support and update driver documentation accordingly. Signed-off-by: Gustavo Pimentel Signed-off-by: Lorenzo Pieralisi Acked-by: Kishon Vijay Abraham I --- Documentation/PCI/endpoint/pci-endpoint.txt | 4 ++-- Documentation/PCI/endpoint/pci-test-function.txt | 4 +++- Documentation/PCI/endpoint/pci-test-howto.txt | 22 ++++++++++++++--- Documentation/ioctl/ioctl-number.txt | 1 + Documentation/misc-devices/pci-endpoint-test.txt | 3 +++ drivers/misc/pci_endpoint_test.c | 29 ++++++++++++++++------- drivers/pci/controller/dwc/pcie-designware-plat.c | 1 + drivers/pci/endpoint/functions/pci-epf-test.c | 29 +++++++++++++++++++++-- include/linux/pci-epc.h | 1 + include/uapi/linux/pcitest.h | 1 + 10 files changed, 79 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/Documentation/PCI/endpoint/pci-endpoint.txt b/Documentation/PCI/endpoint/pci-endpoint.txt index 9b1d66829290..e86a96b66a6a 100644 --- a/Documentation/PCI/endpoint/pci-endpoint.txt +++ b/Documentation/PCI/endpoint/pci-endpoint.txt @@ -44,7 +44,7 @@ by the PCI controller driver. * clear_bar: ops to reset the BAR * alloc_addr_space: ops to allocate in PCI controller address space * free_addr_space: ops to free the allocated address space - * raise_irq: ops to raise a legacy or MSI interrupt + * raise_irq: ops to raise a legacy, MSI or MSI-X interrupt * start: ops to start the PCI link * stop: ops to stop the PCI link @@ -96,7 +96,7 @@ by the PCI endpoint function driver. *) pci_epc_raise_irq() The PCI endpoint function driver should use pci_epc_raise_irq() to raise - Legacy Interrupt or MSI Interrupt. + Legacy Interrupt, MSI or MSI-X Interrupt. *) pci_epc_mem_alloc_addr() diff --git a/Documentation/PCI/endpoint/pci-test-function.txt b/Documentation/PCI/endpoint/pci-test-function.txt index bf4b5cf6fee6..5916f1f592bb 100644 --- a/Documentation/PCI/endpoint/pci-test-function.txt +++ b/Documentation/PCI/endpoint/pci-test-function.txt @@ -36,7 +36,7 @@ that the endpoint device must perform. Bitfield Description: Bit 0 : raise legacy IRQ Bit 1 : raise MSI IRQ - Bit 2 : raise MSI-X IRQ (reserved for future implementation) + Bit 2 : raise MSI-X IRQ Bit 3 : read command (read data from RC buffer) Bit 4 : write command (write data to RC buffer) Bit 5 : copy command (copy data from one RC buffer to another @@ -75,6 +75,7 @@ for the READ/WRITE/COPY and raise IRQ (Legacy/MSI) commands. Possible types: - Legacy : 0 - MSI : 1 + - MSI-X : 2 *) PCI_ENDPOINT_TEST_IRQ_NUMBER @@ -83,3 +84,4 @@ This register contains the triggered ID interrupt. Admissible values: - Legacy : 0 - MSI : [1 .. 32] + - MSI-X : [1 .. 2048] diff --git a/Documentation/PCI/endpoint/pci-test-howto.txt b/Documentation/PCI/endpoint/pci-test-howto.txt index 75f48c3bb191..65f1a137e35c 100644 --- a/Documentation/PCI/endpoint/pci-test-howto.txt +++ b/Documentation/PCI/endpoint/pci-test-howto.txt @@ -45,9 +45,9 @@ The PCI endpoint framework populates the directory with the following configurable fields. # ls functions/pci_epf_test/func1 - baseclass_code interrupt_pin revid subsys_vendor_id - cache_line_size msi_interrupts subclass_code vendorid - deviceid progif_code subsys_id + baseclass_code interrupt_pin progif_code subsys_id + cache_line_size msi_interrupts revid subsys_vendorid + deviceid msix_interrupts subclass_code vendorid The PCI endpoint function driver populates these entries with default values when the device is bound to the driver. The pci-epf-test driver populates @@ -67,6 +67,7 @@ device, the following commands can be used. # echo 0x104c > functions/pci_epf_test/func1/vendorid # echo 0xb500 > functions/pci_epf_test/func1/deviceid # echo 16 > functions/pci_epf_test/func1/msi_interrupts + # echo 8 > functions/pci_epf_test/func1/msix_interrupts 1.5 Binding pci-epf-test Device to EP Controller @@ -153,6 +154,21 @@ following commands. MSI30: NOT OKAY MSI31: NOT OKAY MSI32: NOT OKAY + MSIX1: OKAY + MSIX2: OKAY + MSIX3: OKAY + MSIX4: OKAY + MSIX5: OKAY + MSIX6: OKAY + MSIX7: OKAY + MSIX8: OKAY + MSIX9: NOT OKAY + MSIX10: NOT OKAY + MSIX11: NOT OKAY + MSIX12: NOT OKAY + MSIX13: NOT OKAY + [...] + MSIX2048: NOT OKAY Read Tests diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt index 480c8609dc58..65259d459fd1 100644 --- a/Documentation/ioctl/ioctl-number.txt +++ b/Documentation/ioctl/ioctl-number.txt @@ -166,6 +166,7 @@ Code Seq#(hex) Include File Comments 'P' all linux/soundcard.h conflict! 'P' 60-6F sound/sscape_ioctl.h conflict! 'P' 00-0F drivers/usb/class/usblp.c conflict! +'P' 01-07 drivers/misc/pci_endpoint_test.c conflict! 'Q' all linux/soundcard.h 'R' 00-1F linux/random.h conflict! 'R' 01 linux/rfkill.h conflict! diff --git a/Documentation/misc-devices/pci-endpoint-test.txt b/Documentation/misc-devices/pci-endpoint-test.txt index 4ebc3594b32c..fdfa0f66d3d0 100644 --- a/Documentation/misc-devices/pci-endpoint-test.txt +++ b/Documentation/misc-devices/pci-endpoint-test.txt @@ -10,6 +10,7 @@ The PCI driver for the test device performs the following tests *) verifying addresses programmed in BAR *) raise legacy IRQ *) raise MSI IRQ + *) raise MSI-X IRQ *) read data *) write data *) copy data @@ -25,6 +26,8 @@ ioctl PCITEST_LEGACY_IRQ: Tests legacy IRQ PCITEST_MSI: Tests message signalled interrupts. The MSI number to be tested should be passed as argument. + PCITEST_MSIX: Tests message signalled interrupts. The MSI-X number + to be tested should be passed as argument. PCITEST_WRITE: Perform write tests. The size of the buffer should be passed as argument. PCITEST_READ: Perform read tests. The size of the buffer should be passed diff --git a/drivers/misc/pci_endpoint_test.c b/drivers/misc/pci_endpoint_test.c index 349794cbe1f3..f4fef108caff 100644 --- a/drivers/misc/pci_endpoint_test.c +++ b/drivers/misc/pci_endpoint_test.c @@ -39,13 +39,14 @@ #define IRQ_TYPE_LEGACY 0 #define IRQ_TYPE_MSI 1 +#define IRQ_TYPE_MSIX 2 #define PCI_ENDPOINT_TEST_MAGIC 0x0 #define PCI_ENDPOINT_TEST_COMMAND 0x4 #define COMMAND_RAISE_LEGACY_IRQ BIT(0) #define COMMAND_RAISE_MSI_IRQ BIT(1) -/* BIT(2) is reserved for raising MSI-X IRQ command */ +#define COMMAND_RAISE_MSIX_IRQ BIT(2) #define COMMAND_READ BIT(3) #define COMMAND_WRITE BIT(4) #define COMMAND_COPY BIT(5) @@ -84,7 +85,7 @@ MODULE_PARM_DESC(no_msi, "Disable MSI interrupt in pci_endpoint_test"); static int irq_type = IRQ_TYPE_MSI; module_param(irq_type, int, 0444); -MODULE_PARM_DESC(irq_type, "IRQ mode selection in pci_endpoint_test (0 - Legacy, 1 - MSI)"); +MODULE_PARM_DESC(irq_type, "IRQ mode selection in pci_endpoint_test (0 - Legacy, 1 - MSI, 2 - MSI-X)"); enum pci_barno { BAR_0, @@ -202,16 +203,18 @@ static bool pci_endpoint_test_legacy_irq(struct pci_endpoint_test *test) } static bool pci_endpoint_test_msi_irq(struct pci_endpoint_test *test, - u8 msi_num) + u16 msi_num, bool msix) { u32 val; struct pci_dev *pdev = test->pdev; pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_TYPE, - IRQ_TYPE_MSI); + msix == false ? IRQ_TYPE_MSI : + IRQ_TYPE_MSIX); pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_NUMBER, msi_num); pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_COMMAND, - COMMAND_RAISE_MSI_IRQ); + msix == false ? COMMAND_RAISE_MSI_IRQ : + COMMAND_RAISE_MSIX_IRQ); val = wait_for_completion_timeout(&test->irq_raised, msecs_to_jiffies(1000)); if (!val) @@ -456,7 +459,8 @@ static long pci_endpoint_test_ioctl(struct file *file, unsigned int cmd, ret = pci_endpoint_test_legacy_irq(test); break; case PCITEST_MSI: - ret = pci_endpoint_test_msi_irq(test, arg); + case PCITEST_MSIX: + ret = pci_endpoint_test_msi_irq(test, arg, cmd == PCITEST_MSIX); break; case PCITEST_WRITE: ret = pci_endpoint_test_write(test, arg); @@ -542,6 +546,12 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev, dev_err(dev, "Failed to get MSI interrupts\n"); test->num_irqs = irq; break; + case IRQ_TYPE_MSIX: + irq = pci_alloc_irq_vectors(pdev, 1, 2048, PCI_IRQ_MSIX); + if (irq < 0) + dev_err(dev, "Failed to get MSI-X interrupts\n"); + test->num_irqs = irq; + break; default: dev_err(dev, "Invalid IRQ type selected\n"); } @@ -558,8 +568,9 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev, pci_endpoint_test_irqhandler, IRQF_SHARED, DRV_MODULE_NAME, test); if (err) - dev_err(dev, "failed to request IRQ %d for MSI %d\n", - pci_irq_vector(pdev, i), i + 1); + dev_err(dev, "Failed to request IRQ %d for MSI%s %d\n", + pci_irq_vector(pdev, i), + irq_type == IRQ_TYPE_MSIX ? "-X" : "", i + 1); } for (bar = BAR_0; bar <= BAR_5; bar++) { @@ -625,6 +636,7 @@ err_iounmap: err_disable_msi: pci_disable_msi(pdev); + pci_disable_msix(pdev); pci_release_regions(pdev); err_disable_pdev: @@ -656,6 +668,7 @@ static void pci_endpoint_test_remove(struct pci_dev *pdev) for (i = 0; i < test->num_irqs; i++) devm_free_irq(&pdev->dev, pci_irq_vector(pdev, i), test); pci_disable_msi(pdev); + pci_disable_msix(pdev); pci_release_regions(pdev); pci_disable_device(pdev); } diff --git a/drivers/pci/controller/dwc/pcie-designware-plat.c b/drivers/pci/controller/dwc/pcie-designware-plat.c index 3f8a3aa3a91e..c12bf794d69c 100644 --- a/drivers/pci/controller/dwc/pcie-designware-plat.c +++ b/drivers/pci/controller/dwc/pcie-designware-plat.c @@ -77,6 +77,7 @@ static void dw_plat_pcie_ep_init(struct dw_pcie_ep *ep) dw_pcie_ep_reset_bar(pci, bar); epc->features |= EPC_FEATURE_NO_LINKUP_NOTIFIER; + epc->features |= EPC_FEATURE_MSIX_AVAILABLE; } static int dw_plat_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no, diff --git a/drivers/pci/endpoint/functions/pci-epf-test.c b/drivers/pci/endpoint/functions/pci-epf-test.c index db4b23672004..3e86fa3c7da3 100644 --- a/drivers/pci/endpoint/functions/pci-epf-test.c +++ b/drivers/pci/endpoint/functions/pci-epf-test.c @@ -20,10 +20,11 @@ #define IRQ_TYPE_LEGACY 0 #define IRQ_TYPE_MSI 1 +#define IRQ_TYPE_MSIX 2 #define COMMAND_RAISE_LEGACY_IRQ BIT(0) #define COMMAND_RAISE_MSI_IRQ BIT(1) -/* BIT(2) is reserved for raising MSI-X IRQ command */ +#define COMMAND_RAISE_MSIX_IRQ BIT(2) #define COMMAND_READ BIT(3) #define COMMAND_WRITE BIT(4) #define COMMAND_COPY BIT(5) @@ -47,6 +48,7 @@ struct pci_epf_test { struct pci_epf *epf; enum pci_barno test_reg_bar; bool linkup_notifier; + bool msix_available; struct delayed_work cmd_handler; }; @@ -266,6 +268,9 @@ static void pci_epf_test_raise_irq(struct pci_epf_test *epf_test, u8 irq_type, case IRQ_TYPE_MSI: pci_epc_raise_irq(epc, epf->func_no, PCI_EPC_IRQ_MSI, irq); break; + case IRQ_TYPE_MSIX: + pci_epc_raise_irq(epc, epf->func_no, PCI_EPC_IRQ_MSIX, irq); + break; default: dev_err(dev, "Failed to raise IRQ, unknown type\n"); break; @@ -292,7 +297,7 @@ static void pci_epf_test_cmd_handler(struct work_struct *work) reg->command = 0; reg->status = 0; - if (reg->irq_type > IRQ_TYPE_MSI) { + if (reg->irq_type > IRQ_TYPE_MSIX) { dev_err(dev, "Failed to detect IRQ type\n"); goto reset_handler; } @@ -346,6 +351,16 @@ static void pci_epf_test_cmd_handler(struct work_struct *work) goto reset_handler; } + if (command & COMMAND_RAISE_MSIX_IRQ) { + count = pci_epc_get_msix(epc, epf->func_no); + if (reg->irq_number > count || count <= 0) + goto reset_handler; + reg->status = STATUS_IRQ_RAISED; + pci_epc_raise_irq(epc, epf->func_no, PCI_EPC_IRQ_MSIX, + reg->irq_number); + goto reset_handler; + } + reset_handler: queue_delayed_work(kpcitest_workqueue, &epf_test->cmd_handler, msecs_to_jiffies(1)); @@ -459,6 +474,8 @@ static int pci_epf_test_bind(struct pci_epf *epf) else epf_test->linkup_notifier = true; + epf_test->msix_available = epc->features & EPC_FEATURE_MSIX_AVAILABLE; + epf_test->test_reg_bar = EPC_FEATURE_GET_BAR(epc->features); ret = pci_epc_write_header(epc, epf->func_no, header); @@ -481,6 +498,14 @@ static int pci_epf_test_bind(struct pci_epf *epf) return ret; } + if (epf_test->msix_available) { + ret = pci_epc_set_msix(epc, epf->func_no, epf->msix_interrupts); + if (ret) { + dev_err(dev, "MSI-X configuration failed\n"); + return ret; + } + } + if (!epf_test->linkup_notifier) queue_work(kpcitest_workqueue, &epf_test->cmd_handler.work); diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h index bb2395b56f13..37dab8116901 100644 --- a/include/linux/pci-epc.h +++ b/include/linux/pci-epc.h @@ -102,6 +102,7 @@ struct pci_epc { #define EPC_FEATURE_NO_LINKUP_NOTIFIER BIT(0) #define EPC_FEATURE_BAR_MASK (BIT(1) | BIT(2) | BIT(3)) +#define EPC_FEATURE_MSIX_AVAILABLE BIT(4) #define EPC_FEATURE_SET_BAR(features, bar) \ (features |= (EPC_FEATURE_BAR_MASK & (bar << 1))) #define EPC_FEATURE_GET_BAR(features) \ diff --git a/include/uapi/linux/pcitest.h b/include/uapi/linux/pcitest.h index 953cf036cb26..d746fb159dcd 100644 --- a/include/uapi/linux/pcitest.h +++ b/include/uapi/linux/pcitest.h @@ -16,5 +16,6 @@ #define PCITEST_WRITE _IOW('P', 0x4, unsigned long) #define PCITEST_READ _IOW('P', 0x5, unsigned long) #define PCITEST_COPY _IOW('P', 0x6, unsigned long) +#define PCITEST_MSIX _IOW('P', 0x7, int) #endif /* __UAPI_LINUX_PCITEST_H */ -- cgit v1.2.3 From e03327122e2c8e6ae4565ef5b3d3cbe4364546a1 Mon Sep 17 00:00:00 2001 From: Gustavo Pimentel Date: Thu, 19 Jul 2018 10:32:20 +0200 Subject: pci_endpoint_test: Add 2 ioctl commands Add MSI-X support and update driver documentation accordingly. Add 2 new IOCTL commands: - Allow to reconfigure driver IRQ type in runtime. - Allow to retrieve current driver IRQ type configured. Add IRQ type validation before executing the READ/WRITE/COPY tests. Signed-off-by: Gustavo Pimentel Signed-off-by: Lorenzo Pieralisi Acked-by: Kishon Vijay Abraham I --- Documentation/ioctl/ioctl-number.txt | 2 +- Documentation/misc-devices/pci-endpoint-test.txt | 3 + drivers/misc/pci_endpoint_test.c | 206 +++++++++++++++++------ include/uapi/linux/pcitest.h | 2 + 4 files changed, 165 insertions(+), 48 deletions(-) (limited to 'include') diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt index 65259d459fd1..c15c4f3bdd82 100644 --- a/Documentation/ioctl/ioctl-number.txt +++ b/Documentation/ioctl/ioctl-number.txt @@ -166,7 +166,7 @@ Code Seq#(hex) Include File Comments 'P' all linux/soundcard.h conflict! 'P' 60-6F sound/sscape_ioctl.h conflict! 'P' 00-0F drivers/usb/class/usblp.c conflict! -'P' 01-07 drivers/misc/pci_endpoint_test.c conflict! +'P' 01-09 drivers/misc/pci_endpoint_test.c conflict! 'Q' all linux/soundcard.h 'R' 00-1F linux/random.h conflict! 'R' 01 linux/rfkill.h conflict! diff --git a/Documentation/misc-devices/pci-endpoint-test.txt b/Documentation/misc-devices/pci-endpoint-test.txt index fdfa0f66d3d0..58ccca4416b1 100644 --- a/Documentation/misc-devices/pci-endpoint-test.txt +++ b/Documentation/misc-devices/pci-endpoint-test.txt @@ -28,6 +28,9 @@ ioctl to be tested should be passed as argument. PCITEST_MSIX: Tests message signalled interrupts. The MSI-X number to be tested should be passed as argument. + PCITEST_SET_IRQTYPE: Changes driver IRQ type configuration. The IRQ type + should be passed as argument (0: Legacy, 1:MSI, 2:MSI-X). + PCITEST_GET_IRQTYPE: Gets driver IRQ type configuration. PCITEST_WRITE: Perform write tests. The size of the buffer should be passed as argument. PCITEST_READ: Perform read tests. The size of the buffer should be passed diff --git a/drivers/misc/pci_endpoint_test.c b/drivers/misc/pci_endpoint_test.c index f4fef108caff..896e2df9400f 100644 --- a/drivers/misc/pci_endpoint_test.c +++ b/drivers/misc/pci_endpoint_test.c @@ -37,6 +37,7 @@ #define DRV_MODULE_NAME "pci-endpoint-test" +#define IRQ_TYPE_UNDEFINED -1 #define IRQ_TYPE_LEGACY 0 #define IRQ_TYPE_MSI 1 #define IRQ_TYPE_MSIX 2 @@ -157,6 +158,100 @@ static irqreturn_t pci_endpoint_test_irqhandler(int irq, void *dev_id) return IRQ_HANDLED; } +static void pci_endpoint_test_free_irq_vectors(struct pci_endpoint_test *test) +{ + struct pci_dev *pdev = test->pdev; + + pci_free_irq_vectors(pdev); +} + +static bool pci_endpoint_test_alloc_irq_vectors(struct pci_endpoint_test *test, + int type) +{ + int irq = -1; + struct pci_dev *pdev = test->pdev; + struct device *dev = &pdev->dev; + bool res = true; + + switch (type) { + case IRQ_TYPE_LEGACY: + irq = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_LEGACY); + if (irq < 0) + dev_err(dev, "Failed to get Legacy interrupt\n"); + break; + case IRQ_TYPE_MSI: + irq = pci_alloc_irq_vectors(pdev, 1, 32, PCI_IRQ_MSI); + if (irq < 0) + dev_err(dev, "Failed to get MSI interrupts\n"); + break; + case IRQ_TYPE_MSIX: + irq = pci_alloc_irq_vectors(pdev, 1, 2048, PCI_IRQ_MSIX); + if (irq < 0) + dev_err(dev, "Failed to get MSI-X interrupts\n"); + break; + default: + dev_err(dev, "Invalid IRQ type selected\n"); + } + + if (irq < 0) { + irq = 0; + res = false; + } + test->num_irqs = irq; + + return res; +} + +static void pci_endpoint_test_release_irq(struct pci_endpoint_test *test) +{ + int i; + struct pci_dev *pdev = test->pdev; + struct device *dev = &pdev->dev; + + for (i = 0; i < test->num_irqs; i++) + devm_free_irq(dev, pci_irq_vector(pdev, i), test); + + test->num_irqs = 0; +} + +static bool pci_endpoint_test_request_irq(struct pci_endpoint_test *test) +{ + int i; + int err; + struct pci_dev *pdev = test->pdev; + struct device *dev = &pdev->dev; + + for (i = 0; i < test->num_irqs; i++) { + err = devm_request_irq(dev, pci_irq_vector(pdev, i), + pci_endpoint_test_irqhandler, + IRQF_SHARED, DRV_MODULE_NAME, test); + if (err) + goto fail; + } + + return true; + +fail: + switch (irq_type) { + case IRQ_TYPE_LEGACY: + dev_err(dev, "Failed to request IRQ %d for Legacy\n", + pci_irq_vector(pdev, i)); + break; + case IRQ_TYPE_MSI: + dev_err(dev, "Failed to request IRQ %d for MSI %d\n", + pci_irq_vector(pdev, i), + i + 1); + break; + case IRQ_TYPE_MSIX: + dev_err(dev, "Failed to request IRQ %d for MSI-X %d\n", + pci_irq_vector(pdev, i), + i + 1); + break; + } + + return false; +} + static bool pci_endpoint_test_bar(struct pci_endpoint_test *test, enum pci_barno barno) { @@ -247,6 +342,11 @@ static bool pci_endpoint_test_copy(struct pci_endpoint_test *test, size_t size) if (size > SIZE_MAX - alignment) goto err; + if (irq_type < IRQ_TYPE_LEGACY || irq_type > IRQ_TYPE_MSIX) { + dev_err(dev, "Invalid IRQ type option\n"); + goto err; + } + orig_src_addr = dma_alloc_coherent(dev, size + alignment, &orig_src_phys_addr, GFP_KERNEL); if (!orig_src_addr) { @@ -337,6 +437,11 @@ static bool pci_endpoint_test_write(struct pci_endpoint_test *test, size_t size) if (size > SIZE_MAX - alignment) goto err; + if (irq_type < IRQ_TYPE_LEGACY || irq_type > IRQ_TYPE_MSIX) { + dev_err(dev, "Invalid IRQ type option\n"); + goto err; + } + orig_addr = dma_alloc_coherent(dev, size + alignment, &orig_phys_addr, GFP_KERNEL); if (!orig_addr) { @@ -400,6 +505,11 @@ static bool pci_endpoint_test_read(struct pci_endpoint_test *test, size_t size) if (size > SIZE_MAX - alignment) goto err; + if (irq_type < IRQ_TYPE_LEGACY || irq_type > IRQ_TYPE_MSIX) { + dev_err(dev, "Invalid IRQ type option\n"); + goto err; + } + orig_addr = dma_alloc_coherent(dev, size + alignment, &orig_phys_addr, GFP_KERNEL); if (!orig_addr) { @@ -440,6 +550,38 @@ err: return ret; } +static bool pci_endpoint_test_set_irq(struct pci_endpoint_test *test, + int req_irq_type) +{ + struct pci_dev *pdev = test->pdev; + struct device *dev = &pdev->dev; + + if (req_irq_type < IRQ_TYPE_LEGACY || req_irq_type > IRQ_TYPE_MSIX) { + dev_err(dev, "Invalid IRQ type option\n"); + return false; + } + + if (irq_type == req_irq_type) + return true; + + pci_endpoint_test_release_irq(test); + pci_endpoint_test_free_irq_vectors(test); + + if (!pci_endpoint_test_alloc_irq_vectors(test, req_irq_type)) + goto err; + + if (!pci_endpoint_test_request_irq(test)) + goto err; + + irq_type = req_irq_type; + return true; + +err: + pci_endpoint_test_free_irq_vectors(test); + irq_type = IRQ_TYPE_UNDEFINED; + return false; +} + static long pci_endpoint_test_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { @@ -471,6 +613,12 @@ static long pci_endpoint_test_ioctl(struct file *file, unsigned int cmd, case PCITEST_COPY: ret = pci_endpoint_test_copy(test, arg); break; + case PCITEST_SET_IRQTYPE: + ret = pci_endpoint_test_set_irq(test, arg); + break; + case PCITEST_GET_IRQTYPE: + ret = irq_type; + break; } ret: @@ -486,9 +634,7 @@ static const struct file_operations pci_endpoint_test_fops = { static int pci_endpoint_test_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { - int i; int err; - int irq = 0; int id; char name[20]; enum pci_barno bar; @@ -537,41 +683,11 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev, pci_set_master(pdev); - switch (irq_type) { - case IRQ_TYPE_LEGACY: - break; - case IRQ_TYPE_MSI: - irq = pci_alloc_irq_vectors(pdev, 1, 32, PCI_IRQ_MSI); - if (irq < 0) - dev_err(dev, "Failed to get MSI interrupts\n"); - test->num_irqs = irq; - break; - case IRQ_TYPE_MSIX: - irq = pci_alloc_irq_vectors(pdev, 1, 2048, PCI_IRQ_MSIX); - if (irq < 0) - dev_err(dev, "Failed to get MSI-X interrupts\n"); - test->num_irqs = irq; - break; - default: - dev_err(dev, "Invalid IRQ type selected\n"); - } + if (!pci_endpoint_test_alloc_irq_vectors(test, irq_type)) + goto err_disable_irq; - err = devm_request_irq(dev, pdev->irq, pci_endpoint_test_irqhandler, - IRQF_SHARED, DRV_MODULE_NAME, test); - if (err) { - dev_err(dev, "Failed to request IRQ %d\n", pdev->irq); - goto err_disable_msi; - } - - for (i = 1; i < irq; i++) { - err = devm_request_irq(dev, pci_irq_vector(pdev, i), - pci_endpoint_test_irqhandler, - IRQF_SHARED, DRV_MODULE_NAME, test); - if (err) - dev_err(dev, "Failed to request IRQ %d for MSI%s %d\n", - pci_irq_vector(pdev, i), - irq_type == IRQ_TYPE_MSIX ? "-X" : "", i + 1); - } + if (!pci_endpoint_test_request_irq(test)) + goto err_disable_irq; for (bar = BAR_0; bar <= BAR_5; bar++) { if (pci_resource_flags(pdev, bar) & IORESOURCE_MEM) { @@ -630,13 +746,10 @@ err_iounmap: if (test->bar[bar]) pci_iounmap(pdev, test->bar[bar]); } + pci_endpoint_test_release_irq(test); - for (i = 0; i < irq; i++) - devm_free_irq(&pdev->dev, pci_irq_vector(pdev, i), test); - -err_disable_msi: - pci_disable_msi(pdev); - pci_disable_msix(pdev); +err_disable_irq: + pci_endpoint_test_free_irq_vectors(test); pci_release_regions(pdev); err_disable_pdev: @@ -648,7 +761,6 @@ err_disable_pdev: static void pci_endpoint_test_remove(struct pci_dev *pdev) { int id; - int i; enum pci_barno bar; struct pci_endpoint_test *test = pci_get_drvdata(pdev); struct miscdevice *misc_device = &test->miscdev; @@ -665,10 +777,10 @@ static void pci_endpoint_test_remove(struct pci_dev *pdev) if (test->bar[bar]) pci_iounmap(pdev, test->bar[bar]); } - for (i = 0; i < test->num_irqs; i++) - devm_free_irq(&pdev->dev, pci_irq_vector(pdev, i), test); - pci_disable_msi(pdev); - pci_disable_msix(pdev); + + pci_endpoint_test_release_irq(test); + pci_endpoint_test_free_irq_vectors(test); + pci_release_regions(pdev); pci_disable_device(pdev); } diff --git a/include/uapi/linux/pcitest.h b/include/uapi/linux/pcitest.h index d746fb159dcd..cbf422e56696 100644 --- a/include/uapi/linux/pcitest.h +++ b/include/uapi/linux/pcitest.h @@ -17,5 +17,7 @@ #define PCITEST_READ _IOW('P', 0x5, unsigned long) #define PCITEST_COPY _IOW('P', 0x6, unsigned long) #define PCITEST_MSIX _IOW('P', 0x7, int) +#define PCITEST_SET_IRQTYPE _IOW('P', 0x8, int) +#define PCITEST_GET_IRQTYPE _IO('P', 0x9) #endif /* __UAPI_LINUX_PCITEST_H */ -- cgit v1.2.3 From 44109c60176ae73924a42a6bef64ef151aba9095 Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Tue, 15 May 2018 23:34:28 +0100 Subject: MIPS: Add DSP ASE regset support Define an NT_MIPS_DSP core file note type and implement a corresponding regset holding the DSP ASE register context, following the layout of the `mips_dsp_state' structure, except for the DSPControl register stored as a 64-bit rather than 32-bit quantity in a 64-bit note. The lack of DSP ASE register saving to core files can be considered a design flaw with commit e50c0a8fa60d ("Support the MIPS32 / MIPS64 DSP ASE."), leading to an incomplete state being saved. Consequently no DSP ASE regset has been created with commit 7aeb753b5353 ("MIPS: Implement task_user_regset_view."), when regset support was added to the MIPS port. Additionally there is no way for ptrace(2) to correctly access the DSP accumulator registers in n32 processes with the existing interfaces. This is due to 32-bit truncation of data passed with PTRACE_PEEKUSR and PTRACE_POKEUSR requests, which cannot be avoided owing to how the data types for ptrace(3) have been defined. This new NT_MIPS_DSP regset fills the missing interface gap. [paul.burton@mips.com: - Change NT_MIPS_DSP to 0x800 to avoid conflict with NT_VMCOREDD introduced by commit 2724273e8fd0 ("vmcore: add API to collect hardware dump in second kernel"). - Drop stable tag. Whilst I agree the lack of this functionality can be considered a flaw in earlier DSP ASE support, it's still new functionality which doesn't meet up to the requirements set out in Documentation/process/stable-kernel-rules.rst.] Signed-off-by: Maciej W. Rozycki Signed-off-by: Paul Burton References: 7aeb753b5353 ("MIPS: Implement task_user_regset_view.") Patchwork: https://patchwork.linux-mips.org/patch/19330/ Cc: Alexander Viro Cc: James Hogan Cc: Ralf Baechle Cc: linux-fsdevel@vger.kernel.org Cc: linux-mips@linux-mips.org Cc: linux-kernel@vger.kernel.org --- arch/mips/kernel/ptrace.c | 189 ++++++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/elf.h | 1 + 2 files changed, 190 insertions(+) (limited to 'include') diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c index 8c8d42823bda..a536271ba084 100644 --- a/arch/mips/kernel/ptrace.c +++ b/arch/mips/kernel/ptrace.c @@ -41,6 +41,7 @@ #include #include #include +#include #include #include #include @@ -589,9 +590,179 @@ static int fpr_set(struct task_struct *target, return err; } +#if defined(CONFIG_32BIT) || defined(CONFIG_MIPS32_O32) + +/* + * Copy the DSP context to the supplied 32-bit NT_MIPS_DSP buffer. + */ +static int dsp32_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + unsigned int start, num_regs, i; + u32 dspregs[NUM_DSP_REGS + 1]; + + BUG_ON(count % sizeof(u32)); + + if (!cpu_has_dsp) + return -EIO; + + start = pos / sizeof(u32); + num_regs = count / sizeof(u32); + + if (start + num_regs > NUM_DSP_REGS + 1) + return -EIO; + + for (i = start; i < num_regs; i++) + switch (i) { + case 0 ... NUM_DSP_REGS - 1: + dspregs[i] = target->thread.dsp.dspr[i]; + break; + case NUM_DSP_REGS: + dspregs[i] = target->thread.dsp.dspcontrol; + break; + } + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, dspregs, 0, + sizeof(dspregs)); +} + +/* + * Copy the supplied 32-bit NT_MIPS_DSP buffer to the DSP context. + */ +static int dsp32_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + unsigned int start, num_regs, i; + u32 dspregs[NUM_DSP_REGS + 1]; + int err; + + BUG_ON(count % sizeof(u32)); + + if (!cpu_has_dsp) + return -EIO; + + start = pos / sizeof(u32); + num_regs = count / sizeof(u32); + + if (start + num_regs > NUM_DSP_REGS + 1) + return -EIO; + + err = user_regset_copyin(&pos, &count, &kbuf, &ubuf, dspregs, 0, + sizeof(dspregs)); + if (err) + return err; + + for (i = start; i < num_regs; i++) + switch (i) { + case 0 ... NUM_DSP_REGS - 1: + target->thread.dsp.dspr[i] = (s32)dspregs[i]; + break; + case NUM_DSP_REGS: + target->thread.dsp.dspcontrol = (s32)dspregs[i]; + break; + } + + return 0; +} + +#endif /* CONFIG_32BIT || CONFIG_MIPS32_O32 */ + +#ifdef CONFIG_64BIT + +/* + * Copy the DSP context to the supplied 64-bit NT_MIPS_DSP buffer. + */ +static int dsp64_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + unsigned int start, num_regs, i; + u64 dspregs[NUM_DSP_REGS + 1]; + + BUG_ON(count % sizeof(u64)); + + if (!cpu_has_dsp) + return -EIO; + + start = pos / sizeof(u64); + num_regs = count / sizeof(u64); + + if (start + num_regs > NUM_DSP_REGS + 1) + return -EIO; + + for (i = start; i < num_regs; i++) + switch (i) { + case 0 ... NUM_DSP_REGS - 1: + dspregs[i] = target->thread.dsp.dspr[i]; + break; + case NUM_DSP_REGS: + dspregs[i] = target->thread.dsp.dspcontrol; + break; + } + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, dspregs, 0, + sizeof(dspregs)); +} + +/* + * Copy the supplied 64-bit NT_MIPS_DSP buffer to the DSP context. + */ +static int dsp64_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + unsigned int start, num_regs, i; + u64 dspregs[NUM_DSP_REGS + 1]; + int err; + + BUG_ON(count % sizeof(u64)); + + if (!cpu_has_dsp) + return -EIO; + + start = pos / sizeof(u64); + num_regs = count / sizeof(u64); + + if (start + num_regs > NUM_DSP_REGS + 1) + return -EIO; + + err = user_regset_copyin(&pos, &count, &kbuf, &ubuf, dspregs, 0, + sizeof(dspregs)); + if (err) + return err; + + for (i = start; i < num_regs; i++) + switch (i) { + case 0 ... NUM_DSP_REGS - 1: + target->thread.dsp.dspr[i] = dspregs[i]; + break; + case NUM_DSP_REGS: + target->thread.dsp.dspcontrol = dspregs[i]; + break; + } + + return 0; +} + +#endif /* CONFIG_64BIT */ + +/* + * Determine whether the DSP context is present. + */ +static int dsp_active(struct task_struct *target, + const struct user_regset *regset) +{ + return cpu_has_dsp ? NUM_DSP_REGS + 1 : -ENODEV; +} + enum mips_regset { REGSET_GPR, REGSET_FPR, + REGSET_DSP, }; struct pt_regs_offset { @@ -697,6 +868,15 @@ static const struct user_regset mips_regsets[] = { .get = fpr_get, .set = fpr_set, }, + [REGSET_DSP] = { + .core_note_type = NT_MIPS_DSP, + .n = NUM_DSP_REGS + 1, + .size = sizeof(u32), + .align = sizeof(u32), + .get = dsp32_get, + .set = dsp32_set, + .active = dsp_active, + }, }; static const struct user_regset_view user_mips_view = { @@ -728,6 +908,15 @@ static const struct user_regset mips64_regsets[] = { .get = fpr_get, .set = fpr_set, }, + [REGSET_DSP] = { + .core_note_type = NT_MIPS_DSP, + .n = NUM_DSP_REGS + 1, + .size = sizeof(u64), + .align = sizeof(u64), + .get = dsp64_get, + .set = dsp64_set, + .active = dsp_active, + }, }; static const struct user_regset_view user_mips64_view = { diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index 4e12c423b9fe..e326c99b3881 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -422,6 +422,7 @@ typedef struct elf64_shdr { #define NT_ARM_SVE 0x405 /* ARM Scalable Vector Extension registers */ #define NT_ARC_V2 0x600 /* ARCv2 accumulator/extra registers */ #define NT_VMCOREDD 0x700 /* Vmcore Device Dump Note */ +#define NT_MIPS_DSP 0x800 /* MIPS DSP ASE registers */ /* Note header in a PT_NOTE section */ typedef struct elf32_note { -- cgit v1.2.3 From 1ae22a0e35636efceab83728ba30b013df761592 Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Tue, 15 May 2018 23:40:18 +0100 Subject: MIPS: Add FP_MODE regset support Define an NT_MIPS_FP_MODE core file note and implement a corresponding regset holding the state handled by PR_SET_FP_MODE and PR_GET_FP_MODE prctl(2) requests. This lets debug software correctly interpret the contents of floating-point general registers both in live debugging and in core files, and also switch floating-point modes of a live process. [paul.burton@mips.com: - Changed NT_MIPS_FP_MODE to 0x801 to match first nibble of NT_MIPS_DSP, which was also changed to avoid a conflict.] Signed-off-by: Maciej W. Rozycki Signed-off-by: Paul Burton Patchwork: https://patchwork.linux-mips.org/patch/19331/ Cc: James Hogan Cc: Ralf Baechle Cc: linux-mips@linux-mips.org Cc: linux-kernel@vger.kernel.org --- arch/mips/kernel/ptrace.c | 63 +++++++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/elf.h | 1 + 2 files changed, 64 insertions(+) (limited to 'include') diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c index a536271ba084..e5ba56c01ee0 100644 --- a/arch/mips/kernel/ptrace.c +++ b/arch/mips/kernel/ptrace.c @@ -759,10 +759,57 @@ static int dsp_active(struct task_struct *target, return cpu_has_dsp ? NUM_DSP_REGS + 1 : -ENODEV; } +/* Copy the FP mode setting to the supplied NT_MIPS_FP_MODE buffer. */ +static int fp_mode_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + int fp_mode; + + fp_mode = mips_get_process_fp_mode(target); + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &fp_mode, 0, + sizeof(fp_mode)); +} + +/* + * Copy the supplied NT_MIPS_FP_MODE buffer to the FP mode setting. + * + * We optimize for the case where `count % sizeof(int) == 0', which + * is supposed to have been guaranteed by the kernel before calling + * us, e.g. in `ptrace_regset'. We enforce that requirement, so + * that we can safely avoid preinitializing temporaries for partial + * mode writes. + */ +static int fp_mode_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int fp_mode; + int err; + + BUG_ON(count % sizeof(int)); + + if (pos + count > sizeof(fp_mode)) + return -EIO; + + err = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &fp_mode, 0, + sizeof(fp_mode)); + if (err) + return err; + + if (count > 0) + err = mips_set_process_fp_mode(target, fp_mode); + + return err; +} + enum mips_regset { REGSET_GPR, REGSET_FPR, REGSET_DSP, + REGSET_FP_MODE, }; struct pt_regs_offset { @@ -877,6 +924,14 @@ static const struct user_regset mips_regsets[] = { .set = dsp32_set, .active = dsp_active, }, + [REGSET_FP_MODE] = { + .core_note_type = NT_MIPS_FP_MODE, + .n = 1, + .size = sizeof(int), + .align = sizeof(int), + .get = fp_mode_get, + .set = fp_mode_set, + }, }; static const struct user_regset_view user_mips_view = { @@ -917,6 +972,14 @@ static const struct user_regset mips64_regsets[] = { .set = dsp64_set, .active = dsp_active, }, + [REGSET_FP_MODE] = { + .core_note_type = NT_MIPS_FP_MODE, + .n = 1, + .size = sizeof(int), + .align = sizeof(int), + .get = fp_mode_get, + .set = fp_mode_set, + }, }; static const struct user_regset_view user_mips64_view = { diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index e326c99b3881..c5358e0ae7c5 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -423,6 +423,7 @@ typedef struct elf64_shdr { #define NT_ARC_V2 0x600 /* ARCv2 accumulator/extra registers */ #define NT_VMCOREDD 0x700 /* Vmcore Device Dump Note */ #define NT_MIPS_DSP 0x800 /* MIPS DSP ASE registers */ +#define NT_MIPS_FP_MODE 0x801 /* MIPS floating-point mode */ /* Note header in a PT_NOTE section */ typedef struct elf32_note { -- cgit v1.2.3 From d70420bcd447e5400a0116b20b9b6088bb32448e Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 18 Jul 2018 22:33:02 +0200 Subject: mtd: adapt misleading comment in mtd_oob_ops structure A comment in the kernel doc of the mtd_oob_ops structure tells that it is not possible to write more than one page with OOB. This is actually true for only a few MTD devices like 'onenand' but it is definitely not a general limitation. While this would benefit to be handled elsewhere either by the MTD layer or by the limited drivers, let's update this comment to reflect the reality. Signed-off-by: Miquel Raynal Signed-off-by: Boris Brezillon --- include/linux/mtd/mtd.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index a86c4fa93115..cd0be91bdefa 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -67,9 +67,11 @@ struct mtd_erase_region_info { * @datbuf: data buffer - if NULL only oob data are read/written * @oobbuf: oob data buffer * - * Note, it is allowed to read more than one OOB area at one go, but not write. - * The interface assumes that the OOB write requests program only one page's - * OOB area. + * Note, some MTD drivers do not allow you to write more than one OOB area at + * one go. If you try to do that on such an MTD device, -EINVAL will be + * returned. If you want to make your implementation portable on all kind of MTD + * devices you should split the write request into several sub-requests when the + * request crosses a page boundary. */ struct mtd_oob_ops { unsigned int mode; -- cgit v1.2.3 From 0d6030ac041f6835974deb88a1a9c299b4adc3ad Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Wed, 18 Jul 2018 10:42:17 +0200 Subject: mtd: rawnand: Expose _notsupp() helpers for raw page accessors Some implementations simply can't disable their ECC engine. Expose helpers returning -ENOTSUPP so that the caller knows that raw accesses are not supported instead of silently falling back to non-raw accessors. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/nand_base.c | 33 +++++++++++++++++++++++++++++++++ include/linux/mtd/rawnand.h | 4 ++++ 2 files changed, 37 insertions(+) (limited to 'include') diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index 4fa5e20d9690..c4b74630f4c5 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -2966,6 +2966,23 @@ int nand_check_erased_ecc_chunk(void *data, int datalen, } EXPORT_SYMBOL(nand_check_erased_ecc_chunk); +/** + * nand_read_page_raw_notsupp - dummy read raw page function + * @mtd: mtd info structure + * @chip: nand chip info structure + * @buf: buffer to store read data + * @oob_required: caller requires OOB data read to chip->oob_poi + * @page: page number to read + * + * Returns -ENOTSUPP unconditionally. + */ +int nand_read_page_raw_notsupp(struct mtd_info *mtd, struct nand_chip *chip, + u8 *buf, int oob_required, int page) +{ + return -ENOTSUPP; +} +EXPORT_SYMBOL(nand_read_page_raw_notsupp); + /** * nand_read_page_raw - [INTERN] read raw page data without ecc * @mtd: mtd info structure @@ -3960,6 +3977,22 @@ static int nand_read_oob(struct mtd_info *mtd, loff_t from, return ret; } +/** + * nand_write_page_raw_notsupp - dummy raw page write function + * @mtd: mtd info structure + * @chip: nand chip info structure + * @buf: data buffer + * @oob_required: must write chip->oob_poi to OOB + * @page: page number to write + * + * Returns -ENOTSUPP unconditionally. + */ +int nand_write_page_raw_notsupp(struct mtd_info *mtd, struct nand_chip *chip, + const u8 *buf, int oob_required, int page) +{ + return -ENOTSUPP; +} +EXPORT_SYMBOL(nand_write_page_raw_notsupp); /** * nand_write_page_raw - [INTERN] raw page write function diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 11c2426fc363..f60fad29eae6 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1681,10 +1681,14 @@ int nand_get_set_features_notsupp(struct mtd_info *mtd, struct nand_chip *chip, /* Default read_page_raw implementation */ int nand_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip, uint8_t *buf, int oob_required, int page); +int nand_read_page_raw_notsupp(struct mtd_info *mtd, struct nand_chip *chip, + u8 *buf, int oob_required, int page); /* Default write_page_raw implementation */ int nand_write_page_raw(struct mtd_info *mtd, struct nand_chip *chip, const uint8_t *buf, int oob_required, int page); +int nand_write_page_raw_notsupp(struct mtd_info *mtd, struct nand_chip *chip, + const u8 *buf, int oob_required, int page); /* Reset and initialize a NAND device */ int nand_reset(struct nand_chip *chip, int chipnr); -- cgit v1.2.3 From 60ed982a4e78ff938824a750dbac8a10e5b472ef Mon Sep 17 00:00:00 2001 From: Rajat Jain Date: Thu, 21 Jun 2018 16:48:26 -0700 Subject: PCI/AER: Move internal declarations to drivers/pci/pci.h Since pci_aer_init() and pci_no_aer() are used only internally, move their declarations to the PCI internal header file. Also, no one cares about return value of pci_aer_init(), so make it void. Signed-off-by: Rajat Jain Signed-off-by: Bjorn Helgaas --- drivers/pci/pci.h | 8 ++++++++ drivers/pci/pcie/aer.c | 4 ++-- include/linux/pci.h | 4 ---- 3 files changed, 10 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 4f723442f602..52bc5b350dfb 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -480,4 +480,12 @@ static inline int devm_of_pci_get_host_bridge_resources(struct device *dev, } #endif +#ifdef CONFIG_PCIEAER +void pci_no_aer(void); +void pci_aer_init(struct pci_dev *dev); +#else +static inline void pci_no_aer(void) { } +static inline int pci_aer_init(struct pci_dev *d) { return -ENODEV; } +#endif + #endif /* DRIVERS_PCI_H */ diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c index e6d5255d718c..0c6fe22eaf75 100644 --- a/drivers/pci/pcie/aer.c +++ b/drivers/pci/pcie/aer.c @@ -382,10 +382,10 @@ int pci_cleanup_aer_error_status_regs(struct pci_dev *dev) return 0; } -int pci_aer_init(struct pci_dev *dev) +void pci_aer_init(struct pci_dev *dev) { dev->aer_cap = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR); - return pci_cleanup_aer_error_status_regs(dev); + pci_cleanup_aer_error_status_regs(dev); } #define AER_AGENT_RECEIVER 0 diff --git a/include/linux/pci.h b/include/linux/pci.h index 340029b2fb38..b4ffea05c999 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1468,13 +1468,9 @@ static inline bool pcie_aspm_support_enabled(void) { return false; } #endif #ifdef CONFIG_PCIEAER -void pci_no_aer(void); bool pci_aer_available(void); -int pci_aer_init(struct pci_dev *dev); #else -static inline void pci_no_aer(void) { } static inline bool pci_aer_available(void) { return false; } -static inline int pci_aer_init(struct pci_dev *d) { return -ENODEV; } #endif #ifdef CONFIG_PCIE_ECRC -- cgit v1.2.3 From db89ccbe52c7885644ba578c7771e57620f879b1 Mon Sep 17 00:00:00 2001 From: Rajat Jain Date: Sat, 30 Jun 2018 15:07:17 -0500 Subject: PCI/AER: Define aer_stats structure for AER capable devices Define a structure to hold the AER statistics. There are 2 groups of statistics: dev_* counters that are to be collected for all AER capable devices and rootport_* counters that are collected for all (AER capable) rootports only. Allocate and free this structure when device is added or released (thus counters survive the lifetime of the device). Signed-off-by: Rajat Jain Signed-off-by: Bjorn Helgaas --- drivers/pci/pci.h | 2 ++ drivers/pci/pcie/aer.c | 53 ++++++++++++++++++++++++++++++++++++++++++++++++-- drivers/pci/probe.c | 1 + include/linux/pci.h | 1 + 4 files changed, 55 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 52bc5b350dfb..1877a14e06a9 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -483,9 +483,11 @@ static inline int devm_of_pci_get_host_bridge_resources(struct device *dev, #ifdef CONFIG_PCIEAER void pci_no_aer(void); void pci_aer_init(struct pci_dev *dev); +void pci_aer_exit(struct pci_dev *dev); #else static inline void pci_no_aer(void) { } static inline int pci_aer_init(struct pci_dev *d) { return -ENODEV; } +static inline void pci_aer_exit(struct pci_dev *d) { } #endif #endif /* DRIVERS_PCI_H */ diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c index 0c6fe22eaf75..fe1b9d22a331 100644 --- a/drivers/pci/pcie/aer.c +++ b/drivers/pci/pcie/aer.c @@ -32,6 +32,9 @@ #define AER_ERROR_SOURCES_MAX 100 +#define AER_MAX_TYPEOF_COR_ERRS 16 /* as per PCI_ERR_COR_STATUS */ +#define AER_MAX_TYPEOF_UNCOR_ERRS 26 /* as per PCI_ERR_UNCOR_STATUS*/ + struct aer_err_source { unsigned int status; unsigned int id; @@ -56,6 +59,42 @@ struct aer_rpc { */ }; +/* AER stats for the device */ +struct aer_stats { + + /* + * Fields for all AER capable devices. They indicate the errors + * "as seen by this device". Note that this may mean that if an + * end point is causing problems, the AER counters may increment + * at its link partner (e.g. root port) because the errors will be + * "seen" by the link partner and not the the problematic end point + * itself (which may report all counters as 0 as it never saw any + * problems). + */ + /* Counters for different type of correctable errors */ + u64 dev_cor_errs[AER_MAX_TYPEOF_COR_ERRS]; + /* Counters for different type of fatal uncorrectable errors */ + u64 dev_fatal_errs[AER_MAX_TYPEOF_UNCOR_ERRS]; + /* Counters for different type of nonfatal uncorrectable errors */ + u64 dev_nonfatal_errs[AER_MAX_TYPEOF_UNCOR_ERRS]; + /* Total number of ERR_COR sent by this device */ + u64 dev_total_cor_errs; + /* Total number of ERR_FATAL sent by this device */ + u64 dev_total_fatal_errs; + /* Total number of ERR_NONFATAL sent by this device */ + u64 dev_total_nonfatal_errs; + + /* + * Fields for Root ports & root complex event collectors only, these + * indicate the total number of ERR_COR, ERR_FATAL, and ERR_NONFATAL + * messages received by the root port / event collector, INCLUDING the + * ones that are generated internally (by the rootport itself) + */ + u64 rootport_total_cor_errs; + u64 rootport_total_fatal_errs; + u64 rootport_total_nonfatal_errs; +}; + #define AER_LOG_TLP_MASKS (PCI_ERR_UNC_POISON_TLP| \ PCI_ERR_UNC_ECRC| \ PCI_ERR_UNC_UNSUP| \ @@ -385,9 +424,19 @@ int pci_cleanup_aer_error_status_regs(struct pci_dev *dev) void pci_aer_init(struct pci_dev *dev) { dev->aer_cap = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR); + + if (dev->aer_cap) + dev->aer_stats = kzalloc(sizeof(struct aer_stats), GFP_KERNEL); + pci_cleanup_aer_error_status_regs(dev); } +void pci_aer_exit(struct pci_dev *dev) +{ + kfree(dev->aer_stats); + dev->aer_stats = NULL; +} + #define AER_AGENT_RECEIVER 0 #define AER_AGENT_REQUESTER 1 #define AER_AGENT_COMPLETER 2 @@ -438,7 +487,7 @@ static const char *aer_error_layer[] = { "Transaction Layer" }; -static const char *aer_correctable_error_string[] = { +static const char *aer_correctable_error_string[AER_MAX_TYPEOF_COR_ERRS] = { "RxErr", /* Bit Position 0 */ NULL, NULL, @@ -457,7 +506,7 @@ static const char *aer_correctable_error_string[] = { "HeaderOF", /* Bit Position 15 */ }; -static const char *aer_uncorrectable_error_string[] = { +static const char *aer_uncorrectable_error_string[AER_MAX_TYPEOF_UNCOR_ERRS] = { "Undefined", /* Bit Position 0 */ NULL, NULL, diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index ac876e32de4b..48edd0c9e4bc 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2064,6 +2064,7 @@ static void pci_configure_device(struct pci_dev *dev) static void pci_release_capabilities(struct pci_dev *dev) { + pci_aer_exit(dev); pci_vpd_release(dev); pci_iov_release(dev); pci_free_cap_save_buffers(dev); diff --git a/include/linux/pci.h b/include/linux/pci.h index b4ffea05c999..6bc0aa0fc33f 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -299,6 +299,7 @@ struct pci_dev { u8 hdr_type; /* PCI header type (`multi' flag masked out) */ #ifdef CONFIG_PCIEAER u16 aer_cap; /* AER capability offset */ + struct aer_stats *aer_stats; /* AER stats for this device */ #endif u8 pcie_cap; /* PCIe capability offset */ u8 msi_cap; /* MSI capability offset */ -- cgit v1.2.3 From 3eca993740b8eb40f514b90b1877a4dbcf0a6710 Mon Sep 17 00:00:00 2001 From: Pavel Tatashin Date: Thu, 19 Jul 2018 16:55:34 -0400 Subject: timekeeping: Replace read_boot_clock64() with read_persistent_wall_and_boot_offset() If architecture does not support exact boot time, it is challenging to estimate boot time without having a reference to the current persistent clock value. Yet, it cannot read the persistent clock time again, because this may lead to math discrepancies with the caller of read_boot_clock64() who have read the persistent clock at a different time. This is why it is better to provide two values simultaneously: the persistent clock value, and the boot time. Replace read_boot_clock64() with: read_persistent_wall_and_boot_offset(wall_time, boot_offset) Where wall_time is returned by read_persistent_clock() And boot_offset is wall_time - boot time, which defaults to 0. Signed-off-by: Pavel Tatashin Signed-off-by: Thomas Gleixner Cc: steven.sistare@oracle.com Cc: daniel.m.jordan@oracle.com Cc: linux@armlinux.org.uk Cc: schwidefsky@de.ibm.com Cc: heiko.carstens@de.ibm.com Cc: john.stultz@linaro.org Cc: sboyd@codeaurora.org Cc: hpa@zytor.com Cc: douly.fnst@cn.fujitsu.com Cc: peterz@infradead.org Cc: prarit@redhat.com Cc: feng.tang@intel.com Cc: pmladek@suse.com Cc: gnomes@lxorguk.ukuu.org.uk Cc: linux-s390@vger.kernel.org Cc: boris.ostrovsky@oracle.com Cc: jgross@suse.com Cc: pbonzini@redhat.com Link: https://lkml.kernel.org/r/20180719205545.16512-16-pasha.tatashin@oracle.com --- include/linux/timekeeping.h | 3 ++- kernel/time/timekeeping.c | 59 +++++++++++++++++++++++---------------------- 2 files changed, 32 insertions(+), 30 deletions(-) (limited to 'include') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 86bc2026efce..686bc27acef0 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -243,7 +243,8 @@ extern void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot); extern int persistent_clock_is_local; extern void read_persistent_clock64(struct timespec64 *ts); -extern void read_boot_clock64(struct timespec64 *ts); +void read_persistent_clock_and_boot_offset(struct timespec64 *wall_clock, + struct timespec64 *boot_offset); extern int update_persistent_clock64(struct timespec64 now); /* diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 4786df904c22..cb738f825c12 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include @@ -1496,18 +1497,20 @@ void __weak read_persistent_clock64(struct timespec64 *ts64) } /** - * read_boot_clock64 - Return time of the system start. + * read_persistent_wall_and_boot_offset - Read persistent clock, and also offset + * from the boot. * * Weak dummy function for arches that do not yet support it. - * Function to read the exact time the system has been started. - * Returns a timespec64 with tv_sec=0 and tv_nsec=0 if unsupported. - * - * XXX - Do be sure to remove it once all arches implement it. + * wall_time - current time as returned by persistent clock + * boot_offset - offset that is defined as wall_time - boot_time + * default to 0. */ -void __weak read_boot_clock64(struct timespec64 *ts) +void __weak __init +read_persistent_wall_and_boot_offset(struct timespec64 *wall_time, + struct timespec64 *boot_offset) { - ts->tv_sec = 0; - ts->tv_nsec = 0; + read_persistent_clock64(wall_time); + *boot_offset = (struct timespec64){0}; } /* Flag for if timekeeping_resume() has injected sleeptime */ @@ -1521,28 +1524,29 @@ static bool persistent_clock_exists; */ void __init timekeeping_init(void) { + struct timespec64 wall_time, boot_offset, wall_to_mono; struct timekeeper *tk = &tk_core.timekeeper; struct clocksource *clock; unsigned long flags; - struct timespec64 now, boot, tmp; - - read_persistent_clock64(&now); - if (!timespec64_valid_strict(&now)) { - pr_warn("WARNING: Persistent clock returned invalid value!\n" - " Check your CMOS/BIOS settings.\n"); - now.tv_sec = 0; - now.tv_nsec = 0; - } else if (now.tv_sec || now.tv_nsec) - persistent_clock_exists = true; - read_boot_clock64(&boot); - if (!timespec64_valid_strict(&boot)) { - pr_warn("WARNING: Boot clock returned invalid value!\n" - " Check your CMOS/BIOS settings.\n"); - boot.tv_sec = 0; - boot.tv_nsec = 0; + read_persistent_wall_and_boot_offset(&wall_time, &boot_offset); + if (timespec64_valid_strict(&wall_time) && + timespec64_to_ns(&wall_time) > 0) { + persistent_clock_exists = true; + } else { + pr_warn("Persistent clock returned invalid value"); + wall_time = (struct timespec64){0}; } + if (timespec64_compare(&wall_time, &boot_offset) < 0) + boot_offset = (struct timespec64){0}; + + /* + * We want set wall_to_mono, so the following is true: + * wall time + wall_to_mono = boot time + */ + wall_to_mono = timespec64_sub(boot_offset, wall_time); + raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); ntp_init(); @@ -1552,13 +1556,10 @@ void __init timekeeping_init(void) clock->enable(clock); tk_setup_internals(tk, clock); - tk_set_xtime(tk, &now); + tk_set_xtime(tk, &wall_time); tk->raw_sec = 0; - if (boot.tv_sec == 0 && boot.tv_nsec == 0) - boot = tk_xtime(tk); - set_normalized_timespec64(&tmp, -boot.tv_sec, -boot.tv_nsec); - tk_set_wall_to_mono(tk, tmp); + tk_set_wall_to_mono(tk, wall_to_mono); timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); -- cgit v1.2.3 From 5d2a4e91a541cb04d20d11602f0f9340291322ac Mon Sep 17 00:00:00 2001 From: Pavel Tatashin Date: Thu, 19 Jul 2018 16:55:41 -0400 Subject: sched/clock: Move sched clock initialization and merge with generic clock sched_clock_postinit() initializes a generic clock on systems where no other clock is provided. This function may be called only after timekeeping_init(). Rename sched_clock_postinit to generic_clock_inti() and call it from sched_clock_init(). Move the call for sched_clock_init() until after time_init(). Suggested-by: Peter Zijlstra Signed-off-by: Pavel Tatashin Signed-off-by: Thomas Gleixner Cc: steven.sistare@oracle.com Cc: daniel.m.jordan@oracle.com Cc: linux@armlinux.org.uk Cc: schwidefsky@de.ibm.com Cc: heiko.carstens@de.ibm.com Cc: john.stultz@linaro.org Cc: sboyd@codeaurora.org Cc: hpa@zytor.com Cc: douly.fnst@cn.fujitsu.com Cc: prarit@redhat.com Cc: feng.tang@intel.com Cc: pmladek@suse.com Cc: gnomes@lxorguk.ukuu.org.uk Cc: linux-s390@vger.kernel.org Cc: boris.ostrovsky@oracle.com Cc: jgross@suse.com Cc: pbonzini@redhat.com Link: https://lkml.kernel.org/r/20180719205545.16512-23-pasha.tatashin@oracle.com --- include/linux/sched_clock.h | 5 ++--- init/main.c | 4 ++-- kernel/sched/clock.c | 27 +++++++++++++++++---------- kernel/sched/core.c | 1 - kernel/time/sched_clock.c | 2 +- 5 files changed, 22 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/include/linux/sched_clock.h b/include/linux/sched_clock.h index 411b52e424e1..abe28d5cb3f4 100644 --- a/include/linux/sched_clock.h +++ b/include/linux/sched_clock.h @@ -9,17 +9,16 @@ #define LINUX_SCHED_CLOCK #ifdef CONFIG_GENERIC_SCHED_CLOCK -extern void sched_clock_postinit(void); +extern void generic_sched_clock_init(void); extern void sched_clock_register(u64 (*read)(void), int bits, unsigned long rate); #else -static inline void sched_clock_postinit(void) { } +static inline void generic_sched_clock_init(void) { } static inline void sched_clock_register(u64 (*read)(void), int bits, unsigned long rate) { - ; } #endif diff --git a/init/main.c b/init/main.c index 3b4ada11ed52..162d931c9511 100644 --- a/init/main.c +++ b/init/main.c @@ -79,7 +79,7 @@ #include #include #include -#include +#include #include #include #include @@ -642,7 +642,7 @@ asmlinkage __visible void __init start_kernel(void) softirq_init(); timekeeping_init(); time_init(); - sched_clock_postinit(); + sched_clock_init(); printk_safe_init(); perf_event_init(); profile_init(); diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c index 10c83e73837a..0e9dbb2d9aea 100644 --- a/kernel/sched/clock.c +++ b/kernel/sched/clock.c @@ -53,6 +53,7 @@ * */ #include "sched.h" +#include /* * Scheduler clock - returns current time in nanosec units. @@ -68,11 +69,6 @@ EXPORT_SYMBOL_GPL(sched_clock); __read_mostly int sched_clock_running; -void sched_clock_init(void) -{ - sched_clock_running = 1; -} - #ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK /* * We must start with !__sched_clock_stable because the unstable -> stable @@ -199,6 +195,15 @@ void clear_sched_clock_stable(void) __clear_sched_clock_stable(); } +static void __sched_clock_gtod_offset(void) +{ + __gtod_offset = (sched_clock() + __sched_clock_offset) - ktime_get_ns(); +} + +void __init sched_clock_init(void) +{ + sched_clock_running = 1; +} /* * We run this as late_initcall() such that it runs after all built-in drivers, * notably: acpi_processor and intel_idle, which can mark the TSC as unstable. @@ -385,8 +390,6 @@ void sched_clock_tick(void) void sched_clock_tick_stable(void) { - u64 gtod, clock; - if (!sched_clock_stable()) return; @@ -398,9 +401,7 @@ void sched_clock_tick_stable(void) * TSC to be unstable, any computation will be computing crap. */ local_irq_disable(); - gtod = ktime_get_ns(); - clock = sched_clock(); - __gtod_offset = (clock + __sched_clock_offset) - gtod; + __sched_clock_gtod_offset(); local_irq_enable(); } @@ -434,6 +435,12 @@ EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event); #else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */ +void __init sched_clock_init(void) +{ + sched_clock_running = 1; + generic_sched_clock_init(); +} + u64 sched_clock_cpu(int cpu) { if (unlikely(!sched_clock_running)) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index fe365c9a08e9..552406e9713b 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5954,7 +5954,6 @@ void __init sched_init(void) int i, j; unsigned long alloc_size = 0, ptr; - sched_clock_init(); wait_bit_init(); #ifdef CONFIG_FAIR_GROUP_SCHED diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c index 2d8f05aad442..cbc72c2c1fca 100644 --- a/kernel/time/sched_clock.c +++ b/kernel/time/sched_clock.c @@ -237,7 +237,7 @@ sched_clock_register(u64 (*read)(void), int bits, unsigned long rate) pr_debug("Registered %pF as sched_clock source\n", read); } -void __init sched_clock_postinit(void) +void __init generic_sched_clock_init(void) { /* * If no sched_clock() function has been provided at that point, -- cgit v1.2.3 From 381634cad15b711e033a2638d558232b60f753f6 Mon Sep 17 00:00:00 2001 From: Sinan Kaya Date: Thu, 19 Jul 2018 18:04:11 -0500 Subject: PCI: Hide pci_reset_bridge_secondary_bus() from drivers Rename pci_reset_bridge_secondary_bus() to pci_bridge_secondary_bus_reset() and move the declaration from linux/pci.h to drivers/pci.h to be used internally in PCI directory only. Signed-off-by: Sinan Kaya Signed-off-by: Bjorn Helgaas --- drivers/pci/hotplug/pciehp_hpc.c | 2 +- drivers/pci/pci.c | 11 +++++------ drivers/pci/pci.h | 1 + drivers/pci/pcie/aer.c | 2 +- drivers/pci/pcie/err.c | 2 +- include/linux/pci.h | 1 - 6 files changed, 9 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c index bbaa2114f953..8dae23221344 100644 --- a/drivers/pci/hotplug/pciehp_hpc.c +++ b/drivers/pci/hotplug/pciehp_hpc.c @@ -746,7 +746,7 @@ int pciehp_reset_slot(struct slot *slot, int probe) if (pciehp_poll_mode) del_timer_sync(&ctrl->poll_timer); - rc = pci_reset_bridge_secondary_bus(ctrl->pcie->port); + rc = pci_bridge_secondary_bus_reset(ctrl->pcie->port); pcie_capability_write_word(pdev, PCI_EXP_SLTSTA, stat_mask); pcie_write_cmd_nowait(ctrl, ctrl_mask, ctrl_mask); diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 98d149070205..236220cb0f77 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -4224,19 +4224,18 @@ void __weak pcibios_reset_secondary_bus(struct pci_dev *dev) } /** - * pci_reset_bridge_secondary_bus - Reset the secondary bus on a PCI bridge. + * pci_bridge_secondary_bus_reset - Reset the secondary bus on a PCI bridge. * @dev: Bridge device * * Use the bridge control register to assert reset on the secondary bus. * Devices on the secondary bus are left in power-on state. */ -int pci_reset_bridge_secondary_bus(struct pci_dev *dev) +int pci_bridge_secondary_bus_reset(struct pci_dev *dev) { pcibios_reset_secondary_bus(dev); return pci_dev_wait(dev, "bus reset", PCIE_RESET_READY_POLL_MS); } -EXPORT_SYMBOL_GPL(pci_reset_bridge_secondary_bus); static int pci_parent_bus_reset(struct pci_dev *dev, int probe) { @@ -4253,7 +4252,7 @@ static int pci_parent_bus_reset(struct pci_dev *dev, int probe) if (probe) return 0; - return pci_reset_bridge_secondary_bus(dev->bus->self); + return pci_bridge_secondary_bus_reset(dev->bus->self); } static int pci_reset_hotplug_slot(struct hotplug_slot *hotplug, int probe) @@ -4860,7 +4859,7 @@ static int pci_bus_reset(struct pci_bus *bus, int probe) might_sleep(); - ret = pci_reset_bridge_secondary_bus(bus->self); + ret = pci_bridge_secondary_bus_reset(bus->self); pci_bus_unlock(bus); @@ -4924,7 +4923,7 @@ int pci_try_reset_bus(struct pci_bus *bus) if (pci_bus_trylock(bus)) { might_sleep(); - rc = pci_reset_bridge_secondary_bus(bus->self); + rc = pci_bridge_secondary_bus_reset(bus->self); pci_bus_unlock(bus); } else rc = -EAGAIN; diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index c358e7a07f3f..f784263ad587 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -33,6 +33,7 @@ int pci_mmap_fits(struct pci_dev *pdev, int resno, struct vm_area_struct *vmai, enum pci_mmap_api mmap_api); int pci_probe_reset_function(struct pci_dev *dev); +int pci_bridge_secondary_bus_reset(struct pci_dev *dev); /** * struct pci_platform_pm_ops - Firmware PM callbacks diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c index bde723db3d65..8c12efca9259 100644 --- a/drivers/pci/pcie/aer.c +++ b/drivers/pci/pcie/aer.c @@ -1314,7 +1314,7 @@ static pci_ers_result_t aer_root_reset(struct pci_dev *dev) reg32 &= ~ROOT_PORT_INTR_ON_MESG_MASK; pci_write_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, reg32); - rc = pci_reset_bridge_secondary_bus(dev); + rc = pci_bridge_secondary_bus_reset(dev); pci_printk(KERN_DEBUG, dev, "Root Port link has been reset\n"); /* Clear Root Error Status */ diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c index 03075cff86f4..ae72f88d3ca2 100644 --- a/drivers/pci/pcie/err.c +++ b/drivers/pci/pcie/err.c @@ -177,7 +177,7 @@ static pci_ers_result_t default_reset_link(struct pci_dev *dev) { int rc; - rc = pci_reset_bridge_secondary_bus(dev); + rc = pci_bridge_secondary_bus_reset(dev); pci_printk(KERN_DEBUG, dev, "downstream link has been reset\n"); return rc ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED; } diff --git a/include/linux/pci.h b/include/linux/pci.h index 6ba818449095..03520ff23d73 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1103,7 +1103,6 @@ int pci_reset_bus(struct pci_bus *bus); int pci_try_reset_bus(struct pci_bus *bus); void pci_reset_secondary_bus(struct pci_dev *dev); void pcibios_reset_secondary_bus(struct pci_dev *dev); -int pci_reset_bridge_secondary_bus(struct pci_dev *dev); void pci_update_resource(struct pci_dev *dev, int resno); int __must_check pci_assign_resource(struct pci_dev *dev, int i); int __must_check pci_reassign_resource(struct pci_dev *dev, int i, resource_size_t add_size, resource_size_t align); -- cgit v1.2.3 From 811c5cb37df46b0cd714dbd053d19cdb97d08cff Mon Sep 17 00:00:00 2001 From: Sinan Kaya Date: Thu, 19 Jul 2018 18:04:12 -0500 Subject: PCI: Unify try slot and bus reset API Drivers are expected to call pci_try_reset_slot() or pci_try_reset_bus() by querying if a system supports hotplug or not. A survey showed that most drivers don't do this and we are leaking hotplug capability to the user. Hide pci_try_slot_reset() from drivers and embed into pci_try_bus_reset(). Change pci_try_reset_bus() parameter from struct pci_bus to struct pci_dev. Signed-off-by: Sinan Kaya Signed-off-by: Bjorn Helgaas --- drivers/infiniband/hw/hfi1/pcie.c | 2 +- drivers/pci/pci.c | 21 ++++++++++++++++----- drivers/vfio/pci/vfio_pci.c | 6 ++---- include/linux/pci.h | 3 +-- 4 files changed, 20 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/hw/hfi1/pcie.c b/drivers/infiniband/hw/hfi1/pcie.c index 4570c4dc93d9..df4f2d390be8 100644 --- a/drivers/infiniband/hw/hfi1/pcie.c +++ b/drivers/infiniband/hw/hfi1/pcie.c @@ -905,7 +905,7 @@ static int trigger_sbr(struct hfi1_devdata *dd) * delay after a reset is required. Per spec requirements, * the link is either working or not after that point. */ - return pci_try_reset_bus(dev->bus); + return pci_try_reset_bus(dev); } /* diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 236220cb0f77..a31e6dbf21c3 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -4817,12 +4817,12 @@ int pci_reset_slot(struct pci_slot *slot) EXPORT_SYMBOL_GPL(pci_reset_slot); /** - * pci_try_reset_slot - Try to reset a PCI slot + * __pci_try_reset_slot - Try to reset a PCI slot * @slot: PCI slot to reset * * Same as above except return -EAGAIN if the slot cannot be locked */ -int pci_try_reset_slot(struct pci_slot *slot) +static int __pci_try_reset_slot(struct pci_slot *slot) { int rc; @@ -4843,7 +4843,6 @@ int pci_try_reset_slot(struct pci_slot *slot) return rc; } -EXPORT_SYMBOL_GPL(pci_try_reset_slot); static int pci_bus_reset(struct pci_bus *bus, int probe) { @@ -4906,12 +4905,12 @@ int pci_reset_bus(struct pci_bus *bus) EXPORT_SYMBOL_GPL(pci_reset_bus); /** - * pci_try_reset_bus - Try to reset a PCI bus + * __pci_try_reset_bus - Try to reset a PCI bus * @bus: top level PCI bus to reset * * Same as above except return -EAGAIN if the bus cannot be locked */ -int pci_try_reset_bus(struct pci_bus *bus) +static int __pci_try_reset_bus(struct pci_bus *bus) { int rc; @@ -4932,6 +4931,18 @@ int pci_try_reset_bus(struct pci_bus *bus) return rc; } + +/** + * pci_try_reset_bus - Try to reset a PCI bus + * @pdev: top level PCI device to reset via slot/bus + * + * Same as above except return -EAGAIN if the bus cannot be locked + */ +int pci_try_reset_bus(struct pci_dev *pdev) +{ + return pci_probe_reset_slot(pdev->slot) ? + __pci_try_reset_slot(pdev->slot) : __pci_try_reset_bus(pdev->bus); +} EXPORT_SYMBOL_GPL(pci_try_reset_bus); /** diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index b423a309a6e0..71018ec9065b 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -1010,8 +1010,7 @@ reset_info_exit: &info, slot); if (!ret) /* User has access, do the reset */ - ret = slot ? pci_try_reset_slot(vdev->pdev->slot) : - pci_try_reset_bus(vdev->pdev->bus); + ret = pci_try_reset_bus(vdev->pdev); hot_reset_release: for (i--; i >= 0; i--) @@ -1373,8 +1372,7 @@ static void vfio_pci_try_bus_reset(struct vfio_pci_device *vdev) } if (needs_reset) - ret = slot ? pci_try_reset_slot(vdev->pdev->slot) : - pci_try_reset_bus(vdev->pdev->bus); + ret = pci_try_reset_bus(vdev->pdev); put_devs: for (i = 0; i < devs.cur_index; i++) { diff --git a/include/linux/pci.h b/include/linux/pci.h index 03520ff23d73..19fb82559145 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1097,10 +1097,9 @@ int pci_reset_function_locked(struct pci_dev *dev); int pci_try_reset_function(struct pci_dev *dev); int pci_probe_reset_slot(struct pci_slot *slot); int pci_reset_slot(struct pci_slot *slot); -int pci_try_reset_slot(struct pci_slot *slot); int pci_probe_reset_bus(struct pci_bus *bus); int pci_reset_bus(struct pci_bus *bus); -int pci_try_reset_bus(struct pci_bus *bus); +int pci_try_reset_bus(struct pci_dev *dev); void pci_reset_secondary_bus(struct pci_dev *dev); void pcibios_reset_secondary_bus(struct pci_dev *dev); void pci_update_resource(struct pci_dev *dev, int resno); -- cgit v1.2.3 From fe32e2fa656c29d5d25f959f8e6168ac405d9ab4 Mon Sep 17 00:00:00 2001 From: Sinan Kaya Date: Thu, 19 Jul 2018 18:04:14 -0500 Subject: PCI: Deprecate pci_reset_bus() and pci_reset_slot() functions pci_reset_bus() and pci_reset_slot() functions are not being used by any code. Remove them from the kernel in favor of pci_try_reset_bus() and pci_try_reset_slot() functions. Signed-off-by: Sinan Kaya Signed-off-by: Bjorn Helgaas --- drivers/pci/pci.c | 53 +---------------------------------------------------- include/linux/pci.h | 2 -- 2 files changed, 1 insertion(+), 54 deletions(-) (limited to 'include') diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index a31e6dbf21c3..8ee9f386c1ee 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -4784,7 +4784,7 @@ int pci_probe_reset_slot(struct pci_slot *slot) EXPORT_SYMBOL_GPL(pci_probe_reset_slot); /** - * pci_reset_slot - reset a PCI slot + * __pci_try_reset_slot - Try to reset a PCI slot * @slot: PCI slot to reset * * A PCI bus may host multiple slots, each slot may support a reset mechanism @@ -4796,30 +4796,6 @@ EXPORT_SYMBOL_GPL(pci_probe_reset_slot); * through this function. PCI config space of all devices in the slot and * behind the slot is saved before and restored after reset. * - * Return 0 on success, non-zero on error. - */ -int pci_reset_slot(struct pci_slot *slot) -{ - int rc; - - rc = pci_slot_reset(slot, 1); - if (rc) - return rc; - - pci_slot_save_and_disable(slot); - - rc = pci_slot_reset(slot, 0); - - pci_slot_restore(slot); - - return rc; -} -EXPORT_SYMBOL_GPL(pci_reset_slot); - -/** - * __pci_try_reset_slot - Try to reset a PCI slot - * @slot: PCI slot to reset - * * Same as above except return -EAGAIN if the slot cannot be locked */ static int __pci_try_reset_slot(struct pci_slot *slot) @@ -4877,33 +4853,6 @@ int pci_probe_reset_bus(struct pci_bus *bus) } EXPORT_SYMBOL_GPL(pci_probe_reset_bus); -/** - * pci_reset_bus - reset a PCI bus - * @bus: top level PCI bus to reset - * - * Do a bus reset on the given bus and any subordinate buses, saving - * and restoring state of all devices. - * - * Return 0 on success, non-zero on error. - */ -int pci_reset_bus(struct pci_bus *bus) -{ - int rc; - - rc = pci_bus_reset(bus, 1); - if (rc) - return rc; - - pci_bus_save_and_disable(bus); - - rc = pci_bus_reset(bus, 0); - - pci_bus_restore(bus); - - return rc; -} -EXPORT_SYMBOL_GPL(pci_reset_bus); - /** * __pci_try_reset_bus - Try to reset a PCI bus * @bus: top level PCI bus to reset diff --git a/include/linux/pci.h b/include/linux/pci.h index 19fb82559145..cf53ecb50789 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1096,9 +1096,7 @@ int pci_reset_function(struct pci_dev *dev); int pci_reset_function_locked(struct pci_dev *dev); int pci_try_reset_function(struct pci_dev *dev); int pci_probe_reset_slot(struct pci_slot *slot); -int pci_reset_slot(struct pci_slot *slot); int pci_probe_reset_bus(struct pci_bus *bus); -int pci_reset_bus(struct pci_bus *bus); int pci_try_reset_bus(struct pci_dev *dev); void pci_reset_secondary_bus(struct pci_dev *dev); void pcibios_reset_secondary_bus(struct pci_dev *dev); -- cgit v1.2.3 From c6a44ba950d147e15fe6dab6455a52f91d8fe625 Mon Sep 17 00:00:00 2001 From: Sinan Kaya Date: Thu, 19 Jul 2018 18:04:15 -0500 Subject: PCI: Rename pci_try_reset_bus() to pci_reset_bus() Now that the old implementation of pci_reset_bus() is gone, replace pci_try_reset_bus() with pci_reset_bus(). Compared to the old implementation, new code will fail immmediately with -EAGAIN if object lock cannot be obtained. Signed-off-by: Sinan Kaya Signed-off-by: Bjorn Helgaas --- drivers/infiniband/hw/hfi1/pcie.c | 2 +- drivers/pci/pci.c | 16 ++++++++-------- drivers/vfio/pci/vfio_pci.c | 4 ++-- include/linux/pci.h | 2 +- 4 files changed, 12 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/hw/hfi1/pcie.c b/drivers/infiniband/hw/hfi1/pcie.c index df4f2d390be8..baf7c324f7b8 100644 --- a/drivers/infiniband/hw/hfi1/pcie.c +++ b/drivers/infiniband/hw/hfi1/pcie.c @@ -905,7 +905,7 @@ static int trigger_sbr(struct hfi1_devdata *dd) * delay after a reset is required. Per spec requirements, * the link is either working or not after that point. */ - return pci_try_reset_bus(dev); + return pci_reset_bus(dev); } /* diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 8ee9f386c1ee..d123c2b173da 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -4784,7 +4784,7 @@ int pci_probe_reset_slot(struct pci_slot *slot) EXPORT_SYMBOL_GPL(pci_probe_reset_slot); /** - * __pci_try_reset_slot - Try to reset a PCI slot + * __pci_reset_slot - Try to reset a PCI slot * @slot: PCI slot to reset * * A PCI bus may host multiple slots, each slot may support a reset mechanism @@ -4798,7 +4798,7 @@ EXPORT_SYMBOL_GPL(pci_probe_reset_slot); * * Same as above except return -EAGAIN if the slot cannot be locked */ -static int __pci_try_reset_slot(struct pci_slot *slot) +static int __pci_reset_slot(struct pci_slot *slot) { int rc; @@ -4854,12 +4854,12 @@ int pci_probe_reset_bus(struct pci_bus *bus) EXPORT_SYMBOL_GPL(pci_probe_reset_bus); /** - * __pci_try_reset_bus - Try to reset a PCI bus + * __pci_reset_bus - Try to reset a PCI bus * @bus: top level PCI bus to reset * * Same as above except return -EAGAIN if the bus cannot be locked */ -static int __pci_try_reset_bus(struct pci_bus *bus) +static int __pci_reset_bus(struct pci_bus *bus) { int rc; @@ -4882,17 +4882,17 @@ static int __pci_try_reset_bus(struct pci_bus *bus) } /** - * pci_try_reset_bus - Try to reset a PCI bus + * pci_reset_bus - Try to reset a PCI bus * @pdev: top level PCI device to reset via slot/bus * * Same as above except return -EAGAIN if the bus cannot be locked */ -int pci_try_reset_bus(struct pci_dev *pdev) +int pci_reset_bus(struct pci_dev *pdev) { return pci_probe_reset_slot(pdev->slot) ? - __pci_try_reset_slot(pdev->slot) : __pci_try_reset_bus(pdev->bus); + __pci_reset_slot(pdev->slot) : __pci_reset_bus(pdev->bus); } -EXPORT_SYMBOL_GPL(pci_try_reset_bus); +EXPORT_SYMBOL_GPL(pci_reset_bus); /** * pcix_get_max_mmrbc - get PCI-X maximum designed memory read byte count diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 71018ec9065b..345c0dc8a6dc 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -1010,7 +1010,7 @@ reset_info_exit: &info, slot); if (!ret) /* User has access, do the reset */ - ret = pci_try_reset_bus(vdev->pdev); + ret = pci_reset_bus(vdev->pdev); hot_reset_release: for (i--; i >= 0; i--) @@ -1372,7 +1372,7 @@ static void vfio_pci_try_bus_reset(struct vfio_pci_device *vdev) } if (needs_reset) - ret = pci_try_reset_bus(vdev->pdev); + ret = pci_reset_bus(vdev->pdev); put_devs: for (i = 0; i < devs.cur_index; i++) { diff --git a/include/linux/pci.h b/include/linux/pci.h index cf53ecb50789..307b336496f6 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1097,7 +1097,7 @@ int pci_reset_function_locked(struct pci_dev *dev); int pci_try_reset_function(struct pci_dev *dev); int pci_probe_reset_slot(struct pci_slot *slot); int pci_probe_reset_bus(struct pci_bus *bus); -int pci_try_reset_bus(struct pci_dev *dev); +int pci_reset_bus(struct pci_dev *dev); void pci_reset_secondary_bus(struct pci_dev *dev); void pcibios_reset_secondary_bus(struct pci_dev *dev); void pci_update_resource(struct pci_dev *dev, int resno); -- cgit v1.2.3 From b976690f5db26fbc7c2be413bfa0fbd270547a94 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Wed, 18 Jul 2018 11:41:06 +0200 Subject: x86/mm/pti: Introduce pti_finalize() Introduce a new function to finalize the kernel mappings for the userspace page-table after all ro/nx protections have been applied to the kernel mappings. Also move the call to pti_clone_kernel_text() to that function so that it will run on 32 bit kernels too. Signed-off-by: Joerg Roedel Signed-off-by: Thomas Gleixner Tested-by: Pavel Machek Cc: "H . Peter Anvin" Cc: linux-mm@kvack.org Cc: Linus Torvalds Cc: Andy Lutomirski Cc: Dave Hansen Cc: Josh Poimboeuf Cc: Juergen Gross Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Jiri Kosina Cc: Boris Ostrovsky Cc: Brian Gerst Cc: David Laight Cc: Denys Vlasenko Cc: Eduardo Valentin Cc: Greg KH Cc: Will Deacon Cc: aliguori@amazon.com Cc: daniel.gruss@iaik.tugraz.at Cc: hughd@google.com Cc: keescook@google.com Cc: Andrea Arcangeli Cc: Waiman Long Cc: "David H . Gutteridge" Cc: joro@8bytes.org Link: https://lkml.kernel.org/r/1531906876-13451-30-git-send-email-joro@8bytes.org --- arch/x86/include/asm/pti.h | 3 +-- arch/x86/mm/init_64.c | 6 ------ arch/x86/mm/pti.c | 14 +++++++++++++- include/linux/pti.h | 1 + init/main.c | 7 +++++++ 5 files changed, 22 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/arch/x86/include/asm/pti.h b/arch/x86/include/asm/pti.h index 38a17f1d5c9d..5df09a0b80b8 100644 --- a/arch/x86/include/asm/pti.h +++ b/arch/x86/include/asm/pti.h @@ -6,10 +6,9 @@ #ifdef CONFIG_PAGE_TABLE_ISOLATION extern void pti_init(void); extern void pti_check_boottime_disable(void); -extern void pti_clone_kernel_text(void); +extern void pti_finalize(void); #else static inline void pti_check_boottime_disable(void) { } -static inline void pti_clone_kernel_text(void) { } #endif #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index a688617c727e..9b19f9a8948e 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1291,12 +1291,6 @@ void mark_rodata_ro(void) (unsigned long) __va(__pa_symbol(_sdata))); debug_checkwx(); - - /* - * Do this after all of the manipulation of the - * kernel text page tables are complete. - */ - pti_clone_kernel_text(); } int kern_addr_valid(unsigned long addr) diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c index e41ee93c430d..fcfb815d420f 100644 --- a/arch/x86/mm/pti.c +++ b/arch/x86/mm/pti.c @@ -462,7 +462,7 @@ static inline bool pti_kernel_image_global_ok(void) * For some configurations, map all of kernel text into the user page * tables. This reduces TLB misses, especially on non-PCID systems. */ -void pti_clone_kernel_text(void) +static void pti_clone_kernel_text(void) { /* * rodata is part of the kernel image and is normally @@ -526,3 +526,15 @@ void __init pti_init(void) pti_setup_espfix64(); pti_setup_vsyscall(); } + +/* + * Finalize the kernel mappings in the userspace page-table. + */ +void pti_finalize(void) +{ + /* + * Do this after all of the manipulation of the + * kernel text page tables are complete. + */ + pti_clone_kernel_text(); +} diff --git a/include/linux/pti.h b/include/linux/pti.h index 0174883a935a..1a941efcaa62 100644 --- a/include/linux/pti.h +++ b/include/linux/pti.h @@ -6,6 +6,7 @@ #include #else static inline void pti_init(void) { } +static inline void pti_finalize(void) { } #endif #endif diff --git a/init/main.c b/init/main.c index 3b4ada11ed52..fcfef46c935a 100644 --- a/init/main.c +++ b/init/main.c @@ -1065,6 +1065,13 @@ static int __ref kernel_init(void *unused) jump_label_invalidate_initmem(); free_initmem(); mark_readonly(); + + /* + * Kernel mappings are now finalized - update the userspace page-table + * to finalize PTI. + */ + pti_finalize(); + system_state = SYSTEM_RUNNING; numa_default_policy(); -- cgit v1.2.3 From 985e695074d35768cb04d65f58bca45f7bf1a99d Mon Sep 17 00:00:00 2001 From: Ondrej Mosnacek Date: Fri, 13 Jul 2018 14:06:42 +0200 Subject: timekeeping/ntp: Constify some function arguments Add 'const' to some function arguments and variables to make it easier to read the code. Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Miroslav Lichvar Cc: Richard Cochran Cc: Prarit Bhargava Cc: Stephen Boyd Signed-off-by: Ondrej Mosnacek [jstultz: Also fixup pre-existing checkpatch warnings for prototype arguments with no variable name] Signed-off-by: John Stultz --- include/linux/timekeeping.h | 2 +- kernel/time/ntp.c | 6 +++--- kernel/time/ntp_internal.h | 4 ++-- kernel/time/timekeeping.c | 29 +++++++++++++++-------------- kernel/time/timekeeping_debug.c | 2 +- kernel/time/timekeeping_internal.h | 2 +- 6 files changed, 23 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 86bc2026efce..edace6b656e9 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -177,7 +177,7 @@ static inline time64_t ktime_get_clocktai_seconds(void) extern bool timekeeping_rtc_skipsuspend(void); extern bool timekeeping_rtc_skipresume(void); -extern void timekeeping_inject_sleeptime64(struct timespec64 *delta); +extern void timekeeping_inject_sleeptime64(const struct timespec64 *delta); /* * struct system_time_snapshot - simultaneous raw/real time capture with diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index a627cae8baab..c5e0cba3b39c 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -642,7 +642,7 @@ void ntp_notify_cmos_timer(void) /* * Propagate a new txc->status value into the NTP state: */ -static inline void process_adj_status(struct timex *txc) +static inline void process_adj_status(const struct timex *txc) { if ((time_status & STA_PLL) && !(txc->status & STA_PLL)) { time_state = TIME_OK; @@ -665,7 +665,7 @@ static inline void process_adj_status(struct timex *txc) } -static inline void process_adjtimex_modes(struct timex *txc, s32 *time_tai) +static inline void process_adjtimex_modes(const struct timex *txc, s32 *time_tai) { if (txc->modes & ADJ_STATUS) process_adj_status(txc); @@ -716,7 +716,7 @@ static inline void process_adjtimex_modes(struct timex *txc, s32 *time_tai) * adjtimex mainly allows reading (and writing, if superuser) of * kernel time-keeping variables. used by xntpd. */ -int __do_adjtimex(struct timex *txc, struct timespec64 *ts, s32 *time_tai) +int __do_adjtimex(struct timex *txc, const struct timespec64 *ts, s32 *time_tai) { int result; diff --git a/kernel/time/ntp_internal.h b/kernel/time/ntp_internal.h index 909bd1f1bfb1..c24b0e13f011 100644 --- a/kernel/time/ntp_internal.h +++ b/kernel/time/ntp_internal.h @@ -8,6 +8,6 @@ extern void ntp_clear(void); extern u64 ntp_tick_length(void); extern ktime_t ntp_get_next_leap(void); extern int second_overflow(time64_t secs); -extern int __do_adjtimex(struct timex *, struct timespec64 *, s32 *); -extern void __hardpps(const struct timespec64 *, const struct timespec64 *); +extern int __do_adjtimex(struct timex *txc, const struct timespec64 *ts, s32 *time_tai); +extern void __hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts); #endif /* _LINUX_NTP_INTERNAL_H */ diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index ad779c2ec53a..7033ac1fee65 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -105,7 +105,7 @@ static inline void tk_normalize_xtime(struct timekeeper *tk) } } -static inline struct timespec64 tk_xtime(struct timekeeper *tk) +static inline struct timespec64 tk_xtime(const struct timekeeper *tk) { struct timespec64 ts; @@ -162,7 +162,7 @@ static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta) * a read of the fast-timekeeper tkrs (which is protected by its own locking * and update logic). */ -static inline u64 tk_clock_read(struct tk_read_base *tkr) +static inline u64 tk_clock_read(const struct tk_read_base *tkr) { struct clocksource *clock = READ_ONCE(tkr->clock); @@ -211,7 +211,7 @@ static void timekeeping_check_update(struct timekeeper *tk, u64 offset) } } -static inline u64 timekeeping_get_delta(struct tk_read_base *tkr) +static inline u64 timekeeping_get_delta(const struct tk_read_base *tkr) { struct timekeeper *tk = &tk_core.timekeeper; u64 now, last, mask, max, delta; @@ -255,7 +255,7 @@ static inline u64 timekeeping_get_delta(struct tk_read_base *tkr) static inline void timekeeping_check_update(struct timekeeper *tk, u64 offset) { } -static inline u64 timekeeping_get_delta(struct tk_read_base *tkr) +static inline u64 timekeeping_get_delta(const struct tk_read_base *tkr) { u64 cycle_now, delta; @@ -352,7 +352,7 @@ u32 (*arch_gettimeoffset)(void) = default_arch_gettimeoffset; static inline u32 arch_gettimeoffset(void) { return 0; } #endif -static inline u64 timekeeping_delta_to_ns(struct tk_read_base *tkr, u64 delta) +static inline u64 timekeeping_delta_to_ns(const struct tk_read_base *tkr, u64 delta) { u64 nsec; @@ -363,7 +363,7 @@ static inline u64 timekeeping_delta_to_ns(struct tk_read_base *tkr, u64 delta) return nsec + arch_gettimeoffset(); } -static inline u64 timekeeping_get_ns(struct tk_read_base *tkr) +static inline u64 timekeeping_get_ns(const struct tk_read_base *tkr) { u64 delta; @@ -371,7 +371,7 @@ static inline u64 timekeeping_get_ns(struct tk_read_base *tkr) return timekeeping_delta_to_ns(tkr, delta); } -static inline u64 timekeeping_cycles_to_ns(struct tk_read_base *tkr, u64 cycles) +static inline u64 timekeeping_cycles_to_ns(const struct tk_read_base *tkr, u64 cycles) { u64 delta; @@ -394,7 +394,8 @@ static inline u64 timekeeping_cycles_to_ns(struct tk_read_base *tkr, u64 cycles) * slightly wrong timestamp (a few nanoseconds). See * @ktime_get_mono_fast_ns. */ -static void update_fast_timekeeper(struct tk_read_base *tkr, struct tk_fast *tkf) +static void update_fast_timekeeper(const struct tk_read_base *tkr, + struct tk_fast *tkf) { struct tk_read_base *base = tkf->base; @@ -549,10 +550,10 @@ EXPORT_SYMBOL_GPL(ktime_get_real_fast_ns); * number of cycles every time until timekeeping is resumed at which time the * proper readout base for the fast timekeeper will be restored automatically. */ -static void halt_fast_timekeeper(struct timekeeper *tk) +static void halt_fast_timekeeper(const struct timekeeper *tk) { static struct tk_read_base tkr_dummy; - struct tk_read_base *tkr = &tk->tkr_mono; + const struct tk_read_base *tkr = &tk->tkr_mono; memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); cycles_at_suspend = tk_clock_read(tkr); @@ -1277,7 +1278,7 @@ EXPORT_SYMBOL(do_settimeofday64); * * Adds or subtracts an offset value from the current time. */ -static int timekeeping_inject_offset(struct timespec64 *ts) +static int timekeeping_inject_offset(const struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; @@ -1585,7 +1586,7 @@ static struct timespec64 timekeeping_suspend_time; * adds the sleep offset to the timekeeping variables. */ static void __timekeeping_inject_sleeptime(struct timekeeper *tk, - struct timespec64 *delta) + const struct timespec64 *delta) { if (!timespec64_valid_strict(delta)) { printk_deferred(KERN_WARNING @@ -1646,7 +1647,7 @@ bool timekeeping_rtc_skipsuspend(void) * This function should only be called by rtc_resume(), and allows * a suspend offset to be injected into the timekeeping values. */ -void timekeeping_inject_sleeptime64(struct timespec64 *delta) +void timekeeping_inject_sleeptime64(const struct timespec64 *delta) { struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; @@ -2240,7 +2241,7 @@ ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real, /** * timekeeping_validate_timex - Ensures the timex is ok for use in do_adjtimex */ -static int timekeeping_validate_timex(struct timex *txc) +static int timekeeping_validate_timex(const struct timex *txc) { if (txc->modes & ADJ_ADJTIME) { /* singleshot must not be used with any other mode bits */ diff --git a/kernel/time/timekeeping_debug.c b/kernel/time/timekeeping_debug.c index 0754cadfa9e6..238e4be60229 100644 --- a/kernel/time/timekeeping_debug.c +++ b/kernel/time/timekeeping_debug.c @@ -70,7 +70,7 @@ static int __init tk_debug_sleep_time_init(void) } late_initcall(tk_debug_sleep_time_init); -void tk_debug_account_sleep_time(struct timespec64 *t) +void tk_debug_account_sleep_time(const struct timespec64 *t) { /* Cap bin index so we don't overflow the array */ int bin = min(fls(t->tv_sec), NUM_BINS-1); diff --git a/kernel/time/timekeeping_internal.h b/kernel/time/timekeeping_internal.h index cf5c0828ee31..bcbb52db2256 100644 --- a/kernel/time/timekeeping_internal.h +++ b/kernel/time/timekeeping_internal.h @@ -8,7 +8,7 @@ #include #ifdef CONFIG_DEBUG_FS -extern void tk_debug_account_sleep_time(struct timespec64 *t); +extern void tk_debug_account_sleep_time(const struct timespec64 *t); #else #define tk_debug_account_sleep_time(x) #endif -- cgit v1.2.3 From 39232ed5a1793f67b11430c43ed8a9ed6e96c6eb Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Tue, 17 Jul 2018 15:55:16 +0800 Subject: time: Introduce one suspend clocksource to compensate the suspend time On some hardware with multiple clocksources, we have coarse grained clocksources that support the CLOCK_SOURCE_SUSPEND_NONSTOP flag, but which are less than ideal for timekeeping whereas other clocksources can be better candidates but halt on suspend. Currently, the timekeeping core only supports timing suspend using CLOCK_SOURCE_SUSPEND_NONSTOP clocksources if that clocksource is the current clocksource for timekeeping. As a result, some architectures try to implement read_persistent_clock64() using those non-stop clocksources, but isn't really ideal, which will introduce more duplicate code. To fix this, provide logic to allow a registered SUSPEND_NONSTOP clocksource, which isn't the current clocksource, to be used to calculate the suspend time. Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Miroslav Lichvar Cc: Richard Cochran Cc: Prarit Bhargava Cc: Stephen Boyd Cc: Daniel Lezcano Reviewed-by: Thomas Gleixner Reviewed-by: Daniel Lezcano Suggested-by: Thomas Gleixner Signed-off-by: Baolin Wang [jstultz: minor tweaks to merge with previous resume changes] Signed-off-by: John Stultz --- include/linux/clocksource.h | 3 + kernel/time/clocksource.c | 149 ++++++++++++++++++++++++++++++++++++++++++++ kernel/time/timekeeping.c | 22 ++++--- 3 files changed, 166 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 7dff1963c185..308918928767 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -194,6 +194,9 @@ extern void clocksource_suspend(void); extern void clocksource_resume(void); extern struct clocksource * __init clocksource_default_clock(void); extern void clocksource_mark_unstable(struct clocksource *cs); +extern void +clocksource_start_suspend_timing(struct clocksource *cs, u64 start_cycles); +extern u64 clocksource_stop_suspend_timing(struct clocksource *cs, u64 now); extern u64 clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask, u64 *max_cycles); diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index f89a78e2792b..f74fb00d8064 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -94,6 +94,8 @@ EXPORT_SYMBOL_GPL(clocks_calc_mult_shift); /*[Clocksource internal variables]--------- * curr_clocksource: * currently selected clocksource. + * suspend_clocksource: + * used to calculate the suspend time. * clocksource_list: * linked list with the registered clocksources * clocksource_mutex: @@ -102,10 +104,12 @@ EXPORT_SYMBOL_GPL(clocks_calc_mult_shift); * Name of the user-specified clocksource. */ static struct clocksource *curr_clocksource; +static struct clocksource *suspend_clocksource; static LIST_HEAD(clocksource_list); static DEFINE_MUTEX(clocksource_mutex); static char override_name[CS_NAME_LEN]; static int finished_booting; +static u64 suspend_start; #ifdef CONFIG_CLOCKSOURCE_WATCHDOG static void clocksource_watchdog_work(struct work_struct *work); @@ -447,6 +451,140 @@ static inline void clocksource_watchdog_unlock(unsigned long *flags) { } #endif /* CONFIG_CLOCKSOURCE_WATCHDOG */ +static bool clocksource_is_suspend(struct clocksource *cs) +{ + return cs == suspend_clocksource; +} + +static void __clocksource_suspend_select(struct clocksource *cs) +{ + /* + * Skip the clocksource which will be stopped in suspend state. + */ + if (!(cs->flags & CLOCK_SOURCE_SUSPEND_NONSTOP)) + return; + + /* + * The nonstop clocksource can be selected as the suspend clocksource to + * calculate the suspend time, so it should not supply suspend/resume + * interfaces to suspend the nonstop clocksource when system suspends. + */ + if (cs->suspend || cs->resume) { + pr_warn("Nonstop clocksource %s should not supply suspend/resume interfaces\n", + cs->name); + } + + /* Pick the best rating. */ + if (!suspend_clocksource || cs->rating > suspend_clocksource->rating) + suspend_clocksource = cs; +} + +/** + * clocksource_suspend_select - Select the best clocksource for suspend timing + * @fallback: if select a fallback clocksource + */ +static void clocksource_suspend_select(bool fallback) +{ + struct clocksource *cs, *old_suspend; + + old_suspend = suspend_clocksource; + if (fallback) + suspend_clocksource = NULL; + + list_for_each_entry(cs, &clocksource_list, list) { + /* Skip current if we were requested for a fallback. */ + if (fallback && cs == old_suspend) + continue; + + __clocksource_suspend_select(cs); + } +} + +/** + * clocksource_start_suspend_timing - Start measuring the suspend timing + * @cs: current clocksource from timekeeping + * @start_cycles: current cycles from timekeeping + * + * This function will save the start cycle values of suspend timer to calculate + * the suspend time when resuming system. + * + * This function is called late in the suspend process from timekeeping_suspend(), + * that means processes are freezed, non-boot cpus and interrupts are disabled + * now. It is therefore possible to start the suspend timer without taking the + * clocksource mutex. + */ +void clocksource_start_suspend_timing(struct clocksource *cs, u64 start_cycles) +{ + if (!suspend_clocksource) + return; + + /* + * If current clocksource is the suspend timer, we should use the + * tkr_mono.cycle_last value as suspend_start to avoid same reading + * from suspend timer. + */ + if (clocksource_is_suspend(cs)) { + suspend_start = start_cycles; + return; + } + + if (suspend_clocksource->enable && + suspend_clocksource->enable(suspend_clocksource)) { + pr_warn_once("Failed to enable the non-suspend-able clocksource.\n"); + return; + } + + suspend_start = suspend_clocksource->read(suspend_clocksource); +} + +/** + * clocksource_stop_suspend_timing - Stop measuring the suspend timing + * @cs: current clocksource from timekeeping + * @cycle_now: current cycles from timekeeping + * + * This function will calculate the suspend time from suspend timer. + * + * Returns nanoseconds since suspend started, 0 if no usable suspend clocksource. + * + * This function is called early in the resume process from timekeeping_resume(), + * that means there is only one cpu, no processes are running and the interrupts + * are disabled. It is therefore possible to stop the suspend timer without + * taking the clocksource mutex. + */ +u64 clocksource_stop_suspend_timing(struct clocksource *cs, u64 cycle_now) +{ + u64 now, delta, nsec = 0; + + if (!suspend_clocksource) + return 0; + + /* + * If current clocksource is the suspend timer, we should use the + * tkr_mono.cycle_last value from timekeeping as current cycle to + * avoid same reading from suspend timer. + */ + if (clocksource_is_suspend(cs)) + now = cycle_now; + else + now = suspend_clocksource->read(suspend_clocksource); + + if (now > suspend_start) { + delta = clocksource_delta(now, suspend_start, + suspend_clocksource->mask); + nsec = mul_u64_u32_shr(delta, suspend_clocksource->mult, + suspend_clocksource->shift); + } + + /* + * Disable the suspend timer to save power if current clocksource is + * not the suspend timer. + */ + if (!clocksource_is_suspend(cs) && suspend_clocksource->disable) + suspend_clocksource->disable(suspend_clocksource); + + return nsec; +} + /** * clocksource_suspend - suspend the clocksource(s) */ @@ -792,6 +930,7 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq) clocksource_select(); clocksource_select_watchdog(false); + __clocksource_suspend_select(cs); mutex_unlock(&clocksource_mutex); return 0; } @@ -820,6 +959,7 @@ void clocksource_change_rating(struct clocksource *cs, int rating) clocksource_select(); clocksource_select_watchdog(false); + clocksource_suspend_select(false); mutex_unlock(&clocksource_mutex); } EXPORT_SYMBOL(clocksource_change_rating); @@ -845,6 +985,15 @@ static int clocksource_unbind(struct clocksource *cs) return -EBUSY; } + if (clocksource_is_suspend(cs)) { + /* + * Select and try to install a replacement suspend clocksource. + * If no replacement suspend clocksource, we will just let the + * clocksource go and have no suspend clocksource. + */ + clocksource_suspend_select(true); + } + clocksource_watchdog_lock(&flags); clocksource_dequeue_watchdog(cs); list_del_init(&cs->list); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 19414b16cf9e..d9e659a12c76 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1692,7 +1692,7 @@ void timekeeping_resume(void) struct clocksource *clock = tk->tkr_mono.clock; unsigned long flags; struct timespec64 ts_new, ts_delta; - u64 cycle_now; + u64 cycle_now, nsec; bool inject_sleeptime = false; read_persistent_clock64(&ts_new); @@ -1716,13 +1716,8 @@ void timekeeping_resume(void) * usable source. The rtc part is handled separately in rtc core code. */ cycle_now = tk_clock_read(&tk->tkr_mono); - if ((clock->flags & CLOCK_SOURCE_SUSPEND_NONSTOP) && - cycle_now > tk->tkr_mono.cycle_last) { - u64 nsec, cyc_delta; - - cyc_delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, - tk->tkr_mono.mask); - nsec = mul_u64_u32_shr(cyc_delta, clock->mult, clock->shift); + nsec = clocksource_stop_suspend_timing(clock, cycle_now); + if (nsec > 0) { ts_delta = ns_to_timespec64(nsec); inject_sleeptime = true; } else if (timespec64_compare(&ts_new, &timekeeping_suspend_time) > 0) { @@ -1757,6 +1752,8 @@ int timekeeping_suspend(void) unsigned long flags; struct timespec64 delta, delta_delta; static struct timespec64 old_delta; + struct clocksource *curr_clock; + u64 cycle_now; read_persistent_clock64(&timekeeping_suspend_time); @@ -1775,6 +1772,15 @@ int timekeeping_suspend(void) timekeeping_forward_now(tk); timekeeping_suspended = 1; + /* + * Since we've called forward_now, cycle_last stores the value + * just read from the current clocksource. Save this to potentially + * use in suspend timing. + */ + curr_clock = tk->tkr_mono.clock; + cycle_now = tk->tkr_mono.cycle_last; + clocksource_start_suspend_timing(curr_clock, cycle_now); + if (persistent_clock_exists) { /* * To avoid drift caused by repeated suspend/resumes, -- cgit v1.2.3 From cf862cbc831982a27f14a08adf82ad9ca8d86205 Mon Sep 17 00:00:00 2001 From: Stephan Mueller Date: Tue, 10 Jul 2018 17:56:33 +0200 Subject: crypto: drbg - eliminate constant reinitialization of SGL The CTR DRBG requires two SGLs pointing to input/output buffers for the CTR AES operation. The used SGLs always have only one entry. Thus, the SGL can be initialized during allocation time, preventing a re-initialization of the SGLs during each call. The performance is increased by about 1 to 3 percent depending on the size of the requested buffer size. Signed-off-by: Stephan Mueller Signed-off-by: Herbert Xu --- crypto/drbg.c | 11 +++++++---- include/crypto/drbg.h | 1 + 2 files changed, 8 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/crypto/drbg.c b/crypto/drbg.c index 466a112a4446..ee302fd229ad 100644 --- a/crypto/drbg.c +++ b/crypto/drbg.c @@ -1715,6 +1715,9 @@ static int drbg_init_sym_kernel(struct drbg_state *drbg) drbg->outscratchpad = (u8 *)PTR_ALIGN(drbg->outscratchpadbuf, alignmask + 1); + sg_init_table(&drbg->sg_in, 1); + sg_init_table(&drbg->sg_out, 1); + return alignmask; } @@ -1743,17 +1746,17 @@ static int drbg_kcapi_sym_ctr(struct drbg_state *drbg, u8 *inbuf, u32 inlen, u8 *outbuf, u32 outlen) { - struct scatterlist sg_in, sg_out; + struct scatterlist *sg_in = &drbg->sg_in, *sg_out = &drbg->sg_out; int ret; - sg_init_one(&sg_in, inbuf, inlen); - sg_init_one(&sg_out, drbg->outscratchpad, DRBG_OUTSCRATCHLEN); + sg_set_buf(sg_in, inbuf, inlen); + sg_set_buf(sg_out, drbg->outscratchpad, DRBG_OUTSCRATCHLEN); while (outlen) { u32 cryptlen = min3(inlen, outlen, (u32)DRBG_OUTSCRATCHLEN); /* Output buffer may not be valid for SGL, use scratchpad */ - skcipher_request_set_crypt(drbg->ctr_req, &sg_in, &sg_out, + skcipher_request_set_crypt(drbg->ctr_req, sg_in, sg_out, cryptlen, drbg->V); ret = crypto_wait_req(crypto_skcipher_encrypt(drbg->ctr_req), &drbg->ctr_wait); diff --git a/include/crypto/drbg.h b/include/crypto/drbg.h index 8f941102af36..54b9f5d375f5 100644 --- a/include/crypto/drbg.h +++ b/include/crypto/drbg.h @@ -127,6 +127,7 @@ struct drbg_state { __u8 *outscratchpadbuf; /* CTR mode output scratchpad */ __u8 *outscratchpad; /* CTR mode aligned outbuf */ struct crypto_wait ctr_wait; /* CTR mode async wait obj */ + struct scatterlist sg_in, sg_out; /* CTR mode SGLs */ bool seeded; /* DRBG fully seeded? */ bool pr; /* Prediction resistance enabled? */ -- cgit v1.2.3 From 07a557f47d7e09b2c60ad4d51b1ac8b035b75f73 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Tue, 17 Jul 2018 19:27:16 +0300 Subject: net/sched: tunnel_key: Allow to set tos and ttl for tc based ip tunnels Allow user-space to provide tos and ttl to be set for the tunnel headers. Signed-off-by: Or Gerlitz Reviewed-by: Roi Dayan Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/uapi/linux/tc_act/tc_tunnel_key.h | 2 ++ net/sched/act_tunnel_key.c | 20 ++++++++++++++++++-- 2 files changed, 20 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/tc_act/tc_tunnel_key.h b/include/uapi/linux/tc_act/tc_tunnel_key.h index e284fec8c467..be384d63e1b5 100644 --- a/include/uapi/linux/tc_act/tc_tunnel_key.h +++ b/include/uapi/linux/tc_act/tc_tunnel_key.h @@ -39,6 +39,8 @@ enum { TCA_TUNNEL_KEY_ENC_OPTS, /* Nested TCA_TUNNEL_KEY_ENC_OPTS_ * attributes */ + TCA_TUNNEL_KEY_ENC_TOS, /* u8 */ + TCA_TUNNEL_KEY_ENC_TTL, /* u8 */ __TCA_TUNNEL_KEY_MAX, }; diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 3ec585d58762..22f26e9ea8f1 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -197,6 +197,8 @@ static const struct nla_policy tunnel_key_policy[TCA_TUNNEL_KEY_MAX + 1] = { [TCA_TUNNEL_KEY_ENC_DST_PORT] = {.type = NLA_U16}, [TCA_TUNNEL_KEY_NO_CSUM] = { .type = NLA_U8 }, [TCA_TUNNEL_KEY_ENC_OPTS] = { .type = NLA_NESTED }, + [TCA_TUNNEL_KEY_ENC_TOS] = { .type = NLA_U8 }, + [TCA_TUNNEL_KEY_ENC_TTL] = { .type = NLA_U8 }, }; static int tunnel_key_init(struct net *net, struct nlattr *nla, @@ -216,6 +218,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, int opts_len = 0; __be64 key_id; __be16 flags; + u8 tos, ttl; int ret = 0; int err; @@ -273,6 +276,13 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, } } + tos = 0; + if (tb[TCA_TUNNEL_KEY_ENC_TOS]) + tos = nla_get_u8(tb[TCA_TUNNEL_KEY_ENC_TOS]); + ttl = 0; + if (tb[TCA_TUNNEL_KEY_ENC_TTL]) + ttl = nla_get_u8(tb[TCA_TUNNEL_KEY_ENC_TTL]); + if (tb[TCA_TUNNEL_KEY_ENC_IPV4_SRC] && tb[TCA_TUNNEL_KEY_ENC_IPV4_DST]) { __be32 saddr; @@ -281,7 +291,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, saddr = nla_get_in_addr(tb[TCA_TUNNEL_KEY_ENC_IPV4_SRC]); daddr = nla_get_in_addr(tb[TCA_TUNNEL_KEY_ENC_IPV4_DST]); - metadata = __ip_tun_set_dst(saddr, daddr, 0, 0, + metadata = __ip_tun_set_dst(saddr, daddr, tos, ttl, dst_port, flags, key_id, opts_len); } else if (tb[TCA_TUNNEL_KEY_ENC_IPV6_SRC] && @@ -292,7 +302,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, saddr = nla_get_in6_addr(tb[TCA_TUNNEL_KEY_ENC_IPV6_SRC]); daddr = nla_get_in6_addr(tb[TCA_TUNNEL_KEY_ENC_IPV6_DST]); - metadata = __ipv6_tun_set_dst(&saddr, &daddr, 0, 0, dst_port, + metadata = __ipv6_tun_set_dst(&saddr, &daddr, tos, ttl, dst_port, 0, flags, key_id, 0); } else { @@ -504,6 +514,12 @@ static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a, !(key->tun_flags & TUNNEL_CSUM)) || tunnel_key_opts_dump(skb, info)) goto nla_put_failure; + + if (key->tos && nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_TOS, key->tos)) + goto nla_put_failure; + + if (key->ttl && nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_TTL, key->ttl)) + goto nla_put_failure; } tcf_tm_dump(&tm, &t->tcf_tm); -- cgit v1.2.3 From 5544adb9707fda5d54494c37940701894c16b9a0 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Tue, 17 Jul 2018 19:27:17 +0300 Subject: flow_dissector: Dissect tos and ttl from the tunnel info Add dissection of the tos and ttl from the ip tunnel headers fields in case a match is needed on them. Signed-off-by: Or Gerlitz Reviewed-by: Roi Dayan Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/flow_dissector.h | 2 +- net/core/flow_dissector.c | 14 +++++++++++++- 2 files changed, 14 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index c64406717eee..2a17f041f7a1 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -207,7 +207,7 @@ enum flow_dissector_key_id { FLOW_DISSECTOR_KEY_TCP, /* struct flow_dissector_key_tcp */ FLOW_DISSECTOR_KEY_IP, /* struct flow_dissector_key_ip */ FLOW_DISSECTOR_KEY_CVLAN, /* struct flow_dissector_key_flow_vlan */ - + FLOW_DISSECTOR_KEY_ENC_IP, /* struct flow_dissector_key_ip */ FLOW_DISSECTOR_KEY_MAX, }; diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index b555fc229e96..08a5184f4b34 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -152,7 +152,9 @@ skb_flow_dissect_tunnel_info(const struct sk_buff *skb, !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_CONTROL) && !dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_ENC_PORTS)) + FLOW_DISSECTOR_KEY_ENC_PORTS) && + !dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_ENC_IP)) return; info = skb_tunnel_info(skb); @@ -212,6 +214,16 @@ skb_flow_dissect_tunnel_info(const struct sk_buff *skb, tp->src = key->tp_src; tp->dst = key->tp_dst; } + + if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IP)) { + struct flow_dissector_key_ip *ip; + + ip = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_ENC_IP, + target_container); + ip->tos = key->tos; + ip->ttl = key->ttl; + } } EXPORT_SYMBOL(skb_flow_dissect_tunnel_info); -- cgit v1.2.3 From 0e2c17b64d5c7f57bcd7054ef87797376dcdee26 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Tue, 17 Jul 2018 19:27:18 +0300 Subject: net/sched: cls_flower: Support matching on ip tos and ttl for tunnels Allow users to set rules matching on ipv4 tos and ttl or ipv6 traffic-class and hoplimit of tunnel headers. Signed-off-by: Or Gerlitz Reviewed-by: Roi Dayan Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/uapi/linux/pkt_cls.h | 5 +++++ net/sched/cls_flower.c | 43 ++++++++++++++++++++++++++++--------------- 2 files changed, 33 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index c4262d911596..b4512254036b 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -473,6 +473,11 @@ enum { TCA_FLOWER_KEY_CVLAN_PRIO, /* u8 */ TCA_FLOWER_KEY_CVLAN_ETH_TYPE, /* be16 */ + TCA_FLOWER_KEY_ENC_IP_TOS, /* u8 */ + TCA_FLOWER_KEY_ENC_IP_TOS_MASK, /* u8 */ + TCA_FLOWER_KEY_ENC_IP_TTL, /* u8 */ + TCA_FLOWER_KEY_ENC_IP_TTL_MASK, /* u8 */ + __TCA_FLOWER_MAX, }; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index c53fdd411f90..38d74803e2df 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -52,6 +52,7 @@ struct fl_flow_key { struct flow_dissector_key_mpls mpls; struct flow_dissector_key_tcp tcp; struct flow_dissector_key_ip ip; + struct flow_dissector_key_ip enc_ip; } __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */ struct fl_flow_mask_range { @@ -453,6 +454,10 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { [TCA_FLOWER_KEY_CVLAN_ID] = { .type = NLA_U16 }, [TCA_FLOWER_KEY_CVLAN_PRIO] = { .type = NLA_U8 }, [TCA_FLOWER_KEY_CVLAN_ETH_TYPE] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_ENC_IP_TOS] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_ENC_IP_TOS_MASK] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_ENC_IP_TTL] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_ENC_IP_TTL_MASK] = { .type = NLA_U8 }, }; static void fl_set_key_val(struct nlattr **tb, @@ -561,17 +566,17 @@ static int fl_set_key_flags(struct nlattr **tb, return 0; } -static void fl_set_key_ip(struct nlattr **tb, +static void fl_set_key_ip(struct nlattr **tb, bool encap, struct flow_dissector_key_ip *key, struct flow_dissector_key_ip *mask) { - fl_set_key_val(tb, &key->tos, TCA_FLOWER_KEY_IP_TOS, - &mask->tos, TCA_FLOWER_KEY_IP_TOS_MASK, - sizeof(key->tos)); + int tos_key = encap ? TCA_FLOWER_KEY_ENC_IP_TOS : TCA_FLOWER_KEY_IP_TOS; + int ttl_key = encap ? TCA_FLOWER_KEY_ENC_IP_TTL : TCA_FLOWER_KEY_IP_TTL; + int tos_mask = encap ? TCA_FLOWER_KEY_ENC_IP_TOS_MASK : TCA_FLOWER_KEY_IP_TOS_MASK; + int ttl_mask = encap ? TCA_FLOWER_KEY_ENC_IP_TTL_MASK : TCA_FLOWER_KEY_IP_TTL_MASK; - fl_set_key_val(tb, &key->ttl, TCA_FLOWER_KEY_IP_TTL, - &mask->ttl, TCA_FLOWER_KEY_IP_TTL_MASK, - sizeof(key->ttl)); + fl_set_key_val(tb, &key->tos, tos_key, &mask->tos, tos_mask, sizeof(key->tos)); + fl_set_key_val(tb, &key->ttl, ttl_key, &mask->ttl, ttl_mask, sizeof(key->ttl)); } static int fl_set_key(struct net *net, struct nlattr **tb, @@ -633,7 +638,7 @@ static int fl_set_key(struct net *net, struct nlattr **tb, fl_set_key_val(tb, &key->basic.ip_proto, TCA_FLOWER_KEY_IP_PROTO, &mask->basic.ip_proto, TCA_FLOWER_UNSPEC, sizeof(key->basic.ip_proto)); - fl_set_key_ip(tb, &key->ip, &mask->ip); + fl_set_key_ip(tb, false, &key->ip, &mask->ip); } if (tb[TCA_FLOWER_KEY_IPV4_SRC] || tb[TCA_FLOWER_KEY_IPV4_DST]) { @@ -768,6 +773,8 @@ static int fl_set_key(struct net *net, struct nlattr **tb, &mask->enc_tp.dst, TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK, sizeof(key->enc_tp.dst)); + fl_set_key_ip(tb, true, &key->enc_ip, &mask->enc_ip); + if (tb[TCA_FLOWER_KEY_FLAGS]) ret = fl_set_key_flags(tb, &key->control.flags, &mask->control.flags); @@ -860,6 +867,8 @@ static void fl_init_dissector(struct fl_flow_mask *mask) enc_control); FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, FLOW_DISSECTOR_KEY_ENC_PORTS, enc_tp); + FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, + FLOW_DISSECTOR_KEY_ENC_IP, enc_ip); skb_flow_dissector_init(&mask->dissector, keys, cnt); } @@ -1208,14 +1217,17 @@ static int fl_dump_key_mpls(struct sk_buff *skb, return 0; } -static int fl_dump_key_ip(struct sk_buff *skb, +static int fl_dump_key_ip(struct sk_buff *skb, bool encap, struct flow_dissector_key_ip *key, struct flow_dissector_key_ip *mask) { - if (fl_dump_key_val(skb, &key->tos, TCA_FLOWER_KEY_IP_TOS, &mask->tos, - TCA_FLOWER_KEY_IP_TOS_MASK, sizeof(key->tos)) || - fl_dump_key_val(skb, &key->ttl, TCA_FLOWER_KEY_IP_TTL, &mask->ttl, - TCA_FLOWER_KEY_IP_TTL_MASK, sizeof(key->ttl))) + int tos_key = encap ? TCA_FLOWER_KEY_ENC_IP_TOS : TCA_FLOWER_KEY_IP_TOS; + int ttl_key = encap ? TCA_FLOWER_KEY_ENC_IP_TTL : TCA_FLOWER_KEY_IP_TTL; + int tos_mask = encap ? TCA_FLOWER_KEY_ENC_IP_TOS_MASK : TCA_FLOWER_KEY_IP_TOS_MASK; + int ttl_mask = encap ? TCA_FLOWER_KEY_ENC_IP_TTL_MASK : TCA_FLOWER_KEY_IP_TTL_MASK; + + if (fl_dump_key_val(skb, &key->tos, tos_key, &mask->tos, tos_mask, sizeof(key->tos)) || + fl_dump_key_val(skb, &key->ttl, ttl_key, &mask->ttl, ttl_mask, sizeof(key->ttl))) return -1; return 0; @@ -1361,7 +1373,7 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh, (fl_dump_key_val(skb, &key->basic.ip_proto, TCA_FLOWER_KEY_IP_PROTO, &mask->basic.ip_proto, TCA_FLOWER_UNSPEC, sizeof(key->basic.ip_proto)) || - fl_dump_key_ip(skb, &key->ip, &mask->ip))) + fl_dump_key_ip(skb, false, &key->ip, &mask->ip))) goto nla_put_failure; if (key->control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS && @@ -1486,7 +1498,8 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh, TCA_FLOWER_KEY_ENC_UDP_DST_PORT, &mask->enc_tp.dst, TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK, - sizeof(key->enc_tp.dst))) + sizeof(key->enc_tp.dst)) || + fl_dump_key_ip(skb, true, &key->enc_ip, &mask->enc_ip)) goto nla_put_failure; if (fl_dump_key_flags(skb, key->control.flags, mask->control.flags)) -- cgit v1.2.3 From b51dab46c6adfbb7e80cd0f59ae17b8a30d94b1a Mon Sep 17 00:00:00 2001 From: Sudarsana Reddy Kalluru Date: Wed, 18 Jul 2018 06:27:22 -0700 Subject: qed: Add qed APIs for PHY module query. This patch adds qed APIs for reading the PHY module. Signed-off-by: Sudarsana Reddy Kalluru Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_hsi.h | 16 ++++++++++ drivers/net/ethernet/qlogic/qed/qed_main.c | 23 ++++++++++++++ drivers/net/ethernet/qlogic/qed/qed_mcp.c | 49 ++++++++++++++++++++++++++++++ drivers/net/ethernet/qlogic/qed/qed_mcp.h | 16 ++++++++++ include/linux/qed/qed_if.h | 15 +++++++++ 5 files changed, 119 insertions(+) (limited to 'include') diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h index bee10c1781fb..8faceb691657 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h +++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h @@ -12444,6 +12444,8 @@ struct public_drv_mb { #define DRV_MSG_CODE_STATS_TYPE_ISCSI 3 #define DRV_MSG_CODE_STATS_TYPE_RDMA 4 +#define DRV_MSG_CODE_TRANSCEIVER_READ 0x00160000 + #define DRV_MSG_CODE_MASK_PARITIES 0x001a0000 #define DRV_MSG_CODE_BIST_TEST 0x001e0000 @@ -12543,6 +12545,15 @@ struct public_drv_mb { #define DRV_MB_PARAM_SET_LED_MODE_ON 0x1 #define DRV_MB_PARAM_SET_LED_MODE_OFF 0x2 +#define DRV_MB_PARAM_TRANSCEIVER_PORT_OFFSET 0 +#define DRV_MB_PARAM_TRANSCEIVER_PORT_MASK 0x00000003 +#define DRV_MB_PARAM_TRANSCEIVER_SIZE_OFFSET 2 +#define DRV_MB_PARAM_TRANSCEIVER_SIZE_MASK 0x000000FC +#define DRV_MB_PARAM_TRANSCEIVER_I2C_ADDRESS_OFFSET 8 +#define DRV_MB_PARAM_TRANSCEIVER_I2C_ADDRESS_MASK 0x0000FF00 +#define DRV_MB_PARAM_TRANSCEIVER_OFFSET_OFFSET 16 +#define DRV_MB_PARAM_TRANSCEIVER_OFFSET_MASK 0xFFFF0000 + /* Resource Allocation params - Driver version support */ #define DRV_MB_PARAM_RESOURCE_ALLOC_VERSION_MAJOR_MASK 0xFFFF0000 #define DRV_MB_PARAM_RESOURCE_ALLOC_VERSION_MAJOR_SHIFT 16 @@ -12596,6 +12607,9 @@ struct public_drv_mb { #define FW_MSG_CODE_PHY_OK 0x00110000 #define FW_MSG_CODE_OK 0x00160000 #define FW_MSG_CODE_ERROR 0x00170000 +#define FW_MSG_CODE_TRANSCEIVER_DIAG_OK 0x00160000 +#define FW_MSG_CODE_TRANSCEIVER_DIAG_ERROR 0x00170000 +#define FW_MSG_CODE_TRANSCEIVER_NOT_PRESENT 0x00020000 #define FW_MSG_CODE_OS_WOL_SUPPORTED 0x00800000 #define FW_MSG_CODE_OS_WOL_NOT_SUPPORTED 0x00810000 @@ -12687,6 +12701,8 @@ struct mcp_public_data { struct public_func func[MCP_GLOB_FUNC_MAX]; }; +#define MAX_I2C_TRANSACTION_SIZE 16 + /* OCBB definitions */ enum tlvs { /* Category 1: Device Properties */ diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index 0cbc74d6ca8b..158944aa6097 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -2102,6 +2102,28 @@ out: return status; } +static int qed_read_module_eeprom(struct qed_dev *cdev, char *buf, + u8 dev_addr, u32 offset, u32 len) +{ + struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev); + struct qed_ptt *ptt; + int rc = 0; + + if (IS_VF(cdev)) + return 0; + + ptt = qed_ptt_acquire(hwfn); + if (!ptt) + return -EAGAIN; + + rc = qed_mcp_phy_sfp_read(hwfn, ptt, MFW_PORT(hwfn), dev_addr, + offset, len, buf); + + qed_ptt_release(hwfn, ptt); + + return rc; +} + static struct qed_selftest_ops qed_selftest_ops_pass = { .selftest_memory = &qed_selftest_memory, .selftest_interrupt = &qed_selftest_interrupt, @@ -2144,6 +2166,7 @@ const struct qed_common_ops qed_common_ops_pass = { .update_mac = &qed_update_mac, .update_mtu = &qed_update_mtu, .update_wol = &qed_update_wol, + .read_module_eeprom = &qed_read_module_eeprom, }; void qed_get_protocol_stats(struct qed_dev *cdev, diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index 4e0b443c9519..62a220fce6e1 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -2463,6 +2463,55 @@ out: return rc; } +int qed_mcp_phy_sfp_read(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, + u32 port, u32 addr, u32 offset, u32 len, u8 *p_buf) +{ + u32 bytes_left, bytes_to_copy, buf_size, nvm_offset = 0; + u32 resp, param; + int rc; + + nvm_offset |= (port << DRV_MB_PARAM_TRANSCEIVER_PORT_OFFSET) & + DRV_MB_PARAM_TRANSCEIVER_PORT_MASK; + nvm_offset |= (addr << DRV_MB_PARAM_TRANSCEIVER_I2C_ADDRESS_OFFSET) & + DRV_MB_PARAM_TRANSCEIVER_I2C_ADDRESS_MASK; + + addr = offset; + offset = 0; + bytes_left = len; + while (bytes_left > 0) { + bytes_to_copy = min_t(u32, bytes_left, + MAX_I2C_TRANSACTION_SIZE); + nvm_offset &= (DRV_MB_PARAM_TRANSCEIVER_I2C_ADDRESS_MASK | + DRV_MB_PARAM_TRANSCEIVER_PORT_MASK); + nvm_offset |= ((addr + offset) << + DRV_MB_PARAM_TRANSCEIVER_OFFSET_OFFSET) & + DRV_MB_PARAM_TRANSCEIVER_OFFSET_MASK; + nvm_offset |= (bytes_to_copy << + DRV_MB_PARAM_TRANSCEIVER_SIZE_OFFSET) & + DRV_MB_PARAM_TRANSCEIVER_SIZE_MASK; + rc = qed_mcp_nvm_rd_cmd(p_hwfn, p_ptt, + DRV_MSG_CODE_TRANSCEIVER_READ, + nvm_offset, &resp, ¶m, &buf_size, + (u32 *)(p_buf + offset)); + if (rc) { + DP_NOTICE(p_hwfn, + "Failed to send a transceiver read command to the MFW. rc = %d.\n", + rc); + return rc; + } + + if (resp == FW_MSG_CODE_TRANSCEIVER_NOT_PRESENT) + return -ENODEV; + else if (resp != FW_MSG_CODE_TRANSCEIVER_DIAG_OK) + return -EINVAL; + + offset += buf_size; + bytes_left -= buf_size; + } + + return 0; +} + int qed_mcp_bist_register_test(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) { u32 drv_mb_param = 0, rsp, param; diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h index 632a838f1fe3..047976d5c6e9 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h @@ -839,6 +839,22 @@ int qed_mcp_nvm_rd_cmd(struct qed_hwfn *p_hwfn, u32 *o_mcp_resp, u32 *o_mcp_param, u32 *o_txn_size, u32 *o_buf); +/** + * @brief Read from sfp + * + * @param p_hwfn - hw function + * @param p_ptt - PTT required for register access + * @param port - transceiver port + * @param addr - I2C address + * @param offset - offset in sfp + * @param len - buffer length + * @param p_buf - buffer to read into + * + * @return int - 0 - operation was successful. + */ +int qed_mcp_phy_sfp_read(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, + u32 port, u32 addr, u32 offset, u32 len, u8 *p_buf); + /** * @brief indicates whether the MFW objects [under mcp_info] are accessible * diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index b4040023cbfb..8cd34645e892 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -759,6 +759,9 @@ struct qed_generic_tlvs { u8 mac[QED_TLV_MAC_COUNT][ETH_ALEN]; }; +#define QED_I2C_DEV_ADDR_A0 0xA0 +#define QED_I2C_DEV_ADDR_A2 0xA2 + #define QED_NVM_SIGNATURE 0x12435687 enum qed_nvm_flash_cmd { @@ -1026,6 +1029,18 @@ struct qed_common_ops { * @param enabled - true iff WoL should be enabled. */ int (*update_wol) (struct qed_dev *cdev, bool enabled); + +/** + * @brief read_module_eeprom + * + * @param cdev + * @param buf - buffer + * @param dev_addr - PHY device memory region + * @param offset - offset into eeprom contents to be read + * @param len - buffer length, i.e., max bytes to be read + */ + int (*read_module_eeprom)(struct qed_dev *cdev, + char *buf, u8 dev_addr, u32 offset, u32 len); }; #define MASK_FIELD(_name, _value) \ -- cgit v1.2.3 From bc56b33404599edc412b91933d74b36873e8ea25 Mon Sep 17 00:00:00 2001 From: Benedict Wong Date: Thu, 19 Jul 2018 10:50:44 -0700 Subject: xfrm: Remove xfrmi interface ID from flowi In order to remove performance impact of having the extra u32 in every single flowi, this change removes the flowi_xfrm struct, prefering to take the if_id as a method parameter where needed. In the inbound direction, if_id is only needed during the __xfrm_check_policy() function, and the if_id can be determined at that point based on the skb. As such, xfrmi_decode_session() is only called with the skb in __xfrm_check_policy(). In the outbound direction, the only place where if_id is needed is the xfrm_lookup() call in xfrmi_xmit2(). With this change, the if_id is directly passed into the xfrm_lookup_with_ifid() call. All existing callers can still call xfrm_lookup(), which uses a default if_id of 0. This change does not change any behavior of XFRMIs except for improving overall system performance via flowi size reduction. This change has been tested against the Android Kernel Networking Tests: https://android.googlesource.com/kernel/tests/+/master/net/test Signed-off-by: Benedict Wong Signed-off-by: Steffen Klassert --- include/net/dst.h | 14 +++++++ include/net/flow.h | 9 ----- include/net/xfrm.h | 2 +- net/xfrm/xfrm_interface.c | 4 +- net/xfrm/xfrm_policy.c | 98 +++++++++++++++++++++++++++++++---------------- net/xfrm/xfrm_state.c | 3 +- 6 files changed, 83 insertions(+), 47 deletions(-) (limited to 'include') diff --git a/include/net/dst.h b/include/net/dst.h index b3219cd8a5a1..7f735e76ca73 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -475,6 +475,14 @@ static inline struct dst_entry *xfrm_lookup(struct net *net, return dst_orig; } +static inline struct dst_entry * +xfrm_lookup_with_ifid(struct net *net, struct dst_entry *dst_orig, + const struct flowi *fl, const struct sock *sk, + int flags, u32 if_id) +{ + return dst_orig; +} + static inline struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, @@ -494,6 +502,12 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, const struct sock *sk, int flags); +struct dst_entry *xfrm_lookup_with_ifid(struct net *net, + struct dst_entry *dst_orig, + const struct flowi *fl, + const struct sock *sk, int flags, + u32 if_id); + struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, const struct sock *sk, int flags); diff --git a/include/net/flow.h b/include/net/flow.h index 187c9bef672f..8ce21793094e 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -26,10 +26,6 @@ struct flowi_tunnel { __be64 tun_id; }; -struct flowi_xfrm { - __u32 if_id; -}; - struct flowi_common { int flowic_oif; int flowic_iif; @@ -43,7 +39,6 @@ struct flowi_common { #define FLOWI_FLAG_SKIP_NH_OIF 0x04 __u32 flowic_secid; struct flowi_tunnel flowic_tun_key; - struct flowi_xfrm xfrm; kuid_t flowic_uid; }; @@ -83,7 +78,6 @@ struct flowi4 { #define flowi4_secid __fl_common.flowic_secid #define flowi4_tun_key __fl_common.flowic_tun_key #define flowi4_uid __fl_common.flowic_uid -#define flowi4_xfrm __fl_common.xfrm /* (saddr,daddr) must be grouped, same order as in IP header */ __be32 saddr; @@ -115,7 +109,6 @@ static inline void flowi4_init_output(struct flowi4 *fl4, int oif, fl4->flowi4_flags = flags; fl4->flowi4_secid = 0; fl4->flowi4_tun_key.tun_id = 0; - fl4->flowi4_xfrm.if_id = 0; fl4->flowi4_uid = uid; fl4->daddr = daddr; fl4->saddr = saddr; @@ -145,7 +138,6 @@ struct flowi6 { #define flowi6_secid __fl_common.flowic_secid #define flowi6_tun_key __fl_common.flowic_tun_key #define flowi6_uid __fl_common.flowic_uid -#define flowi6_xfrm __fl_common.xfrm struct in6_addr daddr; struct in6_addr saddr; /* Note: flowi6_tos is encoded in flowlabel, too. */ @@ -193,7 +185,6 @@ struct flowi { #define flowi_secid u.__fl_common.flowic_secid #define flowi_tun_key u.__fl_common.flowic_tun_key #define flowi_uid u.__fl_common.flowic_uid -#define flowi_xfrm u.__fl_common.xfrm } __attribute__((__aligned__(BITS_PER_LONG/8))); static inline struct flowi *flowi4_to_flowi(struct flowi4 *fl4) diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 1350e2cf0749..ca820945f30c 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1557,7 +1557,7 @@ struct xfrm_state *xfrm_state_find(const xfrm_address_t *daddr, const struct flowi *fl, struct xfrm_tmpl *tmpl, struct xfrm_policy *pol, int *err, - unsigned short family); + unsigned short family, u32 if_id); struct xfrm_state *xfrm_stateonly_find(struct net *net, u32 mark, u32 if_id, xfrm_address_t *daddr, xfrm_address_t *saddr, diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c index 31cb1c7e3881..ccfe18d67e98 100644 --- a/net/xfrm/xfrm_interface.c +++ b/net/xfrm/xfrm_interface.c @@ -307,10 +307,8 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) if (!dst) goto tx_err_link_failure; - fl->flowi_xfrm.if_id = xi->p.if_id; - dst_hold(dst); - dst = xfrm_lookup(xi->net, dst, fl, NULL, 0); + dst = xfrm_lookup_with_ifid(xi->net, dst, fl, NULL, 0, xi->p.if_id); if (IS_ERR(dst)) { err = PTR_ERR(dst); dst = NULL; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 5d2f734f4309..2f70fe68b9b0 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1068,14 +1068,14 @@ EXPORT_SYMBOL(xfrm_policy_walk_done); */ static int xfrm_policy_match(const struct xfrm_policy *pol, const struct flowi *fl, - u8 type, u16 family, int dir) + u8 type, u16 family, int dir, u32 if_id) { const struct xfrm_selector *sel = &pol->selector; int ret = -ESRCH; bool match; if (pol->family != family || - pol->if_id != fl->flowi_xfrm.if_id || + pol->if_id != if_id || (fl->flowi_mark & pol->mark.m) != pol->mark.v || pol->type != type) return ret; @@ -1090,7 +1090,8 @@ static int xfrm_policy_match(const struct xfrm_policy *pol, static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, const struct flowi *fl, - u16 family, u8 dir) + u16 family, u8 dir, + u32 if_id) { int err; struct xfrm_policy *pol, *ret; @@ -1114,7 +1115,7 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, priority = ~0U; ret = NULL; hlist_for_each_entry_rcu(pol, chain, bydst) { - err = xfrm_policy_match(pol, fl, type, family, dir); + err = xfrm_policy_match(pol, fl, type, family, dir, if_id); if (err) { if (err == -ESRCH) continue; @@ -1133,7 +1134,7 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, if ((pol->priority >= priority) && ret) break; - err = xfrm_policy_match(pol, fl, type, family, dir); + err = xfrm_policy_match(pol, fl, type, family, dir, if_id); if (err) { if (err == -ESRCH) continue; @@ -1158,21 +1159,25 @@ fail: return ret; } -static struct xfrm_policy * -xfrm_policy_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir) +static struct xfrm_policy *xfrm_policy_lookup(struct net *net, + const struct flowi *fl, + u16 family, u8 dir, u32 if_id) { #ifdef CONFIG_XFRM_SUB_POLICY struct xfrm_policy *pol; - pol = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_SUB, fl, family, dir); + pol = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_SUB, fl, family, + dir, if_id); if (pol != NULL) return pol; #endif - return xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN, fl, family, dir); + return xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN, fl, family, + dir, if_id); } static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir, - const struct flowi *fl, u16 family) + const struct flowi *fl, + u16 family, u32 if_id) { struct xfrm_policy *pol; @@ -1191,7 +1196,7 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir, match = xfrm_selector_match(&pol->selector, fl, family); if (match) { if ((sk->sk_mark & pol->mark.m) != pol->mark.v || - pol->if_id != fl->flowi_xfrm.if_id) { + pol->if_id != if_id) { pol = NULL; goto out; } @@ -1405,7 +1410,8 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, const struct flowi *fl, } } - x = xfrm_state_find(remote, local, fl, tmpl, policy, &error, family); + x = xfrm_state_find(remote, local, fl, tmpl, policy, &error, + family, policy->if_id); if (x && x->km.state == XFRM_STATE_VALID) { xfrm[nx++] = x; @@ -1708,7 +1714,8 @@ static int xfrm_expand_policies(const struct flowi *fl, u16 family, pols[1] = xfrm_policy_lookup_bytype(xp_net(pols[0]), XFRM_POLICY_TYPE_MAIN, fl, family, - XFRM_POLICY_OUT); + XFRM_POLICY_OUT, + pols[0]->if_id); if (pols[1]) { if (IS_ERR(pols[1])) { xfrm_pols_put(pols, *num_pols); @@ -1942,8 +1949,10 @@ free_dst: goto out; } -static struct xfrm_dst * -xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir, struct xfrm_flo *xflo) +static struct xfrm_dst *xfrm_bundle_lookup(struct net *net, + const struct flowi *fl, + u16 family, u8 dir, + struct xfrm_flo *xflo, u32 if_id) { struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX]; int num_pols = 0, num_xfrms = 0, err; @@ -1952,7 +1961,7 @@ xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir, /* Resolve policies to use if we couldn't get them from * previous cache entry */ num_pols = 1; - pols[0] = xfrm_policy_lookup(net, fl, family, dir); + pols[0] = xfrm_policy_lookup(net, fl, family, dir, if_id); err = xfrm_expand_policies(fl, family, pols, &num_pols, &num_xfrms); if (err < 0) @@ -2020,14 +2029,19 @@ static struct dst_entry *make_blackhole(struct net *net, u16 family, return ret; } -/* Main function: finds/creates a bundle for given flow. +/* Finds/creates a bundle for given flow and if_id * * At the moment we eat a raw IP route. Mostly to speed up lookups * on interfaces with disabled IPsec. + * + * xfrm_lookup uses an if_id of 0 by default, and is provided for + * compatibility */ -struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, - const struct flowi *fl, - const struct sock *sk, int flags) +struct dst_entry *xfrm_lookup_with_ifid(struct net *net, + struct dst_entry *dst_orig, + const struct flowi *fl, + const struct sock *sk, + int flags, u32 if_id) { struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX]; struct xfrm_dst *xdst; @@ -2043,7 +2057,8 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, sk = sk_const_to_full_sk(sk); if (sk && sk->sk_policy[XFRM_POLICY_OUT]) { num_pols = 1; - pols[0] = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl, family); + pols[0] = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl, family, + if_id); err = xfrm_expand_policies(fl, family, pols, &num_pols, &num_xfrms); if (err < 0) @@ -2087,7 +2102,7 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, !net->xfrm.policy_count[XFRM_POLICY_OUT]) goto nopol; - xdst = xfrm_bundle_lookup(net, fl, family, dir, &xflo); + xdst = xfrm_bundle_lookup(net, fl, family, dir, &xflo, if_id); if (xdst == NULL) goto nopol; if (IS_ERR(xdst)) { @@ -2168,6 +2183,19 @@ dropdst: xfrm_pols_put(pols, drop_pols); return ERR_PTR(err); } +EXPORT_SYMBOL(xfrm_lookup_with_ifid); + +/* Main function: finds/creates a bundle for given flow. + * + * At the moment we eat a raw IP route. Mostly to speed up lookups + * on interfaces with disabled IPsec. + */ +struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, + const struct flowi *fl, const struct sock *sk, + int flags) +{ + return xfrm_lookup_with_ifid(net, dst_orig, fl, sk, flags, 0); +} EXPORT_SYMBOL(xfrm_lookup); /* Callers of xfrm_lookup_route() must ensure a call to dst_output(). @@ -2257,19 +2285,12 @@ int __xfrm_decode_session(struct sk_buff *skb, struct flowi *fl, unsigned int family, int reverse) { const struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family); - const struct xfrm_if_cb *ifcb = xfrm_if_get_cb(); - struct xfrm_if *xi; int err; if (unlikely(afinfo == NULL)) return -EAFNOSUPPORT; afinfo->decode_session(skb, fl, reverse); - if (ifcb) { - xi = ifcb->decode_session(skb); - if (xi) - fl->flowi_xfrm.if_id = xi->p.if_id; - } err = security_xfrm_decode_session(skb, &fl->flowi_secid); rcu_read_unlock(); @@ -2301,6 +2322,19 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, int reverse; struct flowi fl; int xerr_idx = -1; + const struct xfrm_if_cb *ifcb; + struct xfrm_if *xi; + u32 if_id = 0; + + rcu_read_lock(); + ifcb = xfrm_if_get_cb(); + + if (ifcb) { + xi = ifcb->decode_session(skb); + if (xi) + if_id = xi->p.if_id; + } + rcu_read_unlock(); reverse = dir & ~XFRM_POLICY_MASK; dir &= XFRM_POLICY_MASK; @@ -2328,7 +2362,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, pol = NULL; sk = sk_to_full_sk(sk); if (sk && sk->sk_policy[dir]) { - pol = xfrm_sk_policy_lookup(sk, dir, &fl, family); + pol = xfrm_sk_policy_lookup(sk, dir, &fl, family, if_id); if (IS_ERR(pol)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR); return 0; @@ -2336,7 +2370,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, } if (!pol) - pol = xfrm_policy_lookup(net, &fl, family, dir); + pol = xfrm_policy_lookup(net, &fl, family, dir, if_id); if (IS_ERR(pol)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR); @@ -2360,7 +2394,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, if (pols[0]->type != XFRM_POLICY_TYPE_MAIN) { pols[1] = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN, &fl, family, - XFRM_POLICY_IN); + XFRM_POLICY_IN, if_id); if (pols[1]) { if (IS_ERR(pols[1])) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 27c84e63c7ff..bd5cb7ad2447 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -930,7 +930,7 @@ struct xfrm_state * xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, const struct flowi *fl, struct xfrm_tmpl *tmpl, struct xfrm_policy *pol, int *err, - unsigned short family) + unsigned short family, u32 if_id) { static xfrm_address_t saddr_wildcard = { }; struct net *net = xp_net(pol); @@ -940,7 +940,6 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, int error = 0; struct xfrm_state *best = NULL; u32 mark = pol->mark.v & pol->mark.m; - u32 if_id = fl->flowi_xfrm.if_id; unsigned short encap_family = tmpl->encap_family; unsigned int sequence; struct km_event c; -- cgit v1.2.3 From cbdfab3b675f4c34258b0ec9e4707de44e1f6989 Mon Sep 17 00:00:00 2001 From: Jerome Brunet Date: Tue, 17 Jul 2018 17:43:02 +0200 Subject: ASoC: export snd_soc_of_get_slot_mask Amlogic's axg card driver can't use snd_soc_of_parse_tdm_slot() directly because it needs to handle 4 mask for each direction. Yet the parsing of each mask is the same, so export snd_soc_of_get_slot_mask() to reuse the the existing code. Signed-off-by: Jerome Brunet Signed-off-by: Mark Brown --- include/sound/soc.h | 3 +++ sound/soc/soc-core.c | 7 ++++--- 2 files changed, 7 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/sound/soc.h b/include/sound/soc.h index a23ecdf3eff1..ace474e8649e 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -1433,6 +1433,9 @@ int snd_soc_of_parse_card_name(struct snd_soc_card *card, const char *propname); int snd_soc_of_parse_audio_simple_widgets(struct snd_soc_card *card, const char *propname); +int snd_soc_of_get_slot_mask(struct device_node *np, + const char *prop_name, + unsigned int *mask); int snd_soc_of_parse_tdm_slot(struct device_node *np, unsigned int *tx_mask, unsigned int *rx_mask, diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index 08e189485009..ad5b0ef16d82 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -3428,9 +3428,9 @@ int snd_soc_of_parse_audio_simple_widgets(struct snd_soc_card *card, } EXPORT_SYMBOL_GPL(snd_soc_of_parse_audio_simple_widgets); -static int snd_soc_of_get_slot_mask(struct device_node *np, - const char *prop_name, - unsigned int *mask) +int snd_soc_of_get_slot_mask(struct device_node *np, + const char *prop_name, + unsigned int *mask) { u32 val; const __be32 *of_slot_mask = of_get_property(np, prop_name, &val); @@ -3445,6 +3445,7 @@ static int snd_soc_of_get_slot_mask(struct device_node *np, return val; } +EXPORT_SYMBOL_GPL(snd_soc_of_get_slot_mask); int snd_soc_of_parse_tdm_slot(struct device_node *np, unsigned int *tx_mask, -- cgit v1.2.3 From eef5ba1aa148ca5e6deb1e0aa1de797fa4e12cb7 Mon Sep 17 00:00:00 2001 From: Peter Rosin Date: Wed, 20 Jun 2018 10:51:53 +0200 Subject: i2c: smbus: add unlocked __i2c_smbus_xfer variant Removes all locking from i2c_smbus_xfer and renames it to __i2c_smbus_xfer, then adds a new i2c_smbus_xfer function that simply grabs the lock while calling the unlocked variant. This is not perfectly equivalent, since i2c_smbus_xfer was callable from atomic/irq context if you happened to end up emulating SMBus with an I2C transfer, and that is no longer the case with this patch. It is unknown (to me) if anything depends on that quirk, but it seems fragile enough to simply break those cases and require them to call i2c_transfer directly instead. While at it, for consistency rename the 2nd to last argument (size) of the i2c_smbus_xfer declaration to protocol and remove the surplus extern marker. Signed-off-by: Peter Rosin Signed-off-by: Wolfram Sang --- drivers/i2c/i2c-core-smbus.c | 28 ++++++++++++++++++++-------- include/linux/i2c.h | 11 ++++++++--- 2 files changed, 28 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/drivers/i2c/i2c-core-smbus.c b/drivers/i2c/i2c-core-smbus.c index 51970bae3c4a..9cd66cabb84f 100644 --- a/drivers/i2c/i2c-core-smbus.c +++ b/drivers/i2c/i2c-core-smbus.c @@ -463,7 +463,7 @@ static s32 i2c_smbus_xfer_emulated(struct i2c_adapter *adapter, u16 addr, msg[num-1].len++; } - status = i2c_transfer(adapter, msg, num); + status = __i2c_transfer(adapter, msg, num); if (status < 0) goto cleanup; if (status != num) { @@ -524,9 +524,24 @@ cleanup: * This executes an SMBus protocol operation, and returns a negative * errno code else zero on success. */ -s32 i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr, unsigned short flags, - char read_write, u8 command, int protocol, - union i2c_smbus_data *data) +s32 i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr, + unsigned short flags, char read_write, + u8 command, int protocol, union i2c_smbus_data *data) +{ + s32 res; + + i2c_lock_bus(adapter, I2C_LOCK_SEGMENT); + res = __i2c_smbus_xfer(adapter, addr, flags, read_write, + command, protocol, data); + i2c_unlock_bus(adapter, I2C_LOCK_SEGMENT); + + return res; +} +EXPORT_SYMBOL(i2c_smbus_xfer); + +s32 __i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr, + unsigned short flags, char read_write, + u8 command, int protocol, union i2c_smbus_data *data) { unsigned long orig_jiffies; int try; @@ -543,8 +558,6 @@ s32 i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr, unsigned short flags, flags &= I2C_M_TEN | I2C_CLIENT_PEC | I2C_CLIENT_SCCB; if (adapter->algo->smbus_xfer) { - i2c_lock_bus(adapter, I2C_LOCK_SEGMENT); - /* Retry automatically on arbitration loss */ orig_jiffies = jiffies; for (res = 0, try = 0; try <= adapter->retries; try++) { @@ -557,7 +570,6 @@ s32 i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr, unsigned short flags, orig_jiffies + adapter->timeout)) break; } - i2c_unlock_bus(adapter, I2C_LOCK_SEGMENT); if (res != -EOPNOTSUPP || !adapter->algo->master_xfer) goto trace; @@ -579,7 +591,7 @@ trace: return res; } -EXPORT_SYMBOL(i2c_smbus_xfer); +EXPORT_SYMBOL(__i2c_smbus_xfer); /** * i2c_smbus_read_i2c_block_data_or_emulated - read block or emulate diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 254cd34eeae2..465afb092fa7 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -140,9 +140,14 @@ extern int __i2c_transfer(struct i2c_adapter *adap, struct i2c_msg *msgs, and probably just as fast. Note that we use i2c_adapter here, because you do not need a specific smbus adapter to call this function. */ -extern s32 i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr, - unsigned short flags, char read_write, u8 command, - int size, union i2c_smbus_data *data); +s32 i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr, + unsigned short flags, char read_write, u8 command, + int protocol, union i2c_smbus_data *data); + +/* Unlocked flavor */ +s32 __i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr, + unsigned short flags, char read_write, u8 command, + int protocol, union i2c_smbus_data *data); /* Now follow the 'nice' access routines. These also document the calling conventions of i2c_smbus_xfer. */ -- cgit v1.2.3 From 488dee96bb62f0b3d9e678cf42574034d5b033a5 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Fri, 20 Jul 2018 21:56:47 +0000 Subject: kernfs: allow creating kernfs objects with arbitrary uid/gid This change allows creating kernfs files and directories with arbitrary uid/gid instead of always using GLOBAL_ROOT_UID/GID by extending kernfs_create_dir_ns() and kernfs_create_file_ns() with uid/gid arguments. The "simple" kernfs_create_file() and kernfs_create_dir() are left alone and always create objects belonging to the global root. When creating symlinks ownership (uid/gid) is taken from the target kernfs object. Co-Developed-by: Tyler Hicks Signed-off-by: Dmitry Torokhov Signed-off-by: Tyler Hicks Signed-off-by: David S. Miller --- arch/x86/kernel/cpu/intel_rdt_rdtgroup.c | 4 +++- fs/kernfs/dir.c | 29 ++++++++++++++++++++++++++--- fs/kernfs/file.c | 8 ++++++-- fs/kernfs/inode.c | 2 +- fs/kernfs/kernfs-internal.h | 2 ++ fs/kernfs/symlink.c | 11 ++++++++++- fs/sysfs/dir.c | 4 +++- fs/sysfs/file.c | 5 +++-- include/linux/kernfs.h | 28 +++++++++++++++++++--------- kernel/cgroup/cgroup.c | 4 +++- 10 files changed, 76 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c index 749856a2e736..9af1a21265d3 100644 --- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -146,6 +146,7 @@ static int rdtgroup_add_file(struct kernfs_node *parent_kn, struct rftype *rft) int ret; kn = __kernfs_create_file(parent_kn, rft->name, rft->mode, + GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, 0, rft->kf_ops, rft, NULL, NULL); if (IS_ERR(kn)) return PTR_ERR(kn); @@ -1503,7 +1504,8 @@ static int mon_addfile(struct kernfs_node *parent_kn, const char *name, struct kernfs_node *kn; int ret = 0; - kn = __kernfs_create_file(parent_kn, name, 0444, 0, + kn = __kernfs_create_file(parent_kn, name, 0444, + GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, 0, &kf_mondata_ops, priv, NULL, NULL); if (IS_ERR(kn)) return PTR_ERR(kn); diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index d66cc0777303..4ca0b5c18192 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -619,6 +619,7 @@ struct kernfs_node *kernfs_node_from_dentry(struct dentry *dentry) static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root, const char *name, umode_t mode, + kuid_t uid, kgid_t gid, unsigned flags) { struct kernfs_node *kn; @@ -661,8 +662,22 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root, kn->mode = mode; kn->flags = flags; + if (!uid_eq(uid, GLOBAL_ROOT_UID) || !gid_eq(gid, GLOBAL_ROOT_GID)) { + struct iattr iattr = { + .ia_valid = ATTR_UID | ATTR_GID, + .ia_uid = uid, + .ia_gid = gid, + }; + + ret = __kernfs_setattr(kn, &iattr); + if (ret < 0) + goto err_out3; + } + return kn; + err_out3: + idr_remove(&root->ino_idr, kn->id.ino); err_out2: kmem_cache_free(kernfs_node_cache, kn); err_out1: @@ -672,11 +687,13 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root, struct kernfs_node *kernfs_new_node(struct kernfs_node *parent, const char *name, umode_t mode, + kuid_t uid, kgid_t gid, unsigned flags) { struct kernfs_node *kn; - kn = __kernfs_new_node(kernfs_root(parent), name, mode, flags); + kn = __kernfs_new_node(kernfs_root(parent), + name, mode, uid, gid, flags); if (kn) { kernfs_get(parent); kn->parent = parent; @@ -946,6 +963,7 @@ struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops, root->next_generation = 1; kn = __kernfs_new_node(root, "", S_IFDIR | S_IRUGO | S_IXUGO, + GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, KERNFS_DIR); if (!kn) { idr_destroy(&root->ino_idr); @@ -984,6 +1002,8 @@ void kernfs_destroy_root(struct kernfs_root *root) * @parent: parent in which to create a new directory * @name: name of the new directory * @mode: mode of the new directory + * @uid: uid of the new directory + * @gid: gid of the new directory * @priv: opaque data associated with the new directory * @ns: optional namespace tag of the directory * @@ -991,13 +1011,15 @@ void kernfs_destroy_root(struct kernfs_root *root) */ struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent, const char *name, umode_t mode, + kuid_t uid, kgid_t gid, void *priv, const void *ns) { struct kernfs_node *kn; int rc; /* allocate */ - kn = kernfs_new_node(parent, name, mode | S_IFDIR, KERNFS_DIR); + kn = kernfs_new_node(parent, name, mode | S_IFDIR, + uid, gid, KERNFS_DIR); if (!kn) return ERR_PTR(-ENOMEM); @@ -1028,7 +1050,8 @@ struct kernfs_node *kernfs_create_empty_dir(struct kernfs_node *parent, int rc; /* allocate */ - kn = kernfs_new_node(parent, name, S_IRUGO|S_IXUGO|S_IFDIR, KERNFS_DIR); + kn = kernfs_new_node(parent, name, S_IRUGO|S_IXUGO|S_IFDIR, + GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, KERNFS_DIR); if (!kn) return ERR_PTR(-ENOMEM); diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index 2015d8c45e4a..dbf5bc250bfd 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -965,6 +965,8 @@ const struct file_operations kernfs_file_fops = { * @parent: directory to create the file in * @name: name of the file * @mode: mode of the file + * @uid: uid of the file + * @gid: gid of the file * @size: size of the file * @ops: kernfs operations for the file * @priv: private data for the file @@ -975,7 +977,8 @@ const struct file_operations kernfs_file_fops = { */ struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent, const char *name, - umode_t mode, loff_t size, + umode_t mode, kuid_t uid, kgid_t gid, + loff_t size, const struct kernfs_ops *ops, void *priv, const void *ns, struct lock_class_key *key) @@ -986,7 +989,8 @@ struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent, flags = KERNFS_FILE; - kn = kernfs_new_node(parent, name, (mode & S_IALLUGO) | S_IFREG, flags); + kn = kernfs_new_node(parent, name, (mode & S_IALLUGO) | S_IFREG, + uid, gid, flags); if (!kn) return ERR_PTR(-ENOMEM); diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index 3d73fe9d56e2..80cebcd94c90 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -63,7 +63,7 @@ out_unlock: return ret; } -static int __kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr) +int __kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr) { struct kernfs_iattrs *attrs; struct iattr *iattrs; diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h index 0f260dcca177..3d83b114bb08 100644 --- a/fs/kernfs/kernfs-internal.h +++ b/fs/kernfs/kernfs-internal.h @@ -90,6 +90,7 @@ int kernfs_iop_setattr(struct dentry *dentry, struct iattr *iattr); int kernfs_iop_getattr(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags); ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size); +int __kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr); /* * dir.c @@ -104,6 +105,7 @@ void kernfs_put_active(struct kernfs_node *kn); int kernfs_add_one(struct kernfs_node *kn); struct kernfs_node *kernfs_new_node(struct kernfs_node *parent, const char *name, umode_t mode, + kuid_t uid, kgid_t gid, unsigned flags); struct kernfs_node *kernfs_find_and_get_node_by_ino(struct kernfs_root *root, unsigned int ino); diff --git a/fs/kernfs/symlink.c b/fs/kernfs/symlink.c index 08ccabd7047f..5ffed48f3d0e 100644 --- a/fs/kernfs/symlink.c +++ b/fs/kernfs/symlink.c @@ -21,6 +21,7 @@ * @target: target node for the symlink to point to * * Returns the created node on success, ERR_PTR() value on error. + * Ownership of the link matches ownership of the target. */ struct kernfs_node *kernfs_create_link(struct kernfs_node *parent, const char *name, @@ -28,8 +29,16 @@ struct kernfs_node *kernfs_create_link(struct kernfs_node *parent, { struct kernfs_node *kn; int error; + kuid_t uid = GLOBAL_ROOT_UID; + kgid_t gid = GLOBAL_ROOT_GID; - kn = kernfs_new_node(parent, name, S_IFLNK|S_IRWXUGO, KERNFS_LINK); + if (target->iattr) { + uid = target->iattr->ia_iattr.ia_uid; + gid = target->iattr->ia_iattr.ia_gid; + } + + kn = kernfs_new_node(parent, name, S_IFLNK|S_IRWXUGO, uid, gid, + KERNFS_LINK); if (!kn) return ERR_PTR(-ENOMEM); diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c index 58eba92a0e41..e39b884f0867 100644 --- a/fs/sysfs/dir.c +++ b/fs/sysfs/dir.c @@ -52,7 +52,9 @@ int sysfs_create_dir_ns(struct kobject *kobj, const void *ns) return -ENOENT; kn = kernfs_create_dir_ns(parent, kobject_name(kobj), - S_IRWXU | S_IRUGO | S_IXUGO, kobj, ns); + S_IRWXU | S_IRUGO | S_IXUGO, + GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, + kobj, ns); if (IS_ERR(kn)) { if (PTR_ERR(kn) == -EEXIST) sysfs_warn_dup(parent, kobject_name(kobj)); diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 5c13f29bfcdb..513fa691ecbd 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -302,8 +302,9 @@ int sysfs_add_file_mode_ns(struct kernfs_node *parent, if (!attr->ignore_lockdep) key = attr->key ?: (struct lock_class_key *)&attr->skey; #endif - kn = __kernfs_create_file(parent, attr->name, mode & 0777, size, ops, - (void *)attr, ns, key); + kn = __kernfs_create_file(parent, attr->name, + mode & 0777, GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, + size, ops, (void *)attr, ns, key); if (IS_ERR(kn)) { if (PTR_ERR(kn) == -EEXIST) sysfs_warn_dup(parent, attr->name); diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index ab25c8b6d9e3..814643f7ee52 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -15,6 +15,7 @@ #include #include #include +#include #include struct file; @@ -325,12 +326,14 @@ void kernfs_destroy_root(struct kernfs_root *root); struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent, const char *name, umode_t mode, + kuid_t uid, kgid_t gid, void *priv, const void *ns); struct kernfs_node *kernfs_create_empty_dir(struct kernfs_node *parent, const char *name); struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent, - const char *name, - umode_t mode, loff_t size, + const char *name, umode_t mode, + kuid_t uid, kgid_t gid, + loff_t size, const struct kernfs_ops *ops, void *priv, const void *ns, struct lock_class_key *key); @@ -415,12 +418,14 @@ static inline void kernfs_destroy_root(struct kernfs_root *root) { } static inline struct kernfs_node * kernfs_create_dir_ns(struct kernfs_node *parent, const char *name, - umode_t mode, void *priv, const void *ns) + umode_t mode, kuid_t uid, kgid_t gid, + void *priv, const void *ns) { return ERR_PTR(-ENOSYS); } static inline struct kernfs_node * __kernfs_create_file(struct kernfs_node *parent, const char *name, - umode_t mode, loff_t size, const struct kernfs_ops *ops, + umode_t mode, kuid_t uid, kgid_t gid, + loff_t size, const struct kernfs_ops *ops, void *priv, const void *ns, struct lock_class_key *key) { return ERR_PTR(-ENOSYS); } @@ -498,12 +503,15 @@ static inline struct kernfs_node * kernfs_create_dir(struct kernfs_node *parent, const char *name, umode_t mode, void *priv) { - return kernfs_create_dir_ns(parent, name, mode, priv, NULL); + return kernfs_create_dir_ns(parent, name, mode, + GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, + priv, NULL); } static inline struct kernfs_node * kernfs_create_file_ns(struct kernfs_node *parent, const char *name, - umode_t mode, loff_t size, const struct kernfs_ops *ops, + umode_t mode, kuid_t uid, kgid_t gid, + loff_t size, const struct kernfs_ops *ops, void *priv, const void *ns) { struct lock_class_key *key = NULL; @@ -511,15 +519,17 @@ kernfs_create_file_ns(struct kernfs_node *parent, const char *name, #ifdef CONFIG_DEBUG_LOCK_ALLOC key = (struct lock_class_key *)&ops->lockdep_key; #endif - return __kernfs_create_file(parent, name, mode, size, ops, priv, ns, - key); + return __kernfs_create_file(parent, name, mode, uid, gid, + size, ops, priv, ns, key); } static inline struct kernfs_node * kernfs_create_file(struct kernfs_node *parent, const char *name, umode_t mode, loff_t size, const struct kernfs_ops *ops, void *priv) { - return kernfs_create_file_ns(parent, name, mode, size, ops, priv, NULL); + return kernfs_create_file_ns(parent, name, mode, + GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, + size, ops, priv, NULL); } static inline int kernfs_remove_by_name(struct kernfs_node *parent, diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 077370bf8964..35cf3d71f8aa 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3557,7 +3557,9 @@ static int cgroup_add_file(struct cgroup_subsys_state *css, struct cgroup *cgrp, key = &cft->lockdep_key; #endif kn = __kernfs_create_file(cgrp->kn, cgroup_file_name(cgrp, cft, name), - cgroup_file_mode(cft), 0, cft->kf_ops, cft, + cgroup_file_mode(cft), + GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, + 0, cft->kf_ops, cft, NULL, key); if (IS_ERR(kn)) return PTR_ERR(kn); -- cgit v1.2.3 From 5f81880d5204ee2388fd9a75bb850ccd526885b7 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Fri, 20 Jul 2018 21:56:48 +0000 Subject: sysfs, kobject: allow creating kobject belonging to arbitrary users Normally kobjects and their sysfs representation belong to global root, however it is not necessarily the case for objects in separate namespaces. For example, objects in separate network namespace logically belong to the container's root and not global root. This change lays groundwork for allowing network namespace objects ownership to be transferred to container's root user by defining get_ownership() callback in ktype structure and using it in sysfs code to retrieve desired uid/gid when creating sysfs objects for given kobject. Co-Developed-by: Tyler Hicks Signed-off-by: Dmitry Torokhov Signed-off-by: Tyler Hicks Signed-off-by: David S. Miller --- fs/sysfs/dir.c | 7 +++++-- fs/sysfs/file.c | 32 ++++++++++++++++++++------------ fs/sysfs/group.c | 23 +++++++++++++++++------ fs/sysfs/sysfs.h | 5 ++--- include/linux/kobject.h | 4 ++++ lib/kobject.c | 19 +++++++++++++++++++ 6 files changed, 67 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c index e39b884f0867..feeae8081c22 100644 --- a/fs/sysfs/dir.c +++ b/fs/sysfs/dir.c @@ -40,6 +40,8 @@ void sysfs_warn_dup(struct kernfs_node *parent, const char *name) int sysfs_create_dir_ns(struct kobject *kobj, const void *ns) { struct kernfs_node *parent, *kn; + kuid_t uid; + kgid_t gid; BUG_ON(!kobj); @@ -51,9 +53,10 @@ int sysfs_create_dir_ns(struct kobject *kobj, const void *ns) if (!parent) return -ENOENT; + kobject_get_ownership(kobj, &uid, &gid); + kn = kernfs_create_dir_ns(parent, kobject_name(kobj), - S_IRWXU | S_IRUGO | S_IXUGO, - GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, + S_IRWXU | S_IRUGO | S_IXUGO, uid, gid, kobj, ns); if (IS_ERR(kn)) { if (PTR_ERR(kn) == -EEXIST) diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 513fa691ecbd..fa46216523cf 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -245,7 +245,7 @@ static const struct kernfs_ops sysfs_bin_kfops_mmap = { int sysfs_add_file_mode_ns(struct kernfs_node *parent, const struct attribute *attr, bool is_bin, - umode_t mode, const void *ns) + umode_t mode, kuid_t uid, kgid_t gid, const void *ns) { struct lock_class_key *key = NULL; const struct kernfs_ops *ops; @@ -302,8 +302,8 @@ int sysfs_add_file_mode_ns(struct kernfs_node *parent, if (!attr->ignore_lockdep) key = attr->key ?: (struct lock_class_key *)&attr->skey; #endif - kn = __kernfs_create_file(parent, attr->name, - mode & 0777, GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, + + kn = __kernfs_create_file(parent, attr->name, mode & 0777, uid, gid, size, ops, (void *)attr, ns, key); if (IS_ERR(kn)) { if (PTR_ERR(kn) == -EEXIST) @@ -313,12 +313,6 @@ int sysfs_add_file_mode_ns(struct kernfs_node *parent, return 0; } -int sysfs_add_file(struct kernfs_node *parent, const struct attribute *attr, - bool is_bin) -{ - return sysfs_add_file_mode_ns(parent, attr, is_bin, attr->mode, NULL); -} - /** * sysfs_create_file_ns - create an attribute file for an object with custom ns * @kobj: object we're creating for @@ -328,9 +322,14 @@ int sysfs_add_file(struct kernfs_node *parent, const struct attribute *attr, int sysfs_create_file_ns(struct kobject *kobj, const struct attribute *attr, const void *ns) { + kuid_t uid; + kgid_t gid; + BUG_ON(!kobj || !kobj->sd || !attr); - return sysfs_add_file_mode_ns(kobj->sd, attr, false, attr->mode, ns); + kobject_get_ownership(kobj, &uid, &gid); + return sysfs_add_file_mode_ns(kobj->sd, attr, false, attr->mode, + uid, gid, ns); } EXPORT_SYMBOL_GPL(sysfs_create_file_ns); @@ -359,6 +358,8 @@ int sysfs_add_file_to_group(struct kobject *kobj, const struct attribute *attr, const char *group) { struct kernfs_node *parent; + kuid_t uid; + kgid_t gid; int error; if (group) { @@ -371,7 +372,9 @@ int sysfs_add_file_to_group(struct kobject *kobj, if (!parent) return -ENOENT; - error = sysfs_add_file(parent, attr, false); + kobject_get_ownership(kobj, &uid, &gid); + error = sysfs_add_file_mode_ns(kobj->sd, attr, false, + attr->mode, uid, gid, NULL); kernfs_put(parent); return error; @@ -487,9 +490,14 @@ EXPORT_SYMBOL_GPL(sysfs_remove_file_from_group); int sysfs_create_bin_file(struct kobject *kobj, const struct bin_attribute *attr) { + kuid_t uid; + kgid_t gid; + BUG_ON(!kobj || !kobj->sd || !attr); - return sysfs_add_file(kobj->sd, &attr->attr, true); + kobject_get_ownership(kobj, &uid, &gid); + return sysfs_add_file_mode_ns(kobj->sd, &attr->attr, true, + attr->attr.mode, uid, gid, NULL); } EXPORT_SYMBOL_GPL(sysfs_create_bin_file); diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c index 4802ec0e1e3a..c7a716c4acc9 100644 --- a/fs/sysfs/group.c +++ b/fs/sysfs/group.c @@ -31,6 +31,7 @@ static void remove_files(struct kernfs_node *parent, } static int create_files(struct kernfs_node *parent, struct kobject *kobj, + kuid_t uid, kgid_t gid, const struct attribute_group *grp, int update) { struct attribute *const *attr; @@ -60,7 +61,7 @@ static int create_files(struct kernfs_node *parent, struct kobject *kobj, mode &= SYSFS_PREALLOC | 0664; error = sysfs_add_file_mode_ns(parent, *attr, false, - mode, NULL); + mode, uid, gid, NULL); if (unlikely(error)) break; } @@ -90,7 +91,8 @@ static int create_files(struct kernfs_node *parent, struct kobject *kobj, mode &= SYSFS_PREALLOC | 0664; error = sysfs_add_file_mode_ns(parent, &(*bin_attr)->attr, true, - mode, NULL); + mode, + uid, gid, NULL); if (error) break; } @@ -106,6 +108,8 @@ static int internal_create_group(struct kobject *kobj, int update, const struct attribute_group *grp) { struct kernfs_node *kn; + kuid_t uid; + kgid_t gid; int error; BUG_ON(!kobj || (!update && !kobj->sd)); @@ -118,9 +122,11 @@ static int internal_create_group(struct kobject *kobj, int update, kobj->name, grp->name ?: ""); return -EINVAL; } + kobject_get_ownership(kobj, &uid, &gid); if (grp->name) { - kn = kernfs_create_dir(kobj->sd, grp->name, - S_IRWXU | S_IRUGO | S_IXUGO, kobj); + kn = kernfs_create_dir_ns(kobj->sd, grp->name, + S_IRWXU | S_IRUGO | S_IXUGO, + uid, gid, kobj, NULL); if (IS_ERR(kn)) { if (PTR_ERR(kn) == -EEXIST) sysfs_warn_dup(kobj->sd, grp->name); @@ -129,7 +135,7 @@ static int internal_create_group(struct kobject *kobj, int update, } else kn = kobj->sd; kernfs_get(kn); - error = create_files(kn, kobj, grp, update); + error = create_files(kn, kobj, uid, gid, grp, update); if (error) { if (grp->name) kernfs_remove(kn); @@ -281,6 +287,8 @@ int sysfs_merge_group(struct kobject *kobj, const struct attribute_group *grp) { struct kernfs_node *parent; + kuid_t uid; + kgid_t gid; int error = 0; struct attribute *const *attr; int i; @@ -289,8 +297,11 @@ int sysfs_merge_group(struct kobject *kobj, if (!parent) return -ENOENT; + kobject_get_ownership(kobj, &uid, &gid); + for ((i = 0, attr = grp->attrs); *attr && !error; (++i, ++attr)) - error = sysfs_add_file(parent, *attr, false); + error = sysfs_add_file_mode_ns(parent, *attr, false, + (*attr)->mode, uid, gid, NULL); if (error) { while (--i >= 0) kernfs_remove_by_name(parent, (*--attr)->name); diff --git a/fs/sysfs/sysfs.h b/fs/sysfs/sysfs.h index d098e015fcc9..0050cc0c0236 100644 --- a/fs/sysfs/sysfs.h +++ b/fs/sysfs/sysfs.h @@ -27,11 +27,10 @@ void sysfs_warn_dup(struct kernfs_node *parent, const char *name); /* * file.c */ -int sysfs_add_file(struct kernfs_node *parent, - const struct attribute *attr, bool is_bin); int sysfs_add_file_mode_ns(struct kernfs_node *parent, const struct attribute *attr, bool is_bin, - umode_t amode, const void *ns); + umode_t amode, kuid_t uid, kgid_t gid, + const void *ns); /* * symlink.c diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 7f6f93c3df9c..b49ff230beba 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -26,6 +26,7 @@ #include #include #include +#include #define UEVENT_HELPER_PATH_LEN 256 #define UEVENT_NUM_ENVP 32 /* number of env pointers */ @@ -114,6 +115,8 @@ extern struct kobject * __must_check kobject_get_unless_zero( extern void kobject_put(struct kobject *kobj); extern const void *kobject_namespace(struct kobject *kobj); +extern void kobject_get_ownership(struct kobject *kobj, + kuid_t *uid, kgid_t *gid); extern char *kobject_get_path(struct kobject *kobj, gfp_t flag); struct kobj_type { @@ -122,6 +125,7 @@ struct kobj_type { struct attribute **default_attrs; const struct kobj_ns_type_operations *(*child_ns_type)(struct kobject *kobj); const void *(*namespace)(struct kobject *kobj); + void (*get_ownership)(struct kobject *kobj, kuid_t *uid, kgid_t *gid); }; struct kobj_uevent_env { diff --git a/lib/kobject.c b/lib/kobject.c index 18989b5b3b56..f2dc1f756007 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -35,6 +35,25 @@ const void *kobject_namespace(struct kobject *kobj) return kobj->ktype->namespace(kobj); } +/** + * kobject_get_ownership - get sysfs ownership data for @kobj + * @kobj: kobject in question + * @uid: kernel user ID for sysfs objects + * @gid: kernel group ID for sysfs objects + * + * Returns initial uid/gid pair that should be used when creating sysfs + * representation of given kobject. Normally used to adjust ownership of + * objects in a container. + */ +void kobject_get_ownership(struct kobject *kobj, kuid_t *uid, kgid_t *gid) +{ + *uid = GLOBAL_ROOT_UID; + *gid = GLOBAL_ROOT_GID; + + if (kobj->ktype->get_ownership) + kobj->ktype->get_ownership(kobj, uid, gid); +} + /* * populate_dir - populate directory with attributes. * @kobj: object we're working on. -- cgit v1.2.3 From 9944e894c1266dc8515c82d1ff752d681215526b Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Fri, 20 Jul 2018 21:56:50 +0000 Subject: driver core: set up ownership of class devices in sysfs Plumb in get_ownership() callback for devices belonging to a class so that they can be created with uid/gid different from global root. This will allow network devices in a container to belong to container's root and not global root. Signed-off-by: Dmitry Torokhov Reviewed-by: Tyler Hicks Signed-off-by: David S. Miller --- drivers/base/core.c | 9 +++++++++ include/linux/device.h | 5 +++++ 2 files changed, 14 insertions(+) (limited to 'include') diff --git a/drivers/base/core.c b/drivers/base/core.c index df3e1a44707a..276c7e3f754c 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -866,10 +866,19 @@ static const void *device_namespace(struct kobject *kobj) return ns; } +static void device_get_ownership(struct kobject *kobj, kuid_t *uid, kgid_t *gid) +{ + struct device *dev = kobj_to_dev(kobj); + + if (dev->class && dev->class->get_ownership) + dev->class->get_ownership(dev, uid, gid); +} + static struct kobj_type device_ktype = { .release = device_release, .sysfs_ops = &dev_sysfs_ops, .namespace = device_namespace, + .get_ownership = device_get_ownership, }; diff --git a/include/linux/device.h b/include/linux/device.h index 055a69dbcd18..fe6ccb6dc119 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -384,6 +384,9 @@ int subsys_virtual_register(struct bus_type *subsys, * @shutdown_pre: Called at shut-down time before driver shutdown. * @ns_type: Callbacks so sysfs can detemine namespaces. * @namespace: Namespace of the device belongs to this class. + * @get_ownership: Allows class to specify uid/gid of the sysfs directories + * for the devices belonging to the class. Usually tied to + * device's namespace. * @pm: The default device power management operations of this class. * @p: The private data of the driver core, no one other than the * driver core can touch this. @@ -413,6 +416,8 @@ struct class { const struct kobj_ns_type_operations *ns_type; const void *(*namespace)(struct device *dev); + void (*get_ownership)(struct device *dev, kuid_t *uid, kgid_t *gid); + const struct dev_pm_ops *pm; struct subsys_private *p; -- cgit v1.2.3 From fbdeaed408cf2728c62640c10848ddb1b67e63d3 Mon Sep 17 00:00:00 2001 From: Tyler Hicks Date: Fri, 20 Jul 2018 21:56:53 +0000 Subject: net: create reusable function for getting ownership info of sysfs inodes Make net_ns_get_ownership() reusable by networking code outside of core. This is useful, for example, to allow bridge related sysfs files to be owned by container root. Add a function comment since this is a potentially dangerous function to use given the way that kobject_get_ownership() works by initializing uid and gid before calling .get_ownership(). Signed-off-by: Tyler Hicks Signed-off-by: David S. Miller --- include/net/net_namespace.h | 10 ++++++++++ net/core/net-sysfs.c | 18 ------------------ net/core/net_namespace.c | 28 ++++++++++++++++++++++++++++ 3 files changed, 38 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index a71264d75d7f..9b5fdc50519a 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -10,6 +10,7 @@ #include #include #include +#include #include #include @@ -170,6 +171,8 @@ extern struct net init_net; struct net *copy_net_ns(unsigned long flags, struct user_namespace *user_ns, struct net *old_net); +void net_ns_get_ownership(const struct net *net, kuid_t *uid, kgid_t *gid); + void net_ns_barrier(void); #else /* CONFIG_NET_NS */ #include @@ -182,6 +185,13 @@ static inline struct net *copy_net_ns(unsigned long flags, return old_net; } +static inline void net_ns_get_ownership(const struct net *net, + kuid_t *uid, kgid_t *gid) +{ + *uid = GLOBAL_ROOT_UID; + *gid = GLOBAL_ROOT_GID; +} + static inline void net_ns_barrier(void) {} #endif /* CONFIG_NET_NS */ diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index ada065fc685e..0a95bcf64cdc 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -656,24 +656,6 @@ static const struct attribute_group wireless_group = { #define net_class_groups NULL #endif /* CONFIG_SYSFS */ -static void net_ns_get_ownership(const struct net *net, - kuid_t *uid, kgid_t *gid) -{ - if (net) { - kuid_t ns_root_uid = make_kuid(net->user_ns, 0); - kgid_t ns_root_gid = make_kgid(net->user_ns, 0); - - if (uid_valid(ns_root_uid)) - *uid = ns_root_uid; - - if (gid_valid(ns_root_gid)) - *gid = ns_root_gid; - } else { - *uid = GLOBAL_ROOT_UID; - *gid = GLOBAL_ROOT_GID; - } -} - #ifdef CONFIG_SYSFS #define to_rx_queue_attr(_attr) \ container_of(_attr, struct rx_queue_attribute, attr) diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index a11e03f920d3..738871af5efa 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include @@ -448,6 +449,33 @@ dec_ucounts: return net; } +/** + * net_ns_get_ownership - get sysfs ownership data for @net + * @net: network namespace in question (can be NULL) + * @uid: kernel user ID for sysfs objects + * @gid: kernel group ID for sysfs objects + * + * Returns the uid/gid pair of root in the user namespace associated with the + * given network namespace. + */ +void net_ns_get_ownership(const struct net *net, kuid_t *uid, kgid_t *gid) +{ + if (net) { + kuid_t ns_root_uid = make_kuid(net->user_ns, 0); + kgid_t ns_root_gid = make_kgid(net->user_ns, 0); + + if (uid_valid(ns_root_uid)) + *uid = ns_root_uid; + + if (gid_valid(ns_root_gid)) + *gid = ns_root_gid; + } else { + *uid = GLOBAL_ROOT_UID; + *gid = GLOBAL_ROOT_GID; + } +} +EXPORT_SYMBOL_GPL(net_ns_get_ownership); + static void unhash_nsid(struct net *net, struct net *last) { struct net *tmp; -- cgit v1.2.3 From a3134fb09e0bc5bee76e13bf863173b86f21cf87 Mon Sep 17 00:00:00 2001 From: Rishabh Bhatnagar Date: Wed, 23 May 2018 17:35:21 -0700 Subject: drivers: soc: Add LLCC driver LLCC (Last Level Cache Controller) provides additional cache memory in the system. LLCC is partitioned into multiple slices and each slice gets its own priority, size, ID and other config parameters. LLCC driver programs these parameters for each slice. Clients that are assigned to use LLCC need to get information such size & ID of the slice they get and activate or deactivate the slice as needed. LLCC driver provides API for the clients to perform these operations. Signed-off-by: Channagoud Kadabi Signed-off-by: Rishabh Bhatnagar Reviewed-by: Evan Green Reviewed-by: Rob Herring Reviewed-by: Bjorn Andersson Signed-off-by: Andy Gross --- drivers/soc/qcom/Kconfig | 17 ++ drivers/soc/qcom/Makefile | 2 + drivers/soc/qcom/llcc-sdm845.c | 94 +++++++++++ drivers/soc/qcom/llcc-slice.c | 335 +++++++++++++++++++++++++++++++++++++ include/linux/soc/qcom/llcc-qcom.h | 180 ++++++++++++++++++++ 5 files changed, 628 insertions(+) create mode 100644 drivers/soc/qcom/llcc-sdm845.c create mode 100644 drivers/soc/qcom/llcc-slice.c create mode 100644 include/linux/soc/qcom/llcc-qcom.h (limited to 'include') diff --git a/drivers/soc/qcom/Kconfig b/drivers/soc/qcom/Kconfig index 9dc02f390ba3..d1a41852ae7a 100644 --- a/drivers/soc/qcom/Kconfig +++ b/drivers/soc/qcom/Kconfig @@ -39,6 +39,23 @@ config QCOM_GSBI functions for connecting the underlying serial UART, SPI, and I2C devices to the output pins. +config QCOM_LLCC + tristate "Qualcomm Technologies, Inc. LLCC driver" + depends on ARCH_QCOM + help + Qualcomm Technologies, Inc. platform specific + Last Level Cache Controller(LLCC) driver. This provides interfaces + to clients that use the LLCC. Say yes here to enable LLCC slice + driver. + +config QCOM_SDM845_LLCC + tristate "Qualcomm Technologies, Inc. SDM845 LLCC driver" + depends on QCOM_LLCC + help + Say yes here to enable the LLCC driver for SDM845. This provides + data required to configure LLCC so that clients can start using the + LLCC slices. + config QCOM_MDT_LOADER tristate select QCOM_SCM diff --git a/drivers/soc/qcom/Makefile b/drivers/soc/qcom/Makefile index 19dcf957cb3a..5921454c4ddd 100644 --- a/drivers/soc/qcom/Makefile +++ b/drivers/soc/qcom/Makefile @@ -15,3 +15,5 @@ obj-$(CONFIG_QCOM_SMP2P) += smp2p.o obj-$(CONFIG_QCOM_SMSM) += smsm.o obj-$(CONFIG_QCOM_WCNSS_CTRL) += wcnss_ctrl.o obj-$(CONFIG_QCOM_APR) += apr.o +obj-$(CONFIG_QCOM_LLCC) += llcc-slice.o +obj-$(CONFIG_QCOM_SDM845_LLCC) += llcc-sdm845.o diff --git a/drivers/soc/qcom/llcc-sdm845.c b/drivers/soc/qcom/llcc-sdm845.c new file mode 100644 index 000000000000..2e1e4f0a5db8 --- /dev/null +++ b/drivers/soc/qcom/llcc-sdm845.c @@ -0,0 +1,94 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2017-2018, The Linux Foundation. All rights reserved. + * + */ + +#include +#include +#include +#include +#include + +/* + * SCT(System Cache Table) entry contains of the following members: + * usecase_id: Unique id for the client's use case + * slice_id: llcc slice id for each client + * max_cap: The maximum capacity of the cache slice provided in KB + * priority: Priority of the client used to select victim line for replacement + * fixed_size: Boolean indicating if the slice has a fixed capacity + * bonus_ways: Bonus ways are additional ways to be used for any slice, + * if client ends up using more than reserved cache ways. Bonus + * ways are allocated only if they are not reserved for some + * other client. + * res_ways: Reserved ways for the cache slice, the reserved ways cannot + * be used by any other client than the one its assigned to. + * cache_mode: Each slice operates as a cache, this controls the mode of the + * slice: normal or TCM(Tightly Coupled Memory) + * probe_target_ways: Determines what ways to probe for access hit. When + * configured to 1 only bonus and reserved ways are probed. + * When configured to 0 all ways in llcc are probed. + * dis_cap_alloc: Disable capacity based allocation for a client + * retain_on_pc: If this bit is set and client has maintained active vote + * then the ways assigned to this client are not flushed on power + * collapse. + * activate_on_init: Activate the slice immediately after the SCT is programmed + */ +#define SCT_ENTRY(uid, sid, mc, p, fs, bway, rway, cmod, ptw, dca, rp, a) \ + { \ + .usecase_id = uid, \ + .slice_id = sid, \ + .max_cap = mc, \ + .priority = p, \ + .fixed_size = fs, \ + .bonus_ways = bway, \ + .res_ways = rway, \ + .cache_mode = cmod, \ + .probe_target_ways = ptw, \ + .dis_cap_alloc = dca, \ + .retain_on_pc = rp, \ + .activate_on_init = a, \ + } + +static struct llcc_slice_config sdm845_data[] = { + SCT_ENTRY(LLCC_CPUSS, 1, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 1), + SCT_ENTRY(LLCC_VIDSC0, 2, 512, 2, 1, 0x0, 0x0f0, 0, 0, 1, 1, 0), + SCT_ENTRY(LLCC_VIDSC1, 3, 512, 2, 1, 0x0, 0x0f0, 0, 0, 1, 1, 0), + SCT_ENTRY(LLCC_ROTATOR, 4, 563, 2, 1, 0x0, 0x00e, 2, 0, 1, 1, 0), + SCT_ENTRY(LLCC_VOICE, 5, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 0), + SCT_ENTRY(LLCC_AUDIO, 6, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 0), + SCT_ENTRY(LLCC_MDMHPGRW, 7, 1024, 2, 0, 0xfc, 0xf00, 0, 0, 1, 1, 0), + SCT_ENTRY(LLCC_MDM, 8, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 0), + SCT_ENTRY(LLCC_CMPT, 10, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 0), + SCT_ENTRY(LLCC_GPUHTW, 11, 512, 1, 1, 0xc, 0x0, 0, 0, 1, 1, 0), + SCT_ENTRY(LLCC_GPU, 12, 2304, 1, 0, 0xff0, 0x2, 0, 0, 1, 1, 0), + SCT_ENTRY(LLCC_MMUHWT, 13, 256, 2, 0, 0x0, 0x1, 0, 0, 1, 0, 1), + SCT_ENTRY(LLCC_CMPTDMA, 15, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 0), + SCT_ENTRY(LLCC_DISP, 16, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 0), + SCT_ENTRY(LLCC_VIDFW, 17, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 0), + SCT_ENTRY(LLCC_MDMHPFX, 20, 1024, 2, 1, 0x0, 0xf00, 0, 0, 1, 1, 0), + SCT_ENTRY(LLCC_MDMPNG, 21, 1024, 0, 1, 0x1e, 0x0, 0, 0, 1, 1, 0), + SCT_ENTRY(LLCC_AUDHW, 22, 1024, 1, 1, 0xffc, 0x2, 0, 0, 1, 1, 0), +}; + +static int sdm845_qcom_llcc_probe(struct platform_device *pdev) +{ + return qcom_llcc_probe(pdev, sdm845_data, ARRAY_SIZE(sdm845_data)); +} + +static const struct of_device_id sdm845_qcom_llcc_of_match[] = { + { .compatible = "qcom,sdm845-llcc", }, + { } +}; + +static struct platform_driver sdm845_qcom_llcc_driver = { + .driver = { + .name = "sdm845-llcc", + .of_match_table = sdm845_qcom_llcc_of_match, + }, + .probe = sdm845_qcom_llcc_probe, +}; +module_platform_driver(sdm845_qcom_llcc_driver); + +MODULE_DESCRIPTION("QCOM sdm845 LLCC driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/soc/qcom/llcc-slice.c b/drivers/soc/qcom/llcc-slice.c new file mode 100644 index 000000000000..fcaad1a4b41d --- /dev/null +++ b/drivers/soc/qcom/llcc-slice.c @@ -0,0 +1,335 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2017-2018, The Linux Foundation. All rights reserved. + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define ACTIVATE BIT(0) +#define DEACTIVATE BIT(1) +#define ACT_CTRL_OPCODE_ACTIVATE BIT(0) +#define ACT_CTRL_OPCODE_DEACTIVATE BIT(1) +#define ACT_CTRL_ACT_TRIG BIT(0) +#define ACT_CTRL_OPCODE_SHIFT 0x01 +#define ATTR1_PROBE_TARGET_WAYS_SHIFT 0x02 +#define ATTR1_FIXED_SIZE_SHIFT 0x03 +#define ATTR1_PRIORITY_SHIFT 0x04 +#define ATTR1_MAX_CAP_SHIFT 0x10 +#define ATTR0_RES_WAYS_MASK GENMASK(11, 0) +#define ATTR0_BONUS_WAYS_MASK GENMASK(27, 16) +#define ATTR0_BONUS_WAYS_SHIFT 0x10 +#define LLCC_STATUS_READ_DELAY 100 + +#define CACHE_LINE_SIZE_SHIFT 6 + +#define LLCC_COMMON_STATUS0 0x0003000c +#define LLCC_LB_CNT_MASK GENMASK(31, 28) +#define LLCC_LB_CNT_SHIFT 28 + +#define MAX_CAP_TO_BYTES(n) (n * SZ_1K) +#define LLCC_TRP_ACT_CTRLn(n) (n * SZ_4K) +#define LLCC_TRP_STATUSn(n) (4 + n * SZ_4K) +#define LLCC_TRP_ATTR0_CFGn(n) (0x21000 + SZ_8 * n) +#define LLCC_TRP_ATTR1_CFGn(n) (0x21004 + SZ_8 * n) + +#define BANK_OFFSET_STRIDE 0x80000 + +static struct llcc_drv_data *drv_data; + +static const struct regmap_config llcc_regmap_config = { + .reg_bits = 32, + .reg_stride = 4, + .val_bits = 32, + .fast_io = true, +}; + +/** + * llcc_slice_getd - get llcc slice descriptor + * @uid: usecase_id for the client + * + * A pointer to llcc slice descriptor will be returned on success and + * and error pointer is returned on failure + */ +struct llcc_slice_desc *llcc_slice_getd(u32 uid) +{ + const struct llcc_slice_config *cfg; + struct llcc_slice_desc *desc; + u32 sz, count; + + cfg = drv_data->cfg; + sz = drv_data->cfg_size; + + for (count = 0; cfg && count < sz; count++, cfg++) + if (cfg->usecase_id == uid) + break; + + if (count == sz || !cfg) + return ERR_PTR(-ENODEV); + + desc = kzalloc(sizeof(*desc), GFP_KERNEL); + if (!desc) + return ERR_PTR(-ENOMEM); + + desc->slice_id = cfg->slice_id; + desc->slice_size = cfg->max_cap; + + return desc; +} +EXPORT_SYMBOL_GPL(llcc_slice_getd); + +/** + * llcc_slice_putd - llcc slice descritpor + * @desc: Pointer to llcc slice descriptor + */ +void llcc_slice_putd(struct llcc_slice_desc *desc) +{ + kfree(desc); +} +EXPORT_SYMBOL_GPL(llcc_slice_putd); + +static int llcc_update_act_ctrl(u32 sid, + u32 act_ctrl_reg_val, u32 status) +{ + u32 act_ctrl_reg; + u32 status_reg; + u32 slice_status; + int ret; + + act_ctrl_reg = drv_data->bcast_off + LLCC_TRP_ACT_CTRLn(sid); + status_reg = drv_data->bcast_off + LLCC_TRP_STATUSn(sid); + + /* Set the ACTIVE trigger */ + act_ctrl_reg_val |= ACT_CTRL_ACT_TRIG; + ret = regmap_write(drv_data->regmap, act_ctrl_reg, act_ctrl_reg_val); + if (ret) + return ret; + + /* Clear the ACTIVE trigger */ + act_ctrl_reg_val &= ~ACT_CTRL_ACT_TRIG; + ret = regmap_write(drv_data->regmap, act_ctrl_reg, act_ctrl_reg_val); + if (ret) + return ret; + + ret = regmap_read_poll_timeout(drv_data->regmap, status_reg, + slice_status, !(slice_status & status), + 0, LLCC_STATUS_READ_DELAY); + return ret; +} + +/** + * llcc_slice_activate - Activate the llcc slice + * @desc: Pointer to llcc slice descriptor + * + * A value of zero will be returned on success and a negative errno will + * be returned in error cases + */ +int llcc_slice_activate(struct llcc_slice_desc *desc) +{ + int ret; + u32 act_ctrl_val; + + mutex_lock(&drv_data->lock); + if (test_bit(desc->slice_id, drv_data->bitmap)) { + mutex_unlock(&drv_data->lock); + return 0; + } + + act_ctrl_val = ACT_CTRL_OPCODE_ACTIVATE << ACT_CTRL_OPCODE_SHIFT; + + ret = llcc_update_act_ctrl(desc->slice_id, act_ctrl_val, + DEACTIVATE); + if (ret) { + mutex_unlock(&drv_data->lock); + return ret; + } + + __set_bit(desc->slice_id, drv_data->bitmap); + mutex_unlock(&drv_data->lock); + + return ret; +} +EXPORT_SYMBOL_GPL(llcc_slice_activate); + +/** + * llcc_slice_deactivate - Deactivate the llcc slice + * @desc: Pointer to llcc slice descriptor + * + * A value of zero will be returned on success and a negative errno will + * be returned in error cases + */ +int llcc_slice_deactivate(struct llcc_slice_desc *desc) +{ + u32 act_ctrl_val; + int ret; + + mutex_lock(&drv_data->lock); + if (!test_bit(desc->slice_id, drv_data->bitmap)) { + mutex_unlock(&drv_data->lock); + return 0; + } + act_ctrl_val = ACT_CTRL_OPCODE_DEACTIVATE << ACT_CTRL_OPCODE_SHIFT; + + ret = llcc_update_act_ctrl(desc->slice_id, act_ctrl_val, + ACTIVATE); + if (ret) { + mutex_unlock(&drv_data->lock); + return ret; + } + + __clear_bit(desc->slice_id, drv_data->bitmap); + mutex_unlock(&drv_data->lock); + + return ret; +} +EXPORT_SYMBOL_GPL(llcc_slice_deactivate); + +/** + * llcc_get_slice_id - return the slice id + * @desc: Pointer to llcc slice descriptor + */ +int llcc_get_slice_id(struct llcc_slice_desc *desc) +{ + return desc->slice_id; +} +EXPORT_SYMBOL_GPL(llcc_get_slice_id); + +/** + * llcc_get_slice_size - return the slice id + * @desc: Pointer to llcc slice descriptor + */ +size_t llcc_get_slice_size(struct llcc_slice_desc *desc) +{ + return desc->slice_size; +} +EXPORT_SYMBOL_GPL(llcc_get_slice_size); + +static int qcom_llcc_cfg_program(struct platform_device *pdev) +{ + int i; + u32 attr1_cfg; + u32 attr0_cfg; + u32 attr1_val; + u32 attr0_val; + u32 max_cap_cacheline; + u32 sz; + int ret; + const struct llcc_slice_config *llcc_table; + struct llcc_slice_desc desc; + u32 bcast_off = drv_data->bcast_off; + + sz = drv_data->cfg_size; + llcc_table = drv_data->cfg; + + for (i = 0; i < sz; i++) { + attr1_cfg = bcast_off + + LLCC_TRP_ATTR1_CFGn(llcc_table[i].slice_id); + attr0_cfg = bcast_off + + LLCC_TRP_ATTR0_CFGn(llcc_table[i].slice_id); + + attr1_val = llcc_table[i].cache_mode; + attr1_val |= llcc_table[i].probe_target_ways << + ATTR1_PROBE_TARGET_WAYS_SHIFT; + attr1_val |= llcc_table[i].fixed_size << + ATTR1_FIXED_SIZE_SHIFT; + attr1_val |= llcc_table[i].priority << + ATTR1_PRIORITY_SHIFT; + + max_cap_cacheline = MAX_CAP_TO_BYTES(llcc_table[i].max_cap); + + /* LLCC instances can vary for each target. + * The SW writes to broadcast register which gets propagated + * to each llcc instace (llcc0,.. llccN). + * Since the size of the memory is divided equally amongst the + * llcc instances, we need to configure the max cap accordingly. + */ + max_cap_cacheline = max_cap_cacheline / drv_data->num_banks; + max_cap_cacheline >>= CACHE_LINE_SIZE_SHIFT; + attr1_val |= max_cap_cacheline << ATTR1_MAX_CAP_SHIFT; + + attr0_val = llcc_table[i].res_ways & ATTR0_RES_WAYS_MASK; + attr0_val |= llcc_table[i].bonus_ways << ATTR0_BONUS_WAYS_SHIFT; + + ret = regmap_write(drv_data->regmap, attr1_cfg, attr1_val); + if (ret) + return ret; + ret = regmap_write(drv_data->regmap, attr0_cfg, attr0_val); + if (ret) + return ret; + if (llcc_table[i].activate_on_init) { + desc.slice_id = llcc_table[i].slice_id; + ret = llcc_slice_activate(&desc); + } + } + return ret; +} + +int qcom_llcc_probe(struct platform_device *pdev, + const struct llcc_slice_config *llcc_cfg, u32 sz) +{ + u32 num_banks; + struct device *dev = &pdev->dev; + struct resource *res; + void __iomem *base; + int ret, i; + + drv_data = devm_kzalloc(dev, sizeof(*drv_data), GFP_KERNEL); + if (!drv_data) + return -ENOMEM; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + base = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(base)) + return PTR_ERR(base); + + drv_data->regmap = devm_regmap_init_mmio(dev, base, + &llcc_regmap_config); + if (IS_ERR(drv_data->regmap)) + return PTR_ERR(drv_data->regmap); + + ret = regmap_read(drv_data->regmap, LLCC_COMMON_STATUS0, + &num_banks); + if (ret) + return ret; + + num_banks &= LLCC_LB_CNT_MASK; + num_banks >>= LLCC_LB_CNT_SHIFT; + drv_data->num_banks = num_banks; + + for (i = 0; i < sz; i++) + if (llcc_cfg[i].slice_id > drv_data->max_slices) + drv_data->max_slices = llcc_cfg[i].slice_id; + + drv_data->offsets = devm_kcalloc(dev, num_banks, sizeof(u32), + GFP_KERNEL); + if (!drv_data->offsets) + return -ENOMEM; + + for (i = 0; i < num_banks; i++) + drv_data->offsets[i] = i * BANK_OFFSET_STRIDE; + + drv_data->bcast_off = num_banks * BANK_OFFSET_STRIDE; + + drv_data->bitmap = devm_kcalloc(dev, + BITS_TO_LONGS(drv_data->max_slices), sizeof(unsigned long), + GFP_KERNEL); + if (!drv_data->bitmap) + return -ENOMEM; + + drv_data->cfg = llcc_cfg; + drv_data->cfg_size = sz; + mutex_init(&drv_data->lock); + platform_set_drvdata(pdev, drv_data); + + return qcom_llcc_cfg_program(pdev); +} +EXPORT_SYMBOL_GPL(qcom_llcc_probe); diff --git a/include/linux/soc/qcom/llcc-qcom.h b/include/linux/soc/qcom/llcc-qcom.h new file mode 100644 index 000000000000..7e3b9c605ab2 --- /dev/null +++ b/include/linux/soc/qcom/llcc-qcom.h @@ -0,0 +1,180 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2017-2018, The Linux Foundation. All rights reserved. + * + */ + +#include +#ifndef __LLCC_QCOM__ +#define __LLCC_QCOM__ + +#define LLCC_CPUSS 1 +#define LLCC_VIDSC0 2 +#define LLCC_VIDSC1 3 +#define LLCC_ROTATOR 4 +#define LLCC_VOICE 5 +#define LLCC_AUDIO 6 +#define LLCC_MDMHPGRW 7 +#define LLCC_MDM 8 +#define LLCC_CMPT 10 +#define LLCC_GPUHTW 11 +#define LLCC_GPU 12 +#define LLCC_MMUHWT 13 +#define LLCC_CMPTDMA 15 +#define LLCC_DISP 16 +#define LLCC_VIDFW 17 +#define LLCC_MDMHPFX 20 +#define LLCC_MDMPNG 21 +#define LLCC_AUDHW 22 + +/** + * llcc_slice_desc - Cache slice descriptor + * @slice_id: llcc slice id + * @slice_size: Size allocated for the llcc slice + */ +struct llcc_slice_desc { + u32 slice_id; + size_t slice_size; +}; + +/** + * llcc_slice_config - Data associated with the llcc slice + * @usecase_id: usecase id for which the llcc slice is used + * @slice_id: llcc slice id assigned to each slice + * @max_cap: maximum capacity of the llcc slice + * @priority: priority of the llcc slice + * @fixed_size: whether the llcc slice can grow beyond its size + * @bonus_ways: bonus ways associated with llcc slice + * @res_ways: reserved ways associated with llcc slice + * @cache_mode: mode of the llcc slice + * @probe_target_ways: Probe only reserved and bonus ways on a cache miss + * @dis_cap_alloc: Disable capacity based allocation + * @retain_on_pc: Retain through power collapse + * @activate_on_init: activate the slice on init + */ +struct llcc_slice_config { + u32 usecase_id; + u32 slice_id; + u32 max_cap; + u32 priority; + bool fixed_size; + u32 bonus_ways; + u32 res_ways; + u32 cache_mode; + u32 probe_target_ways; + bool dis_cap_alloc; + bool retain_on_pc; + bool activate_on_init; +}; + +/** + * llcc_drv_data - Data associated with the llcc driver + * @regmap: regmap associated with the llcc device + * @cfg: pointer to the data structure for slice configuration + * @lock: mutex associated with each slice + * @cfg_size: size of the config data table + * @max_slices: max slices as read from device tree + * @bcast_off: Offset of the broadcast bank + * @num_banks: Number of llcc banks + * @bitmap: Bit map to track the active slice ids + * @offsets: Pointer to the bank offsets array + */ +struct llcc_drv_data { + struct regmap *regmap; + const struct llcc_slice_config *cfg; + struct mutex lock; + u32 cfg_size; + u32 max_slices; + u32 bcast_off; + u32 num_banks; + unsigned long *bitmap; + u32 *offsets; +}; + +#if IS_ENABLED(CONFIG_QCOM_LLCC) +/** + * llcc_slice_getd - get llcc slice descriptor + * @uid: usecase_id of the client + */ +struct llcc_slice_desc *llcc_slice_getd(u32 uid); + +/** + * llcc_slice_putd - llcc slice descritpor + * @desc: Pointer to llcc slice descriptor + */ +void llcc_slice_putd(struct llcc_slice_desc *desc); + +/** + * llcc_get_slice_id - get slice id + * @desc: Pointer to llcc slice descriptor + */ +int llcc_get_slice_id(struct llcc_slice_desc *desc); + +/** + * llcc_get_slice_size - llcc slice size + * @desc: Pointer to llcc slice descriptor + */ +size_t llcc_get_slice_size(struct llcc_slice_desc *desc); + +/** + * llcc_slice_activate - Activate the llcc slice + * @desc: Pointer to llcc slice descriptor + */ +int llcc_slice_activate(struct llcc_slice_desc *desc); + +/** + * llcc_slice_deactivate - Deactivate the llcc slice + * @desc: Pointer to llcc slice descriptor + */ +int llcc_slice_deactivate(struct llcc_slice_desc *desc); + +/** + * qcom_llcc_probe - program the sct table + * @pdev: platform device pointer + * @table: soc sct table + * @sz: Size of the config table + */ +int qcom_llcc_probe(struct platform_device *pdev, + const struct llcc_slice_config *table, u32 sz); +#else +static inline struct llcc_slice_desc *llcc_slice_getd(u32 uid) +{ + return NULL; +} + +static inline void llcc_slice_putd(struct llcc_slice_desc *desc) +{ + +}; + +static inline int llcc_get_slice_id(struct llcc_slice_desc *desc) +{ + return -EINVAL; +} + +static inline size_t llcc_get_slice_size(struct llcc_slice_desc *desc) +{ + return 0; +} +static inline int llcc_slice_activate(struct llcc_slice_desc *desc) +{ + return -EINVAL; +} + +static inline int llcc_slice_deactivate(struct llcc_slice_desc *desc) +{ + return -EINVAL; +} +static inline int qcom_llcc_probe(struct platform_device *pdev, + const struct llcc_slice_config *table, u32 sz) +{ + return -ENODEV; +} + +static inline int qcom_llcc_remove(struct platform_device *pdev) +{ + return -ENODEV; +} +#endif + +#endif -- cgit v1.2.3 From 658628e7ef78e875cfe13064387c1a7a287d6338 Mon Sep 17 00:00:00 2001 From: Lina Iyer Date: Wed, 20 Jun 2018 18:56:58 +0530 Subject: drivers: qcom: rpmh-rsc: add RPMH controller for QCOM SoCs Add controller driver for QCOM SoCs that have hardware based shared resource management. The hardware IP known as RSC (Resource State Coordinator) houses multiple Direct Resource Voter (DRV) for different execution levels. A DRV is a unique voter on the state of a shared resource. A Trigger Control Set (TCS) is a bunch of slots that can house multiple resource state requests, that when triggered will issue those requests through an internal bus to the Resource Power Manager Hardened (RPMH) blocks. These hardware blocks are capable of adjusting clocks, voltages, etc. The resource state request from a DRV are aggregated along with state requests from other processors in the SoC and the aggregate value is applied on the resource. Some important aspects of the RPMH communication - - Requests are with some header information - Multiple requests (upto 16) may be sent through a TCS, at a time - Requests in a TCS are sent in sequence - Requests may be fire-n-forget or completion (response expected) - Multiple TCS from the same DRV may be triggered simultaneously - Cannot send a request if another request for the same addr is in progress from the same DRV - When all the requests from a TCS are complete, an IRQ is raised - The IRQ handler needs to clear the TCS before it is available for reuse - TCS configuration is specific to a DRV - Platform drivers may use DRV from different RSCs to make requests Resource state requests made when CPUs are active are called 'active' state requests. Requests made when all the CPUs are powered down (idle state) are called 'sleep' state requests. They are matched by a corresponding 'wake' state requests which puts the resources back in to previously requested active state before resuming any CPU. TCSes are dedicated for each type of requests. Active mode TCSes (AMC) are used to send requests immediately to the resource, while control TCS are used to provide specific information to the controller. Sleep and Wake TCS send sleep and wake requests, after and before the system halt respectively. Signed-off-by: Lina Iyer Signed-off-by: Raju P.L.S.S.S.N Signed-off-by: Andy Gross --- drivers/soc/qcom/Kconfig | 10 + drivers/soc/qcom/Makefile | 1 + drivers/soc/qcom/rpmh-internal.h | 69 +++++ drivers/soc/qcom/rpmh-rsc.c | 481 ++++++++++++++++++++++++++++++++ include/dt-bindings/soc/qcom,rpmh-rsc.h | 14 + include/soc/qcom/tcs.h | 56 ++++ 6 files changed, 631 insertions(+) create mode 100644 drivers/soc/qcom/rpmh-internal.h create mode 100644 drivers/soc/qcom/rpmh-rsc.c create mode 100644 include/dt-bindings/soc/qcom,rpmh-rsc.h create mode 100644 include/soc/qcom/tcs.h (limited to 'include') diff --git a/drivers/soc/qcom/Kconfig b/drivers/soc/qcom/Kconfig index d1a41852ae7a..ccbdb398fa63 100644 --- a/drivers/soc/qcom/Kconfig +++ b/drivers/soc/qcom/Kconfig @@ -91,6 +91,16 @@ config QCOM_RMTFS_MEM Say y here if you intend to boot the modem remoteproc. +config QCOM_RPMH + bool "Qualcomm RPM-Hardened (RPMH) Communication" + depends on ARCH_QCOM && ARM64 && OF || COMPILE_TEST + help + Support for communication with the hardened-RPM blocks in + Qualcomm Technologies Inc (QTI) SoCs. RPMH communication uses an + internal bus to transmit state requests for shared resources. A set + of hardware components aggregate requests for these resources and + help apply the aggregated state on the resource. + config QCOM_SMEM tristate "Qualcomm Shared Memory Manager (SMEM)" depends on ARCH_QCOM diff --git a/drivers/soc/qcom/Makefile b/drivers/soc/qcom/Makefile index 5921454c4ddd..b2faf9aeed3f 100644 --- a/drivers/soc/qcom/Makefile +++ b/drivers/soc/qcom/Makefile @@ -8,6 +8,7 @@ obj-$(CONFIG_QCOM_PM) += spm.o obj-$(CONFIG_QCOM_QMI_HELPERS) += qmi_helpers.o qmi_helpers-y += qmi_encdec.o qmi_interface.o obj-$(CONFIG_QCOM_RMTFS_MEM) += rmtfs_mem.o +obj-$(CONFIG_QCOM_RPMH) += rpmh-rsc.o obj-$(CONFIG_QCOM_SMD_RPM) += smd-rpm.o obj-$(CONFIG_QCOM_SMEM) += smem.o obj-$(CONFIG_QCOM_SMEM_STATE) += smem_state.o diff --git a/drivers/soc/qcom/rpmh-internal.h b/drivers/soc/qcom/rpmh-internal.h new file mode 100644 index 000000000000..cc29176f1303 --- /dev/null +++ b/drivers/soc/qcom/rpmh-internal.h @@ -0,0 +1,69 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved. + */ + + +#ifndef __RPM_INTERNAL_H__ +#define __RPM_INTERNAL_H__ + +#include +#include + +#define TCS_TYPE_NR 4 +#define MAX_CMDS_PER_TCS 16 +#define MAX_TCS_PER_TYPE 3 +#define MAX_TCS_NR (MAX_TCS_PER_TYPE * TCS_TYPE_NR) + +struct rsc_drv; + +/** + * struct tcs_group: group of Trigger Command Sets (TCS) to send state requests + * to the controller + * + * @drv: the controller + * @type: type of the TCS in this group - active, sleep, wake + * @mask: mask of the TCSes relative to all the TCSes in the RSC + * @offset: start of the TCS group relative to the TCSes in the RSC + * @num_tcs: number of TCSes in this type + * @ncpt: number of commands in each TCS + * @lock: lock for synchronizing this TCS writes + * @req: requests that are sent from the TCS + */ +struct tcs_group { + struct rsc_drv *drv; + int type; + u32 mask; + u32 offset; + int num_tcs; + int ncpt; + spinlock_t lock; + const struct tcs_request *req[MAX_TCS_PER_TYPE]; +}; + +/** + * struct rsc_drv: the Direct Resource Voter (DRV) of the + * Resource State Coordinator controller (RSC) + * + * @name: controller identifier + * @tcs_base: start address of the TCS registers in this controller + * @id: instance id in the controller (Direct Resource Voter) + * @num_tcs: number of TCSes in this DRV + * @tcs: TCS groups + * @tcs_in_use: s/w state of the TCS + * @lock: synchronize state of the controller + */ +struct rsc_drv { + const char *name; + void __iomem *tcs_base; + int id; + int num_tcs; + struct tcs_group tcs[TCS_TYPE_NR]; + DECLARE_BITMAP(tcs_in_use, MAX_TCS_NR); + spinlock_t lock; +}; + + +int rpmh_rsc_send_data(struct rsc_drv *drv, const struct tcs_request *msg); + +#endif /* __RPM_INTERNAL_H__ */ diff --git a/drivers/soc/qcom/rpmh-rsc.c b/drivers/soc/qcom/rpmh-rsc.c new file mode 100644 index 000000000000..c5e0793cdfb7 --- /dev/null +++ b/drivers/soc/qcom/rpmh-rsc.c @@ -0,0 +1,481 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved. + */ + +#define pr_fmt(fmt) "%s " fmt, KBUILD_MODNAME + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#include "rpmh-internal.h" + +#define RSC_DRV_TCS_OFFSET 672 +#define RSC_DRV_CMD_OFFSET 20 + +/* DRV Configuration Information Register */ +#define DRV_PRNT_CHLD_CONFIG 0x0C +#define DRV_NUM_TCS_MASK 0x3F +#define DRV_NUM_TCS_SHIFT 6 +#define DRV_NCPT_MASK 0x1F +#define DRV_NCPT_SHIFT 27 + +/* Register offsets */ +#define RSC_DRV_IRQ_ENABLE 0x00 +#define RSC_DRV_IRQ_STATUS 0x04 +#define RSC_DRV_IRQ_CLEAR 0x08 +#define RSC_DRV_CMD_WAIT_FOR_CMPL 0x10 +#define RSC_DRV_CONTROL 0x14 +#define RSC_DRV_STATUS 0x18 +#define RSC_DRV_CMD_ENABLE 0x1C +#define RSC_DRV_CMD_MSGID 0x30 +#define RSC_DRV_CMD_ADDR 0x34 +#define RSC_DRV_CMD_DATA 0x38 +#define RSC_DRV_CMD_STATUS 0x3C +#define RSC_DRV_CMD_RESP_DATA 0x40 + +#define TCS_AMC_MODE_ENABLE BIT(16) +#define TCS_AMC_MODE_TRIGGER BIT(24) + +/* TCS CMD register bit mask */ +#define CMD_MSGID_LEN 8 +#define CMD_MSGID_RESP_REQ BIT(8) +#define CMD_MSGID_WRITE BIT(16) +#define CMD_STATUS_ISSUED BIT(8) +#define CMD_STATUS_COMPL BIT(16) + +static u32 read_tcs_reg(struct rsc_drv *drv, int reg, int tcs_id, int cmd_id) +{ + return readl_relaxed(drv->tcs_base + reg + RSC_DRV_TCS_OFFSET * tcs_id + + RSC_DRV_CMD_OFFSET * cmd_id); +} + +static void write_tcs_cmd(struct rsc_drv *drv, int reg, int tcs_id, int cmd_id, + u32 data) +{ + writel_relaxed(data, drv->tcs_base + reg + RSC_DRV_TCS_OFFSET * tcs_id + + RSC_DRV_CMD_OFFSET * cmd_id); +} + +static void write_tcs_reg(struct rsc_drv *drv, int reg, int tcs_id, u32 data) +{ + writel_relaxed(data, drv->tcs_base + reg + RSC_DRV_TCS_OFFSET * tcs_id); +} + +static void write_tcs_reg_sync(struct rsc_drv *drv, int reg, int tcs_id, + u32 data) +{ + writel(data, drv->tcs_base + reg + RSC_DRV_TCS_OFFSET * tcs_id); + for (;;) { + if (data == readl(drv->tcs_base + reg + + RSC_DRV_TCS_OFFSET * tcs_id)) + break; + udelay(1); + } +} + +static bool tcs_is_free(struct rsc_drv *drv, int tcs_id) +{ + return !test_bit(tcs_id, drv->tcs_in_use) && + read_tcs_reg(drv, RSC_DRV_STATUS, tcs_id, 0); +} + +static struct tcs_group *get_tcs_of_type(struct rsc_drv *drv, int type) +{ + return &drv->tcs[type]; +} + +static struct tcs_group *get_tcs_for_msg(struct rsc_drv *drv, + const struct tcs_request *msg) +{ + int type; + + switch (msg->state) { + case RPMH_ACTIVE_ONLY_STATE: + type = ACTIVE_TCS; + break; + default: + return ERR_PTR(-EINVAL); + } + + return get_tcs_of_type(drv, type); +} + +static const struct tcs_request *get_req_from_tcs(struct rsc_drv *drv, + int tcs_id) +{ + struct tcs_group *tcs; + int i; + + for (i = 0; i < drv->num_tcs; i++) { + tcs = &drv->tcs[i]; + if (tcs->mask & BIT(tcs_id)) + return tcs->req[tcs_id - tcs->offset]; + } + + return NULL; +} + +/** + * tcs_tx_done: TX Done interrupt handler + */ +static irqreturn_t tcs_tx_done(int irq, void *p) +{ + struct rsc_drv *drv = p; + int i, j; + unsigned long irq_status; + const struct tcs_request *req; + struct tcs_cmd *cmd; + + irq_status = read_tcs_reg(drv, RSC_DRV_IRQ_STATUS, 0, 0); + + for_each_set_bit(i, &irq_status, BITS_PER_LONG) { + req = get_req_from_tcs(drv, i); + if (!req) { + WARN_ON(1); + goto skip; + } + + for (j = 0; j < req->num_cmds; j++) { + u32 sts; + + cmd = &req->cmds[j]; + sts = read_tcs_reg(drv, RSC_DRV_CMD_STATUS, i, j); + if (!(sts & CMD_STATUS_ISSUED) || + ((req->wait_for_compl || cmd->wait) && + !(sts & CMD_STATUS_COMPL))) { + pr_err("Incomplete request: %s: addr=%#x data=%#x", + drv->name, cmd->addr, cmd->data); + } + } +skip: + /* Reclaim the TCS */ + write_tcs_reg(drv, RSC_DRV_CMD_ENABLE, i, 0); + write_tcs_reg(drv, RSC_DRV_IRQ_CLEAR, 0, BIT(i)); + spin_lock(&drv->lock); + clear_bit(i, drv->tcs_in_use); + spin_unlock(&drv->lock); + } + + return IRQ_HANDLED; +} + +static void __tcs_buffer_write(struct rsc_drv *drv, int tcs_id, int cmd_id, + const struct tcs_request *msg) +{ + u32 msgid, cmd_msgid; + u32 cmd_enable = 0; + u32 cmd_complete; + struct tcs_cmd *cmd; + int i, j; + + cmd_msgid = CMD_MSGID_LEN; + cmd_msgid |= msg->wait_for_compl ? CMD_MSGID_RESP_REQ : 0; + cmd_msgid |= CMD_MSGID_WRITE; + + cmd_complete = read_tcs_reg(drv, RSC_DRV_CMD_WAIT_FOR_CMPL, tcs_id, 0); + + for (i = 0, j = cmd_id; i < msg->num_cmds; i++, j++) { + cmd = &msg->cmds[i]; + cmd_enable |= BIT(j); + cmd_complete |= cmd->wait << j; + msgid = cmd_msgid; + msgid |= cmd->wait ? CMD_MSGID_RESP_REQ : 0; + write_tcs_cmd(drv, RSC_DRV_CMD_MSGID, tcs_id, j, msgid); + write_tcs_cmd(drv, RSC_DRV_CMD_ADDR, tcs_id, j, cmd->addr); + write_tcs_cmd(drv, RSC_DRV_CMD_DATA, tcs_id, j, cmd->data); + } + + write_tcs_reg(drv, RSC_DRV_CMD_WAIT_FOR_CMPL, tcs_id, cmd_complete); + cmd_enable |= read_tcs_reg(drv, RSC_DRV_CMD_ENABLE, tcs_id, 0); + write_tcs_reg(drv, RSC_DRV_CMD_ENABLE, tcs_id, cmd_enable); +} + +static void __tcs_trigger(struct rsc_drv *drv, int tcs_id) +{ + u32 enable; + + /* + * HW req: Clear the DRV_CONTROL and enable TCS again + * While clearing ensure that the AMC mode trigger is cleared + * and then the mode enable is cleared. + */ + enable = read_tcs_reg(drv, RSC_DRV_CONTROL, tcs_id, 0); + enable &= ~TCS_AMC_MODE_TRIGGER; + write_tcs_reg_sync(drv, RSC_DRV_CONTROL, tcs_id, enable); + enable &= ~TCS_AMC_MODE_ENABLE; + write_tcs_reg_sync(drv, RSC_DRV_CONTROL, tcs_id, enable); + + /* Enable the AMC mode on the TCS and then trigger the TCS */ + enable = TCS_AMC_MODE_ENABLE; + write_tcs_reg_sync(drv, RSC_DRV_CONTROL, tcs_id, enable); + enable |= TCS_AMC_MODE_TRIGGER; + write_tcs_reg_sync(drv, RSC_DRV_CONTROL, tcs_id, enable); +} + +static int check_for_req_inflight(struct rsc_drv *drv, struct tcs_group *tcs, + const struct tcs_request *msg) +{ + unsigned long curr_enabled; + u32 addr; + int i, j, k; + int tcs_id = tcs->offset; + + for (i = 0; i < tcs->num_tcs; i++, tcs_id++) { + if (tcs_is_free(drv, tcs_id)) + continue; + + curr_enabled = read_tcs_reg(drv, RSC_DRV_CMD_ENABLE, tcs_id, 0); + + for_each_set_bit(j, &curr_enabled, MAX_CMDS_PER_TCS) { + addr = read_tcs_reg(drv, RSC_DRV_CMD_ADDR, tcs_id, j); + for (k = 0; k < msg->num_cmds; k++) { + if (addr == msg->cmds[k].addr) + return -EBUSY; + } + } + } + + return 0; +} + +static int find_free_tcs(struct tcs_group *tcs) +{ + int i; + + for (i = 0; i < tcs->num_tcs; i++) { + if (tcs_is_free(tcs->drv, tcs->offset + i)) + return tcs->offset + i; + } + + return -EBUSY; +} + +static int tcs_write(struct rsc_drv *drv, const struct tcs_request *msg) +{ + struct tcs_group *tcs; + int tcs_id; + unsigned long flags; + int ret; + + tcs = get_tcs_for_msg(drv, msg); + if (IS_ERR(tcs)) + return PTR_ERR(tcs); + + spin_lock_irqsave(&tcs->lock, flags); + spin_lock(&drv->lock); + /* + * The h/w does not like if we send a request to the same address, + * when one is already in-flight or being processed. + */ + ret = check_for_req_inflight(drv, tcs, msg); + if (ret) { + spin_unlock(&drv->lock); + goto done_write; + } + + tcs_id = find_free_tcs(tcs); + if (tcs_id < 0) { + ret = tcs_id; + spin_unlock(&drv->lock); + goto done_write; + } + + tcs->req[tcs_id - tcs->offset] = msg; + set_bit(tcs_id, drv->tcs_in_use); + spin_unlock(&drv->lock); + + __tcs_buffer_write(drv, tcs_id, 0, msg); + __tcs_trigger(drv, tcs_id); + +done_write: + spin_unlock_irqrestore(&tcs->lock, flags); + return ret; +} + +/** + * rpmh_rsc_send_data: Validate the incoming message and write to the + * appropriate TCS block. + * + * @drv: the controller + * @msg: the data to be sent + * + * Return: 0 on success, -EINVAL on error. + * Note: This call blocks until a valid data is written to the TCS. + */ +int rpmh_rsc_send_data(struct rsc_drv *drv, const struct tcs_request *msg) +{ + int ret; + + if (!msg || !msg->cmds || !msg->num_cmds || + msg->num_cmds > MAX_RPMH_PAYLOAD) { + WARN_ON(1); + return -EINVAL; + } + + do { + ret = tcs_write(drv, msg); + if (ret == -EBUSY) { + pr_info_ratelimited("TCS Busy, retrying RPMH message send: addr=%#x\n", + msg->cmds[0].addr); + udelay(10); + } + } while (ret == -EBUSY); + + return ret; +} + +static int rpmh_probe_tcs_config(struct platform_device *pdev, + struct rsc_drv *drv) +{ + struct tcs_type_config { + u32 type; + u32 n; + } tcs_cfg[TCS_TYPE_NR] = { { 0 } }; + struct device_node *dn = pdev->dev.of_node; + u32 config, max_tcs, ncpt, offset; + int i, ret, n, st = 0; + struct tcs_group *tcs; + struct resource *res; + void __iomem *base; + char drv_id[10] = {0}; + + snprintf(drv_id, ARRAY_SIZE(drv_id), "drv-%d", drv->id); + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, drv_id); + base = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(base)) + return PTR_ERR(base); + + ret = of_property_read_u32(dn, "qcom,tcs-offset", &offset); + if (ret) + return ret; + drv->tcs_base = base + offset; + + config = readl_relaxed(base + DRV_PRNT_CHLD_CONFIG); + + max_tcs = config; + max_tcs &= DRV_NUM_TCS_MASK << (DRV_NUM_TCS_SHIFT * drv->id); + max_tcs = max_tcs >> (DRV_NUM_TCS_SHIFT * drv->id); + + ncpt = config & (DRV_NCPT_MASK << DRV_NCPT_SHIFT); + ncpt = ncpt >> DRV_NCPT_SHIFT; + + n = of_property_count_u32_elems(dn, "qcom,tcs-config"); + if (n != 2 * TCS_TYPE_NR) + return -EINVAL; + + for (i = 0; i < TCS_TYPE_NR; i++) { + ret = of_property_read_u32_index(dn, "qcom,tcs-config", + i * 2, &tcs_cfg[i].type); + if (ret) + return ret; + if (tcs_cfg[i].type >= TCS_TYPE_NR) + return -EINVAL; + + ret = of_property_read_u32_index(dn, "qcom,tcs-config", + i * 2 + 1, &tcs_cfg[i].n); + if (ret) + return ret; + if (tcs_cfg[i].n > MAX_TCS_PER_TYPE) + return -EINVAL; + } + + for (i = 0; i < TCS_TYPE_NR; i++) { + tcs = &drv->tcs[tcs_cfg[i].type]; + if (tcs->drv) + return -EINVAL; + tcs->drv = drv; + tcs->type = tcs_cfg[i].type; + tcs->num_tcs = tcs_cfg[i].n; + tcs->ncpt = ncpt; + spin_lock_init(&tcs->lock); + + if (!tcs->num_tcs || tcs->type == CONTROL_TCS) + continue; + + if (st + tcs->num_tcs > max_tcs || + st + tcs->num_tcs >= BITS_PER_BYTE * sizeof(tcs->mask)) + return -EINVAL; + + tcs->mask = ((1 << tcs->num_tcs) - 1) << st; + tcs->offset = st; + st += tcs->num_tcs; + } + + drv->num_tcs = st; + + return 0; +} + +static int rpmh_rsc_probe(struct platform_device *pdev) +{ + struct device_node *dn = pdev->dev.of_node; + struct rsc_drv *drv; + int ret, irq; + + drv = devm_kzalloc(&pdev->dev, sizeof(*drv), GFP_KERNEL); + if (!drv) + return -ENOMEM; + + ret = of_property_read_u32(dn, "qcom,drv-id", &drv->id); + if (ret) + return ret; + + drv->name = of_get_property(dn, "label", NULL); + if (!drv->name) + drv->name = dev_name(&pdev->dev); + + ret = rpmh_probe_tcs_config(pdev, drv); + if (ret) + return ret; + + spin_lock_init(&drv->lock); + bitmap_zero(drv->tcs_in_use, MAX_TCS_NR); + + irq = platform_get_irq(pdev, drv->id); + if (irq < 0) + return irq; + + ret = devm_request_irq(&pdev->dev, irq, tcs_tx_done, + IRQF_TRIGGER_HIGH | IRQF_NO_SUSPEND, + drv->name, drv); + if (ret) + return ret; + + /* Enable the active TCS to send requests immediately */ + write_tcs_reg(drv, RSC_DRV_IRQ_ENABLE, 0, drv->tcs[ACTIVE_TCS].mask); + + return devm_of_platform_populate(&pdev->dev); +} + +static const struct of_device_id rpmh_drv_match[] = { + { .compatible = "qcom,rpmh-rsc", }, + { } +}; + +static struct platform_driver rpmh_driver = { + .probe = rpmh_rsc_probe, + .driver = { + .name = "rpmh", + .of_match_table = rpmh_drv_match, + }, +}; + +static int __init rpmh_driver_init(void) +{ + return platform_driver_register(&rpmh_driver); +} +arch_initcall(rpmh_driver_init); diff --git a/include/dt-bindings/soc/qcom,rpmh-rsc.h b/include/dt-bindings/soc/qcom,rpmh-rsc.h new file mode 100644 index 000000000000..868f998ea998 --- /dev/null +++ b/include/dt-bindings/soc/qcom,rpmh-rsc.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved. + */ + +#ifndef __DT_QCOM_RPMH_RSC_H__ +#define __DT_QCOM_RPMH_RSC_H__ + +#define SLEEP_TCS 0 +#define WAKE_TCS 1 +#define ACTIVE_TCS 2 +#define CONTROL_TCS 3 + +#endif /* __DT_QCOM_RPMH_RSC_H__ */ diff --git a/include/soc/qcom/tcs.h b/include/soc/qcom/tcs.h new file mode 100644 index 000000000000..262876a59e86 --- /dev/null +++ b/include/soc/qcom/tcs.h @@ -0,0 +1,56 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved. + */ + +#ifndef __SOC_QCOM_TCS_H__ +#define __SOC_QCOM_TCS_H__ + +#define MAX_RPMH_PAYLOAD 16 + +/** + * rpmh_state: state for the request + * + * RPMH_SLEEP_STATE: State of the resource when the processor subsystem + * is powered down. There is no client using the + * resource actively. + * RPMH_WAKE_ONLY_STATE: Resume resource state to the value previously + * requested before the processor was powered down. + * RPMH_ACTIVE_ONLY_STATE: Active or AMC mode requests. Resource state + * is aggregated immediately. + */ +enum rpmh_state { + RPMH_SLEEP_STATE, + RPMH_WAKE_ONLY_STATE, + RPMH_ACTIVE_ONLY_STATE, +}; + +/** + * struct tcs_cmd: an individual request to RPMH. + * + * @addr: the address of the resource slv_id:18:16 | offset:0:15 + * @data: the resource state request + * @wait: wait for this request to be complete before sending the next + */ +struct tcs_cmd { + u32 addr; + u32 data; + u32 wait; +}; + +/** + * struct tcs_request: A set of tcs_cmds sent together in a TCS + * + * @state: state for the request. + * @wait_for_compl: wait until we get a response from the h/w accelerator + * @num_cmds: the number of @cmds in this request + * @cmds: an array of tcs_cmds + */ +struct tcs_request { + enum rpmh_state state; + u32 wait_for_compl; + u32 num_cmds; + struct tcs_cmd *cmds; +}; + +#endif /* __SOC_QCOM_TCS_H__ */ -- cgit v1.2.3 From c1038456b02b86cc4445441a8d33c5aca0ac103e Mon Sep 17 00:00:00 2001 From: Lina Iyer Date: Wed, 20 Jun 2018 18:57:01 +0530 Subject: drivers: qcom: rpmh: add RPMH helper functions Sending RPMH requests and waiting for response from the controller through a callback is common functionality across all platform drivers. To simplify drivers, add a library functions to create RPMH client and send resource state requests. rpmh_write() is a synchronous blocking call that can be used to send active state requests. Signed-off-by: Lina Iyer Signed-off-by: Raju P.L.S.S.S.N Signed-off-by: Andy Gross --- drivers/soc/qcom/Makefile | 4 +- drivers/soc/qcom/rpmh-internal.h | 31 ++++++++++- drivers/soc/qcom/rpmh-rsc.c | 6 +- drivers/soc/qcom/rpmh.c | 116 +++++++++++++++++++++++++++++++++++++++ include/soc/qcom/rpmh.h | 25 +++++++++ 5 files changed, 179 insertions(+), 3 deletions(-) create mode 100644 drivers/soc/qcom/rpmh.c create mode 100644 include/soc/qcom/rpmh.h (limited to 'include') diff --git a/drivers/soc/qcom/Makefile b/drivers/soc/qcom/Makefile index 036ecc45cbbd..f25b54cd6cf8 100644 --- a/drivers/soc/qcom/Makefile +++ b/drivers/soc/qcom/Makefile @@ -9,7 +9,9 @@ obj-$(CONFIG_QCOM_PM) += spm.o obj-$(CONFIG_QCOM_QMI_HELPERS) += qmi_helpers.o qmi_helpers-y += qmi_encdec.o qmi_interface.o obj-$(CONFIG_QCOM_RMTFS_MEM) += rmtfs_mem.o -obj-$(CONFIG_QCOM_RPMH) += rpmh-rsc.o +obj-$(CONFIG_QCOM_RPMH) += qcom_rpmh.o +qcom_rpmh-y += rpmh-rsc.o +qcom_rpmh-y += rpmh.o obj-$(CONFIG_QCOM_SMD_RPM) += smd-rpm.o obj-$(CONFIG_QCOM_SMEM) += smem.o obj-$(CONFIG_QCOM_SMEM_STATE) += smem_state.o diff --git a/drivers/soc/qcom/rpmh-internal.h b/drivers/soc/qcom/rpmh-internal.h index cc29176f1303..1e687f719301 100644 --- a/drivers/soc/qcom/rpmh-internal.h +++ b/drivers/soc/qcom/rpmh-internal.h @@ -41,6 +41,32 @@ struct tcs_group { const struct tcs_request *req[MAX_TCS_PER_TYPE]; }; +/** + * struct rpmh_request: the message to be sent to rpmh-rsc + * + * @msg: the request + * @cmd: the payload that will be part of the @msg + * @completion: triggered when request is done + * @dev: the device making the request + * @err: err return from the controller + */ +struct rpmh_request { + struct tcs_request msg; + struct tcs_cmd cmd[MAX_RPMH_PAYLOAD]; + struct completion *completion; + const struct device *dev; + int err; +}; + +/** + * struct rpmh_ctrlr: our representation of the controller + * + * @drv: the controller instance + */ +struct rpmh_ctrlr { + struct rsc_drv *drv; +}; + /** * struct rsc_drv: the Direct Resource Voter (DRV) of the * Resource State Coordinator controller (RSC) @@ -52,6 +78,7 @@ struct tcs_group { * @tcs: TCS groups * @tcs_in_use: s/w state of the TCS * @lock: synchronize state of the controller + * @client: handle to the DRV's client. */ struct rsc_drv { const char *name; @@ -61,9 +88,11 @@ struct rsc_drv { struct tcs_group tcs[TCS_TYPE_NR]; DECLARE_BITMAP(tcs_in_use, MAX_TCS_NR); spinlock_t lock; + struct rpmh_ctrlr client; }; - int rpmh_rsc_send_data(struct rsc_drv *drv, const struct tcs_request *msg); +void rpmh_tx_done(const struct tcs_request *msg, int r); + #endif /* __RPM_INTERNAL_H__ */ diff --git a/drivers/soc/qcom/rpmh-rsc.c b/drivers/soc/qcom/rpmh-rsc.c index 89d41cdd8d71..91f8d60d17cc 100644 --- a/drivers/soc/qcom/rpmh-rsc.c +++ b/drivers/soc/qcom/rpmh-rsc.c @@ -138,7 +138,7 @@ static const struct tcs_request *get_req_from_tcs(struct rsc_drv *drv, static irqreturn_t tcs_tx_done(int irq, void *p) { struct rsc_drv *drv = p; - int i, j, err; + int i, j, err = 0; unsigned long irq_status; const struct tcs_request *req; struct tcs_cmd *cmd; @@ -175,6 +175,8 @@ skip: spin_lock(&drv->lock); clear_bit(i, drv->tcs_in_use); spin_unlock(&drv->lock); + if (req) + rpmh_tx_done(req, err); } return IRQ_HANDLED; @@ -467,6 +469,8 @@ static int rpmh_rsc_probe(struct platform_device *pdev) /* Enable the active TCS to send requests immediately */ write_tcs_reg(drv, RSC_DRV_IRQ_ENABLE, 0, drv->tcs[ACTIVE_TCS].mask); + dev_set_drvdata(&pdev->dev, drv); + return devm_of_platform_populate(&pdev->dev); } diff --git a/drivers/soc/qcom/rpmh.c b/drivers/soc/qcom/rpmh.c new file mode 100644 index 000000000000..5e022cba8ab5 --- /dev/null +++ b/drivers/soc/qcom/rpmh.c @@ -0,0 +1,116 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "rpmh-internal.h" + +#define RPMH_TIMEOUT_MS msecs_to_jiffies(10000) + +#define DEFINE_RPMH_MSG_ONSTACK(dev, s, q, name) \ + struct rpmh_request name = { \ + .msg = { \ + .state = s, \ + .cmds = name.cmd, \ + .num_cmds = 0, \ + .wait_for_compl = true, \ + }, \ + .cmd = { { 0 } }, \ + .completion = q, \ + .dev = dev, \ + } + +#define ctrlr_to_drv(ctrlr) container_of(ctrlr, struct rsc_drv, client) + +static struct rpmh_ctrlr *get_rpmh_ctrlr(const struct device *dev) +{ + struct rsc_drv *drv = dev_get_drvdata(dev->parent); + + return &drv->client; +} + +void rpmh_tx_done(const struct tcs_request *msg, int r) +{ + struct rpmh_request *rpm_msg = container_of(msg, struct rpmh_request, + msg); + struct completion *compl = rpm_msg->completion; + + rpm_msg->err = r; + + if (r) + dev_err(rpm_msg->dev, "RPMH TX fail in msg addr=%#x, err=%d\n", + rpm_msg->msg.cmds[0].addr, r); + + /* Signal the blocking thread we are done */ + if (compl) + complete(compl); +} + +/** + * __rpmh_write: send the RPMH request + * + * @dev: The device making the request + * @state: Active/Sleep request type + * @rpm_msg: The data that needs to be sent (cmds). + */ +static int __rpmh_write(const struct device *dev, enum rpmh_state state, + struct rpmh_request *rpm_msg) +{ + struct rpmh_ctrlr *ctrlr = get_rpmh_ctrlr(dev); + + rpm_msg->msg.state = state; + + if (state != RPMH_ACTIVE_ONLY_STATE) + return -EINVAL; + + WARN_ON(irqs_disabled()); + + return rpmh_rsc_send_data(ctrlr_to_drv(ctrlr), &rpm_msg->msg); +} + +/** + * rpmh_write: Write a set of RPMH commands and block until response + * + * @rc: The RPMH handle got from rpmh_get_client + * @state: Active/sleep set + * @cmd: The payload data + * @n: The number of elements in @cmd + * + * May sleep. Do not call from atomic contexts. + */ +int rpmh_write(const struct device *dev, enum rpmh_state state, + const struct tcs_cmd *cmd, u32 n) +{ + DECLARE_COMPLETION_ONSTACK(compl); + DEFINE_RPMH_MSG_ONSTACK(dev, state, &compl, rpm_msg); + int ret; + + if (!cmd || !n || n > MAX_RPMH_PAYLOAD) + return -EINVAL; + + memcpy(rpm_msg.cmd, cmd, n * sizeof(*cmd)); + rpm_msg.msg.num_cmds = n; + + ret = __rpmh_write(dev, state, &rpm_msg); + if (ret) + return ret; + + ret = wait_for_completion_timeout(&compl, RPMH_TIMEOUT_MS); + WARN_ON(!ret); + return (ret > 0) ? 0 : -ETIMEDOUT; +} +EXPORT_SYMBOL(rpmh_write); diff --git a/include/soc/qcom/rpmh.h b/include/soc/qcom/rpmh.h new file mode 100644 index 000000000000..c1d0f902bd71 --- /dev/null +++ b/include/soc/qcom/rpmh.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved. + */ + +#ifndef __SOC_QCOM_RPMH_H__ +#define __SOC_QCOM_RPMH_H__ + +#include +#include + + +#if IS_ENABLED(CONFIG_QCOM_RPMH) +int rpmh_write(const struct device *dev, enum rpmh_state state, + const struct tcs_cmd *cmd, u32 n); + +#else + +static inline int rpmh_write(const struct device *dev, enum rpmh_state state, + const struct tcs_cmd *cmd, u32 n) +{ return -ENODEV; } + +#endif /* CONFIG_QCOM_RPMH */ + +#endif /* __SOC_QCOM_RPMH_H__ */ -- cgit v1.2.3 From 600513dfeef33cb05c694d1b13d319b9e8cde536 Mon Sep 17 00:00:00 2001 From: Lina Iyer Date: Wed, 20 Jun 2018 18:57:04 +0530 Subject: drivers: qcom: rpmh: cache sleep/wake state requests Active state requests are sent immediately to the RSC controller, while sleep and wake state requests are cached in this driver to avoid taxing the RSC controller repeatedly. The cached values will be sent to the controller when the rpmh_flush() is called. Generally, flushing is a system PM activity and may be called from the system PM drivers when the system is entering suspend or deeper sleep modes during cpuidle. Also allow invalidating the cached requests, so they may be re-populated again. Signed-off-by: Lina Iyer [rplsssn: remove unneeded semicolon, address line over 80chars error] Signed-off-by: Raju P.L.S.S.S.N Reviewed-by: Evan Green Reviewed-by: Matthias Kaehlcke Signed-off-by: Andy Gross --- drivers/soc/qcom/rpmh-internal.h | 8 +- drivers/soc/qcom/rpmh-rsc.c | 3 + drivers/soc/qcom/rpmh.c | 201 ++++++++++++++++++++++++++++++++++++++- include/soc/qcom/rpmh.h | 11 +++ 4 files changed, 216 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/drivers/soc/qcom/rpmh-internal.h b/drivers/soc/qcom/rpmh-internal.h index af4da1cb6558..101145c9db1c 100644 --- a/drivers/soc/qcom/rpmh-internal.h +++ b/drivers/soc/qcom/rpmh-internal.h @@ -66,10 +66,14 @@ struct rpmh_request { /** * struct rpmh_ctrlr: our representation of the controller * - * @drv: the controller instance + * @cache: the list of cached requests + * @cache_lock: synchronize access to the cache data + * @dirty: was the cache updated since flush */ struct rpmh_ctrlr { - struct rsc_drv *drv; + struct list_head cache; + spinlock_t cache_lock; + bool dirty; }; /** diff --git a/drivers/soc/qcom/rpmh-rsc.c b/drivers/soc/qcom/rpmh-rsc.c index fed8459c0ef6..5d0dd0581904 100644 --- a/drivers/soc/qcom/rpmh-rsc.c +++ b/drivers/soc/qcom/rpmh-rsc.c @@ -634,6 +634,9 @@ static int rpmh_rsc_probe(struct platform_device *pdev) /* Enable the active TCS to send requests immediately */ write_tcs_reg(drv, RSC_DRV_IRQ_ENABLE, 0, drv->tcs[ACTIVE_TCS].mask); + spin_lock_init(&drv->client.cache_lock); + INIT_LIST_HEAD(&drv->client.cache); + dev_set_drvdata(&pdev->dev, drv); return devm_of_platform_populate(&pdev->dev); diff --git a/drivers/soc/qcom/rpmh.c b/drivers/soc/qcom/rpmh.c index 5e022cba8ab5..c355ba13e73f 100644 --- a/drivers/soc/qcom/rpmh.c +++ b/drivers/soc/qcom/rpmh.c @@ -8,10 +8,12 @@ #include #include #include +#include #include #include #include #include +#include #include #include @@ -36,6 +38,21 @@ #define ctrlr_to_drv(ctrlr) container_of(ctrlr, struct rsc_drv, client) +/** + * struct cache_req: the request object for caching + * + * @addr: the address of the resource + * @sleep_val: the sleep vote + * @wake_val: the wake vote + * @list: linked list obj + */ +struct cache_req { + u32 addr; + u32 sleep_val; + u32 wake_val; + struct list_head list; +}; + static struct rpmh_ctrlr *get_rpmh_ctrlr(const struct device *dev) { struct rsc_drv *drv = dev_get_drvdata(dev->parent); @@ -60,26 +77,107 @@ void rpmh_tx_done(const struct tcs_request *msg, int r) complete(compl); } +static struct cache_req *__find_req(struct rpmh_ctrlr *ctrlr, u32 addr) +{ + struct cache_req *p, *req = NULL; + + list_for_each_entry(p, &ctrlr->cache, list) { + if (p->addr == addr) { + req = p; + break; + } + } + + return req; +} + +static struct cache_req *cache_rpm_request(struct rpmh_ctrlr *ctrlr, + enum rpmh_state state, + struct tcs_cmd *cmd) +{ + struct cache_req *req; + unsigned long flags; + + spin_lock_irqsave(&ctrlr->cache_lock, flags); + req = __find_req(ctrlr, cmd->addr); + if (req) + goto existing; + + req = kzalloc(sizeof(*req), GFP_ATOMIC); + if (!req) { + req = ERR_PTR(-ENOMEM); + goto unlock; + } + + req->addr = cmd->addr; + req->sleep_val = req->wake_val = UINT_MAX; + INIT_LIST_HEAD(&req->list); + list_add_tail(&req->list, &ctrlr->cache); + +existing: + switch (state) { + case RPMH_ACTIVE_ONLY_STATE: + if (req->sleep_val != UINT_MAX) + req->wake_val = cmd->data; + break; + case RPMH_WAKE_ONLY_STATE: + req->wake_val = cmd->data; + break; + case RPMH_SLEEP_STATE: + req->sleep_val = cmd->data; + break; + default: + break; + } + + ctrlr->dirty = true; +unlock: + spin_unlock_irqrestore(&ctrlr->cache_lock, flags); + + return req; +} + /** - * __rpmh_write: send the RPMH request + * __rpmh_write: Cache and send the RPMH request * * @dev: The device making the request * @state: Active/Sleep request type * @rpm_msg: The data that needs to be sent (cmds). + * + * Cache the RPMH request and send if the state is ACTIVE_ONLY. + * SLEEP/WAKE_ONLY requests are not sent to the controller at + * this time. Use rpmh_flush() to send them to the controller. */ static int __rpmh_write(const struct device *dev, enum rpmh_state state, struct rpmh_request *rpm_msg) { struct rpmh_ctrlr *ctrlr = get_rpmh_ctrlr(dev); + int ret = -EINVAL; + struct cache_req *req; + int i; rpm_msg->msg.state = state; - if (state != RPMH_ACTIVE_ONLY_STATE) - return -EINVAL; + /* Cache the request in our store and link the payload */ + for (i = 0; i < rpm_msg->msg.num_cmds; i++) { + req = cache_rpm_request(ctrlr, state, &rpm_msg->msg.cmds[i]); + if (IS_ERR(req)) + return PTR_ERR(req); + } + + rpm_msg->msg.state = state; - WARN_ON(irqs_disabled()); + if (state == RPMH_ACTIVE_ONLY_STATE) { + WARN_ON(irqs_disabled()); + ret = rpmh_rsc_send_data(ctrlr_to_drv(ctrlr), &rpm_msg->msg); + } else { + ret = rpmh_rsc_write_ctrl_data(ctrlr_to_drv(ctrlr), + &rpm_msg->msg); + /* Clean up our call by spoofing tx_done */ + rpmh_tx_done(&rpm_msg->msg, ret); + } - return rpmh_rsc_send_data(ctrlr_to_drv(ctrlr), &rpm_msg->msg); + return ret; } /** @@ -114,3 +212,96 @@ int rpmh_write(const struct device *dev, enum rpmh_state state, return (ret > 0) ? 0 : -ETIMEDOUT; } EXPORT_SYMBOL(rpmh_write); + +static int is_req_valid(struct cache_req *req) +{ + return (req->sleep_val != UINT_MAX && + req->wake_val != UINT_MAX && + req->sleep_val != req->wake_val); +} + +static int send_single(const struct device *dev, enum rpmh_state state, + u32 addr, u32 data) +{ + DEFINE_RPMH_MSG_ONSTACK(dev, state, NULL, rpm_msg); + struct rpmh_ctrlr *ctrlr = get_rpmh_ctrlr(dev); + + /* Wake sets are always complete and sleep sets are not */ + rpm_msg.msg.wait_for_compl = (state == RPMH_WAKE_ONLY_STATE); + rpm_msg.cmd[0].addr = addr; + rpm_msg.cmd[0].data = data; + rpm_msg.msg.num_cmds = 1; + + return rpmh_rsc_write_ctrl_data(ctrlr_to_drv(ctrlr), &rpm_msg.msg); +} + +/** + * rpmh_flush: Flushes the buffered active and sleep sets to TCS + * + * @dev: The device making the request + * + * Return: -EBUSY if the controller is busy, probably waiting on a response + * to a RPMH request sent earlier. + * + * This function is always called from the sleep code from the last CPU + * that is powering down the entire system. Since no other RPMH API would be + * executing at this time, it is safe to run lockless. + */ +int rpmh_flush(const struct device *dev) +{ + struct cache_req *p; + struct rpmh_ctrlr *ctrlr = get_rpmh_ctrlr(dev); + int ret; + + if (!ctrlr->dirty) { + pr_debug("Skipping flush, TCS has latest data.\n"); + return 0; + } + + /* + * Nobody else should be calling this function other than system PM, + * hence we can run without locks. + */ + list_for_each_entry(p, &ctrlr->cache, list) { + if (!is_req_valid(p)) { + pr_debug("%s: skipping RPMH req: a:%#x s:%#x w:%#x", + __func__, p->addr, p->sleep_val, p->wake_val); + continue; + } + ret = send_single(dev, RPMH_SLEEP_STATE, p->addr, p->sleep_val); + if (ret) + return ret; + ret = send_single(dev, RPMH_WAKE_ONLY_STATE, + p->addr, p->wake_val); + if (ret) + return ret; + } + + ctrlr->dirty = false; + + return 0; +} +EXPORT_SYMBOL(rpmh_flush); + +/** + * rpmh_invalidate: Invalidate all sleep and active sets + * sets. + * + * @dev: The device making the request + * + * Invalidate the sleep and active values in the TCS blocks. + */ +int rpmh_invalidate(const struct device *dev) +{ + struct rpmh_ctrlr *ctrlr = get_rpmh_ctrlr(dev); + int ret; + + ctrlr->dirty = true; + + do { + ret = rpmh_rsc_invalidate(ctrlr_to_drv(ctrlr)); + } while (ret == -EAGAIN); + + return ret; +} +EXPORT_SYMBOL(rpmh_invalidate); diff --git a/include/soc/qcom/rpmh.h b/include/soc/qcom/rpmh.h index c1d0f902bd71..42e62a0d26d8 100644 --- a/include/soc/qcom/rpmh.h +++ b/include/soc/qcom/rpmh.h @@ -14,12 +14,23 @@ int rpmh_write(const struct device *dev, enum rpmh_state state, const struct tcs_cmd *cmd, u32 n); +int rpmh_flush(const struct device *dev); + +int rpmh_invalidate(const struct device *dev); + #else static inline int rpmh_write(const struct device *dev, enum rpmh_state state, const struct tcs_cmd *cmd, u32 n) { return -ENODEV; } + +static inline int rpmh_flush(const struct device *dev) +{ return -ENODEV; } + +static inline int rpmh_invalidate(const struct device *dev) +{ return -ENODEV; } + #endif /* CONFIG_QCOM_RPMH */ #endif /* __SOC_QCOM_RPMH_H__ */ -- cgit v1.2.3 From 564b5e24ccd4c840a7f84dfd952e5715dd9b3966 Mon Sep 17 00:00:00 2001 From: Lina Iyer Date: Wed, 20 Jun 2018 18:57:05 +0530 Subject: drivers: qcom: rpmh: allow requests to be sent asynchronously Platform drivers that want to send a request but do not want to block until the RPMH request completes have now a new API - rpmh_write_async(). The API allocates memory and send the requests and returns the control back to the platform driver. The tx_done callback from the controller is handled in the context of the controller's thread and frees the allocated memory. This API allows RPMH requests from atomic contexts as well. Signed-off-by: Lina Iyer Signed-off-by: Raju P.L.S.S.S.N Signed-off-by: Andy Gross --- drivers/soc/qcom/rpmh-internal.h | 2 ++ drivers/soc/qcom/rpmh.c | 51 ++++++++++++++++++++++++++++++++++++++++ include/soc/qcom/rpmh.h | 7 ++++++ 3 files changed, 60 insertions(+) (limited to 'include') diff --git a/drivers/soc/qcom/rpmh-internal.h b/drivers/soc/qcom/rpmh-internal.h index 101145c9db1c..6a8a4b7aeead 100644 --- a/drivers/soc/qcom/rpmh-internal.h +++ b/drivers/soc/qcom/rpmh-internal.h @@ -54,6 +54,7 @@ struct tcs_group { * @completion: triggered when request is done * @dev: the device making the request * @err: err return from the controller + * @needs_free: check to free dynamically allocated request object */ struct rpmh_request { struct tcs_request msg; @@ -61,6 +62,7 @@ struct rpmh_request { struct completion *completion; const struct device *dev; int err; + bool needs_free; }; /** diff --git a/drivers/soc/qcom/rpmh.c b/drivers/soc/qcom/rpmh.c index c355ba13e73f..1e3d34876af1 100644 --- a/drivers/soc/qcom/rpmh.c +++ b/drivers/soc/qcom/rpmh.c @@ -34,6 +34,7 @@ .cmd = { { 0 } }, \ .completion = q, \ .dev = dev, \ + .needs_free = false, \ } #define ctrlr_to_drv(ctrlr) container_of(ctrlr, struct rsc_drv, client) @@ -75,6 +76,9 @@ void rpmh_tx_done(const struct tcs_request *msg, int r) /* Signal the blocking thread we are done */ if (compl) complete(compl); + + if (rpm_msg->needs_free) + kfree(rpm_msg); } static struct cache_req *__find_req(struct rpmh_ctrlr *ctrlr, u32 addr) @@ -180,6 +184,53 @@ static int __rpmh_write(const struct device *dev, enum rpmh_state state, return ret; } +static int __fill_rpmh_msg(struct rpmh_request *req, enum rpmh_state state, + const struct tcs_cmd *cmd, u32 n) +{ + if (!cmd || !n || n > MAX_RPMH_PAYLOAD) + return -EINVAL; + + memcpy(req->cmd, cmd, n * sizeof(*cmd)); + + req->msg.state = state; + req->msg.cmds = req->cmd; + req->msg.num_cmds = n; + + return 0; +} + +/** + * rpmh_write_async: Write a set of RPMH commands + * + * @dev: The device making the request + * @state: Active/sleep set + * @cmd: The payload data + * @n: The number of elements in payload + * + * Write a set of RPMH commands, the order of commands is maintained + * and will be sent as a single shot. + */ +int rpmh_write_async(const struct device *dev, enum rpmh_state state, + const struct tcs_cmd *cmd, u32 n) +{ + struct rpmh_request *rpm_msg; + int ret; + + rpm_msg = kzalloc(sizeof(*rpm_msg), GFP_ATOMIC); + if (!rpm_msg) + return -ENOMEM; + rpm_msg->needs_free = true; + + ret = __fill_rpmh_msg(rpm_msg, state, cmd, n); + if (ret) { + kfree(rpm_msg); + return ret; + } + + return __rpmh_write(dev, state, rpm_msg); +} +EXPORT_SYMBOL(rpmh_write_async); + /** * rpmh_write: Write a set of RPMH commands and block until response * diff --git a/include/soc/qcom/rpmh.h b/include/soc/qcom/rpmh.h index 42e62a0d26d8..1161a5c77e75 100644 --- a/include/soc/qcom/rpmh.h +++ b/include/soc/qcom/rpmh.h @@ -14,6 +14,9 @@ int rpmh_write(const struct device *dev, enum rpmh_state state, const struct tcs_cmd *cmd, u32 n); +int rpmh_write_async(const struct device *dev, enum rpmh_state state, + const struct tcs_cmd *cmd, u32 n); + int rpmh_flush(const struct device *dev); int rpmh_invalidate(const struct device *dev); @@ -24,6 +27,10 @@ static inline int rpmh_write(const struct device *dev, enum rpmh_state state, const struct tcs_cmd *cmd, u32 n) { return -ENODEV; } +static inline int rpmh_write_async(const struct device *dev, + enum rpmh_state state, + const struct tcs_cmd *cmd, u32 n) +{ return -ENODEV; } static inline int rpmh_flush(const struct device *dev) { return -ENODEV; } -- cgit v1.2.3 From c8790cb6da58d3fa09dfa707aa486fe6769c23bc Mon Sep 17 00:00:00 2001 From: Lina Iyer Date: Wed, 20 Jun 2018 18:57:06 +0530 Subject: drivers: qcom: rpmh: add support for batch RPMH request Platform drivers need make a lot of resource state requests at the same time, say, at the start or end of an usecase. It can be quite inefficient to send each request separately. Instead they can give the RPMH library a batch of requests to be sent and wait on the whole transaction to be complete. rpmh_write_batch() is a blocking call that can be used to send multiple RPMH command sets. Each RPMH command set is set asynchronously and the API blocks until all the command sets are complete and receive their tx_done callbacks. Signed-off-by: Lina Iyer Signed-off-by: Raju P.L.S.S.S.N Reviewed-by: Matthias Kaehlcke Signed-off-by: Andy Gross --- drivers/soc/qcom/rpmh-internal.h | 2 + drivers/soc/qcom/rpmh-rsc.c | 1 + drivers/soc/qcom/rpmh.c | 159 ++++++++++++++++++++++++++++++++++++++- include/soc/qcom/rpmh.h | 8 ++ 4 files changed, 168 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/soc/qcom/rpmh-internal.h b/drivers/soc/qcom/rpmh-internal.h index 6a8a4b7aeead..a7bbbb67991c 100644 --- a/drivers/soc/qcom/rpmh-internal.h +++ b/drivers/soc/qcom/rpmh-internal.h @@ -71,11 +71,13 @@ struct rpmh_request { * @cache: the list of cached requests * @cache_lock: synchronize access to the cache data * @dirty: was the cache updated since flush + * @batch_cache: Cache sleep and wake requests sent as batch */ struct rpmh_ctrlr { struct list_head cache; spinlock_t cache_lock; bool dirty; + struct list_head batch_cache; }; /** diff --git a/drivers/soc/qcom/rpmh-rsc.c b/drivers/soc/qcom/rpmh-rsc.c index 5d0dd0581904..4c0c1f24911a 100644 --- a/drivers/soc/qcom/rpmh-rsc.c +++ b/drivers/soc/qcom/rpmh-rsc.c @@ -636,6 +636,7 @@ static int rpmh_rsc_probe(struct platform_device *pdev) spin_lock_init(&drv->client.cache_lock); INIT_LIST_HEAD(&drv->client.cache); + INIT_LIST_HEAD(&drv->client.batch_cache); dev_set_drvdata(&pdev->dev, drv); diff --git a/drivers/soc/qcom/rpmh.c b/drivers/soc/qcom/rpmh.c index 1e3d34876af1..c7beb6841289 100644 --- a/drivers/soc/qcom/rpmh.c +++ b/drivers/soc/qcom/rpmh.c @@ -54,6 +54,20 @@ struct cache_req { struct list_head list; }; +/** + * struct batch_cache_req - An entry in our batch catch + * + * @list: linked list obj + * @count: number of messages + * @rpm_msgs: the messages + */ + +struct batch_cache_req { + struct list_head list; + int count; + struct rpmh_request rpm_msgs[]; +}; + static struct rpmh_ctrlr *get_rpmh_ctrlr(const struct device *dev) { struct rsc_drv *drv = dev_get_drvdata(dev->parent); @@ -73,10 +87,13 @@ void rpmh_tx_done(const struct tcs_request *msg, int r) dev_err(rpm_msg->dev, "RPMH TX fail in msg addr=%#x, err=%d\n", rpm_msg->msg.cmds[0].addr, r); + if (!compl) + goto exit; + /* Signal the blocking thread we are done */ - if (compl) - complete(compl); + complete(compl); +exit: if (rpm_msg->needs_free) kfree(rpm_msg); } @@ -264,6 +281,138 @@ int rpmh_write(const struct device *dev, enum rpmh_state state, } EXPORT_SYMBOL(rpmh_write); +static void cache_batch(struct rpmh_ctrlr *ctrlr, struct batch_cache_req *req) +{ + unsigned long flags; + + spin_lock_irqsave(&ctrlr->cache_lock, flags); + list_add_tail(&req->list, &ctrlr->batch_cache); + spin_unlock_irqrestore(&ctrlr->cache_lock, flags); +} + +static int flush_batch(struct rpmh_ctrlr *ctrlr) +{ + struct batch_cache_req *req; + const struct rpmh_request *rpm_msg; + unsigned long flags; + int ret = 0; + int i; + + /* Send Sleep/Wake requests to the controller, expect no response */ + spin_lock_irqsave(&ctrlr->cache_lock, flags); + list_for_each_entry(req, &ctrlr->batch_cache, list) { + for (i = 0; i < req->count; i++) { + rpm_msg = req->rpm_msgs + i; + ret = rpmh_rsc_write_ctrl_data(ctrlr_to_drv(ctrlr), + &rpm_msg->msg); + if (ret) + break; + } + } + spin_unlock_irqrestore(&ctrlr->cache_lock, flags); + + return ret; +} + +static void invalidate_batch(struct rpmh_ctrlr *ctrlr) +{ + struct batch_cache_req *req, *tmp; + unsigned long flags; + + spin_lock_irqsave(&ctrlr->cache_lock, flags); + list_for_each_entry_safe(req, tmp, &ctrlr->batch_cache, list) + kfree(req); + INIT_LIST_HEAD(&ctrlr->batch_cache); + spin_unlock_irqrestore(&ctrlr->cache_lock, flags); +} + +/** + * rpmh_write_batch: Write multiple sets of RPMH commands and wait for the + * batch to finish. + * + * @dev: the device making the request + * @state: Active/sleep set + * @cmd: The payload data + * @n: The array of count of elements in each batch, 0 terminated. + * + * Write a request to the RSC controller without caching. If the request + * state is ACTIVE, then the requests are treated as completion request + * and sent to the controller immediately. The function waits until all the + * commands are complete. If the request was to SLEEP or WAKE_ONLY, then the + * request is sent as fire-n-forget and no ack is expected. + * + * May sleep. Do not call from atomic contexts for ACTIVE_ONLY requests. + */ +int rpmh_write_batch(const struct device *dev, enum rpmh_state state, + const struct tcs_cmd *cmd, u32 *n) +{ + struct batch_cache_req *req; + struct rpmh_request *rpm_msgs; + DECLARE_COMPLETION_ONSTACK(compl); + struct rpmh_ctrlr *ctrlr = get_rpmh_ctrlr(dev); + unsigned long time_left; + int count = 0; + int ret, i, j; + + if (!cmd || !n) + return -EINVAL; + + while (n[count] > 0) + count++; + if (!count) + return -EINVAL; + + req = kzalloc(sizeof(*req) + count * sizeof(req->rpm_msgs[0]), + GFP_ATOMIC); + if (!req) + return -ENOMEM; + req->count = count; + rpm_msgs = req->rpm_msgs; + + for (i = 0; i < count; i++) { + __fill_rpmh_msg(rpm_msgs + i, state, cmd, n[i]); + cmd += n[i]; + } + + if (state != RPMH_ACTIVE_ONLY_STATE) { + cache_batch(ctrlr, req); + return 0; + } + + for (i = 0; i < count; i++) { + rpm_msgs[i].completion = &compl; + ret = rpmh_rsc_send_data(ctrlr_to_drv(ctrlr), &rpm_msgs[i].msg); + if (ret) { + pr_err("Error(%d) sending RPMH message addr=%#x\n", + ret, rpm_msgs[i].msg.cmds[0].addr); + for (j = i; j < count; j++) + rpmh_tx_done(&rpm_msgs[j].msg, ret); + break; + } + } + + time_left = RPMH_TIMEOUT_MS; + for (i = 0; i < count; i++) { + time_left = wait_for_completion_timeout(&compl, time_left); + if (!time_left) { + /* + * Better hope they never finish because they'll signal + * the completion on our stack and that's bad once + * we've returned from the function. + */ + WARN_ON(1); + ret = -ETIMEDOUT; + goto exit; + } + } + +exit: + kfree(req); + + return ret; +} +EXPORT_SYMBOL(rpmh_write_batch); + static int is_req_valid(struct cache_req *req) { return (req->sleep_val != UINT_MAX && @@ -309,6 +458,11 @@ int rpmh_flush(const struct device *dev) return 0; } + /* First flush the cached batch requests */ + ret = flush_batch(ctrlr); + if (ret) + return ret; + /* * Nobody else should be calling this function other than system PM, * hence we can run without locks. @@ -347,6 +501,7 @@ int rpmh_invalidate(const struct device *dev) struct rpmh_ctrlr *ctrlr = get_rpmh_ctrlr(dev); int ret; + invalidate_batch(ctrlr); ctrlr->dirty = true; do { diff --git a/include/soc/qcom/rpmh.h b/include/soc/qcom/rpmh.h index 1161a5c77e75..619e07c75da9 100644 --- a/include/soc/qcom/rpmh.h +++ b/include/soc/qcom/rpmh.h @@ -17,6 +17,9 @@ int rpmh_write(const struct device *dev, enum rpmh_state state, int rpmh_write_async(const struct device *dev, enum rpmh_state state, const struct tcs_cmd *cmd, u32 n); +int rpmh_write_batch(const struct device *dev, enum rpmh_state state, + const struct tcs_cmd *cmd, u32 *n); + int rpmh_flush(const struct device *dev); int rpmh_invalidate(const struct device *dev); @@ -32,6 +35,11 @@ static inline int rpmh_write_async(const struct device *dev, const struct tcs_cmd *cmd, u32 n) { return -ENODEV; } +static inline int rpmh_write_batch(const struct device *dev, + enum rpmh_state state, + const struct tcs_cmd *cmd, u32 *n) +{ return -ENODEV; } + static inline int rpmh_flush(const struct device *dev) { return -ENODEV; } -- cgit v1.2.3 From a0b1561f846191a1967e8f5a26d8ef59c1b9162a Mon Sep 17 00:00:00 2001 From: Niklas Cassel Date: Tue, 12 Jun 2018 15:23:13 +0200 Subject: firmware: qcom: scm: add a dummy qcom_scm_assign_mem() Add a dummy qcom_scm_assign_mem() to enable building drivers when CONFIG_COMPILE_TEST=y && CONFIG_QCOM_SCM=n. All other qcom_scm_* functions already have a dummy version. Signed-off-by: Niklas Cassel Reviewed-by: Bjorn Andersson Signed-off-by: Andy Gross --- include/linux/qcom_scm.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h index b401b962afff..5d65521260b3 100644 --- a/include/linux/qcom_scm.h +++ b/include/linux/qcom_scm.h @@ -87,6 +87,10 @@ static inline int qcom_scm_pas_mem_setup(u32 peripheral, phys_addr_t addr, static inline int qcom_scm_pas_auth_and_reset(u32 peripheral) { return -ENODEV; } static inline int qcom_scm_pas_shutdown(u32 peripheral) { return -ENODEV; } +static inline int qcom_scm_assign_mem(phys_addr_t mem_addr, size_t mem_sz, + unsigned int *src, + struct qcom_scm_vmperm *newvm, + int dest_cnt) { return -ENODEV; } static inline void qcom_scm_cpu_power_down(u32 flags) {} static inline u32 qcom_scm_get_version(void) { return 0; } static inline u32 -- cgit v1.2.3 From c4db9c1e8c70bc60e392da8a485bcfb035d559c2 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Fri, 20 Jul 2018 10:47:23 +0900 Subject: efi: Deduplicate efi_open_volume() There's one ARM, one x86_32 and one x86_64 version of efi_open_volume() which can be folded into a single shared version by masking their differences with the efi_call_proto() macro introduced by commit: 3552fdf29f01 ("efi: Allow bitness-agnostic protocol calls"). To be able to dereference the device_handle attribute from the efi_loaded_image_t table in an arch- and bitness-agnostic manner, introduce the efi_table_attr() macro (which already exists for x86) to arm and arm64. No functional change intended. Signed-off-by: Lukas Wunner Signed-off-by: Ard Biesheuvel Cc: Andy Shevchenko Cc: Hans de Goede Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/20180720014726.24031-7-ard.biesheuvel@linaro.org Signed-off-by: Ingo Molnar --- arch/arm/include/asm/efi.h | 3 ++ arch/arm64/include/asm/efi.h | 3 ++ arch/x86/boot/compressed/eboot.c | 63 -------------------------- drivers/firmware/efi/libstub/arm-stub.c | 25 ---------- drivers/firmware/efi/libstub/efi-stub-helper.c | 31 ++++++++++++- drivers/firmware/efi/libstub/efistub.h | 3 -- include/linux/efi.h | 10 ++++ 7 files changed, 45 insertions(+), 93 deletions(-) (limited to 'include') diff --git a/arch/arm/include/asm/efi.h b/arch/arm/include/asm/efi.h index 17f1f1a814ff..38badaae8d9d 100644 --- a/arch/arm/include/asm/efi.h +++ b/arch/arm/include/asm/efi.h @@ -58,6 +58,9 @@ void efi_virtmap_unload(void); #define efi_call_runtime(f, ...) sys_table_arg->runtime->f(__VA_ARGS__) #define efi_is_64bit() (false) +#define efi_table_attr(table, attr, instance) \ + ((table##_t *)instance)->attr + #define efi_call_proto(protocol, f, instance, ...) \ ((protocol##_t *)instance)->f(instance, ##__VA_ARGS__) diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h index 192d791f1103..7ed320895d1f 100644 --- a/arch/arm64/include/asm/efi.h +++ b/arch/arm64/include/asm/efi.h @@ -87,6 +87,9 @@ static inline unsigned long efi_get_max_initrd_addr(unsigned long dram_base, #define efi_call_runtime(f, ...) sys_table_arg->runtime->f(__VA_ARGS__) #define efi_is_64bit() (true) +#define efi_table_attr(table, attr, instance) \ + ((table##_t *)instance)->attr + #define efi_call_proto(protocol, f, instance, ...) \ ((protocol##_t *)instance)->f(instance, ##__VA_ARGS__) diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index 92b573fd239c..915c64edbe8e 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -41,69 +41,6 @@ static void setup_boot_services##bits(struct efi_config *c) \ BOOT_SERVICES(32); BOOT_SERVICES(64); -static inline efi_status_t __open_volume32(void *__image, void **__fh) -{ - efi_file_io_interface_t *io; - efi_loaded_image_32_t *image = __image; - efi_file_handle_32_t *fh; - efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID; - efi_status_t status; - void *handle = (void *)(unsigned long)image->device_handle; - unsigned long func; - - status = efi_call_early(handle_protocol, handle, - &fs_proto, (void **)&io); - if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to handle fs_proto\n"); - return status; - } - - func = (unsigned long)io->open_volume; - status = efi_early->call(func, io, &fh); - if (status != EFI_SUCCESS) - efi_printk(sys_table, "Failed to open volume\n"); - - *__fh = fh; - - return status; -} - -static inline efi_status_t __open_volume64(void *__image, void **__fh) -{ - efi_file_io_interface_t *io; - efi_loaded_image_64_t *image = __image; - efi_file_handle_64_t *fh; - efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID; - efi_status_t status; - void *handle = (void *)(unsigned long)image->device_handle; - unsigned long func; - - status = efi_call_early(handle_protocol, handle, - &fs_proto, (void **)&io); - if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to handle fs_proto\n"); - return status; - } - - func = (unsigned long)io->open_volume; - status = efi_early->call(func, io, &fh); - if (status != EFI_SUCCESS) - efi_printk(sys_table, "Failed to open volume\n"); - - *__fh = fh; - - return status; -} - -efi_status_t -efi_open_volume(efi_system_table_t *sys_table, void *__image, void **__fh) -{ - if (efi_early->is64) - return __open_volume64(__image, __fh); - - return __open_volume32(__image, __fh); -} - void efi_char16_printk(efi_system_table_t *table, efi_char16_t *str) { efi_call_proto(efi_simple_text_output_protocol, output_string, diff --git a/drivers/firmware/efi/libstub/arm-stub.c b/drivers/firmware/efi/libstub/arm-stub.c index c98b1856fc3d..6920033de6d4 100644 --- a/drivers/firmware/efi/libstub/arm-stub.c +++ b/drivers/firmware/efi/libstub/arm-stub.c @@ -40,31 +40,6 @@ static u64 virtmap_base = EFI_RT_VIRTUAL_BASE; -efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg, - void *__image, void **__fh) -{ - efi_file_io_interface_t *io; - efi_loaded_image_t *image = __image; - efi_file_handle_t *fh; - efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID; - efi_status_t status; - void *handle = (void *)(unsigned long)image->device_handle; - - status = sys_table_arg->boottime->handle_protocol(handle, - &fs_proto, (void **)&io); - if (status != EFI_SUCCESS) { - efi_printk(sys_table_arg, "Failed to handle fs_proto\n"); - return status; - } - - status = io->open_volume(io, &fh); - if (status != EFI_SUCCESS) - efi_printk(sys_table_arg, "Failed to open volume\n"); - - *__fh = fh; - return status; -} - void efi_char16_printk(efi_system_table_t *sys_table_arg, efi_char16_t *str) { diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c index 50a9cab5a834..e94975f4655b 100644 --- a/drivers/firmware/efi/libstub/efi-stub-helper.c +++ b/drivers/firmware/efi/libstub/efi-stub-helper.c @@ -413,6 +413,34 @@ static efi_status_t efi_file_close(void *handle) return efi_call_proto(efi_file_handle, close, handle); } +static efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg, + efi_loaded_image_t *image, + efi_file_handle_t **__fh) +{ + efi_file_io_interface_t *io; + efi_file_handle_t *fh; + efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID; + efi_status_t status; + void *handle = (void *)(unsigned long)efi_table_attr(efi_loaded_image, + device_handle, + image); + + status = efi_call_early(handle_protocol, handle, + &fs_proto, (void **)&io); + if (status != EFI_SUCCESS) { + efi_printk(sys_table_arg, "Failed to handle fs_proto\n"); + return status; + } + + status = efi_call_proto(efi_file_io_interface, open_volume, io, &fh); + if (status != EFI_SUCCESS) + efi_printk(sys_table_arg, "Failed to open volume\n"); + else + *__fh = fh; + + return status; +} + /* * Parse the ASCII string 'cmdline' for EFI options, denoted by the efi= * option, e.g. efi=nochunk. @@ -563,8 +591,7 @@ efi_status_t handle_cmdline_files(efi_system_table_t *sys_table_arg, /* Only open the volume once. */ if (!i) { - status = efi_open_volume(sys_table_arg, image, - (void **)&fh); + status = efi_open_volume(sys_table_arg, image, &fh); if (status != EFI_SUCCESS) goto free_files; } diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h index f59564b72ddc..32799cf039ef 100644 --- a/drivers/firmware/efi/libstub/efistub.h +++ b/drivers/firmware/efi/libstub/efistub.h @@ -36,9 +36,6 @@ extern int __pure is_quiet(void); void efi_char16_printk(efi_system_table_t *, efi_char16_t *); -efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg, void *__image, - void **__fh); - unsigned long get_dram_base(efi_system_table_t *sys_table_arg); efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table, diff --git a/include/linux/efi.h b/include/linux/efi.h index e190652f5ef9..401e4b254e30 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -894,6 +894,16 @@ typedef struct _efi_file_handle { void *flush; } efi_file_handle_t; +typedef struct { + u64 revision; + u32 open_volume; +} efi_file_io_interface_32_t; + +typedef struct { + u64 revision; + u64 open_volume; +} efi_file_io_interface_64_t; + typedef struct _efi_file_io_interface { u64 revision; int (*open_volume)(struct _efi_file_io_interface *, -- cgit v1.2.3 From 042f8825569d628517784d558aefe23c212f0fb2 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 20 Jul 2018 21:14:38 -0700 Subject: nfp: bring back support for offloading shared blocks Now that we have offload replay infrastructure added by commit 326367427cc0 ("net: sched: call reoffload op on block callback reg") and flows are guaranteed to be removed correctly, we can revert commit 951a8ee6def3 ("nfp: reject binding to shared blocks"). Signed-off-by: Jakub Kicinski Reviewed-by: John Hurley Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/bpf/main.c | 3 --- drivers/net/ethernet/netronome/nfp/flower/offload.c | 3 --- include/net/pkt_cls.h | 5 ----- 3 files changed, 11 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c index 458f49235d06..994d2b756fe1 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c @@ -195,9 +195,6 @@ static int nfp_bpf_setup_tc_block(struct net_device *netdev, if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS) return -EOPNOTSUPP; - if (tcf_block_shared(f->block)) - return -EOPNOTSUPP; - switch (f->command) { case TC_BLOCK_BIND: return tcf_block_cb_register(f->block, diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index 43b9bf12b174..6bc8a97f7e03 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -631,9 +631,6 @@ static int nfp_flower_setup_tc_block(struct net_device *netdev, if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS) return -EOPNOTSUPP; - if (tcf_block_shared(f->block)) - return -EOPNOTSUPP; - switch (f->command) { case TC_BLOCK_BIND: return tcf_block_cb_register(f->block, diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index e4252a176eec..4f405ca8346f 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -114,11 +114,6 @@ void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q, { } -static inline bool tcf_block_shared(struct tcf_block *block) -{ - return false; -} - static inline struct Qdisc *tcf_block_q(struct tcf_block *block) { return NULL; -- cgit v1.2.3 From 40c6f9c28ef03f2f2c3ee58c2447a6e6b9a713f2 Mon Sep 17 00:00:00 2001 From: Revanth Rajashekar Date: Fri, 15 Jun 2018 12:39:27 -0600 Subject: nvme.h: resync with nvme-cli Added some feature ids present in nvme-cli but not kernel. Signed-off-by: Revanth Rajashekar Signed-off-by: Christoph Hellwig --- include/linux/nvme.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 2950ce957656..80dfedcf0bf7 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -749,6 +749,11 @@ enum { NVME_FEAT_HOST_MEM_BUF = 0x0d, NVME_FEAT_TIMESTAMP = 0x0e, NVME_FEAT_KATO = 0x0f, + NVME_FEAT_HCTM = 0x10, + NVME_FEAT_NOPSC = 0x11, + NVME_FEAT_RRL = 0x12, + NVME_FEAT_PLM_CONFIG = 0x13, + NVME_FEAT_PLM_WINDOW = 0x14, NVME_FEAT_SW_PROGRESS = 0x80, NVME_FEAT_HOST_ID = 0x81, NVME_FEAT_RESV_MASK = 0x82, -- cgit v1.2.3 From 977d5ad39f3ea12ac0bd51d75020cea5ecdca235 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Tue, 17 Jul 2018 17:19:11 +0300 Subject: ACPI: Convert ACPI reference args to generic fwnode reference args Convert all users of struct acpi_reference_args to more generic fwnode_reference_args. This will 1) avoid an ACPI specific references to device nodes with integer arguments as well as 2) allow making references to nodes other than device nodes in ACPI. As a by-product, convert the fwnode interger arguments to u64. The arguments were 64-bit integers on ACPI but the fwnode arguments were just 32-bit. Signed-off-by: Sakari Ailus Signed-off-by: Rafael J. Wysocki --- drivers/acpi/property.c | 36 ++++++++--------------- drivers/gpio/gpiolib-acpi.c | 11 ++++--- drivers/infiniband/hw/hns/hns_roce_hw_v1.c | 10 +++---- drivers/media/v4l2-core/v4l2-fwnode.c | 2 +- drivers/net/ethernet/apm/xgene/xgene_enet_hw.c | 6 ++-- drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c | 6 ++-- drivers/net/ethernet/hisilicon/hns/hns_enet.c | 8 +++-- include/linux/acpi.h | 17 ++++------- include/linux/fwnode.h | 2 +- 9 files changed, 43 insertions(+), 55 deletions(-) (limited to 'include') diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c index 5815356ea6ad..3fa40010fd67 100644 --- a/drivers/acpi/property.c +++ b/drivers/acpi/property.c @@ -579,7 +579,7 @@ static int acpi_data_get_property_array(const struct acpi_device_data *data, */ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode, const char *propname, size_t index, size_t num_args, - struct acpi_reference_args *args) + struct fwnode_reference_args *args) { const union acpi_object *element, *end; const union acpi_object *obj; @@ -607,7 +607,7 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode, if (ret) return ret == -ENODEV ? -EINVAL : ret; - args->adev = device; + args->fwnode = acpi_fwnode_handle(device); args->nargs = 0; return 0; } @@ -653,11 +653,11 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode, return -EINVAL; } - if (nargs > MAX_ACPI_REFERENCE_ARGS) + if (nargs > NR_FWNODE_REFERENCE_ARGS) return -EINVAL; if (idx == index) { - args->adev = device; + args->fwnode = acpi_fwnode_handle(device); args->nargs = nargs; for (i = 0; i < nargs; i++) args->args[i] = element[i].integer.value; @@ -1089,7 +1089,7 @@ int acpi_graph_get_remote_endpoint(const struct fwnode_handle *__fwnode, { struct fwnode_handle *fwnode; unsigned int port_nr, endpoint_nr; - struct acpi_reference_args args; + struct fwnode_reference_args args; int ret; memset(&args, 0, sizeof(args)); @@ -1098,6 +1098,10 @@ int acpi_graph_get_remote_endpoint(const struct fwnode_handle *__fwnode, if (ret) return ret; + /* Ensure this is a device node. */ + if (!is_acpi_device_node(args.fwnode)) + return -ENODEV; + /* * Always require two arguments with the reference: port and * endpoint indices. @@ -1105,7 +1109,7 @@ int acpi_graph_get_remote_endpoint(const struct fwnode_handle *__fwnode, if (args.nargs != 2) return -EPROTO; - fwnode = acpi_fwnode_handle(args.adev); + fwnode = args.fwnode; port_nr = args.args[0]; endpoint_nr = args.args[1]; @@ -1209,24 +1213,8 @@ acpi_fwnode_get_reference_args(const struct fwnode_handle *fwnode, unsigned int args_count, unsigned int index, struct fwnode_reference_args *args) { - struct acpi_reference_args acpi_args; - unsigned int i; - int ret; - - ret = __acpi_node_get_property_reference(fwnode, prop, index, - args_count, &acpi_args); - if (ret < 0) - return ret; - if (!args) - return 0; - - args->nargs = acpi_args.nargs; - args->fwnode = acpi_fwnode_handle(acpi_args.adev); - - for (i = 0; i < NR_FWNODE_REFERENCE_ARGS; i++) - args->args[i] = i < acpi_args.nargs ? acpi_args.args[i] : 0; - - return 0; + return __acpi_node_get_property_reference(fwnode, prop, index, + args_count, args); } static struct fwnode_handle * diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c index e2232cbcec8b..4e8fdae1cde4 100644 --- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -353,7 +353,7 @@ EXPORT_SYMBOL_GPL(devm_acpi_dev_remove_driver_gpios); static bool acpi_get_driver_gpio_data(struct acpi_device *adev, const char *name, int index, - struct acpi_reference_args *args, + struct fwnode_reference_args *args, unsigned int *quirks) { const struct acpi_gpio_mapping *gm; @@ -365,7 +365,7 @@ static bool acpi_get_driver_gpio_data(struct acpi_device *adev, if (!strcmp(name, gm->name) && gm->data && index < gm->size) { const struct acpi_gpio_params *par = gm->data + index; - args->adev = adev; + args->fwnode = acpi_fwnode_handle(adev); args->args[0] = par->crs_entry_index; args->args[1] = par->line_index; args->args[2] = par->active_low; @@ -528,7 +528,7 @@ static int acpi_gpio_property_lookup(struct fwnode_handle *fwnode, const char *propname, int index, struct acpi_gpio_lookup *lookup) { - struct acpi_reference_args args; + struct fwnode_reference_args args; unsigned int quirks = 0; int ret; @@ -549,6 +549,8 @@ static int acpi_gpio_property_lookup(struct fwnode_handle *fwnode, * The property was found and resolved, so need to lookup the GPIO based * on returned args. */ + if (!to_acpi_device_node(args.fwnode)) + return -EINVAL; if (args.nargs != 3) return -EPROTO; @@ -556,8 +558,9 @@ static int acpi_gpio_property_lookup(struct fwnode_handle *fwnode, lookup->pin_index = args.args[1]; lookup->active_low = !!args.args[2]; - lookup->info.adev = args.adev; + lookup->info.adev = to_acpi_device_node(args.fwnode); lookup->info.quirks = quirks; + return 0; } diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c index 8013d69c5ac4..8444234ed092 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c @@ -1435,7 +1435,7 @@ static int hns_roce_v1_reset(struct hns_roce_dev *hr_dev, bool dereset) } fwnode = &dsaf_node->fwnode; } else if (is_acpi_device_node(dev->fwnode)) { - struct acpi_reference_args args; + struct fwnode_reference_args args; ret = acpi_node_get_property_reference(dev->fwnode, "dsaf-handle", 0, &args); @@ -1443,7 +1443,7 @@ static int hns_roce_v1_reset(struct hns_roce_dev *hr_dev, bool dereset) dev_err(dev, "could not find dsaf-handle\n"); return ret; } - fwnode = acpi_fwnode_handle(args.adev); + fwnode = args.fwnode; } else { dev_err(dev, "cannot read data from DT or ACPI\n"); return -ENXIO; @@ -4835,16 +4835,14 @@ static int hns_roce_get_cfg(struct hns_roce_dev *hr_dev) continue; pdev = of_find_device_by_node(net_node); } else if (is_acpi_device_node(dev->fwnode)) { - struct acpi_reference_args args; - struct fwnode_handle *fwnode; + struct fwnode_reference_args args; ret = acpi_node_get_property_reference(dev->fwnode, "eth-handle", i, &args); if (ret) continue; - fwnode = acpi_fwnode_handle(args.adev); - pdev = hns_roce_find_pdev(fwnode); + pdev = hns_roce_find_pdev(args.fwnode); } else { dev_err(dev, "cannot read data from DT or ACPI\n"); return -ENXIO; diff --git a/drivers/media/v4l2-core/v4l2-fwnode.c b/drivers/media/v4l2-core/v4l2-fwnode.c index 3f77aa318035..82595cebc0b8 100644 --- a/drivers/media/v4l2-core/v4l2-fwnode.c +++ b/drivers/media/v4l2-core/v4l2-fwnode.c @@ -739,7 +739,7 @@ static struct fwnode_handle *v4l2_fwnode_reference_get_int_prop( const char * const *props, unsigned int nprops) { struct fwnode_reference_args fwnode_args; - unsigned int *args = fwnode_args.args; + u64 *args = fwnode_args.args; struct fwnode_handle *child; int ret; diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c index 3188f553da35..078a04dc1182 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c @@ -836,19 +836,19 @@ static void xgene_enet_adjust_link(struct net_device *ndev) #ifdef CONFIG_ACPI static struct acpi_device *acpi_phy_find_device(struct device *dev) { - struct acpi_reference_args args; + struct fwnode_reference_args args; struct fwnode_handle *fw_node; int status; fw_node = acpi_fwnode_handle(ACPI_COMPANION(dev)); status = acpi_node_get_property_reference(fw_node, "phy-handle", 0, &args); - if (ACPI_FAILURE(status)) { + if (ACPI_FAILURE(status) || !is_acpi_device_node(args.fwnode)) { dev_dbg(dev, "No matching phy in ACPI table\n"); return NULL; } - return args.adev; + return to_acpi_device_node(args.fwnode); } #endif diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c index 9dcc5765f11f..794516718d9d 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c @@ -708,7 +708,7 @@ hns_mac_register_phydev(struct mii_bus *mdio, struct hns_mac_cb *mac_cb, static int hns_mac_register_phy(struct hns_mac_cb *mac_cb) { - struct acpi_reference_args args; + struct fwnode_reference_args args; struct platform_device *pdev; struct mii_bus *mii_bus; int rc; @@ -722,13 +722,15 @@ static int hns_mac_register_phy(struct hns_mac_cb *mac_cb) mac_cb->fw_port, "mdio-node", 0, &args); if (rc) return rc; + if (!is_acpi_device_node(args.fwnode)) + return -EINVAL; addr = hns_mac_phy_parse_addr(mac_cb->dev, mac_cb->fw_port); if (addr < 0) return addr; /* dev address in adev */ - pdev = hns_dsaf_find_platform_device(acpi_fwnode_handle(args.adev)); + pdev = hns_dsaf_find_platform_device(args.fwnode); if (!pdev) { dev_err(mac_cb->dev, "mac%d mdio pdev is NULL\n", mac_cb->mac_id); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index ef9ef703d13a..5608f807d7ba 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -2377,7 +2377,7 @@ static int hns_nic_dev_probe(struct platform_device *pdev) } priv->fwnode = &ae_node->fwnode; } else if (is_acpi_node(dev->fwnode)) { - struct acpi_reference_args args; + struct fwnode_reference_args args; if (acpi_dev_found(hns_enet_acpi_match[0].id)) priv->enet_ver = AE_VERSION_1; @@ -2393,7 +2393,11 @@ static int hns_nic_dev_probe(struct platform_device *pdev) dev_err(dev, "not find ae-handle\n"); goto out_read_prop_fail; } - priv->fwnode = acpi_fwnode_handle(args.adev); + if (!is_acpi_device_node(args.fwnode)) { + ret = -EINVAL; + goto out_read_prop_fail; + } + priv->fwnode = args.fwnode; } else { dev_err(dev, "cannot read cfg data from OF or acpi\n"); return -ENXIO; diff --git a/include/linux/acpi.h b/include/linux/acpi.h index e54f40974eb0..11cf39719fd8 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1058,27 +1058,20 @@ static inline int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index) /* Device properties */ -#define MAX_ACPI_REFERENCE_ARGS 8 -struct acpi_reference_args { - struct acpi_device *adev; - size_t nargs; - u64 args[MAX_ACPI_REFERENCE_ARGS]; -}; - #ifdef CONFIG_ACPI int acpi_dev_get_property(const struct acpi_device *adev, const char *name, acpi_object_type type, const union acpi_object **obj); int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode, const char *name, size_t index, size_t num_args, - struct acpi_reference_args *args); + struct fwnode_reference_args *args); static inline int acpi_node_get_property_reference( const struct fwnode_handle *fwnode, const char *name, size_t index, - struct acpi_reference_args *args) + struct fwnode_reference_args *args) { return __acpi_node_get_property_reference(fwnode, name, index, - MAX_ACPI_REFERENCE_ARGS, args); + NR_FWNODE_REFERENCE_ARGS, args); } int acpi_node_prop_get(const struct fwnode_handle *fwnode, const char *propname, @@ -1169,7 +1162,7 @@ static inline int acpi_dev_get_property(struct acpi_device *adev, static inline int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode, const char *name, size_t index, size_t num_args, - struct acpi_reference_args *args) + struct fwnode_reference_args *args) { return -ENXIO; } @@ -1177,7 +1170,7 @@ __acpi_node_get_property_reference(const struct fwnode_handle *fwnode, static inline int acpi_node_get_property_reference(const struct fwnode_handle *fwnode, const char *name, size_t index, - struct acpi_reference_args *args) + struct fwnode_reference_args *args) { return -ENXIO; } diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index 4fe8f289b3f6..faebf0ca0686 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -45,7 +45,7 @@ struct fwnode_endpoint { struct fwnode_reference_args { struct fwnode_handle *fwnode; unsigned int nargs; - unsigned int args[NR_FWNODE_REFERENCE_ARGS]; + u64 args[NR_FWNODE_REFERENCE_ARGS]; }; /** -- cgit v1.2.3 From 0ef7478639c5165a672f01b4024aacfffa951813 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Tue, 17 Jul 2018 17:19:14 +0300 Subject: ACPI: property: Make the ACPI graph API private The fwnode graph API is preferred over the ACPI graph API. Therefore make the ACPI graph API private, and use it as a back-end for the fwnode graph API only. Unused functionality is removed while the functionality actually used remains the same. Signed-off-by: Sakari Ailus Signed-off-by: Rafael J. Wysocki --- drivers/acpi/property.c | 83 ++++++++++--------------------------------------- include/linux/acpi.h | 8 ----- 2 files changed, 16 insertions(+), 75 deletions(-) (limited to 'include') diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c index 5878d3678b38..19bdada64435 100644 --- a/drivers/acpi/property.c +++ b/drivers/acpi/property.c @@ -1033,10 +1033,10 @@ struct fwnode_handle *acpi_node_get_parent(const struct fwnode_handle *fwnode) * @prev: Previous endpoint node or %NULL to get the first * * Looks up next endpoint ACPI firmware node below a given @fwnode. Returns - * %NULL if there is no next endpoint, ERR_PTR() in case of error. In case - * of success the next endpoint is returned. + * %NULL if there is no next endpoint or in case of error. In case of success + * the next endpoint is returned. */ -struct fwnode_handle *acpi_graph_get_next_endpoint( +static struct fwnode_handle *acpi_graph_get_next_endpoint( const struct fwnode_handle *fwnode, struct fwnode_handle *prev) { struct fwnode_handle *port = NULL; @@ -1065,11 +1065,9 @@ struct fwnode_handle *acpi_graph_get_next_endpoint( endpoint = fwnode_get_next_child_node(port, NULL); } - if (endpoint) { - /* Endpoints must have "endpoint" property */ - if (!fwnode_property_present(endpoint, "endpoint")) - return ERR_PTR(-EPROTO); - } + /* Endpoints must have "endpoint" property */ + if (!fwnode_property_present(endpoint, "endpoint")) + return NULL; return endpoint; } @@ -1106,18 +1104,12 @@ static struct fwnode_handle *acpi_graph_get_child_prop_value( /** * acpi_graph_get_remote_enpoint - Parses and returns remote end of an endpoint * @fwnode: Endpoint firmware node pointing to a remote device - * @parent: Firmware node of remote port parent is filled here if not %NULL - * @port: Firmware node of remote port is filled here if not %NULL * @endpoint: Firmware node of remote endpoint is filled here if not %NULL * - * Function parses remote end of ACPI firmware remote endpoint and fills in - * fields requested by the caller. Returns %0 in case of success and - * negative errno otherwise. + * Returns the remote endpoint corresponding to @__fwnode. NULL on error. */ -int acpi_graph_get_remote_endpoint(const struct fwnode_handle *__fwnode, - struct fwnode_handle **parent, - struct fwnode_handle **port, - struct fwnode_handle **endpoint) +static struct fwnode_handle * +acpi_graph_get_remote_endpoint(const struct fwnode_handle *__fwnode) { struct fwnode_handle *fwnode; unsigned int port_nr, endpoint_nr; @@ -1128,47 +1120,27 @@ int acpi_graph_get_remote_endpoint(const struct fwnode_handle *__fwnode, ret = acpi_node_get_property_reference(__fwnode, "remote-endpoint", 0, &args); if (ret) - return ret; + return NULL; /* Ensure this is a device node. */ if (!is_acpi_device_node(args.fwnode)) - return -ENODEV; + return NULL; /* * Always require two arguments with the reference: port and * endpoint indices. */ if (args.nargs != 2) - return -EPROTO; + return NULL; fwnode = args.fwnode; port_nr = args.args[0]; endpoint_nr = args.args[1]; - if (parent) - *parent = fwnode; - - if (!port && !endpoint) - return 0; - fwnode = acpi_graph_get_child_prop_value(fwnode, "port", port_nr); - if (!fwnode) - return -EPROTO; - - if (port) - *port = fwnode; - - if (!endpoint) - return 0; - - fwnode = acpi_graph_get_child_prop_value(fwnode, "endpoint", - endpoint_nr); - if (!fwnode) - return -EPROTO; - *endpoint = fwnode; - - return 0; + return acpi_graph_get_child_prop_value(fwnode, "endpoint", + endpoint_nr); } static bool acpi_fwnode_device_is_available(const struct fwnode_handle *fwnode) @@ -1232,29 +1204,6 @@ acpi_fwnode_get_reference_args(const struct fwnode_handle *fwnode, args_count, args); } -static struct fwnode_handle * -acpi_fwnode_graph_get_next_endpoint(const struct fwnode_handle *fwnode, - struct fwnode_handle *prev) -{ - struct fwnode_handle *endpoint; - - endpoint = acpi_graph_get_next_endpoint(fwnode, prev); - if (IS_ERR(endpoint)) - return NULL; - - return endpoint; -} - -static struct fwnode_handle * -acpi_fwnode_graph_get_remote_endpoint(const struct fwnode_handle *fwnode) -{ - struct fwnode_handle *endpoint = NULL; - - acpi_graph_get_remote_endpoint(fwnode, NULL, NULL, &endpoint); - - return endpoint; -} - static struct fwnode_handle * acpi_fwnode_get_parent(struct fwnode_handle *fwnode) { @@ -1295,9 +1244,9 @@ acpi_fwnode_device_get_match_data(const struct fwnode_handle *fwnode, .get_named_child_node = acpi_fwnode_get_named_child_node, \ .get_reference_args = acpi_fwnode_get_reference_args, \ .graph_get_next_endpoint = \ - acpi_fwnode_graph_get_next_endpoint, \ + acpi_graph_get_next_endpoint, \ .graph_get_remote_endpoint = \ - acpi_fwnode_graph_get_remote_endpoint, \ + acpi_graph_get_remote_endpoint, \ .graph_get_port_parent = acpi_fwnode_get_parent, \ .graph_parse_endpoint = acpi_fwnode_graph_parse_endpoint, \ }; \ diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 11cf39719fd8..de8d3d3fa651 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1089,14 +1089,6 @@ struct fwnode_handle *acpi_get_next_subnode(const struct fwnode_handle *fwnode, struct fwnode_handle *child); struct fwnode_handle *acpi_node_get_parent(const struct fwnode_handle *fwnode); -struct fwnode_handle * -acpi_graph_get_next_endpoint(const struct fwnode_handle *fwnode, - struct fwnode_handle *prev); -int acpi_graph_get_remote_endpoint(const struct fwnode_handle *fwnode, - struct fwnode_handle **remote, - struct fwnode_handle **port, - struct fwnode_handle **endpoint); - struct acpi_probe_entry; typedef bool (*acpi_probe_entry_validate_subtbl)(struct acpi_subtable_header *, struct acpi_probe_entry *); -- cgit v1.2.3 From 0e3fd810c4f41dbd63fb7caddc11684959176727 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 10 Jul 2018 16:46:41 +0200 Subject: Documentation: document ktime_get_*() APIs As Dave Chinner points out, we don't have a proper documentation for the ktime_get() family of interfaces, making it rather unclear which of the over 30 (!) interfaces one should actually use in a driver or elsewhere in the kernel. I wrote up an explanation from how I personally see the interfaces, documenting what each of the functions do and hopefully making it a bit clearer which should be used where. This is the first time I tried writing .rst format documentation, so in addition to any mistakes in the content, I probably also introduce nonstandard formatting ;-) I first tried to add an extra section to Documentation/timers/timekeeping.txt, but this is currently not included in the generated API, and it seems useful to have the API docs as part of what gets generated in https://www.kernel.org/doc/html/latest/core-api/index.html#core-utilities instead, so I started a new file there. I also considered adding the documentation inline in the include/linux/timekeeping.h header, but couldn't figure out how to do that in a way that would result both in helpful inline comments as well as readable html output, so I settled for the latter, with a small note pointing to it from the header. Cc: Dave Chinner Cc: John Stultz Cc: Thomas Gleixner Cc: Stephen Boyd Tested-by: Randy Dunlap Reviewed-by: Randy Dunlap Reviewed-by: Linus Walleij Signed-off-by: Arnd Bergmann Signed-off-by: Jonathan Corbet --- Documentation/core-api/index.rst | 1 + Documentation/core-api/timekeeping.rst | 185 +++++++++++++++++++++++++++++++++ include/linux/timekeeping.h | 15 +++ 3 files changed, 201 insertions(+) create mode 100644 Documentation/core-api/timekeeping.rst (limited to 'include') diff --git a/Documentation/core-api/index.rst b/Documentation/core-api/index.rst index f5a66b72f984..989c97cc232a 100644 --- a/Documentation/core-api/index.rst +++ b/Documentation/core-api/index.rst @@ -28,6 +28,7 @@ Core utilities printk-formats circular-buffers gfp_mask-from-fs-io + timekeeping Interfaces for kernel debugging =============================== diff --git a/Documentation/core-api/timekeeping.rst b/Documentation/core-api/timekeeping.rst new file mode 100644 index 000000000000..93cbeb9daec0 --- /dev/null +++ b/Documentation/core-api/timekeeping.rst @@ -0,0 +1,185 @@ +ktime accessors +=============== + +Device drivers can read the current time using ktime_get() and the many +related functions declared in linux/timekeeping.h. As a rule of thumb, +using an accessor with a shorter name is preferred over one with a longer +name if both are equally fit for a particular use case. + +Basic ktime_t based interfaces +------------------------------ + +The recommended simplest form returns an opaque ktime_t, with variants +that return time for different clock references: + + +.. c:function:: ktime_t ktime_get( void ) + + CLOCK_MONOTONIC + + Useful for reliable timestamps and measuring short time intervals + accurately. Starts at system boot time but stops during suspend. + +.. c:function:: ktime_t ktime_get_boottime( void ) + + CLOCK_BOOTTIME + + Like ktime_get(), but does not stop when suspended. This can be + used e.g. for key expiration times that need to be synchronized + with other machines across a suspend operation. + +.. c:function:: ktime_t ktime_get_real( void ) + + CLOCK_REALTIME + + Returns the time in relative to the UNIX epoch starting in 1970 + using the Coordinated Universal Time (UTC), same as gettimeofday() + user space. This is used for all timestamps that need to + persist across a reboot, like inode times, but should be avoided + for internal uses, since it can jump backwards due to a leap + second update, NTP adjustment settimeofday() operation from user + space. + +.. c:function:: ktime_t ktime_get_clocktai( void ) + + CLOCK_TAI + + Like ktime_get_real(), but uses the International Atomic Time (TAI) + reference instead of UTC to avoid jumping on leap second updates. + This is rarely useful in the kernel. + +.. c:function:: ktime_t ktime_get_raw( void ) + + CLOCK_MONOTONIC_RAW + + Like ktime_get(), but runs at the same rate as the hardware + clocksource without (NTP) adjustments for clock drift. This is + also rarely needed in the kernel. + +nanosecond, timespec64, and second output +----------------------------------------- + +For all of the above, there are variants that return the time in a +different format depending on what is required by the user: + +.. c:function:: u64 ktime_get_ns( void ) + u64 ktime_get_boottime_ns( void ) + u64 ktime_get_real_ns( void ) + u64 ktime_get_tai_ns( void ) + u64 ktime_get_raw_ns( void ) + + Same as the plain ktime_get functions, but returning a u64 number + of nanoseconds in the respective time reference, which may be + more convenient for some callers. + +.. c:function:: void ktime_get_ts64( struct timespec64 * ) + void ktime_get_boottime_ts64( struct timespec64 * ) + void ktime_get_real_ts64( struct timespec64 * ) + void ktime_get_clocktai_ts64( struct timespec64 * ) + void ktime_get_raw_ts64( struct timespec64 * ) + + Same above, but returns the time in a 'struct timespec64', split + into seconds and nanoseconds. This can avoid an extra division + when printing the time, or when passing it into an external + interface that expects a 'timespec' or 'timeval' structure. + +.. c:function:: time64_t ktime_get_seconds( void ) + time64_t ktime_get_boottime_seconds( void ) + time64_t ktime_get_real_seconds( void ) + time64_t ktime_get_clocktai_seconds( void ) + time64_t ktime_get_raw_seconds( void ) + + Return a coarse-grained version of the time as a scalar + time64_t. This avoids accessing the clock hardware and rounds + down the seconds to the full seconds of the last timer tick + using the respective reference. + +Coarse and fast_ns access +------------------------- + +Some additional variants exist for more specialized cases: + +.. c:function:: ktime_t ktime_get_coarse_boottime( void ) + ktime_t ktime_get_coarse_real( void ) + ktime_t ktime_get_coarse_clocktai( void ) + ktime_t ktime_get_coarse_raw( void ) + +.. c:function:: void ktime_get_coarse_ts64( struct timespec64 * ) + void ktime_get_coarse_boottime_ts64( struct timespec64 * ) + void ktime_get_coarse_real_ts64( struct timespec64 * ) + void ktime_get_coarse_clocktai_ts64( struct timespec64 * ) + void ktime_get_coarse_raw_ts64( struct timespec64 * ) + + These are quicker than the non-coarse versions, but less accurate, + corresponding to CLOCK_MONONOTNIC_COARSE and CLOCK_REALTIME_COARSE + in user space, along with the equivalent boottime/tai/raw + timebase not available in user space. + + The time returned here corresponds to the last timer tick, which + may be as much as 10ms in the past (for CONFIG_HZ=100), same as + reading the 'jiffies' variable. These are only useful when called + in a fast path and one still expects better than second accuracy, + but can't easily use 'jiffies', e.g. for inode timestamps. + Skipping the hardware clock access saves around 100 CPU cycles + on most modern machines with a reliable cycle counter, but + up to several microseconds on older hardware with an external + clocksource. + +.. c:function:: u64 ktime_get_mono_fast_ns( void ) + u64 ktime_get_raw_fast_ns( void ) + u64 ktime_get_boot_fast_ns( void ) + u64 ktime_get_real_fast_ns( void ) + + These variants are safe to call from any context, including from + a non-maskable interrupt (NMI) during a timekeeper update, and + while we are entering suspend with the clocksource powered down. + This is useful in some tracing or debugging code as well as + machine check reporting, but most drivers should never call them, + since the time is allowed to jump under certain conditions. + +Deprecated time interfaces +-------------------------- + +Older kernels used some other interfaces that are now being phased out +but may appear in third-party drivers being ported here. In particular, +all interfaces returning a 'struct timeval' or 'struct timespec' have +been replaced because the tv_sec member overflows in year 2038 on 32-bit +architectures. These are the recommended replacements: + +.. c:function:: void ktime_get_ts( struct timespec * ) + + Use ktime_get() or ktime_get_ts64() instead. + +.. c:function:: struct timeval do_gettimeofday( void ) + struct timespec getnstimeofday( void ) + struct timespec64 getnstimeofday64( void ) + void ktime_get_real_ts( struct timespec * ) + + ktime_get_real_ts64() is a direct replacement, but consider using + monotonic time (ktime_get_ts64()) and/or a ktime_t based interface + (ktime_get()/ktime_get_real()). + +.. c:function:: struct timespec current_kernel_time( void ) + struct timespec64 current_kernel_time64( void ) + struct timespec get_monotonic_coarse( void ) + struct timespec64 get_monotonic_coarse64( void ) + + These are replaced by ktime_get_coarse_real_ts64() and + ktime_get_coarse_ts64(). However, A lot of code that wants + coarse-grained times can use the simple 'jiffies' instead, while + some drivers may actually want the higher resolution accessors + these days. + +.. c:function:: struct timespec getrawmonotonic( void ) + struct timespec64 getrawmonotonic64( void ) + struct timespec timekeeping_clocktai( void ) + struct timespec64 timekeeping_clocktai64( void ) + struct timespec get_monotonic_boottime( void ) + struct timespec64 get_monotonic_boottime64( void ) + + These are replaced by ktime_get_raw()/ktime_get_raw_ts64(), + ktime_get_clocktai()/ktime_get_clocktai_ts64() as well + as ktime_get_boottime()/ktime_get_boottime_ts64(). + However, if the particular choice of clock source is not + important for the user, consider converting to + ktime_get()/ktime_get_ts64() instead for consistency. diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 86bc2026efce..947b1b8d2d01 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -20,6 +20,21 @@ extern int do_settimeofday64(const struct timespec64 *ts); extern int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz); +/* + * ktime_get() family: read the current time in a multitude of ways, + * + * The default time reference is CLOCK_MONOTONIC, starting at + * boot time but not counting the time spent in suspend. + * For other references, use the functions with "real", "clocktai", + * "boottime" and "raw" suffixes. + * + * To get the time in a different format, use the ones wit + * "ns", "ts64" and "seconds" suffix. + * + * See Documentation/core-api/timekeeping.rst for more details. + */ + + /* * timespec64 based interfaces */ -- cgit v1.2.3 From 2756f68c314917d03eb348084edb08bb929139d9 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Mon, 23 Jul 2018 11:16:59 +0300 Subject: net: bridge: add support for backup port This patch adds a new port attribute - IFLA_BRPORT_BACKUP_PORT, which allows to set a backup port to be used for known unicast traffic if the port has gone carrier down. The backup pointer is rcu protected and set only under RTNL, a counter is maintained so when deleting a port we know how many other ports reference it as a backup and we remove it from all. Also the pointer is in the first cache line which is hot at the time of the check and thus in the common case we only add one more test. The backup port will be used only for the non-flooding case since it's a part of the bridge and the flooded packets will be forwarded to it anyway. To remove the forwarding just send a 0/non-existing backup port. This is used to avoid numerous scalability problems when using MLAG most notably if we have thousands of fdbs one would need to change all of them on port carrier going down which takes too long and causes a storm of fdb notifications (and again when the port comes back up). In a Multi-chassis Link Aggregation setup usually hosts are connected to two different switches which act as a single logical switch. Those switches usually have a control and backup link between them called peerlink which might be used for communication in case a host loses connectivity to one of them. We need a fast way to failover in case a host port goes down and currently none of the solutions (like bond) cannot fulfill the requirements because the participating ports are actually the "master" devices and must have the same peerlink as their backup interface and at the same time all of them must participate in the bridge device. As Roopa noted it's normal practice in routing called fast re-route where a precalculated backup path is used when the main one is down. Another use case of this is with EVPN, having a single vxlan device which is backup of every port. Due to the nature of master devices it's not currently possible to use one device as a backup for many and still have all of them participate in the bridge (which is master itself). More detailed information about MLAG is available at the link below. https://docs.cumulusnetworks.com/display/DOCS/Multi-Chassis+Link+Aggregation+-+MLAG Further explanation and a diagram by Roopa: Two switches acting in a MLAG pair are connected by the peerlink interface which is a bridge port. the config on one of the switches looks like the below. The other switch also has a similar config. eth0 is connected to one port on the server. And the server is connected to both switches. br0 -- team0---eth0 | -- switch-peerlink Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_forward.c | 16 ++++++++++++- net/bridge/br_if.c | 53 ++++++++++++++++++++++++++++++++++++++++++++ net/bridge/br_netlink.c | 30 ++++++++++++++++++++++++- net/bridge/br_private.h | 3 +++ net/bridge/br_sysfs_if.c | 33 +++++++++++++++++++++++++++ 6 files changed, 134 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 8759cfb8aa2e..01b5069a73a5 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -334,6 +334,7 @@ enum { IFLA_BRPORT_GROUP_FWD_MASK, IFLA_BRPORT_NEIGH_SUPPRESS, IFLA_BRPORT_ISOLATED, + IFLA_BRPORT_BACKUP_PORT, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 9019f326fe81..5372e2042adf 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -142,7 +142,20 @@ static int deliver_clone(const struct net_bridge_port *prev, void br_forward(const struct net_bridge_port *to, struct sk_buff *skb, bool local_rcv, bool local_orig) { - if (to && should_deliver(to, skb)) { + if (unlikely(!to)) + goto out; + + /* redirect to backup link if the destination port is down */ + if (rcu_access_pointer(to->backup_port) && !netif_carrier_ok(to->dev)) { + struct net_bridge_port *backup_port; + + backup_port = rcu_dereference(to->backup_port); + if (unlikely(!backup_port)) + goto out; + to = backup_port; + } + + if (should_deliver(to, skb)) { if (local_rcv) deliver_clone(to, skb, local_orig); else @@ -150,6 +163,7 @@ void br_forward(const struct net_bridge_port *to, return; } +out: if (!local_rcv) kfree_skb(skb); } diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index e7c8d55212aa..0363f1bdc401 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -170,6 +170,58 @@ void br_manage_promisc(struct net_bridge *br) } } +int nbp_backup_change(struct net_bridge_port *p, + struct net_device *backup_dev) +{ + struct net_bridge_port *old_backup = rtnl_dereference(p->backup_port); + struct net_bridge_port *backup_p = NULL; + + ASSERT_RTNL(); + + if (backup_dev) { + if (!br_port_exists(backup_dev)) + return -ENOENT; + + backup_p = br_port_get_rtnl(backup_dev); + if (backup_p->br != p->br) + return -EINVAL; + } + + if (p == backup_p) + return -EINVAL; + + if (old_backup == backup_p) + return 0; + + /* if the backup link is already set, clear it */ + if (old_backup) + old_backup->backup_redirected_cnt--; + + if (backup_p) + backup_p->backup_redirected_cnt++; + rcu_assign_pointer(p->backup_port, backup_p); + + return 0; +} + +static void nbp_backup_clear(struct net_bridge_port *p) +{ + nbp_backup_change(p, NULL); + if (p->backup_redirected_cnt) { + struct net_bridge_port *cur_p; + + list_for_each_entry(cur_p, &p->br->port_list, list) { + struct net_bridge_port *backup_p; + + backup_p = rtnl_dereference(cur_p->backup_port); + if (backup_p == p) + nbp_backup_change(cur_p, NULL); + } + } + + WARN_ON(rcu_access_pointer(p->backup_port) || p->backup_redirected_cnt); +} + static void nbp_update_port_count(struct net_bridge *br) { struct net_bridge_port *p; @@ -295,6 +347,7 @@ static void del_nbp(struct net_bridge_port *p) nbp_vlan_flush(p); br_fdb_delete_by_port(br, p, 0, 1); switchdev_deferred_process(); + nbp_backup_clear(p); nbp_update_port_count(br); diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 9f5eb05b0373..ec2b58a09f76 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -169,13 +169,15 @@ static inline size_t br_nlmsg_size(struct net_device *dev, u32 filter_mask) + nla_total_size(1) /* IFLA_OPERSTATE */ + nla_total_size(br_port_info_size()) /* IFLA_PROTINFO */ + nla_total_size(br_get_link_af_size_filtered(dev, - filter_mask)); /* IFLA_AF_SPEC */ + filter_mask)) /* IFLA_AF_SPEC */ + + nla_total_size(4); /* IFLA_BRPORT_BACKUP_PORT */ } static int br_port_fill_attrs(struct sk_buff *skb, const struct net_bridge_port *p) { u8 mode = !!(p->flags & BR_HAIRPIN_MODE); + struct net_bridge_port *backup_p; u64 timerval; if (nla_put_u8(skb, IFLA_BRPORT_STATE, p->state) || @@ -237,6 +239,14 @@ static int br_port_fill_attrs(struct sk_buff *skb, return -EMSGSIZE; #endif + /* we might be called only with br->lock */ + rcu_read_lock(); + backup_p = rcu_dereference(p->backup_port); + if (backup_p) + nla_put_u32(skb, IFLA_BRPORT_BACKUP_PORT, + backup_p->dev->ifindex); + rcu_read_unlock(); + return 0; } @@ -663,6 +673,7 @@ static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = { [IFLA_BRPORT_GROUP_FWD_MASK] = { .type = NLA_U16 }, [IFLA_BRPORT_NEIGH_SUPPRESS] = { .type = NLA_U8 }, [IFLA_BRPORT_ISOLATED] = { .type = NLA_U8 }, + [IFLA_BRPORT_BACKUP_PORT] = { .type = NLA_U32 }, }; /* Change the state of the port and notify spanning tree */ @@ -817,6 +828,23 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[]) if (err) return err; + if (tb[IFLA_BRPORT_BACKUP_PORT]) { + struct net_device *backup_dev = NULL; + u32 backup_ifindex; + + backup_ifindex = nla_get_u32(tb[IFLA_BRPORT_BACKUP_PORT]); + if (backup_ifindex) { + backup_dev = __dev_get_by_index(dev_net(p->dev), + backup_ifindex); + if (!backup_dev) + return -ENOENT; + } + + err = nbp_backup_change(p, backup_dev); + if (err) + return err; + } + br_port_flags_change(p, old_flags ^ p->flags); return 0; } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index cf0005d2a4d0..11ed2029985f 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -237,6 +237,7 @@ struct net_bridge_port { #ifdef CONFIG_BRIDGE_VLAN_FILTERING struct net_bridge_vlan_group __rcu *vlgrp; #endif + struct net_bridge_port __rcu *backup_port; /* STP */ u8 priority; @@ -281,6 +282,7 @@ struct net_bridge_port { int offload_fwd_mark; #endif u16 group_fwd_mask; + u16 backup_redirected_cnt; }; #define kobj_to_brport(obj) container_of(obj, struct net_bridge_port, kobj) @@ -597,6 +599,7 @@ netdev_features_t br_features_recompute(struct net_bridge *br, netdev_features_t features); void br_port_flags_change(struct net_bridge_port *port, unsigned long mask); void br_manage_promisc(struct net_bridge *br); +int nbp_backup_change(struct net_bridge_port *p, struct net_device *backup_dev); /* br_input.c */ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb); diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c index 4ac940067754..7c87a2fe5248 100644 --- a/net/bridge/br_sysfs_if.c +++ b/net/bridge/br_sysfs_if.c @@ -191,6 +191,38 @@ static int store_group_fwd_mask(struct net_bridge_port *p, static BRPORT_ATTR(group_fwd_mask, 0644, show_group_fwd_mask, store_group_fwd_mask); +static ssize_t show_backup_port(struct net_bridge_port *p, char *buf) +{ + struct net_bridge_port *backup_p; + int ret = 0; + + rcu_read_lock(); + backup_p = rcu_dereference(p->backup_port); + if (backup_p) + ret = sprintf(buf, "%s\n", backup_p->dev->name); + rcu_read_unlock(); + + return ret; +} + +static int store_backup_port(struct net_bridge_port *p, char *buf) +{ + struct net_device *backup_dev = NULL; + char *nl = strchr(buf, '\n'); + + if (nl) + *nl = '\0'; + + if (strlen(buf) > 0) { + backup_dev = __dev_get_by_name(dev_net(p->dev), buf); + if (!backup_dev) + return -ENOENT; + } + + return nbp_backup_change(p, backup_dev); +} +static BRPORT_ATTR_RAW(backup_port, 0644, show_backup_port, store_backup_port); + BRPORT_ATTR_FLAG(hairpin_mode, BR_HAIRPIN_MODE); BRPORT_ATTR_FLAG(bpdu_guard, BR_BPDU_GUARD); BRPORT_ATTR_FLAG(root_block, BR_ROOT_BLOCK); @@ -254,6 +286,7 @@ static const struct brport_attribute *brport_attrs[] = { &brport_attr_group_fwd_mask, &brport_attr_neigh_suppress, &brport_attr_isolated, + &brport_attr_backup_port, NULL }; -- cgit v1.2.3 From c601171d7a60b5b09d7c2fe0579953323a80744e Mon Sep 17 00:00:00 2001 From: Karsten Graul Date: Mon, 23 Jul 2018 13:53:08 +0200 Subject: net/smc: provide smc mode in smc_diag.c Rename field diag_fallback into diag_mode and set the smc mode of a connection explicitly. Signed-off-by: Karsten Graul Signed-off-by: Ursula Braun Signed-off-by: David S. Miller --- include/uapi/linux/smc_diag.h | 9 ++++++++- net/smc/smc_diag.c | 7 ++++++- 2 files changed, 14 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/smc_diag.h b/include/uapi/linux/smc_diag.h index 92be255e534c..48ae3ee22b2d 100644 --- a/include/uapi/linux/smc_diag.h +++ b/include/uapi/linux/smc_diag.h @@ -20,7 +20,7 @@ struct smc_diag_req { struct smc_diag_msg { __u8 diag_family; __u8 diag_state; - __u8 diag_fallback; + __u8 diag_mode; __u8 diag_shutdown; struct inet_diag_sockid id; @@ -28,6 +28,13 @@ struct smc_diag_msg { __u64 diag_inode; }; +/* Mode of a connection */ +enum { + SMC_DIAG_MODE_SMCR, + SMC_DIAG_MODE_FALLBACK_TCP, + SMC_DIAG_MODE_SMCD, +}; + /* Extensions */ enum { diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c index 6d83eef1b743..d772cd10297e 100644 --- a/net/smc/smc_diag.c +++ b/net/smc/smc_diag.c @@ -91,7 +91,12 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb, r = nlmsg_data(nlh); smc_diag_msg_common_fill(r, sk); r->diag_state = sk->sk_state; - r->diag_fallback = smc->use_fallback; + if (smc->use_fallback) + r->diag_mode = SMC_DIAG_MODE_FALLBACK_TCP; + else if (smc->conn.lgr && smc->conn.lgr->is_smcd) + r->diag_mode = SMC_DIAG_MODE_SMCD; + else + r->diag_mode = SMC_DIAG_MODE_SMCR; user_ns = sk_user_ns(NETLINK_CB(cb->skb).sk); if (smc_diag_msg_attrs_fill(sk, skb, r, user_ns)) goto errout; -- cgit v1.2.3 From f53aaa31cce7b543e407da7e97690a700206f7b9 Mon Sep 17 00:00:00 2001 From: Feras Daoud Date: Mon, 16 Jul 2018 15:22:01 -0700 Subject: net/mlx5: FW tracer, implement tracer logic Implement FW tracer logic and registers access, initialization and cleanup flows. Initializing the tracer will be part of load one flow, as multiple PFs will try to acquire ownership but only one will succeed and will be the tracer owner. Signed-off-by: Feras Daoud Signed-off-by: Saeed Mahameed --- .../ethernet/mellanox/mlx5/core/diag/fw_tracer.c | 196 +++++++++++++++++++++ .../ethernet/mellanox/mlx5/core/diag/fw_tracer.h | 66 +++++++ include/linux/mlx5/driver.h | 3 + 3 files changed, 265 insertions(+) create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c new file mode 100644 index 000000000000..3ecbf06b4d71 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -0,0 +1,196 @@ +/* + * Copyright (c) 2018, Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include "fw_tracer.h" + +static int mlx5_query_mtrc_caps(struct mlx5_fw_tracer *tracer) +{ + u32 *string_db_base_address_out = tracer->str_db.base_address_out; + u32 *string_db_size_out = tracer->str_db.size_out; + struct mlx5_core_dev *dev = tracer->dev; + u32 out[MLX5_ST_SZ_DW(mtrc_cap)] = {0}; + u32 in[MLX5_ST_SZ_DW(mtrc_cap)] = {0}; + void *mtrc_cap_sp; + int err, i; + + err = mlx5_core_access_reg(dev, in, sizeof(in), out, sizeof(out), + MLX5_REG_MTRC_CAP, 0, 0); + if (err) { + mlx5_core_warn(dev, "FWTracer: Error reading tracer caps %d\n", + err); + return err; + } + + if (!MLX5_GET(mtrc_cap, out, trace_to_memory)) { + mlx5_core_dbg(dev, "FWTracer: Device does not support logging traces to memory\n"); + return -ENOTSUPP; + } + + tracer->trc_ver = MLX5_GET(mtrc_cap, out, trc_ver); + tracer->str_db.first_string_trace = + MLX5_GET(mtrc_cap, out, first_string_trace); + tracer->str_db.num_string_trace = + MLX5_GET(mtrc_cap, out, num_string_trace); + tracer->str_db.num_string_db = MLX5_GET(mtrc_cap, out, num_string_db); + tracer->owner = !!MLX5_GET(mtrc_cap, out, trace_owner); + + for (i = 0; i < tracer->str_db.num_string_db; i++) { + mtrc_cap_sp = MLX5_ADDR_OF(mtrc_cap, out, string_db_param[i]); + string_db_base_address_out[i] = MLX5_GET(mtrc_string_db_param, + mtrc_cap_sp, + string_db_base_address); + string_db_size_out[i] = MLX5_GET(mtrc_string_db_param, + mtrc_cap_sp, string_db_size); + } + + return err; +} + +static int mlx5_set_mtrc_caps_trace_owner(struct mlx5_fw_tracer *tracer, + u32 *out, u32 out_size, + u8 trace_owner) +{ + struct mlx5_core_dev *dev = tracer->dev; + u32 in[MLX5_ST_SZ_DW(mtrc_cap)] = {0}; + + MLX5_SET(mtrc_cap, in, trace_owner, trace_owner); + + return mlx5_core_access_reg(dev, in, sizeof(in), out, out_size, + MLX5_REG_MTRC_CAP, 0, 1); +} + +static int mlx5_fw_tracer_ownership_acquire(struct mlx5_fw_tracer *tracer) +{ + struct mlx5_core_dev *dev = tracer->dev; + u32 out[MLX5_ST_SZ_DW(mtrc_cap)] = {0}; + int err; + + err = mlx5_set_mtrc_caps_trace_owner(tracer, out, sizeof(out), + MLX5_FW_TRACER_ACQUIRE_OWNERSHIP); + if (err) { + mlx5_core_warn(dev, "FWTracer: Acquire tracer ownership failed %d\n", + err); + return err; + } + + tracer->owner = !!MLX5_GET(mtrc_cap, out, trace_owner); + + if (!tracer->owner) + return -EBUSY; + + return 0; +} + +static void mlx5_fw_tracer_ownership_release(struct mlx5_fw_tracer *tracer) +{ + u32 out[MLX5_ST_SZ_DW(mtrc_cap)] = {0}; + + mlx5_set_mtrc_caps_trace_owner(tracer, out, sizeof(out), + MLX5_FW_TRACER_RELEASE_OWNERSHIP); + tracer->owner = false; +} + +static void mlx5_fw_tracer_ownership_change(struct work_struct *work) +{ + struct mlx5_fw_tracer *tracer = container_of(work, struct mlx5_fw_tracer, + ownership_change_work); + struct mlx5_core_dev *dev = tracer->dev; + int err; + + if (tracer->owner) { + mlx5_fw_tracer_ownership_release(tracer); + return; + } + + err = mlx5_fw_tracer_ownership_acquire(tracer); + if (err) { + mlx5_core_dbg(dev, "FWTracer: Ownership was not granted %d\n", err); + return; + } +} + +struct mlx5_fw_tracer *mlx5_fw_tracer_create(struct mlx5_core_dev *dev) +{ + struct mlx5_fw_tracer *tracer = NULL; + int err; + + if (!MLX5_CAP_MCAM_REG(dev, tracer_registers)) { + mlx5_core_dbg(dev, "FWTracer: Tracer capability not present\n"); + return NULL; + } + + tracer = kzalloc(sizeof(*tracer), GFP_KERNEL); + if (!tracer) + return ERR_PTR(-ENOMEM); + + tracer->work_queue = create_singlethread_workqueue("mlx5_fw_tracer"); + if (!tracer->work_queue) { + err = -ENOMEM; + goto free_tracer; + } + + tracer->dev = dev; + + INIT_WORK(&tracer->ownership_change_work, mlx5_fw_tracer_ownership_change); + + err = mlx5_query_mtrc_caps(tracer); + if (err) { + mlx5_core_dbg(dev, "FWTracer: Failed to query capabilities %d\n", err); + goto destroy_workqueue; + } + + mlx5_fw_tracer_ownership_change(&tracer->ownership_change_work); + + return tracer; + +destroy_workqueue: + tracer->dev = NULL; + destroy_workqueue(tracer->work_queue); +free_tracer: + kfree(tracer); + return ERR_PTR(err); +} + +void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer) +{ + if (!tracer) + return; + + cancel_work_sync(&tracer->ownership_change_work); + + if (tracer->owner) + mlx5_fw_tracer_ownership_release(tracer); + + flush_workqueue(tracer->work_queue); + destroy_workqueue(tracer->work_queue); + kfree(tracer); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h new file mode 100644 index 000000000000..721c41a5e827 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h @@ -0,0 +1,66 @@ +/* + * Copyright (c) 2018, Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#ifndef __LIB_TRACER_H__ +#define __LIB_TRACER_H__ + +#include +#include "mlx5_core.h" + +#define STRINGS_DB_SECTIONS_NUM 8 + +struct mlx5_fw_tracer { + struct mlx5_core_dev *dev; + bool owner; + u8 trc_ver; + struct workqueue_struct *work_queue; + struct work_struct ownership_change_work; + + /* Strings DB */ + struct { + u8 first_string_trace; + u8 num_string_trace; + u32 num_string_db; + u32 base_address_out[STRINGS_DB_SECTIONS_NUM]; + u32 size_out[STRINGS_DB_SECTIONS_NUM]; + } str_db; +}; + +enum mlx5_fw_tracer_ownership_state { + MLX5_FW_TRACER_RELEASE_OWNERSHIP, + MLX5_FW_TRACER_ACQUIRE_OWNERSHIP, +}; + +struct mlx5_fw_tracer *mlx5_fw_tracer_create(struct mlx5_core_dev *dev); +void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer); + +#endif diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 957199c20a0f..86cb0ebf92fa 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -816,6 +816,8 @@ struct mlx5_clock { struct mlx5_pps pps_info; }; +struct mlx5_fw_tracer; + struct mlx5_core_dev { struct pci_dev *pdev; /* sync pci state */ @@ -860,6 +862,7 @@ struct mlx5_core_dev { struct mlx5_clock clock; struct mlx5_ib_clock_info *clock_info; struct page *clock_info_page; + struct mlx5_fw_tracer *tracer; }; struct mlx5_db { -- cgit v1.2.3 From c71ad41ccb0c29fce95149b74786574b354c9dda Mon Sep 17 00:00:00 2001 From: Feras Daoud Date: Wed, 7 Feb 2018 11:08:56 +0200 Subject: net/mlx5: FW tracer, events handling The tracer has one event, event 0x26, with two subtypes: - Subtype 0: Ownership change - Subtype 1: Traces available An ownership change occurs in the following cases: 1- Owner releases his ownership, in this case, an event will be sent to inform others to reattempt acquire ownership. 2- Ownership was taken by a higher priority tool, in this case the owner should understand that it lost ownership, and go through tear down flow. The second subtype indicates that there are traces in the trace buffer, in this case, the driver polls the tracer buffer for new traces, parse them and prepares the messages for printing. The HW starts tracing from the first address in the tracer buffer. Driver receives an event notifying that new trace block exists. HW posts a timestamp event at the last 8B of every 256B block. Comparing the timestamp to the last handled timestamp would indicate that this is a new trace block. Once the new timestamp is detected, the entire block is considered valid. Block validation and parsing, should be done after copying the current block to a different location, in order to avoid block overwritten during processing. Signed-off-by: Feras Daoud Signed-off-by: Saeed Mahameed --- .../ethernet/mellanox/mlx5/core/diag/fw_tracer.c | 268 ++++++++++++++++++++- .../ethernet/mellanox/mlx5/core/diag/fw_tracer.h | 71 +++++- drivers/net/ethernet/mellanox/mlx5/core/eq.c | 11 + include/linux/mlx5/device.h | 7 + 4 files changed, 347 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c index d6cc27b0ff34..bd887d1d3396 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -318,25 +318,244 @@ out: return; } -static void mlx5_fw_tracer_ownership_change(struct work_struct *work) +static void mlx5_fw_tracer_arm(struct mlx5_core_dev *dev) { - struct mlx5_fw_tracer *tracer = container_of(work, struct mlx5_fw_tracer, - ownership_change_work); - struct mlx5_core_dev *dev = tracer->dev; + u32 out[MLX5_ST_SZ_DW(mtrc_ctrl)] = {0}; + u32 in[MLX5_ST_SZ_DW(mtrc_ctrl)] = {0}; int err; - if (tracer->owner) { - mlx5_fw_tracer_ownership_release(tracer); + MLX5_SET(mtrc_ctrl, in, arm_event, 1); + + err = mlx5_core_access_reg(dev, in, sizeof(in), out, sizeof(out), + MLX5_REG_MTRC_CTRL, 0, 1); + if (err) + mlx5_core_warn(dev, "FWTracer: Failed to arm tracer event %d\n", err); +} + +static void poll_trace(struct mlx5_fw_tracer *tracer, + struct tracer_event *tracer_event, u64 *trace) +{ + u32 timestamp_low, timestamp_mid, timestamp_high, urts; + + tracer_event->event_id = MLX5_GET(tracer_event, trace, event_id); + tracer_event->lost_event = MLX5_GET(tracer_event, trace, lost); + + switch (tracer_event->event_id) { + case TRACER_EVENT_TYPE_TIMESTAMP: + tracer_event->type = TRACER_EVENT_TYPE_TIMESTAMP; + urts = MLX5_GET(tracer_timestamp_event, trace, urts); + if (tracer->trc_ver == 0) + tracer_event->timestamp_event.unreliable = !!(urts >> 2); + else + tracer_event->timestamp_event.unreliable = !!(urts & 1); + + timestamp_low = MLX5_GET(tracer_timestamp_event, + trace, timestamp7_0); + timestamp_mid = MLX5_GET(tracer_timestamp_event, + trace, timestamp39_8); + timestamp_high = MLX5_GET(tracer_timestamp_event, + trace, timestamp52_40); + + tracer_event->timestamp_event.timestamp = + ((u64)timestamp_high << 40) | + ((u64)timestamp_mid << 8) | + (u64)timestamp_low; + break; + default: + if (tracer_event->event_id >= tracer->str_db.first_string_trace || + tracer_event->event_id <= tracer->str_db.first_string_trace + + tracer->str_db.num_string_trace) { + tracer_event->type = TRACER_EVENT_TYPE_STRING; + tracer_event->string_event.timestamp = + MLX5_GET(tracer_string_event, trace, timestamp); + tracer_event->string_event.string_param = + MLX5_GET(tracer_string_event, trace, string_param); + tracer_event->string_event.tmsn = + MLX5_GET(tracer_string_event, trace, tmsn); + tracer_event->string_event.tdsn = + MLX5_GET(tracer_string_event, trace, tdsn); + } else { + tracer_event->type = TRACER_EVENT_TYPE_UNRECOGNIZED; + } + break; + } +} + +static u64 get_block_timestamp(struct mlx5_fw_tracer *tracer, u64 *ts_event) +{ + struct tracer_event tracer_event; + u8 event_id; + + event_id = MLX5_GET(tracer_event, ts_event, event_id); + + if (event_id == TRACER_EVENT_TYPE_TIMESTAMP) + poll_trace(tracer, &tracer_event, ts_event); + else + tracer_event.timestamp_event.timestamp = 0; + + return tracer_event.timestamp_event.timestamp; +} + +static void mlx5_fw_tracer_handle_traces(struct work_struct *work) +{ + struct mlx5_fw_tracer *tracer = + container_of(work, struct mlx5_fw_tracer, handle_traces_work); + u64 block_timestamp, last_block_timestamp, tmp_trace_block[TRACES_PER_BLOCK]; + u32 block_count, start_offset, prev_start_offset, prev_consumer_index; + u32 trace_event_size = MLX5_ST_SZ_BYTES(tracer_event); + struct tracer_event tracer_event; + struct mlx5_core_dev *dev; + int i; + + if (!tracer->owner) return; + + dev = tracer->dev; + block_count = tracer->buff.size / TRACER_BLOCK_SIZE_BYTE; + start_offset = tracer->buff.consumer_index * TRACER_BLOCK_SIZE_BYTE; + + /* Copy the block to local buffer to avoid HW override while being processed*/ + memcpy(tmp_trace_block, tracer->buff.log_buf + start_offset, + TRACER_BLOCK_SIZE_BYTE); + + block_timestamp = + get_block_timestamp(tracer, &tmp_trace_block[TRACES_PER_BLOCK - 1]); + + while (block_timestamp > tracer->last_timestamp) { + /* Check block override if its not the first block */ + if (!tracer->last_timestamp) { + u64 *ts_event; + /* To avoid block override be the HW in case of buffer + * wraparound, the time stamp of the previous block + * should be compared to the last timestamp handled + * by the driver. + */ + prev_consumer_index = + (tracer->buff.consumer_index - 1) & (block_count - 1); + prev_start_offset = prev_consumer_index * TRACER_BLOCK_SIZE_BYTE; + + ts_event = tracer->buff.log_buf + prev_start_offset + + (TRACES_PER_BLOCK - 1) * trace_event_size; + last_block_timestamp = get_block_timestamp(tracer, ts_event); + /* If previous timestamp different from last stored + * timestamp then there is a good chance that the + * current buffer is overwritten and therefore should + * not be parsed. + */ + if (tracer->last_timestamp != last_block_timestamp) { + mlx5_core_warn(dev, "FWTracer: Events were lost\n"); + tracer->last_timestamp = block_timestamp; + tracer->buff.consumer_index = + (tracer->buff.consumer_index + 1) & (block_count - 1); + break; + } + } + + /* Parse events */ + for (i = 0; i < TRACES_PER_BLOCK ; i++) + poll_trace(tracer, &tracer_event, &tmp_trace_block[i]); + + tracer->buff.consumer_index = + (tracer->buff.consumer_index + 1) & (block_count - 1); + + tracer->last_timestamp = block_timestamp; + start_offset = tracer->buff.consumer_index * TRACER_BLOCK_SIZE_BYTE; + memcpy(tmp_trace_block, tracer->buff.log_buf + start_offset, + TRACER_BLOCK_SIZE_BYTE); + block_timestamp = get_block_timestamp(tracer, + &tmp_trace_block[TRACES_PER_BLOCK - 1]); } + mlx5_fw_tracer_arm(dev); +} + +static int mlx5_fw_tracer_set_mtrc_conf(struct mlx5_fw_tracer *tracer) +{ + struct mlx5_core_dev *dev = tracer->dev; + u32 out[MLX5_ST_SZ_DW(mtrc_conf)] = {0}; + u32 in[MLX5_ST_SZ_DW(mtrc_conf)] = {0}; + int err; + + MLX5_SET(mtrc_conf, in, trace_mode, TRACE_TO_MEMORY); + MLX5_SET(mtrc_conf, in, log_trace_buffer_size, + ilog2(TRACER_BUFFER_PAGE_NUM)); + MLX5_SET(mtrc_conf, in, trace_mkey, tracer->buff.mkey.key); + + err = mlx5_core_access_reg(dev, in, sizeof(in), out, sizeof(out), + MLX5_REG_MTRC_CONF, 0, 1); + if (err) + mlx5_core_warn(dev, "FWTracer: Failed to set tracer configurations %d\n", err); + + return err; +} + +static int mlx5_fw_tracer_set_mtrc_ctrl(struct mlx5_fw_tracer *tracer, u8 status, u8 arm) +{ + struct mlx5_core_dev *dev = tracer->dev; + u32 out[MLX5_ST_SZ_DW(mtrc_ctrl)] = {0}; + u32 in[MLX5_ST_SZ_DW(mtrc_ctrl)] = {0}; + int err; + + MLX5_SET(mtrc_ctrl, in, modify_field_select, TRACE_STATUS); + MLX5_SET(mtrc_ctrl, in, trace_status, status); + MLX5_SET(mtrc_ctrl, in, arm_event, arm); + + err = mlx5_core_access_reg(dev, in, sizeof(in), out, sizeof(out), + MLX5_REG_MTRC_CTRL, 0, 1); + + if (!err && status) + tracer->last_timestamp = 0; + + return err; +} + +static int mlx5_fw_tracer_start(struct mlx5_fw_tracer *tracer) +{ + struct mlx5_core_dev *dev = tracer->dev; + int err; + err = mlx5_fw_tracer_ownership_acquire(tracer); if (err) { mlx5_core_dbg(dev, "FWTracer: Ownership was not granted %d\n", err); + /* Don't fail since ownership can be acquired on a later FW event */ + return 0; + } + + err = mlx5_fw_tracer_set_mtrc_conf(tracer); + if (err) { + mlx5_core_warn(dev, "FWTracer: Failed to set tracer configuration %d\n", err); + goto release_ownership; + } + + /* enable tracer & trace events */ + err = mlx5_fw_tracer_set_mtrc_ctrl(tracer, 1, 1); + if (err) { + mlx5_core_warn(dev, "FWTracer: Failed to enable tracer %d\n", err); + goto release_ownership; + } + + return 0; + +release_ownership: + mlx5_fw_tracer_ownership_release(tracer); + return err; +} + +static void mlx5_fw_tracer_ownership_change(struct work_struct *work) +{ + struct mlx5_fw_tracer *tracer = + container_of(work, struct mlx5_fw_tracer, ownership_change_work); + + if (tracer->owner) { + tracer->owner = false; + tracer->buff.consumer_index = 0; return; } + + mlx5_fw_tracer_start(tracer); } +/* Create software resources (Buffers, etc ..) */ struct mlx5_fw_tracer *mlx5_fw_tracer_create(struct mlx5_core_dev *dev) { struct mlx5_fw_tracer *tracer = NULL; @@ -361,6 +580,8 @@ struct mlx5_fw_tracer *mlx5_fw_tracer_create(struct mlx5_core_dev *dev) INIT_WORK(&tracer->ownership_change_work, mlx5_fw_tracer_ownership_change); INIT_WORK(&tracer->read_fw_strings_work, mlx5_tracer_read_strings_db); + INIT_WORK(&tracer->handle_traces_work, mlx5_fw_tracer_handle_traces); + err = mlx5_query_mtrc_caps(tracer); if (err) { @@ -392,6 +613,9 @@ free_tracer: return ERR_PTR(err); } +/* Create HW resources + start tracer + * must be called before Async EQ is created + */ int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer) { struct mlx5_core_dev *dev; @@ -417,22 +641,25 @@ int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer) goto err_dealloc_pd; } - err = mlx5_fw_tracer_ownership_acquire(tracer); - if (err) /* Don't fail since ownership can be acquired on a later FW event */ - mlx5_core_dbg(dev, "FWTracer: Ownership was not granted %d\n", err); + mlx5_fw_tracer_start(tracer); return 0; + err_dealloc_pd: mlx5_core_dealloc_pd(dev, tracer->buff.pdn); return err; } +/* Stop tracer + Cleanup HW resources + * must be called after Async EQ is destroyed + */ void mlx5_fw_tracer_cleanup(struct mlx5_fw_tracer *tracer) { if (IS_ERR_OR_NULL(tracer)) return; cancel_work_sync(&tracer->ownership_change_work); + cancel_work_sync(&tracer->handle_traces_work); if (tracer->owner) mlx5_fw_tracer_ownership_release(tracer); @@ -441,6 +668,7 @@ void mlx5_fw_tracer_cleanup(struct mlx5_fw_tracer *tracer) mlx5_core_dealloc_pd(tracer->dev, tracer->buff.pdn); } +/* Free software resources (Buffers, etc ..) */ void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer) { if (IS_ERR_OR_NULL(tracer)) @@ -454,4 +682,26 @@ void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer) kfree(tracer); } +void mlx5_fw_tracer_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe) +{ + struct mlx5_fw_tracer *tracer = dev->tracer; + + if (!tracer) + return; + + switch (eqe->sub_type) { + case MLX5_TRACER_SUBTYPE_OWNERSHIP_CHANGE: + if (test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) + queue_work(tracer->work_queue, &tracer->ownership_change_work); + break; + case MLX5_TRACER_SUBTYPE_TRACES_AVAILABLE: + if (likely(tracer->str_db.loaded)) + queue_work(tracer->work_queue, &tracer->handle_traces_work); + break; + default: + mlx5_core_dbg(dev, "FWTracer: Event with unrecognized subtype: sub_type %d\n", + eqe->sub_type); + } +} + EXPORT_TRACEPOINT_SYMBOL(mlx5_fw); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h index 66cb7e7ada28..3915e91486b2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h @@ -43,6 +43,9 @@ #define TRACER_BUFFER_CHUNK 4096 #define TRACE_BUFFER_SIZE_BYTE (TRACER_BUFFER_PAGE_NUM * TRACER_BUFFER_CHUNK) +#define TRACER_BLOCK_SIZE_BYTE 256 +#define TRACES_PER_BLOCK 32 + struct mlx5_fw_tracer { struct mlx5_core_dev *dev; bool owner; @@ -69,8 +72,11 @@ struct mlx5_fw_tracer { dma_addr_t dma; u32 size; struct mlx5_core_mkey mkey; - + u32 consumer_index; } buff; + + u64 last_timestamp; + struct work_struct handle_traces_work; }; enum mlx5_fw_tracer_ownership_state { @@ -78,7 +84,70 @@ enum mlx5_fw_tracer_ownership_state { MLX5_FW_TRACER_ACQUIRE_OWNERSHIP, }; +enum tracer_ctrl_fields_select { + TRACE_STATUS = 1 << 0, +}; + +enum tracer_event_type { + TRACER_EVENT_TYPE_STRING, + TRACER_EVENT_TYPE_TIMESTAMP = 0xFF, + TRACER_EVENT_TYPE_UNRECOGNIZED, +}; + +enum tracing_mode { + TRACE_TO_MEMORY = 1 << 0, +}; + +struct tracer_timestamp_event { + u64 timestamp; + u8 unreliable; +}; + +struct tracer_string_event { + u32 timestamp; + u32 tmsn; + u32 tdsn; + u32 string_param; +}; + +struct tracer_event { + bool lost_event; + u32 type; + u8 event_id; + union { + struct tracer_string_event string_event; + struct tracer_timestamp_event timestamp_event; + }; +}; + +struct mlx5_ifc_tracer_event_bits { + u8 lost[0x1]; + u8 timestamp[0x7]; + u8 event_id[0x8]; + u8 event_data[0x30]; +}; + +struct mlx5_ifc_tracer_string_event_bits { + u8 lost[0x1]; + u8 timestamp[0x7]; + u8 event_id[0x8]; + u8 tmsn[0xd]; + u8 tdsn[0x3]; + u8 string_param[0x20]; +}; + +struct mlx5_ifc_tracer_timestamp_event_bits { + u8 timestamp7_0[0x8]; + u8 event_id[0x8]; + u8 urts[0x3]; + u8 timestamp52_40[0xd]; + u8 timestamp39_8[0x20]; +}; + struct mlx5_fw_tracer *mlx5_fw_tracer_create(struct mlx5_core_dev *dev); +int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer); +void mlx5_fw_tracer_cleanup(struct mlx5_fw_tracer *tracer); void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer); +void mlx5_fw_tracer_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe) { return; } #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 406c23862f5f..7669b4380779 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -40,6 +40,7 @@ #include "mlx5_core.h" #include "fpga/core.h" #include "eswitch.h" +#include "diag/fw_tracer.h" enum { MLX5_EQE_SIZE = sizeof(struct mlx5_eqe), @@ -168,6 +169,8 @@ static const char *eqe_type_str(u8 type) return "MLX5_EVENT_TYPE_FPGA_QP_ERROR"; case MLX5_EVENT_TYPE_GENERAL_EVENT: return "MLX5_EVENT_TYPE_GENERAL_EVENT"; + case MLX5_EVENT_TYPE_DEVICE_TRACER: + return "MLX5_EVENT_TYPE_DEVICE_TRACER"; default: return "Unrecognized event"; } @@ -576,6 +579,11 @@ static irqreturn_t mlx5_eq_int(int irq, void *eq_ptr) case MLX5_EVENT_TYPE_GENERAL_EVENT: general_event_handler(dev, eqe); break; + + case MLX5_EVENT_TYPE_DEVICE_TRACER: + mlx5_fw_tracer_event(dev, eqe); + break; + default: mlx5_core_warn(dev, "Unhandled event 0x%x on EQ 0x%x\n", eqe->type, eq->eqn); @@ -853,6 +861,9 @@ int mlx5_start_eqs(struct mlx5_core_dev *dev) if (MLX5_CAP_GEN(dev, temp_warn_event)) async_event_mask |= (1ull << MLX5_EVENT_TYPE_TEMP_WARN_EVENT); + if (MLX5_CAP_MCAM_REG(dev, tracer_registers)) + async_event_mask |= (1ull << MLX5_EVENT_TYPE_DEVICE_TRACER); + err = mlx5_create_map_eq(dev, &table->cmd_eq, MLX5_EQ_VEC_CMD, MLX5_NUM_CMD_EQE, 1ull << MLX5_EVENT_TYPE_CMD, "mlx5_cmd_eq", MLX5_EQ_TYPE_ASYNC); diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 0566c6a94805..d489494b0a84 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -332,6 +332,13 @@ enum mlx5_event { MLX5_EVENT_TYPE_FPGA_ERROR = 0x20, MLX5_EVENT_TYPE_FPGA_QP_ERROR = 0x21, + + MLX5_EVENT_TYPE_DEVICE_TRACER = 0x26, +}; + +enum { + MLX5_TRACER_SUBTYPE_OWNERSHIP_CHANGE = 0x0, + MLX5_TRACER_SUBTYPE_TRACES_AVAILABLE = 0x1, }; enum { -- cgit v1.2.3 From 51bbf9bee34ff5d4006d266f24a54dc9c1669eb5 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Thu, 19 Jul 2018 17:27:43 -0500 Subject: PCI: hotplug: Demidlayer registration with the core When a hotplug driver calls pci_hp_register(), all steps necessary for registration are carried out in one go, including creation of a kobject and addition to sysfs. That's a problem for pciehp once it's converted to enable/disable the slot exclusively from the IRQ thread: The thread needs to be spawned after creation of the kobject (because it uses the kobject's name), but before addition to sysfs (because it will handle enable/disable requests submitted via sysfs). pci_hp_deregister() does offer a ->release callback that's invoked after deletion from sysfs and before destruction of the kobject. But because pci_hp_register() doesn't offer a counterpart, hotplug drivers' ->probe and ->remove code becomes asymmetric, which is error prone as recently discovered use-after-free bugs in pciehp's ->remove hook have shown. In a sense, this appears to be a case of the midlayer antipattern: "The core thesis of the "midlayer mistake" is that midlayers are bad and should not exist. That common functionality which it is so tempting to put in a midlayer should instead be provided as library routines which can [be] used, augmented, or ignored by each bottom level driver independently. Thus every subsystem that supports multiple implementations (or drivers) should provide a very thin top layer which calls directly into the bottom layer drivers, and a rich library of support code that eases the implementation of those drivers. This library is available to, but not forced upon, those drivers." -- Neil Brown (2009), https://lwn.net/Articles/336262/ The presence of midlayer traits in the PCI hotplug core might be ascribed to its age: When it was introduced in February 2002, the blessings of a library approach might not have been well known: https://git.kernel.org/tglx/history/c/a8a2069f432c For comparison, the driver core does offer split functions for creating a kobject (device_initialize()) and addition to sysfs (device_add()) as an alternative to carrying out everything at once (device_register()). This was introduced in October 2002: https://git.kernel.org/tglx/history/c/8b290eb19962 The odd ->release callback in the PCI hotplug core was added in 2003: https://git.kernel.org/tglx/history/c/69f8d663b595 Clearly, a library approach would not force every hotplug driver to implement a ->release callback, but rather allow the driver to remove the sysfs files, release its data structures and finally destroy the kobject. Alternatively, a driver may choose to remove everything with pci_hp_deregister(), then release its data structures. To this end, offer drivers pci_hp_initialize() and pci_hp_add() as a split-up version of pci_hp_register(). Likewise, offer pci_hp_del() and pci_hp_destroy() as a split-up version of pci_hp_deregister(). Eliminate the ->release callback and move its code into each driver's teardown routine. Declare pci_hp_deregister() void, in keeping with the usual kernel pattern that enablement can fail, but disablement cannot. It only returned an error if the caller passed in a NULL pointer or a slot which has never or is no longer registered or is sharing its name with another slot. Those would be bugs, so WARN about them. Few hotplug drivers actually checked the return value and those that did only printed a useless error message to dmesg. Remove that. For most drivers the conversion was straightforward since it doesn't matter whether the code in the ->release callback is executed before or after destruction of the kobject. But in the case of ibmphp, it was unclear to me whether setting slot_cur->ctrl and slot_cur->bus_on to NULL needs to happen before the kobject is destroyed, so I erred on the side of caution and ensured that the order stays the same. Another nontrivial case is pnv_php, I've found the list and kref logic difficult to understand, however my impression was that it is safe to delete the list element and drop the references until after the kobject is destroyed. Signed-off-by: Lukas Wunner Signed-off-by: Bjorn Helgaas Acked-by: Andy Shevchenko # drivers/platform/x86 Cc: Rafael J. Wysocki Cc: Len Brown Cc: Scott Murray Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: Gavin Shan Cc: Sebastian Ott Cc: Gerald Schaefer Cc: Corentin Chary Cc: Darren Hart Cc: Andy Shevchenko --- drivers/pci/hotplug/acpiphp_core.c | 22 +---- drivers/pci/hotplug/cpci_hotplug_core.c | 14 +--- drivers/pci/hotplug/cpqphp_core.c | 16 +--- drivers/pci/hotplug/ibmphp_core.c | 15 +++- drivers/pci/hotplug/ibmphp_ebda.c | 20 ----- drivers/pci/hotplug/pci_hotplug_core.c | 139 +++++++++++++++++++++++--------- drivers/pci/hotplug/pciehp_core.c | 19 ++--- drivers/pci/hotplug/pnv_php.c | 5 +- drivers/pci/hotplug/rpaphp_core.c | 2 +- drivers/pci/hotplug/rpaphp_slot.c | 13 +-- drivers/pci/hotplug/s390_pci_hpc.c | 13 +-- drivers/pci/hotplug/sgi_hotplug.c | 9 ++- drivers/pci/hotplug/shpchp_core.c | 20 +---- drivers/platform/x86/asus-wmi.c | 12 +-- drivers/platform/x86/eeepc-laptop.c | 12 +-- include/linux/pci_hotplug.h | 15 +++- 16 files changed, 168 insertions(+), 178 deletions(-) (limited to 'include') diff --git a/drivers/pci/hotplug/acpiphp_core.c b/drivers/pci/hotplug/acpiphp_core.c index 12b5655fd390..ad32ffbc4b91 100644 --- a/drivers/pci/hotplug/acpiphp_core.c +++ b/drivers/pci/hotplug/acpiphp_core.c @@ -254,20 +254,6 @@ static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value) return 0; } -/** - * release_slot - free up the memory used by a slot - * @hotplug_slot: slot to free - */ -static void release_slot(struct hotplug_slot *hotplug_slot) -{ - struct slot *slot = hotplug_slot->private; - - pr_debug("%s - physical_slot = %s\n", __func__, slot_name(slot)); - - kfree(slot->hotplug_slot); - kfree(slot); -} - /* callback routine to initialize 'struct slot' for each slot */ int acpiphp_register_hotplug_slot(struct acpiphp_slot *acpiphp_slot, unsigned int sun) @@ -287,7 +273,6 @@ int acpiphp_register_hotplug_slot(struct acpiphp_slot *acpiphp_slot, slot->hotplug_slot->info = &slot->info; slot->hotplug_slot->private = slot; - slot->hotplug_slot->release = &release_slot; slot->hotplug_slot->ops = &acpi_hotplug_slot_ops; slot->acpi_slot = acpiphp_slot; @@ -324,13 +309,12 @@ error: void acpiphp_unregister_hotplug_slot(struct acpiphp_slot *acpiphp_slot) { struct slot *slot = acpiphp_slot->slot; - int retval = 0; pr_info("Slot [%s] unregistered\n", slot_name(slot)); - retval = pci_hp_deregister(slot->hotplug_slot); - if (retval) - pr_err("pci_hp_deregister failed with error %d\n", retval); + pci_hp_deregister(slot->hotplug_slot); + kfree(slot->hotplug_slot); + kfree(slot); } diff --git a/drivers/pci/hotplug/cpci_hotplug_core.c b/drivers/pci/hotplug/cpci_hotplug_core.c index 07b533adc9df..52a339baf06c 100644 --- a/drivers/pci/hotplug/cpci_hotplug_core.c +++ b/drivers/pci/hotplug/cpci_hotplug_core.c @@ -195,10 +195,8 @@ get_latch_status(struct hotplug_slot *hotplug_slot, u8 *value) return 0; } -static void release_slot(struct hotplug_slot *hotplug_slot) +static void release_slot(struct slot *slot) { - struct slot *slot = hotplug_slot->private; - kfree(slot->hotplug_slot->info); kfree(slot->hotplug_slot); pci_dev_put(slot->dev); @@ -253,7 +251,6 @@ cpci_hp_register_bus(struct pci_bus *bus, u8 first, u8 last) snprintf(name, SLOT_NAME_SIZE, "%02x:%02x", bus->number, i); hotplug_slot->private = slot; - hotplug_slot->release = &release_slot; hotplug_slot->ops = &cpci_hotplug_slot_ops; /* @@ -308,12 +305,8 @@ cpci_hp_unregister_bus(struct pci_bus *bus) slots--; dbg("deregistering slot %s", slot_name(slot)); - status = pci_hp_deregister(slot->hotplug_slot); - if (status) { - err("pci_hp_deregister failed with error %d", - status); - break; - } + pci_hp_deregister(slot->hotplug_slot); + release_slot(slot); } } up_write(&list_rwsem); @@ -623,6 +616,7 @@ cleanup_slots(void) list_for_each_entry_safe(slot, tmp, &slot_list, slot_list) { list_del(&slot->slot_list); pci_hp_deregister(slot->hotplug_slot); + release_slot(slot); } cleanup_null: up_write(&list_rwsem); diff --git a/drivers/pci/hotplug/cpqphp_core.c b/drivers/pci/hotplug/cpqphp_core.c index 1797e36ec586..5a06636e910a 100644 --- a/drivers/pci/hotplug/cpqphp_core.c +++ b/drivers/pci/hotplug/cpqphp_core.c @@ -266,17 +266,6 @@ static void __iomem *get_SMBIOS_entry(void __iomem *smbios_start, return previous; } -static void release_slot(struct hotplug_slot *hotplug_slot) -{ - struct slot *slot = hotplug_slot->private; - - dbg("%s - physical_slot = %s\n", __func__, slot_name(slot)); - - kfree(slot->hotplug_slot->info); - kfree(slot->hotplug_slot); - kfree(slot); -} - static int ctrl_slot_cleanup(struct controller *ctrl) { struct slot *old_slot, *next_slot; @@ -285,9 +274,11 @@ static int ctrl_slot_cleanup(struct controller *ctrl) ctrl->slot = NULL; while (old_slot) { - /* memory will be freed by the release_slot callback */ next_slot = old_slot->next; pci_hp_deregister(old_slot->hotplug_slot); + kfree(old_slot->hotplug_slot->info); + kfree(old_slot->hotplug_slot); + kfree(old_slot); old_slot = next_slot; } @@ -678,7 +669,6 @@ static int ctrl_slot_setup(struct controller *ctrl, ((read_slot_enable(ctrl) << 2) >> ctrl_slot) & 0x04; /* register this slot with the hotplug pci core */ - hotplug_slot->release = &release_slot; hotplug_slot->private = slot; snprintf(name, SLOT_NAME_SIZE, "%u", slot->number); hotplug_slot->ops = &cpqphp_hotplug_slot_ops; diff --git a/drivers/pci/hotplug/ibmphp_core.c b/drivers/pci/hotplug/ibmphp_core.c index 1869b0411ce0..4ea57e9019f1 100644 --- a/drivers/pci/hotplug/ibmphp_core.c +++ b/drivers/pci/hotplug/ibmphp_core.c @@ -673,7 +673,20 @@ static void free_slots(void) list_for_each_entry_safe(slot_cur, next, &ibmphp_slot_head, ibm_slot_list) { - pci_hp_deregister(slot_cur->hotplug_slot); + pci_hp_del(slot_cur->hotplug_slot); + slot_cur->ctrl = NULL; + slot_cur->bus_on = NULL; + + /* + * We don't want to actually remove the resources, + * since ibmphp_free_resources() will do just that. + */ + ibmphp_unconfigure_card(&slot_cur, -1); + + pci_hp_destroy(slot_cur->hotplug_slot); + kfree(slot_cur->hotplug_slot->info); + kfree(slot_cur->hotplug_slot); + kfree(slot_cur); } debug("%s -- exit\n", __func__); } diff --git a/drivers/pci/hotplug/ibmphp_ebda.c b/drivers/pci/hotplug/ibmphp_ebda.c index 64549aa24c0f..6f8e90e3ec08 100644 --- a/drivers/pci/hotplug/ibmphp_ebda.c +++ b/drivers/pci/hotplug/ibmphp_ebda.c @@ -699,25 +699,6 @@ static int fillslotinfo(struct hotplug_slot *hotplug_slot) return rc; } -static void release_slot(struct hotplug_slot *hotplug_slot) -{ - struct slot *slot; - - if (!hotplug_slot || !hotplug_slot->private) - return; - - slot = hotplug_slot->private; - kfree(slot->hotplug_slot->info); - kfree(slot->hotplug_slot); - slot->ctrl = NULL; - slot->bus_on = NULL; - - /* we don't want to actually remove the resources, since free_resources will do just that */ - ibmphp_unconfigure_card(&slot, -1); - - kfree(slot); -} - static struct pci_driver ibmphp_driver; /* @@ -941,7 +922,6 @@ static int __init ebda_rsrc_controller(void) tmp_slot->hotplug_slot = hp_slot_ptr; hp_slot_ptr->private = tmp_slot; - hp_slot_ptr->release = release_slot; rc = fillslotinfo(hp_slot_ptr); if (rc) diff --git a/drivers/pci/hotplug/pci_hotplug_core.c b/drivers/pci/hotplug/pci_hotplug_core.c index fd93783a87b0..90fde5f106d8 100644 --- a/drivers/pci/hotplug/pci_hotplug_core.c +++ b/drivers/pci/hotplug/pci_hotplug_core.c @@ -396,8 +396,9 @@ static struct hotplug_slot *get_slot_from_name(const char *name) * @owner: caller module owner * @mod_name: caller module name * - * Registers a hotplug slot with the pci hotplug subsystem, which will allow - * userspace interaction to the slot. + * Prepares a hotplug slot for in-kernel use and immediately publishes it to + * user space in one go. Drivers may alternatively carry out the two steps + * separately by invoking pci_hp_initialize() and pci_hp_add(). * * Returns 0 if successful, anything else for an error. */ @@ -406,54 +407,91 @@ int __pci_hp_register(struct hotplug_slot *slot, struct pci_bus *bus, struct module *owner, const char *mod_name) { int result; + + result = __pci_hp_initialize(slot, bus, devnr, name, owner, mod_name); + if (result) + return result; + + result = pci_hp_add(slot); + if (result) + pci_hp_destroy(slot); + + return result; +} +EXPORT_SYMBOL_GPL(__pci_hp_register); + +/** + * __pci_hp_initialize - prepare hotplug slot for in-kernel use + * @slot: pointer to the &struct hotplug_slot to initialize + * @bus: bus this slot is on + * @devnr: slot number + * @name: name registered with kobject core + * @owner: caller module owner + * @mod_name: caller module name + * + * Allocate and fill in a PCI slot for use by a hotplug driver. Once this has + * been called, the driver may invoke hotplug_slot_name() to get the slot's + * unique name. The driver must be prepared to handle a ->reset_slot callback + * from this point on. + * + * Returns 0 on success or a negative int on error. + */ +int __pci_hp_initialize(struct hotplug_slot *slot, struct pci_bus *bus, + int devnr, const char *name, struct module *owner, + const char *mod_name) +{ struct pci_slot *pci_slot; if (slot == NULL) return -ENODEV; if ((slot->info == NULL) || (slot->ops == NULL)) return -EINVAL; - if (slot->release == NULL) { - dbg("Why are you trying to register a hotplug slot without a proper release function?\n"); - return -EINVAL; - } slot->ops->owner = owner; slot->ops->mod_name = mod_name; - mutex_lock(&pci_hp_mutex); /* * No problems if we call this interface from both ACPI_PCI_SLOT * driver and call it here again. If we've already created the * pci_slot, the interface will simply bump the refcount. */ pci_slot = pci_create_slot(bus, devnr, name, slot); - if (IS_ERR(pci_slot)) { - result = PTR_ERR(pci_slot); - goto out; - } + if (IS_ERR(pci_slot)) + return PTR_ERR(pci_slot); slot->pci_slot = pci_slot; pci_slot->hotplug = slot; + return 0; +} +EXPORT_SYMBOL_GPL(__pci_hp_initialize); - list_add(&slot->slot_list, &pci_hotplug_slot_list); +/** + * pci_hp_add - publish hotplug slot to user space + * @slot: pointer to the &struct hotplug_slot to publish + * + * Make a hotplug slot's sysfs interface available and inform user space of its + * addition by sending a uevent. The hotplug driver must be prepared to handle + * all &struct hotplug_slot_ops callbacks from this point on. + * + * Returns 0 on success or a negative int on error. + */ +int pci_hp_add(struct hotplug_slot *slot) +{ + struct pci_slot *pci_slot = slot->pci_slot; + int result; result = fs_add_slot(pci_slot); if (result) - goto err_list_del; + return result; kobject_uevent(&pci_slot->kobj, KOBJ_ADD); - dbg("Added slot %s to the list\n", name); - goto out; - -err_list_del: - list_del(&slot->slot_list); - pci_slot->hotplug = NULL; - pci_destroy_slot(pci_slot); -out: + mutex_lock(&pci_hp_mutex); + list_add(&slot->slot_list, &pci_hotplug_slot_list); mutex_unlock(&pci_hp_mutex); - return result; + dbg("Added slot %s to the list\n", hotplug_slot_name(slot)); + return 0; } -EXPORT_SYMBOL_GPL(__pci_hp_register); +EXPORT_SYMBOL_GPL(pci_hp_add); /** * pci_hp_deregister - deregister a hotplug_slot with the PCI hotplug subsystem @@ -464,35 +502,62 @@ EXPORT_SYMBOL_GPL(__pci_hp_register); * * Returns 0 if successful, anything else for an error. */ -int pci_hp_deregister(struct hotplug_slot *slot) +void pci_hp_deregister(struct hotplug_slot *slot) +{ + pci_hp_del(slot); + pci_hp_destroy(slot); +} +EXPORT_SYMBOL_GPL(pci_hp_deregister); + +/** + * pci_hp_del - unpublish hotplug slot from user space + * @slot: pointer to the &struct hotplug_slot to unpublish + * + * Remove a hotplug slot's sysfs interface. + * + * Returns 0 on success or a negative int on error. + */ +void pci_hp_del(struct hotplug_slot *slot) { struct hotplug_slot *temp; - struct pci_slot *pci_slot; - if (!slot) - return -ENODEV; + if (WARN_ON(!slot)) + return; mutex_lock(&pci_hp_mutex); temp = get_slot_from_name(hotplug_slot_name(slot)); - if (temp != slot) { + if (WARN_ON(temp != slot)) { mutex_unlock(&pci_hp_mutex); - return -ENODEV; + return; } list_del(&slot->slot_list); - - pci_slot = slot->pci_slot; - fs_remove_slot(pci_slot); + mutex_unlock(&pci_hp_mutex); dbg("Removed slot %s from the list\n", hotplug_slot_name(slot)); + fs_remove_slot(slot->pci_slot); +} +EXPORT_SYMBOL_GPL(pci_hp_del); + +/** + * pci_hp_destroy - remove hotplug slot from in-kernel use + * @slot: pointer to the &struct hotplug_slot to destroy + * + * Destroy a PCI slot used by a hotplug driver. Once this has been called, + * the driver may no longer invoke hotplug_slot_name() to get the slot's + * unique name. The driver no longer needs to handle a ->reset_slot callback + * from this point on. + * + * Returns 0 on success or a negative int on error. + */ +void pci_hp_destroy(struct hotplug_slot *slot) +{ + struct pci_slot *pci_slot = slot->pci_slot; - slot->release(slot); + slot->pci_slot = NULL; pci_slot->hotplug = NULL; pci_destroy_slot(pci_slot); - mutex_unlock(&pci_hp_mutex); - - return 0; } -EXPORT_SYMBOL_GPL(pci_hp_deregister); +EXPORT_SYMBOL_GPL(pci_hp_destroy); /** * pci_hp_change_slot_info - changes the slot's information structure in the core diff --git a/drivers/pci/hotplug/pciehp_core.c b/drivers/pci/hotplug/pciehp_core.c index b360645377c2..37d8f81e548f 100644 --- a/drivers/pci/hotplug/pciehp_core.c +++ b/drivers/pci/hotplug/pciehp_core.c @@ -56,17 +56,6 @@ static int get_latch_status(struct hotplug_slot *slot, u8 *value); static int get_adapter_status(struct hotplug_slot *slot, u8 *value); static int reset_slot(struct hotplug_slot *slot, int probe); -/** - * release_slot - free up the memory used by a slot - * @hotplug_slot: slot to free - */ -static void release_slot(struct hotplug_slot *hotplug_slot) -{ - kfree(hotplug_slot->ops); - kfree(hotplug_slot->info); - kfree(hotplug_slot); -} - static int init_slot(struct controller *ctrl) { struct slot *slot = ctrl->slot; @@ -107,7 +96,6 @@ static int init_slot(struct controller *ctrl) /* register this slot with the hotplug pci core */ hotplug->info = info; hotplug->private = slot; - hotplug->release = &release_slot; hotplug->ops = ops; slot->hotplug_slot = hotplug; snprintf(name, SLOT_NAME_SIZE, "%u", PSN(ctrl)); @@ -127,7 +115,12 @@ out: static void cleanup_slot(struct controller *ctrl) { - pci_hp_deregister(ctrl->slot->hotplug_slot); + struct hotplug_slot *hotplug_slot = ctrl->slot->hotplug_slot; + + pci_hp_deregister(hotplug_slot); + kfree(hotplug_slot->ops); + kfree(hotplug_slot->info); + kfree(hotplug_slot); } /* diff --git a/drivers/pci/hotplug/pnv_php.c b/drivers/pci/hotplug/pnv_php.c index 6c2e8d7307c6..3276a5e4c430 100644 --- a/drivers/pci/hotplug/pnv_php.c +++ b/drivers/pci/hotplug/pnv_php.c @@ -538,9 +538,8 @@ static struct hotplug_slot_ops php_slot_ops = { .disable_slot = pnv_php_disable_slot, }; -static void pnv_php_release(struct hotplug_slot *slot) +static void pnv_php_release(struct pnv_php_slot *php_slot) { - struct pnv_php_slot *php_slot = slot->private; unsigned long flags; /* Remove from global or child list */ @@ -596,7 +595,6 @@ static struct pnv_php_slot *pnv_php_alloc_slot(struct device_node *dn) php_slot->power_state_check = false; php_slot->slot.ops = &php_slot_ops; php_slot->slot.info = &php_slot->slot_info; - php_slot->slot.release = pnv_php_release; php_slot->slot.private = php_slot; INIT_LIST_HEAD(&php_slot->children); @@ -924,6 +922,7 @@ static void pnv_php_unregister_one(struct device_node *dn) php_slot->state = PNV_PHP_STATE_OFFLINE; pci_hp_deregister(&php_slot->slot); + pnv_php_release(php_slot); pnv_php_put_slot(php_slot); } diff --git a/drivers/pci/hotplug/rpaphp_core.c b/drivers/pci/hotplug/rpaphp_core.c index fb5e0845429d..857c358b727b 100644 --- a/drivers/pci/hotplug/rpaphp_core.c +++ b/drivers/pci/hotplug/rpaphp_core.c @@ -404,13 +404,13 @@ static void __exit cleanup_slots(void) /* * Unregister all of our slots with the pci_hotplug subsystem, * and free up all memory that we had allocated. - * memory will be freed in release_slot callback. */ list_for_each_entry_safe(slot, next, &rpaphp_slot_head, rpaphp_slot_list) { list_del(&slot->rpaphp_slot_list); pci_hp_deregister(slot->hotplug_slot); + dealloc_slot_struct(slot); } return; } diff --git a/drivers/pci/hotplug/rpaphp_slot.c b/drivers/pci/hotplug/rpaphp_slot.c index 3840a2075e6a..b916c8e4372d 100644 --- a/drivers/pci/hotplug/rpaphp_slot.c +++ b/drivers/pci/hotplug/rpaphp_slot.c @@ -19,12 +19,6 @@ #include "rpaphp.h" /* free up the memory used by a slot */ -static void rpaphp_release_slot(struct hotplug_slot *hotplug_slot) -{ - struct slot *slot = (struct slot *) hotplug_slot->private; - dealloc_slot_struct(slot); -} - void dealloc_slot_struct(struct slot *slot) { kfree(slot->hotplug_slot->info); @@ -56,7 +50,6 @@ struct slot *alloc_slot_struct(struct device_node *dn, slot->power_domain = power_domain; slot->hotplug_slot->private = slot; slot->hotplug_slot->ops = &rpaphp_hotplug_slot_ops; - slot->hotplug_slot->release = &rpaphp_release_slot; return (slot); @@ -90,10 +83,8 @@ int rpaphp_deregister_slot(struct slot *slot) __func__, slot->name); list_del(&slot->rpaphp_slot_list); - - retval = pci_hp_deregister(php_slot); - if (retval) - err("Problem unregistering a slot %s\n", slot->name); + pci_hp_deregister(php_slot); + dealloc_slot_struct(slot); dbg("%s - Exit: rc[%d]\n", __func__, retval); return retval; diff --git a/drivers/pci/hotplug/s390_pci_hpc.c b/drivers/pci/hotplug/s390_pci_hpc.c index ffdc2977395d..93b5341d282c 100644 --- a/drivers/pci/hotplug/s390_pci_hpc.c +++ b/drivers/pci/hotplug/s390_pci_hpc.c @@ -130,15 +130,6 @@ static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value) return 0; } -static void release_slot(struct hotplug_slot *hotplug_slot) -{ - struct slot *slot = hotplug_slot->private; - - kfree(slot->hotplug_slot->info); - kfree(slot->hotplug_slot); - kfree(slot); -} - static struct hotplug_slot_ops s390_hotplug_slot_ops = { .enable_slot = enable_slot, .disable_slot = disable_slot, @@ -175,7 +166,6 @@ int zpci_init_slot(struct zpci_dev *zdev) hotplug_slot->info = info; hotplug_slot->ops = &s390_hotplug_slot_ops; - hotplug_slot->release = &release_slot; get_power_status(hotplug_slot, &info->power_status); get_adapter_status(hotplug_slot, &info->adapter_status); @@ -209,5 +199,8 @@ void zpci_exit_slot(struct zpci_dev *zdev) continue; list_del(&slot->slot_list); pci_hp_deregister(slot->hotplug_slot); + kfree(slot->hotplug_slot->info); + kfree(slot->hotplug_slot); + kfree(slot); } } diff --git a/drivers/pci/hotplug/sgi_hotplug.c b/drivers/pci/hotplug/sgi_hotplug.c index 78b6bdbb3a39..babd23409f61 100644 --- a/drivers/pci/hotplug/sgi_hotplug.c +++ b/drivers/pci/hotplug/sgi_hotplug.c @@ -628,7 +628,6 @@ static int sn_hotplug_slot_register(struct pci_bus *pci_bus) goto alloc_err; } bss_hotplug_slot->ops = &sn_hotplug_slot_ops; - bss_hotplug_slot->release = &sn_release_slot; rc = pci_hp_register(bss_hotplug_slot, pci_bus, device, name); if (rc) @@ -656,8 +655,10 @@ alloc_err: sn_release_slot(bss_hotplug_slot); /* destroy anything else on the list */ - while ((bss_hotplug_slot = sn_hp_destroy())) + while ((bss_hotplug_slot = sn_hp_destroy())) { pci_hp_deregister(bss_hotplug_slot); + sn_release_slot(bss_hotplug_slot); + } return rc; } @@ -703,8 +704,10 @@ static void __exit sn_pci_hotplug_exit(void) { struct hotplug_slot *bss_hotplug_slot; - while ((bss_hotplug_slot = sn_hp_destroy())) + while ((bss_hotplug_slot = sn_hp_destroy())) { pci_hp_deregister(bss_hotplug_slot); + sn_release_slot(bss_hotplug_slot); + } if (!list_empty(&sn_hp_list)) printk(KERN_ERR "%s: internal list is not empty\n", __FILE__); diff --git a/drivers/pci/hotplug/shpchp_core.c b/drivers/pci/hotplug/shpchp_core.c index 8e3c6ce12f31..97cee23f3d51 100644 --- a/drivers/pci/hotplug/shpchp_core.c +++ b/drivers/pci/hotplug/shpchp_core.c @@ -61,22 +61,6 @@ static struct hotplug_slot_ops shpchp_hotplug_slot_ops = { .get_adapter_status = get_adapter_status, }; -/** - * release_slot - free up the memory used by a slot - * @hotplug_slot: slot to free - */ -static void release_slot(struct hotplug_slot *hotplug_slot) -{ - struct slot *slot = hotplug_slot->private; - - ctrl_dbg(slot->ctrl, "%s: physical_slot = %s\n", - __func__, slot_name(slot)); - - kfree(slot->hotplug_slot->info); - kfree(slot->hotplug_slot); - kfree(slot); -} - static int init_slots(struct controller *ctrl) { struct slot *slot; @@ -125,7 +109,6 @@ static int init_slots(struct controller *ctrl) /* register this slot with the hotplug pci core */ hotplug_slot->private = slot; - hotplug_slot->release = &release_slot; snprintf(name, SLOT_NAME_SIZE, "%d", slot->number); hotplug_slot->ops = &shpchp_hotplug_slot_ops; @@ -171,6 +154,9 @@ void cleanup_slots(struct controller *ctrl) cancel_delayed_work(&slot->work); destroy_workqueue(slot->wq); pci_hp_deregister(slot->hotplug_slot); + kfree(slot->hotplug_slot->info); + kfree(slot->hotplug_slot); + kfree(slot); } } diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index 3d523ca64694..d67f32a29bb4 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -858,12 +858,6 @@ static int asus_get_adapter_status(struct hotplug_slot *hotplug_slot, return 0; } -static void asus_cleanup_pci_hotplug(struct hotplug_slot *hotplug_slot) -{ - kfree(hotplug_slot->info); - kfree(hotplug_slot); -} - static struct hotplug_slot_ops asus_hotplug_slot_ops = { .owner = THIS_MODULE, .get_adapter_status = asus_get_adapter_status, @@ -905,7 +899,6 @@ static int asus_setup_pci_hotplug(struct asus_wmi *asus) goto error_info; asus->hotplug_slot->private = asus; - asus->hotplug_slot->release = &asus_cleanup_pci_hotplug; asus->hotplug_slot->ops = &asus_hotplug_slot_ops; asus_get_adapter_status(asus->hotplug_slot, &asus->hotplug_slot->info->adapter_status); @@ -1051,8 +1044,11 @@ static void asus_wmi_rfkill_exit(struct asus_wmi *asus) * asus_unregister_rfkill_notifier() */ asus_rfkill_hotplug(asus); - if (asus->hotplug_slot) + if (asus->hotplug_slot) { pci_hp_deregister(asus->hotplug_slot); + kfree(asus->hotplug_slot->info); + kfree(asus->hotplug_slot); + } if (asus->hotplug_workqueue) destroy_workqueue(asus->hotplug_workqueue); diff --git a/drivers/platform/x86/eeepc-laptop.c b/drivers/platform/x86/eeepc-laptop.c index 4c38904a8a32..a4bbf6ecd1f0 100644 --- a/drivers/platform/x86/eeepc-laptop.c +++ b/drivers/platform/x86/eeepc-laptop.c @@ -726,12 +726,6 @@ static int eeepc_get_adapter_status(struct hotplug_slot *hotplug_slot, return 0; } -static void eeepc_cleanup_pci_hotplug(struct hotplug_slot *hotplug_slot) -{ - kfree(hotplug_slot->info); - kfree(hotplug_slot); -} - static struct hotplug_slot_ops eeepc_hotplug_slot_ops = { .owner = THIS_MODULE, .get_adapter_status = eeepc_get_adapter_status, @@ -758,7 +752,6 @@ static int eeepc_setup_pci_hotplug(struct eeepc_laptop *eeepc) goto error_info; eeepc->hotplug_slot->private = eeepc; - eeepc->hotplug_slot->release = &eeepc_cleanup_pci_hotplug; eeepc->hotplug_slot->ops = &eeepc_hotplug_slot_ops; eeepc_get_adapter_status(eeepc->hotplug_slot, &eeepc->hotplug_slot->info->adapter_status); @@ -837,8 +830,11 @@ static void eeepc_rfkill_exit(struct eeepc_laptop *eeepc) eeepc->wlan_rfkill = NULL; } - if (eeepc->hotplug_slot) + if (eeepc->hotplug_slot) { pci_hp_deregister(eeepc->hotplug_slot); + kfree(eeepc->hotplug_slot->info); + kfree(eeepc->hotplug_slot); + } if (eeepc->bluetooth_rfkill) { rfkill_unregister(eeepc->bluetooth_rfkill); diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h index cf5e22103f68..a6d6650a0490 100644 --- a/include/linux/pci_hotplug.h +++ b/include/linux/pci_hotplug.h @@ -80,15 +80,12 @@ struct hotplug_slot_info { * @ops: pointer to the &struct hotplug_slot_ops to be used for this slot * @info: pointer to the &struct hotplug_slot_info for the initial values for * this slot. - * @release: called during pci_hp_deregister to free memory allocated in a - * hotplug_slot structure. * @private: used by the hotplug pci controller driver to store whatever it * needs. */ struct hotplug_slot { struct hotplug_slot_ops *ops; struct hotplug_slot_info *info; - void (*release) (struct hotplug_slot *slot); void *private; /* Variables below this are for use only by the hotplug pci core. */ @@ -104,13 +101,23 @@ static inline const char *hotplug_slot_name(const struct hotplug_slot *slot) int __pci_hp_register(struct hotplug_slot *slot, struct pci_bus *pbus, int nr, const char *name, struct module *owner, const char *mod_name); -int pci_hp_deregister(struct hotplug_slot *slot); +int __pci_hp_initialize(struct hotplug_slot *slot, struct pci_bus *bus, int nr, + const char *name, struct module *owner, + const char *mod_name); +int pci_hp_add(struct hotplug_slot *slot); + +void pci_hp_del(struct hotplug_slot *slot); +void pci_hp_destroy(struct hotplug_slot *slot); +void pci_hp_deregister(struct hotplug_slot *slot); + int __must_check pci_hp_change_slot_info(struct hotplug_slot *slot, struct hotplug_slot_info *info); /* use a define to avoid include chaining to get THIS_MODULE & friends */ #define pci_hp_register(slot, pbus, devnr, name) \ __pci_hp_register(slot, pbus, devnr, name, THIS_MODULE, KBUILD_MODNAME) +#define pci_hp_initialize(slot, bus, nr, name) \ + __pci_hp_initialize(slot, bus, nr, name, THIS_MODULE, KBUILD_MODNAME) /* PCI Setting Record (Type 0) */ struct hpp_type0 { -- cgit v1.2.3 From f71e0ca4db187af7c44987e9d21e9042c3046070 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 23 Jul 2018 09:23:05 +0200 Subject: net: sched: Avoid implicit chain 0 creation Currently, chain 0 is implicitly created during block creation. However that does not align with chain object exposure, creation and destruction api introduced later on. So make the chain 0 behave the same way as any other chain and only create it when it is needed. Since chain 0 is somehow special as the qdiscs need to hold pointer to the first chain tp, this requires to move the chain head change callback infra to the block structure. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/sch_generic.h | 5 ++- net/sched/cls_api.c | 86 +++++++++++++++++++++-------------------------- 2 files changed, 43 insertions(+), 48 deletions(-) (limited to 'include') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 7432100027b7..86f4651784e8 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -300,7 +300,6 @@ typedef void tcf_chain_head_change_t(struct tcf_proto *tp_head, void *priv); struct tcf_chain { struct tcf_proto __rcu *filter_chain; - struct list_head filter_chain_list; struct list_head list; struct tcf_block *block; u32 index; /* chain index */ @@ -318,6 +317,10 @@ struct tcf_block { bool keep_dst; unsigned int offloadcnt; /* Number of oddloaded filters */ unsigned int nooffloaddevcnt; /* Number of devs unable to do offload */ + struct { + struct tcf_chain *chain; + struct list_head filter_chain_list; + } chain0; }; static inline void tcf_block_offload_inc(struct tcf_block *block, u32 *flags) diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 1e8d69790d82..eb0bf9037ef9 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -204,11 +204,12 @@ static struct tcf_chain *tcf_chain_create(struct tcf_block *block, chain = kzalloc(sizeof(*chain), GFP_KERNEL); if (!chain) return NULL; - INIT_LIST_HEAD(&chain->filter_chain_list); list_add_tail(&chain->list, &block->chain_list); chain->block = block; chain->index = chain_index; chain->refcnt = 1; + if (!chain->index) + block->chain0.chain = chain; return chain; } @@ -218,12 +219,16 @@ static void tcf_chain_head_change_item(struct tcf_filter_chain_list_item *item, if (item->chain_head_change) item->chain_head_change(tp_head, item->chain_head_change_priv); } -static void tcf_chain_head_change(struct tcf_chain *chain, - struct tcf_proto *tp_head) + +static void tcf_chain0_head_change(struct tcf_chain *chain, + struct tcf_proto *tp_head) { struct tcf_filter_chain_list_item *item; + struct tcf_block *block = chain->block; - list_for_each_entry(item, &chain->filter_chain_list, list) + if (chain->index) + return; + list_for_each_entry(item, &block->chain0.filter_chain_list, list) tcf_chain_head_change_item(item, tp_head); } @@ -231,7 +236,7 @@ static void tcf_chain_flush(struct tcf_chain *chain) { struct tcf_proto *tp = rtnl_dereference(chain->filter_chain); - tcf_chain_head_change(chain, NULL); + tcf_chain0_head_change(chain, NULL); while (tp) { RCU_INIT_POINTER(chain->filter_chain, tp->next); tcf_proto_destroy(tp, NULL); @@ -245,8 +250,10 @@ static void tcf_chain_destroy(struct tcf_chain *chain) struct tcf_block *block = chain->block; list_del(&chain->list); + if (!chain->index) + block->chain0.chain = NULL; kfree(chain); - if (list_empty(&block->chain_list)) + if (list_empty(&block->chain_list) && block->refcnt == 0) kfree(block); } @@ -346,10 +353,11 @@ no_offload_dev_dec: } static int -tcf_chain_head_change_cb_add(struct tcf_chain *chain, - struct tcf_block_ext_info *ei, - struct netlink_ext_ack *extack) +tcf_chain0_head_change_cb_add(struct tcf_block *block, + struct tcf_block_ext_info *ei, + struct netlink_ext_ack *extack) { + struct tcf_chain *chain0 = block->chain0.chain; struct tcf_filter_chain_list_item *item; item = kmalloc(sizeof(*item), GFP_KERNEL); @@ -359,23 +367,25 @@ tcf_chain_head_change_cb_add(struct tcf_chain *chain, } item->chain_head_change = ei->chain_head_change; item->chain_head_change_priv = ei->chain_head_change_priv; - if (chain->filter_chain) - tcf_chain_head_change_item(item, chain->filter_chain); - list_add(&item->list, &chain->filter_chain_list); + if (chain0 && chain0->filter_chain) + tcf_chain_head_change_item(item, chain0->filter_chain); + list_add(&item->list, &block->chain0.filter_chain_list); return 0; } static void -tcf_chain_head_change_cb_del(struct tcf_chain *chain, - struct tcf_block_ext_info *ei) +tcf_chain0_head_change_cb_del(struct tcf_block *block, + struct tcf_block_ext_info *ei) { + struct tcf_chain *chain0 = block->chain0.chain; struct tcf_filter_chain_list_item *item; - list_for_each_entry(item, &chain->filter_chain_list, list) { + list_for_each_entry(item, &block->chain0.filter_chain_list, list) { if ((!ei->chain_head_change && !ei->chain_head_change_priv) || (item->chain_head_change == ei->chain_head_change && item->chain_head_change_priv == ei->chain_head_change_priv)) { - tcf_chain_head_change_item(item, NULL); + if (chain0) + tcf_chain_head_change_item(item, NULL); list_del(&item->list); kfree(item); return; @@ -411,8 +421,6 @@ static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q, struct netlink_ext_ack *extack) { struct tcf_block *block; - struct tcf_chain *chain; - int err; block = kzalloc(sizeof(*block), GFP_KERNEL); if (!block) { @@ -422,14 +430,8 @@ static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q, INIT_LIST_HEAD(&block->chain_list); INIT_LIST_HEAD(&block->cb_list); INIT_LIST_HEAD(&block->owner_list); + INIT_LIST_HEAD(&block->chain0.filter_chain_list); - /* Create chain 0 by default, it has to be always present. */ - chain = tcf_chain_create(block, 0); - if (!chain) { - NL_SET_ERR_MSG(extack, "Failed to create new tcf chain"); - err = -ENOMEM; - goto err_chain_create; - } block->refcnt = 1; block->net = net; block->index = block_index; @@ -438,10 +440,6 @@ static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q, if (!tcf_block_shared(block)) block->q = q; return block; - -err_chain_create: - kfree(block); - return ERR_PTR(err); } static struct tcf_block *tcf_block_lookup(struct net *net, u32 block_index) @@ -523,11 +521,6 @@ static struct tcf_block *tcf_block_find(struct net *net, struct Qdisc **q, return block; } -static struct tcf_chain *tcf_block_chain_zero(struct tcf_block *block) -{ - return list_first_entry(&block->chain_list, struct tcf_chain, list); -} - struct tcf_block_owner_item { struct list_head list; struct Qdisc *q; @@ -621,10 +614,9 @@ int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q, tcf_block_owner_netif_keep_dst(block, q, ei->binder_type); - err = tcf_chain_head_change_cb_add(tcf_block_chain_zero(block), - ei, extack); + err = tcf_chain0_head_change_cb_add(block, ei, extack); if (err) - goto err_chain_head_change_cb_add; + goto err_chain0_head_change_cb_add; err = tcf_block_offload_bind(block, q, ei, extack); if (err) @@ -634,15 +626,14 @@ int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q, return 0; err_block_offload_bind: - tcf_chain_head_change_cb_del(tcf_block_chain_zero(block), ei); -err_chain_head_change_cb_add: + tcf_chain0_head_change_cb_del(block, ei); +err_chain0_head_change_cb_add: tcf_block_owner_del(block, q, ei->binder_type); err_block_owner_add: if (created) { if (tcf_block_shared(block)) tcf_block_remove(block, net); err_block_insert: - kfree(tcf_block_chain_zero(block)); kfree(block); } else { block->refcnt--; @@ -682,10 +673,10 @@ void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q, if (!block) return; - tcf_chain_head_change_cb_del(tcf_block_chain_zero(block), ei); + tcf_chain0_head_change_cb_del(block, ei); tcf_block_owner_del(block, q, ei->binder_type); - if (--block->refcnt == 0) { + if (block->refcnt == 1) { if (tcf_block_shared(block)) tcf_block_remove(block, block->net); @@ -701,13 +692,14 @@ void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q, tcf_block_offload_unbind(block, q, ei); - if (block->refcnt == 0) { + if (block->refcnt == 1) { /* At this point, all the chains should have refcnt >= 1. */ list_for_each_entry_safe(chain, tmp, &block->chain_list, list) tcf_chain_put(chain); - /* Finally, put chain 0 and allow block to be freed. */ - tcf_chain_put(tcf_block_chain_zero(block)); + block->refcnt--; + if (list_empty(&block->chain_list)) + kfree(block); } } EXPORT_SYMBOL(tcf_block_put_ext); @@ -947,7 +939,7 @@ static void tcf_chain_tp_insert(struct tcf_chain *chain, struct tcf_proto *tp) { if (*chain_info->pprev == chain->filter_chain) - tcf_chain_head_change(chain, tp); + tcf_chain0_head_change(chain, tp); RCU_INIT_POINTER(tp->next, tcf_chain_tp_prev(chain_info)); rcu_assign_pointer(*chain_info->pprev, tp); tcf_chain_hold(chain); @@ -960,7 +952,7 @@ static void tcf_chain_tp_remove(struct tcf_chain *chain, struct tcf_proto *next = rtnl_dereference(chain_info->next); if (tp == chain->filter_chain) - tcf_chain_head_change(chain, next); + tcf_chain0_head_change(chain, next); RCU_INIT_POINTER(*chain_info->pprev, next); tcf_chain_put(chain); } -- cgit v1.2.3 From 32a4f5ecd7381f30ae3bb36dea77a150ba68af2e Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 23 Jul 2018 09:23:06 +0200 Subject: net: sched: introduce chain object to uapi Allow user to create, destroy, get and dump chain objects. Do that by extending rtnl commands by the chain-specific ones. User will now be able to explicitly create or destroy chains (so far this was done only automatically according the filter/act needs and refcounting). Also, the user will receive notification about any chain creation or destuction. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/sch_generic.h | 1 + include/uapi/linux/rtnetlink.h | 7 + net/sched/cls_api.c | 308 +++++++++++++++++++++++++++++++++++++++-- security/selinux/nlmsgtab.c | 2 +- 4 files changed, 309 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 86f4651784e8..81ec8276db9c 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -304,6 +304,7 @@ struct tcf_chain { struct tcf_block *block; u32 index; /* chain index */ unsigned int refcnt; + bool explicitly_created; }; struct tcf_block { diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 7d8502313c99..46399367627f 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -150,6 +150,13 @@ enum { RTM_NEWCACHEREPORT = 96, #define RTM_NEWCACHEREPORT RTM_NEWCACHEREPORT + RTM_NEWCHAIN = 100, +#define RTM_NEWCHAIN RTM_NEWCHAIN + RTM_DELCHAIN, +#define RTM_DELCHAIN RTM_DELCHAIN + RTM_GETCHAIN, +#define RTM_GETCHAIN RTM_GETCHAIN + __RTM_MAX, #define RTM_MAX (((__RTM_MAX + 3) & ~3) - 1) }; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index eb0bf9037ef9..e65b390336aa 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -262,29 +262,57 @@ static void tcf_chain_hold(struct tcf_chain *chain) ++chain->refcnt; } -struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index, - bool create) +static struct tcf_chain *tcf_chain_lookup(struct tcf_block *block, + u32 chain_index) { struct tcf_chain *chain; list_for_each_entry(chain, &block->chain_list, list) { - if (chain->index == chain_index) { - tcf_chain_hold(chain); + if (chain->index == chain_index) return chain; - } + } + return NULL; +} + +static int tc_chain_notify(struct tcf_chain *chain, struct sk_buff *oskb, + u32 seq, u16 flags, int event, bool unicast); + +struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index, + bool create) +{ + struct tcf_chain *chain = tcf_chain_lookup(block, chain_index); + + if (chain) { + tcf_chain_hold(chain); + return chain; } - return create ? tcf_chain_create(block, chain_index) : NULL; + if (!create) + return NULL; + chain = tcf_chain_create(block, chain_index); + if (!chain) + return NULL; + tc_chain_notify(chain, NULL, 0, NLM_F_CREATE | NLM_F_EXCL, + RTM_NEWCHAIN, false); + return chain; } EXPORT_SYMBOL(tcf_chain_get); void tcf_chain_put(struct tcf_chain *chain) { - if (--chain->refcnt == 0) + if (--chain->refcnt == 0) { + tc_chain_notify(chain, NULL, 0, 0, RTM_DELCHAIN, false); tcf_chain_destroy(chain); + } } EXPORT_SYMBOL(tcf_chain_put); +static void tcf_chain_put_explicitly_created(struct tcf_chain *chain) +{ + if (chain->explicitly_created) + tcf_chain_put(chain); +} + static bool tcf_block_offload_in_use(struct tcf_block *block) { return block->offloadcnt; @@ -694,8 +722,10 @@ void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q, if (block->refcnt == 1) { /* At this point, all the chains should have refcnt >= 1. */ - list_for_each_entry_safe(chain, tmp, &block->chain_list, list) + list_for_each_entry_safe(chain, tmp, &block->chain_list, list) { + tcf_chain_put_explicitly_created(chain); tcf_chain_put(chain); + } block->refcnt--; if (list_empty(&block->chain_list)) @@ -1609,6 +1639,264 @@ out: return skb->len; } +static int tc_chain_fill_node(struct tcf_chain *chain, struct net *net, + struct sk_buff *skb, struct tcf_block *block, + u32 portid, u32 seq, u16 flags, int event) +{ + unsigned char *b = skb_tail_pointer(skb); + struct nlmsghdr *nlh; + struct tcmsg *tcm; + + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags); + if (!nlh) + goto out_nlmsg_trim; + tcm = nlmsg_data(nlh); + tcm->tcm_family = AF_UNSPEC; + tcm->tcm__pad1 = 0; + tcm->tcm__pad2 = 0; + tcm->tcm_handle = 0; + if (block->q) { + tcm->tcm_ifindex = qdisc_dev(block->q)->ifindex; + tcm->tcm_parent = block->q->handle; + } else { + tcm->tcm_ifindex = TCM_IFINDEX_MAGIC_BLOCK; + tcm->tcm_block_index = block->index; + } + + if (nla_put_u32(skb, TCA_CHAIN, chain->index)) + goto nla_put_failure; + + nlh->nlmsg_len = skb_tail_pointer(skb) - b; + return skb->len; + +out_nlmsg_trim: +nla_put_failure: + nlmsg_trim(skb, b); + return -EMSGSIZE; +} + +static int tc_chain_notify(struct tcf_chain *chain, struct sk_buff *oskb, + u32 seq, u16 flags, int event, bool unicast) +{ + u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; + struct tcf_block *block = chain->block; + struct net *net = block->net; + struct sk_buff *skb; + + skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + if (!skb) + return -ENOBUFS; + + if (tc_chain_fill_node(chain, net, skb, block, portid, + seq, flags, event) <= 0) { + kfree_skb(skb); + return -EINVAL; + } + + if (unicast) + return netlink_unicast(net->rtnl, skb, portid, MSG_DONTWAIT); + + return rtnetlink_send(skb, net, portid, RTNLGRP_TC, flags & NLM_F_ECHO); +} + +/* Add/delete/get a chain */ + +static int tc_ctl_chain(struct sk_buff *skb, struct nlmsghdr *n, + struct netlink_ext_ack *extack) +{ + struct net *net = sock_net(skb->sk); + struct nlattr *tca[TCA_MAX + 1]; + struct tcmsg *t; + u32 parent; + u32 chain_index; + struct Qdisc *q = NULL; + struct tcf_chain *chain = NULL; + struct tcf_block *block; + unsigned long cl; + int err; + + if (n->nlmsg_type != RTM_GETCHAIN && + !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) + return -EPERM; + +replay: + err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, NULL, extack); + if (err < 0) + return err; + + t = nlmsg_data(n); + parent = t->tcm_parent; + cl = 0; + + block = tcf_block_find(net, &q, &parent, &cl, + t->tcm_ifindex, t->tcm_block_index, extack); + if (IS_ERR(block)) + return PTR_ERR(block); + + chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0; + if (chain_index > TC_ACT_EXT_VAL_MASK) { + NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit"); + return -EINVAL; + } + chain = tcf_chain_lookup(block, chain_index); + if (n->nlmsg_type == RTM_NEWCHAIN) { + if (chain) { + NL_SET_ERR_MSG(extack, "Filter chain already exists"); + return -EEXIST; + } + if (!(n->nlmsg_flags & NLM_F_CREATE)) { + NL_SET_ERR_MSG(extack, "Need both RTM_NEWCHAIN and NLM_F_CREATE to create a new chain"); + return -ENOENT; + } + chain = tcf_chain_create(block, chain_index); + if (!chain) { + NL_SET_ERR_MSG(extack, "Failed to create filter chain"); + return -ENOMEM; + } + } else { + if (!chain) { + NL_SET_ERR_MSG(extack, "Cannot find specified filter chain"); + return -EINVAL; + } + tcf_chain_hold(chain); + } + + switch (n->nlmsg_type) { + case RTM_NEWCHAIN: + /* In case the chain was successfully added, take a reference + * to the chain. This ensures that an empty chain + * does not disappear at the end of this function. + */ + tcf_chain_hold(chain); + chain->explicitly_created = true; + tc_chain_notify(chain, NULL, 0, NLM_F_CREATE | NLM_F_EXCL, + RTM_NEWCHAIN, false); + break; + case RTM_DELCHAIN: + /* Flush the chain first as the user requested chain removal. */ + tcf_chain_flush(chain); + /* In case the chain was successfully deleted, put a reference + * to the chain previously taken during addition. + */ + tcf_chain_put_explicitly_created(chain); + break; + case RTM_GETCHAIN: + break; + err = tc_chain_notify(chain, skb, n->nlmsg_seq, + n->nlmsg_seq, n->nlmsg_type, true); + if (err < 0) + NL_SET_ERR_MSG(extack, "Failed to send chain notify message"); + break; + default: + err = -EOPNOTSUPP; + NL_SET_ERR_MSG(extack, "Unsupported message type"); + goto errout; + } + +errout: + tcf_chain_put(chain); + if (err == -EAGAIN) + /* Replay the request. */ + goto replay; + return err; +} + +/* called with RTNL */ +static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct net *net = sock_net(skb->sk); + struct nlattr *tca[TCA_MAX + 1]; + struct Qdisc *q = NULL; + struct tcf_block *block; + struct tcf_chain *chain; + struct tcmsg *tcm = nlmsg_data(cb->nlh); + long index_start; + long index; + u32 parent; + int err; + + if (nlmsg_len(cb->nlh) < sizeof(*tcm)) + return skb->len; + + err = nlmsg_parse(cb->nlh, sizeof(*tcm), tca, TCA_MAX, NULL, NULL); + if (err) + return err; + + if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) { + block = tcf_block_lookup(net, tcm->tcm_block_index); + if (!block) + goto out; + /* If we work with block index, q is NULL and parent value + * will never be used in the following code. The check + * in tcf_fill_node prevents it. However, compiler does not + * see that far, so set parent to zero to silence the warning + * about parent being uninitialized. + */ + parent = 0; + } else { + const struct Qdisc_class_ops *cops; + struct net_device *dev; + unsigned long cl = 0; + + dev = __dev_get_by_index(net, tcm->tcm_ifindex); + if (!dev) + return skb->len; + + parent = tcm->tcm_parent; + if (!parent) { + q = dev->qdisc; + parent = q->handle; + } else { + q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent)); + } + if (!q) + goto out; + cops = q->ops->cl_ops; + if (!cops) + goto out; + if (!cops->tcf_block) + goto out; + if (TC_H_MIN(tcm->tcm_parent)) { + cl = cops->find(q, tcm->tcm_parent); + if (cl == 0) + goto out; + } + block = cops->tcf_block(q, cl, NULL); + if (!block) + goto out; + if (tcf_block_shared(block)) + q = NULL; + } + + index_start = cb->args[0]; + index = 0; + + list_for_each_entry(chain, &block->chain_list, list) { + if ((tca[TCA_CHAIN] && + nla_get_u32(tca[TCA_CHAIN]) != chain->index)) + continue; + if (index < index_start) { + index++; + continue; + } + err = tc_chain_fill_node(chain, net, skb, block, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, + RTM_NEWCHAIN); + if (err <= 0) + break; + index++; + } + + cb->args[0] = index; + +out: + /* If we did no progress, the error (EMSGSIZE) is real */ + if (skb->len == 0 && err) + return err; + return skb->len; +} + void tcf_exts_destroy(struct tcf_exts *exts) { #ifdef CONFIG_NET_CLS_ACT @@ -1825,6 +2113,10 @@ static int __init tc_filter_init(void) rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_del_tfilter, NULL, 0); rtnl_register(PF_UNSPEC, RTM_GETTFILTER, tc_get_tfilter, tc_dump_tfilter, 0); + rtnl_register(PF_UNSPEC, RTM_NEWCHAIN, tc_ctl_chain, NULL, 0); + rtnl_register(PF_UNSPEC, RTM_DELCHAIN, tc_ctl_chain, NULL, 0); + rtnl_register(PF_UNSPEC, RTM_GETCHAIN, tc_ctl_chain, + tc_dump_chain, 0); return 0; diff --git a/security/selinux/nlmsgtab.c b/security/selinux/nlmsgtab.c index 7b7433a1a34c..74b951f55608 100644 --- a/security/selinux/nlmsgtab.c +++ b/security/selinux/nlmsgtab.c @@ -159,7 +159,7 @@ int selinux_nlmsg_lookup(u16 sclass, u16 nlmsg_type, u32 *perm) switch (sclass) { case SECCLASS_NETLINK_ROUTE_SOCKET: /* RTM_MAX always point to RTM_SETxxxx, ie RTM_NEWxxx + 3 */ - BUILD_BUG_ON(RTM_MAX != (RTM_NEWCACHEREPORT + 3)); + BUILD_BUG_ON(RTM_MAX != (RTM_NEWCHAIN + 3)); err = nlmsg_perm(nlmsg_type, perm, nlmsg_route_perms, sizeof(nlmsg_route_perms)); break; -- cgit v1.2.3 From 9f407f1768d3e1a5ddd7bd49fa4d1f5a26e10ed2 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 23 Jul 2018 09:23:07 +0200 Subject: net: sched: introduce chain templates Allow user to set a template for newly created chains. Template lock down the chain for particular classifier type/options combinations. The classifier needs to support templates, otherwise kernel would reply with error. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/sch_generic.h | 12 +++++++++ net/sched/cls_api.c | 65 +++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 77 insertions(+) (limited to 'include') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 81ec8276db9c..085c509c8674 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -238,6 +238,8 @@ struct tcf_result { }; }; +struct tcf_chain; + struct tcf_proto_ops { struct list_head head; char kind[IFNAMSIZ]; @@ -263,10 +265,18 @@ struct tcf_proto_ops { tc_setup_cb_t *cb, void *cb_priv, struct netlink_ext_ack *extack); void (*bind_class)(void *, u32, unsigned long); + void * (*tmplt_create)(struct net *net, + struct tcf_chain *chain, + struct nlattr **tca, + struct netlink_ext_ack *extack); + void (*tmplt_destroy)(void *tmplt_priv); /* rtnetlink specific */ int (*dump)(struct net*, struct tcf_proto*, void *, struct sk_buff *skb, struct tcmsg*); + int (*tmplt_dump)(struct sk_buff *skb, + struct net *net, + void *tmplt_priv); struct module *owner; }; @@ -305,6 +315,8 @@ struct tcf_chain { u32 index; /* chain index */ unsigned int refcnt; bool explicitly_created; + const struct tcf_proto_ops *tmplt_ops; + void *tmplt_priv; }; struct tcf_block { diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index e65b390336aa..5f7098b5405e 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -298,10 +298,13 @@ struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index, } EXPORT_SYMBOL(tcf_chain_get); +static void tc_chain_tmplt_del(struct tcf_chain *chain); + void tcf_chain_put(struct tcf_chain *chain) { if (--chain->refcnt == 0) { tc_chain_notify(chain, NULL, 0, 0, RTM_DELCHAIN, false); + tc_chain_tmplt_del(chain); tcf_chain_destroy(chain); } } @@ -1258,6 +1261,12 @@ replay: goto errout; } + if (chain->tmplt_ops && chain->tmplt_ops != tp->ops) { + NL_SET_ERR_MSG(extack, "Chain template is set to a different filter kind"); + err = -EINVAL; + goto errout; + } + err = tp->ops->change(net, skb, tp, cl, t->tcm_handle, tca, &fh, n->nlmsg_flags & NLM_F_CREATE ? TCA_ACT_NOREPLACE : TCA_ACT_REPLACE, extack); @@ -1644,8 +1653,13 @@ static int tc_chain_fill_node(struct tcf_chain *chain, struct net *net, u32 portid, u32 seq, u16 flags, int event) { unsigned char *b = skb_tail_pointer(skb); + const struct tcf_proto_ops *ops; struct nlmsghdr *nlh; struct tcmsg *tcm; + void *priv; + + ops = chain->tmplt_ops; + priv = chain->tmplt_priv; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags); if (!nlh) @@ -1666,6 +1680,13 @@ static int tc_chain_fill_node(struct tcf_chain *chain, struct net *net, if (nla_put_u32(skb, TCA_CHAIN, chain->index)) goto nla_put_failure; + if (ops) { + if (nla_put_string(skb, TCA_KIND, ops->kind)) + goto nla_put_failure; + if (ops->tmplt_dump(skb, net, priv) < 0) + goto nla_put_failure; + } + nlh->nlmsg_len = skb_tail_pointer(skb) - b; return skb->len; @@ -1699,6 +1720,47 @@ static int tc_chain_notify(struct tcf_chain *chain, struct sk_buff *oskb, return rtnetlink_send(skb, net, portid, RTNLGRP_TC, flags & NLM_F_ECHO); } +static int tc_chain_tmplt_add(struct tcf_chain *chain, struct net *net, + struct nlattr **tca, + struct netlink_ext_ack *extack) +{ + const struct tcf_proto_ops *ops; + void *tmplt_priv; + + /* If kind is not set, user did not specify template. */ + if (!tca[TCA_KIND]) + return 0; + + ops = tcf_proto_lookup_ops(nla_data(tca[TCA_KIND]), extack); + if (IS_ERR(ops)) + return PTR_ERR(ops); + if (!ops->tmplt_create || !ops->tmplt_destroy || !ops->tmplt_dump) { + NL_SET_ERR_MSG(extack, "Chain templates are not supported with specified classifier"); + return -EOPNOTSUPP; + } + + tmplt_priv = ops->tmplt_create(net, chain, tca, extack); + if (IS_ERR(tmplt_priv)) { + module_put(ops->owner); + return PTR_ERR(tmplt_priv); + } + chain->tmplt_ops = ops; + chain->tmplt_priv = tmplt_priv; + return 0; +} + +static void tc_chain_tmplt_del(struct tcf_chain *chain) +{ + const struct tcf_proto_ops *ops = chain->tmplt_ops; + + /* If template ops are set, no work to do for us. */ + if (!ops) + return; + + ops->tmplt_destroy(chain->tmplt_priv); + module_put(ops->owner); +} + /* Add/delete/get a chain */ static int tc_ctl_chain(struct sk_buff *skb, struct nlmsghdr *n, @@ -1763,6 +1825,9 @@ replay: switch (n->nlmsg_type) { case RTM_NEWCHAIN: + err = tc_chain_tmplt_add(chain, net, tca, extack); + if (err) + goto errout; /* In case the chain was successfully added, take a reference * to the chain. This ensures that an empty chain * does not disappear at the end of this function. -- cgit v1.2.3 From 34738452739069947e528123810533f28dd8332b Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 23 Jul 2018 09:23:11 +0200 Subject: net: sched: cls_flower: propagate chain teplate creation and destruction to drivers Introduce a couple of flower offload commands in order to propagate template creation/destruction events down to device drivers. Drivers may use this information to prepare HW in an optimal way for future filter insertions. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/pkt_cls.h | 2 ++ net/sched/cls_flower.c | 39 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 41 insertions(+) (limited to 'include') diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 4f405ca8346f..a3101582f642 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -721,6 +721,8 @@ enum tc_fl_command { TC_CLSFLOWER_REPLACE, TC_CLSFLOWER_DESTROY, TC_CLSFLOWER_STATS, + TC_CLSFLOWER_TMPLT_CREATE, + TC_CLSFLOWER_TMPLT_DESTROY, }; struct tc_cls_flower_offload { diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index f0c80758a594..6ccf60364297 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -1194,6 +1194,42 @@ static int fl_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb, return 0; } +static void fl_hw_create_tmplt(struct tcf_chain *chain, + struct fl_flow_tmplt *tmplt) +{ + struct tc_cls_flower_offload cls_flower = {}; + struct tcf_block *block = chain->block; + struct tcf_exts dummy_exts = { 0, }; + + cls_flower.common.chain_index = chain->index; + cls_flower.command = TC_CLSFLOWER_TMPLT_CREATE; + cls_flower.cookie = (unsigned long) tmplt; + cls_flower.dissector = &tmplt->dissector; + cls_flower.mask = &tmplt->mask; + cls_flower.key = &tmplt->dummy_key; + cls_flower.exts = &dummy_exts; + + /* We don't care if driver (any of them) fails to handle this + * call. It serves just as a hint for it. + */ + tc_setup_cb_call(block, NULL, TC_SETUP_CLSFLOWER, + &cls_flower, false); +} + +static void fl_hw_destroy_tmplt(struct tcf_chain *chain, + struct fl_flow_tmplt *tmplt) +{ + struct tc_cls_flower_offload cls_flower = {}; + struct tcf_block *block = chain->block; + + cls_flower.common.chain_index = chain->index; + cls_flower.command = TC_CLSFLOWER_TMPLT_DESTROY; + cls_flower.cookie = (unsigned long) tmplt; + + tc_setup_cb_call(block, NULL, TC_SETUP_CLSFLOWER, + &cls_flower, false); +} + static void *fl_tmplt_create(struct net *net, struct tcf_chain *chain, struct nlattr **tca, struct netlink_ext_ack *extack) @@ -1224,6 +1260,8 @@ static void *fl_tmplt_create(struct net *net, struct tcf_chain *chain, fl_init_dissector(&tmplt->dissector, &tmplt->mask); + fl_hw_create_tmplt(chain, tmplt); + return tmplt; errout_tmplt: @@ -1237,6 +1275,7 @@ static void fl_tmplt_destroy(void *tmplt_priv) { struct fl_flow_tmplt *tmplt = tmplt_priv; + fl_hw_destroy_tmplt(tmplt->chain, tmplt); kfree(tmplt); } -- cgit v1.2.3 From b7ff8b1036f0b0df1390ba6b5e9bc7ec458e857a Mon Sep 17 00:00:00 2001 From: Ka-Cheong Poon Date: Mon, 23 Jul 2018 20:51:23 -0700 Subject: rds: Extend RDS API for IPv6 support There are many data structures (RDS socket options) used by RDS apps which use a 32 bit integer to store IP address. To support IPv6, struct in6_addr needs to be used. To ensure backward compatibility, a new data structure is introduced for each of those data structures which use a 32 bit integer to represent an IP address. And new socket options are introduced to use those new structures. This means that existing apps should work without a problem with the new RDS module. For apps which want to use IPv6, those new data structures and socket options can be used. IPv4 mapped address is used to represent IPv4 address in the new data structures. v4: Revert changes to SO_RDS_TRANSPORT Signed-off-by: Ka-Cheong Poon Acked-by: Santosh Shilimkar Signed-off-by: David S. Miller --- include/uapi/linux/rds.h | 69 +++++++++++++++++++++++++++++++- net/rds/connection.c | 101 +++++++++++++++++++++++++++++++++++++++++++---- net/rds/ib.c | 52 ++++++++++++++++++++++++ net/rds/ib_mr.h | 2 + net/rds/ib_rdma.c | 11 +++++- net/rds/recv.c | 25 ++++++++++++ net/rds/tcp.c | 44 +++++++++++++++++++++ 7 files changed, 293 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/rds.h b/include/uapi/linux/rds.h index 20c6bd0b0007..dc520e1a4123 100644 --- a/include/uapi/linux/rds.h +++ b/include/uapi/linux/rds.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */ /* - * Copyright (c) 2008 Oracle. All rights reserved. + * Copyright (c) 2008, 2018 Oracle and/or its affiliates. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU @@ -118,7 +118,17 @@ #define RDS_INFO_IB_CONNECTIONS 10008 #define RDS_INFO_CONNECTION_STATS 10009 #define RDS_INFO_IWARP_CONNECTIONS 10010 -#define RDS_INFO_LAST 10010 + +/* PF_RDS6 options */ +#define RDS6_INFO_CONNECTIONS 10011 +#define RDS6_INFO_SEND_MESSAGES 10012 +#define RDS6_INFO_RETRANS_MESSAGES 10013 +#define RDS6_INFO_RECV_MESSAGES 10014 +#define RDS6_INFO_SOCKETS 10015 +#define RDS6_INFO_TCP_SOCKETS 10016 +#define RDS6_INFO_IB_CONNECTIONS 10017 + +#define RDS_INFO_LAST 10017 struct rds_info_counter { __u8 name[32]; @@ -140,6 +150,15 @@ struct rds_info_connection { __u8 flags; } __attribute__((packed)); +struct rds6_info_connection { + __u64 next_tx_seq; + __u64 next_rx_seq; + struct in6_addr laddr; + struct in6_addr faddr; + __u8 transport[TRANSNAMSIZ]; /* null term ascii */ + __u8 flags; +} __attribute__((packed)); + #define RDS_INFO_MESSAGE_FLAG_ACK 0x01 #define RDS_INFO_MESSAGE_FLAG_FAST_ACK 0x02 @@ -153,6 +172,17 @@ struct rds_info_message { __u8 flags; } __attribute__((packed)); +struct rds6_info_message { + __u64 seq; + __u32 len; + struct in6_addr laddr; + struct in6_addr faddr; + __be16 lport; + __be16 fport; + __u8 flags; + __u8 tos; +} __attribute__((packed)); + struct rds_info_socket { __u32 sndbuf; __be32 bound_addr; @@ -163,6 +193,16 @@ struct rds_info_socket { __u64 inum; } __attribute__((packed)); +struct rds6_info_socket { + __u32 sndbuf; + struct in6_addr bound_addr; + struct in6_addr connected_addr; + __be16 bound_port; + __be16 connected_port; + __u32 rcvbuf; + __u64 inum; +} __attribute__((packed)); + struct rds_info_tcp_socket { __be32 local_addr; __be16 local_port; @@ -175,6 +215,18 @@ struct rds_info_tcp_socket { __u32 last_seen_una; } __attribute__((packed)); +struct rds6_info_tcp_socket { + struct in6_addr local_addr; + __be16 local_port; + struct in6_addr peer_addr; + __be16 peer_port; + __u64 hdr_rem; + __u64 data_rem; + __u32 last_sent_nxt; + __u32 last_expected_una; + __u32 last_seen_una; +} __attribute__((packed)); + #define RDS_IB_GID_LEN 16 struct rds_info_rdma_connection { __be32 src_addr; @@ -189,6 +241,19 @@ struct rds_info_rdma_connection { __u32 rdma_mr_size; }; +struct rds6_info_rdma_connection { + struct in6_addr src_addr; + struct in6_addr dst_addr; + __u8 src_gid[RDS_IB_GID_LEN]; + __u8 dst_gid[RDS_IB_GID_LEN]; + + __u32 max_send_wr; + __u32 max_recv_wr; + __u32 max_send_sge; + __u32 rdma_mr_max; + __u32 rdma_mr_size; +}; + /* RDS message Receive Path Latency points */ enum rds_message_rxpath_latency { RDS_MSG_RX_HDR_TO_DGRAM_START = 0, diff --git a/net/rds/connection.c b/net/rds/connection.c index 5c9ceed55dae..051e35c1e7c6 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -498,16 +498,19 @@ EXPORT_SYMBOL_GPL(rds_conn_destroy); static void __rds_inc_msg_cp(struct rds_incoming *inc, struct rds_info_iterator *iter, - void *saddr, void *daddr, int flip) + void *saddr, void *daddr, int flip, bool isv6) { - rds_inc_info_copy(inc, iter, *(__be32 *)saddr, - *(__be32 *)daddr, flip); + if (isv6) + rds6_inc_info_copy(inc, iter, saddr, daddr, flip); + else + rds_inc_info_copy(inc, iter, *(__be32 *)saddr, + *(__be32 *)daddr, flip); } static void rds_conn_message_info_cmn(struct socket *sock, unsigned int len, struct rds_info_iterator *iter, struct rds_info_lengths *lens, - int want_send) + int want_send, bool isv6) { struct hlist_head *head; struct list_head *list; @@ -518,7 +521,10 @@ static void rds_conn_message_info_cmn(struct socket *sock, unsigned int len, size_t i; int j; - len /= sizeof(struct rds_info_message); + if (isv6) + len /= sizeof(struct rds6_info_message); + else + len /= sizeof(struct rds_info_message); rcu_read_lock(); @@ -528,6 +534,9 @@ static void rds_conn_message_info_cmn(struct socket *sock, unsigned int len, struct rds_conn_path *cp; int npaths; + if (!isv6 && conn->c_isv6) + continue; + npaths = (conn->c_trans->t_mp_capable ? RDS_MPATH_WORKERS : 1); @@ -548,7 +557,7 @@ static void rds_conn_message_info_cmn(struct socket *sock, unsigned int len, iter, &conn->c_laddr, &conn->c_faddr, - 0); + 0, isv6); } spin_unlock_irqrestore(&cp->cp_lock, flags); @@ -558,7 +567,10 @@ static void rds_conn_message_info_cmn(struct socket *sock, unsigned int len, rcu_read_unlock(); lens->nr = total; - lens->each = sizeof(struct rds_info_message); + if (isv6) + lens->each = sizeof(struct rds6_info_message); + else + lens->each = sizeof(struct rds_info_message); } static void rds_conn_message_info(struct socket *sock, unsigned int len, @@ -566,7 +578,15 @@ static void rds_conn_message_info(struct socket *sock, unsigned int len, struct rds_info_lengths *lens, int want_send) { - rds_conn_message_info_cmn(sock, len, iter, lens, want_send); + rds_conn_message_info_cmn(sock, len, iter, lens, want_send, false); +} + +static void rds6_conn_message_info(struct socket *sock, unsigned int len, + struct rds_info_iterator *iter, + struct rds_info_lengths *lens, + int want_send) +{ + rds_conn_message_info_cmn(sock, len, iter, lens, want_send, true); } static void rds_conn_message_info_send(struct socket *sock, unsigned int len, @@ -576,6 +596,13 @@ static void rds_conn_message_info_send(struct socket *sock, unsigned int len, rds_conn_message_info(sock, len, iter, lens, 1); } +static void rds6_conn_message_info_send(struct socket *sock, unsigned int len, + struct rds_info_iterator *iter, + struct rds_info_lengths *lens) +{ + rds6_conn_message_info(sock, len, iter, lens, 1); +} + static void rds_conn_message_info_retrans(struct socket *sock, unsigned int len, struct rds_info_iterator *iter, @@ -584,6 +611,14 @@ static void rds_conn_message_info_retrans(struct socket *sock, rds_conn_message_info(sock, len, iter, lens, 0); } +static void rds6_conn_message_info_retrans(struct socket *sock, + unsigned int len, + struct rds_info_iterator *iter, + struct rds_info_lengths *lens) +{ + rds6_conn_message_info(sock, len, iter, lens, 0); +} + void rds_for_each_conn_info(struct socket *sock, unsigned int len, struct rds_info_iterator *iter, struct rds_info_lengths *lens, @@ -699,6 +734,34 @@ static int rds_conn_info_visitor(struct rds_conn_path *cp, void *buffer) return 1; } +static int rds6_conn_info_visitor(struct rds_conn_path *cp, void *buffer) +{ + struct rds6_info_connection *cinfo6 = buffer; + struct rds_connection *conn = cp->cp_conn; + + cinfo6->next_tx_seq = cp->cp_next_tx_seq; + cinfo6->next_rx_seq = cp->cp_next_rx_seq; + cinfo6->laddr = conn->c_laddr; + cinfo6->faddr = conn->c_faddr; + strncpy(cinfo6->transport, conn->c_trans->t_name, + sizeof(cinfo6->transport)); + cinfo6->flags = 0; + + rds_conn_info_set(cinfo6->flags, test_bit(RDS_IN_XMIT, &cp->cp_flags), + SENDING); + /* XXX Future: return the state rather than these funky bits */ + rds_conn_info_set(cinfo6->flags, + atomic_read(&cp->cp_state) == RDS_CONN_CONNECTING, + CONNECTING); + rds_conn_info_set(cinfo6->flags, + atomic_read(&cp->cp_state) == RDS_CONN_UP, + CONNECTED); + /* Just return 1 as there is no error case. This is a helper function + * for rds_walk_conn_path_info() and it wants a return value. + */ + return 1; +} + static void rds_conn_info(struct socket *sock, unsigned int len, struct rds_info_iterator *iter, struct rds_info_lengths *lens) @@ -711,6 +774,18 @@ static void rds_conn_info(struct socket *sock, unsigned int len, sizeof(struct rds_info_connection)); } +static void rds6_conn_info(struct socket *sock, unsigned int len, + struct rds_info_iterator *iter, + struct rds_info_lengths *lens) +{ + u64 buffer[(sizeof(struct rds6_info_connection) + 7) / 8]; + + rds_walk_conn_path_info(sock, len, iter, lens, + rds6_conn_info_visitor, + buffer, + sizeof(struct rds6_info_connection)); +} + int rds_conn_init(void) { int ret; @@ -732,6 +807,11 @@ int rds_conn_init(void) rds_conn_message_info_send); rds_info_register_func(RDS_INFO_RETRANS_MESSAGES, rds_conn_message_info_retrans); + rds_info_register_func(RDS6_INFO_CONNECTIONS, rds6_conn_info); + rds_info_register_func(RDS6_INFO_SEND_MESSAGES, + rds6_conn_message_info_send); + rds_info_register_func(RDS6_INFO_RETRANS_MESSAGES, + rds6_conn_message_info_retrans); return 0; } @@ -750,6 +830,11 @@ void rds_conn_exit(void) rds_conn_message_info_send); rds_info_deregister_func(RDS_INFO_RETRANS_MESSAGES, rds_conn_message_info_retrans); + rds_info_deregister_func(RDS6_INFO_CONNECTIONS, rds6_conn_info); + rds_info_deregister_func(RDS6_INFO_SEND_MESSAGES, + rds6_conn_message_info_send); + rds_info_deregister_func(RDS6_INFO_RETRANS_MESSAGES, + rds6_conn_message_info_retrans); } /* diff --git a/net/rds/ib.c b/net/rds/ib.c index 756225c5540f..63d95ea7cdff 100644 --- a/net/rds/ib.c +++ b/net/rds/ib.c @@ -321,6 +321,43 @@ static int rds_ib_conn_info_visitor(struct rds_connection *conn, return 1; } +/* IPv6 version of rds_ib_conn_info_visitor(). */ +static int rds6_ib_conn_info_visitor(struct rds_connection *conn, + void *buffer) +{ + struct rds6_info_rdma_connection *iinfo6 = buffer; + struct rds_ib_connection *ic; + + /* We will only ever look at IB transports */ + if (conn->c_trans != &rds_ib_transport) + return 0; + + iinfo6->src_addr = conn->c_laddr; + iinfo6->dst_addr = conn->c_faddr; + + memset(&iinfo6->src_gid, 0, sizeof(iinfo6->src_gid)); + memset(&iinfo6->dst_gid, 0, sizeof(iinfo6->dst_gid)); + + if (rds_conn_state(conn) == RDS_CONN_UP) { + struct rds_ib_device *rds_ibdev; + struct rdma_dev_addr *dev_addr; + + ic = conn->c_transport_data; + dev_addr = &ic->i_cm_id->route.addr.dev_addr; + rdma_addr_get_sgid(dev_addr, + (union ib_gid *)&iinfo6->src_gid); + rdma_addr_get_dgid(dev_addr, + (union ib_gid *)&iinfo6->dst_gid); + + rds_ibdev = ic->rds_ibdev; + iinfo6->max_send_wr = ic->i_send_ring.w_nr; + iinfo6->max_recv_wr = ic->i_recv_ring.w_nr; + iinfo6->max_send_sge = rds_ibdev->max_sge; + rds6_ib_get_mr_info(rds_ibdev, iinfo6); + } + return 1; +} + static void rds_ib_ic_info(struct socket *sock, unsigned int len, struct rds_info_iterator *iter, struct rds_info_lengths *lens) @@ -333,6 +370,19 @@ static void rds_ib_ic_info(struct socket *sock, unsigned int len, sizeof(struct rds_info_rdma_connection)); } +/* IPv6 version of rds_ib_ic_info(). */ +static void rds6_ib_ic_info(struct socket *sock, unsigned int len, + struct rds_info_iterator *iter, + struct rds_info_lengths *lens) +{ + u64 buffer[(sizeof(struct rds6_info_rdma_connection) + 7) / 8]; + + rds_for_each_conn_info(sock, len, iter, lens, + rds6_ib_conn_info_visitor, + buffer, + sizeof(struct rds6_info_rdma_connection)); +} + /* * Early RDS/IB was built to only bind to an address if there is an IPoIB * device with that address set. @@ -441,6 +491,7 @@ void rds_ib_exit(void) rds_ib_set_unloading(); synchronize_rcu(); rds_info_deregister_func(RDS_INFO_IB_CONNECTIONS, rds_ib_ic_info); + rds_info_deregister_func(RDS6_INFO_IB_CONNECTIONS, rds6_ib_ic_info); rds_ib_unregister_client(); rds_ib_destroy_nodev_conns(); rds_ib_sysctl_exit(); @@ -502,6 +553,7 @@ int rds_ib_init(void) rds_trans_register(&rds_ib_transport); rds_info_register_func(RDS_INFO_IB_CONNECTIONS, rds_ib_ic_info); + rds_info_register_func(RDS6_INFO_IB_CONNECTIONS, rds6_ib_ic_info); goto out; diff --git a/net/rds/ib_mr.h b/net/rds/ib_mr.h index 0ea4ab017a8c..f440ace584c8 100644 --- a/net/rds/ib_mr.h +++ b/net/rds/ib_mr.h @@ -113,6 +113,8 @@ struct rds_ib_mr_pool *rds_ib_create_mr_pool(struct rds_ib_device *rds_dev, int npages); void rds_ib_get_mr_info(struct rds_ib_device *rds_ibdev, struct rds_info_rdma_connection *iinfo); +void rds6_ib_get_mr_info(struct rds_ib_device *rds_ibdev, + struct rds6_info_rdma_connection *iinfo6); void rds_ib_destroy_mr_pool(struct rds_ib_mr_pool *); void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents, struct rds_sock *rs, u32 *key_ret); diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c index 0ec9df043dd0..e3c8bbbdb43f 100644 --- a/net/rds/ib_rdma.c +++ b/net/rds/ib_rdma.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved. + * Copyright (c) 2006, 2018 Oracle and/or its affiliates. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU @@ -180,6 +180,15 @@ void rds_ib_get_mr_info(struct rds_ib_device *rds_ibdev, struct rds_info_rdma_co iinfo->rdma_mr_size = pool_1m->fmr_attr.max_pages; } +void rds6_ib_get_mr_info(struct rds_ib_device *rds_ibdev, + struct rds6_info_rdma_connection *iinfo6) +{ + struct rds_ib_mr_pool *pool_1m = rds_ibdev->mr_1m_pool; + + iinfo6->rdma_mr_max = pool_1m->max_items; + iinfo6->rdma_mr_size = pool_1m->fmr_attr.max_pages; +} + struct rds_ib_mr *rds_ib_reuse_mr(struct rds_ib_mr_pool *pool) { struct rds_ib_mr *ibmr = NULL; diff --git a/net/rds/recv.c b/net/rds/recv.c index 1402c21210b1..03cd8df54c26 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -792,3 +792,28 @@ void rds_inc_info_copy(struct rds_incoming *inc, rds_info_copy(iter, &minfo, sizeof(minfo)); } + +void rds6_inc_info_copy(struct rds_incoming *inc, + struct rds_info_iterator *iter, + struct in6_addr *saddr, struct in6_addr *daddr, + int flip) +{ + struct rds6_info_message minfo6; + + minfo6.seq = be64_to_cpu(inc->i_hdr.h_sequence); + minfo6.len = be32_to_cpu(inc->i_hdr.h_len); + + if (flip) { + minfo6.laddr = *daddr; + minfo6.faddr = *saddr; + minfo6.lport = inc->i_hdr.h_dport; + minfo6.fport = inc->i_hdr.h_sport; + } else { + minfo6.laddr = *saddr; + minfo6.faddr = *daddr; + minfo6.lport = inc->i_hdr.h_sport; + minfo6.fport = inc->i_hdr.h_dport; + } + + rds_info_copy(iter, &minfo6, sizeof(minfo6)); +} diff --git a/net/rds/tcp.c b/net/rds/tcp.c index 890d0e1d8908..7028d6e51947 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -273,6 +273,48 @@ out: spin_unlock_irqrestore(&rds_tcp_tc_list_lock, flags); } +/* Handle RDS6_INFO_TCP_SOCKETS socket option. It returns both IPv4 and + * IPv6 connections. IPv4 connection address is returned in an IPv4 mapped + * address. + */ +static void rds6_tcp_tc_info(struct socket *sock, unsigned int len, + struct rds_info_iterator *iter, + struct rds_info_lengths *lens) +{ + struct rds6_info_tcp_socket tsinfo6; + struct rds_tcp_connection *tc; + unsigned long flags; + + spin_lock_irqsave(&rds_tcp_tc_list_lock, flags); + + if (len / sizeof(tsinfo6) < rds6_tcp_tc_count) + goto out; + + list_for_each_entry(tc, &rds_tcp_tc_list, t_list_item) { + struct sock *sk = tc->t_sock->sk; + struct inet_sock *inet = inet_sk(sk); + + tsinfo6.local_addr = sk->sk_v6_rcv_saddr; + tsinfo6.local_port = inet->inet_sport; + tsinfo6.peer_addr = sk->sk_v6_daddr; + tsinfo6.peer_port = inet->inet_dport; + + tsinfo6.hdr_rem = tc->t_tinc_hdr_rem; + tsinfo6.data_rem = tc->t_tinc_data_rem; + tsinfo6.last_sent_nxt = tc->t_last_sent_nxt; + tsinfo6.last_expected_una = tc->t_last_expected_una; + tsinfo6.last_seen_una = tc->t_last_seen_una; + + rds_info_copy(iter, &tsinfo6, sizeof(tsinfo6)); + } + +out: + lens->nr = rds6_tcp_tc_count; + lens->each = sizeof(tsinfo6); + + spin_unlock_irqrestore(&rds_tcp_tc_list_lock, flags); +} + static int rds_tcp_laddr_check(struct net *net, const struct in6_addr *addr, __u32 scope_id) { @@ -628,6 +670,7 @@ static void rds_tcp_exit(void) rds_tcp_set_unloading(); synchronize_rcu(); rds_info_deregister_func(RDS_INFO_TCP_SOCKETS, rds_tcp_tc_info); + rds_info_deregister_func(RDS6_INFO_TCP_SOCKETS, rds6_tcp_tc_info); unregister_pernet_device(&rds_tcp_net_ops); rds_tcp_destroy_conns(); rds_trans_unregister(&rds_tcp_transport); @@ -659,6 +702,7 @@ static int rds_tcp_init(void) rds_trans_register(&rds_tcp_transport); rds_info_register_func(RDS_INFO_TCP_SOCKETS, rds_tcp_tc_info); + rds_info_register_func(RDS6_INFO_TCP_SOCKETS, rds6_tcp_tc_info); goto out; out_recv: -- cgit v1.2.3 From 467b061f1ac80f323bedb56d20a24f7bc0d2cec5 Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Mon, 23 Jul 2018 16:54:03 +0100 Subject: ASoC: core: add support to snd_soc_dai_get_channel_map() On Qualcomm platforms, specifically with SLIMbus interfaced codecs, the codec slim channel numbers are passed to DSP while configuring the slim audio path. Having get_channel_map() would allow dais to share such information across multiple dais. Signed-off-by: Srinivas Kandagatla Signed-off-by: Mark Brown --- include/sound/soc-dai.h | 8 ++++++++ sound/soc/soc-core.c | 22 ++++++++++++++++++++++ 2 files changed, 30 insertions(+) (limited to 'include') diff --git a/include/sound/soc-dai.h b/include/sound/soc-dai.h index a14bc0608ae9..f5d70041108f 100644 --- a/include/sound/soc-dai.h +++ b/include/sound/soc-dai.h @@ -138,6 +138,11 @@ int snd_soc_dai_set_tristate(struct snd_soc_dai *dai, int tristate); int snd_soc_dai_digital_mute(struct snd_soc_dai *dai, int mute, int direction); + +int snd_soc_dai_get_channel_map(struct snd_soc_dai *dai, + unsigned int *tx_num, unsigned int *tx_slot, + unsigned int *rx_num, unsigned int *rx_slot); + int snd_soc_dai_is_dummy(struct snd_soc_dai *dai); struct snd_soc_dai_ops { @@ -165,6 +170,9 @@ struct snd_soc_dai_ops { int (*set_channel_map)(struct snd_soc_dai *dai, unsigned int tx_num, unsigned int *tx_slot, unsigned int rx_num, unsigned int *rx_slot); + int (*get_channel_map)(struct snd_soc_dai *dai, + unsigned int *tx_num, unsigned int *tx_slot, + unsigned int *rx_num, unsigned int *rx_slot); int (*set_tristate)(struct snd_soc_dai *dai, int tristate); int (*set_sdw_stream)(struct snd_soc_dai *dai, diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index ad5b0ef16d82..81b27923303d 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -2679,6 +2679,28 @@ int snd_soc_dai_set_channel_map(struct snd_soc_dai *dai, } EXPORT_SYMBOL_GPL(snd_soc_dai_set_channel_map); +/** + * snd_soc_dai_get_channel_map - Get DAI audio channel map + * @dai: DAI + * @tx_num: how many TX channels + * @tx_slot: pointer to an array which imply the TX slot number channel + * 0~num-1 uses + * @rx_num: how many RX channels + * @rx_slot: pointer to an array which imply the RX slot number channel + * 0~num-1 uses + */ +int snd_soc_dai_get_channel_map(struct snd_soc_dai *dai, + unsigned int *tx_num, unsigned int *tx_slot, + unsigned int *rx_num, unsigned int *rx_slot) +{ + if (dai->driver->ops->get_channel_map) + return dai->driver->ops->get_channel_map(dai, tx_num, tx_slot, + rx_num, rx_slot); + else + return -ENOTSUPP; +} +EXPORT_SYMBOL_GPL(snd_soc_dai_get_channel_map); + /** * snd_soc_dai_set_tristate - configure DAI system or master clock. * @dai: DAI -- cgit v1.2.3 From 3730cf4dd70b6a36e48d58a862120311411b77f5 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 24 Jul 2018 12:47:56 +0200 Subject: netlink: do not store start function in netlink_cb ->start() is called once when dump is being initialized, there is no need to store it in netlink_cb. Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/linux/netlink.h | 1 - net/netlink/af_netlink.c | 5 ++--- 2 files changed, 2 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index f3075d6c7e82..71f121b66ca8 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -170,7 +170,6 @@ netlink_skb_clone(struct sk_buff *skb, gfp_t gfp_mask) struct netlink_callback { struct sk_buff *skb; const struct nlmsghdr *nlh; - int (*start)(struct netlink_callback *); int (*dump)(struct sk_buff * skb, struct netlink_callback *cb); int (*done)(struct netlink_callback *cb); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 393573a99a5a..f6ac7693d2cc 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2300,7 +2300,6 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, cb = &nlk->cb; memset(cb, 0, sizeof(*cb)); - cb->start = control->start; cb->dump = control->dump; cb->done = control->done; cb->nlh = nlh; @@ -2309,8 +2308,8 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, cb->min_dump_alloc = control->min_dump_alloc; cb->skb = skb; - if (cb->start) { - ret = cb->start(cb); + if (control->start) { + ret = control->start(cb); if (ret) goto error_put; } -- cgit v1.2.3 From 9b04fcc1d8a9b5480f9e7ec93072c3a1bc517256 Mon Sep 17 00:00:00 2001 From: Jacopo Mondi Date: Mon, 9 Jul 2018 10:19:19 -0400 Subject: media: v4l2-fwnode: parse 'data-enable-active' prop MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Parse the newly defined 'data-enable-active' property in parallel endpoint parsing function. Signed-off-by: Jacopo Mondi Reviewed-by: Niklas Söderlund Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- drivers/media/v4l2-core/v4l2-fwnode.c | 4 ++++ include/media/v4l2-mediabus.h | 2 ++ 2 files changed, 6 insertions(+) (limited to 'include') diff --git a/drivers/media/v4l2-core/v4l2-fwnode.c b/drivers/media/v4l2-core/v4l2-fwnode.c index 3f77aa318035..61051911e779 100644 --- a/drivers/media/v4l2-core/v4l2-fwnode.c +++ b/drivers/media/v4l2-core/v4l2-fwnode.c @@ -154,6 +154,10 @@ static void v4l2_fwnode_endpoint_parse_parallel_bus( flags |= v ? V4L2_MBUS_VIDEO_SOG_ACTIVE_HIGH : V4L2_MBUS_VIDEO_SOG_ACTIVE_LOW; + if (!fwnode_property_read_u32(fwnode, "data-enable-active", &v)) + flags |= v ? V4L2_MBUS_DATA_ENABLE_HIGH : + V4L2_MBUS_DATA_ENABLE_LOW; + bus->flags = flags; } diff --git a/include/media/v4l2-mediabus.h b/include/media/v4l2-mediabus.h index 4d8626c468bc..4bbb5f3d2b02 100644 --- a/include/media/v4l2-mediabus.h +++ b/include/media/v4l2-mediabus.h @@ -45,6 +45,8 @@ /* Active state of Sync-on-green (SoG) signal, 0/1 for LOW/HIGH respectively. */ #define V4L2_MBUS_VIDEO_SOG_ACTIVE_HIGH BIT(12) #define V4L2_MBUS_VIDEO_SOG_ACTIVE_LOW BIT(13) +#define V4L2_MBUS_DATA_ENABLE_HIGH BIT(14) +#define V4L2_MBUS_DATA_ENABLE_LOW BIT(15) /* Serial flags */ /* How many lanes the client can use */ -- cgit v1.2.3 From e5cda42c16d89720c29678f51d95a119490ef7d8 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Mon, 23 Jul 2018 19:52:57 +0200 Subject: ARM: exynos: Define EINT_WAKEUP_MASK registers for S5Pv210 and Exynos5433 S5Pv210 and Exynos5433/Exynos7 have different address of EINT_WAKEUP_MASK register. Rename existing S5P_EINT_WAKEUP_MASK to avoid confusion and add new ones. Signed-off-by: Krzysztof Kozlowski Cc: Tomasz Figa Cc: Sylwester Nawrocki Acked-by: Tomasz Figa Tested-by: Marek Szyprowski --- arch/arm/mach-exynos/suspend.c | 2 +- include/linux/soc/samsung/exynos-regs-pmu.h | 6 +++++- 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/arch/arm/mach-exynos/suspend.c b/arch/arm/mach-exynos/suspend.c index d3db306a5a70..f3384e3a675d 100644 --- a/arch/arm/mach-exynos/suspend.c +++ b/arch/arm/mach-exynos/suspend.c @@ -272,7 +272,7 @@ static int exynos5420_cpu_suspend(unsigned long arg) static void exynos_pm_set_wakeup_mask(void) { /* Set wake-up mask registers */ - pmu_raw_writel(exynos_get_eint_wake_mask(), S5P_EINT_WAKEUP_MASK); + pmu_raw_writel(exynos_get_eint_wake_mask(), EXYNOS_EINT_WAKEUP_MASK); pmu_raw_writel(exynos_irqwake_intmask & ~(1 << 31), S5P_WAKEUP_MASK); } diff --git a/include/linux/soc/samsung/exynos-regs-pmu.h b/include/linux/soc/samsung/exynos-regs-pmu.h index 66dcb9ec273a..eb0d240df7a7 100644 --- a/include/linux/soc/samsung/exynos-regs-pmu.h +++ b/include/linux/soc/samsung/exynos-regs-pmu.h @@ -42,7 +42,7 @@ #define EXYNOS_SWRESET 0x0400 #define S5P_WAKEUP_STAT 0x0600 -#define S5P_EINT_WAKEUP_MASK 0x0604 +#define EXYNOS_EINT_WAKEUP_MASK 0x0604 #define S5P_WAKEUP_MASK 0x0608 #define S5P_WAKEUP_MASK2 0x0614 @@ -180,6 +180,9 @@ #define S5P_CORE_WAKEUP_FROM_LOCAL_CFG (0x3 << 8) #define S5P_CORE_AUTOWAKEUP_EN (1 << 31) +/* Only for S5Pv210 */ +#define S5PV210_EINT_WAKEUP_MASK 0xC004 + /* Only for EXYNOS4210 */ #define S5P_CMU_CLKSTOP_LCD1_LOWPWR 0x1154 #define S5P_CMU_RESET_LCD1_LOWPWR 0x1174 @@ -641,6 +644,7 @@ | EXYNOS5420_KFC_USE_STANDBY_WFI3) /* For EXYNOS5433 */ +#define EXYNOS5433_EINT_WAKEUP_MASK (0x060C) #define EXYNOS5433_USBHOST30_PHY_CONTROL (0x0728) #define EXYNOS5433_PAD_RETENTION_AUD_OPTION (0x3028) #define EXYNOS5433_PAD_RETENTION_MMC2_OPTION (0x30C8) -- cgit v1.2.3 From a8be2af0218cf037704dc2e733bf56d6560fa324 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Mon, 23 Jul 2018 19:52:58 +0200 Subject: pinctrl: samsung: Write external wakeup interrupt mask The pinctrl driver defines an IRQ chip which handles external wakeup interrupts, therefore from logical point of view, it is the owner of external interrupt mask. The register controlling the mask belongs to Power Management Unit address space so it has to be accessed with PMU syscon regmap handle. This mask should be written to hardware during system suspend. Till now ARMv7 machine code was responsible for this which created a dependency between pin controller driver and arch/arm/mach code. Try to rework this dependency so the pinctrl driver will write external wakeup interrupt mask during late suspend. Impact on ARMv7 designs (S5Pv210 and Exynos) ============================================ This duplicates setting mask with existing machine code arch/arm/mach-exynos/suspend.c and arch/arm/mach-s5pv210/pm.c but it is not a problem - the wakeup mask register will be written twice. The machine code will be cleaned up later. The difference between implementation here and ARMv7 machine code (arch/arm/mach-*) is the time of writing the mask: 1. The machine code is writing the mask quite late during system suspend path, after offlining secondary CPUs and just before doing actual suspend. 2. The implementation in pinctrl driver uses late suspend ops, therefore it will write the mask much earlier. Hopefully late enough, after all drivers will enable or disable their interrupt wakeups (enable_irq_wake() etc). Impact on ARMv8 designs (Exynos5433 and Exynos7) ================================================ The Suspend to RAM was not supported and external wakeup interrupt mask was not written to HW. This change brings us one step closer to supporting Suspend to RAM. Signed-off-by: Krzysztof Kozlowski Cc: Tomasz Figa Cc: Sylwester Nawrocki Acked-by: Tomasz Figa Tested-by: Marek Szyprowski --- drivers/pinctrl/samsung/pinctrl-exynos.c | 50 ++++++++++++++++++++++++++++- drivers/pinctrl/samsung/pinctrl-samsung.h | 3 ++ include/linux/soc/samsung/exynos-regs-pmu.h | 2 ++ 3 files changed, 54 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/pinctrl/samsung/pinctrl-exynos.c b/drivers/pinctrl/samsung/pinctrl-exynos.c index 29d86d704b0c..40ef14956876 100644 --- a/drivers/pinctrl/samsung/pinctrl-exynos.c +++ b/drivers/pinctrl/samsung/pinctrl-exynos.c @@ -25,6 +25,7 @@ #include #include #include +#include #include @@ -37,6 +38,8 @@ struct exynos_irq_chip { u32 eint_con; u32 eint_mask; u32 eint_pend; + u32 eint_wake_mask_value; + u32 eint_wake_mask_reg; }; static inline struct exynos_irq_chip *to_exynos_irq_chip(struct irq_chip *chip) @@ -215,6 +218,7 @@ static struct exynos_irq_chip exynos_gpio_irq_chip = { .eint_con = EXYNOS_GPIO_ECON_OFFSET, .eint_mask = EXYNOS_GPIO_EMASK_OFFSET, .eint_pend = EXYNOS_GPIO_EPEND_OFFSET, + /* eint_wake_mask_value not used */ }; static int exynos_eint_irq_map(struct irq_domain *h, unsigned int virq, @@ -330,6 +334,8 @@ u32 exynos_get_eint_wake_mask(void) static int exynos_wkup_irq_set_wake(struct irq_data *irqd, unsigned int on) { + struct irq_chip *chip = irq_data_get_irq_chip(irqd); + struct exynos_irq_chip *our_chip = to_exynos_irq_chip(chip); struct samsung_pin_bank *bank = irq_data_get_irq_chip_data(irqd); unsigned long bit = 1UL << (2 * bank->eint_offset + irqd->hwirq); @@ -339,6 +345,7 @@ static int exynos_wkup_irq_set_wake(struct irq_data *irqd, unsigned int on) exynos_eint_wake_mask |= bit; else exynos_eint_wake_mask &= ~bit; + our_chip->eint_wake_mask_value = exynos_eint_wake_mask; return 0; } @@ -360,6 +367,9 @@ static const struct exynos_irq_chip s5pv210_wkup_irq_chip __initconst = { .eint_con = EXYNOS_WKUP_ECON_OFFSET, .eint_mask = EXYNOS_WKUP_EMASK_OFFSET, .eint_pend = EXYNOS_WKUP_EPEND_OFFSET, + .eint_wake_mask_value = EXYNOS_EINT_WAKEUP_MASK_DISABLED, + /* Only difference with exynos4210_wkup_irq_chip: */ + .eint_wake_mask_reg = S5PV210_EINT_WAKEUP_MASK, }; static const struct exynos_irq_chip exynos4210_wkup_irq_chip __initconst = { @@ -376,6 +386,8 @@ static const struct exynos_irq_chip exynos4210_wkup_irq_chip __initconst = { .eint_con = EXYNOS_WKUP_ECON_OFFSET, .eint_mask = EXYNOS_WKUP_EMASK_OFFSET, .eint_pend = EXYNOS_WKUP_EPEND_OFFSET, + .eint_wake_mask_value = EXYNOS_EINT_WAKEUP_MASK_DISABLED, + .eint_wake_mask_reg = EXYNOS_EINT_WAKEUP_MASK, }; static const struct exynos_irq_chip exynos7_wkup_irq_chip __initconst = { @@ -392,6 +404,8 @@ static const struct exynos_irq_chip exynos7_wkup_irq_chip __initconst = { .eint_con = EXYNOS7_WKUP_ECON_OFFSET, .eint_mask = EXYNOS7_WKUP_EMASK_OFFSET, .eint_pend = EXYNOS7_WKUP_EPEND_OFFSET, + .eint_wake_mask_value = EXYNOS_EINT_WAKEUP_MASK_DISABLED, + .eint_wake_mask_reg = EXYNOS5433_EINT_WAKEUP_MASK, }; /* list of external wakeup controllers supported */ @@ -560,6 +574,27 @@ int exynos_eint_wkup_init(struct samsung_pinctrl_drv_data *d) return 0; } +static void +exynos_pinctrl_set_eint_wakeup_mask(struct samsung_pinctrl_drv_data *drvdata, + struct exynos_irq_chip *irq_chip) +{ + struct regmap *pmu_regs; + + if (!drvdata->retention_ctrl || !drvdata->retention_ctrl->priv) { + dev_warn(drvdata->dev, + "No retention data configured bank with external wakeup interrupt. Wake-up mask will not be set.\n"); + return; + } + + pmu_regs = drvdata->retention_ctrl->priv; + dev_info(drvdata->dev, + "Setting external wakeup interrupt wakeup mask: 0x%x\n", + irq_chip->eint_wake_mask_value); + + regmap_write(pmu_regs, irq_chip->eint_wake_mask_reg, + irq_chip->eint_wake_mask_value); +} + static void exynos_pinctrl_suspend_bank( struct samsung_pinctrl_drv_data *drvdata, struct samsung_pin_bank *bank) @@ -582,11 +617,24 @@ static void exynos_pinctrl_suspend_bank( void exynos_pinctrl_suspend(struct samsung_pinctrl_drv_data *drvdata) { struct samsung_pin_bank *bank = drvdata->pin_banks; + struct exynos_irq_chip *irq_chip = NULL; int i; - for (i = 0; i < drvdata->nr_banks; ++i, ++bank) + for (i = 0; i < drvdata->nr_banks; ++i, ++bank) { if (bank->eint_type == EINT_TYPE_GPIO) exynos_pinctrl_suspend_bank(drvdata, bank); + else if (bank->eint_type == EINT_TYPE_WKUP) { + if (!irq_chip) { + irq_chip = bank->irq_chip; + exynos_pinctrl_set_eint_wakeup_mask(drvdata, + irq_chip); + } else if (bank->irq_chip != irq_chip) { + dev_warn(drvdata->dev, + "More than one external wakeup interrupt chip configured (bank: %s). This is not supported by hardware nor by driver.\n", + bank->name); + } + } + } } static void exynos_pinctrl_resume_bank( diff --git a/drivers/pinctrl/samsung/pinctrl-samsung.h b/drivers/pinctrl/samsung/pinctrl-samsung.h index aac16cc8362a..e571bbd7139b 100644 --- a/drivers/pinctrl/samsung/pinctrl-samsung.h +++ b/drivers/pinctrl/samsung/pinctrl-samsung.h @@ -227,6 +227,9 @@ struct samsung_retention_data { * device suspend, see samsung_pinctrl_suspend() * @resume: platform specific resume callback, executed during pin controller * device suspend, see samsung_pinctrl_resume() + * + * External wakeup interrupts must define at least eint_wkup_init, + * retention_data and suspend in order for proper suspend/resume to work. */ struct samsung_pin_ctrl { const struct samsung_pin_bank_data *pin_banks; diff --git a/include/linux/soc/samsung/exynos-regs-pmu.h b/include/linux/soc/samsung/exynos-regs-pmu.h index eb0d240df7a7..5addaf5ccbce 100644 --- a/include/linux/soc/samsung/exynos-regs-pmu.h +++ b/include/linux/soc/samsung/exynos-regs-pmu.h @@ -42,6 +42,8 @@ #define EXYNOS_SWRESET 0x0400 #define S5P_WAKEUP_STAT 0x0600 +/* Value for EXYNOS_EINT_WAKEUP_MASK disabling all external wakeup interrupts */ +#define EXYNOS_EINT_WAKEUP_MASK_DISABLED 0xffffffff #define EXYNOS_EINT_WAKEUP_MASK 0x0604 #define S5P_WAKEUP_MASK 0x0608 #define S5P_WAKEUP_MASK2 0x0614 -- cgit v1.2.3 From b3793159249bb091efce4b1515ce18cdfc4c6e41 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 18 Jul 2018 22:03:50 +0200 Subject: dt-bindings: pinctrl: samsung: Add SPDX license identifier Replace GPL license statement with SPDX license identifier (GPL-2.0). Signed-off-by: Krzysztof Kozlowski --- include/dt-bindings/pinctrl/samsung.h | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/dt-bindings/pinctrl/samsung.h b/include/dt-bindings/pinctrl/samsung.h index ceb672305f59..b1832506b923 100644 --- a/include/dt-bindings/pinctrl/samsung.h +++ b/include/dt-bindings/pinctrl/samsung.h @@ -1,14 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Samsung's Exynos pinctrl bindings * * Copyright (c) 2016 Samsung Electronics Co., Ltd. * http://www.samsung.com * Author: Krzysztof Kozlowski - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. -*/ + */ #ifndef __DT_BINDINGS_PINCTRL_SAMSUNG_H__ #define __DT_BINDINGS_PINCTRL_SAMSUNG_H__ -- cgit v1.2.3 From 071f52fbce6161706d070ceada5accb81630bf02 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 24 Jul 2018 09:52:32 +0200 Subject: block: remove bio_clone_kmalloc Unused now. Signed-off-by: Christoph Hellwig Reviewed-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/bio.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index ab221c517f4e..b861baa59454 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -443,12 +443,6 @@ static inline struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned int nr_iovecs) return bio_alloc_bioset(gfp_mask, nr_iovecs, NULL); } -static inline struct bio *bio_clone_kmalloc(struct bio *bio, gfp_t gfp_mask) -{ - return bio_clone_bioset(bio, gfp_mask, NULL); - -} - extern blk_qc_t submit_bio(struct bio *); extern void bio_endio(struct bio *); -- cgit v1.2.3 From c55183c9aaa00d2bbb578169a480e31aff3d397c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 24 Jul 2018 09:52:34 +0200 Subject: block: unexport bio_clone_bioset Now only used by the bounce code, so move it there and mark the function static. Signed-off-by: Christoph Hellwig Reviewed-by: Ming Lei Signed-off-by: Jens Axboe --- block/bio.c | 77 ----------------------------------------------------- block/bounce.c | 69 ++++++++++++++++++++++++++++++++++++++++++++++- include/linux/bio.h | 1 - 3 files changed, 68 insertions(+), 79 deletions(-) (limited to 'include') diff --git a/block/bio.c b/block/bio.c index 07d3ffd95989..b832151cd0bf 100644 --- a/block/bio.c +++ b/block/bio.c @@ -646,83 +646,6 @@ struct bio *bio_clone_fast(struct bio *bio, gfp_t gfp_mask, struct bio_set *bs) } EXPORT_SYMBOL(bio_clone_fast); -/** - * bio_clone_bioset - clone a bio - * @bio_src: bio to clone - * @gfp_mask: allocation priority - * @bs: bio_set to allocate from - * - * Clone bio. Caller will own the returned bio, but not the actual data it - * points to. Reference count of returned bio will be one. - */ -struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask, - struct bio_set *bs) -{ - struct bvec_iter iter; - struct bio_vec bv; - struct bio *bio; - - /* - * Pre immutable biovecs, __bio_clone() used to just do a memcpy from - * bio_src->bi_io_vec to bio->bi_io_vec. - * - * We can't do that anymore, because: - * - * - The point of cloning the biovec is to produce a bio with a biovec - * the caller can modify: bi_idx and bi_bvec_done should be 0. - * - * - The original bio could've had more than BIO_MAX_PAGES biovecs; if - * we tried to clone the whole thing bio_alloc_bioset() would fail. - * But the clone should succeed as long as the number of biovecs we - * actually need to allocate is fewer than BIO_MAX_PAGES. - * - * - Lastly, bi_vcnt should not be looked at or relied upon by code - * that does not own the bio - reason being drivers don't use it for - * iterating over the biovec anymore, so expecting it to be kept up - * to date (i.e. for clones that share the parent biovec) is just - * asking for trouble and would force extra work on - * __bio_clone_fast() anyways. - */ - - bio = bio_alloc_bioset(gfp_mask, bio_segments(bio_src), bs); - if (!bio) - return NULL; - bio->bi_disk = bio_src->bi_disk; - bio->bi_opf = bio_src->bi_opf; - bio->bi_write_hint = bio_src->bi_write_hint; - bio->bi_iter.bi_sector = bio_src->bi_iter.bi_sector; - bio->bi_iter.bi_size = bio_src->bi_iter.bi_size; - - switch (bio_op(bio)) { - case REQ_OP_DISCARD: - case REQ_OP_SECURE_ERASE: - case REQ_OP_WRITE_ZEROES: - break; - case REQ_OP_WRITE_SAME: - bio->bi_io_vec[bio->bi_vcnt++] = bio_src->bi_io_vec[0]; - break; - default: - bio_for_each_segment(bv, bio_src, iter) - bio->bi_io_vec[bio->bi_vcnt++] = bv; - break; - } - - if (bio_integrity(bio_src)) { - int ret; - - ret = bio_integrity_clone(bio, bio_src, gfp_mask); - if (ret < 0) { - bio_put(bio); - return NULL; - } - } - - bio_clone_blkcg_association(bio, bio_src); - - return bio; -} -EXPORT_SYMBOL(bio_clone_bioset); - /** * bio_add_pc_page - attempt to add page to bio * @q: the target queue diff --git a/block/bounce.c b/block/bounce.c index fd31347b7836..bc63b3a2d18c 100644 --- a/block/bounce.c +++ b/block/bounce.c @@ -195,6 +195,73 @@ static void bounce_end_io_read_isa(struct bio *bio) __bounce_end_io_read(bio, &isa_page_pool); } +static struct bio *bounce_clone_bio(struct bio *bio_src, gfp_t gfp_mask, + struct bio_set *bs) +{ + struct bvec_iter iter; + struct bio_vec bv; + struct bio *bio; + + /* + * Pre immutable biovecs, __bio_clone() used to just do a memcpy from + * bio_src->bi_io_vec to bio->bi_io_vec. + * + * We can't do that anymore, because: + * + * - The point of cloning the biovec is to produce a bio with a biovec + * the caller can modify: bi_idx and bi_bvec_done should be 0. + * + * - The original bio could've had more than BIO_MAX_PAGES biovecs; if + * we tried to clone the whole thing bio_alloc_bioset() would fail. + * But the clone should succeed as long as the number of biovecs we + * actually need to allocate is fewer than BIO_MAX_PAGES. + * + * - Lastly, bi_vcnt should not be looked at or relied upon by code + * that does not own the bio - reason being drivers don't use it for + * iterating over the biovec anymore, so expecting it to be kept up + * to date (i.e. for clones that share the parent biovec) is just + * asking for trouble and would force extra work on + * __bio_clone_fast() anyways. + */ + + bio = bio_alloc_bioset(gfp_mask, bio_segments(bio_src), bs); + if (!bio) + return NULL; + bio->bi_disk = bio_src->bi_disk; + bio->bi_opf = bio_src->bi_opf; + bio->bi_write_hint = bio_src->bi_write_hint; + bio->bi_iter.bi_sector = bio_src->bi_iter.bi_sector; + bio->bi_iter.bi_size = bio_src->bi_iter.bi_size; + + switch (bio_op(bio)) { + case REQ_OP_DISCARD: + case REQ_OP_SECURE_ERASE: + case REQ_OP_WRITE_ZEROES: + break; + case REQ_OP_WRITE_SAME: + bio->bi_io_vec[bio->bi_vcnt++] = bio_src->bi_io_vec[0]; + break; + default: + bio_for_each_segment(bv, bio_src, iter) + bio->bi_io_vec[bio->bi_vcnt++] = bv; + break; + } + + if (bio_integrity(bio_src)) { + int ret; + + ret = bio_integrity_clone(bio, bio_src, gfp_mask); + if (ret < 0) { + bio_put(bio); + return NULL; + } + } + + bio_clone_blkcg_association(bio, bio_src); + + return bio; +} + static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig, mempool_t *pool) { @@ -222,7 +289,7 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig, generic_make_request(*bio_orig); *bio_orig = bio; } - bio = bio_clone_bioset(*bio_orig, GFP_NOIO, passthrough ? NULL : + bio = bounce_clone_bio(*bio_orig, GFP_NOIO, passthrough ? NULL : &bounce_bio_set); bio_for_each_segment_all(to, bio, i) { diff --git a/include/linux/bio.h b/include/linux/bio.h index b861baa59454..51371740d2a8 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -429,7 +429,6 @@ extern void bio_put(struct bio *); extern void __bio_clone_fast(struct bio *, struct bio *); extern struct bio *bio_clone_fast(struct bio *, gfp_t, struct bio_set *); -extern struct bio *bio_clone_bioset(struct bio *, gfp_t, struct bio_set *bs); extern struct bio_set fs_bio_set; -- cgit v1.2.3 From 56ab8cdbc1438507d79085fcc7e511327d84aeb8 Mon Sep 17 00:00:00 2001 From: Niklas Söderlund Date: Thu, 17 May 2018 10:30:16 -0400 Subject: media: v4l: Add support for STD ioctls on subdev nodes MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is no way to control the standard of subdevices which are part of a media device. The ioctls which exists all target video devices explicitly and the idea is that the video device should talk to the subdevice. For subdevices part of a media graph this is not possible and the standard must be controlled on the subdev device directly. Add four new ioctls to be able to directly interact with subdevices and control the video standard; VIDIOC_SUBDEV_ENUMSTD, VIDIOC_SUBDEV_G_STD, VIDIOC_SUBDEV_S_STD and VIDIOC_SUBDEV_QUERYSTD. Signed-off-by: Niklas Söderlund Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- Documentation/media/uapi/v4l/vidioc-enumstd.rst | 11 +++++++---- Documentation/media/uapi/v4l/vidioc-g-std.rst | 14 ++++++++++---- Documentation/media/uapi/v4l/vidioc-querystd.rst | 11 +++++++---- drivers/media/v4l2-core/v4l2-subdev.c | 22 ++++++++++++++++++++++ include/uapi/linux/v4l2-subdev.h | 4 ++++ 5 files changed, 50 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/Documentation/media/uapi/v4l/vidioc-enumstd.rst b/Documentation/media/uapi/v4l/vidioc-enumstd.rst index b7fda29f46a1..2644a62acd4b 100644 --- a/Documentation/media/uapi/v4l/vidioc-enumstd.rst +++ b/Documentation/media/uapi/v4l/vidioc-enumstd.rst @@ -2,14 +2,14 @@ .. _VIDIOC_ENUMSTD: -******************** -ioctl VIDIOC_ENUMSTD -******************** +******************************************* +ioctl VIDIOC_ENUMSTD, VIDIOC_SUBDEV_ENUMSTD +******************************************* Name ==== -VIDIOC_ENUMSTD - Enumerate supported video standards +VIDIOC_ENUMSTD - VIDIOC_SUBDEV_ENUMSTD - Enumerate supported video standards Synopsis @@ -18,6 +18,9 @@ Synopsis .. c:function:: int ioctl( int fd, VIDIOC_ENUMSTD, struct v4l2_standard *argp ) :name: VIDIOC_ENUMSTD +.. c:function:: int ioctl( int fd, VIDIOC_SUBDEV_ENUMSTD, struct v4l2_standard *argp ) + :name: VIDIOC_SUBDEV_ENUMSTD + Arguments ========= diff --git a/Documentation/media/uapi/v4l/vidioc-g-std.rst b/Documentation/media/uapi/v4l/vidioc-g-std.rst index 90791ab51a53..8d94f0404df2 100644 --- a/Documentation/media/uapi/v4l/vidioc-g-std.rst +++ b/Documentation/media/uapi/v4l/vidioc-g-std.rst @@ -2,14 +2,14 @@ .. _VIDIOC_G_STD: -******************************** -ioctl VIDIOC_G_STD, VIDIOC_S_STD -******************************** +************************************************************************** +ioctl VIDIOC_G_STD, VIDIOC_S_STD, VIDIOC_SUBDEV_G_STD, VIDIOC_SUBDEV_S_STD +************************************************************************** Name ==== -VIDIOC_G_STD - VIDIOC_S_STD - Query or select the video standard of the current input +VIDIOC_G_STD - VIDIOC_S_STD - VIDIOC_SUBDEV_G_STD - VIDIOC_SUBDEV_S_STD - Query or select the video standard of the current input Synopsis @@ -21,6 +21,12 @@ Synopsis .. c:function:: int ioctl( int fd, VIDIOC_S_STD, const v4l2_std_id *argp ) :name: VIDIOC_S_STD +.. c:function:: int ioctl( int fd, VIDIOC_SUBDEV_G_STD, v4l2_std_id *argp ) + :name: VIDIOC_SUBDEV_G_STD + +.. c:function:: int ioctl( int fd, VIDIOC_SUBDEV_S_STD, const v4l2_std_id *argp ) + :name: VIDIOC_SUBDEV_S_STD + Arguments ========= diff --git a/Documentation/media/uapi/v4l/vidioc-querystd.rst b/Documentation/media/uapi/v4l/vidioc-querystd.rst index cf40bca19b9f..a8385cc74818 100644 --- a/Documentation/media/uapi/v4l/vidioc-querystd.rst +++ b/Documentation/media/uapi/v4l/vidioc-querystd.rst @@ -2,14 +2,14 @@ .. _VIDIOC_QUERYSTD: -********************* -ioctl VIDIOC_QUERYSTD -********************* +********************************************* +ioctl VIDIOC_QUERYSTD, VIDIOC_SUBDEV_QUERYSTD +********************************************* Name ==== -VIDIOC_QUERYSTD - Sense the video standard received by the current input +VIDIOC_QUERYSTD - VIDIOC_SUBDEV_QUERYSTD - Sense the video standard received by the current input Synopsis @@ -18,6 +18,9 @@ Synopsis .. c:function:: int ioctl( int fd, VIDIOC_QUERYSTD, v4l2_std_id *argp ) :name: VIDIOC_QUERYSTD +.. c:function:: int ioctl( int fd, VIDIOC_SUBDEV_QUERYSTD, v4l2_std_id *argp ) + :name: VIDIOC_SUBDEV_QUERYSTD + Arguments ========= diff --git a/drivers/media/v4l2-core/v4l2-subdev.c b/drivers/media/v4l2-core/v4l2-subdev.c index 6a7f7f75dfd7..2b63fa6b6fc9 100644 --- a/drivers/media/v4l2-core/v4l2-subdev.c +++ b/drivers/media/v4l2-core/v4l2-subdev.c @@ -494,6 +494,28 @@ static long subdev_do_ioctl(struct file *file, unsigned int cmd, void *arg) case VIDIOC_SUBDEV_S_DV_TIMINGS: return v4l2_subdev_call(sd, video, s_dv_timings, arg); + + case VIDIOC_SUBDEV_G_STD: + return v4l2_subdev_call(sd, video, g_std, arg); + + case VIDIOC_SUBDEV_S_STD: { + v4l2_std_id *std = arg; + + return v4l2_subdev_call(sd, video, s_std, *std); + } + + case VIDIOC_SUBDEV_ENUMSTD: { + struct v4l2_standard *p = arg; + v4l2_std_id id; + + if (v4l2_subdev_call(sd, video, g_tvnorms, &id)) + return -EINVAL; + + return v4l_video_std_enumstd(p, id); + } + + case VIDIOC_SUBDEV_QUERYSTD: + return v4l2_subdev_call(sd, video, querystd, arg); #endif default: return v4l2_subdev_call(sd, core, ioctl, cmd, arg); diff --git a/include/uapi/linux/v4l2-subdev.h b/include/uapi/linux/v4l2-subdev.h index c95a53e6743c..03970ce30741 100644 --- a/include/uapi/linux/v4l2-subdev.h +++ b/include/uapi/linux/v4l2-subdev.h @@ -170,8 +170,12 @@ struct v4l2_subdev_selection { #define VIDIOC_SUBDEV_G_SELECTION _IOWR('V', 61, struct v4l2_subdev_selection) #define VIDIOC_SUBDEV_S_SELECTION _IOWR('V', 62, struct v4l2_subdev_selection) /* The following ioctls are identical to the ioctls in videodev2.h */ +#define VIDIOC_SUBDEV_G_STD _IOR('V', 23, v4l2_std_id) +#define VIDIOC_SUBDEV_S_STD _IOW('V', 24, v4l2_std_id) +#define VIDIOC_SUBDEV_ENUMSTD _IOWR('V', 25, struct v4l2_standard) #define VIDIOC_SUBDEV_G_EDID _IOWR('V', 40, struct v4l2_edid) #define VIDIOC_SUBDEV_S_EDID _IOWR('V', 41, struct v4l2_edid) +#define VIDIOC_SUBDEV_QUERYSTD _IOR('V', 63, v4l2_std_id) #define VIDIOC_SUBDEV_S_DV_TIMINGS _IOWR('V', 87, struct v4l2_dv_timings) #define VIDIOC_SUBDEV_G_DV_TIMINGS _IOWR('V', 88, struct v4l2_dv_timings) #define VIDIOC_SUBDEV_ENUM_DV_TIMINGS _IOWR('V', 98, struct v4l2_enum_dv_timings) -- cgit v1.2.3 From b8f8c8eb408b36ad55dd41a616b3f51998880fb6 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sat, 21 Jul 2018 15:48:47 +0200 Subject: net: phy: add GBit master / slave error detection Certain PHY's have issues when operating in GBit slave mode and can be forced to master mode. Examples are RTL8211C, also the Micrel PHY driver has a DT setting to force master mode. If two such chips are link partners the autonegotiation will fail. Standard defines a self-clearing on read, latched-high bit to indicate this error. Check this bit to inform the user. Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- drivers/net/phy/phy_device.c | 8 ++++++++ include/uapi/linux/mii.h | 1 + 2 files changed, 9 insertions(+) (limited to 'include') diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index b9f5f40a7ac1..db1172db1e7c 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1555,6 +1555,14 @@ int genphy_read_status(struct phy_device *phydev) if (adv < 0) return adv; + if (lpagb & LPA_1000MSFAIL) { + if (adv & CTL1000_ENABLE_MASTER) + phydev_err(phydev, "Master/Slave resolution failed, maybe conflicting manual settings?\n"); + else + phydev_err(phydev, "Master/Slave resolution failed\n"); + return -ENOLINK; + } + phydev->lp_advertising = mii_stat1000_to_ethtool_lpa_t(lpagb); common_adv_gb = lpagb & adv << 2; diff --git a/include/uapi/linux/mii.h b/include/uapi/linux/mii.h index b5c2fdcf23fd..a506216591d6 100644 --- a/include/uapi/linux/mii.h +++ b/include/uapi/linux/mii.h @@ -136,6 +136,7 @@ #define CTL1000_ENABLE_MASTER 0x1000 /* 1000BASE-T Status register */ +#define LPA_1000MSFAIL 0x8000 /* Master/Slave resolution failure */ #define LPA_1000LOCALRXOK 0x2000 /* Link partner local receiver status */ #define LPA_1000REMRXOK 0x1000 /* Link partner remote receiver status */ #define LPA_1000FULL 0x0800 /* Link partner 1000BASE-T full duplex */ -- cgit v1.2.3 From aea5f654e6b78a0c976f7a25950155932c77a53f Mon Sep 17 00:00:00 2001 From: Nishanth Devarajan Date: Mon, 23 Jul 2018 19:37:41 +0530 Subject: net/sched: add skbprio scheduler Skbprio (SKB Priority Queue) is a queueing discipline that prioritizes packets according to their skb->priority field. Under congestion, already-enqueued lower priority packets will be dropped to make space available for higher priority packets. Skbprio was conceived as a solution for denial-of-service defenses that need to route packets with different priorities as a means to overcome DoS attacks. v5 *Do not reference qdisc_dev(sch)->tx_queue_len for setting limit. Instead set default sch->limit to 64. v4 *Drop Documentation/networking/sch_skbprio.txt doc file to move it to tc man page for Skbprio, in iproute2. v3 *Drop max_limit parameter in struct skbprio_sched_data and instead use sch->limit. *Reference qdisc_dev(sch)->tx_queue_len only once, during initialisation for qdisc (previously being referenced every time qdisc changes). *Move qdisc's detailed description from in-code to Documentation/networking. *When qdisc is saturated, enqueue incoming packet first before dequeueing lowest priority packet in queue - improves usage of call stack registers. *Introduce and use overlimit stat to keep track of number of dropped packets. v2 *Use skb->priority field rather than DS field. Rename queueing discipline as SKB Priority Queue (previously Gatekeeper Priority Queue). *Queueing discipline is made classful to expose Skbprio's internal priority queues. Signed-off-by: Nishanth Devarajan Reviewed-by: Sachin Paryani Reviewed-by: Cody Doucette Reviewed-by: Michel Machado Acked-by: Cong Wang Signed-off-by: David S. Miller --- include/uapi/linux/pkt_sched.h | 15 ++ net/sched/Kconfig | 13 ++ net/sched/Makefile | 1 + net/sched/sch_skbprio.c | 320 +++++++++++++++++++++++++++++++++++++++++ 4 files changed, 349 insertions(+) create mode 100644 net/sched/sch_skbprio.c (limited to 'include') diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index d9cc9dc4f547..8975fd1a1421 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -124,6 +124,21 @@ struct tc_fifo_qopt { __u32 limit; /* Queue length: bytes for bfifo, packets for pfifo */ }; +/* SKBPRIO section */ + +/* + * Priorities go from zero to (SKBPRIO_MAX_PRIORITY - 1). + * SKBPRIO_MAX_PRIORITY should be at least 64 in order for skbprio to be able + * to map one to one the DS field of IPV4 and IPV6 headers. + * Memory allocation grows linearly with SKBPRIO_MAX_PRIORITY. + */ + +#define SKBPRIO_MAX_PRIORITY 64 + +struct tc_skbprio_qopt { + __u32 limit; /* Queue length in packets. */ +}; + /* PRIO section */ #define TCQ_PRIO_BANDS 16 diff --git a/net/sched/Kconfig b/net/sched/Kconfig index bba71225adbd..e95741388311 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -251,6 +251,19 @@ config NET_SCH_MQPRIO If unsure, say N. +config NET_SCH_SKBPRIO + tristate "SKB priority queue scheduler (SKBPRIO)" + help + Say Y here if you want to use the SKB priority queue + scheduler. This schedules packets according to skb->priority, + which is useful for request packets in DoS mitigation systems such + as Gatekeeper. + + To compile this driver as a module, choose M here: the module will + be called sch_skbprio. + + If unsure, say N. + config NET_SCH_CHOKE tristate "CHOose and Keep responsive flow scheduler (CHOKE)" help diff --git a/net/sched/Makefile b/net/sched/Makefile index 910ec7463a36..f0403f49edcb 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -46,6 +46,7 @@ obj-$(CONFIG_NET_SCH_NETEM) += sch_netem.o obj-$(CONFIG_NET_SCH_DRR) += sch_drr.o obj-$(CONFIG_NET_SCH_PLUG) += sch_plug.o obj-$(CONFIG_NET_SCH_MQPRIO) += sch_mqprio.o +obj-$(CONFIG_NET_SCH_SKBPRIO) += sch_skbprio.o obj-$(CONFIG_NET_SCH_CHOKE) += sch_choke.o obj-$(CONFIG_NET_SCH_QFQ) += sch_qfq.o obj-$(CONFIG_NET_SCH_CODEL) += sch_codel.o diff --git a/net/sched/sch_skbprio.c b/net/sched/sch_skbprio.c new file mode 100644 index 000000000000..52c0b6d8f1d7 --- /dev/null +++ b/net/sched/sch_skbprio.c @@ -0,0 +1,320 @@ +/* + * net/sched/sch_skbprio.c SKB Priority Queue. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Authors: Nishanth Devarajan, + * Cody Doucette, + * original idea by Michel Machado, Cody Doucette, and Qiaobin Fu + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* SKB Priority Queue + * ================================= + * + * Skbprio (SKB Priority Queue) is a queueing discipline that prioritizes + * packets according to their skb->priority field. Under congestion, + * Skbprio drops already-enqueued lower priority packets to make space + * available for higher priority packets; it was conceived as a solution + * for denial-of-service defenses that need to route packets with different + * priorities as a mean to overcome DoS attacks. + */ + +struct skbprio_sched_data { + /* Queue state. */ + struct sk_buff_head qdiscs[SKBPRIO_MAX_PRIORITY]; + struct gnet_stats_queue qstats[SKBPRIO_MAX_PRIORITY]; + u16 highest_prio; + u16 lowest_prio; +}; + +static u16 calc_new_high_prio(const struct skbprio_sched_data *q) +{ + int prio; + + for (prio = q->highest_prio - 1; prio >= q->lowest_prio; prio--) { + if (!skb_queue_empty(&q->qdiscs[prio])) + return prio; + } + + /* SKB queue is empty, return 0 (default highest priority setting). */ + return 0; +} + +static u16 calc_new_low_prio(const struct skbprio_sched_data *q) +{ + int prio; + + for (prio = q->lowest_prio + 1; prio <= q->highest_prio; prio++) { + if (!skb_queue_empty(&q->qdiscs[prio])) + return prio; + } + + /* SKB queue is empty, return SKBPRIO_MAX_PRIORITY - 1 + * (default lowest priority setting). + */ + return SKBPRIO_MAX_PRIORITY - 1; +} + +static int skbprio_enqueue(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff **to_free) +{ + const unsigned int max_priority = SKBPRIO_MAX_PRIORITY - 1; + struct skbprio_sched_data *q = qdisc_priv(sch); + struct sk_buff_head *qdisc; + struct sk_buff_head *lp_qdisc; + struct sk_buff *to_drop; + u16 prio, lp; + + /* Obtain the priority of @skb. */ + prio = min(skb->priority, max_priority); + + qdisc = &q->qdiscs[prio]; + if (sch->q.qlen < sch->limit) { + __skb_queue_tail(qdisc, skb); + qdisc_qstats_backlog_inc(sch, skb); + q->qstats[prio].backlog += qdisc_pkt_len(skb); + + /* Check to update highest and lowest priorities. */ + if (prio > q->highest_prio) + q->highest_prio = prio; + + if (prio < q->lowest_prio) + q->lowest_prio = prio; + + sch->q.qlen++; + return NET_XMIT_SUCCESS; + } + + /* If this packet has the lowest priority, drop it. */ + lp = q->lowest_prio; + if (prio <= lp) { + q->qstats[prio].drops++; + q->qstats[prio].overlimits++; + return qdisc_drop(skb, sch, to_free); + } + + __skb_queue_tail(qdisc, skb); + qdisc_qstats_backlog_inc(sch, skb); + q->qstats[prio].backlog += qdisc_pkt_len(skb); + + /* Drop the packet at the tail of the lowest priority qdisc. */ + lp_qdisc = &q->qdiscs[lp]; + to_drop = __skb_dequeue_tail(lp_qdisc); + BUG_ON(!to_drop); + qdisc_qstats_backlog_dec(sch, to_drop); + qdisc_drop(to_drop, sch, to_free); + + q->qstats[lp].backlog -= qdisc_pkt_len(to_drop); + q->qstats[lp].drops++; + q->qstats[lp].overlimits++; + + /* Check to update highest and lowest priorities. */ + if (skb_queue_empty(lp_qdisc)) { + if (q->lowest_prio == q->highest_prio) { + /* The incoming packet is the only packet in queue. */ + BUG_ON(sch->q.qlen != 1); + q->lowest_prio = prio; + q->highest_prio = prio; + } else { + q->lowest_prio = calc_new_low_prio(q); + } + } + + if (prio > q->highest_prio) + q->highest_prio = prio; + + return NET_XMIT_CN; +} + +static struct sk_buff *skbprio_dequeue(struct Qdisc *sch) +{ + struct skbprio_sched_data *q = qdisc_priv(sch); + struct sk_buff_head *hpq = &q->qdiscs[q->highest_prio]; + struct sk_buff *skb = __skb_dequeue(hpq); + + if (unlikely(!skb)) + return NULL; + + sch->q.qlen--; + qdisc_qstats_backlog_dec(sch, skb); + qdisc_bstats_update(sch, skb); + + q->qstats[q->highest_prio].backlog -= qdisc_pkt_len(skb); + + /* Update highest priority field. */ + if (skb_queue_empty(hpq)) { + if (q->lowest_prio == q->highest_prio) { + BUG_ON(sch->q.qlen); + q->highest_prio = 0; + q->lowest_prio = SKBPRIO_MAX_PRIORITY - 1; + } else { + q->highest_prio = calc_new_high_prio(q); + } + } + return skb; +} + +static int skbprio_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + struct tc_skbprio_qopt *ctl = nla_data(opt); + + sch->limit = ctl->limit; + return 0; +} + +static int skbprio_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + struct skbprio_sched_data *q = qdisc_priv(sch); + int prio; + + /* Initialise all queues, one for each possible priority. */ + for (prio = 0; prio < SKBPRIO_MAX_PRIORITY; prio++) + __skb_queue_head_init(&q->qdiscs[prio]); + + memset(&q->qstats, 0, sizeof(q->qstats)); + q->highest_prio = 0; + q->lowest_prio = SKBPRIO_MAX_PRIORITY - 1; + sch->limit = 64; + if (!opt) + return 0; + + return skbprio_change(sch, opt, extack); +} + +static int skbprio_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + struct tc_skbprio_qopt opt; + + opt.limit = sch->limit; + + if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt)) + return -1; + + return skb->len; +} + +static void skbprio_reset(struct Qdisc *sch) +{ + struct skbprio_sched_data *q = qdisc_priv(sch); + int prio; + + sch->qstats.backlog = 0; + sch->q.qlen = 0; + + for (prio = 0; prio < SKBPRIO_MAX_PRIORITY; prio++) + __skb_queue_purge(&q->qdiscs[prio]); + + memset(&q->qstats, 0, sizeof(q->qstats)); + q->highest_prio = 0; + q->lowest_prio = SKBPRIO_MAX_PRIORITY - 1; +} + +static void skbprio_destroy(struct Qdisc *sch) +{ + struct skbprio_sched_data *q = qdisc_priv(sch); + int prio; + + for (prio = 0; prio < SKBPRIO_MAX_PRIORITY; prio++) + __skb_queue_purge(&q->qdiscs[prio]); +} + +static struct Qdisc *skbprio_leaf(struct Qdisc *sch, unsigned long arg) +{ + return NULL; +} + +static unsigned long skbprio_find(struct Qdisc *sch, u32 classid) +{ + return 0; +} + +static int skbprio_dump_class(struct Qdisc *sch, unsigned long cl, + struct sk_buff *skb, struct tcmsg *tcm) +{ + tcm->tcm_handle |= TC_H_MIN(cl); + return 0; +} + +static int skbprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, + struct gnet_dump *d) +{ + struct skbprio_sched_data *q = qdisc_priv(sch); + if (gnet_stats_copy_queue(d, NULL, &q->qstats[cl - 1], + q->qstats[cl - 1].qlen) < 0) + return -1; + return 0; +} + +static void skbprio_walk(struct Qdisc *sch, struct qdisc_walker *arg) +{ + unsigned int i; + + if (arg->stop) + return; + + for (i = 0; i < SKBPRIO_MAX_PRIORITY; i++) { + if (arg->count < arg->skip) { + arg->count++; + continue; + } + if (arg->fn(sch, i + 1, arg) < 0) { + arg->stop = 1; + break; + } + arg->count++; + } +} + +static const struct Qdisc_class_ops skbprio_class_ops = { + .leaf = skbprio_leaf, + .find = skbprio_find, + .dump = skbprio_dump_class, + .dump_stats = skbprio_dump_class_stats, + .walk = skbprio_walk, +}; + +static struct Qdisc_ops skbprio_qdisc_ops __read_mostly = { + .cl_ops = &skbprio_class_ops, + .id = "skbprio", + .priv_size = sizeof(struct skbprio_sched_data), + .enqueue = skbprio_enqueue, + .dequeue = skbprio_dequeue, + .peek = qdisc_peek_dequeued, + .init = skbprio_init, + .reset = skbprio_reset, + .change = skbprio_change, + .dump = skbprio_dump, + .destroy = skbprio_destroy, + .owner = THIS_MODULE, +}; + +static int __init skbprio_module_init(void) +{ + return register_qdisc(&skbprio_qdisc_ops); +} + +static void __exit skbprio_module_exit(void) +{ + unregister_qdisc(&skbprio_qdisc_ops); +} + +module_init(skbprio_module_init) +module_exit(skbprio_module_exit) + +MODULE_LICENSE("GPL"); -- cgit v1.2.3 From 5525b8314389a0c558d15464e86f438974b94e32 Mon Sep 17 00:00:00 2001 From: Ezequiel Garcia Date: Mon, 18 Jun 2018 00:38:52 -0400 Subject: media: mem2mem: Make .job_abort optional Implementing job_abort() does not make sense on some drivers. This is not a problem, as the abort is not required to wait for the job to finish. Quite the opposite, drivers are encouraged not to wait. Demote v4l2_m2m_ops.job_abort from required to optional, and clean all drivers with dummy implementations. Signed-off-by: Ezequiel Garcia Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/media/platform/mtk-jpeg/mtk_jpeg_core.c | 5 ----- drivers/media/platform/mtk-mdp/mtk_mdp_m2m.c | 5 ----- drivers/media/platform/rcar_jpu.c | 5 ----- drivers/media/platform/rockchip/rga/rga.c | 6 ------ drivers/media/platform/s5p-g2d/g2d.c | 5 ----- drivers/media/platform/s5p-jpeg/jpeg-core.c | 7 ------- drivers/media/v4l2-core/v4l2-mem2mem.c | 6 +++--- include/media/v4l2-mem2mem.h | 2 +- 8 files changed, 4 insertions(+), 37 deletions(-) (limited to 'include') diff --git a/drivers/media/platform/mtk-jpeg/mtk_jpeg_core.c b/drivers/media/platform/mtk-jpeg/mtk_jpeg_core.c index 328e8f650d9b..4f24da8afecc 100644 --- a/drivers/media/platform/mtk-jpeg/mtk_jpeg_core.c +++ b/drivers/media/platform/mtk-jpeg/mtk_jpeg_core.c @@ -861,14 +861,9 @@ static int mtk_jpeg_job_ready(void *priv) return (ctx->state == MTK_JPEG_RUNNING) ? 1 : 0; } -static void mtk_jpeg_job_abort(void *priv) -{ -} - static const struct v4l2_m2m_ops mtk_jpeg_m2m_ops = { .device_run = mtk_jpeg_device_run, .job_ready = mtk_jpeg_job_ready, - .job_abort = mtk_jpeg_job_abort, }; static int mtk_jpeg_queue_init(void *priv, struct vb2_queue *src_vq, diff --git a/drivers/media/platform/mtk-mdp/mtk_mdp_m2m.c b/drivers/media/platform/mtk-mdp/mtk_mdp_m2m.c index c2e2f5f1ebf1..ceffc31cc6eb 100644 --- a/drivers/media/platform/mtk-mdp/mtk_mdp_m2m.c +++ b/drivers/media/platform/mtk-mdp/mtk_mdp_m2m.c @@ -441,10 +441,6 @@ static void mtk_mdp_m2m_stop_streaming(struct vb2_queue *q) pm_runtime_put(&ctx->mdp_dev->pdev->dev); } -static void mtk_mdp_m2m_job_abort(void *priv) -{ -} - /* The color format (num_planes) must be already configured. */ static void mtk_mdp_prepare_addr(struct mtk_mdp_ctx *ctx, struct vb2_buffer *vb, @@ -1215,7 +1211,6 @@ static const struct v4l2_file_operations mtk_mdp_m2m_fops = { static const struct v4l2_m2m_ops mtk_mdp_m2m_ops = { .device_run = mtk_mdp_m2m_device_run, - .job_abort = mtk_mdp_m2m_job_abort, }; int mtk_mdp_register_m2m_device(struct mtk_mdp_dev *mdp) diff --git a/drivers/media/platform/rcar_jpu.c b/drivers/media/platform/rcar_jpu.c index 90d40b2d6259..a808258a4180 100644 --- a/drivers/media/platform/rcar_jpu.c +++ b/drivers/media/platform/rcar_jpu.c @@ -1492,13 +1492,8 @@ static void jpu_device_run(void *priv) spin_unlock_irqrestore(&ctx->jpu->lock, flags); } -static void jpu_job_abort(void *priv) -{ -} - static const struct v4l2_m2m_ops jpu_m2m_ops = { .device_run = jpu_device_run, - .job_abort = jpu_job_abort, }; /* diff --git a/drivers/media/platform/rockchip/rga/rga.c b/drivers/media/platform/rockchip/rga/rga.c index 8ace1873202a..69a2797d7bbe 100644 --- a/drivers/media/platform/rockchip/rga/rga.c +++ b/drivers/media/platform/rockchip/rga/rga.c @@ -39,11 +39,6 @@ static int debug; module_param(debug, int, 0644); -static void job_abort(void *prv) -{ - /* Can't do anything rational here */ -} - static void device_run(void *prv) { struct rga_ctx *ctx = prv; @@ -104,7 +99,6 @@ static irqreturn_t rga_isr(int irq, void *prv) static struct v4l2_m2m_ops rga_m2m_ops = { .device_run = device_run, - .job_abort = job_abort, }; static int diff --git a/drivers/media/platform/s5p-g2d/g2d.c b/drivers/media/platform/s5p-g2d/g2d.c index ee7322b33666..e901201b6fcc 100644 --- a/drivers/media/platform/s5p-g2d/g2d.c +++ b/drivers/media/platform/s5p-g2d/g2d.c @@ -483,10 +483,6 @@ static int vidioc_s_crop(struct file *file, void *prv, const struct v4l2_crop *c return 0; } -static void job_abort(void *prv) -{ -} - static void device_run(void *prv) { struct g2d_ctx *ctx = prv; @@ -605,7 +601,6 @@ static const struct video_device g2d_videodev = { static const struct v4l2_m2m_ops g2d_m2m_ops = { .device_run = device_run, - .job_abort = job_abort, }; static const struct of_device_id exynos_g2d_match[]; diff --git a/drivers/media/platform/s5p-jpeg/jpeg-core.c b/drivers/media/platform/s5p-jpeg/jpeg-core.c index 79b63da27f53..04fd2e0493c0 100644 --- a/drivers/media/platform/s5p-jpeg/jpeg-core.c +++ b/drivers/media/platform/s5p-jpeg/jpeg-core.c @@ -2467,26 +2467,19 @@ static int s5p_jpeg_job_ready(void *priv) return 1; } -static void s5p_jpeg_job_abort(void *priv) -{ -} - static struct v4l2_m2m_ops s5p_jpeg_m2m_ops = { .device_run = s5p_jpeg_device_run, .job_ready = s5p_jpeg_job_ready, - .job_abort = s5p_jpeg_job_abort, }; static struct v4l2_m2m_ops exynos3250_jpeg_m2m_ops = { .device_run = exynos3250_jpeg_device_run, .job_ready = s5p_jpeg_job_ready, - .job_abort = s5p_jpeg_job_abort, }; static struct v4l2_m2m_ops exynos4_jpeg_m2m_ops = { .device_run = exynos4_jpeg_device_run, .job_ready = s5p_jpeg_job_ready, - .job_abort = s5p_jpeg_job_abort, }; /* diff --git a/drivers/media/v4l2-core/v4l2-mem2mem.c b/drivers/media/v4l2-core/v4l2-mem2mem.c index 725da74d15d8..4aeedb91594a 100644 --- a/drivers/media/v4l2-core/v4l2-mem2mem.c +++ b/drivers/media/v4l2-core/v4l2-mem2mem.c @@ -322,7 +322,8 @@ static void v4l2_m2m_cancel_job(struct v4l2_m2m_ctx *m2m_ctx) m2m_ctx->job_flags |= TRANS_ABORT; if (m2m_ctx->job_flags & TRANS_RUNNING) { spin_unlock_irqrestore(&m2m_dev->job_spinlock, flags); - m2m_dev->m2m_ops->job_abort(m2m_ctx->priv); + if (m2m_dev->m2m_ops->job_abort) + m2m_dev->m2m_ops->job_abort(m2m_ctx->priv); dprintk("m2m_ctx %p running, will wait to complete", m2m_ctx); wait_event(m2m_ctx->finished, !(m2m_ctx->job_flags & TRANS_RUNNING)); @@ -788,8 +789,7 @@ struct v4l2_m2m_dev *v4l2_m2m_init(const struct v4l2_m2m_ops *m2m_ops) { struct v4l2_m2m_dev *m2m_dev; - if (!m2m_ops || WARN_ON(!m2m_ops->device_run) || - WARN_ON(!m2m_ops->job_abort)) + if (!m2m_ops || WARN_ON(!m2m_ops->device_run)) return ERR_PTR(-EINVAL); m2m_dev = kzalloc(sizeof *m2m_dev, GFP_KERNEL); diff --git a/include/media/v4l2-mem2mem.h b/include/media/v4l2-mem2mem.h index af48b1eca025..d60d3060f762 100644 --- a/include/media/v4l2-mem2mem.h +++ b/include/media/v4l2-mem2mem.h @@ -32,7 +32,7 @@ * assumed that one source and one destination buffer are all * that is required for the driver to perform one full transaction. * This method may not sleep. - * @job_abort: required. Informs the driver that it has to abort the currently + * @job_abort: optional. Informs the driver that it has to abort the currently * running transaction as soon as possible (i.e. as soon as it can * stop the device safely; e.g. in the next interrupt handler), * even if the transaction would not have been finished by then. -- cgit v1.2.3 From 6e30396767508101eacec8b93b068e8905e660dc Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Wed, 20 Jun 2018 22:32:42 +0530 Subject: sched/numa: Remove redundant field 'numa_entry' is a struct list_head defined in task_struct, but never used. No functional change. Signed-off-by: Srikar Dronamraju Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Rik van Riel Acked-by: Mel Gorman Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1529514181-9842-2-git-send-email-srikar@linux.vnet.ibm.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 43731fe51c97..e0f4f56c9310 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1017,7 +1017,6 @@ struct task_struct { u64 last_sum_exec_runtime; struct callback_head numa_work; - struct list_head numa_entry; struct numa_group *numa_group; /* -- cgit v1.2.3 From df79ed2c064363cdc7d2d896923c1885d4e30520 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 16 Jul 2018 12:30:08 +0100 Subject: locking/atomics: Simplify cmpxchg() instrumentation Currently we define some fairly verbose wrappers for the cmpxchg() family so that we can pass a pointer and size into kasan_check_write(). The wrappers duplicate the size-switching logic necessary in arch code, and only work for scalar types. On some architectures, (cmp)xchg are used on non-scalar types, and thus the instrumented wrappers need to be able to handle this. We could take the type-punning logic from {READ,WRITE}_ONCE(), but this makes the wrappers even more verbose, and requires several local variables in the macros. Instead, let's simplify the wrappers into simple macros which: * snapshot the pointer into a single local variable, called __ai_ptr to avoid conflicts with variables in the scope of the caller. * call kasan_check_write() on __ai_ptr. * invoke the relevant arch_*() function, passing the original arguments, bar __ai_ptr being substituted for ptr. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Acked-by: Peter Zijlstra (Intel) Acked-by: Will Deacon Cc: Boqun Feng Cc: Dmitry Vyukov Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: andy.shevchenko@gmail.com Cc: arnd@arndb.de Cc: aryabinin@virtuozzo.com Cc: catalin.marinas@arm.com Cc: glider@google.com Cc: linux-arm-kernel@lists.infradead.org Cc: parri.andrea@gmail.com Cc: peter@hurleysoftware.com Link: http://lkml.kernel.org/r/20180716113017.3909-4-mark.rutland@arm.com Signed-off-by: Ingo Molnar --- include/asm-generic/atomic-instrumented.h | 100 +++++------------------------- 1 file changed, 15 insertions(+), 85 deletions(-) (limited to 'include') diff --git a/include/asm-generic/atomic-instrumented.h b/include/asm-generic/atomic-instrumented.h index 3c64e95d5ed0..c7c3e4cdd942 100644 --- a/include/asm-generic/atomic-instrumented.h +++ b/include/asm-generic/atomic-instrumented.h @@ -408,109 +408,39 @@ static __always_inline bool atomic64_add_negative(s64 i, atomic64_t *v) } #endif -static __always_inline unsigned long -cmpxchg_size(volatile void *ptr, unsigned long old, unsigned long new, int size) -{ - kasan_check_write(ptr, size); - switch (size) { - case 1: - return arch_cmpxchg((u8 *)ptr, (u8)old, (u8)new); - case 2: - return arch_cmpxchg((u16 *)ptr, (u16)old, (u16)new); - case 4: - return arch_cmpxchg((u32 *)ptr, (u32)old, (u32)new); - case 8: - BUILD_BUG_ON(sizeof(unsigned long) != 8); - return arch_cmpxchg((u64 *)ptr, (u64)old, (u64)new); - } - BUILD_BUG(); - return 0; -} - #define cmpxchg(ptr, old, new) \ ({ \ - ((__typeof__(*(ptr)))cmpxchg_size((ptr), (unsigned long)(old), \ - (unsigned long)(new), sizeof(*(ptr)))); \ + typeof(ptr) __ai_ptr = (ptr); \ + kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg(__ai_ptr, (old), (new)); \ }) -static __always_inline unsigned long -sync_cmpxchg_size(volatile void *ptr, unsigned long old, unsigned long new, - int size) -{ - kasan_check_write(ptr, size); - switch (size) { - case 1: - return arch_sync_cmpxchg((u8 *)ptr, (u8)old, (u8)new); - case 2: - return arch_sync_cmpxchg((u16 *)ptr, (u16)old, (u16)new); - case 4: - return arch_sync_cmpxchg((u32 *)ptr, (u32)old, (u32)new); - case 8: - BUILD_BUG_ON(sizeof(unsigned long) != 8); - return arch_sync_cmpxchg((u64 *)ptr, (u64)old, (u64)new); - } - BUILD_BUG(); - return 0; -} - #define sync_cmpxchg(ptr, old, new) \ ({ \ - ((__typeof__(*(ptr)))sync_cmpxchg_size((ptr), \ - (unsigned long)(old), (unsigned long)(new), \ - sizeof(*(ptr)))); \ + typeof(ptr) __ai_ptr = (ptr); \ + kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_sync_cmpxchg(__ai_ptr, (old), (new)); \ }) -static __always_inline unsigned long -cmpxchg_local_size(volatile void *ptr, unsigned long old, unsigned long new, - int size) -{ - kasan_check_write(ptr, size); - switch (size) { - case 1: - return arch_cmpxchg_local((u8 *)ptr, (u8)old, (u8)new); - case 2: - return arch_cmpxchg_local((u16 *)ptr, (u16)old, (u16)new); - case 4: - return arch_cmpxchg_local((u32 *)ptr, (u32)old, (u32)new); - case 8: - BUILD_BUG_ON(sizeof(unsigned long) != 8); - return arch_cmpxchg_local((u64 *)ptr, (u64)old, (u64)new); - } - BUILD_BUG(); - return 0; -} - #define cmpxchg_local(ptr, old, new) \ ({ \ - ((__typeof__(*(ptr)))cmpxchg_local_size((ptr), \ - (unsigned long)(old), (unsigned long)(new), \ - sizeof(*(ptr)))); \ + typeof(ptr) __ai_ptr = (ptr); \ + kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg_local(__ai_ptr, (old), (new)); \ }) -static __always_inline u64 -cmpxchg64_size(volatile u64 *ptr, u64 old, u64 new) -{ - kasan_check_write(ptr, sizeof(*ptr)); - return arch_cmpxchg64(ptr, old, new); -} - #define cmpxchg64(ptr, old, new) \ ({ \ - ((__typeof__(*(ptr)))cmpxchg64_size((ptr), (u64)(old), \ - (u64)(new))); \ + typeof(ptr) __ai_ptr = (ptr); \ + kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg64(__ai_ptr, (old), (new)); \ }) -static __always_inline u64 -cmpxchg64_local_size(volatile u64 *ptr, u64 old, u64 new) -{ - kasan_check_write(ptr, sizeof(*ptr)); - return arch_cmpxchg64_local(ptr, old, new); -} - #define cmpxchg64_local(ptr, old, new) \ ({ \ - ((__typeof__(*(ptr)))cmpxchg64_local_size((ptr), (u64)(old), \ - (u64)(new))); \ + typeof(ptr) __ai_ptr = (ptr); \ + kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg64_local(__ai_ptr, (old), (new)); \ }) /* -- cgit v1.2.3 From f9881cc43b118efc6f82fef2d121166113ee9f8e Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 16 Jul 2018 12:30:09 +0100 Subject: locking/atomics: Instrument xchg() While we instrument all of the (non-relaxed) atomic_*() functions and cmpxchg(), we missed xchg(). Let's add instrumentation for xchg(), fixing up x86 to implement arch_xchg(). Signed-off-by: Mark Rutland Acked-by: Peter Zijlstra (Intel) Acked-by: Will Deacon Cc: Boqun Feng Cc: Dmitry Vyukov Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: andy.shevchenko@gmail.com Cc: arnd@arndb.de Cc: aryabinin@virtuozzo.com Cc: catalin.marinas@arm.com Cc: glider@google.com Cc: linux-arm-kernel@lists.infradead.org Cc: parri.andrea@gmail.com Cc: peter@hurleysoftware.com Link: http://lkml.kernel.org/r/20180716113017.3909-5-mark.rutland@arm.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/atomic.h | 2 +- arch/x86/include/asm/atomic64_64.h | 2 +- arch/x86/include/asm/cmpxchg.h | 2 +- include/asm-generic/atomic-instrumented.h | 7 +++++++ 4 files changed, 10 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h index 823fd2f320cf..b143717b92b3 100644 --- a/arch/x86/include/asm/atomic.h +++ b/arch/x86/include/asm/atomic.h @@ -202,7 +202,7 @@ static __always_inline bool arch_atomic_try_cmpxchg(atomic_t *v, int *old, int n static inline int arch_atomic_xchg(atomic_t *v, int new) { - return xchg(&v->counter, new); + return arch_xchg(&v->counter, new); } static inline void arch_atomic_and(int i, atomic_t *v) diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h index 849f1c566a11..4343d9b4f30e 100644 --- a/arch/x86/include/asm/atomic64_64.h +++ b/arch/x86/include/asm/atomic64_64.h @@ -188,7 +188,7 @@ static __always_inline bool arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, l static inline long arch_atomic64_xchg(atomic64_t *v, long new) { - return xchg(&v->counter, new); + return arch_xchg(&v->counter, new); } static inline void arch_atomic64_and(long i, atomic64_t *v) diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h index e3efd8a06066..a55d79b233d3 100644 --- a/arch/x86/include/asm/cmpxchg.h +++ b/arch/x86/include/asm/cmpxchg.h @@ -75,7 +75,7 @@ extern void __add_wrong_size(void) * use "asm volatile" and "memory" clobbers to prevent gcc from moving * information around. */ -#define xchg(ptr, v) __xchg_op((ptr), (v), xchg, "") +#define arch_xchg(ptr, v) __xchg_op((ptr), (v), xchg, "") /* * Atomic compare and exchange. Compare OLD with MEM, if identical, diff --git a/include/asm-generic/atomic-instrumented.h b/include/asm-generic/atomic-instrumented.h index c7c3e4cdd942..53481b6eacdf 100644 --- a/include/asm-generic/atomic-instrumented.h +++ b/include/asm-generic/atomic-instrumented.h @@ -408,6 +408,13 @@ static __always_inline bool atomic64_add_negative(s64 i, atomic64_t *v) } #endif +#define xchg(ptr, new) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + kasan_check_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_xchg(__ai_ptr, (new)); \ +}) + #define cmpxchg(ptr, old, new) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ -- cgit v1.2.3 From 4d2b25f630c731218d04f72580b4de68cb7a6e00 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 16 Jul 2018 12:30:10 +0100 Subject: locking/atomics: Instrument cmpxchg_double*() We currently don't instrument cmpxchg_double() and cmpxchg_double_local() due to compilation issues reported in the past, which are supposedly related to GCC bug 72873 [1], reported when GCC 7 was not yet released. This bug only applies to x86-64, and does not apply to other architectures. While the test case for GCC bug 72873 triggers issues with released versions of GCC, the instrumented kernel code compiles fine for all configurations I have tried, and it is unclear how the two cases are/were related. As we can't reproduce the kernel build failures, let's instrument cmpxchg_double*() again. We can revisit the issue if build failures reappear. Signed-off-by: Mark Rutland Acked-by: Peter Zijlstra (Intel) Acked-by: Will Deacon Cc: Arnd Bergmann Cc: Boqun Feng Cc: Dmitry Vyukov Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: andy.shevchenko@gmail.com Cc: aryabinin@virtuozzo.com Cc: catalin.marinas@arm.com Cc: glider@google.com Cc: linux-arm-kernel@lists.infradead.org Cc: parri.andrea@gmail.com Cc: peter@hurleysoftware.com Link: http://lkml.kernel.org/r/20180716113017.3909-6-mark.rutland@arm.com Signed-off-by: Ingo Molnar --- include/asm-generic/atomic-instrumented.h | 21 ++++++++------------- 1 file changed, 8 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/asm-generic/atomic-instrumented.h b/include/asm-generic/atomic-instrumented.h index 53481b6eacdf..0d4b1d3dbc1e 100644 --- a/include/asm-generic/atomic-instrumented.h +++ b/include/asm-generic/atomic-instrumented.h @@ -450,23 +450,18 @@ static __always_inline bool atomic64_add_negative(s64 i, atomic64_t *v) arch_cmpxchg64_local(__ai_ptr, (old), (new)); \ }) -/* - * Originally we had the following code here: - * __typeof__(p1) ____p1 = (p1); - * kasan_check_write(____p1, 2 * sizeof(*____p1)); - * arch_cmpxchg_double(____p1, (p2), (o1), (o2), (n1), (n2)); - * But it leads to compilation failures (see gcc issue 72873). - * So for now it's left non-instrumented. - * There are few callers of cmpxchg_double(), so it's not critical. - */ #define cmpxchg_double(p1, p2, o1, o2, n1, n2) \ ({ \ - arch_cmpxchg_double((p1), (p2), (o1), (o2), (n1), (n2)); \ + typeof(p1) __ai_p1 = (p1); \ + kasan_check_write(__ai_p1, 2 * sizeof(*__ai_p1)); \ + arch_cmpxchg_double(__ai_p1, (p2), (o1), (o2), (n1), (n2)); \ }) -#define cmpxchg_double_local(p1, p2, o1, o2, n1, n2) \ -({ \ - arch_cmpxchg_double_local((p1), (p2), (o1), (o2), (n1), (n2)); \ +#define cmpxchg_double_local(p1, p2, o1, o2, n1, n2) \ +({ \ + typeof(p1) __ai_p1 = (p1); \ + kasan_check_write(__ai_p1, 2 * sizeof(*__ai_p1)); \ + arch_cmpxchg_double_local(__ai_p1, (p2), (o1), (o2), (n1), (n2)); \ }) #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */ -- cgit v1.2.3 From fd2efaa4eb5317c3a86357a83a7d456a1b86a0ac Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 16 Jul 2018 12:30:11 +0100 Subject: locking/atomics: Rework ordering barriers Currently architectures can override __atomic_op_*() to define the barriers used before/after a relaxed atomic when used to build acquire/release/fence variants. This has the unfortunate property of requiring the architecture to define the full wrapper for the atomics, rather than just the barriers they care about, and gets in the way of generating atomics which can be easily read. Instead, this patch has architectures define an optional set of barriers: * __atomic_acquire_fence() * __atomic_release_fence() * __atomic_pre_full_fence() * __atomic_post_full_fence() ... which uses to build the wrappers. It would be nice if we could undef these, along with the __atomic_op_*() wrappers, but that would break the cmpxchg() wrappers, which are written in preprocessor. Undefs would have been nice, but alas. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Acked-by: Peter Zijlstra (Intel) Acked-by: Will Deacon Cc: Andrea Parri Cc: Boqun Feng Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: andy.shevchenko@gmail.com Cc: arnd@arndb.de Cc: aryabinin@virtuozzo.com Cc: catalin.marinas@arm.com Cc: dvyukov@google.com Cc: glider@google.com Cc: linux-arm-kernel@lists.infradead.org Cc: peter@hurleysoftware.com Link: http://lkml.kernel.org/r/20180716113017.3909-7-mark.rutland@arm.com Signed-off-by: Ingo Molnar --- arch/alpha/include/asm/atomic.h | 8 ++++---- arch/powerpc/include/asm/atomic.h | 17 +++++------------ arch/riscv/include/asm/atomic.h | 17 +++++------------ include/linux/atomic.h | 38 ++++++++++++++++++++++---------------- 4 files changed, 36 insertions(+), 44 deletions(-) (limited to 'include') diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h index 4a6a8f58c9c9..150a1c5d6a2c 100644 --- a/arch/alpha/include/asm/atomic.h +++ b/arch/alpha/include/asm/atomic.h @@ -18,11 +18,11 @@ * To ensure dependency ordering is preserved for the _relaxed and * _release atomics, an smp_read_barrier_depends() is unconditionally * inserted into the _relaxed variants, which are used to build the - * barriered versions. To avoid redundant back-to-back fences, we can - * define the _acquire and _fence versions explicitly. + * barriered versions. Avoid redundant back-to-back fences in the + * _acquire and _fence versions. */ -#define __atomic_op_acquire(op, args...) op##_relaxed(args) -#define __atomic_op_fence __atomic_op_release +#define __atomic_acquire_fence() +#define __atomic_post_full_fence() #define ATOMIC_INIT(i) { (i) } #define ATOMIC64_INIT(i) { (i) } diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h index a0156cb43d1f..963abf8bf1c0 100644 --- a/arch/powerpc/include/asm/atomic.h +++ b/arch/powerpc/include/asm/atomic.h @@ -18,18 +18,11 @@ * a "bne-" instruction at the end, so an isync is enough as a acquire barrier * on the platform without lwsync. */ -#define __atomic_op_acquire(op, args...) \ -({ \ - typeof(op##_relaxed(args)) __ret = op##_relaxed(args); \ - __asm__ __volatile__(PPC_ACQUIRE_BARRIER "" : : : "memory"); \ - __ret; \ -}) - -#define __atomic_op_release(op, args...) \ -({ \ - __asm__ __volatile__(PPC_RELEASE_BARRIER "" : : : "memory"); \ - op##_relaxed(args); \ -}) +#define __atomic_acquire_fence() \ + __asm__ __volatile__(PPC_ACQUIRE_BARRIER "" : : : "memory") + +#define __atomic_release_fence() \ + __asm__ __volatile__(PPC_RELEASE_BARRIER "" : : : "memory") static __inline__ int atomic_read(const atomic_t *v) { diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h index 512b89485790..c452359c9cb8 100644 --- a/arch/riscv/include/asm/atomic.h +++ b/arch/riscv/include/asm/atomic.h @@ -25,18 +25,11 @@ #define ATOMIC_INIT(i) { (i) } -#define __atomic_op_acquire(op, args...) \ -({ \ - typeof(op##_relaxed(args)) __ret = op##_relaxed(args); \ - __asm__ __volatile__(RISCV_ACQUIRE_BARRIER "" ::: "memory"); \ - __ret; \ -}) - -#define __atomic_op_release(op, args...) \ -({ \ - __asm__ __volatile__(RISCV_RELEASE_BARRIER "" ::: "memory"); \ - op##_relaxed(args); \ -}) +#define __atomic_acquire_fence() \ + __asm__ __volatile__(RISCV_ACQUIRE_BARRIER "" ::: "memory") + +#define __atomic_release_fence() \ + __asm__ __volatile__(RISCV_RELEASE_BARRIER "" ::: "memory"); static __always_inline int atomic_read(const atomic_t *v) { diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 8e04f1f69bd9..1e8e88bdaf09 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -38,40 +38,46 @@ * barriers on top of the relaxed variant. In the case where the relaxed * variant is already fully ordered, no additional barriers are needed. * - * Besides, if an arch has a special barrier for acquire/release, it could - * implement its own __atomic_op_* and use the same framework for building - * variants - * - * If an architecture overrides __atomic_op_acquire() it will probably want - * to define smp_mb__after_spinlock(). + * If an architecture overrides __atomic_acquire_fence() it will probably + * want to define smp_mb__after_spinlock(). */ -#ifndef __atomic_op_acquire +#ifndef __atomic_acquire_fence +#define __atomic_acquire_fence smp_mb__after_atomic +#endif + +#ifndef __atomic_release_fence +#define __atomic_release_fence smp_mb__before_atomic +#endif + +#ifndef __atomic_pre_full_fence +#define __atomic_pre_full_fence smp_mb__before_atomic +#endif + +#ifndef __atomic_post_full_fence +#define __atomic_post_full_fence smp_mb__after_atomic +#endif + #define __atomic_op_acquire(op, args...) \ ({ \ typeof(op##_relaxed(args)) __ret = op##_relaxed(args); \ - smp_mb__after_atomic(); \ + __atomic_acquire_fence(); \ __ret; \ }) -#endif -#ifndef __atomic_op_release #define __atomic_op_release(op, args...) \ ({ \ - smp_mb__before_atomic(); \ + __atomic_release_fence(); \ op##_relaxed(args); \ }) -#endif -#ifndef __atomic_op_fence #define __atomic_op_fence(op, args...) \ ({ \ typeof(op##_relaxed(args)) __ret; \ - smp_mb__before_atomic(); \ + __atomic_pre_full_fence(); \ __ret = op##_relaxed(args); \ - smp_mb__after_atomic(); \ + __atomic_post_full_fence(); \ __ret; \ }) -#endif /* atomic_add_return_relaxed */ #ifndef atomic_add_return_relaxed -- cgit v1.2.3 From f48a534adbd321362c3199140008c9e2f2a81b3a Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Thu, 28 Jun 2018 07:43:26 -0400 Subject: media: uapi/linux/cec.h: add 5V events Add two new events to signal when the 5V line goes high or low. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/cec.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/cec.h b/include/uapi/linux/cec.h index 20fe091b7e96..097fcd812471 100644 --- a/include/uapi/linux/cec.h +++ b/include/uapi/linux/cec.h @@ -384,6 +384,8 @@ struct cec_log_addrs { #define CEC_EVENT_PIN_CEC_HIGH 4 #define CEC_EVENT_PIN_HPD_LOW 5 #define CEC_EVENT_PIN_HPD_HIGH 6 +#define CEC_EVENT_PIN_5V_LOW 7 +#define CEC_EVENT_PIN_5V_HIGH 8 #define CEC_EVENT_FL_INITIAL_STATE (1 << 0) #define CEC_EVENT_FL_DROPPED_EVENTS (1 << 1) -- cgit v1.2.3 From 4786b0d6f3ca6da8db02b0a58cd2b785cb0b80ab Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Thu, 28 Jun 2018 07:43:46 -0400 Subject: media: cec: add support for 5V signal testing Add support for the new 5V CEC events Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/media/cec/cec-adap.c | 18 +++++++++++++++++- drivers/media/cec/cec-api.c | 8 ++++++++ include/media/cec-pin.h | 4 ++++ include/media/cec.h | 12 +++++++++++- 4 files changed, 40 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/media/cec/cec-adap.c b/drivers/media/cec/cec-adap.c index b7fad0ec5710..030b2602faf0 100644 --- a/drivers/media/cec/cec-adap.c +++ b/drivers/media/cec/cec-adap.c @@ -74,7 +74,7 @@ void cec_queue_event_fh(struct cec_fh *fh, const struct cec_event *new_ev, u64 ts) { static const u16 max_events[CEC_NUM_EVENTS] = { - 1, 1, 800, 800, 8, 8, + 1, 1, 800, 800, 8, 8, 8, 8 }; struct cec_event_entry *entry; unsigned int ev_idx = new_ev->event - 1; @@ -176,6 +176,22 @@ void cec_queue_pin_hpd_event(struct cec_adapter *adap, bool is_high, ktime_t ts) } EXPORT_SYMBOL_GPL(cec_queue_pin_hpd_event); +/* Notify userspace that the 5V pin changed state at the given time. */ +void cec_queue_pin_5v_event(struct cec_adapter *adap, bool is_high, ktime_t ts) +{ + struct cec_event ev = { + .event = is_high ? CEC_EVENT_PIN_5V_HIGH : + CEC_EVENT_PIN_5V_LOW, + }; + struct cec_fh *fh; + + mutex_lock(&adap->devnode.lock); + list_for_each_entry(fh, &adap->devnode.fhs, list) + cec_queue_event_fh(fh, &ev, ktime_to_ns(ts)); + mutex_unlock(&adap->devnode.lock); +} +EXPORT_SYMBOL_GPL(cec_queue_pin_5v_event); + /* * Queue a new message for this filehandle. * diff --git a/drivers/media/cec/cec-api.c b/drivers/media/cec/cec-api.c index 10b67fc40318..b6536bbad530 100644 --- a/drivers/media/cec/cec-api.c +++ b/drivers/media/cec/cec-api.c @@ -579,6 +579,14 @@ static int cec_open(struct inode *inode, struct file *filp) cec_queue_event_fh(fh, &ev, 0); } } + if (adap->pin && adap->pin->ops->read_5v) { + err = adap->pin->ops->read_5v(adap); + if (err >= 0) { + ev.event = err ? CEC_EVENT_PIN_5V_HIGH : + CEC_EVENT_PIN_5V_LOW; + cec_queue_event_fh(fh, &ev, 0); + } + } #endif list_add(&fh->list, &devnode->fhs); diff --git a/include/media/cec-pin.h b/include/media/cec-pin.h index ed16c6dde0ba..604e79cb6cbf 100644 --- a/include/media/cec-pin.h +++ b/include/media/cec-pin.h @@ -25,6 +25,9 @@ * @read_hpd: read the HPD pin. Return true if high, false if low or * an error if negative. If NULL or -ENOTTY is returned, * then this is not supported. + * @read_5v: read the 5V pin. Return true if high, false if low or + * an error if negative. If NULL or -ENOTTY is returned, + * then this is not supported. * * These operations are used by the cec pin framework to manipulate * the CEC pin. @@ -38,6 +41,7 @@ struct cec_pin_ops { void (*free)(struct cec_adapter *adap); void (*status)(struct cec_adapter *adap, struct seq_file *file); int (*read_hpd)(struct cec_adapter *adap); + int (*read_5v)(struct cec_adapter *adap); }; /** diff --git a/include/media/cec.h b/include/media/cec.h index 580ab1042898..ff9847f7f99d 100644 --- a/include/media/cec.h +++ b/include/media/cec.h @@ -79,7 +79,7 @@ struct cec_event_entry { }; #define CEC_NUM_CORE_EVENTS 2 -#define CEC_NUM_EVENTS CEC_EVENT_PIN_HPD_HIGH +#define CEC_NUM_EVENTS CEC_EVENT_PIN_5V_HIGH struct cec_fh { struct list_head list; @@ -308,6 +308,16 @@ void cec_queue_pin_cec_event(struct cec_adapter *adap, bool is_high, */ void cec_queue_pin_hpd_event(struct cec_adapter *adap, bool is_high, ktime_t ts); +/** + * cec_queue_pin_5v_event() - queue a pin event with a given timestamp. + * + * @adap: pointer to the cec adapter + * @is_high: when true the 5V pin is high, otherwise it is low + * @ts: the timestamp for this event + * + */ +void cec_queue_pin_5v_event(struct cec_adapter *adap, bool is_high, ktime_t ts); + /** * cec_get_edid_phys_addr() - find and return the physical address * -- cgit v1.2.3 From d27fb99f62af7b79c542d161aa5155ed57271ddc Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Mon, 23 Jul 2018 22:42:48 +0100 Subject: dma-mapping: relax warning for per-device areas The reasons why dma_free_attrs() should not be called from IRQ context are not necessarily obvious and somewhat buried in the development history, so let's start by documenting the warning itself to help anyone who does happen to hit it and wonder what the deal is. However, this check turns out to be slightly over-restrictive for the way that per-device memory has been spliced into the general API, since for that case we know that dma_declare_coherent_memory() has created an appropriate CPU mapping for the entire area and nothing dynamic should be happening. Given that the usage model for per-device memory is often more akin to streaming DMA than 'real' coherent DMA (e.g. allocating and freeing space to copy short-lived packets in and out), it is also somewhat more reasonable for those operations to happen in IRQ handlers for such devices. Therefore, let's move the irqs_disabled() check down past the per-device area hook, so that that gets a chance to resolve the request before we reach definite "you're doing it wrong" territory. Reported-by: Fredrik Noring Tested-by: Fredrik Noring Signed-off-by: Robin Murphy Signed-off-by: Christoph Hellwig --- include/linux/dma-mapping.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index f9cc309507d9..1db6a6b46d0d 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -538,10 +538,17 @@ static inline void dma_free_attrs(struct device *dev, size_t size, const struct dma_map_ops *ops = get_dma_ops(dev); BUG_ON(!ops); - WARN_ON(irqs_disabled()); if (dma_release_from_dev_coherent(dev, get_order(size), cpu_addr)) return; + /* + * On non-coherent platforms which implement DMA-coherent buffers via + * non-cacheable remaps, ops->free() may call vunmap(). Thus getting + * this far in IRQ context is a) at risk of a BUG_ON() or trying to + * sleep on some machines, and b) an indication that the driver is + * probably misusing the coherent API anyway. + */ + WARN_ON(irqs_disabled()); if (!ops->free || !cpu_addr) return; -- cgit v1.2.3 From 30b914c8d825da7d4c651ade34667cef05e3ee27 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Tue, 27 Feb 2018 07:24:09 -0500 Subject: media: add 'index' to struct media_v2_pad The v2 pad structure never exposed the pad index, which made it impossible to call the MEDIA_IOC_SETUP_LINK ioctl, which needs that information. It is really trivial to just expose this information, so implement this. Signed-off-by: Hans Verkuil Acked-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- drivers/media/media-device.c | 1 + include/uapi/linux/media.h | 12 +++++++++++- 2 files changed, 12 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/media/media-device.c b/drivers/media/media-device.c index 47bb2254fbfd..047d38372a27 100644 --- a/drivers/media/media-device.c +++ b/drivers/media/media-device.c @@ -331,6 +331,7 @@ static long media_device_get_topology(struct media_device *mdev, void *arg) kpad.id = pad->graph_obj.id; kpad.entity_id = pad->entity->graph_obj.id; kpad.flags = pad->flags; + kpad.index = pad->index; if (copy_to_user(upad, &kpad, sizeof(kpad))) ret = -EFAULT; diff --git a/include/uapi/linux/media.h b/include/uapi/linux/media.h index 86c7dcc9cba3..f6338bd57929 100644 --- a/include/uapi/linux/media.h +++ b/include/uapi/linux/media.h @@ -305,11 +305,21 @@ struct media_v2_interface { }; } __attribute__ ((packed)); +/* + * Appeared in 4.19.0. + * + * The media_version argument comes from the media_version field in + * struct media_device_info. + */ +#define MEDIA_V2_PAD_HAS_INDEX(media_version) \ + ((media_version) >= ((4 << 16) | (19 << 8) | 0)) + struct media_v2_pad { __u32 id; __u32 entity_id; __u32 flags; - __u32 reserved[5]; + __u32 index; + __u32 reserved[4]; } __attribute__ ((packed)); struct media_v2_link { -- cgit v1.2.3 From 588f4ee7e6fc5c9a0fb07c7051cdd341949e0feb Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Wed, 28 Feb 2018 05:41:11 -0500 Subject: media: add flags field to struct media_v2_entity The v2 entity structure never exposed the entity flags, which made it impossible to detect connector or default entities. It is really trivial to just expose this information, so implement this. Signed-off-by: Hans Verkuil Acked-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- drivers/media/media-device.c | 1 + include/uapi/linux/media.h | 12 +++++++++++- 2 files changed, 12 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/media/media-device.c b/drivers/media/media-device.c index 047d38372a27..14959b19a342 100644 --- a/drivers/media/media-device.c +++ b/drivers/media/media-device.c @@ -266,6 +266,7 @@ static long media_device_get_topology(struct media_device *mdev, void *arg) memset(&kentity, 0, sizeof(kentity)); kentity.id = entity->graph_obj.id; kentity.function = entity->function; + kentity.flags = entity->flags; strlcpy(kentity.name, entity->name, sizeof(kentity.name)); diff --git a/include/uapi/linux/media.h b/include/uapi/linux/media.h index f6338bd57929..ebd2cda67833 100644 --- a/include/uapi/linux/media.h +++ b/include/uapi/linux/media.h @@ -280,11 +280,21 @@ struct media_links_enum { * MC next gen API definitions */ +/* + * Appeared in 4.19.0. + * + * The media_version argument comes from the media_version field in + * struct media_device_info. + */ +#define MEDIA_V2_ENTITY_HAS_FLAGS(media_version) \ + ((media_version) >= ((4 << 16) | (19 << 8) | 0)) + struct media_v2_entity { __u32 id; char name[64]; __u32 function; /* Main function of the entity */ - __u32 reserved[6]; + __u32 flags; + __u32 reserved[5]; } __attribute__ ((packed)); /* Should match the specific fields at media_intf_devnode */ -- cgit v1.2.3 From d272bc92c4a4fcec4102c011eaa85630bd2d8d38 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Thu, 28 Jun 2018 08:56:02 -0400 Subject: media: rename MEDIA_ENT_F_DTV_DECODER to MEDIA_ENT_F_DV_DECODER The use of 'DTV' is very confusing since it normally refers to Digital TV e.g. DVB etc. Instead use 'DV' (Digital Video), which nicely corresponds to the DV Timings API used to configure such receivers and transmitters. We keep an alias to avoid breaking userspace applications. Since this alias is only available if __KERNEL__ is *not* defined (i.e. it is only available for userspace, not kernelspace), any drivers that use it also have to be converted to the new define. These drivers are adv7604, adv7842 and tda1997x. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- Documentation/media/uapi/mediactl/media-types.rst | 2 +- drivers/media/i2c/adv7604.c | 1 + drivers/media/i2c/adv7842.c | 1 + drivers/media/i2c/tda1997x.c | 2 +- include/uapi/linux/media.h | 4 +++- 5 files changed, 7 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/Documentation/media/uapi/mediactl/media-types.rst b/Documentation/media/uapi/mediactl/media-types.rst index 96910cf2eaaa..c11b0c7e890b 100644 --- a/Documentation/media/uapi/mediactl/media-types.rst +++ b/Documentation/media/uapi/mediactl/media-types.rst @@ -200,7 +200,7 @@ Types and flags used to represent the media graph elements MIPI CSI-2, etc.), and outputs them on its source pad to an output video bus of another type (eDP, MIPI CSI-2, parallel, etc.). - * - ``MEDIA_ENT_F_DTV_DECODER`` + * - ``MEDIA_ENT_F_DV_DECODER`` - Digital video decoder. The basic function of the video decoder is to accept digital video from a wide variety of sources and output it in some digital video standard, with appropriate diff --git a/drivers/media/i2c/adv7604.c b/drivers/media/i2c/adv7604.c index 1a3b2c04d9f9..668be2bca57a 100644 --- a/drivers/media/i2c/adv7604.c +++ b/drivers/media/i2c/adv7604.c @@ -3499,6 +3499,7 @@ static int adv76xx_probe(struct i2c_client *client, for (i = 0; i < state->source_pad; ++i) state->pads[i].flags = MEDIA_PAD_FL_SINK; state->pads[state->source_pad].flags = MEDIA_PAD_FL_SOURCE; + sd->entity.function = MEDIA_ENT_F_DV_DECODER; err = media_entity_pads_init(&sd->entity, state->source_pad + 1, state->pads); diff --git a/drivers/media/i2c/adv7842.c b/drivers/media/i2c/adv7842.c index fddac32e5051..99d781343fb1 100644 --- a/drivers/media/i2c/adv7842.c +++ b/drivers/media/i2c/adv7842.c @@ -3541,6 +3541,7 @@ static int adv7842_probe(struct i2c_client *client, INIT_DELAYED_WORK(&state->delayed_work_enable_hotplug, adv7842_delayed_work_enable_hotplug); + sd->entity.function = MEDIA_ENT_F_DV_DECODER; state->pad.flags = MEDIA_PAD_FL_SOURCE; err = media_entity_pads_init(&sd->entity, 1, &state->pad); if (err) diff --git a/drivers/media/i2c/tda1997x.c b/drivers/media/i2c/tda1997x.c index 039a92c3294a..d114ac5243ec 100644 --- a/drivers/media/i2c/tda1997x.c +++ b/drivers/media/i2c/tda1997x.c @@ -2570,7 +2570,7 @@ static int tda1997x_probe(struct i2c_client *client, id->name, i2c_adapter_id(client->adapter), client->addr); sd->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE | V4L2_SUBDEV_FL_HAS_EVENTS; - sd->entity.function = MEDIA_ENT_F_DTV_DECODER; + sd->entity.function = MEDIA_ENT_F_DV_DECODER; sd->entity.ops = &tda1997x_media_ops; /* set allowed mbus modes based on chip, bus-type, and bus-width */ diff --git a/include/uapi/linux/media.h b/include/uapi/linux/media.h index ebd2cda67833..99f5e0978ebb 100644 --- a/include/uapi/linux/media.h +++ b/include/uapi/linux/media.h @@ -93,7 +93,7 @@ struct media_device_info { * Video decoder functions */ #define MEDIA_ENT_F_ATV_DECODER (MEDIA_ENT_F_OLD_SUBDEV_BASE + 4) -#define MEDIA_ENT_F_DTV_DECODER (MEDIA_ENT_F_BASE + 0x6001) +#define MEDIA_ENT_F_DV_DECODER (MEDIA_ENT_F_BASE + 0x6001) /* * Digital TV, analog TV, radio and/or software defined radio tuner functions. @@ -400,6 +400,8 @@ struct media_v2_topology { #define MEDIA_ENT_T_V4L2_SUBDEV_DECODER MEDIA_ENT_F_ATV_DECODER #define MEDIA_ENT_T_V4L2_SUBDEV_TUNER MEDIA_ENT_F_TUNER +#define MEDIA_ENT_F_DTV_DECODER MEDIA_ENT_F_DV_DECODER + /* * There is still no ALSA support in the media controller. These * defines should not have been added and we leave them here only -- cgit v1.2.3 From 7c8362c4b9eb7e4e9cbebc71ab529dc455c21b6b Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Mon, 18 Jun 2018 05:07:43 -0400 Subject: media: media.h: add MEDIA_ENT_F_DV_ENCODER Add a new function for digital video encoders such as HDMI transmitters. Signed-off-by: Hans Verkuil Acked-by: Sakari Ailus Reviewed-by: Laurent Pinchart Signed-off-by: Mauro Carvalho Chehab --- Documentation/media/uapi/mediactl/media-types.rst | 7 +++++++ include/uapi/linux/media.h | 3 ++- 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/Documentation/media/uapi/mediactl/media-types.rst b/Documentation/media/uapi/mediactl/media-types.rst index c11b0c7e890b..e90d4d0a7f8b 100644 --- a/Documentation/media/uapi/mediactl/media-types.rst +++ b/Documentation/media/uapi/mediactl/media-types.rst @@ -206,6 +206,13 @@ Types and flags used to represent the media graph elements and output it in some digital video standard, with appropriate timing signals. + * - ``MEDIA_ENT_F_DV_ENCODER`` + - Digital video encoder. The basic function of the video encoder is + to accept digital video from some digital video standard with + appropriate timing signals (usually a parallel video bus with sync + signals) and output this to a digital video output connector such + as HDMI or DisplayPort. + .. tabularcolumns:: |p{5.5cm}|p{12.0cm}| .. _media-entity-flag: diff --git a/include/uapi/linux/media.h b/include/uapi/linux/media.h index 99f5e0978ebb..6f594fa238c2 100644 --- a/include/uapi/linux/media.h +++ b/include/uapi/linux/media.h @@ -90,10 +90,11 @@ struct media_device_info { #define MEDIA_ENT_F_LENS (MEDIA_ENT_F_OLD_SUBDEV_BASE + 3) /* - * Video decoder functions + * Video decoder/encoder functions */ #define MEDIA_ENT_F_ATV_DECODER (MEDIA_ENT_F_OLD_SUBDEV_BASE + 4) #define MEDIA_ENT_F_DV_DECODER (MEDIA_ENT_F_BASE + 0x6001) +#define MEDIA_ENT_F_DV_ENCODER (MEDIA_ENT_F_BASE + 0x6002) /* * Digital TV, analog TV, radio and/or software defined radio tuner functions. -- cgit v1.2.3 From f2399f7522ac2a255f6502537609a51974be84be Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Thu, 28 Jun 2018 09:03:42 -0400 Subject: media: media.h: reorder video en/decoder functions Keep the function defines in numerical order: 0x6000 comes after 0x2000, so move it back. Signed-off-by: Hans Verkuil Reviewed-by: Laurent Pinchart Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/media.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/media.h b/include/uapi/linux/media.h index 6f594fa238c2..76d9bd64c116 100644 --- a/include/uapi/linux/media.h +++ b/include/uapi/linux/media.h @@ -89,13 +89,6 @@ struct media_device_info { #define MEDIA_ENT_F_FLASH (MEDIA_ENT_F_OLD_SUBDEV_BASE + 2) #define MEDIA_ENT_F_LENS (MEDIA_ENT_F_OLD_SUBDEV_BASE + 3) -/* - * Video decoder/encoder functions - */ -#define MEDIA_ENT_F_ATV_DECODER (MEDIA_ENT_F_OLD_SUBDEV_BASE + 4) -#define MEDIA_ENT_F_DV_DECODER (MEDIA_ENT_F_BASE + 0x6001) -#define MEDIA_ENT_F_DV_ENCODER (MEDIA_ENT_F_BASE + 0x6002) - /* * Digital TV, analog TV, radio and/or software defined radio tuner functions. * @@ -140,6 +133,13 @@ struct media_device_info { #define MEDIA_ENT_F_VID_MUX (MEDIA_ENT_F_BASE + 0x5001) #define MEDIA_ENT_F_VID_IF_BRIDGE (MEDIA_ENT_F_BASE + 0x5002) +/* + * Video decoder/encoder functions + */ +#define MEDIA_ENT_F_ATV_DECODER (MEDIA_ENT_F_OLD_SUBDEV_BASE + 4) +#define MEDIA_ENT_F_DV_DECODER (MEDIA_ENT_F_BASE + 0x6001) +#define MEDIA_ENT_F_DV_ENCODER (MEDIA_ENT_F_BASE + 0x6002) + /* Entity flags */ #define MEDIA_ENT_FL_DEFAULT (1 << 0) #define MEDIA_ENT_FL_CONNECTOR (1 << 1) -- cgit v1.2.3 From ea107a183be1d6e69448d7100121c479e24b7c1d Mon Sep 17 00:00:00 2001 From: vkorjani Date: Tue, 10 Apr 2018 10:12:45 -0400 Subject: drm: Add support for pps and compression mode command packet After enabling DSC we need to send compression mode command packet and pps data packet, for which 2 new data types are added 07h Compression Mode Data Type Write , short write, 2 parameters 0Ah PPS Long Write (word count determines number of bytes) This patch adds support to send these packets. Cc: David Airlie Cc: Jean-Christophe Plagniol-Villard Cc: Tomi Valkeinen Cc: dri-devel@lists.freedesktop.org Cc: linux-kernel@vger.kernel.org Cc: linux-fbdev@vger.kernel.org Changes in v3: - None Signed-off-by: vkorjani [seanpaul removed pps_write_buffer fn, added types to packet_format helpers] Signed-off-by: Sean Paul Signed-off-by: Rob Clark --- drivers/gpu/drm/drm_mipi_dsi.c | 2 ++ include/video/mipi_display.h | 3 +++ 2 files changed, 5 insertions(+) (limited to 'include') diff --git a/drivers/gpu/drm/drm_mipi_dsi.c b/drivers/gpu/drm/drm_mipi_dsi.c index bc73b7f5b9fc..80b75501f5c6 100644 --- a/drivers/gpu/drm/drm_mipi_dsi.c +++ b/drivers/gpu/drm/drm_mipi_dsi.c @@ -392,6 +392,7 @@ bool mipi_dsi_packet_format_is_short(u8 type) case MIPI_DSI_DCS_SHORT_WRITE: case MIPI_DSI_DCS_SHORT_WRITE_PARAM: case MIPI_DSI_DCS_READ: + case MIPI_DSI_DCS_COMPRESSION_MODE: case MIPI_DSI_SET_MAXIMUM_RETURN_PACKET_SIZE: return true; } @@ -410,6 +411,7 @@ EXPORT_SYMBOL(mipi_dsi_packet_format_is_short); bool mipi_dsi_packet_format_is_long(u8 type) { switch (type) { + case MIPI_DSI_PPS_LONG_WRITE: case MIPI_DSI_NULL_PACKET: case MIPI_DSI_BLANKING_PACKET: case MIPI_DSI_GENERIC_LONG_WRITE: diff --git a/include/video/mipi_display.h b/include/video/mipi_display.h index 19aa65a35546..49a53ef8da96 100644 --- a/include/video/mipi_display.h +++ b/include/video/mipi_display.h @@ -38,6 +38,9 @@ enum { MIPI_DSI_DCS_READ = 0x06, + MIPI_DSI_DCS_COMPRESSION_MODE = 0x07, + MIPI_DSI_PPS_LONG_WRITE = 0x0A, + MIPI_DSI_SET_MAXIMUM_RETURN_PACKET_SIZE = 0x37, MIPI_DSI_END_OF_TRANSMISSION = 0x08, -- cgit v1.2.3 From 45841a977391f24b9bf713548c588d148a576d22 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Wed, 4 Jul 2018 10:13:47 -0400 Subject: media: media.h: add encoder/decoder functions for codecs Add MEDIA_ENT_F_PROC_VIDEO_EN/DECODER to be used for the encoder and decoder entities of codec hardware. [mchehab+samsung@kernel.org: split description on two senteces by adding dots] Signed-off-by: Hans Verkuil Acked-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- Documentation/media/uapi/mediactl/media-types.rst | 11 +++++++++++ include/uapi/linux/media.h | 2 ++ 2 files changed, 13 insertions(+) (limited to 'include') diff --git a/Documentation/media/uapi/mediactl/media-types.rst b/Documentation/media/uapi/mediactl/media-types.rst index e90d4d0a7f8b..7b17acc049cf 100644 --- a/Documentation/media/uapi/mediactl/media-types.rst +++ b/Documentation/media/uapi/mediactl/media-types.rst @@ -37,6 +37,8 @@ Types and flags used to represent the media graph elements .. _MEDIA-ENT-F-PROC-VIDEO-LUT: .. _MEDIA-ENT-F-PROC-VIDEO-SCALER: .. _MEDIA-ENT-F-PROC-VIDEO-STATISTICS: +.. _MEDIA-ENT-F-PROC-VIDEO-ENCODER: +.. _MEDIA-ENT-F-PROC-VIDEO-DECODER: .. _MEDIA-ENT-F-VID-MUX: .. _MEDIA-ENT-F-VID-IF-BRIDGE: .. _MEDIA-ENT-F-DTV-DECODER: @@ -188,6 +190,15 @@ Types and flags used to represent the media graph elements received on its sink pad and outputs the statistics data on its source pad. + * - ``MEDIA_ENT_F_PROC_VIDEO_ENCODER`` + - Video (MPEG, HEVC, VPx, etc.) encoder. An entity capable of + compressing video frames. Must have one sink pad and one source pad. + + * - ``MEDIA_ENT_F_PROC_VIDEO_DECODER`` + - Video (MPEG, HEVC, VPx, etc.) decoder. An entity capable of + decompressing a compressed video stream into uncompressed video + frames. Must have one sink pad and one source pad. + * - ``MEDIA_ENT_F_VID_MUX`` - Video multiplexer. An entity capable of multiplexing must have at least two sink pads and one source pad, and must pass the video diff --git a/include/uapi/linux/media.h b/include/uapi/linux/media.h index 76d9bd64c116..82ec9f132a53 100644 --- a/include/uapi/linux/media.h +++ b/include/uapi/linux/media.h @@ -126,6 +126,8 @@ struct media_device_info { #define MEDIA_ENT_F_PROC_VIDEO_LUT (MEDIA_ENT_F_BASE + 0x4004) #define MEDIA_ENT_F_PROC_VIDEO_SCALER (MEDIA_ENT_F_BASE + 0x4005) #define MEDIA_ENT_F_PROC_VIDEO_STATISTICS (MEDIA_ENT_F_BASE + 0x4006) +#define MEDIA_ENT_F_PROC_VIDEO_ENCODER (MEDIA_ENT_F_BASE + 0x4007) +#define MEDIA_ENT_F_PROC_VIDEO_DECODER (MEDIA_ENT_F_BASE + 0x4008) /* * Switch and bridge entity functions -- cgit v1.2.3 From 62c3fce04154777e6a3ce3a27f123b645d36dcff Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Wed, 4 Jul 2018 10:13:47 -0400 Subject: media: videodev.h: add PIX_FMT_FWHT for use with vicodec Add a new pixelformat for the vicodec software codec using the Fast Walsh Hadamard Transform. Signed-off-by: Hans Verkuil Acked-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- Documentation/media/uapi/v4l/pixfmt-compressed.rst | 7 +++++++ drivers/media/v4l2-core/v4l2-ioctl.c | 1 + include/uapi/linux/videodev2.h | 1 + 3 files changed, 9 insertions(+) (limited to 'include') diff --git a/Documentation/media/uapi/v4l/pixfmt-compressed.rst b/Documentation/media/uapi/v4l/pixfmt-compressed.rst index abec03937bb3..d382e7a5c38e 100644 --- a/Documentation/media/uapi/v4l/pixfmt-compressed.rst +++ b/Documentation/media/uapi/v4l/pixfmt-compressed.rst @@ -95,3 +95,10 @@ Compressed Formats - ``V4L2_PIX_FMT_HEVC`` - 'HEVC' - HEVC/H.265 video elementary stream. + * .. _V4L2-PIX-FMT-FWHT: + + - ``V4L2_PIX_FMT_FWHT`` + - 'FWHT' + - Video elementary stream using a codec based on the Fast Walsh Hadamard + Transform. This codec is implemented by the vicodec ('Virtual Codec') + driver. See the vicodec-codec.h header for more details. diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 01670567641a..26d9702069fd 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1311,6 +1311,7 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_VP8: descr = "VP8"; break; case V4L2_PIX_FMT_VP9: descr = "VP9"; break; case V4L2_PIX_FMT_HEVC: descr = "HEVC"; break; /* aka H.265 */ + case V4L2_PIX_FMT_FWHT: descr = "FWHT"; break; /* used in vicodec */ case V4L2_PIX_FMT_CPIA1: descr = "GSPCA CPiA YUV"; break; case V4L2_PIX_FMT_WNVA: descr = "WNVA"; break; case V4L2_PIX_FMT_SN9C10X: descr = "GSPCA SN9C10X"; break; diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 600877be5c22..3ea8097c2470 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -636,6 +636,7 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_VP8 v4l2_fourcc('V', 'P', '8', '0') /* VP8 */ #define V4L2_PIX_FMT_VP9 v4l2_fourcc('V', 'P', '9', '0') /* VP9 */ #define V4L2_PIX_FMT_HEVC v4l2_fourcc('H', 'E', 'V', 'C') /* HEVC aka H.265 */ +#define V4L2_PIX_FMT_FWHT v4l2_fourcc('F', 'W', 'H', 'T') /* Fast Walsh Hadamard Transform (vicodec) */ /* Vendor-specific formats */ #define V4L2_PIX_FMT_CPIA1 v4l2_fourcc('C', 'P', 'I', 'A') /* cpia1 YUV */ -- cgit v1.2.3 From ee1228cca15ce097b7badebfdd0fef23a2cca9e1 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Tue, 26 Jun 2018 09:26:52 -0400 Subject: media: v4l2-mem2mem: add v4l2_m2m_last_buf() This can be used to mark the last queued source buffer as the last buffer. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/media/v4l2-core/v4l2-mem2mem.c | 18 ++++++++++++++++++ include/media/v4l2-mem2mem.h | 29 +++++++++++++++++++++++++++++ 2 files changed, 47 insertions(+) (limited to 'include') diff --git a/drivers/media/v4l2-core/v4l2-mem2mem.c b/drivers/media/v4l2-core/v4l2-mem2mem.c index 4aeedb91594a..d9565ee44578 100644 --- a/drivers/media/v4l2-core/v4l2-mem2mem.c +++ b/drivers/media/v4l2-core/v4l2-mem2mem.c @@ -129,6 +129,24 @@ void *v4l2_m2m_next_buf(struct v4l2_m2m_queue_ctx *q_ctx) } EXPORT_SYMBOL_GPL(v4l2_m2m_next_buf); +void *v4l2_m2m_last_buf(struct v4l2_m2m_queue_ctx *q_ctx) +{ + struct v4l2_m2m_buffer *b; + unsigned long flags; + + spin_lock_irqsave(&q_ctx->rdy_spinlock, flags); + + if (list_empty(&q_ctx->rdy_queue)) { + spin_unlock_irqrestore(&q_ctx->rdy_spinlock, flags); + return NULL; + } + + b = list_last_entry(&q_ctx->rdy_queue, struct v4l2_m2m_buffer, list); + spin_unlock_irqrestore(&q_ctx->rdy_spinlock, flags); + return &b->vb; +} +EXPORT_SYMBOL_GPL(v4l2_m2m_last_buf); + void *v4l2_m2m_buf_remove(struct v4l2_m2m_queue_ctx *q_ctx) { struct v4l2_m2m_buffer *b; diff --git a/include/media/v4l2-mem2mem.h b/include/media/v4l2-mem2mem.h index d60d3060f762..d655720e16a1 100644 --- a/include/media/v4l2-mem2mem.h +++ b/include/media/v4l2-mem2mem.h @@ -449,6 +449,35 @@ static inline void *v4l2_m2m_next_dst_buf(struct v4l2_m2m_ctx *m2m_ctx) return v4l2_m2m_next_buf(&m2m_ctx->cap_q_ctx); } +/** + * v4l2_m2m_last_buf() - return last buffer from the list of ready buffers + * + * @q_ctx: pointer to struct @v4l2_m2m_queue_ctx + */ +void *v4l2_m2m_last_buf(struct v4l2_m2m_queue_ctx *q_ctx); + +/** + * v4l2_m2m_last_src_buf() - return last destination buffer from the list of + * ready buffers + * + * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx + */ +static inline void *v4l2_m2m_last_src_buf(struct v4l2_m2m_ctx *m2m_ctx) +{ + return v4l2_m2m_last_buf(&m2m_ctx->out_q_ctx); +} + +/** + * v4l2_m2m_last_dst_buf() - return last destination buffer from the list of + * ready buffers + * + * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx + */ +static inline void *v4l2_m2m_last_dst_buf(struct v4l2_m2m_ctx *m2m_ctx) +{ + return v4l2_m2m_last_buf(&m2m_ctx->cap_q_ctx); +} + /** * v4l2_m2m_for_each_dst_buf() - iterate over a list of destination ready * buffers -- cgit v1.2.3 From bf7b70482704bb0785e6b65ee30a6383ab22bbc6 Mon Sep 17 00:00:00 2001 From: Baruch Siach Date: Thu, 5 Jul 2018 05:38:00 -0400 Subject: media: v4l2-ctrls.h: fix v4l2_ctrl field description typos Signed-off-by: Baruch Siach Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-ctrls.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/media/v4l2-ctrls.h b/include/media/v4l2-ctrls.h index 5b445b5654f7..f615ba1b29dd 100644 --- a/include/media/v4l2-ctrls.h +++ b/include/media/v4l2-ctrls.h @@ -181,10 +181,10 @@ typedef void (*v4l2_ctrl_notify_fnc)(struct v4l2_ctrl *ctrl, void *priv); * not freed when the control is deleted. Should this be needed * then a new internal bitfield can be added to tell the framework * to free this pointer. - * @p_cur: The control's current value represented via a union with + * @p_cur: The control's current value represented via a union which * provides a standard way of accessing control types * through a pointer. - * @p_new: The control's new value represented via a union with provides + * @p_new: The control's new value represented via a union which provides * a standard way of accessing control types * through a pointer. */ -- cgit v1.2.3 From cdc50176597cb44ce25eb7331c450058775b8d2a Mon Sep 17 00:00:00 2001 From: Nayan Deshmukh Date: Fri, 20 Jul 2018 17:51:05 +0530 Subject: drm/scheduler: modify API to avoid redundancy MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit entity has a scheduler field and we don't need the sched argument in any of the functions where entity is provided. Signed-off-by: Nayan Deshmukh Reviewed-by: Christian König Reviewed-by: Eric Anholt Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c | 13 +++++-------- drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 3 +-- drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c | 3 +-- drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 4 ++-- drivers/gpu/drm/etnaviv/etnaviv_drv.c | 3 +-- drivers/gpu/drm/etnaviv/etnaviv_sched.c | 4 ++-- drivers/gpu/drm/scheduler/gpu_scheduler.c | 20 +++++++++++--------- drivers/gpu/drm/v3d/v3d_drv.c | 4 +--- drivers/gpu/drm/v3d/v3d_gem.c | 2 -- include/drm/gpu_scheduler.h | 10 +++------- 13 files changed, 30 insertions(+), 42 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index c5d81d6a90e0..4d4575b3bba7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -1232,7 +1232,7 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p, job = p->job; p->job = NULL; - r = drm_sched_job_init(&job->base, &ring->sched, entity, p->filp); + r = drm_sched_job_init(&job->base, entity, p->filp); if (r) { amdgpu_job_free(job); amdgpu_mn_unlock(p->mn); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c index 83e3b320a793..df6965761046 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c @@ -104,8 +104,7 @@ static int amdgpu_ctx_init(struct amdgpu_device *adev, failed: for (j = 0; j < i; j++) - drm_sched_entity_destroy(&adev->rings[j]->sched, - &ctx->rings[j].entity); + drm_sched_entity_destroy(&ctx->rings[j].entity); kfree(ctx->fences); ctx->fences = NULL; return r; @@ -178,8 +177,7 @@ static void amdgpu_ctx_do_release(struct kref *ref) if (ctx->adev->rings[i] == &ctx->adev->gfx.kiq.ring) continue; - drm_sched_entity_destroy(&ctx->adev->rings[i]->sched, - &ctx->rings[i].entity); + drm_sched_entity_destroy(&ctx->rings[i].entity); } amdgpu_ctx_fini(ref); @@ -466,8 +464,8 @@ void amdgpu_ctx_mgr_entity_flush(struct amdgpu_ctx_mgr *mgr) if (ctx->adev->rings[i] == &ctx->adev->gfx.kiq.ring) continue; - max_wait = drm_sched_entity_flush(&ctx->adev->rings[i]->sched, - &ctx->rings[i].entity, max_wait); + max_wait = drm_sched_entity_flush(&ctx->rings[i].entity, + max_wait); } } mutex_unlock(&mgr->lock); @@ -492,8 +490,7 @@ void amdgpu_ctx_mgr_entity_fini(struct amdgpu_ctx_mgr *mgr) continue; if (kref_read(&ctx->refcount) == 1) - drm_sched_entity_fini(&ctx->adev->rings[i]->sched, - &ctx->rings[i].entity); + drm_sched_entity_fini(&ctx->rings[i].entity); else DRM_ERROR("ctx %p is still alive\n", ctx); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index 5a2c26a85984..631481a730e0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -133,7 +133,7 @@ int amdgpu_job_submit(struct amdgpu_job *job, struct drm_sched_entity *entity, if (!f) return -EINVAL; - r = drm_sched_job_init(&job->base, entity->sched, entity, owner); + r = drm_sched_job_init(&job->base, entity, owner); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 6039f8e21358..8c4358e36c87 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -1925,8 +1925,7 @@ void amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, bool enable) return; } } else { - drm_sched_entity_destroy(adev->mman.entity.sched, - &adev->mman.entity); + drm_sched_entity_destroy(&adev->mman.entity); dma_fence_put(man->move); man->move = NULL; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c index e1e4810b9d9e..fca86d71fafc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c @@ -305,8 +305,7 @@ int amdgpu_uvd_sw_fini(struct amdgpu_device *adev) { int i, j; - drm_sched_entity_destroy(&adev->uvd.inst->ring.sched, - &adev->uvd.entity); + drm_sched_entity_destroy(&adev->uvd.entity); for (j = 0; j < adev->uvd.num_uvd_inst; ++j) { kfree(adev->uvd.inst[j].saved_bo); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c index 86182c966ed6..b6ab4f5350c8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c @@ -221,7 +221,7 @@ int amdgpu_vce_sw_fini(struct amdgpu_device *adev) if (adev->vce.vcpu_bo == NULL) return 0; - drm_sched_entity_destroy(&adev->vce.ring[0].sched, &adev->vce.entity); + drm_sched_entity_destroy(&adev->vce.entity); amdgpu_bo_free_kernel(&adev->vce.vcpu_bo, &adev->vce.gpu_addr, (void **)&adev->vce.cpu_addr); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 098dd1ba751a..74b4a28a41d6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -2642,7 +2642,7 @@ error_free_root: vm->root.base.bo = NULL; error_free_sched_entity: - drm_sched_entity_destroy(&ring->sched, &vm->entity); + drm_sched_entity_destroy(&vm->entity); return r; } @@ -2779,7 +2779,7 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm) spin_unlock_irqrestore(&adev->vm_manager.pasid_lock, flags); } - drm_sched_entity_destroy(vm->entity.sched, &vm->entity); + drm_sched_entity_destroy(&vm->entity); if (!RB_EMPTY_ROOT(&vm->va.rb_root)) { dev_err(adev->dev, "still active bo inside vm\n"); diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.c b/drivers/gpu/drm/etnaviv/etnaviv_drv.c index 36414ba56b22..207532c05eb8 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_drv.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.c @@ -78,8 +78,7 @@ static void etnaviv_postclose(struct drm_device *dev, struct drm_file *file) gpu->lastctx = NULL; mutex_unlock(&gpu->lock); - drm_sched_entity_destroy(&gpu->sched, - &ctx->sched_entity[i]); + drm_sched_entity_destroy(&ctx->sched_entity[i]); } } diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c index a74eb57af15b..590e44b0d963 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c @@ -118,8 +118,8 @@ int etnaviv_sched_push_job(struct drm_sched_entity *sched_entity, { int ret; - ret = drm_sched_job_init(&submit->sched_job, &submit->gpu->sched, - sched_entity, submit->cmdbuf.ctx); + ret = drm_sched_job_init(&submit->sched_job, sched_entity, + submit->cmdbuf.ctx); if (ret) return ret; diff --git a/drivers/gpu/drm/scheduler/gpu_scheduler.c b/drivers/gpu/drm/scheduler/gpu_scheduler.c index dac71e3b4514..a3b55c542025 100644 --- a/drivers/gpu/drm/scheduler/gpu_scheduler.c +++ b/drivers/gpu/drm/scheduler/gpu_scheduler.c @@ -273,11 +273,12 @@ static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f, * * Returns the remaining time in jiffies left from the input timeout */ -long drm_sched_entity_flush(struct drm_gpu_scheduler *sched, - struct drm_sched_entity *entity, long timeout) +long drm_sched_entity_flush(struct drm_sched_entity *entity, long timeout) { + struct drm_gpu_scheduler *sched; long ret = timeout; + sched = entity->sched; if (!drm_sched_entity_is_initialized(sched, entity)) return ret; /** @@ -312,10 +313,11 @@ EXPORT_SYMBOL(drm_sched_entity_flush); * entity and signals all jobs with an error code if the process was killed. * */ -void drm_sched_entity_fini(struct drm_gpu_scheduler *sched, - struct drm_sched_entity *entity) +void drm_sched_entity_fini(struct drm_sched_entity *entity) { + struct drm_gpu_scheduler *sched; + sched = entity->sched; drm_sched_entity_set_rq(entity, NULL); /* Consumption of existing IBs wasn't completed. Forcefully @@ -373,11 +375,10 @@ EXPORT_SYMBOL(drm_sched_entity_fini); * * Calls drm_sched_entity_do_release() and drm_sched_entity_cleanup() */ -void drm_sched_entity_destroy(struct drm_gpu_scheduler *sched, - struct drm_sched_entity *entity) +void drm_sched_entity_destroy(struct drm_sched_entity *entity) { - drm_sched_entity_flush(sched, entity, MAX_WAIT_SCHED_ENTITY_Q_EMPTY); - drm_sched_entity_fini(sched, entity); + drm_sched_entity_flush(entity, MAX_WAIT_SCHED_ENTITY_Q_EMPTY); + drm_sched_entity_fini(entity); } EXPORT_SYMBOL(drm_sched_entity_destroy); @@ -740,10 +741,11 @@ EXPORT_SYMBOL(drm_sched_job_recovery); * Returns 0 for success, negative error code otherwise. */ int drm_sched_job_init(struct drm_sched_job *job, - struct drm_gpu_scheduler *sched, struct drm_sched_entity *entity, void *owner) { + struct drm_gpu_scheduler *sched = entity->sched; + job->sched = sched; job->entity = entity; job->s_priority = entity->rq - sched->sched_rq; diff --git a/drivers/gpu/drm/v3d/v3d_drv.c b/drivers/gpu/drm/v3d/v3d_drv.c index 1dceba2b42fd..2a85fa68ffea 100644 --- a/drivers/gpu/drm/v3d/v3d_drv.c +++ b/drivers/gpu/drm/v3d/v3d_drv.c @@ -145,13 +145,11 @@ v3d_open(struct drm_device *dev, struct drm_file *file) static void v3d_postclose(struct drm_device *dev, struct drm_file *file) { - struct v3d_dev *v3d = to_v3d_dev(dev); struct v3d_file_priv *v3d_priv = file->driver_priv; enum v3d_queue q; for (q = 0; q < V3D_MAX_QUEUES; q++) { - drm_sched_entity_destroy(&v3d->queue[q].sched, - &v3d_priv->sched_entity[q]); + drm_sched_entity_destroy(&v3d_priv->sched_entity[q]); } kfree(v3d_priv); diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c index e1fcbb4cd0ae..5ce24098a5fd 100644 --- a/drivers/gpu/drm/v3d/v3d_gem.c +++ b/drivers/gpu/drm/v3d/v3d_gem.c @@ -553,7 +553,6 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data, mutex_lock(&v3d->sched_lock); if (exec->bin.start != exec->bin.end) { ret = drm_sched_job_init(&exec->bin.base, - &v3d->queue[V3D_BIN].sched, &v3d_priv->sched_entity[V3D_BIN], v3d_priv); if (ret) @@ -568,7 +567,6 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data, } ret = drm_sched_job_init(&exec->render.base, - &v3d->queue[V3D_RENDER].sched, &v3d_priv->sched_entity[V3D_RENDER], v3d_priv); if (ret) diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index 2205e89722f6..728346abcc81 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -286,12 +286,9 @@ int drm_sched_entity_init(struct drm_sched_entity *entity, struct drm_sched_rq **rq_list, unsigned int num_rq_list, atomic_t *guilty); -long drm_sched_entity_flush(struct drm_gpu_scheduler *sched, - struct drm_sched_entity *entity, long timeout); -void drm_sched_entity_fini(struct drm_gpu_scheduler *sched, - struct drm_sched_entity *entity); -void drm_sched_entity_destroy(struct drm_gpu_scheduler *sched, - struct drm_sched_entity *entity); +long drm_sched_entity_flush(struct drm_sched_entity *entity, long timeout); +void drm_sched_entity_fini(struct drm_sched_entity *entity); +void drm_sched_entity_destroy(struct drm_sched_entity *entity); void drm_sched_entity_push_job(struct drm_sched_job *sched_job, struct drm_sched_entity *entity); void drm_sched_entity_set_rq(struct drm_sched_entity *entity, @@ -302,7 +299,6 @@ struct drm_sched_fence *drm_sched_fence_create( void drm_sched_fence_scheduled(struct drm_sched_fence *fence); void drm_sched_fence_finished(struct drm_sched_fence *fence); int drm_sched_job_init(struct drm_sched_job *job, - struct drm_gpu_scheduler *sched, struct drm_sched_entity *entity, void *owner); void drm_sched_hw_job_reset(struct drm_gpu_scheduler *sched, -- cgit v1.2.3 From 068c330419ffb3422a43cb7d34351f1ef033950f Mon Sep 17 00:00:00 2001 From: Nayan Deshmukh Date: Fri, 20 Jul 2018 17:51:06 +0530 Subject: drm/scheduler: remove sched field from the entity MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The scheduler of the entity is decided by the run queue on which it is queued. This patch avoids us the effort required to maintain a sync between rq and sched field when we start shifting entites among different rqs. Signed-off-by: Nayan Deshmukh Reviewed-by: Christian König Reviewed-by: Eric Anholt Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 6 +++--- drivers/gpu/drm/scheduler/gpu_scheduler.c | 19 +++++++++---------- drivers/gpu/drm/scheduler/sched_fence.c | 2 +- include/drm/gpu_scheduler.h | 2 -- 6 files changed, 16 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 4d4575b3bba7..178d9ce4eba1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -1262,7 +1262,7 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p, priority = job->base.s_priority; drm_sched_entity_push_job(&job->base, entity); - ring = to_amdgpu_ring(entity->sched); + ring = to_amdgpu_ring(entity->rq->sched); amdgpu_ring_priority_get(ring, priority); ttm_eu_fence_buffer_objects(&p->ticket, &p->validated, p->fence); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index 631481a730e0..391e2f7c03aa 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -143,7 +143,7 @@ int amdgpu_job_submit(struct amdgpu_job *job, struct drm_sched_entity *entity, priority = job->base.s_priority; drm_sched_entity_push_job(&job->base, entity); - ring = to_amdgpu_ring(entity->sched); + ring = to_amdgpu_ring(entity->rq->sched); amdgpu_ring_priority_get(ring, priority); return 0; @@ -167,7 +167,7 @@ int amdgpu_job_submit_direct(struct amdgpu_job *job, struct amdgpu_ring *ring, static struct dma_fence *amdgpu_job_dependency(struct drm_sched_job *sched_job, struct drm_sched_entity *s_entity) { - struct amdgpu_ring *ring = to_amdgpu_ring(s_entity->sched); + struct amdgpu_ring *ring = to_amdgpu_ring(s_entity->rq->sched); struct amdgpu_job *job = to_amdgpu_job(sched_job); struct amdgpu_vm *vm = job->vm; struct dma_fence *fence; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 74b4a28a41d6..5d7d7900ccab 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -387,7 +387,7 @@ static int amdgpu_vm_clear_bo(struct amdgpu_device *adev, ats_entries = 0; } - ring = container_of(vm->entity.sched, struct amdgpu_ring, sched); + ring = container_of(vm->entity.rq->sched, struct amdgpu_ring, sched); r = reservation_object_reserve_shared(bo->tbo.resv); if (r) @@ -1113,7 +1113,7 @@ restart: struct amdgpu_ring *ring; struct dma_fence *fence; - ring = container_of(vm->entity.sched, struct amdgpu_ring, + ring = container_of(vm->entity.rq->sched, struct amdgpu_ring, sched); amdgpu_ring_pad_ib(ring, params.ib); @@ -1403,7 +1403,7 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev, addr, flags); } - ring = container_of(vm->entity.sched, struct amdgpu_ring, sched); + ring = container_of(vm->entity.rq->sched, struct amdgpu_ring, sched); nptes = last - start + 1; diff --git a/drivers/gpu/drm/scheduler/gpu_scheduler.c b/drivers/gpu/drm/scheduler/gpu_scheduler.c index a3b55c542025..3f2fc5e8242a 100644 --- a/drivers/gpu/drm/scheduler/gpu_scheduler.c +++ b/drivers/gpu/drm/scheduler/gpu_scheduler.c @@ -185,7 +185,6 @@ int drm_sched_entity_init(struct drm_sched_entity *entity, memset(entity, 0, sizeof(struct drm_sched_entity)); INIT_LIST_HEAD(&entity->list); entity->rq = rq_list[0]; - entity->sched = rq_list[0]->sched; entity->guilty = guilty; entity->last_scheduled = NULL; @@ -210,8 +209,8 @@ EXPORT_SYMBOL(drm_sched_entity_init); static bool drm_sched_entity_is_initialized(struct drm_gpu_scheduler *sched, struct drm_sched_entity *entity) { - return entity->sched == sched && - entity->rq != NULL; + return entity->rq != NULL && + entity->rq->sched == sched; } /** @@ -278,7 +277,7 @@ long drm_sched_entity_flush(struct drm_sched_entity *entity, long timeout) struct drm_gpu_scheduler *sched; long ret = timeout; - sched = entity->sched; + sched = entity->rq->sched; if (!drm_sched_entity_is_initialized(sched, entity)) return ret; /** @@ -317,7 +316,7 @@ void drm_sched_entity_fini(struct drm_sched_entity *entity) { struct drm_gpu_scheduler *sched; - sched = entity->sched; + sched = entity->rq->sched; drm_sched_entity_set_rq(entity, NULL); /* Consumption of existing IBs wasn't completed. Forcefully @@ -388,7 +387,7 @@ static void drm_sched_entity_wakeup(struct dma_fence *f, struct dma_fence_cb *cb container_of(cb, struct drm_sched_entity, cb); entity->dependency = NULL; dma_fence_put(f); - drm_sched_wakeup(entity->sched); + drm_sched_wakeup(entity->rq->sched); } static void drm_sched_entity_clear_dep(struct dma_fence *f, struct dma_fence_cb *cb) @@ -438,7 +437,7 @@ EXPORT_SYMBOL(drm_sched_entity_set_rq); bool drm_sched_dependency_optimized(struct dma_fence* fence, struct drm_sched_entity *entity) { - struct drm_gpu_scheduler *sched = entity->sched; + struct drm_gpu_scheduler *sched = entity->rq->sched; struct drm_sched_fence *s_fence; if (!fence || dma_fence_is_signaled(fence)) @@ -455,7 +454,7 @@ EXPORT_SYMBOL(drm_sched_dependency_optimized); static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity) { - struct drm_gpu_scheduler *sched = entity->sched; + struct drm_gpu_scheduler *sched = entity->rq->sched; struct dma_fence * fence = entity->dependency; struct drm_sched_fence *s_fence; @@ -500,7 +499,7 @@ static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity) static struct drm_sched_job * drm_sched_entity_pop_job(struct drm_sched_entity *entity) { - struct drm_gpu_scheduler *sched = entity->sched; + struct drm_gpu_scheduler *sched = entity->rq->sched; struct drm_sched_job *sched_job = to_drm_sched_job( spsc_queue_peek(&entity->job_queue)); @@ -744,7 +743,7 @@ int drm_sched_job_init(struct drm_sched_job *job, struct drm_sched_entity *entity, void *owner) { - struct drm_gpu_scheduler *sched = entity->sched; + struct drm_gpu_scheduler *sched = entity->rq->sched; job->sched = sched; job->entity = entity; diff --git a/drivers/gpu/drm/scheduler/sched_fence.c b/drivers/gpu/drm/scheduler/sched_fence.c index 45d9c3affbea..d8d2dff9ea2f 100644 --- a/drivers/gpu/drm/scheduler/sched_fence.c +++ b/drivers/gpu/drm/scheduler/sched_fence.c @@ -161,7 +161,7 @@ struct drm_sched_fence *drm_sched_fence_create(struct drm_sched_entity *entity, return NULL; fence->owner = owner; - fence->sched = entity->sched; + fence->sched = entity->rq->sched; spin_lock_init(&fence->lock); seq = atomic_inc_return(&entity->fence_seq); diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index 728346abcc81..091b9afcd184 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -52,7 +52,6 @@ enum drm_sched_priority { * runqueue. * @rq: runqueue to which this entity belongs. * @rq_lock: lock to modify the runqueue to which this entity belongs. - * @sched: the scheduler instance to which this entity is enqueued. * @job_queue: the list of jobs of this entity. * @fence_seq: a linearly increasing seqno incremented with each * new &drm_sched_fence which is part of the entity. @@ -76,7 +75,6 @@ struct drm_sched_entity { struct list_head list; struct drm_sched_rq *rq; spinlock_t rq_lock; - struct drm_gpu_scheduler *sched; struct spsc_queue job_queue; -- cgit v1.2.3 From 3c507b8af638c67d4a80d70091d2057ecb01e8a6 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Mon, 23 Jul 2018 21:40:07 +0200 Subject: net: phy: add helper phy_polling_mode Add a helper for checking whether polling is used to detect PHY status changes. Signed-off-by: Heiner Kallweit Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/phy/phy.c | 8 ++++---- include/linux/phy.h | 10 ++++++++++ 2 files changed, 14 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 04780db4c963..1ee25877c4d1 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -525,7 +525,7 @@ static int phy_start_aneg_priv(struct phy_device *phydev, bool sync) * negotiation may already be done and aneg interrupt may not be * generated. */ - if (phydev->irq != PHY_POLL && phydev->state == PHY_AN) { + if (!phy_polling_mode(phydev) && phydev->state == PHY_AN) { err = phy_aneg_done(phydev); if (err > 0) { trigger = true; @@ -983,7 +983,7 @@ void phy_state_machine(struct work_struct *work) needs_aneg = true; break; case PHY_NOLINK: - if (phydev->irq != PHY_POLL) + if (!phy_polling_mode(phydev)) break; err = phy_read_status(phydev); @@ -1024,7 +1024,7 @@ void phy_state_machine(struct work_struct *work) /* Only register a CHANGE if we are polling and link changed * since latest checking. */ - if (phydev->irq == PHY_POLL) { + if (phy_polling_mode(phydev)) { old_link = phydev->link; err = phy_read_status(phydev); if (err) @@ -1123,7 +1123,7 @@ void phy_state_machine(struct work_struct *work) * PHY, if PHY_IGNORE_INTERRUPT is set, then we will be moving * between states from phy_mac_interrupt() */ - if (phydev->irq == PHY_POLL) + if (phy_polling_mode(phydev)) queue_delayed_work(system_power_efficient_wq, &phydev->state_queue, PHY_STATE_TIME * HZ); } diff --git a/include/linux/phy.h b/include/linux/phy.h index 075c2f770d3e..cd6f637cbbfb 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -824,6 +824,16 @@ static inline bool phy_interrupt_is_valid(struct phy_device *phydev) return phydev->irq != PHY_POLL && phydev->irq != PHY_IGNORE_INTERRUPT; } +/** + * phy_polling_mode - Convenience function for testing whether polling is + * used to detect PHY status changes + * @phydev: the phy_device struct + */ +static inline bool phy_polling_mode(struct phy_device *phydev) +{ + return phydev->irq == PHY_POLL; +} + /** * phy_is_internal - Convenience function for testing if a PHY is internal * @phydev: the phy_device struct -- cgit v1.2.3 From d0e45d686a3ef18a20d4eac6675b76d3656c4727 Mon Sep 17 00:00:00 2001 From: Saravanan Sekar Date: Thu, 19 Jul 2018 11:06:46 +0200 Subject: dt-bindings: clock: Add S700 support for Actions Semi Soc's Add clock bindings constants for action S700 Maintain common clock dt-bindings for Actions Semi SoC's S700 and S900. Signed-off-by: Parthiban Nallathambi Signed-off-by: Saravanan Sekar Reviewed-by: Rob Herring Signed-off-by: Stephen Boyd --- .../devicetree/bindings/clock/actions,owl-cmu.txt | 49 +++++++++ .../devicetree/bindings/clock/actions,s900-cmu.txt | 47 -------- include/dt-bindings/clock/actions,s700-cmu.h | 118 +++++++++++++++++++++ 3 files changed, 167 insertions(+), 47 deletions(-) create mode 100644 Documentation/devicetree/bindings/clock/actions,owl-cmu.txt delete mode 100644 Documentation/devicetree/bindings/clock/actions,s900-cmu.txt create mode 100644 include/dt-bindings/clock/actions,s700-cmu.h (limited to 'include') diff --git a/Documentation/devicetree/bindings/clock/actions,owl-cmu.txt b/Documentation/devicetree/bindings/clock/actions,owl-cmu.txt new file mode 100644 index 000000000000..d1e60d297387 --- /dev/null +++ b/Documentation/devicetree/bindings/clock/actions,owl-cmu.txt @@ -0,0 +1,49 @@ +* Actions Semi Owl Clock Management Unit (CMU) + +The Actions Semi Owl Clock Management Unit generates and supplies clock +to various controllers within the SoC. The clock binding described here is +applicable to S900 and S700 SoC's. + +Required Properties: + +- compatible: should be one of the following, + "actions,s900-cmu" + "actions,s700-cmu" +- reg: physical base address of the controller and length of memory mapped + region. +- clocks: Reference to the parent clocks ("hosc", "losc") +- #clock-cells: should be 1. + +Each clock is assigned an identifier, and client nodes can use this identifier +to specify the clock which they consume. + +All available clocks are defined as preprocessor macros in corresponding +dt-bindings/clock/actions,s900-cmu.h or actions,s700-cmu.h header and can be +used in device tree sources. + +External clocks: + +The hosc clock used as input for the plls is generated outside the SoC. It is +expected that it is defined using standard clock bindings as "hosc". + +Actions Semi S900 CMU also requires one more clock: + - "losc" - internal low frequency oscillator + +Example: Clock Management Unit node: + + cmu: clock-controller@e0160000 { + compatible = "actions,s900-cmu"; + reg = <0x0 0xe0160000 0x0 0x1000>; + clocks = <&hosc>, <&losc>; + #clock-cells = <1>; + }; + +Example: UART controller node that consumes clock generated by the clock +management unit: + + uart: serial@e012a000 { + compatible = "actions,s900-uart", "actions,owl-uart"; + reg = <0x0 0xe012a000 0x0 0x2000>; + interrupts = ; + clocks = <&cmu CLK_UART5>; + }; diff --git a/Documentation/devicetree/bindings/clock/actions,s900-cmu.txt b/Documentation/devicetree/bindings/clock/actions,s900-cmu.txt deleted file mode 100644 index 93e4fb827cd6..000000000000 --- a/Documentation/devicetree/bindings/clock/actions,s900-cmu.txt +++ /dev/null @@ -1,47 +0,0 @@ -* Actions S900 Clock Management Unit (CMU) - -The Actions S900 clock management unit generates and supplies clock to various -controllers within the SoC. The clock binding described here is applicable to -S900 SoC. - -Required Properties: - -- compatible: should be "actions,s900-cmu" -- reg: physical base address of the controller and length of memory mapped - region. -- clocks: Reference to the parent clocks ("hosc", "losc") -- #clock-cells: should be 1. - -Each clock is assigned an identifier, and client nodes can use this identifier -to specify the clock which they consume. - -All available clocks are defined as preprocessor macros in -dt-bindings/clock/actions,s900-cmu.h header and can be used in device -tree sources. - -External clocks: - -The hosc clock used as input for the plls is generated outside the SoC. It is -expected that it is defined using standard clock bindings as "hosc". - -Actions S900 CMU also requires one more clock: - - "losc" - internal low frequency oscillator - -Example: Clock Management Unit node: - - cmu: clock-controller@e0160000 { - compatible = "actions,s900-cmu"; - reg = <0x0 0xe0160000 0x0 0x1000>; - clocks = <&hosc>, <&losc>; - #clock-cells = <1>; - }; - -Example: UART controller node that consumes clock generated by the clock -management unit: - - uart: serial@e012a000 { - compatible = "actions,s900-uart", "actions,owl-uart"; - reg = <0x0 0xe012a000 0x0 0x2000>; - interrupts = ; - clocks = <&cmu CLK_UART5>; - }; diff --git a/include/dt-bindings/clock/actions,s700-cmu.h b/include/dt-bindings/clock/actions,s700-cmu.h new file mode 100644 index 000000000000..3e1942996724 --- /dev/null +++ b/include/dt-bindings/clock/actions,s700-cmu.h @@ -0,0 +1,118 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * Device Tree binding constants for Actions Semi S700 Clock Management Unit + * + * Copyright (c) 2014 Actions Semi Inc. + * Author: David Liu + * + * Author: Pathiban Nallathambi + * Author: Saravanan Sekar + */ + +#ifndef __DT_BINDINGS_CLOCK_S700_H +#define __DT_BINDINGS_CLOCK_S700_H + +#define CLK_NONE 0 + +/* pll clocks */ +#define CLK_CORE_PLL 1 +#define CLK_DEV_PLL 2 +#define CLK_DDR_PLL 3 +#define CLK_NAND_PLL 4 +#define CLK_DISPLAY_PLL 5 +#define CLK_TVOUT_PLL 6 +#define CLK_CVBS_PLL 7 +#define CLK_AUDIO_PLL 8 +#define CLK_ETHERNET_PLL 9 + +/* system clock */ +#define CLK_CPU 10 +#define CLK_DEV 11 +#define CLK_AHB 12 +#define CLK_APB 13 +#define CLK_DMAC 14 +#define CLK_NOC0_CLK_MUX 15 +#define CLK_NOC1_CLK_MUX 16 +#define CLK_HP_CLK_MUX 17 +#define CLK_HP_CLK_DIV 18 +#define CLK_NOC1_CLK_DIV 19 +#define CLK_NOC0 20 +#define CLK_NOC1 21 +#define CLK_SENOR_SRC 22 + +/* peripheral device clock */ +#define CLK_GPIO 23 +#define CLK_TIMER 24 +#define CLK_DSI 25 +#define CLK_CSI 26 +#define CLK_SI 27 +#define CLK_DE 28 +#define CLK_HDE 29 +#define CLK_VDE 30 +#define CLK_VCE 31 +#define CLK_NAND 32 +#define CLK_SD0 33 +#define CLK_SD1 34 +#define CLK_SD2 35 + +#define CLK_UART0 36 +#define CLK_UART1 37 +#define CLK_UART2 38 +#define CLK_UART3 39 +#define CLK_UART4 40 +#define CLK_UART5 41 +#define CLK_UART6 42 + +#define CLK_PWM0 43 +#define CLK_PWM1 44 +#define CLK_PWM2 45 +#define CLK_PWM3 46 +#define CLK_PWM4 47 +#define CLK_PWM5 48 +#define CLK_GPU3D 49 + +#define CLK_I2C0 50 +#define CLK_I2C1 51 +#define CLK_I2C2 52 +#define CLK_I2C3 53 + +#define CLK_SPI0 54 +#define CLK_SPI1 55 +#define CLK_SPI2 56 +#define CLK_SPI3 57 + +#define CLK_USB3_480MPLL0 58 +#define CLK_USB3_480MPHY0 59 +#define CLK_USB3_5GPHY 60 +#define CLK_USB3_CCE 61 +#define CLK_USB3_MAC 62 + +#define CLK_LCD 63 +#define CLK_HDMI_AUDIO 64 +#define CLK_I2SRX 65 +#define CLK_I2STX 66 + +#define CLK_SENSOR0 67 +#define CLK_SENSOR1 68 + +#define CLK_HDMI_DEV 69 + +#define CLK_ETHERNET 70 +#define CLK_RMII_REF 71 + +#define CLK_USB2H0_PLLEN 72 +#define CLK_USB2H0_PHY 73 +#define CLK_USB2H0_CCE 74 +#define CLK_USB2H1_PLLEN 75 +#define CLK_USB2H1_PHY 76 +#define CLK_USB2H1_CCE 77 + +#define CLK_TVOUT 78 + +#define CLK_THERMAL_SENSOR 79 + +#define CLK_IRC_SWITCH 80 +#define CLK_PCM1 81 +#define CLK_NR_CLKS (CLK_PCM1 + 1) + +#endif /* __DT_BINDINGS_CLOCK_S700_H */ -- cgit v1.2.3 From 603cc1498455cf57f5ca4483b600efb37ea2c56c Mon Sep 17 00:00:00 2001 From: Karsten Graul Date: Wed, 25 Jul 2018 16:35:32 +0200 Subject: net/smc: provide fallback reason code Remember the fallback reason code and the peer diagnosis code for smc sockets, and provide them in smc_diag.c to the netlink interface. And add more detailed reason codes. Signed-off-by: Karsten Graul Signed-off-by: Ursula Braun Signed-off-by: David S. Miller --- include/uapi/linux/smc_diag.h | 6 +++++ net/smc/af_smc.c | 52 +++++++++++++++++++++++++------------------ net/smc/smc.h | 2 ++ net/smc/smc_clc.c | 6 ++++- net/smc/smc_clc.h | 18 ++++++++++----- net/smc/smc_diag.c | 6 +++++ 6 files changed, 61 insertions(+), 29 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/smc_diag.h b/include/uapi/linux/smc_diag.h index 48ae3ee22b2d..ac9e8c96d9bd 100644 --- a/include/uapi/linux/smc_diag.h +++ b/include/uapi/linux/smc_diag.h @@ -43,6 +43,7 @@ enum { SMC_DIAG_LGRINFO, SMC_DIAG_SHUTDOWN, SMC_DIAG_DMBINFO, + SMC_DIAG_FALLBACK, __SMC_DIAG_MAX, }; @@ -92,6 +93,11 @@ struct smc_diag_lgrinfo { __u8 role; }; +struct smc_diag_fallback { + __u32 reason; + __u32 peer_diagnosis; +}; + struct smcd_diag_dmbinfo { /* SMC-D Socket internals */ __u32 linkid; /* Link identifier */ __u64 peer_gid; /* Peer GID */ diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index b81797103260..fce7e4751151 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -344,17 +344,17 @@ static int smc_clnt_conf_first_link(struct smc_sock *smc) rc = smc_ib_modify_qp_rts(link); if (rc) - return SMC_CLC_DECL_INTERR; + return SMC_CLC_DECL_ERR_RDYLNK; smc_wr_remember_qp_attr(link); if (smc_reg_rmb(link, smc->conn.rmb_desc, false)) - return SMC_CLC_DECL_INTERR; + return SMC_CLC_DECL_ERR_REGRMB; /* send CONFIRM LINK response over RoCE fabric */ rc = smc_llc_send_confirm_link(link, SMC_LLC_RESP); if (rc < 0) - return SMC_CLC_DECL_TCL; + return SMC_CLC_DECL_TIMEOUT_CL; /* receive ADD LINK request from server over RoCE fabric */ rest = wait_for_completion_interruptible_timeout(&link->llc_add, @@ -372,7 +372,7 @@ static int smc_clnt_conf_first_link(struct smc_sock *smc) link->smcibdev->mac[link->ibport - 1], link->gid, SMC_LLC_RESP); if (rc < 0) - return SMC_CLC_DECL_TCL; + return SMC_CLC_DECL_TIMEOUT_AL; smc_llc_link_active(link, net->ipv4.sysctl_tcp_keepalive_time); @@ -424,9 +424,10 @@ static void smc_link_save_peer_info(struct smc_link *link, } /* fall back during connect */ -static int smc_connect_fallback(struct smc_sock *smc) +static int smc_connect_fallback(struct smc_sock *smc, int reason_code) { smc->use_fallback = true; + smc->fallback_rsn = reason_code; smc_copy_sock_settings_to_clc(smc); if (smc->sk.sk_state == SMC_INIT) smc->sk.sk_state = SMC_ACTIVE; @@ -443,7 +444,7 @@ static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code) sock_put(&smc->sk); /* passive closing */ return reason_code; } - if (reason_code != SMC_CLC_DECL_REPLY) { + if (reason_code != SMC_CLC_DECL_PEERDECL) { rc = smc_clc_send_decline(smc, reason_code); if (rc < 0) { if (smc->sk.sk_state == SMC_INIT) @@ -451,7 +452,7 @@ static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code) return rc; } } - return smc_connect_fallback(smc); + return smc_connect_fallback(smc, reason_code); } /* abort connecting */ @@ -568,7 +569,7 @@ static int smc_connect_rdma(struct smc_sock *smc, smc_link_save_peer_info(link, aclc); if (smc_rmb_rtoken_handling(&smc->conn, aclc)) - return smc_connect_abort(smc, SMC_CLC_DECL_INTERR, + return smc_connect_abort(smc, SMC_CLC_DECL_ERR_RTOK, local_contact); smc_close_init(smc); @@ -576,12 +577,12 @@ static int smc_connect_rdma(struct smc_sock *smc, if (local_contact == SMC_FIRST_CONTACT) { if (smc_ib_ready_link(link)) - return smc_connect_abort(smc, SMC_CLC_DECL_INTERR, + return smc_connect_abort(smc, SMC_CLC_DECL_ERR_RDYLNK, local_contact); } else { if (!smc->conn.rmb_desc->reused && smc_reg_rmb(link, smc->conn.rmb_desc, true)) - return smc_connect_abort(smc, SMC_CLC_DECL_INTERR, + return smc_connect_abort(smc, SMC_CLC_DECL_ERR_REGRMB, local_contact); } smc_rmb_sync_sg_for_device(&smc->conn); @@ -659,11 +660,11 @@ static int __smc_connect(struct smc_sock *smc) sock_hold(&smc->sk); /* sock put in passive closing */ if (smc->use_fallback) - return smc_connect_fallback(smc); + return smc_connect_fallback(smc, smc->fallback_rsn); /* if peer has not signalled SMC-capability, fall back */ if (!tcp_sk(smc->clcsock->sk)->syn_smc) - return smc_connect_fallback(smc); + return smc_connect_fallback(smc, SMC_CLC_DECL_PEERNOSMC); /* IPSec connections opt out of SMC-R optimizations */ if (using_ipsec(smc)) @@ -693,7 +694,7 @@ static int __smc_connect(struct smc_sock *smc) /* if neither ISM nor RDMA are supported, fallback */ if (!rdma_supported && !ism_supported) - return smc_connect_decline_fallback(smc, SMC_CLC_DECL_CNFERR); + return smc_connect_decline_fallback(smc, SMC_CLC_DECL_NOSMCDEV); /* perform CLC handshake */ rc = smc_connect_clc(smc, smc_type, &aclc, ibdev, ibport, gid, ismdev); @@ -708,7 +709,7 @@ static int __smc_connect(struct smc_sock *smc) else if (ism_supported && aclc.hdr.path == SMC_TYPE_D) rc = smc_connect_ism(smc, &aclc, ismdev); else - rc = SMC_CLC_DECL_CNFERR; + rc = SMC_CLC_DECL_MODEUNSUPP; if (rc) { smc_connect_ism_vlan_cleanup(smc, ism_supported, ismdev, vlan); return smc_connect_decline_fallback(smc, rc); @@ -946,12 +947,12 @@ static int smc_serv_conf_first_link(struct smc_sock *smc) link = &lgr->lnk[SMC_SINGLE_LINK]; if (smc_reg_rmb(link, smc->conn.rmb_desc, false)) - return SMC_CLC_DECL_INTERR; + return SMC_CLC_DECL_ERR_REGRMB; /* send CONFIRM LINK request to client over the RoCE fabric */ rc = smc_llc_send_confirm_link(link, SMC_LLC_REQ); if (rc < 0) - return SMC_CLC_DECL_TCL; + return SMC_CLC_DECL_TIMEOUT_CL; /* receive CONFIRM LINK response from client over the RoCE fabric */ rest = wait_for_completion_interruptible_timeout( @@ -973,7 +974,7 @@ static int smc_serv_conf_first_link(struct smc_sock *smc) link->smcibdev->mac[link->ibport - 1], link->gid, SMC_LLC_REQ); if (rc < 0) - return SMC_CLC_DECL_TCL; + return SMC_CLC_DECL_TIMEOUT_AL; /* receive ADD LINK response from client over the RoCE fabric */ rest = wait_for_completion_interruptible_timeout(&link->llc_add_resp, @@ -1048,7 +1049,8 @@ static void smc_listen_decline(struct smc_sock *new_smc, int reason_code, } smc_conn_free(&new_smc->conn); new_smc->use_fallback = true; - if (reason_code && reason_code != SMC_CLC_DECL_REPLY) { + new_smc->fallback_rsn = reason_code; + if (reason_code && reason_code != SMC_CLC_DECL_PEERDECL) { if (smc_clc_send_decline(new_smc, reason_code) < 0) { smc_listen_out_err(new_smc); return; @@ -1139,7 +1141,7 @@ static int smc_listen_rdma_reg(struct smc_sock *new_smc, int local_contact) if (local_contact != SMC_FIRST_CONTACT) { if (!new_smc->conn.rmb_desc->reused) { if (smc_reg_rmb(link, new_smc->conn.rmb_desc, true)) - return SMC_CLC_DECL_INTERR; + return SMC_CLC_DECL_ERR_REGRMB; } } smc_rmb_sync_sg_for_device(&new_smc->conn); @@ -1159,13 +1161,13 @@ static void smc_listen_rdma_finish(struct smc_sock *new_smc, smc_link_save_peer_info(link, cclc); if (smc_rmb_rtoken_handling(&new_smc->conn, cclc)) { - reason_code = SMC_CLC_DECL_INTERR; + reason_code = SMC_CLC_DECL_ERR_RTOK; goto decline; } if (local_contact == SMC_FIRST_CONTACT) { if (smc_ib_ready_link(link)) { - reason_code = SMC_CLC_DECL_INTERR; + reason_code = SMC_CLC_DECL_ERR_RDYLNK; goto decline; } /* QP confirmation over RoCE fabric */ @@ -1206,6 +1208,7 @@ static void smc_listen_work(struct work_struct *work) /* check if peer is smc capable */ if (!tcp_sk(newclcsock->sk)->syn_smc) { new_smc->use_fallback = true; + new_smc->fallback_rsn = SMC_CLC_DECL_PEERNOSMC; smc_listen_out_connected(new_smc); return; } @@ -1250,7 +1253,8 @@ static void smc_listen_work(struct work_struct *work) smc_listen_rdma_reg(new_smc, local_contact))) { /* SMC not supported, decline */ mutex_unlock(&smc_create_lgr_pending); - smc_listen_decline(new_smc, SMC_CLC_DECL_CNFERR, local_contact); + smc_listen_decline(new_smc, SMC_CLC_DECL_MODEUNSUPP, + local_contact); return; } @@ -1297,6 +1301,7 @@ static void smc_tcp_listen_work(struct work_struct *work) new_smc->listen_smc = lsmc; new_smc->use_fallback = lsmc->use_fallback; + new_smc->fallback_rsn = lsmc->fallback_rsn; sock_hold(lsk); /* sock_put in smc_listen_work */ INIT_WORK(&new_smc->smc_listen_work, smc_listen_work); smc_copy_sock_settings_to_smc(new_smc); @@ -1451,6 +1456,7 @@ static int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) if (msg->msg_flags & MSG_FASTOPEN) { if (sk->sk_state == SMC_INIT) { smc->use_fallback = true; + smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP; } else { rc = -EINVAL; goto out; @@ -1648,6 +1654,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, /* option not supported by SMC */ if (sk->sk_state == SMC_INIT) { smc->use_fallback = true; + smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP; } else { if (!smc->use_fallback) rc = -EINVAL; @@ -1885,6 +1892,7 @@ static int smc_create(struct net *net, struct socket *sock, int protocol, /* create internal TCP socket for CLC handshake and fallback */ smc = smc_sk(sk); smc->use_fallback = false; /* assume rdma capability first */ + smc->fallback_rsn = 0; rc = sock_create_kern(net, family, SOCK_STREAM, IPPROTO_TCP, &smc->clcsock); if (rc) { diff --git a/net/smc/smc.h b/net/smc/smc.h index be20acd7b5ab..08786ace6010 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -208,6 +208,8 @@ struct smc_sock { /* smc sock container */ struct list_head accept_q; /* sockets to be accepted */ spinlock_t accept_q_lock; /* protects accept_q */ bool use_fallback; /* fallback to tcp */ + int fallback_rsn; /* reason for fallback */ + u32 peer_diagnosis; /* decline reason from peer */ int sockopt_defer_accept; /* sockopt TCP_DEFER_ACCEPT * value diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 78d74938a9d9..83aba9ade060 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -334,7 +334,11 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, goto out; } if (clcm->type == SMC_CLC_DECLINE) { - reason_code = SMC_CLC_DECL_REPLY; + struct smc_clc_msg_decline *dclc; + + dclc = (struct smc_clc_msg_decline *)clcm; + reason_code = SMC_CLC_DECL_PEERDECL; + smc->peer_diagnosis = ntohl(dclc->peer_diagnosis); if (((struct smc_clc_msg_decline *)buf)->hdr.flag) { smc->conn.lgr->sync_err = 1; smc_lgr_terminate(smc->conn.lgr); diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h index 6bdc63352d6a..18da89b681c2 100644 --- a/net/smc/smc_clc.h +++ b/net/smc/smc_clc.h @@ -28,15 +28,21 @@ #define SMC_TYPE_B 3 /* SMC-R and SMC-D */ #define CLC_WAIT_TIME (6 * HZ) /* max. wait time on clcsock */ #define SMC_CLC_DECL_MEM 0x01010000 /* insufficient memory resources */ -#define SMC_CLC_DECL_TIMEOUT 0x02000000 /* timeout */ +#define SMC_CLC_DECL_TIMEOUT_CL 0x02010000 /* timeout w4 QP confirm link */ +#define SMC_CLC_DECL_TIMEOUT_AL 0x02020000 /* timeout w4 QP add link */ #define SMC_CLC_DECL_CNFERR 0x03000000 /* configuration error */ -#define SMC_CLC_DECL_IPSEC 0x03030000 /* IPsec usage */ +#define SMC_CLC_DECL_PEERNOSMC 0x03010000 /* peer did not indicate SMC */ +#define SMC_CLC_DECL_IPSEC 0x03020000 /* IPsec usage */ +#define SMC_CLC_DECL_NOSMCDEV 0x03030000 /* no SMC device found */ +#define SMC_CLC_DECL_MODEUNSUPP 0x03040000 /* smc modes do not match (R or D)*/ +#define SMC_CLC_DECL_RMBE_EC 0x03050000 /* peer has eyecatcher in RMBE */ +#define SMC_CLC_DECL_OPTUNSUPP 0x03060000 /* fastopen sockopt not supported */ #define SMC_CLC_DECL_SYNCERR 0x04000000 /* synchronization error */ -#define SMC_CLC_DECL_REPLY 0x06000000 /* reply to a received decline */ +#define SMC_CLC_DECL_PEERDECL 0x05000000 /* peer declined during handshake */ #define SMC_CLC_DECL_INTERR 0x99990000 /* internal error */ -#define SMC_CLC_DECL_TCL 0x02040000 /* timeout w4 QP confirm */ -#define SMC_CLC_DECL_SEND 0x07000000 /* sending problem */ -#define SMC_CLC_DECL_RMBE_EC 0x08000000 /* peer has eyecatcher in RMBE */ +#define SMC_CLC_DECL_ERR_RTOK 0x99990001 /* rtoken handling failed */ +#define SMC_CLC_DECL_ERR_RDYLNK 0x99990002 /* ib ready link failed */ +#define SMC_CLC_DECL_ERR_REGRMB 0x99990003 /* reg rmb failed */ struct smc_clc_msg_hdr { /* header1 of clc messages */ u8 eyecatcher[4]; /* eye catcher */ diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c index a3cf7313a2d3..dbf64a93d68a 100644 --- a/net/smc/smc_diag.c +++ b/net/smc/smc_diag.c @@ -79,6 +79,7 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb, struct nlattr *bc) { struct smc_sock *smc = smc_sk(sk); + struct smc_diag_fallback fallback; struct user_namespace *user_ns; struct smc_diag_msg *r; struct nlmsghdr *nlh; @@ -101,6 +102,11 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb, if (smc_diag_msg_attrs_fill(sk, skb, r, user_ns)) goto errout; + fallback.reason = smc->fallback_rsn; + fallback.peer_diagnosis = smc->peer_diagnosis; + if (nla_put(skb, SMC_DIAG_FALLBACK, sizeof(fallback), &fallback) < 0) + goto errout; + if ((req->diag_ext & (1 << (SMC_DIAG_CONNINFO - 1))) && smc->conn.alert_token_local) { struct smc_connection *conn = &smc->conn; -- cgit v1.2.3 From 95a48b7d4459948b6bacf809809cf01a7dc06d1d Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 25 Jul 2018 23:00:54 +0200 Subject: ALSA: pcm: Add __force to cast in snd_pcm_lib_read/write() The snd_pcm_lib_read() and snd_pcm_lib_write() inline functions have the explicit cast from a user pointer to a kernel pointer, but they lacks of __force prefix. This fixes sparse warnings like: ./include/sound/pcm.h:1093:47: warning: cast removes address space of expression Fixes: 68541213720d ("ALSA: pcm: Direct in-kernel read/write support") Signed-off-by: Takashi Iwai --- include/sound/pcm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/sound/pcm.h b/include/sound/pcm.h index 1206045ccf03..d6bd3caf6878 100644 --- a/include/sound/pcm.h +++ b/include/sound/pcm.h @@ -1090,14 +1090,14 @@ static inline snd_pcm_sframes_t snd_pcm_lib_write(struct snd_pcm_substream *substream, const void __user *buf, snd_pcm_uframes_t frames) { - return __snd_pcm_lib_xfer(substream, (void *)buf, true, frames, false); + return __snd_pcm_lib_xfer(substream, (void __force *)buf, true, frames, false); } static inline snd_pcm_sframes_t snd_pcm_lib_read(struct snd_pcm_substream *substream, void __user *buf, snd_pcm_uframes_t frames) { - return __snd_pcm_lib_xfer(substream, (void *)buf, true, frames, false); + return __snd_pcm_lib_xfer(substream, (void __force *)buf, true, frames, false); } static inline snd_pcm_sframes_t -- cgit v1.2.3 From 601b218568a107370086dc5c7a1b283f8d463268 Mon Sep 17 00:00:00 2001 From: Ruchi Kandoi Date: Tue, 24 Jul 2018 10:35:44 -0700 Subject: cpufreq: trace frequency limits change systrace used for tracing for Android systems has carried a patch for many years in the Android tree that traces when the cpufreq limits change. With the help of this information, systrace can know when the policy limits change and can visually display the data. Lets add upstream support for the same. Signed-off-by: Ruchi Kandoi Signed-off-by: Joel Fernandes (Google) Acked-by: Viresh Kumar Acked-by: Steven Rostedt (VMware) Signed-off-by: Rafael J. Wysocki --- Documentation/trace/events-power.rst | 1 + drivers/cpufreq/cpufreq.c | 1 + include/trace/events/power.h | 25 +++++++++++++++++++++++++ 3 files changed, 27 insertions(+) (limited to 'include') diff --git a/Documentation/trace/events-power.rst b/Documentation/trace/events-power.rst index a77daca75e30..2ef318962e29 100644 --- a/Documentation/trace/events-power.rst +++ b/Documentation/trace/events-power.rst @@ -27,6 +27,7 @@ cpufreq. cpu_idle "state=%lu cpu_id=%lu" cpu_frequency "state=%lu cpu_id=%lu" + cpu_frequency_limits "min=%lu max=%lu cpu_id=%lu" A suspend event is used to indicate the system going in and out of the suspend mode: diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index b0dfd3222013..52566f1f1050 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -2236,6 +2236,7 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy, policy->min = new_policy->min; policy->max = new_policy->max; + trace_cpu_frequency_limits(policy); policy->cached_target_freq = UINT_MAX; diff --git a/include/trace/events/power.h b/include/trace/events/power.h index 908977d69783..f7aece721aed 100644 --- a/include/trace/events/power.h +++ b/include/trace/events/power.h @@ -5,6 +5,7 @@ #if !defined(_TRACE_POWER_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_POWER_H +#include #include #include #include @@ -148,6 +149,30 @@ DEFINE_EVENT(cpu, cpu_frequency, TP_ARGS(frequency, cpu_id) ); +TRACE_EVENT(cpu_frequency_limits, + + TP_PROTO(struct cpufreq_policy *policy), + + TP_ARGS(policy), + + TP_STRUCT__entry( + __field(u32, min_freq) + __field(u32, max_freq) + __field(u32, cpu_id) + ), + + TP_fast_assign( + __entry->min_freq = policy->min; + __entry->max_freq = policy->max; + __entry->cpu_id = policy->cpu; + ), + + TP_printk("min=%lu max=%lu cpu_id=%lu", + (unsigned long)__entry->min_freq, + (unsigned long)__entry->max_freq, + (unsigned long)__entry->cpu_id) +); + TRACE_EVENT(device_pm_callback_start, TP_PROTO(struct device *dev, const char *pm_ops, int event), -- cgit v1.2.3 From 6f4ceee9305dc3fe74099159b460f4b56b506f1d Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Tue, 24 Jul 2018 14:26:04 -0400 Subject: cpu/hotplug: Add a cpus_read_trylock() function There are use cases where it can be useful to have a cpus_read_trylock() function to work around circular lock dependency problem involving the cpu_hotplug_lock. Signed-off-by: Waiman Long Signed-off-by: Rafael J. Wysocki --- include/linux/cpu.h | 2 ++ kernel/cpu.c | 6 ++++++ 2 files changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index a97a63eef59f..e850bfea3e84 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -103,6 +103,7 @@ extern void cpus_write_lock(void); extern void cpus_write_unlock(void); extern void cpus_read_lock(void); extern void cpus_read_unlock(void); +extern int cpus_read_trylock(void); extern void lockdep_assert_cpus_held(void); extern void cpu_hotplug_disable(void); extern void cpu_hotplug_enable(void); @@ -115,6 +116,7 @@ static inline void cpus_write_lock(void) { } static inline void cpus_write_unlock(void) { } static inline void cpus_read_lock(void) { } static inline void cpus_read_unlock(void) { } +static inline int cpus_read_trylock(void) { return true; } static inline void lockdep_assert_cpus_held(void) { } static inline void cpu_hotplug_disable(void) { } static inline void cpu_hotplug_enable(void) { } diff --git a/kernel/cpu.c b/kernel/cpu.c index 0db8938fbb23..307486baa477 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -290,6 +290,12 @@ void cpus_read_lock(void) } EXPORT_SYMBOL_GPL(cpus_read_lock); +int cpus_read_trylock(void) +{ + return percpu_down_read_trylock(&cpu_hotplug_lock); +} +EXPORT_SYMBOL_GPL(cpus_read_trylock); + void cpus_read_unlock(void) { percpu_up_read(&cpu_hotplug_lock); -- cgit v1.2.3 From 2a8536f6e8464b8988baa7db881f30721616b0da Mon Sep 17 00:00:00 2001 From: Jeykumar Sankaran Date: Tue, 5 Jun 2018 19:00:54 -0700 Subject: drm: add msm compressed format modifiers Qualcomm Snapdragon chipsets uses compressed format to optimize BW across multiple IP's. This change adds needed modifier support in drm for a simple 4x4 tile based compressed variants of base formats. Changes in v3: - Removed duplicate entry for DRM_FORMAT_MOD_QCOM_COMPRESSED (Rob Clark) Changes in v4: - Remove all modifiers aside from COMPRESSED, this includes tiled and 10-bit Signed-off-by: Jeykumar Sankaran Signed-off-by: Sean Paul Signed-off-by: Rob Clark --- include/uapi/drm/drm_fourcc.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h index d43949b5bb3e..721ab7e54d96 100644 --- a/include/uapi/drm/drm_fourcc.h +++ b/include/uapi/drm/drm_fourcc.h @@ -299,6 +299,19 @@ extern "C" { */ #define DRM_FORMAT_MOD_SAMSUNG_64_32_TILE fourcc_mod_code(SAMSUNG, 1) +/* + * Qualcomm Compressed Format + * + * Refers to a compressed variant of the base format that is compressed. + * Implementation may be platform and base-format specific. + * + * Each macrotile consists of m x n (mostly 4 x 4) tiles. + * Pixel data pitch/stride is aligned with macrotile width. + * Pixel data height is aligned with macrotile height. + * Entire pixel data buffer is aligned with 4k(bytes). + */ +#define DRM_FORMAT_MOD_QCOM_COMPRESSED fourcc_mod_code(QCOM, 1) + /* Vivante framebuffer modifiers */ /* -- cgit v1.2.3 From 4cae99d9b5305ab8cccc839fccceb81ec9e5abda Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 25 Jul 2018 15:15:56 -0500 Subject: ALSA: memalloc: declare snd_sgbuf_aligned_pages() unconditionally Make this helper inline function available for all platforms. This helps solve 0-day compilation issues when CONFIG_SND_DMA_SGBUF is not defined. Reported-by: kbuild test robot Signed-off-by: Pierre-Louis Bossart Reviewed-by: Takashi Iwai Signed-off-by: Mark Brown --- include/sound/memalloc.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/sound/memalloc.h b/include/sound/memalloc.h index 9c3db3dce32b..c669900e6cbe 100644 --- a/include/sound/memalloc.h +++ b/include/sound/memalloc.h @@ -67,6 +67,14 @@ struct snd_dma_buffer { void *private_data; /* private for allocator; don't touch */ }; +/* + * return the pages matching with the given byte size + */ +static inline unsigned int snd_sgbuf_aligned_pages(size_t size) +{ + return (size + PAGE_SIZE - 1) >> PAGE_SHIFT; +} + #ifdef CONFIG_SND_DMA_SGBUF /* * Scatter-Gather generic device pages @@ -90,14 +98,6 @@ struct snd_sg_buf { struct device *dev; }; -/* - * return the pages matching with the given byte size - */ -static inline unsigned int snd_sgbuf_aligned_pages(size_t size) -{ - return (size + PAGE_SIZE - 1) >> PAGE_SHIFT; -} - /* * return the physical address at the corresponding offset */ -- cgit v1.2.3 From 0b62834e73e332fea76a340d62aaf50c732b17e0 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 25 Jul 2018 23:17:17 +0200 Subject: ALSA: pcm: Add snd_mask_set_format() helper for standard usages Many drivers calling snd_mask_set() need to do ugly cast with __force for shutting up the sparse warnings. Actually almost all of them are about setting the format, so it's far better to provide a common helper snd_mask_set_format() to pass SNDRV_PCM_FORMAT_* directly without the cast. There are a few other calls of snd_mask_set(), but they are in the PCM core code, so we leave them for now. Signed-off-by: Takashi Iwai Signed-off-by: Mark Brown --- include/sound/pcm_params.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/sound/pcm_params.h b/include/sound/pcm_params.h index c704357775fc..2dd37cada7c0 100644 --- a/include/sound/pcm_params.h +++ b/include/sound/pcm_params.h @@ -87,6 +87,13 @@ static inline void snd_mask_set(struct snd_mask *mask, unsigned int val) mask->bits[MASK_OFS(val)] |= MASK_BIT(val); } +/* Most of drivers need only this one */ +static inline void snd_mask_set_format(struct snd_mask *mask, + snd_pcm_format_t format) +{ + snd_mask_set(mask, (__force unsigned int)format); +} + static inline void snd_mask_reset(struct snd_mask *mask, unsigned int val) { mask->bits[MASK_OFS(val)] &= ~MASK_BIT(val); @@ -369,8 +376,7 @@ static inline int params_physical_width(const struct snd_pcm_hw_params *p) static inline void params_set_format(struct snd_pcm_hw_params *p, snd_pcm_format_t fmt) { - snd_mask_set(hw_param_mask(p, SNDRV_PCM_HW_PARAM_FORMAT), - (__force int)fmt); + snd_mask_set_format(hw_param_mask(p, SNDRV_PCM_HW_PARAM_FORMAT), fmt); } #endif /* __SOUND_PCM_PARAMS_H */ -- cgit v1.2.3 From 359f642700f2ff05d9c94cd9216c97af7b8e9553 Mon Sep 17 00:00:00 2001 From: Greg Edwards Date: Wed, 25 Jul 2018 10:22:58 -0400 Subject: block: move bio_integrity_{intervals,bytes} into blkdev.h This allows bio_integrity_bytes() to be called from drivers instead of open coding it. Acked-by: Martin K. Petersen Signed-off-by: Greg Edwards Signed-off-by: Jens Axboe --- block/bio-integrity.c | 22 ---------------------- include/linux/blkdev.h | 34 ++++++++++++++++++++++++++++++++++ 2 files changed, 34 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/block/bio-integrity.c b/block/bio-integrity.c index add7c7c85335..67b5fb861a51 100644 --- a/block/bio-integrity.c +++ b/block/bio-integrity.c @@ -159,28 +159,6 @@ int bio_integrity_add_page(struct bio *bio, struct page *page, } EXPORT_SYMBOL(bio_integrity_add_page); -/** - * bio_integrity_intervals - Return number of integrity intervals for a bio - * @bi: blk_integrity profile for device - * @sectors: Size of the bio in 512-byte sectors - * - * Description: The block layer calculates everything in 512 byte - * sectors but integrity metadata is done in terms of the data integrity - * interval size of the storage device. Convert the block layer sectors - * to the appropriate number of integrity intervals. - */ -static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi, - unsigned int sectors) -{ - return sectors >> (bi->interval_exp - 9); -} - -static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi, - unsigned int sectors) -{ - return bio_integrity_intervals(bi, sectors) * bi->tuple_size; -} - /** * bio_integrity_process - Process integrity metadata for a bio * @bio: bio to generate/verify integrity metadata for diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 331a6cb8805f..050d599f5ea9 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1865,6 +1865,28 @@ static inline bool integrity_req_gap_front_merge(struct request *req, bip_next->bip_vec[0].bv_offset); } +/** + * bio_integrity_intervals - Return number of integrity intervals for a bio + * @bi: blk_integrity profile for device + * @sectors: Size of the bio in 512-byte sectors + * + * Description: The block layer calculates everything in 512 byte + * sectors but integrity metadata is done in terms of the data integrity + * interval size of the storage device. Convert the block layer sectors + * to the appropriate number of integrity intervals. + */ +static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi, + unsigned int sectors) +{ + return sectors >> (bi->interval_exp - 9); +} + +static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi, + unsigned int sectors) +{ + return bio_integrity_intervals(bi, sectors) * bi->tuple_size; +} + #else /* CONFIG_BLK_DEV_INTEGRITY */ struct bio; @@ -1938,6 +1960,18 @@ static inline bool integrity_req_gap_front_merge(struct request *req, return false; } +static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi, + unsigned int sectors) +{ + return 0; +} + +static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi, + unsigned int sectors) +{ + return 0; +} + #endif /* CONFIG_BLK_DEV_INTEGRITY */ struct block_device_operations { -- cgit v1.2.3 From 8c3799ee25e1fda159099af09f5f2e86091e41d4 Mon Sep 17 00:00:00 2001 From: Oleksandr Andrushchenko Date: Fri, 20 Jul 2018 12:01:43 +0300 Subject: xen/grant-table: Make set/clear page private code shared Make set/clear page private code shared and accessible to other kernel modules which can re-use these instead of open-coding. Signed-off-by: Oleksandr Andrushchenko Reviewed-by: Boris Ostrovsky Signed-off-by: Boris Ostrovsky --- drivers/xen/grant-table.c | 54 ++++++++++++++++++++++++++++++----------------- include/xen/grant_table.h | 3 +++ 2 files changed, 38 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index ba9f3eec2bd0..bb4840653bf2 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -769,29 +769,18 @@ void gnttab_free_auto_xlat_frames(void) } EXPORT_SYMBOL_GPL(gnttab_free_auto_xlat_frames); -/** - * gnttab_alloc_pages - alloc pages suitable for grant mapping into - * @nr_pages: number of pages to alloc - * @pages: returns the pages - */ -int gnttab_alloc_pages(int nr_pages, struct page **pages) +int gnttab_pages_set_private(int nr_pages, struct page **pages) { int i; - int ret; - - ret = alloc_xenballooned_pages(nr_pages, pages); - if (ret < 0) - return ret; for (i = 0; i < nr_pages; i++) { #if BITS_PER_LONG < 64 struct xen_page_foreign *foreign; foreign = kzalloc(sizeof(*foreign), GFP_KERNEL); - if (!foreign) { - gnttab_free_pages(nr_pages, pages); + if (!foreign) return -ENOMEM; - } + set_page_private(pages[i], (unsigned long)foreign); #endif SetPagePrivate(pages[i]); @@ -799,14 +788,30 @@ int gnttab_alloc_pages(int nr_pages, struct page **pages) return 0; } -EXPORT_SYMBOL_GPL(gnttab_alloc_pages); +EXPORT_SYMBOL_GPL(gnttab_pages_set_private); /** - * gnttab_free_pages - free pages allocated by gnttab_alloc_pages() - * @nr_pages; number of pages to free - * @pages: the pages + * gnttab_alloc_pages - alloc pages suitable for grant mapping into + * @nr_pages: number of pages to alloc + * @pages: returns the pages */ -void gnttab_free_pages(int nr_pages, struct page **pages) +int gnttab_alloc_pages(int nr_pages, struct page **pages) +{ + int ret; + + ret = alloc_xenballooned_pages(nr_pages, pages); + if (ret < 0) + return ret; + + ret = gnttab_pages_set_private(nr_pages, pages); + if (ret < 0) + gnttab_free_pages(nr_pages, pages); + + return ret; +} +EXPORT_SYMBOL_GPL(gnttab_alloc_pages); + +void gnttab_pages_clear_private(int nr_pages, struct page **pages) { int i; @@ -818,6 +823,17 @@ void gnttab_free_pages(int nr_pages, struct page **pages) ClearPagePrivate(pages[i]); } } +} +EXPORT_SYMBOL_GPL(gnttab_pages_clear_private); + +/** + * gnttab_free_pages - free pages allocated by gnttab_alloc_pages() + * @nr_pages; number of pages to free + * @pages: the pages + */ +void gnttab_free_pages(int nr_pages, struct page **pages) +{ + gnttab_pages_clear_private(nr_pages, pages); free_xenballooned_pages(nr_pages, pages); } EXPORT_SYMBOL_GPL(gnttab_free_pages); diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h index 2e37741f6b8d..de03f2542bb7 100644 --- a/include/xen/grant_table.h +++ b/include/xen/grant_table.h @@ -198,6 +198,9 @@ void gnttab_free_auto_xlat_frames(void); int gnttab_alloc_pages(int nr_pages, struct page **pages); void gnttab_free_pages(int nr_pages, struct page **pages); +int gnttab_pages_set_private(int nr_pages, struct page **pages); +void gnttab_pages_clear_private(int nr_pages, struct page **pages); + int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops, struct gnttab_map_grant_ref *kmap_ops, struct page **pages, unsigned int count); -- cgit v1.2.3 From ae4c51a50c990d6feba7058c181dc8f22ca5f1d8 Mon Sep 17 00:00:00 2001 From: Oleksandr Andrushchenko Date: Fri, 20 Jul 2018 12:01:44 +0300 Subject: xen/balloon: Share common memory reservation routines Memory {increase|decrease}_reservation and VA mappings update/reset code used in balloon driver can be made common, so other drivers can also re-use the same functionality without open-coding. Create a dedicated file for the shared code and export corresponding symbols for other kernel modules. Signed-off-by: Oleksandr Andrushchenko Reviewed-by: Boris Ostrovsky Signed-off-by: Boris Ostrovsky --- drivers/xen/Makefile | 1 + drivers/xen/balloon.c | 75 +++------------------------ drivers/xen/mem-reservation.c | 118 ++++++++++++++++++++++++++++++++++++++++++ include/xen/mem-reservation.h | 59 +++++++++++++++++++++ 4 files changed, 184 insertions(+), 69 deletions(-) create mode 100644 drivers/xen/mem-reservation.c create mode 100644 include/xen/mem-reservation.h (limited to 'include') diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile index 48b154276179..129dd1cc1b83 100644 --- a/drivers/xen/Makefile +++ b/drivers/xen/Makefile @@ -2,6 +2,7 @@ obj-$(CONFIG_HOTPLUG_CPU) += cpu_hotplug.o obj-$(CONFIG_X86) += fallback.o obj-y += grant-table.o features.o balloon.o manage.o preempt.o time.o +obj-y += mem-reservation.o obj-y += events/ obj-y += xenbus/ diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index 065f0b607373..e12bb256036f 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -71,6 +71,7 @@ #include #include #include +#include static int xen_hotplug_unpopulated; @@ -157,13 +158,6 @@ static DECLARE_DELAYED_WORK(balloon_worker, balloon_process); #define GFP_BALLOON \ (GFP_HIGHUSER | __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC) -static void scrub_page(struct page *page) -{ -#ifdef CONFIG_XEN_SCRUB_PAGES - clear_highpage(page); -#endif -} - /* balloon_append: add the given page to the balloon. */ static void __balloon_append(struct page *page) { @@ -463,11 +457,6 @@ static enum bp_state increase_reservation(unsigned long nr_pages) int rc; unsigned long i; struct page *page; - struct xen_memory_reservation reservation = { - .address_bits = 0, - .extent_order = EXTENT_ORDER, - .domid = DOMID_SELF - }; if (nr_pages > ARRAY_SIZE(frame_list)) nr_pages = ARRAY_SIZE(frame_list); @@ -479,16 +468,11 @@ static enum bp_state increase_reservation(unsigned long nr_pages) break; } - /* XENMEM_populate_physmap requires a PFN based on Xen - * granularity. - */ frame_list[i] = page_to_xen_pfn(page); page = balloon_next_page(page); } - set_xen_guest_handle(reservation.extent_start, frame_list); - reservation.nr_extents = nr_pages; - rc = HYPERVISOR_memory_op(XENMEM_populate_physmap, &reservation); + rc = xenmem_reservation_increase(nr_pages, frame_list); if (rc <= 0) return BP_EAGAIN; @@ -496,29 +480,7 @@ static enum bp_state increase_reservation(unsigned long nr_pages) page = balloon_retrieve(false); BUG_ON(page == NULL); -#ifdef CONFIG_XEN_HAVE_PVMMU - /* - * We don't support PV MMU when Linux and Xen is using - * different page granularity. - */ - BUILD_BUG_ON(XEN_PAGE_SIZE != PAGE_SIZE); - - if (!xen_feature(XENFEAT_auto_translated_physmap)) { - unsigned long pfn = page_to_pfn(page); - - set_phys_to_machine(pfn, frame_list[i]); - - /* Link back into the page tables if not highmem. */ - if (!PageHighMem(page)) { - int ret; - ret = HYPERVISOR_update_va_mapping( - (unsigned long)__va(pfn << PAGE_SHIFT), - mfn_pte(frame_list[i], PAGE_KERNEL), - 0); - BUG_ON(ret); - } - } -#endif + xenmem_reservation_va_mapping_update(1, &page, &frame_list[i]); /* Relinquish the page back to the allocator. */ free_reserved_page(page); @@ -535,11 +497,6 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp) unsigned long i; struct page *page, *tmp; int ret; - struct xen_memory_reservation reservation = { - .address_bits = 0, - .extent_order = EXTENT_ORDER, - .domid = DOMID_SELF - }; LIST_HEAD(pages); if (nr_pages > ARRAY_SIZE(frame_list)) @@ -553,7 +510,7 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp) break; } adjust_managed_page_count(page, -1); - scrub_page(page); + xenmem_reservation_scrub_page(page); list_add(&page->lru, &pages); } @@ -572,28 +529,10 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp) */ i = 0; list_for_each_entry_safe(page, tmp, &pages, lru) { - /* XENMEM_decrease_reservation requires a GFN */ frame_list[i++] = xen_page_to_gfn(page); -#ifdef CONFIG_XEN_HAVE_PVMMU - /* - * We don't support PV MMU when Linux and Xen is using - * different page granularity. - */ - BUILD_BUG_ON(XEN_PAGE_SIZE != PAGE_SIZE); - - if (!xen_feature(XENFEAT_auto_translated_physmap)) { - unsigned long pfn = page_to_pfn(page); + xenmem_reservation_va_mapping_reset(1, &page); - if (!PageHighMem(page)) { - ret = HYPERVISOR_update_va_mapping( - (unsigned long)__va(pfn << PAGE_SHIFT), - __pte_ma(0), 0); - BUG_ON(ret); - } - __set_phys_to_machine(pfn, INVALID_P2M_ENTRY); - } -#endif list_del(&page->lru); balloon_append(page); @@ -601,9 +540,7 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp) flush_tlb_all(); - set_xen_guest_handle(reservation.extent_start, frame_list); - reservation.nr_extents = nr_pages; - ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation, &reservation); + ret = xenmem_reservation_decrease(nr_pages, frame_list); BUG_ON(ret != nr_pages); balloon_stats.current_pages -= nr_pages; diff --git a/drivers/xen/mem-reservation.c b/drivers/xen/mem-reservation.c new file mode 100644 index 000000000000..084799c6180e --- /dev/null +++ b/drivers/xen/mem-reservation.c @@ -0,0 +1,118 @@ +// SPDX-License-Identifier: GPL-2.0 + +/****************************************************************************** + * Xen memory reservation utilities. + * + * Copyright (c) 2003, B Dragovic + * Copyright (c) 2003-2004, M Williamson, K Fraser + * Copyright (c) 2005 Dan M. Smith, IBM Corporation + * Copyright (c) 2010 Daniel Kiper + * Copyright (c) 2018 Oleksandr Andrushchenko, EPAM Systems Inc. + */ + +#include + +#include +#include + +/* + * Use one extent per PAGE_SIZE to avoid to break down the page into + * multiple frame. + */ +#define EXTENT_ORDER (fls(XEN_PFN_PER_PAGE) - 1) + +#ifdef CONFIG_XEN_HAVE_PVMMU +void __xenmem_reservation_va_mapping_update(unsigned long count, + struct page **pages, + xen_pfn_t *frames) +{ + int i; + + for (i = 0; i < count; i++) { + struct page *page = pages[i]; + unsigned long pfn = page_to_pfn(page); + + BUG_ON(!page); + + /* + * We don't support PV MMU when Linux and Xen is using + * different page granularity. + */ + BUILD_BUG_ON(XEN_PAGE_SIZE != PAGE_SIZE); + + set_phys_to_machine(pfn, frames[i]); + + /* Link back into the page tables if not highmem. */ + if (!PageHighMem(page)) { + int ret; + + ret = HYPERVISOR_update_va_mapping( + (unsigned long)__va(pfn << PAGE_SHIFT), + mfn_pte(frames[i], PAGE_KERNEL), + 0); + BUG_ON(ret); + } + } +} +EXPORT_SYMBOL_GPL(__xenmem_reservation_va_mapping_update); + +void __xenmem_reservation_va_mapping_reset(unsigned long count, + struct page **pages) +{ + int i; + + for (i = 0; i < count; i++) { + struct page *page = pages[i]; + unsigned long pfn = page_to_pfn(page); + + /* + * We don't support PV MMU when Linux and Xen are using + * different page granularity. + */ + BUILD_BUG_ON(XEN_PAGE_SIZE != PAGE_SIZE); + + if (!PageHighMem(page)) { + int ret; + + ret = HYPERVISOR_update_va_mapping( + (unsigned long)__va(pfn << PAGE_SHIFT), + __pte_ma(0), 0); + BUG_ON(ret); + } + __set_phys_to_machine(pfn, INVALID_P2M_ENTRY); + } +} +EXPORT_SYMBOL_GPL(__xenmem_reservation_va_mapping_reset); +#endif /* CONFIG_XEN_HAVE_PVMMU */ + +/* @frames is an array of PFNs */ +int xenmem_reservation_increase(int count, xen_pfn_t *frames) +{ + struct xen_memory_reservation reservation = { + .address_bits = 0, + .extent_order = EXTENT_ORDER, + .domid = DOMID_SELF + }; + + /* XENMEM_populate_physmap requires a PFN based on Xen granularity. */ + set_xen_guest_handle(reservation.extent_start, frames); + reservation.nr_extents = count; + return HYPERVISOR_memory_op(XENMEM_populate_physmap, &reservation); +} +EXPORT_SYMBOL_GPL(xenmem_reservation_increase); + +/* @frames is an array of GFNs */ +int xenmem_reservation_decrease(int count, xen_pfn_t *frames) +{ + struct xen_memory_reservation reservation = { + .address_bits = 0, + .extent_order = EXTENT_ORDER, + .domid = DOMID_SELF + }; + + /* XENMEM_decrease_reservation requires a GFN */ + set_xen_guest_handle(reservation.extent_start, frames); + reservation.nr_extents = count; + return HYPERVISOR_memory_op(XENMEM_decrease_reservation, &reservation); +} +EXPORT_SYMBOL_GPL(xenmem_reservation_decrease); diff --git a/include/xen/mem-reservation.h b/include/xen/mem-reservation.h new file mode 100644 index 000000000000..80b52b4945e9 --- /dev/null +++ b/include/xen/mem-reservation.h @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Xen memory reservation utilities. + * + * Copyright (c) 2003, B Dragovic + * Copyright (c) 2003-2004, M Williamson, K Fraser + * Copyright (c) 2005 Dan M. Smith, IBM Corporation + * Copyright (c) 2010 Daniel Kiper + * Copyright (c) 2018 Oleksandr Andrushchenko, EPAM Systems Inc. + */ + +#ifndef _XENMEM_RESERVATION_H +#define _XENMEM_RESERVATION_H + +#include + +#include + +static inline void xenmem_reservation_scrub_page(struct page *page) +{ +#ifdef CONFIG_XEN_SCRUB_PAGES + clear_highpage(page); +#endif +} + +#ifdef CONFIG_XEN_HAVE_PVMMU +void __xenmem_reservation_va_mapping_update(unsigned long count, + struct page **pages, + xen_pfn_t *frames); + +void __xenmem_reservation_va_mapping_reset(unsigned long count, + struct page **pages); +#endif + +static inline void xenmem_reservation_va_mapping_update(unsigned long count, + struct page **pages, + xen_pfn_t *frames) +{ +#ifdef CONFIG_XEN_HAVE_PVMMU + if (!xen_feature(XENFEAT_auto_translated_physmap)) + __xenmem_reservation_va_mapping_update(count, pages, frames); +#endif +} + +static inline void xenmem_reservation_va_mapping_reset(unsigned long count, + struct page **pages) +{ +#ifdef CONFIG_XEN_HAVE_PVMMU + if (!xen_feature(XENFEAT_auto_translated_physmap)) + __xenmem_reservation_va_mapping_reset(count, pages); +#endif +} + +int xenmem_reservation_increase(int count, xen_pfn_t *frames); + +int xenmem_reservation_decrease(int count, xen_pfn_t *frames); + +#endif -- cgit v1.2.3 From 9bdc7304f536f3f77f0a69e7c3a8f5afda561a68 Mon Sep 17 00:00:00 2001 From: Oleksandr Andrushchenko Date: Fri, 20 Jul 2018 12:01:45 +0300 Subject: xen/grant-table: Allow allocating buffers suitable for DMA Extend grant table module API to allow allocating buffers that can be used for DMA operations and mapping foreign grant references on top of those. The resulting buffer is similar to the one allocated by the balloon driver in that proper memory reservation is made by ({increase|decrease}_reservation and VA mappings are updated if needed). This is useful for sharing foreign buffers with HW drivers which cannot work with scattered buffers provided by the balloon driver, but require DMAable memory instead. Signed-off-by: Oleksandr Andrushchenko Reviewed-by: Boris Ostrovsky Signed-off-by: Boris Ostrovsky --- drivers/xen/Kconfig | 14 +++++++ drivers/xen/grant-table.c | 97 +++++++++++++++++++++++++++++++++++++++++++++++ include/xen/grant_table.h | 18 +++++++++ 3 files changed, 129 insertions(+) (limited to 'include') diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig index e5d0c28372ea..75e5c40f80a5 100644 --- a/drivers/xen/Kconfig +++ b/drivers/xen/Kconfig @@ -161,6 +161,20 @@ config XEN_GRANT_DEV_ALLOC to other domains. This can be used to implement frontend drivers or as part of an inter-domain shared memory channel. +config XEN_GRANT_DMA_ALLOC + bool "Allow allocating DMA capable buffers with grant reference module" + depends on XEN && HAS_DMA + help + Extends grant table module API to allow allocating DMA capable + buffers and mapping foreign grant references on top of it. + The resulting buffer is similar to one allocated by the balloon + driver in that proper memory reservation is made by + ({increase|decrease}_reservation and VA mappings are updated if + needed). + This is useful for sharing foreign buffers with HW drivers which + cannot work with scattered buffers provided by the balloon driver, + but require DMAable memory instead. + config SWIOTLB_XEN def_bool y select SWIOTLB diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index bb4840653bf2..7bafa703a992 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -45,6 +45,9 @@ #include #include #include +#ifdef CONFIG_XEN_GRANT_DMA_ALLOC +#include +#endif #include #include @@ -57,6 +60,7 @@ #ifdef CONFIG_X86 #include #endif +#include #include #include @@ -838,6 +842,99 @@ void gnttab_free_pages(int nr_pages, struct page **pages) } EXPORT_SYMBOL_GPL(gnttab_free_pages); +#ifdef CONFIG_XEN_GRANT_DMA_ALLOC +/** + * gnttab_dma_alloc_pages - alloc DMAable pages suitable for grant mapping into + * @args: arguments to the function + */ +int gnttab_dma_alloc_pages(struct gnttab_dma_alloc_args *args) +{ + unsigned long pfn, start_pfn; + size_t size; + int i, ret; + + size = args->nr_pages << PAGE_SHIFT; + if (args->coherent) + args->vaddr = dma_alloc_coherent(args->dev, size, + &args->dev_bus_addr, + GFP_KERNEL | __GFP_NOWARN); + else + args->vaddr = dma_alloc_wc(args->dev, size, + &args->dev_bus_addr, + GFP_KERNEL | __GFP_NOWARN); + if (!args->vaddr) { + pr_debug("Failed to allocate DMA buffer of size %zu\n", size); + return -ENOMEM; + } + + start_pfn = __phys_to_pfn(args->dev_bus_addr); + for (pfn = start_pfn, i = 0; pfn < start_pfn + args->nr_pages; + pfn++, i++) { + struct page *page = pfn_to_page(pfn); + + args->pages[i] = page; + args->frames[i] = xen_page_to_gfn(page); + xenmem_reservation_scrub_page(page); + } + + xenmem_reservation_va_mapping_reset(args->nr_pages, args->pages); + + ret = xenmem_reservation_decrease(args->nr_pages, args->frames); + if (ret != args->nr_pages) { + pr_debug("Failed to decrease reservation for DMA buffer\n"); + ret = -EFAULT; + goto fail; + } + + ret = gnttab_pages_set_private(args->nr_pages, args->pages); + if (ret < 0) + goto fail; + + return 0; + +fail: + gnttab_dma_free_pages(args); + return ret; +} +EXPORT_SYMBOL_GPL(gnttab_dma_alloc_pages); + +/** + * gnttab_dma_free_pages - free DMAable pages + * @args: arguments to the function + */ +int gnttab_dma_free_pages(struct gnttab_dma_alloc_args *args) +{ + size_t size; + int i, ret; + + gnttab_pages_clear_private(args->nr_pages, args->pages); + + for (i = 0; i < args->nr_pages; i++) + args->frames[i] = page_to_xen_pfn(args->pages[i]); + + ret = xenmem_reservation_increase(args->nr_pages, args->frames); + if (ret != args->nr_pages) { + pr_debug("Failed to decrease reservation for DMA buffer\n"); + ret = -EFAULT; + } else { + ret = 0; + } + + xenmem_reservation_va_mapping_update(args->nr_pages, args->pages, + args->frames); + + size = args->nr_pages << PAGE_SHIFT; + if (args->coherent) + dma_free_coherent(args->dev, size, + args->vaddr, args->dev_bus_addr); + else + dma_free_wc(args->dev, size, + args->vaddr, args->dev_bus_addr); + return ret; +} +EXPORT_SYMBOL_GPL(gnttab_dma_free_pages); +#endif + /* Handling of paged out grant targets (GNTST_eagain) */ #define MAX_DELAY 256 static inline void diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h index de03f2542bb7..9bc5bc07d4d3 100644 --- a/include/xen/grant_table.h +++ b/include/xen/grant_table.h @@ -198,6 +198,24 @@ void gnttab_free_auto_xlat_frames(void); int gnttab_alloc_pages(int nr_pages, struct page **pages); void gnttab_free_pages(int nr_pages, struct page **pages); +#ifdef CONFIG_XEN_GRANT_DMA_ALLOC +struct gnttab_dma_alloc_args { + /* Device for which DMA memory will be/was allocated. */ + struct device *dev; + /* If set then DMA buffer is coherent and write-combine otherwise. */ + bool coherent; + + int nr_pages; + struct page **pages; + xen_pfn_t *frames; + void *vaddr; + dma_addr_t dev_bus_addr; +}; + +int gnttab_dma_alloc_pages(struct gnttab_dma_alloc_args *args); +int gnttab_dma_free_pages(struct gnttab_dma_alloc_args *args); +#endif + int gnttab_pages_set_private(int nr_pages, struct page **pages); void gnttab_pages_clear_private(int nr_pages, struct page **pages); -- cgit v1.2.3 From 975ef7ff81bb000af6e6c8e63e81f89f3468dcf7 Mon Sep 17 00:00:00 2001 From: Oleksandr Andrushchenko Date: Fri, 20 Jul 2018 12:01:46 +0300 Subject: xen/gntdev: Allow mappings for DMA buffers Allow mappings for DMA backed buffers if grant table module supports such: this extends grant device to not only map buffers made of balloon pages, but also from buffers allocated with dma_alloc_xxx. Signed-off-by: Oleksandr Andrushchenko Reviewed-by: Boris Ostrovsky Signed-off-by: Boris Ostrovsky --- drivers/xen/gntdev.c | 99 ++++++++++++++++++++++++++++++++++++++++++++++- include/uapi/xen/gntdev.h | 15 +++++++ 2 files changed, 112 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c index bd56653b9bbc..173332f439d8 100644 --- a/drivers/xen/gntdev.c +++ b/drivers/xen/gntdev.c @@ -37,6 +37,9 @@ #include #include #include +#ifdef CONFIG_XEN_GRANT_DMA_ALLOC +#include +#endif #include #include @@ -72,6 +75,11 @@ struct gntdev_priv { struct mutex lock; struct mm_struct *mm; struct mmu_notifier mn; + +#ifdef CONFIG_XEN_GRANT_DMA_ALLOC + /* Device for which DMA memory is allocated. */ + struct device *dma_dev; +#endif }; struct unmap_notify { @@ -96,10 +104,27 @@ struct grant_map { struct gnttab_unmap_grant_ref *kunmap_ops; struct page **pages; unsigned long pages_vm_start; + +#ifdef CONFIG_XEN_GRANT_DMA_ALLOC + /* + * If dmabuf_vaddr is not NULL then this mapping is backed by DMA + * capable memory. + */ + + struct device *dma_dev; + /* Flags used to create this DMA buffer: GNTDEV_DMA_FLAG_XXX. */ + int dma_flags; + void *dma_vaddr; + dma_addr_t dma_bus_addr; + /* Needed to avoid allocation in gnttab_dma_free_pages(). */ + xen_pfn_t *frames; +#endif }; static int unmap_grant_pages(struct grant_map *map, int offset, int pages); +static struct miscdevice gntdev_miscdev; + /* ------------------------------------------------------------------ */ static void gntdev_print_maps(struct gntdev_priv *priv, @@ -121,8 +146,27 @@ static void gntdev_free_map(struct grant_map *map) if (map == NULL) return; +#ifdef CONFIG_XEN_GRANT_DMA_ALLOC + if (map->dma_vaddr) { + struct gnttab_dma_alloc_args args; + + args.dev = map->dma_dev; + args.coherent = !!(map->dma_flags & GNTDEV_DMA_FLAG_COHERENT); + args.nr_pages = map->count; + args.pages = map->pages; + args.frames = map->frames; + args.vaddr = map->dma_vaddr; + args.dev_bus_addr = map->dma_bus_addr; + + gnttab_dma_free_pages(&args); + } else +#endif if (map->pages) gnttab_free_pages(map->count, map->pages); + +#ifdef CONFIG_XEN_GRANT_DMA_ALLOC + kfree(map->frames); +#endif kfree(map->pages); kfree(map->grants); kfree(map->map_ops); @@ -132,7 +176,8 @@ static void gntdev_free_map(struct grant_map *map) kfree(map); } -static struct grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count) +static struct grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count, + int dma_flags) { struct grant_map *add; int i; @@ -155,6 +200,37 @@ static struct grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count) NULL == add->pages) goto err; +#ifdef CONFIG_XEN_GRANT_DMA_ALLOC + add->dma_flags = dma_flags; + + /* + * Check if this mapping is requested to be backed + * by a DMA buffer. + */ + if (dma_flags & (GNTDEV_DMA_FLAG_WC | GNTDEV_DMA_FLAG_COHERENT)) { + struct gnttab_dma_alloc_args args; + + add->frames = kcalloc(count, sizeof(add->frames[0]), + GFP_KERNEL); + if (!add->frames) + goto err; + + /* Remember the device, so we can free DMA memory. */ + add->dma_dev = priv->dma_dev; + + args.dev = priv->dma_dev; + args.coherent = !!(dma_flags & GNTDEV_DMA_FLAG_COHERENT); + args.nr_pages = count; + args.pages = add->pages; + args.frames = add->frames; + + if (gnttab_dma_alloc_pages(&args)) + goto err; + + add->dma_vaddr = args.vaddr; + add->dma_bus_addr = args.dev_bus_addr; + } else +#endif if (gnttab_alloc_pages(count, add->pages)) goto err; @@ -325,6 +401,14 @@ static int map_grant_pages(struct grant_map *map) map->unmap_ops[i].handle = map->map_ops[i].handle; if (use_ptemod) map->kunmap_ops[i].handle = map->kmap_ops[i].handle; +#ifdef CONFIG_XEN_GRANT_DMA_ALLOC + else if (map->dma_vaddr) { + unsigned long bfn; + + bfn = pfn_to_bfn(page_to_pfn(map->pages[i])); + map->unmap_ops[i].dev_bus_addr = __pfn_to_phys(bfn); + } +#endif } return err; } @@ -548,6 +632,17 @@ static int gntdev_open(struct inode *inode, struct file *flip) } flip->private_data = priv; +#ifdef CONFIG_XEN_GRANT_DMA_ALLOC + priv->dma_dev = gntdev_miscdev.this_device; + + /* + * The device is not spawn from a device tree, so arch_setup_dma_ops + * is not called, thus leaving the device with dummy DMA ops. + * Fix this by calling of_dma_configure() with a NULL node to set + * default DMA ops. + */ + of_dma_configure(priv->dma_dev, NULL, true); +#endif pr_debug("priv %p\n", priv); return 0; @@ -589,7 +684,7 @@ static long gntdev_ioctl_map_grant_ref(struct gntdev_priv *priv, return -EINVAL; err = -ENOMEM; - map = gntdev_alloc_map(priv, op.count); + map = gntdev_alloc_map(priv, op.count, 0 /* This is not a dma-buf. */); if (!map) return err; diff --git a/include/uapi/xen/gntdev.h b/include/uapi/xen/gntdev.h index 6d1163456c03..4b9d498a31d4 100644 --- a/include/uapi/xen/gntdev.h +++ b/include/uapi/xen/gntdev.h @@ -200,4 +200,19 @@ struct ioctl_gntdev_grant_copy { /* Send an interrupt on the indicated event channel */ #define UNMAP_NOTIFY_SEND_EVENT 0x2 +/* + * Flags to be used while requesting memory mapping's backing storage + * to be allocated with DMA API. + */ + +/* + * The buffer is backed with memory allocated with dma_alloc_wc. + */ +#define GNTDEV_DMA_FLAG_WC (1 << 0) + +/* + * The buffer is backed with memory allocated with dma_alloc_coherent. + */ +#define GNTDEV_DMA_FLAG_COHERENT (1 << 1) + #endif /* __LINUX_PUBLIC_GNTDEV_H__ */ -- cgit v1.2.3 From 932d6562179efe8e2460a0343dbe0fcacf288a9e Mon Sep 17 00:00:00 2001 From: Oleksandr Andrushchenko Date: Fri, 20 Jul 2018 12:01:48 +0300 Subject: xen/gntdev: Add initial support for dma-buf UAPI Add UAPI and IOCTLs for dma-buf grant device driver extension: the extension allows userspace processes and kernel modules to use Xen backed dma-buf implementation. With this extension grant references to the pages of an imported dma-buf can be exported for other domain use and grant references coming from a foreign domain can be converted into a local dma-buf for local export. Implement basic initialization and stubs for Xen DMA buffers' support. Signed-off-by: Oleksandr Andrushchenko Reviewed-by: Boris Ostrovsky Signed-off-by: Boris Ostrovsky --- drivers/xen/Kconfig | 10 +++ drivers/xen/Makefile | 1 + drivers/xen/gntdev-common.h | 6 ++ drivers/xen/gntdev-dmabuf.c | 177 ++++++++++++++++++++++++++++++++++++++++++++ drivers/xen/gntdev-dmabuf.h | 33 +++++++++ drivers/xen/gntdev.c | 31 ++++++++ include/uapi/xen/gntdev.h | 91 +++++++++++++++++++++++ 7 files changed, 349 insertions(+) create mode 100644 drivers/xen/gntdev-dmabuf.c create mode 100644 drivers/xen/gntdev-dmabuf.h (limited to 'include') diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig index 75e5c40f80a5..b459edfacff3 100644 --- a/drivers/xen/Kconfig +++ b/drivers/xen/Kconfig @@ -152,6 +152,16 @@ config XEN_GNTDEV help Allows userspace processes to use grants. +config XEN_GNTDEV_DMABUF + bool "Add support for dma-buf grant access device driver extension" + depends on XEN_GNTDEV && XEN_GRANT_DMA_ALLOC && DMA_SHARED_BUFFER + help + Allows userspace processes and kernel modules to use Xen backed + dma-buf implementation. With this extension grant references to + the pages of an imported dma-buf can be exported for other domain + use and grant references coming from a foreign domain can be + converted into a local dma-buf for local export. + config XEN_GRANT_DEV_ALLOC tristate "User-space grant reference allocator driver" depends on XEN diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile index 129dd1cc1b83..3e542f60f29f 100644 --- a/drivers/xen/Makefile +++ b/drivers/xen/Makefile @@ -41,5 +41,6 @@ obj-$(CONFIG_XEN_PVCALLS_BACKEND) += pvcalls-back.o obj-$(CONFIG_XEN_PVCALLS_FRONTEND) += pvcalls-front.o xen-evtchn-y := evtchn.o xen-gntdev-y := gntdev.o +xen-gntdev-$(CONFIG_XEN_GNTDEV_DMABUF) += gntdev-dmabuf.o xen-gntalloc-y := gntalloc.o xen-privcmd-y := privcmd.o privcmd-buf.o diff --git a/drivers/xen/gntdev-common.h b/drivers/xen/gntdev-common.h index 2346c198f72e..2f8b949c3eeb 100644 --- a/drivers/xen/gntdev-common.h +++ b/drivers/xen/gntdev-common.h @@ -16,6 +16,8 @@ #include #include +struct gntdev_dmabuf_priv; + struct gntdev_priv { /* Maps with visible offsets in the file descriptor. */ struct list_head maps; @@ -33,6 +35,10 @@ struct gntdev_priv { /* Device for which DMA memory is allocated. */ struct device *dma_dev; #endif + +#ifdef CONFIG_XEN_GNTDEV_DMABUF + struct gntdev_dmabuf_priv *dmabuf_priv; +#endif }; struct gntdev_unmap_notify { diff --git a/drivers/xen/gntdev-dmabuf.c b/drivers/xen/gntdev-dmabuf.c new file mode 100644 index 000000000000..af782c0a8a19 --- /dev/null +++ b/drivers/xen/gntdev-dmabuf.c @@ -0,0 +1,177 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Xen dma-buf functionality for gntdev. + * + * Copyright (c) 2018 Oleksandr Andrushchenko, EPAM Systems Inc. + */ + +#include +#include +#include +#include +#include + +#include +#include + +#include "gntdev-common.h" +#include "gntdev-dmabuf.h" + +struct gntdev_dmabuf_priv { + /* List of exported DMA buffers. */ + struct list_head exp_list; + /* List of wait objects. */ + struct list_head exp_wait_list; + /* This is the lock which protects dma_buf_xxx lists. */ + struct mutex lock; +}; + +/* DMA buffer export support. */ + +/* Implementation of wait for exported DMA buffer to be released. */ + +static int dmabuf_exp_wait_released(struct gntdev_dmabuf_priv *priv, int fd, + int wait_to_ms) +{ + return -EINVAL; +} + +static int dmabuf_exp_from_refs(struct gntdev_priv *priv, int flags, + int count, u32 domid, u32 *refs, u32 *fd) +{ + *fd = -1; + return -EINVAL; +} + +/* DMA buffer import support. */ + +static struct gntdev_dmabuf * +dmabuf_imp_to_refs(struct gntdev_dmabuf_priv *priv, struct device *dev, + int fd, int count, int domid) +{ + return ERR_PTR(-ENOMEM); +} + +static u32 *dmabuf_imp_get_refs(struct gntdev_dmabuf *gntdev_dmabuf) +{ + return NULL; +} + +static int dmabuf_imp_release(struct gntdev_dmabuf_priv *priv, u32 fd) +{ + return -EINVAL; +} + +/* DMA buffer IOCTL support. */ + +long gntdev_ioctl_dmabuf_exp_from_refs(struct gntdev_priv *priv, int use_ptemod, + struct ioctl_gntdev_dmabuf_exp_from_refs __user *u) +{ + struct ioctl_gntdev_dmabuf_exp_from_refs op; + u32 *refs; + long ret; + + if (use_ptemod) { + pr_debug("Cannot provide dma-buf: use_ptemode %d\n", + use_ptemod); + return -EINVAL; + } + + if (copy_from_user(&op, u, sizeof(op)) != 0) + return -EFAULT; + + if (unlikely(op.count <= 0)) + return -EINVAL; + + refs = kcalloc(op.count, sizeof(*refs), GFP_KERNEL); + if (!refs) + return -ENOMEM; + + if (copy_from_user(refs, u->refs, sizeof(*refs) * op.count) != 0) { + ret = -EFAULT; + goto out; + } + + ret = dmabuf_exp_from_refs(priv, op.flags, op.count, + op.domid, refs, &op.fd); + if (ret) + goto out; + + if (copy_to_user(u, &op, sizeof(op)) != 0) + ret = -EFAULT; + +out: + kfree(refs); + return ret; +} + +long gntdev_ioctl_dmabuf_exp_wait_released(struct gntdev_priv *priv, + struct ioctl_gntdev_dmabuf_exp_wait_released __user *u) +{ + struct ioctl_gntdev_dmabuf_exp_wait_released op; + + if (copy_from_user(&op, u, sizeof(op)) != 0) + return -EFAULT; + + return dmabuf_exp_wait_released(priv->dmabuf_priv, op.fd, + op.wait_to_ms); +} + +long gntdev_ioctl_dmabuf_imp_to_refs(struct gntdev_priv *priv, + struct ioctl_gntdev_dmabuf_imp_to_refs __user *u) +{ + struct ioctl_gntdev_dmabuf_imp_to_refs op; + struct gntdev_dmabuf *gntdev_dmabuf; + long ret; + + if (copy_from_user(&op, u, sizeof(op)) != 0) + return -EFAULT; + + if (unlikely(op.count <= 0)) + return -EINVAL; + + gntdev_dmabuf = dmabuf_imp_to_refs(priv->dmabuf_priv, + priv->dma_dev, op.fd, + op.count, op.domid); + if (IS_ERR(gntdev_dmabuf)) + return PTR_ERR(gntdev_dmabuf); + + if (copy_to_user(u->refs, dmabuf_imp_get_refs(gntdev_dmabuf), + sizeof(*u->refs) * op.count) != 0) { + ret = -EFAULT; + goto out_release; + } + return 0; + +out_release: + dmabuf_imp_release(priv->dmabuf_priv, op.fd); + return ret; +} + +long gntdev_ioctl_dmabuf_imp_release(struct gntdev_priv *priv, + struct ioctl_gntdev_dmabuf_imp_release __user *u) +{ + struct ioctl_gntdev_dmabuf_imp_release op; + + if (copy_from_user(&op, u, sizeof(op)) != 0) + return -EFAULT; + + return dmabuf_imp_release(priv->dmabuf_priv, op.fd); +} + +struct gntdev_dmabuf_priv *gntdev_dmabuf_init(void) +{ + struct gntdev_dmabuf_priv *priv; + + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) + return ERR_PTR(-ENOMEM); + + return priv; +} + +void gntdev_dmabuf_fini(struct gntdev_dmabuf_priv *priv) +{ + kfree(priv); +} diff --git a/drivers/xen/gntdev-dmabuf.h b/drivers/xen/gntdev-dmabuf.h new file mode 100644 index 000000000000..7220a53d0fc5 --- /dev/null +++ b/drivers/xen/gntdev-dmabuf.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Xen dma-buf functionality for gntdev. + * + * Copyright (c) 2018 Oleksandr Andrushchenko, EPAM Systems Inc. + */ + +#ifndef _GNTDEV_DMABUF_H +#define _GNTDEV_DMABUF_H + +#include + +struct gntdev_dmabuf_priv; +struct gntdev_priv; + +struct gntdev_dmabuf_priv *gntdev_dmabuf_init(void); + +void gntdev_dmabuf_fini(struct gntdev_dmabuf_priv *priv); + +long gntdev_ioctl_dmabuf_exp_from_refs(struct gntdev_priv *priv, int use_ptemod, + struct ioctl_gntdev_dmabuf_exp_from_refs __user *u); + +long gntdev_ioctl_dmabuf_exp_wait_released(struct gntdev_priv *priv, + struct ioctl_gntdev_dmabuf_exp_wait_released __user *u); + +long gntdev_ioctl_dmabuf_imp_to_refs(struct gntdev_priv *priv, + struct ioctl_gntdev_dmabuf_imp_to_refs __user *u); + +long gntdev_ioctl_dmabuf_imp_release(struct gntdev_priv *priv, + struct ioctl_gntdev_dmabuf_imp_release __user *u); + +#endif diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c index e03f50052f3e..c866a62f766d 100644 --- a/drivers/xen/gntdev.c +++ b/drivers/xen/gntdev.c @@ -48,6 +48,9 @@ #include #include "gntdev-common.h" +#ifdef CONFIG_XEN_GNTDEV_DMABUF +#include "gntdev-dmabuf.h" +#endif MODULE_LICENSE("GPL"); MODULE_AUTHOR("Derek G. Murray , " @@ -566,6 +569,15 @@ static int gntdev_open(struct inode *inode, struct file *flip) INIT_LIST_HEAD(&priv->freeable_maps); mutex_init(&priv->lock); +#ifdef CONFIG_XEN_GNTDEV_DMABUF + priv->dmabuf_priv = gntdev_dmabuf_init(); + if (IS_ERR(priv->dmabuf_priv)) { + ret = PTR_ERR(priv->dmabuf_priv); + kfree(priv); + return ret; + } +#endif + if (use_ptemod) { priv->mm = get_task_mm(current); if (!priv->mm) { @@ -616,8 +628,13 @@ static int gntdev_release(struct inode *inode, struct file *flip) WARN_ON(!list_empty(&priv->freeable_maps)); mutex_unlock(&priv->lock); +#ifdef CONFIG_XEN_GNTDEV_DMABUF + gntdev_dmabuf_fini(priv->dmabuf_priv); +#endif + if (use_ptemod) mmu_notifier_unregister(&priv->mn, priv->mm); + kfree(priv); return 0; } @@ -1009,6 +1026,20 @@ static long gntdev_ioctl(struct file *flip, case IOCTL_GNTDEV_GRANT_COPY: return gntdev_ioctl_grant_copy(priv, ptr); +#ifdef CONFIG_XEN_GNTDEV_DMABUF + case IOCTL_GNTDEV_DMABUF_EXP_FROM_REFS: + return gntdev_ioctl_dmabuf_exp_from_refs(priv, use_ptemod, ptr); + + case IOCTL_GNTDEV_DMABUF_EXP_WAIT_RELEASED: + return gntdev_ioctl_dmabuf_exp_wait_released(priv, ptr); + + case IOCTL_GNTDEV_DMABUF_IMP_TO_REFS: + return gntdev_ioctl_dmabuf_imp_to_refs(priv, ptr); + + case IOCTL_GNTDEV_DMABUF_IMP_RELEASE: + return gntdev_ioctl_dmabuf_imp_release(priv, ptr); +#endif + default: pr_debug("priv %p, unknown cmd %x\n", priv, cmd); return -ENOIOCTLCMD; diff --git a/include/uapi/xen/gntdev.h b/include/uapi/xen/gntdev.h index 4b9d498a31d4..fe4423e518c6 100644 --- a/include/uapi/xen/gntdev.h +++ b/include/uapi/xen/gntdev.h @@ -5,6 +5,7 @@ * Interface to /dev/xen/gntdev. * * Copyright (c) 2007, D G Murray + * Copyright (c) 2018, Oleksandr Andrushchenko, EPAM Systems Inc. * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License version 2 @@ -215,4 +216,94 @@ struct ioctl_gntdev_grant_copy { */ #define GNTDEV_DMA_FLAG_COHERENT (1 << 1) +/* + * Create a dma-buf [1] from grant references @refs of count @count provided + * by the foreign domain @domid with flags @flags. + * + * By default dma-buf is backed by system memory pages, but by providing + * one of the GNTDEV_DMA_FLAG_XXX flags it can also be created as + * a DMA write-combine or coherent buffer, e.g. allocated with dma_alloc_wc/ + * dma_alloc_coherent. + * + * Returns 0 if dma-buf was successfully created and the corresponding + * dma-buf's file descriptor is returned in @fd. + * + * [1] Documentation/driver-api/dma-buf.rst + */ + +#define IOCTL_GNTDEV_DMABUF_EXP_FROM_REFS \ + _IOC(_IOC_NONE, 'G', 9, \ + sizeof(struct ioctl_gntdev_dmabuf_exp_from_refs)) +struct ioctl_gntdev_dmabuf_exp_from_refs { + /* IN parameters. */ + /* Specific options for this dma-buf: see GNTDEV_DMA_FLAG_XXX. */ + __u32 flags; + /* Number of grant references in @refs array. */ + __u32 count; + /* OUT parameters. */ + /* File descriptor of the dma-buf. */ + __u32 fd; + /* The domain ID of the grant references to be mapped. */ + __u32 domid; + /* Variable IN parameter. */ + /* Array of grant references of size @count. */ + __u32 refs[1]; +}; + +/* + * This will block until the dma-buf with the file descriptor @fd is + * released. This is only valid for buffers created with + * IOCTL_GNTDEV_DMABUF_EXP_FROM_REFS. + * + * If within @wait_to_ms milliseconds the buffer is not released + * then -ETIMEDOUT error is returned. + * If the buffer with the file descriptor @fd does not exist or has already + * been released, then -ENOENT is returned. For valid file descriptors + * this must not be treated as error. + */ +#define IOCTL_GNTDEV_DMABUF_EXP_WAIT_RELEASED \ + _IOC(_IOC_NONE, 'G', 10, \ + sizeof(struct ioctl_gntdev_dmabuf_exp_wait_released)) +struct ioctl_gntdev_dmabuf_exp_wait_released { + /* IN parameters */ + __u32 fd; + __u32 wait_to_ms; +}; + +/* + * Import a dma-buf with file descriptor @fd and export granted references + * to the pages of that dma-buf into array @refs of size @count. + */ +#define IOCTL_GNTDEV_DMABUF_IMP_TO_REFS \ + _IOC(_IOC_NONE, 'G', 11, \ + sizeof(struct ioctl_gntdev_dmabuf_imp_to_refs)) +struct ioctl_gntdev_dmabuf_imp_to_refs { + /* IN parameters. */ + /* File descriptor of the dma-buf. */ + __u32 fd; + /* Number of grant references in @refs array. */ + __u32 count; + /* The domain ID for which references to be granted. */ + __u32 domid; + /* Reserved - must be zero. */ + __u32 reserved; + /* OUT parameters. */ + /* Array of grant references of size @count. */ + __u32 refs[1]; +}; + +/* + * This will close all references to the imported buffer with file descriptor + * @fd, so it can be released by the owner. This is only valid for buffers + * created with IOCTL_GNTDEV_DMABUF_IMP_TO_REFS. + */ +#define IOCTL_GNTDEV_DMABUF_IMP_RELEASE \ + _IOC(_IOC_NONE, 'G', 12, \ + sizeof(struct ioctl_gntdev_dmabuf_imp_release)) +struct ioctl_gntdev_dmabuf_imp_release { + /* IN parameters */ + __u32 fd; + __u32 reserved; +}; + #endif /* __LINUX_PUBLIC_GNTDEV_H__ */ -- cgit v1.2.3 From a6ea5fe95ab4a1a7af6d57429fe3ecde9acf5b5a Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 25 Jul 2018 23:19:36 +0200 Subject: ALSA: hda: Fix implicit PCM format type conversion The PCM format type is defined with __bitwise, hence it can't be passed as integer but needs an explicit cast. In this patch, instead of the messy cast flood, define the format argument of snd_hdac_calc_stream_format() to be the proper snd_pcm_format_t type. This fixes sparse warnings like: sound/hda/hdac_device.c:760:38: warning: incorrect type in argument 1 (different base types) Signed-off-by: Takashi Iwai --- include/sound/hdaudio.h | 3 ++- sound/hda/hdac_device.c | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/sound/hdaudio.h b/include/sound/hdaudio.h index 8305e7971035..6f1e1f3b3063 100644 --- a/include/sound/hdaudio.h +++ b/include/sound/hdaudio.h @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -133,7 +134,7 @@ int snd_hdac_get_sub_nodes(struct hdac_device *codec, hda_nid_t nid, hda_nid_t *start_id); unsigned int snd_hdac_calc_stream_format(unsigned int rate, unsigned int channels, - unsigned int format, + snd_pcm_format_t format, unsigned int maxbps, unsigned short spdif_ctls); int snd_hdac_query_supported_pcm(struct hdac_device *codec, hda_nid_t nid, diff --git a/sound/hda/hdac_device.c b/sound/hda/hdac_device.c index 7ba100bb1c3f..dbf02a3a8d2f 100644 --- a/sound/hda/hdac_device.c +++ b/sound/hda/hdac_device.c @@ -738,7 +738,7 @@ static struct hda_rate_tbl rate_bits[] = { */ unsigned int snd_hdac_calc_stream_format(unsigned int rate, unsigned int channels, - unsigned int format, + snd_pcm_format_t format, unsigned int maxbps, unsigned short spdif_ctls) { -- cgit v1.2.3 From e5d3765b6c4cb3ba64295a4205a2f68a4e8fe083 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 25 Jul 2018 23:19:44 +0200 Subject: ALSA: sb: Fix sparse warning wrt PCM format type The PCM format type is with __bitwise, and it can't be converted from integer implicitly. Instead of an ugly cast, declare the function argument of snd_sb_csp_autoload() with the proper snd_pcm_format_t type. This fixes the sparse warnings like: sound/isa/sb/sb16_csp.c:743:22: warning: restricted snd_pcm_format_t degrades to integer Signed-off-by: Takashi Iwai --- include/sound/sb16_csp.h | 2 +- sound/isa/sb/sb16_csp.c | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/sound/sb16_csp.h b/include/sound/sb16_csp.h index c7c7788005e4..7817e88bd08d 100644 --- a/include/sound/sb16_csp.h +++ b/include/sound/sb16_csp.h @@ -46,7 +46,7 @@ enum { struct snd_sb_csp_ops { int (*csp_use) (struct snd_sb_csp * p); int (*csp_unuse) (struct snd_sb_csp * p); - int (*csp_autoload) (struct snd_sb_csp * p, int pcm_sfmt, int play_rec_mode); + int (*csp_autoload) (struct snd_sb_csp * p, snd_pcm_format_t pcm_sfmt, int play_rec_mode); int (*csp_start) (struct snd_sb_csp * p, int sample_width, int channels); int (*csp_stop) (struct snd_sb_csp * p); int (*csp_qsound_transfer) (struct snd_sb_csp * p); diff --git a/sound/isa/sb/sb16_csp.c b/sound/isa/sb/sb16_csp.c index fa5780bb0c68..2210e7c72787 100644 --- a/sound/isa/sb/sb16_csp.c +++ b/sound/isa/sb/sb16_csp.c @@ -93,7 +93,7 @@ static int snd_sb_csp_riff_load(struct snd_sb_csp * p, struct snd_sb_csp_microcode __user * code); static int snd_sb_csp_unload(struct snd_sb_csp * p); static int snd_sb_csp_load_user(struct snd_sb_csp * p, const unsigned char __user *buf, int size, int load_flags); -static int snd_sb_csp_autoload(struct snd_sb_csp * p, int pcm_sfmt, int play_rec_mode); +static int snd_sb_csp_autoload(struct snd_sb_csp * p, snd_pcm_format_t pcm_sfmt, int play_rec_mode); static int snd_sb_csp_check_version(struct snd_sb_csp * p); static int snd_sb_csp_use(struct snd_sb_csp * p); @@ -726,7 +726,7 @@ static int snd_sb_csp_firmware_load(struct snd_sb_csp *p, int index, int flags) * autoload hardware codec if necessary * return 0 if CSP is loaded and ready to run (p->running != 0) */ -static int snd_sb_csp_autoload(struct snd_sb_csp * p, int pcm_sfmt, int play_rec_mode) +static int snd_sb_csp_autoload(struct snd_sb_csp * p, snd_pcm_format_t pcm_sfmt, int play_rec_mode) { unsigned long flags; int err = 0; @@ -736,7 +736,7 @@ static int snd_sb_csp_autoload(struct snd_sb_csp * p, int pcm_sfmt, int play_rec return -EBUSY; /* autoload microcode only if requested hardware codec is not already loaded */ - if (((1 << pcm_sfmt) & p->acc_format) && (play_rec_mode & p->mode)) { + if (((1U << (__force int)pcm_sfmt) & p->acc_format) && (play_rec_mode & p->mode)) { p->running = SNDRV_SB_CSP_ST_AUTO; } else { switch (pcm_sfmt) { -- cgit v1.2.3 From 3570a00841fb8a5d2f56ac7c59ccc6c91ea35944 Mon Sep 17 00:00:00 2001 From: Dan Murphy Date: Tue, 29 May 2018 15:26:12 -0500 Subject: can: uapi: can.h: Fix can error class mask dir path The CAN error masks header file is in the include/uapi directory. Fix the path in the header to the correct location. Signed-off-by: Dan Murphy Signed-off-by: Marc Kleine-Budde --- include/uapi/linux/can.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/can.h b/include/uapi/linux/can.h index d7f97ac197a9..0afb7d8e867f 100644 --- a/include/uapi/linux/can.h +++ b/include/uapi/linux/can.h @@ -77,7 +77,7 @@ typedef __u32 canid_t; /* * Controller Area Network Error Message Frame Mask structure * - * bit 0-28 : error class mask (see include/linux/can/error.h) + * bit 0-28 : error class mask (see include/uapi/linux/can/error.h) * bit 29-31 : set to zero */ typedef __u32 can_err_mask_t; -- cgit v1.2.3 From 038709071328ff68a936c6b8c33a24a805eea3c5 Mon Sep 17 00:00:00 2001 From: Zhu Yi Date: Wed, 13 Jun 2018 16:37:17 +0200 Subject: can: dev: enable multi-queue for SocketCAN devices The existing SocketCAN implementation provides alloc_candev() to allocate a CAN device using a single Tx and Rx queue. This can lead to priority inversion in case the single Tx queue is already full with low priority messages and a high priority message needs to be sent while the bus is fully loaded with medium priority messages. This problem can be solved by using the existing multi-queue support of the network subsytem. The commit makes it possible to use multi-queue in the CAN subsystem in the same way it is used in the Ethernet subsystem by adding an alloc_candev_mqs() call and accompanying macros. With this support a CAN device can use multi-queue qdisc (e.g. mqprio) to avoid the aforementioned priority inversion. The exisiting functionality of alloc_candev() is the same as before. CAN devices need to have prioritized multiple hardware queues or are able to abort waiting for arbitration to make sensible use of multi-queues. Signed-off-by: Zhu Yi Signed-off-by: Mark Jonas Reviewed-by: Heiko Schocher Signed-off-by: Marc Kleine-Budde --- drivers/net/can/dev.c | 8 +++++--- include/linux/can/dev.h | 7 ++++++- 2 files changed, 11 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c index 5bb6e8896601..49163570a63a 100644 --- a/drivers/net/can/dev.c +++ b/drivers/net/can/dev.c @@ -701,7 +701,8 @@ EXPORT_SYMBOL_GPL(alloc_can_err_skb); /* * Allocate and setup space for the CAN network device */ -struct net_device *alloc_candev(int sizeof_priv, unsigned int echo_skb_max) +struct net_device *alloc_candev_mqs(int sizeof_priv, unsigned int echo_skb_max, + unsigned int txqs, unsigned int rxqs) { struct net_device *dev; struct can_priv *priv; @@ -713,7 +714,8 @@ struct net_device *alloc_candev(int sizeof_priv, unsigned int echo_skb_max) else size = sizeof_priv; - dev = alloc_netdev(size, "can%d", NET_NAME_UNKNOWN, can_setup); + dev = alloc_netdev_mqs(size, "can%d", NET_NAME_UNKNOWN, can_setup, + txqs, rxqs); if (!dev) return NULL; @@ -732,7 +734,7 @@ struct net_device *alloc_candev(int sizeof_priv, unsigned int echo_skb_max) return dev; } -EXPORT_SYMBOL_GPL(alloc_candev); +EXPORT_SYMBOL_GPL(alloc_candev_mqs); /* * Free space of the CAN network device diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 055aaf5ed9af..a83e1f632eb7 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -143,7 +143,12 @@ u8 can_dlc2len(u8 can_dlc); /* map the sanitized data length to an appropriate data length code */ u8 can_len2dlc(u8 len); -struct net_device *alloc_candev(int sizeof_priv, unsigned int echo_skb_max); +struct net_device *alloc_candev_mqs(int sizeof_priv, unsigned int echo_skb_max, + unsigned int txqs, unsigned int rxqs); +#define alloc_candev(sizeof_priv, echo_skb_max) \ + alloc_candev_mqs(sizeof_priv, echo_skb_max, 1, 1) +#define alloc_candev_mq(sizeof_priv, echo_skb_max, count) \ + alloc_candev_mqs(sizeof_priv, echo_skb_max, count, count) void free_candev(struct net_device *dev); /* a candev safe wrapper around netdev_priv */ -- cgit v1.2.3 From e5225c820c057537dc780244760e2e24c7d27366 Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Thu, 26 Jul 2018 04:17:53 -0400 Subject: media: uvcvideo: Send a control event when a Control Change interrupt arrives UVC defines a method of handling asynchronous controls, which sends a USB packet over the interrupt pipe. This patch implements support for such packets by sending a control event to the user. Since this can involve USB traffic and, therefore, scheduling, this has to be done in a work queue. Signed-off-by: Guennadi Liakhovetski Signed-off-by: Laurent Pinchart Signed-off-by: Mauro Carvalho Chehab --- drivers/media/usb/uvc/uvc_ctrl.c | 211 ++++++++++++++++++++++++++++--------- drivers/media/usb/uvc/uvc_status.c | 121 ++++++++++++++++++--- drivers/media/usb/uvc/uvc_v4l2.c | 4 +- drivers/media/usb/uvc/uvcvideo.h | 15 ++- include/uapi/linux/uvcvideo.h | 2 + 5 files changed, 286 insertions(+), 67 deletions(-) (limited to 'include') diff --git a/drivers/media/usb/uvc/uvc_ctrl.c b/drivers/media/usb/uvc/uvc_ctrl.c index 12b5be66fd2f..c2ad102bd693 100644 --- a/drivers/media/usb/uvc/uvc_ctrl.c +++ b/drivers/media/usb/uvc/uvc_ctrl.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include @@ -971,12 +972,30 @@ static int uvc_ctrl_populate_cache(struct uvc_video_chain *chain, return 0; } +static s32 __uvc_ctrl_get_value(struct uvc_control_mapping *mapping, + const u8 *data) +{ + s32 value = mapping->get(mapping, UVC_GET_CUR, data); + + if (mapping->v4l2_type == V4L2_CTRL_TYPE_MENU) { + struct uvc_menu_info *menu = mapping->menu_info; + unsigned int i; + + for (i = 0; i < mapping->menu_count; ++i, ++menu) { + if (menu->value == value) { + value = i; + break; + } + } + } + + return value; +} + static int __uvc_ctrl_get(struct uvc_video_chain *chain, struct uvc_control *ctrl, struct uvc_control_mapping *mapping, s32 *value) { - struct uvc_menu_info *menu; - unsigned int i; int ret; if ((ctrl->info.flags & UVC_CTRL_FLAG_GET_CUR) == 0) @@ -993,18 +1012,8 @@ static int __uvc_ctrl_get(struct uvc_video_chain *chain, ctrl->loaded = 1; } - *value = mapping->get(mapping, UVC_GET_CUR, - uvc_ctrl_data(ctrl, UVC_CTRL_DATA_CURRENT)); - - if (mapping->v4l2_type == V4L2_CTRL_TYPE_MENU) { - menu = mapping->menu_info; - for (i = 0; i < mapping->menu_count; ++i, ++menu) { - if (menu->value == *value) { - *value = i; - break; - } - } - } + *value = __uvc_ctrl_get_value(mapping, + uvc_ctrl_data(ctrl, UVC_CTRL_DATA_CURRENT)); return 0; } @@ -1216,53 +1225,135 @@ static void uvc_ctrl_fill_event(struct uvc_video_chain *chain, ev->u.ctrl.default_value = v4l2_ctrl.default_value; } -static void uvc_ctrl_send_event(struct uvc_fh *handle, - struct uvc_control *ctrl, struct uvc_control_mapping *mapping, - s32 value, u32 changes) +/* + * Send control change events to all subscribers for the @ctrl control. By + * default the subscriber that generated the event, as identified by @handle, + * is not notified unless it has set the V4L2_EVENT_SUB_FL_ALLOW_FEEDBACK flag. + * @handle can be NULL for asynchronous events related to auto-update controls, + * in which case all subscribers are notified. + */ +static void uvc_ctrl_send_event(struct uvc_video_chain *chain, + struct uvc_fh *handle, struct uvc_control *ctrl, + struct uvc_control_mapping *mapping, s32 value, u32 changes) { + struct v4l2_fh *originator = handle ? &handle->vfh : NULL; struct v4l2_subscribed_event *sev; struct v4l2_event ev; if (list_empty(&mapping->ev_subs)) return; - uvc_ctrl_fill_event(handle->chain, &ev, ctrl, mapping, value, changes); + uvc_ctrl_fill_event(chain, &ev, ctrl, mapping, value, changes); list_for_each_entry(sev, &mapping->ev_subs, node) { - if (sev->fh != &handle->vfh || + if (sev->fh != originator || (sev->flags & V4L2_EVENT_SUB_FL_ALLOW_FEEDBACK) || (changes & V4L2_EVENT_CTRL_CH_FLAGS)) v4l2_event_queue_fh(sev->fh, &ev); } } -static void uvc_ctrl_send_slave_event(struct uvc_fh *handle, - struct uvc_control *master, u32 slave_id, - const struct v4l2_ext_control *xctrls, unsigned int xctrls_count) +/* + * Send control change events for the slave of the @master control identified + * by the V4L2 ID @slave_id. The @handle identifies the event subscriber that + * generated the event and may be NULL for auto-update events. + */ +static void uvc_ctrl_send_slave_event(struct uvc_video_chain *chain, + struct uvc_fh *handle, struct uvc_control *master, u32 slave_id) { struct uvc_control_mapping *mapping = NULL; struct uvc_control *ctrl = NULL; u32 changes = V4L2_EVENT_CTRL_CH_FLAGS; - unsigned int i; s32 val = 0; - /* - * We can skip sending an event for the slave if the slave - * is being modified in the same transaction. - */ - for (i = 0; i < xctrls_count; i++) { - if (xctrls[i].id == slave_id) - return; - } - __uvc_find_control(master->entity, slave_id, &mapping, &ctrl, 0); if (ctrl == NULL) return; - if (__uvc_ctrl_get(handle->chain, ctrl, mapping, &val) == 0) + if (__uvc_ctrl_get(chain, ctrl, mapping, &val) == 0) changes |= V4L2_EVENT_CTRL_CH_VALUE; - uvc_ctrl_send_event(handle, ctrl, mapping, val, changes); + uvc_ctrl_send_event(chain, handle, ctrl, mapping, val, changes); +} + +static void uvc_ctrl_status_event_work(struct work_struct *work) +{ + struct uvc_device *dev = container_of(work, struct uvc_device, + async_ctrl.work); + struct uvc_ctrl_work *w = &dev->async_ctrl; + struct uvc_video_chain *chain = w->chain; + struct uvc_control_mapping *mapping; + struct uvc_control *ctrl = w->ctrl; + struct uvc_fh *handle; + unsigned int i; + int ret; + + mutex_lock(&chain->ctrl_mutex); + + handle = ctrl->handle; + ctrl->handle = NULL; + + list_for_each_entry(mapping, &ctrl->info.mappings, list) { + s32 value = __uvc_ctrl_get_value(mapping, w->data); + + /* + * handle may be NULL here if the device sends auto-update + * events without a prior related control set from userspace. + */ + for (i = 0; i < ARRAY_SIZE(mapping->slave_ids); ++i) { + if (!mapping->slave_ids[i]) + break; + + uvc_ctrl_send_slave_event(chain, handle, ctrl, + mapping->slave_ids[i]); + } + + uvc_ctrl_send_event(chain, handle, ctrl, mapping, value, + V4L2_EVENT_CTRL_CH_VALUE); + } + + mutex_unlock(&chain->ctrl_mutex); + + /* Resubmit the URB. */ + w->urb->interval = dev->int_ep->desc.bInterval; + ret = usb_submit_urb(w->urb, GFP_KERNEL); + if (ret < 0) + uvc_printk(KERN_ERR, "Failed to resubmit status URB (%d).\n", + ret); +} + +bool uvc_ctrl_status_event(struct urb *urb, struct uvc_video_chain *chain, + struct uvc_control *ctrl, const u8 *data) +{ + struct uvc_device *dev = chain->dev; + struct uvc_ctrl_work *w = &dev->async_ctrl; + + if (list_empty(&ctrl->info.mappings)) { + ctrl->handle = NULL; + return false; + } + + w->data = data; + w->urb = urb; + w->chain = chain; + w->ctrl = ctrl; + + schedule_work(&w->work); + + return true; +} + +static bool uvc_ctrl_xctrls_has_control(const struct v4l2_ext_control *xctrls, + unsigned int xctrls_count, u32 id) +{ + unsigned int i; + + for (i = 0; i < xctrls_count; ++i) { + if (xctrls[i].id == id) + return true; + } + + return false; } static void uvc_ctrl_send_events(struct uvc_fh *handle, @@ -1277,29 +1368,39 @@ static void uvc_ctrl_send_events(struct uvc_fh *handle, for (i = 0; i < xctrls_count; ++i) { ctrl = uvc_find_control(handle->chain, xctrls[i].id, &mapping); + if (ctrl->info.flags & UVC_CTRL_FLAG_ASYNCHRONOUS) + /* Notification will be sent from an Interrupt event. */ + continue; + for (j = 0; j < ARRAY_SIZE(mapping->slave_ids); ++j) { - if (!mapping->slave_ids[j]) + u32 slave_id = mapping->slave_ids[j]; + + if (!slave_id) break; - uvc_ctrl_send_slave_event(handle, ctrl, - mapping->slave_ids[j], - xctrls, xctrls_count); + + /* + * We can skip sending an event for the slave if the + * slave is being modified in the same transaction. + */ + if (uvc_ctrl_xctrls_has_control(xctrls, xctrls_count, + slave_id)) + continue; + + uvc_ctrl_send_slave_event(handle->chain, handle, ctrl, + slave_id); } /* * If the master is being modified in the same transaction * flags may change too. */ - if (mapping->master_id) { - for (j = 0; j < xctrls_count; j++) { - if (xctrls[j].id == mapping->master_id) { - changes |= V4L2_EVENT_CTRL_CH_FLAGS; - break; - } - } - } + if (mapping->master_id && + uvc_ctrl_xctrls_has_control(xctrls, xctrls_count, + mapping->master_id)) + changes |= V4L2_EVENT_CTRL_CH_FLAGS; - uvc_ctrl_send_event(handle, ctrl, mapping, xctrls[i].value, - changes); + uvc_ctrl_send_event(handle->chain, handle, ctrl, mapping, + xctrls[i].value, changes); } } @@ -1472,9 +1573,10 @@ int uvc_ctrl_get(struct uvc_video_chain *chain, return __uvc_ctrl_get(chain, ctrl, mapping, &xctrl->value); } -int uvc_ctrl_set(struct uvc_video_chain *chain, +int uvc_ctrl_set(struct uvc_fh *handle, struct v4l2_ext_control *xctrl) { + struct uvc_video_chain *chain = handle->chain; struct uvc_control *ctrl; struct uvc_control_mapping *mapping; s32 value; @@ -1581,6 +1683,9 @@ int uvc_ctrl_set(struct uvc_video_chain *chain, mapping->set(mapping, value, uvc_ctrl_data(ctrl, UVC_CTRL_DATA_CURRENT)); + if (ctrl->info.flags & UVC_CTRL_FLAG_ASYNCHRONOUS) + ctrl->handle = handle; + ctrl->dirty = 1; ctrl->modified = 1; return 0; @@ -1612,7 +1717,9 @@ static int uvc_ctrl_get_flags(struct uvc_device *dev, | (data[0] & UVC_CONTROL_CAP_SET ? UVC_CTRL_FLAG_SET_CUR : 0) | (data[0] & UVC_CONTROL_CAP_AUTOUPDATE ? - UVC_CTRL_FLAG_AUTO_UPDATE : 0); + UVC_CTRL_FLAG_AUTO_UPDATE : 0) + | (data[0] & UVC_CONTROL_CAP_ASYNCHRONOUS ? + UVC_CTRL_FLAG_ASYNCHRONOUS : 0); kfree(data); return ret; @@ -2173,6 +2280,8 @@ int uvc_ctrl_init_device(struct uvc_device *dev) struct uvc_entity *entity; unsigned int i; + INIT_WORK(&dev->async_ctrl.work, uvc_ctrl_status_event_work); + /* Walk the entities list and instantiate controls */ list_for_each_entry(entity, &dev->entities, list) { struct uvc_control *ctrl; @@ -2241,6 +2350,8 @@ void uvc_ctrl_cleanup_device(struct uvc_device *dev) struct uvc_entity *entity; unsigned int i; + cancel_work_sync(&dev->async_ctrl.work); + /* Free controls and control mappings for all entities. */ list_for_each_entry(entity, &dev->entities, list) { for (i = 0; i < entity->ncontrols; ++i) { diff --git a/drivers/media/usb/uvc/uvc_status.c b/drivers/media/usb/uvc/uvc_status.c index 7b710410584a..0722dc684378 100644 --- a/drivers/media/usb/uvc/uvc_status.c +++ b/drivers/media/usb/uvc/uvc_status.c @@ -78,7 +78,24 @@ static void uvc_input_report_key(struct uvc_device *dev, unsigned int code, /* -------------------------------------------------------------------------- * Status interrupt endpoint */ -static void uvc_event_streaming(struct uvc_device *dev, u8 *data, int len) +struct uvc_streaming_status { + u8 bStatusType; + u8 bOriginator; + u8 bEvent; + u8 bValue[]; +} __packed; + +struct uvc_control_status { + u8 bStatusType; + u8 bOriginator; + u8 bEvent; + u8 bSelector; + u8 bAttribute; + u8 bValue[]; +} __packed; + +static void uvc_event_streaming(struct uvc_device *dev, + struct uvc_streaming_status *status, int len) { if (len < 3) { uvc_trace(UVC_TRACE_STATUS, "Invalid streaming status event " @@ -86,31 +103,97 @@ static void uvc_event_streaming(struct uvc_device *dev, u8 *data, int len) return; } - if (data[2] == 0) { + if (status->bEvent == 0) { if (len < 4) return; uvc_trace(UVC_TRACE_STATUS, "Button (intf %u) %s len %d\n", - data[1], data[3] ? "pressed" : "released", len); - uvc_input_report_key(dev, KEY_CAMERA, data[3]); + status->bOriginator, + status->bValue[0] ? "pressed" : "released", len); + uvc_input_report_key(dev, KEY_CAMERA, status->bValue[0]); } else { uvc_trace(UVC_TRACE_STATUS, "Stream %u error event %02x len %d.\n", - data[1], data[2], len); + status->bOriginator, status->bEvent, len); } } -static void uvc_event_control(struct uvc_device *dev, u8 *data, int len) +#define UVC_CTRL_VALUE_CHANGE 0 +#define UVC_CTRL_INFO_CHANGE 1 +#define UVC_CTRL_FAILURE_CHANGE 2 +#define UVC_CTRL_MIN_CHANGE 3 +#define UVC_CTRL_MAX_CHANGE 4 + +static struct uvc_control *uvc_event_entity_find_ctrl(struct uvc_entity *entity, + u8 selector) { - char *attrs[3] = { "value", "info", "failure" }; + struct uvc_control *ctrl; + unsigned int i; + + for (i = 0, ctrl = entity->controls; i < entity->ncontrols; i++, ctrl++) + if (ctrl->info.selector == selector) + return ctrl; + + return NULL; +} - if (len < 6 || data[2] != 0 || data[4] > 2) { +static struct uvc_control *uvc_event_find_ctrl(struct uvc_device *dev, + const struct uvc_control_status *status, + struct uvc_video_chain **chain) +{ + list_for_each_entry((*chain), &dev->chains, list) { + struct uvc_entity *entity; + struct uvc_control *ctrl; + + list_for_each_entry(entity, &(*chain)->entities, chain) { + if (entity->id != status->bOriginator) + continue; + + ctrl = uvc_event_entity_find_ctrl(entity, + status->bSelector); + if (ctrl) + return ctrl; + } + } + + return NULL; +} + +static bool uvc_event_control(struct urb *urb, + const struct uvc_control_status *status, int len) +{ + static const char *attrs[] = { "value", "info", "failure", "min", "max" }; + struct uvc_device *dev = urb->context; + struct uvc_video_chain *chain; + struct uvc_control *ctrl; + + if (len < 6 || status->bEvent != 0 || + status->bAttribute >= ARRAY_SIZE(attrs)) { uvc_trace(UVC_TRACE_STATUS, "Invalid control status event " "received.\n"); - return; + return false; } uvc_trace(UVC_TRACE_STATUS, "Control %u/%u %s change len %d.\n", - data[1], data[3], attrs[data[4]], len); + status->bOriginator, status->bSelector, + attrs[status->bAttribute], len); + + /* Find the control. */ + ctrl = uvc_event_find_ctrl(dev, status, &chain); + if (!ctrl) + return false; + + switch (status->bAttribute) { + case UVC_CTRL_VALUE_CHANGE: + return uvc_ctrl_status_event(urb, chain, ctrl, status->bValue); + + case UVC_CTRL_INFO_CHANGE: + case UVC_CTRL_FAILURE_CHANGE: + case UVC_CTRL_MIN_CHANGE: + case UVC_CTRL_MAX_CHANGE: + break; + } + + return false; } static void uvc_status_complete(struct urb *urb) @@ -138,13 +221,23 @@ static void uvc_status_complete(struct urb *urb) len = urb->actual_length; if (len > 0) { switch (dev->status[0] & 0x0f) { - case UVC_STATUS_TYPE_CONTROL: - uvc_event_control(dev, dev->status, len); + case UVC_STATUS_TYPE_CONTROL: { + struct uvc_control_status *status = + (struct uvc_control_status *)dev->status; + + if (uvc_event_control(urb, status, len)) + /* The URB will be resubmitted in work context. */ + return; break; + } - case UVC_STATUS_TYPE_STREAMING: - uvc_event_streaming(dev, dev->status, len); + case UVC_STATUS_TYPE_STREAMING: { + struct uvc_streaming_status *status = + (struct uvc_streaming_status *)dev->status; + + uvc_event_streaming(dev, status, len); break; + } default: uvc_trace(UVC_TRACE_STATUS, "Unknown status event " diff --git a/drivers/media/usb/uvc/uvc_v4l2.c b/drivers/media/usb/uvc/uvc_v4l2.c index bd32914259ae..18a7384b50ee 100644 --- a/drivers/media/usb/uvc/uvc_v4l2.c +++ b/drivers/media/usb/uvc/uvc_v4l2.c @@ -994,7 +994,7 @@ static int uvc_ioctl_s_ctrl(struct file *file, void *fh, if (ret < 0) return ret; - ret = uvc_ctrl_set(chain, &xctrl); + ret = uvc_ctrl_set(handle, &xctrl); if (ret < 0) { uvc_ctrl_rollback(handle); return ret; @@ -1069,7 +1069,7 @@ static int uvc_ioctl_s_try_ext_ctrls(struct uvc_fh *handle, return ret; for (i = 0; i < ctrls->count; ++ctrl, ++i) { - ret = uvc_ctrl_set(chain, ctrl); + ret = uvc_ctrl_set(handle, ctrl); if (ret < 0) { uvc_ctrl_rollback(handle); ctrls->error_idx = commit ? ctrls->count : i; diff --git a/drivers/media/usb/uvc/uvcvideo.h b/drivers/media/usb/uvc/uvcvideo.h index 6b955e0dd956..e5f5d84f1d1d 100644 --- a/drivers/media/usb/uvc/uvcvideo.h +++ b/drivers/media/usb/uvc/uvcvideo.h @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -259,6 +260,8 @@ struct uvc_control { initialized:1; u8 *uvc_data; + + struct uvc_fh *handle; /* File handle that last changed the control. */ }; struct uvc_format_desc { @@ -603,6 +606,14 @@ struct uvc_device { u8 *status; struct input_dev *input; char input_phys[64]; + + struct uvc_ctrl_work { + struct work_struct work; + struct urb *urb; + struct uvc_video_chain *chain; + struct uvc_control *ctrl; + const void *data; + } async_ctrl; }; enum uvc_handle_state { @@ -756,6 +767,8 @@ int uvc_ctrl_add_mapping(struct uvc_video_chain *chain, int uvc_ctrl_init_device(struct uvc_device *dev); void uvc_ctrl_cleanup_device(struct uvc_device *dev); int uvc_ctrl_restore_values(struct uvc_device *dev); +bool uvc_ctrl_status_event(struct urb *urb, struct uvc_video_chain *chain, + struct uvc_control *ctrl, const u8 *data); int uvc_ctrl_begin(struct uvc_video_chain *chain); int __uvc_ctrl_commit(struct uvc_fh *handle, int rollback, @@ -773,7 +786,7 @@ static inline int uvc_ctrl_rollback(struct uvc_fh *handle) } int uvc_ctrl_get(struct uvc_video_chain *chain, struct v4l2_ext_control *xctrl); -int uvc_ctrl_set(struct uvc_video_chain *chain, struct v4l2_ext_control *xctrl); +int uvc_ctrl_set(struct uvc_fh *handle, struct v4l2_ext_control *xctrl); int uvc_xu_ctrl_query(struct uvc_video_chain *chain, struct uvc_xu_control_query *xqry); diff --git a/include/uapi/linux/uvcvideo.h b/include/uapi/linux/uvcvideo.h index 020714d2c5bd..f80f05b3c423 100644 --- a/include/uapi/linux/uvcvideo.h +++ b/include/uapi/linux/uvcvideo.h @@ -28,6 +28,8 @@ #define UVC_CTRL_FLAG_RESTORE (1 << 6) /* Control can be updated by the camera. */ #define UVC_CTRL_FLAG_AUTO_UPDATE (1 << 7) +/* Control supports asynchronous reporting */ +#define UVC_CTRL_FLAG_ASYNCHRONOUS (1 << 8) #define UVC_CTRL_FLAG_GET_RANGE \ (UVC_CTRL_FLAG_GET_CUR | UVC_CTRL_FLAG_GET_MIN | \ -- cgit v1.2.3 From d0dd962d8a4ef4df9b710c4e3a975e6bfd9f0225 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 28 May 2018 10:32:41 -0400 Subject: media: dvb: get rid of VIDEO_SET_SPU_PALETTE No upstream drivers use it. It doesn't make any sense to have a compat32 code for something that nobody uses upstream. Reported-by: Alexander Viro Signed-off-by: Mauro Carvalho Chehab Reviewed-by: Christoph Hellwig Signed-off-by: Mauro Carvalho Chehab --- .../media/uapi/dvb/video-set-spu-palette.rst | 82 ---------------------- .../media/uapi/dvb/video_function_calls.rst | 1 - Documentation/media/uapi/dvb/video_types.rst | 18 ----- Documentation/media/video.h.rst.exceptions | 1 - fs/compat_ioctl.c | 30 -------- include/uapi/linux/dvb/video.h | 7 -- 6 files changed, 139 deletions(-) delete mode 100644 Documentation/media/uapi/dvb/video-set-spu-palette.rst (limited to 'include') diff --git a/Documentation/media/uapi/dvb/video-set-spu-palette.rst b/Documentation/media/uapi/dvb/video-set-spu-palette.rst deleted file mode 100644 index 51a1913d21d2..000000000000 --- a/Documentation/media/uapi/dvb/video-set-spu-palette.rst +++ /dev/null @@ -1,82 +0,0 @@ -.. -*- coding: utf-8; mode: rst -*- - -.. _VIDEO_SET_SPU_PALETTE: - -===================== -VIDEO_SET_SPU_PALETTE -===================== - -Name ----- - -VIDEO_SET_SPU_PALETTE - -.. attention:: This ioctl is deprecated. - -Synopsis --------- - -.. c:function:: int ioctl(fd, VIDEO_SET_SPU_PALETTE, struct video_spu_palette *palette ) - :name: VIDEO_SET_SPU_PALETTE - - -Arguments ---------- - -.. flat-table:: - :header-rows: 0 - :stub-columns: 0 - - - - .. row 1 - - - int fd - - - File descriptor returned by a previous call to open(). - - - .. row 2 - - - int request - - - Equals VIDEO_SET_SPU_PALETTE for this command. - - - .. row 3 - - - video_spu_palette_t \*palette - - - SPU palette according to section ??. - - -Description ------------ - -This ioctl sets the SPU color palette. - -.. c:type:: video_spu_palette - -.. code-block::c - - typedef struct video_spu_palette { /* SPU Palette information */ - int length; - __u8 __user *palette; - } video_spu_palette_t; - -Return Value ------------- - -On success 0 is returned, on error -1 and the ``errno`` variable is set -appropriately. The generic error codes are described at the -:ref:`Generic Error Codes ` chapter. - - - -.. flat-table:: - :header-rows: 0 - :stub-columns: 0 - - - - .. row 1 - - - ``EINVAL`` - - - input is not a valid palette or driver doesn’t handle SPU. diff --git a/Documentation/media/uapi/dvb/video_function_calls.rst b/Documentation/media/uapi/dvb/video_function_calls.rst index 68588ac7fecb..8d8383ffaeba 100644 --- a/Documentation/media/uapi/dvb/video_function_calls.rst +++ b/Documentation/media/uapi/dvb/video_function_calls.rst @@ -38,6 +38,5 @@ Video Function Calls video-set-system video-set-highlight video-set-spu - video-set-spu-palette video-get-navi video-set-attributes diff --git a/Documentation/media/uapi/dvb/video_types.rst b/Documentation/media/uapi/dvb/video_types.rst index 640a21de6b8a..4cfa00e5c934 100644 --- a/Documentation/media/uapi/dvb/video_types.rst +++ b/Documentation/media/uapi/dvb/video_types.rst @@ -320,24 +320,6 @@ to the following format: } video_spu_t; -.. c:type:: video_spu_palette - -struct video_spu_palette -======================== - -The following structure is used to set the SPU palette by calling -VIDEO_SPU_PALETTE: - - -.. code-block:: c - - typedef - struct video_spu_palette { - int length; - uint8_t *palette; - } video_spu_palette_t; - - .. c:type:: video_navi_pack struct video_navi_pack diff --git a/Documentation/media/video.h.rst.exceptions b/Documentation/media/video.h.rst.exceptions index a91aa884ce0e..89d7c3ef2da7 100644 --- a/Documentation/media/video.h.rst.exceptions +++ b/Documentation/media/video.h.rst.exceptions @@ -36,5 +36,4 @@ replace typedef video_stream_source_t :c:type:`video_stream_source` replace typedef video_play_state_t :c:type:`video_play_state` replace typedef video_highlight_t :c:type:`video_highlight` replace typedef video_spu_t :c:type:`video_spu` -replace typedef video_spu_palette_t :c:type:`video_spu_palette` replace typedef video_navi_pack_t :c:type:`video_navi_pack` diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index 9907475b4226..fdb5ef9b5d06 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -198,34 +198,6 @@ static int do_video_stillpicture(struct file *file, return err; } -struct compat_video_spu_palette { - int length; - compat_uptr_t palette; -}; - -static int do_video_set_spu_palette(struct file *file, - unsigned int cmd, struct compat_video_spu_palette __user *up) -{ - struct video_spu_palette __user *up_native; - compat_uptr_t palp; - int length, err; - - err = get_user(palp, &up->palette); - err |= get_user(length, &up->length); - if (err) - return -EFAULT; - - up_native = compat_alloc_user_space(sizeof(struct video_spu_palette)); - err = put_user(compat_ptr(palp), &up_native->palette); - err |= put_user(length, &up_native->length); - if (err) - return -EFAULT; - - err = do_ioctl(file, cmd, (unsigned long) up_native); - - return err; -} - #ifdef CONFIG_BLOCK typedef struct sg_io_hdr32 { compat_int_t interface_id; /* [i] 'S' for SCSI generic (required) */ @@ -1347,8 +1319,6 @@ static long do_ioctl_trans(unsigned int cmd, return do_video_get_event(file, cmd, argp); case VIDEO_STILLPICTURE: return do_video_stillpicture(file, cmd, argp); - case VIDEO_SET_SPU_PALETTE: - return do_video_set_spu_palette(file, cmd, argp); } /* diff --git a/include/uapi/linux/dvb/video.h b/include/uapi/linux/dvb/video.h index df3d7028c807..6a0c9757b7ba 100644 --- a/include/uapi/linux/dvb/video.h +++ b/include/uapi/linux/dvb/video.h @@ -186,12 +186,6 @@ typedef struct video_spu { } video_spu_t; -typedef struct video_spu_palette { /* SPU Palette information */ - int length; - __u8 __user *palette; -} video_spu_palette_t; - - typedef struct video_navi_pack { int length; /* 0 ... 1024 */ __u8 data[1024]; @@ -248,7 +242,6 @@ typedef __u16 video_attributes_t; #define VIDEO_SET_SYSTEM _IO('o', 38) #define VIDEO_SET_HIGHLIGHT _IOW('o', 39, video_highlight_t) #define VIDEO_SET_SPU _IOW('o', 50, video_spu_t) -#define VIDEO_SET_SPU_PALETTE _IOW('o', 51, video_spu_palette_t) #define VIDEO_GET_NAVI _IOR('o', 52, video_navi_pack_t) #define VIDEO_SET_ATTRIBUTES _IO('o', 53) #define VIDEO_GET_SIZE _IOR('o', 55, video_size_t) -- cgit v1.2.3 From 1fb2e3f276ddafee81073d884f599cd2574c31e2 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 17 Jul 2018 18:05:36 +0200 Subject: lib/crc: Move polynomial definition to separate header Allow other drivers and parts of kernel to use the same define for CRC32 polynomial, instead of duplicating it in many places. This code does not bring any functional changes, except moving existing code. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Herbert Xu --- include/linux/crc32poly.h | 20 ++++++++++++++++++++ lib/crc32.c | 1 + lib/crc32defs.h | 14 -------------- lib/gen_crc32table.c | 1 + 4 files changed, 22 insertions(+), 14 deletions(-) create mode 100644 include/linux/crc32poly.h (limited to 'include') diff --git a/include/linux/crc32poly.h b/include/linux/crc32poly.h new file mode 100644 index 000000000000..7ad5aa92d3c7 --- /dev/null +++ b/include/linux/crc32poly.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_CRC32_POLY_H +#define _LINUX_CRC32_POLY_H + +/* + * There are multiple 16-bit CRC polynomials in common use, but this is + * *the* standard CRC-32 polynomial, first popularized by Ethernet. + * x^32+x^26+x^23+x^22+x^16+x^12+x^11+x^10+x^8+x^7+x^5+x^4+x^2+x^1+x^0 + */ +#define CRCPOLY_LE 0xedb88320 +#define CRCPOLY_BE 0x04c11db7 + +/* + * This is the CRC32c polynomial, as outlined by Castagnoli. + * x^32+x^28+x^27+x^26+x^25+x^23+x^22+x^20+x^19+x^18+x^14+x^13+x^11+x^10+x^9+ + * x^8+x^6+x^0 + */ +#define CRC32C_POLY_LE 0x82F63B78 + +#endif /* _LINUX_CRC32_POLY_H */ diff --git a/lib/crc32.c b/lib/crc32.c index 2ef20fe84b69..341c54cb4edf 100644 --- a/lib/crc32.c +++ b/lib/crc32.c @@ -27,6 +27,7 @@ /* see: Documentation/crc32.txt for a description of algorithms */ #include +#include #include #include #include diff --git a/lib/crc32defs.h b/lib/crc32defs.h index cb275a28a750..0c8fb5923e7e 100644 --- a/lib/crc32defs.h +++ b/lib/crc32defs.h @@ -1,18 +1,4 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* - * There are multiple 16-bit CRC polynomials in common use, but this is - * *the* standard CRC-32 polynomial, first popularized by Ethernet. - * x^32+x^26+x^23+x^22+x^16+x^12+x^11+x^10+x^8+x^7+x^5+x^4+x^2+x^1+x^0 - */ -#define CRCPOLY_LE 0xedb88320 -#define CRCPOLY_BE 0x04c11db7 - -/* - * This is the CRC32c polynomial, as outlined by Castagnoli. - * x^32+x^28+x^27+x^26+x^25+x^23+x^22+x^20+x^19+x^18+x^14+x^13+x^11+x^10+x^9+ - * x^8+x^6+x^0 - */ -#define CRC32C_POLY_LE 0x82F63B78 /* Try to choose an implementation variant via Kconfig */ #ifdef CONFIG_CRC32_SLICEBY8 diff --git a/lib/gen_crc32table.c b/lib/gen_crc32table.c index 8f26660ea10a..34c3bc826f45 100644 --- a/lib/gen_crc32table.c +++ b/lib/gen_crc32table.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include +#include "../include/linux/crc32poly.h" #include "../include/generated/autoconf.h" #include "crc32defs.h" #include -- cgit v1.2.3 From e37f2f93afe594682702439ca34eb8130598cdf2 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 17 Jul 2018 18:05:37 +0200 Subject: lib/crc: Use consistent naming for CRC-32 polynomials Header was defining CRCPOLY_LE/BE and CRC32C_POLY_LE but in fact all of them are CRC-32 polynomials so use consistent naming. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Herbert Xu --- include/linux/crc32poly.h | 4 ++-- lib/crc32.c | 10 +++++----- lib/gen_crc32table.c | 4 ++-- 3 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/crc32poly.h b/include/linux/crc32poly.h index 7ad5aa92d3c7..62c4b7790a28 100644 --- a/include/linux/crc32poly.h +++ b/include/linux/crc32poly.h @@ -7,8 +7,8 @@ * *the* standard CRC-32 polynomial, first popularized by Ethernet. * x^32+x^26+x^23+x^22+x^16+x^12+x^11+x^10+x^8+x^7+x^5+x^4+x^2+x^1+x^0 */ -#define CRCPOLY_LE 0xedb88320 -#define CRCPOLY_BE 0x04c11db7 +#define CRC32_POLY_LE 0xedb88320 +#define CRC32_POLY_BE 0x04c11db7 /* * This is the CRC32c polynomial, as outlined by Castagnoli. diff --git a/lib/crc32.c b/lib/crc32.c index 341c54cb4edf..a6c9afafc8c8 100644 --- a/lib/crc32.c +++ b/lib/crc32.c @@ -185,7 +185,7 @@ static inline u32 __pure crc32_le_generic(u32 crc, unsigned char const *p, #if CRC_LE_BITS == 1 u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len) { - return crc32_le_generic(crc, p, len, NULL, CRCPOLY_LE); + return crc32_le_generic(crc, p, len, NULL, CRC32_POLY_LE); } u32 __pure __crc32c_le(u32 crc, unsigned char const *p, size_t len) { @@ -195,7 +195,7 @@ u32 __pure __crc32c_le(u32 crc, unsigned char const *p, size_t len) u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len) { return crc32_le_generic(crc, p, len, - (const u32 (*)[256])crc32table_le, CRCPOLY_LE); + (const u32 (*)[256])crc32table_le, CRC32_POLY_LE); } u32 __pure __crc32c_le(u32 crc, unsigned char const *p, size_t len) { @@ -269,7 +269,7 @@ static u32 __attribute_const__ crc32_generic_shift(u32 crc, size_t len, u32 __attribute_const__ crc32_le_shift(u32 crc, size_t len) { - return crc32_generic_shift(crc, len, CRCPOLY_LE); + return crc32_generic_shift(crc, len, CRC32_POLY_LE); } u32 __attribute_const__ __crc32c_le_shift(u32 crc, size_t len) @@ -331,13 +331,13 @@ static inline u32 __pure crc32_be_generic(u32 crc, unsigned char const *p, #if CRC_LE_BITS == 1 u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len) { - return crc32_be_generic(crc, p, len, NULL, CRCPOLY_BE); + return crc32_be_generic(crc, p, len, NULL, CRC32_POLY_BE); } #else u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len) { return crc32_be_generic(crc, p, len, - (const u32 (*)[256])crc32table_be, CRCPOLY_BE); + (const u32 (*)[256])crc32table_be, CRC32_POLY_BE); } #endif EXPORT_SYMBOL(crc32_be); diff --git a/lib/gen_crc32table.c b/lib/gen_crc32table.c index 34c3bc826f45..f755b997b967 100644 --- a/lib/gen_crc32table.c +++ b/lib/gen_crc32table.c @@ -58,7 +58,7 @@ static void crc32init_le_generic(const uint32_t polynomial, static void crc32init_le(void) { - crc32init_le_generic(CRCPOLY_LE, crc32table_le); + crc32init_le_generic(CRC32_POLY_LE, crc32table_le); } static void crc32cinit_le(void) @@ -77,7 +77,7 @@ static void crc32init_be(void) crc32table_be[0][0] = 0; for (i = 1; i < BE_TABLE_SIZE; i <<= 1) { - crc = (crc << 1) ^ ((crc & 0x80000000) ? CRCPOLY_BE : 0); + crc = (crc << 1) ^ ((crc & 0x80000000) ? CRC32_POLY_BE : 0); for (j = 0; j < i; j++) crc32table_be[0][i + j] = crc ^ crc32table_be[0][j]; } -- cgit v1.2.3 From 87e1a881e1fe3bfd89903c54ae0d6d6adedb76f1 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Wed, 25 Jul 2018 08:51:39 -0400 Subject: media: media.h: remove linux/version.h include The media.h public header is one of only three public headers that include linux/version.h. Drop it from media.h. It was only used for an obsolete define. It has to be added to media-device.c, since that source relied on media.h to include it. Acked-by: Sakari Ailus Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/media/media-device.c | 1 + include/uapi/linux/media.h | 3 +-- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/media/media-device.c b/drivers/media/media-device.c index 14959b19a342..fcdf3d5dc4b6 100644 --- a/drivers/media/media-device.c +++ b/drivers/media/media-device.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include diff --git a/include/uapi/linux/media.h b/include/uapi/linux/media.h index 82ec9f132a53..36f76e777ef9 100644 --- a/include/uapi/linux/media.h +++ b/include/uapi/linux/media.h @@ -25,7 +25,6 @@ #endif #include #include -#include struct media_device_info { char driver[16]; @@ -421,7 +420,7 @@ struct media_v2_topology { #define MEDIA_INTF_T_ALSA_TIMER (MEDIA_INTF_T_ALSA_BASE + 7) /* Obsolete symbol for media_version, no longer used in the kernel */ -#define MEDIA_API_VERSION KERNEL_VERSION(0, 1, 0) +#define MEDIA_API_VERSION ((0 << 16) | (1 << 8) | 0) #endif -- cgit v1.2.3 From 75cbb3f1d840429e6aa67b351332f38b29e6292c Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 26 Jul 2018 12:17:41 +0800 Subject: bcache: stop using the deprecated get_seconds() The get_seconds function is deprecated now since it returns a 32-bit value that will eventually overflow, and we are replacing it throughout the kernel with ktime_get_seconds() or ktime_get_real_seconds() that return a time64_t. bcache uses get_seconds() to read the current system time and store it in the superblock as well as in uuid_entry structures that are user visible. Unfortunately, the two structures in are still limited to 32 bits, so this won't fix any real problems but will still overflow in year 2106. Let's at least document that properly, in case we get an updated format in the future it can be fixed. We still have a long time before the overflow and checking the tools at https://github.com/koverstreet/bcache-tools reveals no access to any of them. Signed-off-by: Arnd Bergmann Signed-off-by: Coly Li Signed-off-by: Jens Axboe --- drivers/md/bcache/super.c | 12 ++++++------ include/uapi/linux/bcache.h | 4 ++-- 2 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 40fe26fef00f..e0a92104ca23 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -181,7 +181,7 @@ static const char *read_super(struct cache_sb *sb, struct block_device *bdev, goto err; } - sb->last_mount = get_seconds(); + sb->last_mount = (u32)ktime_get_real_seconds(); err = NULL; get_page(bh->b_page); @@ -701,7 +701,7 @@ static void bcache_device_detach(struct bcache_device *d) SET_UUID_FLASH_ONLY(u, 0); memcpy(u->uuid, invalid_uuid, 16); - u->invalidated = cpu_to_le32(get_seconds()); + u->invalidated = cpu_to_le32((u32)ktime_get_real_seconds()); bch_uuid_write(d->c); } @@ -1033,7 +1033,7 @@ void bch_cached_dev_detach(struct cached_dev *dc) int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c, uint8_t *set_uuid) { - uint32_t rtime = cpu_to_le32(get_seconds()); + uint32_t rtime = cpu_to_le32((u32)ktime_get_real_seconds()); struct uuid_entry *u; struct cached_dev *exist_dc, *t; @@ -1076,7 +1076,7 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c, (BDEV_STATE(&dc->sb) == BDEV_STATE_STALE || BDEV_STATE(&dc->sb) == BDEV_STATE_NONE)) { memcpy(u->uuid, invalid_uuid, 16); - u->invalidated = cpu_to_le32(get_seconds()); + u->invalidated = cpu_to_le32((u32)ktime_get_real_seconds()); u = NULL; } @@ -1398,7 +1398,7 @@ int bch_flash_dev_create(struct cache_set *c, uint64_t size) get_random_bytes(u->uuid, 16); memset(u->label, 0, 32); - u->first_reg = u->last_reg = cpu_to_le32(get_seconds()); + u->first_reg = u->last_reg = cpu_to_le32((u32)ktime_get_real_seconds()); SET_UUID_FLASH_ONLY(u, 1); u->sectors = size >> 9; @@ -1902,7 +1902,7 @@ static void run_cache_set(struct cache_set *c) goto err; closure_sync(&cl); - c->sb.last_mount = get_seconds(); + c->sb.last_mount = (u32)ktime_get_real_seconds(); bcache_write_super(c); list_for_each_entry_safe(dc, t, &uncached_devices, list) diff --git a/include/uapi/linux/bcache.h b/include/uapi/linux/bcache.h index 821f71a2e48f..8d19e02d752a 100644 --- a/include/uapi/linux/bcache.h +++ b/include/uapi/linux/bcache.h @@ -195,7 +195,7 @@ struct cache_sb { }; }; - __u32 last_mount; /* time_t */ + __u32 last_mount; /* time overflow in y2106 */ __u16 first_bucket; union { @@ -318,7 +318,7 @@ struct uuid_entry { struct { __u8 uuid[16]; __u8 label[32]; - __u32 first_reg; + __u32 first_reg; /* time overflow in y2106 */ __u32 last_reg; __u32 invalidated; -- cgit v1.2.3 From 1f3ed383fb9a073ae2e408cd7a0717b04c7c3a21 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Fri, 27 Jul 2018 09:45:05 +0200 Subject: net: sched: don't dump chains only held by actions In case a chain is empty and not explicitly created by a user, such chain should not exist. The only exception is if there is an action "goto chain" pointing to it. In that case, don't show the chain in the dump. Track the chain references held by actions and use them to find out if a chain should or should not be shown in chain dump. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/pkt_cls.h | 3 ++ include/net/sch_generic.h | 1 + net/sched/act_api.c | 4 +-- net/sched/cls_api.c | 70 +++++++++++++++++++++++++++++++++++++++-------- 4 files changed, 64 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index a3101582f642..6d02f31abba8 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -39,7 +39,10 @@ bool tcf_queue_work(struct rcu_work *rwork, work_func_t func); #ifdef CONFIG_NET_CLS struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index, bool create); +struct tcf_chain *tcf_chain_get_by_act(struct tcf_block *block, + u32 chain_index); void tcf_chain_put(struct tcf_chain *chain); +void tcf_chain_put_by_act(struct tcf_chain *chain); void tcf_block_netif_keep_dst(struct tcf_block *block); int tcf_block_get(struct tcf_block **p_block, struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q, diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 085c509c8674..c5432362dc26 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -314,6 +314,7 @@ struct tcf_chain { struct tcf_block *block; u32 index; /* chain index */ unsigned int refcnt; + unsigned int action_refcnt; bool explicitly_created; const struct tcf_proto_ops *tmplt_ops; void *tmplt_priv; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 148a89ab789b..b43df1e25c6d 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -36,7 +36,7 @@ static int tcf_action_goto_chain_init(struct tc_action *a, struct tcf_proto *tp) if (!tp) return -EINVAL; - a->goto_chain = tcf_chain_get(tp->chain->block, chain_index, true); + a->goto_chain = tcf_chain_get_by_act(tp->chain->block, chain_index); if (!a->goto_chain) return -ENOMEM; return 0; @@ -44,7 +44,7 @@ static int tcf_action_goto_chain_init(struct tc_action *a, struct tcf_proto *tp) static void tcf_action_goto_chain_fini(struct tc_action *a) { - tcf_chain_put(a->goto_chain); + tcf_chain_put_by_act(a->goto_chain); } static void tcf_action_goto_chain_exec(const struct tc_action *a, diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 75cce2819de9..e20aad1987b8 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -262,6 +262,25 @@ static void tcf_chain_hold(struct tcf_chain *chain) ++chain->refcnt; } +static void tcf_chain_hold_by_act(struct tcf_chain *chain) +{ + ++chain->action_refcnt; +} + +static void tcf_chain_release_by_act(struct tcf_chain *chain) +{ + --chain->action_refcnt; +} + +static bool tcf_chain_is_zombie(struct tcf_chain *chain) +{ + /* In case all the references are action references, this + * chain is a zombie and should not be listed in the chain + * dump list. + */ + return chain->refcnt == chain->action_refcnt; +} + static struct tcf_chain *tcf_chain_lookup(struct tcf_block *block, u32 chain_index) { @@ -298,6 +317,15 @@ struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index, } EXPORT_SYMBOL(tcf_chain_get); +struct tcf_chain *tcf_chain_get_by_act(struct tcf_block *block, u32 chain_index) +{ + struct tcf_chain *chain = tcf_chain_get(block, chain_index, true); + + tcf_chain_hold_by_act(chain); + return chain; +} +EXPORT_SYMBOL(tcf_chain_get_by_act); + static void tc_chain_tmplt_del(struct tcf_chain *chain); void tcf_chain_put(struct tcf_chain *chain) @@ -310,6 +338,13 @@ void tcf_chain_put(struct tcf_chain *chain) } EXPORT_SYMBOL(tcf_chain_put); +void tcf_chain_put_by_act(struct tcf_chain *chain) +{ + tcf_chain_release_by_act(chain); + tcf_chain_put(chain); +} +EXPORT_SYMBOL(tcf_chain_put_by_act); + static void tcf_chain_put_explicitly_created(struct tcf_chain *chain) { if (chain->explicitly_created) @@ -1803,20 +1838,29 @@ replay: chain = tcf_chain_lookup(block, chain_index); if (n->nlmsg_type == RTM_NEWCHAIN) { if (chain) { - NL_SET_ERR_MSG(extack, "Filter chain already exists"); - return -EEXIST; - } - if (!(n->nlmsg_flags & NLM_F_CREATE)) { - NL_SET_ERR_MSG(extack, "Need both RTM_NEWCHAIN and NLM_F_CREATE to create a new chain"); - return -ENOENT; - } - chain = tcf_chain_create(block, chain_index); - if (!chain) { - NL_SET_ERR_MSG(extack, "Failed to create filter chain"); - return -ENOMEM; + if (tcf_chain_is_zombie(chain)) { + /* The chain exists only because there is + * some action referencing it, meaning it + * is a zombie. + */ + tcf_chain_hold(chain); + } else { + NL_SET_ERR_MSG(extack, "Filter chain already exists"); + return -EEXIST; + } + } else { + if (!(n->nlmsg_flags & NLM_F_CREATE)) { + NL_SET_ERR_MSG(extack, "Need both RTM_NEWCHAIN and NLM_F_CREATE to create a new chain"); + return -ENOENT; + } + chain = tcf_chain_create(block, chain_index); + if (!chain) { + NL_SET_ERR_MSG(extack, "Failed to create filter chain"); + return -ENOMEM; + } } } else { - if (!chain) { + if (!chain || tcf_chain_is_zombie(chain)) { NL_SET_ERR_MSG(extack, "Cannot find specified filter chain"); return -EINVAL; } @@ -1944,6 +1988,8 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb) index++; continue; } + if (tcf_chain_is_zombie(chain)) + continue; err = tc_chain_fill_node(chain, net, skb, block, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, -- cgit v1.2.3 From f07d141fe9430cdf9f8a65a87c4136bd83b8ab2e Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Mon, 23 Jul 2018 23:16:07 +0100 Subject: dma-mapping: Generalise dma_32bit_limit flag Whilst the notion of an upstream DMA restriction is most commonly seen in PCI host bridges saddled with a 32-bit native interface, a more general version of the same issue can exist on complex SoCs where a bus or point-to-point interconnect link from a device's DMA master interface to another component along the path to memory (often an IOMMU) may carry fewer address bits than the interfaces at both ends nominally support. In order to properly deal with this, the first step is to expand the dma_32bit_limit flag into an arbitrary mask. To minimise the impact on existing code, we'll make sure to only consider this new mask valid if set. That makes sense anyway, since a mask of zero would represent DMA not being wired up at all, and that would be better handled by not providing valid ops in the first place. Signed-off-by: Robin Murphy Acked-by: Ard Biesheuvel Signed-off-by: Christoph Hellwig --- arch/x86/kernel/pci-dma.c | 2 +- include/linux/device.h | 6 +++--- kernel/dma/direct.c | 6 +++--- 3 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index ab5d9dd668d2..80f9fe8d27d0 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -175,7 +175,7 @@ rootfs_initcall(pci_iommu_init); static int via_no_dac_cb(struct pci_dev *pdev, void *data) { - pdev->dev.dma_32bit_limit = true; + pdev->dev.bus_dma_mask = DMA_BIT_MASK(32); return 0; } diff --git a/include/linux/device.h b/include/linux/device.h index 055a69dbcd18..6d3b000be57e 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -886,6 +886,8 @@ struct dev_links_info { * @coherent_dma_mask: Like dma_mask, but for alloc_coherent mapping as not all * hardware supports 64-bit addresses for consistent allocations * such descriptors. + * @bus_dma_mask: Mask of an upstream bridge or bus which imposes a smaller DMA + * limit than the device itself supports. * @dma_pfn_offset: offset of DMA memory range relatively of RAM * @dma_parms: A low level driver may set these to teach IOMMU code about * segment limitations. @@ -912,8 +914,6 @@ struct dev_links_info { * @offline: Set after successful invocation of bus type's .offline(). * @of_node_reused: Set if the device-tree node is shared with an ancestor * device. - * @dma_32bit_limit: bridge limited to 32bit DMA even if the device itself - * indicates support for a higher limit in the dma_mask field. * * At the lowest level, every device in a Linux system is represented by an * instance of struct device. The device structure contains the information @@ -967,6 +967,7 @@ struct device { not all hardware supports 64 bit addresses for consistent allocations such descriptors. */ + u64 bus_dma_mask; /* upstream dma_mask constraint */ unsigned long dma_pfn_offset; struct device_dma_parameters *dma_parms; @@ -1002,7 +1003,6 @@ struct device { bool offline_disabled:1; bool offline:1; bool of_node_reused:1; - bool dma_32bit_limit:1; }; static inline struct device *kobj_to_dev(struct kobject *kobj) diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 8be8106270c2..c2860c5a9e96 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -180,10 +180,10 @@ int dma_direct_supported(struct device *dev, u64 mask) return 0; #endif /* - * Various PCI/PCIe bridges have broken support for > 32bit DMA even - * if the device itself might support it. + * Upstream PCI/PCIe bridges or SoC interconnects may not carry + * as many DMA address bits as the device itself supports. */ - if (dev->dma_32bit_limit && mask > DMA_BIT_MASK(32)) + if (dev->bus_dma_mask && mask > dev->bus_dma_mask) return 0; return 1; } -- cgit v1.2.3 From 9b89bc3857a6c0dfda18ddae2a42c114ecc32753 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 12 May 2018 18:18:12 +0200 Subject: nvme.h: add support for the log specific field NVMe 1.3 added a new log specific field to the get log page CQ defintion, add it to our get_log_page SQ structure. Signed-off-by: Christoph Hellwig Reviewed-by: Keith Busch Reviewed-by: Sagi Grimberg Reviewed-by: Martin K. Petersen Reviewed-by: Hannes Reinecke Reviewed-by: Johannes Thumshirn --- include/linux/nvme.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 80dfedcf0bf7..39f05b0b8c7f 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -885,7 +885,7 @@ struct nvme_get_log_page_command { __u64 rsvd2[2]; union nvme_data_ptr dptr; __u8 lid; - __u8 rsvd10; + __u8 lsp; /* upper 4 bits reserved */ __le16 numdl; __le16 numdu; __u16 rsvd11; -- cgit v1.2.3 From 1a37621658fe06b10cf8bac02c32304d2a1c888c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 13 May 2018 18:53:57 +0200 Subject: nvme.h: add ANA definitions Add various defintions from NVMe 1.3 TP 4004. Signed-off-by: Christoph Hellwig Reviewed-by: Keith Busch Reviewed-by: Sagi Grimberg Reviewed-by: Martin K. Petersen Reviewed-by: Hannes Reinecke Reviewed-by: Johannes Thumshirn --- include/linux/nvme.h | 50 +++++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 47 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 39f05b0b8c7f..64c9175723de 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -242,7 +242,12 @@ struct nvme_id_ctrl { __le32 sanicap; __le32 hmminds; __le16 hmmaxd; - __u8 rsvd338[174]; + __u8 rsvd338[4]; + __u8 anatt; + __u8 anacap; + __le32 anagrpmax; + __le32 nanagrpid; + __u8 rsvd352[160]; __u8 sqes; __u8 cqes; __le16 maxcmd; @@ -258,7 +263,8 @@ struct nvme_id_ctrl { __le16 acwu; __u8 rsvd534[2]; __le32 sgls; - __u8 rsvd540[228]; + __le32 mnan; + __u8 rsvd544[224]; char subnqn[256]; __u8 rsvd1024[768]; __le32 ioccsz; @@ -312,7 +318,9 @@ struct nvme_id_ns { __le16 nabspf; __le16 noiob; __u8 nvmcap[16]; - __u8 rsvd64[40]; + __u8 rsvd64[28]; + __le32 anagrpid; + __u8 rsvd96[8]; __u8 nguid[16]; __u8 eui64[8]; struct nvme_lbaf lbaf[16]; @@ -425,6 +433,32 @@ struct nvme_effects_log { __u8 resv[2048]; }; +enum nvme_ana_state { + NVME_ANA_OPTIMIZED = 0x01, + NVME_ANA_NONOPTIMIZED = 0x02, + NVME_ANA_INACCESSIBLE = 0x03, + NVME_ANA_PERSISTENT_LOSS = 0x04, + NVME_ANA_CHANGE = 0x0f, +}; + +struct nvme_ana_group_desc { + __le32 grpid; + __le32 nnsids; + __le64 chgcnt; + __u8 state; + __u8 rsvd17[7]; + __le32 nsids[]; +}; + +/* flag for the log specific field of the ANA log */ +#define NVME_ANA_LOG_RGO (1 << 0) + +struct nvme_ana_rsp_hdr { + __le64 chgcnt; + __le16 ngrps; + __le16 rsvd10[3]; +}; + enum { NVME_SMART_CRIT_SPARE = 1 << 0, NVME_SMART_CRIT_TEMPERATURE = 1 << 1, @@ -444,11 +478,13 @@ enum { enum { NVME_AER_NOTICE_NS_CHANGED = 0x00, NVME_AER_NOTICE_FW_ACT_STARTING = 0x01, + NVME_AER_NOTICE_ANA = 0x03, }; enum { NVME_AEN_CFG_NS_ATTR = 1 << 8, NVME_AEN_CFG_FW_ACT = 1 << 9, + NVME_AEN_CFG_ANA_CHANGE = 1 << 11, }; struct nvme_lba_range_type { @@ -763,6 +799,7 @@ enum { NVME_LOG_FW_SLOT = 0x03, NVME_LOG_CHANGED_NS = 0x04, NVME_LOG_CMD_EFFECTS = 0x05, + NVME_LOG_ANA = 0x0c, NVME_LOG_DISC = 0x70, NVME_LOG_RESERVATION = 0x80, NVME_FWACT_REPL = (0 << 3), @@ -1185,6 +1222,13 @@ enum { NVME_SC_ACCESS_DENIED = 0x286, NVME_SC_UNWRITTEN_BLOCK = 0x287, + /* + * Path-related Errors: + */ + NVME_SC_ANA_PERSISTENT_LOSS = 0x301, + NVME_SC_ANA_INACCESSIBLE = 0x302, + NVME_SC_ANA_TRANSITION = 0x303, + NVME_SC_DNR = 0x4000, }; -- cgit v1.2.3 From 2ac305b7c8d7f93a6ef0018391e9865ea4ac0d65 Mon Sep 17 00:00:00 2001 From: Huang Rui Date: Thu, 26 Jul 2018 16:32:08 +0800 Subject: drm/ttm: add ttm_set_memory header (v2) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch moves all non-x86 abstraction to the ttm_set_memory header. It is to make function calling more clearly. (v2): add ttm_ prefix. Suggested-by: Christian König Signed-off-by: Huang Rui Reviewed-by: Bas Nieuwenhuizen Reviewed-by: Christian König Signed-off-by: Alex Deucher --- include/drm/ttm/ttm_set_memory.h | 128 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 128 insertions(+) create mode 100644 include/drm/ttm/ttm_set_memory.h (limited to 'include') diff --git a/include/drm/ttm/ttm_set_memory.h b/include/drm/ttm/ttm_set_memory.h new file mode 100644 index 000000000000..a70723cf208b --- /dev/null +++ b/include/drm/ttm/ttm_set_memory.h @@ -0,0 +1,128 @@ +/************************************************************************** + * + * Copyright (c) 2018 Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the + * "Software"), to deal in the Software without restriction, including + * without limitation the rights to use, copy, modify, merge, publish, + * distribute, sub license, and/or sell copies of the Software, and to + * permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice (including the + * next paragraph) shall be included in all copies or substantial portions + * of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, + * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + * USE OR OTHER DEALINGS IN THE SOFTWARE. + * + **************************************************************************/ +/* + * Authors: Huang Rui + */ + +#ifndef TTM_SET_MEMORY +#define TTM_SET_MEMORY + +#include + +#ifdef CONFIG_X86 + +#include + +static inline int ttm_set_pages_array_wb(struct page **pages, int addrinarray) +{ + return set_pages_array_wb(pages, addrinarray); +} + +static inline int ttm_set_pages_array_wc(struct page **pages, int addrinarray) +{ + return set_pages_array_wc(pages, addrinarray); +} + +static inline int ttm_set_pages_array_uc(struct page **pages, int addrinarray) +{ + return set_pages_array_uc(pages, addrinarray); +} + +static inline int ttm_set_pages_wb(struct page *page, int numpages) +{ + return set_pages_wb(page, numpages); +} + +#else /* for CONFIG_X86 */ + +#if IS_ENABLED(CONFIG_AGP) + +#include + +static inline int ttm_set_pages_array_wb(struct page **pages, int addrinarray) +{ + int i; + + for (i = 0; i < addrinarray; i++) + unmap_page_from_agp(pages[i]); + return 0; +} + +static inline int ttm_set_pages_array_wc(struct page **pages, int addrinarray) +{ + int i; + + for (i = 0; i < addrinarray; i++) + map_page_into_agp(pages[i]); + return 0; +} + +static inline int ttm_set_pages_array_uc(struct page **pages, int addrinarray) +{ + int i; + + for (i = 0; i < addrinarray; i++) + map_page_into_agp(pages[i]); + return 0; +} + +static inline int ttm_set_pages_wb(struct page *page, int numpages) +{ + int i; + + for (i = 0; i < numpages; i++) + unmap_page_from_agp(page++); + return 0; +} + +#else /* for CONFIG_AGP */ + +static inline int ttm_set_pages_array_wb(struct page **pages, int addrinarray) +{ + return 0; +} + +static inline int ttm_set_pages_array_wc(struct page **pages, int addrinarray) +{ + return 0; +} + +static inline int ttm_set_pages_array_uc(struct page **pages, int addrinarray) +{ + return 0; +} + +static inline int ttm_set_pages_wb(struct page *page, int numpages) +{ + return 0; +} + +#endif /* for CONFIG_AGP */ + +#endif /* for CONFIG_X86 */ + +#endif -- cgit v1.2.3 From b67c540b8a987e365dc548e5b2ddf023946e3d63 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Fri, 27 Jul 2018 15:26:56 +0300 Subject: net: dcb: Add priority-to-DSCP map getters On ingress, a network device such as a switch assigns to packets priority based on various criteria. Common options include interpreting PCP and DSCP fields according to user configuration. When a packet egresses the switch, a reverse process may rewrite PCP and/or DSCP values according to packet priority. The following three functions support a) obtaining a DSCP-to-priority map or vice versa, and b) finding default-priority entries in APP database. The DCB subsystem supports for APP entries a very generous M:N mapping between priorities and protocol identifiers. Understandably, several (say) DSCP values can map to the same priority. But this asymmetry holds the other way around as well--one priority can map to several DSCP values. For this reason, the following functions operate in terms of bitmaps, with ones in positions that match some APP entry. - dcb_ieee_getapp_dscp_prio_mask_map() to compute for a given netdevice a map of DSCP-to-priority-mask, which gives for each DSCP value a bitmap of priorities related to that DSCP value by APP, along the lines of dcb_ieee_getapp_mask(). - dcb_ieee_getapp_prio_dscp_mask_map() similarly to compute for a given netdevice a map from priorities to a bitmap of DSCPs. - dcb_ieee_getapp_default_prio_mask() which finds all default-priority rules for a given port in APP database, and returns a mask of priorities allowed by these default-priority rules. Signed-off-by: Petr Machata Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/net/dcbnl.h | 13 ++++++++ net/dcb/dcbnl.c | 86 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 99 insertions(+) (limited to 'include') diff --git a/include/net/dcbnl.h b/include/net/dcbnl.h index 0e5e91be2d30..e22a8a3c089b 100644 --- a/include/net/dcbnl.h +++ b/include/net/dcbnl.h @@ -34,6 +34,19 @@ int dcb_ieee_setapp(struct net_device *, struct dcb_app *); int dcb_ieee_delapp(struct net_device *, struct dcb_app *); u8 dcb_ieee_getapp_mask(struct net_device *, struct dcb_app *); +struct dcb_ieee_app_prio_map { + u64 map[IEEE_8021QAZ_MAX_TCS]; +}; +void dcb_ieee_getapp_prio_dscp_mask_map(const struct net_device *dev, + struct dcb_ieee_app_prio_map *p_map); + +struct dcb_ieee_app_dscp_map { + u8 map[64]; +}; +void dcb_ieee_getapp_dscp_prio_mask_map(const struct net_device *dev, + struct dcb_ieee_app_dscp_map *p_map); +u8 dcb_ieee_getapp_default_prio_mask(const struct net_device *dev); + int dcbnl_ieee_notify(struct net_device *dev, int event, int cmd, u32 seq, u32 pid); int dcbnl_cee_notify(struct net_device *dev, int event, int cmd, diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index 013fdb6fa07a..a556cd708885 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -1958,6 +1958,92 @@ int dcb_ieee_delapp(struct net_device *dev, struct dcb_app *del) } EXPORT_SYMBOL(dcb_ieee_delapp); +/** + * dcb_ieee_getapp_prio_dscp_mask_map - For a given device, find mapping from + * priorities to the DSCP values assigned to that priority. Initialize p_map + * such that each map element holds a bit mask of DSCP values configured for + * that priority by APP entries. + */ +void dcb_ieee_getapp_prio_dscp_mask_map(const struct net_device *dev, + struct dcb_ieee_app_prio_map *p_map) +{ + int ifindex = dev->ifindex; + struct dcb_app_type *itr; + u8 prio; + + memset(p_map->map, 0, sizeof(p_map->map)); + + spin_lock_bh(&dcb_lock); + list_for_each_entry(itr, &dcb_app_list, list) { + if (itr->ifindex == ifindex && + itr->app.selector == IEEE_8021QAZ_APP_SEL_DSCP && + itr->app.protocol < 64 && + itr->app.priority < IEEE_8021QAZ_MAX_TCS) { + prio = itr->app.priority; + p_map->map[prio] |= 1ULL << itr->app.protocol; + } + } + spin_unlock_bh(&dcb_lock); +} +EXPORT_SYMBOL(dcb_ieee_getapp_prio_dscp_mask_map); + +/** + * dcb_ieee_getapp_dscp_prio_mask_map - For a given device, find mapping from + * DSCP values to the priorities assigned to that DSCP value. Initialize p_map + * such that each map element holds a bit mask of priorities configured for a + * given DSCP value by APP entries. + */ +void +dcb_ieee_getapp_dscp_prio_mask_map(const struct net_device *dev, + struct dcb_ieee_app_dscp_map *p_map) +{ + int ifindex = dev->ifindex; + struct dcb_app_type *itr; + + memset(p_map->map, 0, sizeof(p_map->map)); + + spin_lock_bh(&dcb_lock); + list_for_each_entry(itr, &dcb_app_list, list) { + if (itr->ifindex == ifindex && + itr->app.selector == IEEE_8021QAZ_APP_SEL_DSCP && + itr->app.protocol < 64 && + itr->app.priority < IEEE_8021QAZ_MAX_TCS) + p_map->map[itr->app.protocol] |= 1 << itr->app.priority; + } + spin_unlock_bh(&dcb_lock); +} +EXPORT_SYMBOL(dcb_ieee_getapp_dscp_prio_mask_map); + +/** + * Per 802.1Q-2014, the selector value of 1 is used for matching on Ethernet + * type, with valid PID values >= 1536. A special meaning is then assigned to + * protocol value of 0: "default priority. For use when priority is not + * otherwise specified". + * + * dcb_ieee_getapp_default_prio_mask - For a given device, find all APP entries + * of the form {$PRIO, ETHERTYPE, 0} and construct a bit mask of all default + * priorities set by these entries. + */ +u8 dcb_ieee_getapp_default_prio_mask(const struct net_device *dev) +{ + int ifindex = dev->ifindex; + struct dcb_app_type *itr; + u8 mask = 0; + + spin_lock_bh(&dcb_lock); + list_for_each_entry(itr, &dcb_app_list, list) { + if (itr->ifindex == ifindex && + itr->app.selector == IEEE_8021QAZ_APP_SEL_ETHERTYPE && + itr->app.protocol == 0 && + itr->app.priority < IEEE_8021QAZ_MAX_TCS) + mask |= 1 << itr->app.priority; + } + spin_unlock_bh(&dcb_lock); + + return mask; +} +EXPORT_SYMBOL(dcb_ieee_getapp_default_prio_mask); + static int __init dcbnl_init(void) { INIT_LIST_HEAD(&dcb_app_list); -- cgit v1.2.3 From 3ae5536b808dced0af5b2e6768a41862620c779d Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Fri, 27 Jul 2018 10:59:57 +0200 Subject: l2tp: ignore L2TP_ATTR_DATA_SEQ netlink attribute The value of this attribute is never used. Signed-off-by: Guillaume Nault Signed-off-by: David S. Miller --- include/uapi/linux/l2tp.h | 7 ++++--- net/l2tp/l2tp_core.h | 8 -------- net/l2tp/l2tp_debugfs.c | 4 +--- net/l2tp/l2tp_netlink.c | 6 ------ 4 files changed, 5 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/l2tp.h b/include/uapi/linux/l2tp.h index 7d570c7bd117..ae888606b3ec 100644 --- a/include/uapi/linux/l2tp.h +++ b/include/uapi/linux/l2tp.h @@ -65,9 +65,9 @@ struct sockaddr_l2tpip6 { * TUNNEL_MODIFY - CONN_ID, udpcsum * TUNNEL_GETSTATS - CONN_ID, (stats) * TUNNEL_GET - CONN_ID, (...) - * SESSION_CREATE - SESSION_ID, PW_TYPE, data_seq, cookie, peer_cookie, l2spec + * SESSION_CREATE - SESSION_ID, PW_TYPE, cookie, peer_cookie, l2spec * SESSION_DELETE - SESSION_ID - * SESSION_MODIFY - SESSION_ID, data_seq + * SESSION_MODIFY - SESSION_ID * SESSION_GET - SESSION_ID, (...) * SESSION_GETSTATS - SESSION_ID, (stats) * @@ -95,7 +95,7 @@ enum { L2TP_ATTR_PW_TYPE, /* u16, enum l2tp_pwtype */ L2TP_ATTR_ENCAP_TYPE, /* u16, enum l2tp_encap_type */ L2TP_ATTR_OFFSET, /* u16 (not used) */ - L2TP_ATTR_DATA_SEQ, /* u16 */ + L2TP_ATTR_DATA_SEQ, /* u16 (not used) */ L2TP_ATTR_L2SPEC_TYPE, /* u8, enum l2tp_l2spec_type */ L2TP_ATTR_L2SPEC_LEN, /* u8 (not used) */ L2TP_ATTR_PROTO_VERSION, /* u8 */ @@ -169,6 +169,7 @@ enum l2tp_encap_type { L2TP_ENCAPTYPE_IP, }; +/* For L2TP_ATTR_DATA_SEQ. Unused. */ enum l2tp_seqmode { L2TP_SEQ_NONE = 0, L2TP_SEQ_IP = 1, diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index d85fde793a8c..7dbfb55ab3b5 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -45,10 +45,6 @@ struct l2tp_tunnel; */ struct l2tp_session_cfg { enum l2tp_pwtype pw_type; - unsigned int data_seq:2; /* data sequencing level - * 0 => none, 1 => IP only, - * 2 => all - */ unsigned int recv_seq:1; /* expect receive packets with * sequence numbers? */ unsigned int send_seq:1; /* send packets with sequence @@ -99,10 +95,6 @@ struct l2tp_session { char name[32]; /* for logging */ char ifname[IFNAMSIZ]; - unsigned int data_seq:2; /* data sequencing level - * 0 => none, 1 => IP only, - * 2 => all - */ unsigned int recv_seq:1; /* expect receive packets with * sequence numbers? */ unsigned int send_seq:1; /* send packets with sequence diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c index b5d7dde003ef..91b9248610f0 100644 --- a/net/l2tp/l2tp_debugfs.c +++ b/net/l2tp/l2tp_debugfs.c @@ -191,12 +191,10 @@ static void l2tp_dfs_seq_session_show(struct seq_file *m, void *v) if (session->send_seq || session->recv_seq) seq_printf(m, " nr %hu, ns %hu\n", session->nr, session->ns); seq_printf(m, " refcnt %d\n", refcount_read(&session->ref_count)); - seq_printf(m, " config %d/%d/%c/%c/%s/%s %08x %u\n", + seq_printf(m, " config %d/%d/%c/%c/-/%s %08x %u\n", session->mtu, session->mru, session->recv_seq ? 'R' : '-', session->send_seq ? 'S' : '-', - session->data_seq == 1 ? "IPSEQ" : - session->data_seq == 2 ? "DATASEQ" : "-", session->lns_mode ? "LNS" : "LAC", session->debug, jiffies_to_msecs(session->reorder_timeout)); diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index 5b9900889e31..e4785f6966f6 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -560,9 +560,6 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf } if (tunnel->version > 2) { - if (info->attrs[L2TP_ATTR_DATA_SEQ]) - cfg.data_seq = nla_get_u8(info->attrs[L2TP_ATTR_DATA_SEQ]); - if (info->attrs[L2TP_ATTR_L2SPEC_TYPE]) { cfg.l2specific_type = nla_get_u8(info->attrs[L2TP_ATTR_L2SPEC_TYPE]); if (cfg.l2specific_type != L2TP_L2SPECTYPE_DEFAULT && @@ -693,9 +690,6 @@ static int l2tp_nl_cmd_session_modify(struct sk_buff *skb, struct genl_info *inf if (info->attrs[L2TP_ATTR_DEBUG]) session->debug = nla_get_u32(info->attrs[L2TP_ATTR_DEBUG]); - if (info->attrs[L2TP_ATTR_DATA_SEQ]) - session->data_seq = nla_get_u8(info->attrs[L2TP_ATTR_DATA_SEQ]); - if (info->attrs[L2TP_ATTR_RECV_SEQ]) session->recv_seq = nla_get_u8(info->attrs[L2TP_ATTR_RECV_SEQ]); -- cgit v1.2.3 From ae51a7c6d54876c47ae53c455434023df2c19801 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Fri, 27 Jul 2018 10:59:58 +0200 Subject: l2tp: ignore L2TP_ATTR_VLAN_ID netlink attribute The value of this attribute is never used. Signed-off-by: Guillaume Nault Signed-off-by: David S. Miller --- include/uapi/linux/l2tp.h | 4 ++-- net/l2tp/l2tp_core.h | 1 - net/l2tp/l2tp_netlink.c | 3 --- 3 files changed, 2 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/l2tp.h b/include/uapi/linux/l2tp.h index ae888606b3ec..41bf79a4b165 100644 --- a/include/uapi/linux/l2tp.h +++ b/include/uapi/linux/l2tp.h @@ -60,7 +60,7 @@ struct sockaddr_l2tpip6 { /* * Commands. * Valid TLVs of each command are:- - * TUNNEL_CREATE - CONN_ID, pw_type, netns, ifname, ipinfo, udpinfo, udpcsum, vlanid + * TUNNEL_CREATE - CONN_ID, pw_type, netns, ifname, ipinfo, udpinfo, udpcsum * TUNNEL_DELETE - CONN_ID * TUNNEL_MODIFY - CONN_ID, udpcsum * TUNNEL_GETSTATS - CONN_ID, (stats) @@ -105,7 +105,7 @@ enum { L2TP_ATTR_SESSION_ID, /* u32 */ L2TP_ATTR_PEER_SESSION_ID, /* u32 */ L2TP_ATTR_UDP_CSUM, /* u8 */ - L2TP_ATTR_VLAN_ID, /* u16 */ + L2TP_ATTR_VLAN_ID, /* u16 (not used) */ L2TP_ATTR_COOKIE, /* 0, 4 or 8 bytes */ L2TP_ATTR_PEER_COOKIE, /* 0, 4 or 8 bytes */ L2TP_ATTR_DEBUG, /* u32, enum l2tp_debug_flags */ diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 7dbfb55ab3b5..49fd5e05538c 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -54,7 +54,6 @@ struct l2tp_session_cfg { * control of LNS. */ int debug; /* bitmask of debug message * categories */ - u16 vlan_id; /* VLAN pseudowire only */ u16 l2specific_type; /* Layer 2 specific type */ u8 cookie[8]; /* optional cookie */ int cookie_len; /* 0, 4 or 8 bytes */ diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index e4785f6966f6..8ea1deefbc37 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -591,9 +591,6 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf } if (info->attrs[L2TP_ATTR_IFNAME]) cfg.ifname = nla_data(info->attrs[L2TP_ATTR_IFNAME]); - - if (info->attrs[L2TP_ATTR_VLAN_ID]) - cfg.vlan_id = nla_get_u16(info->attrs[L2TP_ATTR_VLAN_ID]); } if (info->attrs[L2TP_ATTR_DEBUG]) -- cgit v1.2.3 From 92ea4a7eec7289468ac8de5386f4b13d9c210cb5 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Fri, 27 Jul 2018 11:00:00 +0200 Subject: l2tp: drop ->mru from struct l2tp_session This field is not used. Treat PPPIOC*MRU the same way as PPPIOC*FLAGS: "get" requests return 0, while "set" requests vadidate the user supplied pointer but discard its value. Signed-off-by: Guillaume Nault Signed-off-by: David S. Miller --- include/uapi/linux/l2tp.h | 2 +- net/l2tp/l2tp_core.c | 1 - net/l2tp/l2tp_core.h | 2 -- net/l2tp/l2tp_debugfs.c | 4 ++-- net/l2tp/l2tp_netlink.c | 10 +--------- net/l2tp/l2tp_ppp.c | 41 +++++------------------------------------ 6 files changed, 9 insertions(+), 51 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/l2tp.h b/include/uapi/linux/l2tp.h index 41bf79a4b165..8bb8c7cfabe5 100644 --- a/include/uapi/linux/l2tp.h +++ b/include/uapi/linux/l2tp.h @@ -120,7 +120,7 @@ enum { L2TP_ATTR_UDP_SPORT, /* u16 */ L2TP_ATTR_UDP_DPORT, /* u16 */ L2TP_ATTR_MTU, /* u16 */ - L2TP_ATTR_MRU, /* u16 */ + L2TP_ATTR_MRU, /* u16 (not used) */ L2TP_ATTR_STATS, /* nested */ L2TP_ATTR_IP6_SADDR, /* struct in6_addr */ L2TP_ATTR_IP6_DADDR, /* struct in6_addr */ diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index d10f4ed52d92..c61a467fd9b8 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1675,7 +1675,6 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn session->pwtype = cfg->pw_type; session->debug = cfg->debug; session->mtu = cfg->mtu; - session->mru = cfg->mru; session->send_seq = cfg->send_seq; session->recv_seq = cfg->recv_seq; session->lns_mode = cfg->lns_mode; diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 49fd5e05538c..fa5ae9432d38 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -62,7 +62,6 @@ struct l2tp_session_cfg { int reorder_timeout; /* configured reorder timeout * (in jiffies) */ int mtu; - int mru; char *ifname; }; @@ -107,7 +106,6 @@ struct l2tp_session { * (in jiffies) */ int reorder_skip; /* set if skip to next nr */ int mtu; - int mru; enum l2tp_pwtype pwtype; struct l2tp_stats stats; struct hlist_node global_hlist; /* Global hash list node */ diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c index 91b9248610f0..aee271741f5b 100644 --- a/net/l2tp/l2tp_debugfs.c +++ b/net/l2tp/l2tp_debugfs.c @@ -191,8 +191,8 @@ static void l2tp_dfs_seq_session_show(struct seq_file *m, void *v) if (session->send_seq || session->recv_seq) seq_printf(m, " nr %hu, ns %hu\n", session->nr, session->ns); seq_printf(m, " refcnt %d\n", refcount_read(&session->ref_count)); - seq_printf(m, " config %d/%d/%c/%c/-/%s %08x %u\n", - session->mtu, session->mru, + seq_printf(m, " config %d/0/%c/%c/-/%s %08x %u\n", + session->mtu, session->recv_seq ? 'R' : '-', session->send_seq ? 'S' : '-', session->lns_mode ? "LNS" : "LAC", diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index 8ea1deefbc37..a7c409215336 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -611,9 +611,6 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf if (info->attrs[L2TP_ATTR_MTU]) cfg.mtu = nla_get_u16(info->attrs[L2TP_ATTR_MTU]); - if (info->attrs[L2TP_ATTR_MRU]) - cfg.mru = nla_get_u16(info->attrs[L2TP_ATTR_MRU]); - #ifdef CONFIG_MODULES if (l2tp_nl_cmd_ops[cfg.pw_type] == NULL) { genl_unlock(); @@ -704,9 +701,6 @@ static int l2tp_nl_cmd_session_modify(struct sk_buff *skb, struct genl_info *inf if (info->attrs[L2TP_ATTR_MTU]) session->mtu = nla_get_u16(info->attrs[L2TP_ATTR_MTU]); - if (info->attrs[L2TP_ATTR_MRU]) - session->mru = nla_get_u16(info->attrs[L2TP_ATTR_MRU]); - ret = l2tp_session_notify(&l2tp_nl_family, info, session, L2TP_CMD_SESSION_MODIFY); @@ -737,9 +731,7 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq, int fl session->peer_session_id) || nla_put_u32(skb, L2TP_ATTR_DEBUG, session->debug) || nla_put_u16(skb, L2TP_ATTR_PW_TYPE, session->pwtype) || - nla_put_u16(skb, L2TP_ATTR_MTU, session->mtu) || - (session->mru && - nla_put_u16(skb, L2TP_ATTR_MRU, session->mru))) + nla_put_u16(skb, L2TP_ATTR_MTU, session->mtu)) goto nla_put_failure; if ((session->ifname[0] && diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 759ce8421269..44cac66284a5 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -570,10 +570,9 @@ static void pppol2tp_session_init(struct l2tp_session *session) if (dst) { u32 pmtu = dst_mtu(dst); - if (pmtu) { + if (pmtu) session->mtu = pmtu - PPPOL2TP_HEADER_OVERHEAD; - session->mru = pmtu - PPPOL2TP_HEADER_OVERHEAD; - } + dst_release(dst); } } @@ -781,7 +780,6 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, } else { /* Default MTU must allow space for UDP/L2TP/PPP headers */ cfg.mtu = 1500 - PPPOL2TP_HEADER_OVERHEAD; - cfg.mru = cfg.mtu; cfg.pw_type = L2TP_PWTYPE_PPP; session = l2tp_session_create(sizeof(struct pppol2tp_session), @@ -885,8 +883,6 @@ static int pppol2tp_session_create(struct net *net, struct l2tp_tunnel *tunnel, /* Default MTU values. */ if (cfg->mtu == 0) cfg->mtu = 1500 - PPPOL2TP_HEADER_OVERHEAD; - if (cfg->mru == 0) - cfg->mru = cfg->mtu; /* Allocate and initialize a new session context. */ session = l2tp_session_create(sizeof(struct pppol2tp_session), @@ -1101,34 +1097,6 @@ static int pppol2tp_session_ioctl(struct l2tp_session *session, break; case PPPIOCGMRU: - err = -ENXIO; - if (!(sk->sk_state & PPPOX_CONNECTED)) - break; - - err = -EFAULT; - if (put_user(session->mru, (int __user *) arg)) - break; - - l2tp_info(session, L2TP_MSG_CONTROL, "%s: get mru=%d\n", - session->name, session->mru); - err = 0; - break; - - case PPPIOCSMRU: - err = -ENXIO; - if (!(sk->sk_state & PPPOX_CONNECTED)) - break; - - err = -EFAULT; - if (get_user(val, (int __user *) arg)) - break; - - session->mru = val; - l2tp_info(session, L2TP_MSG_CONTROL, "%s: set mru=%d\n", - session->name, session->mru); - err = 0; - break; - case PPPIOCGFLAGS: err = -EFAULT; if (put_user(0, (int __user *)arg)) @@ -1136,6 +1104,7 @@ static int pppol2tp_session_ioctl(struct l2tp_session *session, err = 0; break; + case PPPIOCSMRU: case PPPIOCSFLAGS: err = -EFAULT; if (get_user(val, (int __user *)arg)) @@ -1723,8 +1692,8 @@ static void pppol2tp_seq_session_show(struct seq_file *m, void *v) tunnel->peer_tunnel_id, session->peer_session_id, state, user_data_ok); - seq_printf(m, " %d/%d/%c/%c/%s %08x %u\n", - session->mtu, session->mru, + seq_printf(m, " %d/0/%c/%c/%s %08x %u\n", + session->mtu, session->recv_seq ? 'R' : '-', session->send_seq ? 'S' : '-', session->lns_mode ? "LNS" : "LAC", -- cgit v1.2.3 From 22a65aa8b1a84ca429c0fc8415dee5681ab36eb3 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Mon, 25 Dec 2017 18:40:52 +0200 Subject: net/mlx5e: Vxlan, check maximum number of UDP ports The NIC has a limited number of offloaded VXLAN UDP ports (usually 4). Instead of letting the firmware fail when trying to add more ports than it can handle, let the driver check it on its own. Signed-off-by: Gal Pressman Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 1 + drivers/net/ethernet/mellanox/mlx5/core/vxlan.c | 14 ++++++++++++++ include/linux/mlx5/mlx5_ifc.h | 4 +++- 3 files changed, 18 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index c41cfc2a4b70..c4d4db8722f5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -657,6 +657,7 @@ enum { struct mlx5e_vxlan_db { spinlock_t lock; /* protect vxlan table */ struct radix_tree_root tree; + int num_ports; }; struct mlx5e_l2_rule { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c index 2f699998d13e..e3af2efe18ce 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c @@ -52,6 +52,11 @@ void mlx5e_vxlan_init(struct mlx5e_priv *priv) mlx5e_vxlan_add_port(priv, 4789); } +static inline u8 mlx5e_vxlan_max_udp_ports(struct mlx5_core_dev *mdev) +{ + return MLX5_CAP_ETH(mdev, max_vxlan_udp_ports) ?: 4; +} + static int mlx5e_vxlan_core_add_port_cmd(struct mlx5_core_dev *mdev, u16 port) { u32 in[MLX5_ST_SZ_DW(add_vxlan_udp_dport_in)] = {0}; @@ -98,6 +103,13 @@ static void mlx5e_vxlan_add_port(struct mlx5e_priv *priv, u16 port) return; } + if (vxlan_db->num_ports >= mlx5e_vxlan_max_udp_ports(priv->mdev)) { + netdev_info(priv->netdev, + "UDP port (%d) not offloaded, max number of UDP ports (%d) are already offloaded\n", + port, mlx5e_vxlan_max_udp_ports(priv->mdev)); + return; + } + if (mlx5e_vxlan_core_add_port_cmd(priv->mdev, port)) return; @@ -114,6 +126,7 @@ static void mlx5e_vxlan_add_port(struct mlx5e_priv *priv, u16 port) if (err) goto err_free; + vxlan_db->num_ports++; return; err_free: @@ -163,6 +176,7 @@ out_unlock: if (remove) { mlx5e_vxlan_core_del_port_cmd(priv->mdev, port); kfree(vxlan); + vxlan_db->num_ports--; } mutex_unlock(&priv->state_lock); kfree(vxlan_work); diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 22f54bedfaae..60c2308fe062 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -668,7 +668,9 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits { u8 swp[0x1]; u8 swp_csum[0x1]; u8 swp_lso[0x1]; - u8 reserved_at_23[0x1b]; + u8 reserved_at_23[0xd]; + u8 max_vxlan_udp_ports[0x8]; + u8 reserved_at_38[0x6]; u8 max_geneve_opt_len[0x1]; u8 tunnel_stateless_geneve_rx[0x1]; -- cgit v1.2.3 From 358aa5ce288aa1085f0f3ef9f315119563fa6541 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Wed, 9 May 2018 13:28:00 -0700 Subject: net/mlx5e: Vxlan, move vxlan logic to core driver Move vxlan logic and objects to mlx5 core dirver. Since it going to be used from different mlx5 interfaces. e.g. mlx5e PF NIC netdev and mlx5e E-Switch representors. Signed-off-by: Saeed Mahameed Reviewed-by: Or Gerlitz --- drivers/net/ethernet/mellanox/mlx5/core/Makefile | 4 +- drivers/net/ethernet/mellanox/mlx5/core/en.h | 2 - drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 21 +- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 6 +- .../net/ethernet/mellanox/mlx5/core/lib/vxlan.c | 230 +++++++++++++++++++++ .../net/ethernet/mellanox/mlx5/core/lib/vxlan.h | 64 ++++++ drivers/net/ethernet/mellanox/mlx5/core/main.c | 5 + drivers/net/ethernet/mellanox/mlx5/core/vxlan.c | 230 --------------------- drivers/net/ethernet/mellanox/mlx5/core/vxlan.h | 64 ------ include/linux/mlx5/driver.h | 2 + 10 files changed, 315 insertions(+), 313 deletions(-) create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h delete mode 100644 drivers/net/ethernet/mellanox/mlx5/core/vxlan.c delete mode 100644 drivers/net/ethernet/mellanox/mlx5/core/vxlan.h (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index ae2bdcb1647c..f20fda1ced4f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -14,8 +14,8 @@ mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o \ fpga/ipsec.o fpga/tls.o mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \ - en_tx.o en_rx.o en_dim.o en_txrx.o en/xdp.o en_stats.o vxlan.o \ - en_arfs.o en_fs_ethtool.o en_selftest.o en/port.o + en_tx.o en_rx.o en_dim.o en_txrx.o en/xdp.o en_stats.o \ + en_arfs.o en_fs_ethtool.o en_selftest.o en/port.o lib/vxlan.o mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 1bd4536b9061..c7ed3d20fd54 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -52,7 +52,6 @@ #include "wq.h" #include "mlx5_core.h" #include "en_stats.h" -#include "vxlan.h" struct page_pool; @@ -812,7 +811,6 @@ struct mlx5e_priv { u32 tx_rates[MLX5E_MAX_NUM_SQS]; struct mlx5e_flow_steering fs; - struct mlx5_vxlan *vxlan; struct workqueue_struct *wq; struct work_struct update_carrier_work; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index ef4b2f0c427c..fde35021a257 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -45,7 +45,7 @@ #include "en_accel/tls.h" #include "accel/ipsec.h" #include "accel/tls.h" -#include "vxlan.h" +#include "lib/vxlan.h" #include "en/port.h" #include "en/xdp.h" @@ -2974,7 +2974,7 @@ int mlx5e_open(struct net_device *netdev) mlx5_set_port_admin_status(priv->mdev, MLX5_PORT_UP); mutex_unlock(&priv->state_lock); - if (mlx5_vxlan_allowed(priv->vxlan)) + if (mlx5_vxlan_allowed(priv->mdev->vxlan)) udp_tunnel_get_rx_info(netdev); return err; @@ -3983,7 +3983,7 @@ static void mlx5e_vxlan_add_work(struct work_struct *work) u16 port = vxlan_work->port; mutex_lock(&priv->state_lock); - mlx5_vxlan_add_port(priv->vxlan, port); + mlx5_vxlan_add_port(priv->mdev->vxlan, port); mutex_unlock(&priv->state_lock); kfree(vxlan_work); @@ -3997,7 +3997,7 @@ static void mlx5e_vxlan_del_work(struct work_struct *work) u16 port = vxlan_work->port; mutex_lock(&priv->state_lock); - mlx5_vxlan_del_port(priv->vxlan, port); + mlx5_vxlan_del_port(priv->mdev->vxlan, port); mutex_unlock(&priv->state_lock); kfree(vxlan_work); } @@ -4028,7 +4028,7 @@ static void mlx5e_add_vxlan_port(struct net_device *netdev, if (ti->type != UDP_TUNNEL_TYPE_VXLAN) return; - if (!mlx5_vxlan_allowed(priv->vxlan)) + if (!mlx5_vxlan_allowed(priv->mdev->vxlan)) return; mlx5e_vxlan_queue_work(priv, be16_to_cpu(ti->port), 1); @@ -4042,7 +4042,7 @@ static void mlx5e_del_vxlan_port(struct net_device *netdev, if (ti->type != UDP_TUNNEL_TYPE_VXLAN) return; - if (!mlx5_vxlan_allowed(priv->vxlan)) + if (!mlx5_vxlan_allowed(priv->mdev->vxlan)) return; mlx5e_vxlan_queue_work(priv, be16_to_cpu(ti->port), 0); @@ -4076,7 +4076,7 @@ static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv, port = be16_to_cpu(udph->dest); /* Verify if UDP port is being offloaded by HW */ - if (mlx5_vxlan_lookup_port(priv->vxlan, port)) + if (mlx5_vxlan_lookup_port(priv->mdev->vxlan, port)) return features; } @@ -4648,7 +4648,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER; netdev->hw_features |= NETIF_F_HW_VLAN_STAG_TX; - if (mlx5_vxlan_allowed(priv->vxlan) || MLX5_CAP_ETH(mdev, tunnel_stateless_gre)) { + if (mlx5_vxlan_allowed(mdev->vxlan) || MLX5_CAP_ETH(mdev, tunnel_stateless_gre)) { netdev->hw_enc_features |= NETIF_F_IP_CSUM; netdev->hw_enc_features |= NETIF_F_IPV6_CSUM; netdev->hw_enc_features |= NETIF_F_TSO; @@ -4656,7 +4656,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) netdev->hw_enc_features |= NETIF_F_GSO_PARTIAL; } - if (mlx5_vxlan_allowed(priv->vxlan)) { + if (mlx5_vxlan_allowed(mdev->vxlan)) { netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_UDP_TUNNEL_CSUM; netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL | @@ -4758,8 +4758,6 @@ static void mlx5e_nic_init(struct mlx5_core_dev *mdev, struct mlx5e_priv *priv = netdev_priv(netdev); int err; - priv->vxlan = mlx5_vxlan_create(mdev); - mlx5e_build_nic_netdev_priv(mdev, netdev, profile, ppriv); err = mlx5e_ipsec_init(priv); if (err) @@ -4773,7 +4771,6 @@ static void mlx5e_nic_init(struct mlx5_core_dev *mdev, static void mlx5e_nic_cleanup(struct mlx5e_priv *priv) { - mlx5_vxlan_destroy(priv->vxlan); mlx5e_tls_cleanup(priv); mlx5e_ipsec_cleanup(priv); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 1b4931b62094..288a57f76e84 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -50,7 +50,7 @@ #include "en_rep.h" #include "en_tc.h" #include "eswitch.h" -#include "vxlan.h" +#include "lib/vxlan.h" #include "fs_core.h" #include "en/port.h" @@ -1133,7 +1133,7 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv, if (memchr_inv(&mask->dst, 0xff, sizeof(mask->dst))) goto vxlan_match_offload_err; - if (mlx5_vxlan_lookup_port(up_priv->vxlan, be16_to_cpu(key->dst)) && + if (mlx5_vxlan_lookup_port(up_priv->mdev->vxlan, be16_to_cpu(key->dst)) && MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap)) parse_vxlan_attr(spec, f); else { @@ -2557,7 +2557,7 @@ vxlan_encap_offload_err: return -EOPNOTSUPP; } - if (mlx5_vxlan_lookup_port(up_priv->vxlan, be16_to_cpu(key->tp_dst)) && + if (mlx5_vxlan_lookup_port(up_priv->mdev->vxlan, be16_to_cpu(key->tp_dst)) && MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap)) { tunnel_type = MLX5_HEADER_TYPE_VXLAN; } else { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c new file mode 100644 index 000000000000..9a8fd762167b --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c @@ -0,0 +1,230 @@ +/* + * Copyright (c) 2016, Mellanox Technologies, Ltd. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include +#include +#include +#include "mlx5_core.h" +#include "vxlan.h" + +struct mlx5_vxlan { + struct mlx5_core_dev *mdev; + spinlock_t lock; /* protect vxlan table */ + /* max_num_ports is usuallly 4, 16 buckets is more than enough */ + DECLARE_HASHTABLE(htable, 4); + int num_ports; + struct mutex sync_lock; /* sync add/del port HW operations */ +}; + +struct mlx5_vxlan_port { + struct hlist_node hlist; + atomic_t refcount; + u16 udp_port; +}; + +static inline u8 mlx5_vxlan_max_udp_ports(struct mlx5_core_dev *mdev) +{ + return MLX5_CAP_ETH(mdev, max_vxlan_udp_ports) ?: 4; +} + +static int mlx5_vxlan_core_add_port_cmd(struct mlx5_core_dev *mdev, u16 port) +{ + u32 in[MLX5_ST_SZ_DW(add_vxlan_udp_dport_in)] = {0}; + u32 out[MLX5_ST_SZ_DW(add_vxlan_udp_dport_out)] = {0}; + + MLX5_SET(add_vxlan_udp_dport_in, in, opcode, + MLX5_CMD_OP_ADD_VXLAN_UDP_DPORT); + MLX5_SET(add_vxlan_udp_dport_in, in, vxlan_udp_port, port); + return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); +} + +static int mlx5_vxlan_core_del_port_cmd(struct mlx5_core_dev *mdev, u16 port) +{ + u32 in[MLX5_ST_SZ_DW(delete_vxlan_udp_dport_in)] = {0}; + u32 out[MLX5_ST_SZ_DW(delete_vxlan_udp_dport_out)] = {0}; + + MLX5_SET(delete_vxlan_udp_dport_in, in, opcode, + MLX5_CMD_OP_DELETE_VXLAN_UDP_DPORT); + MLX5_SET(delete_vxlan_udp_dport_in, in, vxlan_udp_port, port); + return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); +} + +static struct mlx5_vxlan_port* +mlx5_vxlan_lookup_port_locked(struct mlx5_vxlan *vxlan, u16 port) +{ + struct mlx5_vxlan_port *vxlanp; + + hash_for_each_possible(vxlan->htable, vxlanp, hlist, port) { + if (vxlanp->udp_port == port) + return vxlanp; + } + + return NULL; +} + +struct mlx5_vxlan_port *mlx5_vxlan_lookup_port(struct mlx5_vxlan *vxlan, u16 port) +{ + struct mlx5_vxlan_port *vxlanp; + + if (!mlx5_vxlan_allowed(vxlan)) + return NULL; + + spin_lock_bh(&vxlan->lock); + vxlanp = mlx5_vxlan_lookup_port_locked(vxlan, port); + spin_unlock_bh(&vxlan->lock); + + return vxlanp; +} + +int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port) +{ + struct mlx5_vxlan_port *vxlanp; + int ret = -ENOSPC; + + vxlanp = mlx5_vxlan_lookup_port(vxlan, port); + if (vxlanp) { + atomic_inc(&vxlanp->refcount); + return 0; + } + + mutex_lock(&vxlan->sync_lock); + if (vxlan->num_ports >= mlx5_vxlan_max_udp_ports(vxlan->mdev)) { + mlx5_core_info(vxlan->mdev, + "UDP port (%d) not offloaded, max number of UDP ports (%d) are already offloaded\n", + port, mlx5_vxlan_max_udp_ports(vxlan->mdev)); + ret = -ENOSPC; + goto unlock; + } + + ret = mlx5_vxlan_core_add_port_cmd(vxlan->mdev, port); + if (ret) + goto unlock; + + vxlanp = kzalloc(sizeof(*vxlanp), GFP_KERNEL); + if (!vxlanp) { + ret = -ENOMEM; + goto err_delete_port; + } + + vxlanp->udp_port = port; + atomic_set(&vxlanp->refcount, 1); + + spin_lock_bh(&vxlan->lock); + hash_add(vxlan->htable, &vxlanp->hlist, port); + spin_unlock_bh(&vxlan->lock); + + vxlan->num_ports++; + mutex_unlock(&vxlan->sync_lock); + return 0; + +err_delete_port: + mlx5_vxlan_core_del_port_cmd(vxlan->mdev, port); + +unlock: + mutex_unlock(&vxlan->sync_lock); + return ret; +} + +int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port) +{ + struct mlx5_vxlan_port *vxlanp; + bool remove = false; + int ret = 0; + + mutex_lock(&vxlan->sync_lock); + + spin_lock_bh(&vxlan->lock); + vxlanp = mlx5_vxlan_lookup_port_locked(vxlan, port); + if (!vxlanp) { + ret = -ENOENT; + goto out_unlock; + } + + if (atomic_dec_and_test(&vxlanp->refcount)) { + hash_del(&vxlanp->hlist); + remove = true; + } + +out_unlock: + spin_unlock_bh(&vxlan->lock); + + if (remove) { + mlx5_vxlan_core_del_port_cmd(vxlan->mdev, port); + kfree(vxlanp); + vxlan->num_ports--; + } + + mutex_unlock(&vxlan->sync_lock); + + return ret; +} + +struct mlx5_vxlan *mlx5_vxlan_create(struct mlx5_core_dev *mdev) +{ + struct mlx5_vxlan *vxlan; + + if (!MLX5_CAP_ETH(mdev, tunnel_stateless_vxlan) || !mlx5_core_is_pf(mdev)) + return ERR_PTR(-ENOTSUPP); + + vxlan = kzalloc(sizeof(*vxlan), GFP_KERNEL); + if (!vxlan) + return ERR_PTR(-ENOMEM); + + vxlan->mdev = mdev; + mutex_init(&vxlan->sync_lock); + spin_lock_init(&vxlan->lock); + hash_init(vxlan->htable); + + /* Hardware adds 4789 by default */ + mlx5_vxlan_add_port(vxlan, 4789); + + return vxlan; +} + +void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan) +{ + struct mlx5_vxlan_port *vxlanp; + struct hlist_node *tmp; + int bkt; + + if (!mlx5_vxlan_allowed(vxlan)) + return; + + /* Lockless since we are the only hash table consumers*/ + hash_for_each_safe(vxlan->htable, bkt, tmp, vxlanp, hlist) { + hash_del(&vxlanp->hlist); + mlx5_vxlan_core_del_port_cmd(vxlan->mdev, vxlanp->udp_port); + kfree(vxlanp); + } + + kfree(vxlan); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h new file mode 100644 index 000000000000..fd874a30c4d0 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h @@ -0,0 +1,64 @@ +/* + * Copyright (c) 2016, Mellanox Technologies, Ltd. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ +#ifndef __MLX5_VXLAN_H__ +#define __MLX5_VXLAN_H__ + +#include + +struct mlx5_vxlan; +struct mlx5_vxlan_port; + +#ifdef CONFIG_MLX5_CORE_EN + +static inline bool mlx5_vxlan_allowed(struct mlx5_vxlan *vxlan) +{ + /* not allowed reason is encoded in vxlan pointer as error, + * on mlx5_vxlan_create + */ + return !IS_ERR_OR_NULL(vxlan); +} + +struct mlx5_vxlan *mlx5_vxlan_create(struct mlx5_core_dev *mdev); +void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan); +int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port); +int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port); +struct mlx5_vxlan_port *mlx5_vxlan_lookup_port(struct mlx5_vxlan *vxlan, u16 port); + +#else + +static inline struct mlx5_vxlan* +mlx5_vxlan_create(struct mlx5_core_dev *mdev) { return ERR_PTR(-ENOTSUPP); } +static inline void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan) { return; } + +#endif + +#endif /* __MLX5_VXLAN_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 6ddbb70e95de..03b9c6733eed 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -62,6 +62,7 @@ #include "accel/ipsec.h" #include "accel/tls.h" #include "lib/clock.h" +#include "lib/vxlan.h" #include "diag/fw_tracer.h" MODULE_AUTHOR("Eli Cohen "); @@ -961,6 +962,8 @@ static int mlx5_init_once(struct mlx5_core_dev *dev, struct mlx5_priv *priv) mlx5_init_clock(dev); + dev->vxlan = mlx5_vxlan_create(dev); + err = mlx5_init_rl_table(dev); if (err) { dev_err(&pdev->dev, "Failed to init rate limiting\n"); @@ -1004,6 +1007,7 @@ err_mpfs_cleanup: err_rl_cleanup: mlx5_cleanup_rl_table(dev); err_tables_cleanup: + mlx5_vxlan_destroy(dev->vxlan); mlx5_cleanup_mkey_table(dev); mlx5_cleanup_srq_table(dev); mlx5_cleanup_qp_table(dev); @@ -1024,6 +1028,7 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev) mlx5_eswitch_cleanup(dev->priv.eswitch); mlx5_mpfs_cleanup(dev); mlx5_cleanup_rl_table(dev); + mlx5_vxlan_destroy(dev->vxlan); mlx5_cleanup_clock(dev); mlx5_cleanup_reserved_gids(dev); mlx5_cleanup_mkey_table(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c deleted file mode 100644 index 9a8fd762167b..000000000000 --- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c +++ /dev/null @@ -1,230 +0,0 @@ -/* - * Copyright (c) 2016, Mellanox Technologies, Ltd. All rights reserved. - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed under the terms of the GNU - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and/or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. - */ - -#include -#include -#include -#include "mlx5_core.h" -#include "vxlan.h" - -struct mlx5_vxlan { - struct mlx5_core_dev *mdev; - spinlock_t lock; /* protect vxlan table */ - /* max_num_ports is usuallly 4, 16 buckets is more than enough */ - DECLARE_HASHTABLE(htable, 4); - int num_ports; - struct mutex sync_lock; /* sync add/del port HW operations */ -}; - -struct mlx5_vxlan_port { - struct hlist_node hlist; - atomic_t refcount; - u16 udp_port; -}; - -static inline u8 mlx5_vxlan_max_udp_ports(struct mlx5_core_dev *mdev) -{ - return MLX5_CAP_ETH(mdev, max_vxlan_udp_ports) ?: 4; -} - -static int mlx5_vxlan_core_add_port_cmd(struct mlx5_core_dev *mdev, u16 port) -{ - u32 in[MLX5_ST_SZ_DW(add_vxlan_udp_dport_in)] = {0}; - u32 out[MLX5_ST_SZ_DW(add_vxlan_udp_dport_out)] = {0}; - - MLX5_SET(add_vxlan_udp_dport_in, in, opcode, - MLX5_CMD_OP_ADD_VXLAN_UDP_DPORT); - MLX5_SET(add_vxlan_udp_dport_in, in, vxlan_udp_port, port); - return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); -} - -static int mlx5_vxlan_core_del_port_cmd(struct mlx5_core_dev *mdev, u16 port) -{ - u32 in[MLX5_ST_SZ_DW(delete_vxlan_udp_dport_in)] = {0}; - u32 out[MLX5_ST_SZ_DW(delete_vxlan_udp_dport_out)] = {0}; - - MLX5_SET(delete_vxlan_udp_dport_in, in, opcode, - MLX5_CMD_OP_DELETE_VXLAN_UDP_DPORT); - MLX5_SET(delete_vxlan_udp_dport_in, in, vxlan_udp_port, port); - return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); -} - -static struct mlx5_vxlan_port* -mlx5_vxlan_lookup_port_locked(struct mlx5_vxlan *vxlan, u16 port) -{ - struct mlx5_vxlan_port *vxlanp; - - hash_for_each_possible(vxlan->htable, vxlanp, hlist, port) { - if (vxlanp->udp_port == port) - return vxlanp; - } - - return NULL; -} - -struct mlx5_vxlan_port *mlx5_vxlan_lookup_port(struct mlx5_vxlan *vxlan, u16 port) -{ - struct mlx5_vxlan_port *vxlanp; - - if (!mlx5_vxlan_allowed(vxlan)) - return NULL; - - spin_lock_bh(&vxlan->lock); - vxlanp = mlx5_vxlan_lookup_port_locked(vxlan, port); - spin_unlock_bh(&vxlan->lock); - - return vxlanp; -} - -int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port) -{ - struct mlx5_vxlan_port *vxlanp; - int ret = -ENOSPC; - - vxlanp = mlx5_vxlan_lookup_port(vxlan, port); - if (vxlanp) { - atomic_inc(&vxlanp->refcount); - return 0; - } - - mutex_lock(&vxlan->sync_lock); - if (vxlan->num_ports >= mlx5_vxlan_max_udp_ports(vxlan->mdev)) { - mlx5_core_info(vxlan->mdev, - "UDP port (%d) not offloaded, max number of UDP ports (%d) are already offloaded\n", - port, mlx5_vxlan_max_udp_ports(vxlan->mdev)); - ret = -ENOSPC; - goto unlock; - } - - ret = mlx5_vxlan_core_add_port_cmd(vxlan->mdev, port); - if (ret) - goto unlock; - - vxlanp = kzalloc(sizeof(*vxlanp), GFP_KERNEL); - if (!vxlanp) { - ret = -ENOMEM; - goto err_delete_port; - } - - vxlanp->udp_port = port; - atomic_set(&vxlanp->refcount, 1); - - spin_lock_bh(&vxlan->lock); - hash_add(vxlan->htable, &vxlanp->hlist, port); - spin_unlock_bh(&vxlan->lock); - - vxlan->num_ports++; - mutex_unlock(&vxlan->sync_lock); - return 0; - -err_delete_port: - mlx5_vxlan_core_del_port_cmd(vxlan->mdev, port); - -unlock: - mutex_unlock(&vxlan->sync_lock); - return ret; -} - -int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port) -{ - struct mlx5_vxlan_port *vxlanp; - bool remove = false; - int ret = 0; - - mutex_lock(&vxlan->sync_lock); - - spin_lock_bh(&vxlan->lock); - vxlanp = mlx5_vxlan_lookup_port_locked(vxlan, port); - if (!vxlanp) { - ret = -ENOENT; - goto out_unlock; - } - - if (atomic_dec_and_test(&vxlanp->refcount)) { - hash_del(&vxlanp->hlist); - remove = true; - } - -out_unlock: - spin_unlock_bh(&vxlan->lock); - - if (remove) { - mlx5_vxlan_core_del_port_cmd(vxlan->mdev, port); - kfree(vxlanp); - vxlan->num_ports--; - } - - mutex_unlock(&vxlan->sync_lock); - - return ret; -} - -struct mlx5_vxlan *mlx5_vxlan_create(struct mlx5_core_dev *mdev) -{ - struct mlx5_vxlan *vxlan; - - if (!MLX5_CAP_ETH(mdev, tunnel_stateless_vxlan) || !mlx5_core_is_pf(mdev)) - return ERR_PTR(-ENOTSUPP); - - vxlan = kzalloc(sizeof(*vxlan), GFP_KERNEL); - if (!vxlan) - return ERR_PTR(-ENOMEM); - - vxlan->mdev = mdev; - mutex_init(&vxlan->sync_lock); - spin_lock_init(&vxlan->lock); - hash_init(vxlan->htable); - - /* Hardware adds 4789 by default */ - mlx5_vxlan_add_port(vxlan, 4789); - - return vxlan; -} - -void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan) -{ - struct mlx5_vxlan_port *vxlanp; - struct hlist_node *tmp; - int bkt; - - if (!mlx5_vxlan_allowed(vxlan)) - return; - - /* Lockless since we are the only hash table consumers*/ - hash_for_each_safe(vxlan->htable, bkt, tmp, vxlanp, hlist) { - hash_del(&vxlanp->hlist); - mlx5_vxlan_core_del_port_cmd(vxlan->mdev, vxlanp->udp_port); - kfree(vxlanp); - } - - kfree(vxlan); -} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h deleted file mode 100644 index fd874a30c4d0..000000000000 --- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h +++ /dev/null @@ -1,64 +0,0 @@ -/* - * Copyright (c) 2016, Mellanox Technologies, Ltd. All rights reserved. - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed under the terms of the GNU - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and/or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. - */ -#ifndef __MLX5_VXLAN_H__ -#define __MLX5_VXLAN_H__ - -#include - -struct mlx5_vxlan; -struct mlx5_vxlan_port; - -#ifdef CONFIG_MLX5_CORE_EN - -static inline bool mlx5_vxlan_allowed(struct mlx5_vxlan *vxlan) -{ - /* not allowed reason is encoded in vxlan pointer as error, - * on mlx5_vxlan_create - */ - return !IS_ERR_OR_NULL(vxlan); -} - -struct mlx5_vxlan *mlx5_vxlan_create(struct mlx5_core_dev *mdev); -void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan); -int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port); -int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port); -struct mlx5_vxlan_port *mlx5_vxlan_lookup_port(struct mlx5_vxlan *vxlan, u16 port); - -#else - -static inline struct mlx5_vxlan* -mlx5_vxlan_create(struct mlx5_core_dev *mdev) { return ERR_PTR(-ENOTSUPP); } -static inline void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan) { return; } - -#endif - -#endif /* __MLX5_VXLAN_H__ */ diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index fd0aaa5568fe..54f385cc8811 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -818,6 +818,7 @@ struct mlx5_clock { }; struct mlx5_fw_tracer; +struct mlx5_vxlan; struct mlx5_core_dev { struct pci_dev *pdev; @@ -850,6 +851,7 @@ struct mlx5_core_dev { atomic_t num_qps; u32 issi; struct mlx5e_resources mlx5e_res; + struct mlx5_vxlan *vxlan; struct { struct mlx5_rsvd_gids reserved_gids; u32 roce_en; -- cgit v1.2.3 From 627448e85c766587f6fdde1ea3886d6615081c77 Mon Sep 17 00:00:00 2001 From: Tomas Winkler Date: Thu, 28 Jun 2018 18:13:33 +0300 Subject: tpm: separate cmd_ready/go_idle from runtime_pm Fix tpm ptt initialization error: tpm tpm0: A TPM error (378) occurred get tpm pcr allocation. We cannot use go_idle cmd_ready commands via runtime_pm handles as with the introduction of localities this is no longer an optional feature, while runtime pm can be not enabled. Though cmd_ready/go_idle provides a power saving, it's also a part of TPM2 protocol and should be called explicitly. This patch exposes cmd_read/go_idle via tpm class ops and removes runtime pm support as it is not used by any driver. When calling from nested context always use both flags: TPM_TRANSMIT_UNLOCKED and TPM_TRANSMIT_RAW. Both are needed to resolve tpm spaces and locality request recursive calls to tpm_transmit(). TPM_TRANSMIT_RAW should never be used standalone as it will fail on double locking. While TPM_TRANSMIT_UNLOCKED standalone should be called from non-recursive locked contexts. New wrappers are added tpm_cmd_ready() and tpm_go_idle() to streamline tpm_try_transmit code. tpm_crb no longer needs own power saving functions and can drop using tpm_pm_suspend/resume. This patch cannot be really separated from the locality fix. Fixes: 888d867df441 (tpm: cmd_ready command can be issued only after granting locality) Cc: stable@vger.kernel.org Fixes: 888d867df441 (tpm: cmd_ready command can be issued only after granting locality) Signed-off-by: Tomas Winkler Tested-by: Jarkko Sakkinen Reviewed-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen --- drivers/char/tpm/tpm-interface.c | 51 ++++++++++++++++---- drivers/char/tpm/tpm.h | 12 ++++- drivers/char/tpm/tpm2-space.c | 16 ++++--- drivers/char/tpm/tpm_crb.c | 101 +++++++++++---------------------------- include/linux/tpm.h | 2 + 5 files changed, 90 insertions(+), 92 deletions(-) (limited to 'include') diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c index e32f6e85dc6d..31b86e027f9d 100644 --- a/drivers/char/tpm/tpm-interface.c +++ b/drivers/char/tpm/tpm-interface.c @@ -29,7 +29,6 @@ #include #include #include -#include #include #include "tpm.h" @@ -369,10 +368,13 @@ err_len: return -EINVAL; } -static int tpm_request_locality(struct tpm_chip *chip) +static int tpm_request_locality(struct tpm_chip *chip, unsigned int flags) { int rc; + if (flags & TPM_TRANSMIT_RAW) + return 0; + if (!chip->ops->request_locality) return 0; @@ -385,10 +387,13 @@ static int tpm_request_locality(struct tpm_chip *chip) return 0; } -static void tpm_relinquish_locality(struct tpm_chip *chip) +static void tpm_relinquish_locality(struct tpm_chip *chip, unsigned int flags) { int rc; + if (flags & TPM_TRANSMIT_RAW) + return; + if (!chip->ops->relinquish_locality) return; @@ -399,6 +404,28 @@ static void tpm_relinquish_locality(struct tpm_chip *chip) chip->locality = -1; } +static int tpm_cmd_ready(struct tpm_chip *chip, unsigned int flags) +{ + if (flags & TPM_TRANSMIT_RAW) + return 0; + + if (!chip->ops->cmd_ready) + return 0; + + return chip->ops->cmd_ready(chip); +} + +static int tpm_go_idle(struct tpm_chip *chip, unsigned int flags) +{ + if (flags & TPM_TRANSMIT_RAW) + return 0; + + if (!chip->ops->go_idle) + return 0; + + return chip->ops->go_idle(chip); +} + static ssize_t tpm_try_transmit(struct tpm_chip *chip, struct tpm_space *space, u8 *buf, size_t bufsiz, @@ -449,14 +476,15 @@ static ssize_t tpm_try_transmit(struct tpm_chip *chip, /* Store the decision as chip->locality will be changed. */ need_locality = chip->locality == -1; - if (!(flags & TPM_TRANSMIT_RAW) && need_locality) { - rc = tpm_request_locality(chip); + if (need_locality) { + rc = tpm_request_locality(chip, flags); if (rc < 0) goto out_no_locality; } - if (chip->dev.parent) - pm_runtime_get_sync(chip->dev.parent); + rc = tpm_cmd_ready(chip, flags); + if (rc) + goto out; rc = tpm2_prepare_space(chip, space, ordinal, buf); if (rc) @@ -516,13 +544,16 @@ out_recv: } rc = tpm2_commit_space(chip, space, ordinal, buf, &len); + if (rc) + dev_err(&chip->dev, "tpm2_commit_space: error %d\n", rc); out: - if (chip->dev.parent) - pm_runtime_put_sync(chip->dev.parent); + rc = tpm_go_idle(chip, flags); + if (rc) + goto out; if (need_locality) - tpm_relinquish_locality(chip); + tpm_relinquish_locality(chip, flags); out_no_locality: if (chip->ops->clk_enable != NULL) diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h index 9824cccb2c76..17833ef63f6c 100644 --- a/drivers/char/tpm/tpm.h +++ b/drivers/char/tpm/tpm.h @@ -512,9 +512,17 @@ extern const struct file_operations tpm_fops; extern const struct file_operations tpmrm_fops; extern struct idr dev_nums_idr; +/** + * enum tpm_transmit_flags + * + * @TPM_TRANSMIT_UNLOCKED: used to lock sequence of tpm_transmit calls. + * @TPM_TRANSMIT_RAW: prevent recursive calls into setup steps + * (go idle, locality,..). Always use with UNLOCKED + * as it will fail on double locking. + */ enum tpm_transmit_flags { - TPM_TRANSMIT_UNLOCKED = BIT(0), - TPM_TRANSMIT_RAW = BIT(1), + TPM_TRANSMIT_UNLOCKED = BIT(0), + TPM_TRANSMIT_RAW = BIT(1), }; ssize_t tpm_transmit(struct tpm_chip *chip, struct tpm_space *space, diff --git a/drivers/char/tpm/tpm2-space.c b/drivers/char/tpm/tpm2-space.c index 6122d3276f72..11c85ed8c113 100644 --- a/drivers/char/tpm/tpm2-space.c +++ b/drivers/char/tpm/tpm2-space.c @@ -39,7 +39,8 @@ static void tpm2_flush_sessions(struct tpm_chip *chip, struct tpm_space *space) for (i = 0; i < ARRAY_SIZE(space->session_tbl); i++) { if (space->session_tbl[i]) tpm2_flush_context_cmd(chip, space->session_tbl[i], - TPM_TRANSMIT_UNLOCKED); + TPM_TRANSMIT_UNLOCKED | + TPM_TRANSMIT_RAW); } } @@ -84,7 +85,7 @@ static int tpm2_load_context(struct tpm_chip *chip, u8 *buf, tpm_buf_append(&tbuf, &buf[*offset], body_size); rc = tpm_transmit_cmd(chip, NULL, tbuf.data, PAGE_SIZE, 4, - TPM_TRANSMIT_UNLOCKED, NULL); + TPM_TRANSMIT_UNLOCKED | TPM_TRANSMIT_RAW, NULL); if (rc < 0) { dev_warn(&chip->dev, "%s: failed with a system error %d\n", __func__, rc); @@ -133,7 +134,7 @@ static int tpm2_save_context(struct tpm_chip *chip, u32 handle, u8 *buf, tpm_buf_append_u32(&tbuf, handle); rc = tpm_transmit_cmd(chip, NULL, tbuf.data, PAGE_SIZE, 0, - TPM_TRANSMIT_UNLOCKED, NULL); + TPM_TRANSMIT_UNLOCKED | TPM_TRANSMIT_RAW, NULL); if (rc < 0) { dev_warn(&chip->dev, "%s: failed with a system error %d\n", __func__, rc); @@ -170,7 +171,8 @@ static void tpm2_flush_space(struct tpm_chip *chip) for (i = 0; i < ARRAY_SIZE(space->context_tbl); i++) if (space->context_tbl[i] && ~space->context_tbl[i]) tpm2_flush_context_cmd(chip, space->context_tbl[i], - TPM_TRANSMIT_UNLOCKED); + TPM_TRANSMIT_UNLOCKED | + TPM_TRANSMIT_RAW); tpm2_flush_sessions(chip, space); } @@ -377,7 +379,8 @@ static int tpm2_map_response_header(struct tpm_chip *chip, u32 cc, u8 *rsp, return 0; out_no_slots: - tpm2_flush_context_cmd(chip, phandle, TPM_TRANSMIT_UNLOCKED); + tpm2_flush_context_cmd(chip, phandle, + TPM_TRANSMIT_UNLOCKED | TPM_TRANSMIT_RAW); dev_warn(&chip->dev, "%s: out of slots for 0x%08X\n", __func__, phandle); return -ENOMEM; @@ -465,7 +468,8 @@ static int tpm2_save_space(struct tpm_chip *chip) return rc; tpm2_flush_context_cmd(chip, space->context_tbl[i], - TPM_TRANSMIT_UNLOCKED); + TPM_TRANSMIT_UNLOCKED | + TPM_TRANSMIT_RAW); space->context_tbl[i] = ~0; } diff --git a/drivers/char/tpm/tpm_crb.c b/drivers/char/tpm/tpm_crb.c index 34fbc6cb097b..36952ef98f90 100644 --- a/drivers/char/tpm/tpm_crb.c +++ b/drivers/char/tpm/tpm_crb.c @@ -132,7 +132,7 @@ static bool crb_wait_for_reg_32(u32 __iomem *reg, u32 mask, u32 value, } /** - * crb_go_idle - request tpm crb device to go the idle state + * __crb_go_idle - request tpm crb device to go the idle state * * @dev: crb device * @priv: crb private data @@ -147,7 +147,7 @@ static bool crb_wait_for_reg_32(u32 __iomem *reg, u32 mask, u32 value, * * Return: 0 always */ -static int crb_go_idle(struct device *dev, struct crb_priv *priv) +static int __crb_go_idle(struct device *dev, struct crb_priv *priv) { if ((priv->sm == ACPI_TPM2_START_METHOD) || (priv->sm == ACPI_TPM2_COMMAND_BUFFER_WITH_START_METHOD) || @@ -163,11 +163,20 @@ static int crb_go_idle(struct device *dev, struct crb_priv *priv) dev_warn(dev, "goIdle timed out\n"); return -ETIME; } + return 0; } +static int crb_go_idle(struct tpm_chip *chip) +{ + struct device *dev = &chip->dev; + struct crb_priv *priv = dev_get_drvdata(dev); + + return __crb_go_idle(dev, priv); +} + /** - * crb_cmd_ready - request tpm crb device to enter ready state + * __crb_cmd_ready - request tpm crb device to enter ready state * * @dev: crb device * @priv: crb private data @@ -181,7 +190,7 @@ static int crb_go_idle(struct device *dev, struct crb_priv *priv) * * Return: 0 on success -ETIME on timeout; */ -static int crb_cmd_ready(struct device *dev, struct crb_priv *priv) +static int __crb_cmd_ready(struct device *dev, struct crb_priv *priv) { if ((priv->sm == ACPI_TPM2_START_METHOD) || (priv->sm == ACPI_TPM2_COMMAND_BUFFER_WITH_START_METHOD) || @@ -200,6 +209,14 @@ static int crb_cmd_ready(struct device *dev, struct crb_priv *priv) return 0; } +static int crb_cmd_ready(struct tpm_chip *chip) +{ + struct device *dev = &chip->dev; + struct crb_priv *priv = dev_get_drvdata(dev); + + return __crb_cmd_ready(dev, priv); +} + static int __crb_request_locality(struct device *dev, struct crb_priv *priv, int loc) { @@ -401,6 +418,8 @@ static const struct tpm_class_ops tpm_crb = { .send = crb_send, .cancel = crb_cancel, .req_canceled = crb_req_canceled, + .go_idle = crb_go_idle, + .cmd_ready = crb_cmd_ready, .request_locality = crb_request_locality, .relinquish_locality = crb_relinquish_locality, .req_complete_mask = CRB_DRV_STS_COMPLETE, @@ -520,7 +539,7 @@ static int crb_map_io(struct acpi_device *device, struct crb_priv *priv, * PTT HW bug w/a: wake up the device to access * possibly not retained registers. */ - ret = crb_cmd_ready(dev, priv); + ret = __crb_cmd_ready(dev, priv); if (ret) goto out_relinquish_locality; @@ -565,7 +584,7 @@ out: if (!ret) priv->cmd_size = cmd_size; - crb_go_idle(dev, priv); + __crb_go_idle(dev, priv); out_relinquish_locality: @@ -628,32 +647,7 @@ static int crb_acpi_add(struct acpi_device *device) chip->acpi_dev_handle = device->handle; chip->flags = TPM_CHIP_FLAG_TPM2; - rc = __crb_request_locality(dev, priv, 0); - if (rc) - return rc; - - rc = crb_cmd_ready(dev, priv); - if (rc) - goto out; - - pm_runtime_get_noresume(dev); - pm_runtime_set_active(dev); - pm_runtime_enable(dev); - - rc = tpm_chip_register(chip); - if (rc) { - crb_go_idle(dev, priv); - pm_runtime_put_noidle(dev); - pm_runtime_disable(dev); - goto out; - } - - pm_runtime_put_sync(dev); - -out: - __crb_relinquish_locality(dev, priv, 0); - - return rc; + return tpm_chip_register(chip); } static int crb_acpi_remove(struct acpi_device *device) @@ -663,52 +657,11 @@ static int crb_acpi_remove(struct acpi_device *device) tpm_chip_unregister(chip); - pm_runtime_disable(dev); - return 0; } -static int __maybe_unused crb_pm_runtime_suspend(struct device *dev) -{ - struct tpm_chip *chip = dev_get_drvdata(dev); - struct crb_priv *priv = dev_get_drvdata(&chip->dev); - - return crb_go_idle(dev, priv); -} - -static int __maybe_unused crb_pm_runtime_resume(struct device *dev) -{ - struct tpm_chip *chip = dev_get_drvdata(dev); - struct crb_priv *priv = dev_get_drvdata(&chip->dev); - - return crb_cmd_ready(dev, priv); -} - -static int __maybe_unused crb_pm_suspend(struct device *dev) -{ - int ret; - - ret = tpm_pm_suspend(dev); - if (ret) - return ret; - - return crb_pm_runtime_suspend(dev); -} - -static int __maybe_unused crb_pm_resume(struct device *dev) -{ - int ret; - - ret = crb_pm_runtime_resume(dev); - if (ret) - return ret; - - return tpm_pm_resume(dev); -} - static const struct dev_pm_ops crb_pm = { - SET_SYSTEM_SLEEP_PM_OPS(crb_pm_suspend, crb_pm_resume) - SET_RUNTIME_PM_OPS(crb_pm_runtime_suspend, crb_pm_runtime_resume, NULL) + SET_SYSTEM_SLEEP_PM_OPS(tpm_pm_suspend, tpm_pm_resume) }; static const struct acpi_device_id crb_device_ids[] = { diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 06639fb6ab85..8eb5e5ebe136 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -43,6 +43,8 @@ struct tpm_class_ops { u8 (*status) (struct tpm_chip *chip); bool (*update_timeouts)(struct tpm_chip *chip, unsigned long *timeout_cap); + int (*go_idle)(struct tpm_chip *chip); + int (*cmd_ready)(struct tpm_chip *chip); int (*request_locality)(struct tpm_chip *chip, int loc); int (*relinquish_locality)(struct tpm_chip *chip, int loc); void (*clk_enable)(struct tpm_chip *chip, bool value); -- cgit v1.2.3 From aaae81536351f831fe6719e5b4e6afbadc5e5f85 Mon Sep 17 00:00:00 2001 From: Stefan Berger Date: Tue, 26 Jun 2018 15:09:30 -0400 Subject: tpm: Implement tpm_default_chip() to find a TPM chip Implement tpm_default_chip() to find the first TPM chip and return it to the caller while increasing the reference count on its device. This function can be used by other subsystems, such as IMA, to find the system's default TPM chip and use it for all subsequent TPM operations. Signed-off-by: Stefan Berger Reviewed-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen --- drivers/char/tpm/tpm-chip.c | 27 +++++++++++++++++++++++++++ include/linux/tpm.h | 5 +++++ 2 files changed, 32 insertions(+) (limited to 'include') diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c index 242b716aed5e..f551061262c9 100644 --- a/drivers/char/tpm/tpm-chip.c +++ b/drivers/char/tpm/tpm-chip.c @@ -80,6 +80,33 @@ void tpm_put_ops(struct tpm_chip *chip) } EXPORT_SYMBOL_GPL(tpm_put_ops); +/** + * tpm_default_chip() - find a TPM chip and get a reference to it + */ +struct tpm_chip *tpm_default_chip(void) +{ + struct tpm_chip *chip, *res = NULL; + int chip_num = 0; + int chip_prev; + + mutex_lock(&idr_lock); + + do { + chip_prev = chip_num; + chip = idr_get_next(&dev_nums_idr, &chip_num); + if (chip) { + get_device(&chip->dev); + res = chip; + break; + } + } while (chip_prev != chip_num); + + mutex_unlock(&idr_lock); + + return res; +} +EXPORT_SYMBOL_GPL(tpm_default_chip); + /** * tpm_find_get_ops() - find and reserve a TPM chip * @chip: a &struct tpm_chip instance, %NULL for the default chip diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 8eb5e5ebe136..4609b94142d4 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -63,6 +63,7 @@ extern int tpm_seal_trusted(struct tpm_chip *chip, extern int tpm_unseal_trusted(struct tpm_chip *chip, struct trusted_key_payload *payload, struct trusted_key_options *options); +extern struct tpm_chip *tpm_default_chip(void); #else static inline int tpm_is_tpm2(struct tpm_chip *chip) { @@ -98,5 +99,9 @@ static inline int tpm_unseal_trusted(struct tpm_chip *chip, { return -ENODEV; } +static inline struct tpm_chip *tpm_default_chip(void) +{ + return NULL; +} #endif #endif -- cgit v1.2.3 From 5cbf777cfdf6e5a7b7149006e4881a255da78fdd Mon Sep 17 00:00:00 2001 From: Xin Long Date: Fri, 27 Jul 2018 16:37:28 +0800 Subject: route: add support for directed broadcast forwarding This patch implements the feature described in rfc1812#section-5.3.5.2 and rfc2644. It allows the router to forward directed broadcast when sysctl bc_forwarding is enabled. Note that this feature could be done by iptables -j TEE, but it would cause some problems: - target TEE's gateway param has to be set with a specific address, and it's not flexible especially when the route wants forward all directed broadcasts. - this duplicates the directed broadcasts so this may cause side effects to applications. Besides, to keep consistent with other os router like BSD, it's also necessary to implement it in the route rx path. Note that route cache needs to be flushed when bc_forwarding is changed. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 1 + include/uapi/linux/ip.h | 1 + include/uapi/linux/netconf.h | 1 + net/ipv4/devinet.c | 11 +++++++++++ net/ipv4/route.c | 6 +++++- 5 files changed, 19 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 27650f1bff3d..c759d1cbcedd 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -93,6 +93,7 @@ static inline void ipv4_devconf_setall(struct in_device *in_dev) #define IN_DEV_FORWARD(in_dev) IN_DEV_CONF_GET((in_dev), FORWARDING) #define IN_DEV_MFORWARD(in_dev) IN_DEV_ANDCONF((in_dev), MC_FORWARDING) +#define IN_DEV_BFORWARD(in_dev) IN_DEV_ANDCONF((in_dev), BC_FORWARDING) #define IN_DEV_RPFILTER(in_dev) IN_DEV_MAXCONF((in_dev), RP_FILTER) #define IN_DEV_SRC_VMARK(in_dev) IN_DEV_ORCONF((in_dev), SRC_VMARK) #define IN_DEV_SOURCE_ROUTE(in_dev) IN_DEV_ANDCONF((in_dev), \ diff --git a/include/uapi/linux/ip.h b/include/uapi/linux/ip.h index b24a742beae5..e42d13b55cf3 100644 --- a/include/uapi/linux/ip.h +++ b/include/uapi/linux/ip.h @@ -168,6 +168,7 @@ enum IPV4_DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN, IPV4_DEVCONF_DROP_UNICAST_IN_L2_MULTICAST, IPV4_DEVCONF_DROP_GRATUITOUS_ARP, + IPV4_DEVCONF_BC_FORWARDING, __IPV4_DEVCONF_MAX }; diff --git a/include/uapi/linux/netconf.h b/include/uapi/linux/netconf.h index c84fcdfca862..fac4edd55379 100644 --- a/include/uapi/linux/netconf.h +++ b/include/uapi/linux/netconf.h @@ -18,6 +18,7 @@ enum { NETCONFA_PROXY_NEIGH, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, NETCONFA_INPUT, + NETCONFA_BC_FORWARDING, __NETCONFA_MAX }; #define NETCONFA_MAX (__NETCONFA_MAX - 1) diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index d7585ab1a77a..ea4bd8a52422 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1827,6 +1827,8 @@ static int inet_netconf_msgsize_devconf(int type) size += nla_total_size(4); if (all || type == NETCONFA_MC_FORWARDING) size += nla_total_size(4); + if (all || type == NETCONFA_BC_FORWARDING) + size += nla_total_size(4); if (all || type == NETCONFA_PROXY_NEIGH) size += nla_total_size(4); if (all || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN) @@ -1873,6 +1875,10 @@ static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex, nla_put_s32(skb, NETCONFA_MC_FORWARDING, IPV4_DEVCONF(*devconf, MC_FORWARDING)) < 0) goto nla_put_failure; + if ((all || type == NETCONFA_BC_FORWARDING) && + nla_put_s32(skb, NETCONFA_BC_FORWARDING, + IPV4_DEVCONF(*devconf, BC_FORWARDING)) < 0) + goto nla_put_failure; if ((all || type == NETCONFA_PROXY_NEIGH) && nla_put_s32(skb, NETCONFA_PROXY_NEIGH, IPV4_DEVCONF(*devconf, PROXY_ARP)) < 0) @@ -2143,6 +2149,10 @@ static int devinet_conf_proc(struct ctl_table *ctl, int write, if ((new_value == 0) && (old_value != 0)) rt_cache_flush(net); + if (i == IPV4_DEVCONF_BC_FORWARDING - 1 && + new_value != old_value) + rt_cache_flush(net); + if (i == IPV4_DEVCONF_RP_FILTER - 1 && new_value != old_value) { ifindex = devinet_conf_ifindex(net, cnf); @@ -2259,6 +2269,7 @@ static struct devinet_sysctl_table { DEVINET_SYSCTL_COMPLEX_ENTRY(FORWARDING, "forwarding", devinet_sysctl_forward), DEVINET_SYSCTL_RO_ENTRY(MC_FORWARDING, "mc_forwarding"), + DEVINET_SYSCTL_RW_ENTRY(BC_FORWARDING, "bc_forwarding"), DEVINET_SYSCTL_RW_ENTRY(ACCEPT_REDIRECTS, "accept_redirects"), DEVINET_SYSCTL_RW_ENTRY(SECURE_REDIRECTS, "secure_redirects"), diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 1df6e97106d7..b678466da451 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1996,8 +1996,11 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, goto no_route; } - if (res->type == RTN_BROADCAST) + if (res->type == RTN_BROADCAST) { + if (IN_DEV_BFORWARD(in_dev)) + goto make_route; goto brd_input; + } if (res->type == RTN_LOCAL) { err = fib_validate_source(skb, saddr, daddr, tos, @@ -2014,6 +2017,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (res->type != RTN_UNICAST) goto martian_destination; +make_route: err = ip_mkroute_input(skb, res, in_dev, daddr, saddr, tos, flkeys); out: return err; -- cgit v1.2.3 From 4b09384aaa2a9b2ac09a584d7a9345cf003617f2 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 27 Jul 2018 13:11:00 -0700 Subject: net: dcb: add DSCP to comment about priority selector types Commit ee2059819450 ("net/dcb: Add dscp to priority selector type") added a define for the new DSCP selector type created by IEEE 802.1Qcd, but missed the comment enumerating all selector types. Update the comment. Signed-off-by: Jakub Kicinski Reviewed-by: Petr Machata Signed-off-by: David S. Miller --- include/uapi/linux/dcbnl.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/dcbnl.h b/include/uapi/linux/dcbnl.h index 60aa2e446698..69df19aa8e72 100644 --- a/include/uapi/linux/dcbnl.h +++ b/include/uapi/linux/dcbnl.h @@ -233,7 +233,8 @@ struct cee_pfc { * 2 Well known port number over TCP or SCTP * 3 Well known port number over UDP or DCCP * 4 Well known port number over TCP, SCTP, UDP, or DCCP - * 5-7 Reserved + * 5 Differentiated Services Code Point (DSCP) value + * 6-7 Reserved * * Selector field values for CEE * 0 Ethertype -- cgit v1.2.3 From 3e7a50ceb11ea75c27e944f1a01e478fd62a2d8d Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Fri, 27 Jul 2018 13:43:22 -0700 Subject: net: report min and max mtu network device settings Report the minimum and maximum MTU allowed on a device via netlink so that it can be displayed by tools like ip link. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 2 ++ net/core/rtnetlink.c | 6 ++++++ 2 files changed, 8 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 553c438cabe3..43391e2d1153 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -164,6 +164,8 @@ enum { IFLA_CARRIER_UP_COUNT, IFLA_CARRIER_DOWN_COUNT, IFLA_NEW_IFINDEX, + IFLA_MIN_MTU, + IFLA_MAX_MTU, __IFLA_MAX }; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 92b6fa5d5f6e..510d4f765a13 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1015,6 +1015,8 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(4) /* IFLA_IF_NETNSID */ + nla_total_size(4) /* IFLA_CARRIER_UP_COUNT */ + nla_total_size(4) /* IFLA_CARRIER_DOWN_COUNT */ + + nla_total_size(4) /* IFLA_MIN_MTU */ + + nla_total_size(4) /* IFLA_MAX_MTU */ + 0; } @@ -1601,6 +1603,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, netif_running(dev) ? dev->operstate : IF_OPER_DOWN) || nla_put_u8(skb, IFLA_LINKMODE, dev->link_mode) || nla_put_u32(skb, IFLA_MTU, dev->mtu) || + nla_put_u32(skb, IFLA_MIN_MTU, dev->min_mtu) || + nla_put_u32(skb, IFLA_MAX_MTU, dev->max_mtu) || nla_put_u32(skb, IFLA_GROUP, dev->group) || nla_put_u32(skb, IFLA_PROMISCUITY, dev->promiscuity) || nla_put_u32(skb, IFLA_NUM_TX_QUEUES, dev->num_tx_queues) || @@ -1732,6 +1736,8 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_IF_NETNSID] = { .type = NLA_S32 }, [IFLA_CARRIER_UP_COUNT] = { .type = NLA_U32 }, [IFLA_CARRIER_DOWN_COUNT] = { .type = NLA_U32 }, + [IFLA_MIN_MTU] = { .type = NLA_U32 }, + [IFLA_MAX_MTU] = { .type = NLA_U32 }, }; static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { -- cgit v1.2.3 From 7a4c53bee3324ac00bf964aa2f82d15d279e86e4 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Fri, 27 Jul 2018 13:43:23 -0700 Subject: net: report invalid mtu value via netlink extack If an invalid MTU value is set through rtnetlink return extra error information instead of putting message in kernel log. For other cases where there is no visible API, keep the error report in the log. Example: # ip li set dev enp12s0 mtu 10000 Error: mtu greater than device maximum. # ifconfig enp12s0 mtu 10000 SIOCSIFMTU: Invalid argument # dmesg | tail -1 [ 2047.795467] enp12s0: mtu greater than device maximum Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 ++ net/core/dev.c | 23 +++++++++++++++++------ net/core/rtnetlink.c | 2 +- 3 files changed, 20 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c1295c7a452e..9c917467a2c7 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3546,6 +3546,8 @@ int dev_set_alias(struct net_device *, const char *, size_t); int dev_get_alias(const struct net_device *, char *, size_t); int dev_change_net_namespace(struct net_device *, struct net *, const char *); int __dev_set_mtu(struct net_device *, int); +int dev_set_mtu_ext(struct net_device *dev, int mtu, + struct netlink_ext_ack *extack); int dev_set_mtu(struct net_device *, int); int dev_change_tx_queue_len(struct net_device *, unsigned long); void dev_set_group(struct net_device *, int); diff --git a/net/core/dev.c b/net/core/dev.c index 87c42c8249ae..89031b5fef9f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -7523,13 +7523,15 @@ int __dev_set_mtu(struct net_device *dev, int new_mtu) EXPORT_SYMBOL(__dev_set_mtu); /** - * dev_set_mtu - Change maximum transfer unit + * dev_set_mtu_ext - Change maximum transfer unit * @dev: device * @new_mtu: new transfer unit + * @extack: netlink extended ack * * Change the maximum transfer size of the network device. */ -int dev_set_mtu(struct net_device *dev, int new_mtu) +int dev_set_mtu_ext(struct net_device *dev, int new_mtu, + struct netlink_ext_ack *extack) { int err, orig_mtu; @@ -7538,14 +7540,12 @@ int dev_set_mtu(struct net_device *dev, int new_mtu) /* MTU must be positive, and in range */ if (new_mtu < 0 || new_mtu < dev->min_mtu) { - net_err_ratelimited("%s: Invalid MTU %d requested, hw min %d\n", - dev->name, new_mtu, dev->min_mtu); + NL_SET_ERR_MSG(extack, "mtu less than device minimum"); return -EINVAL; } if (dev->max_mtu > 0 && new_mtu > dev->max_mtu) { - net_err_ratelimited("%s: Invalid MTU %d requested, hw max %d\n", - dev->name, new_mtu, dev->max_mtu); + NL_SET_ERR_MSG(extack, "mtu greater than device maximum"); return -EINVAL; } @@ -7573,6 +7573,17 @@ int dev_set_mtu(struct net_device *dev, int new_mtu) } return err; } + +int dev_set_mtu(struct net_device *dev, int new_mtu) +{ + struct netlink_ext_ack extack; + int err; + + err = dev_set_mtu_ext(dev, new_mtu, &extack); + if (err) + net_err_ratelimited("%s: %s\n", dev->name, extack._msg); + return err; +} EXPORT_SYMBOL(dev_set_mtu); /** diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 510d4f765a13..24431e578310 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2382,7 +2382,7 @@ static int do_setlink(const struct sk_buff *skb, } if (tb[IFLA_MTU]) { - err = dev_set_mtu(dev, nla_get_u32(tb[IFLA_MTU])); + err = dev_set_mtu_ext(dev, nla_get_u32(tb[IFLA_MTU]), extack); if (err < 0) goto errout; status |= DO_SETLINK_MODIFIED; -- cgit v1.2.3 From 0969a204bfdaf7470d2666736b90a8595ae671e9 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 27 Jul 2018 17:47:01 +0300 Subject: gpiolib: Use GPIOD_OUT_{LOW,HIGH} macros in open drain ones There should not be anything more than stated by the name of newly introduced constants, i.e. GPIOD_OUT_LOW_OPEN_DRAIN == GPIOD_OUT_LOW + open drain and nothing more. Make it better to read and slightly more robust by using GPIOD_OUT_LOW and GPIOD_OUT_HIGH constants with open drain flag. No functional change intended. Signed-off-by: Andy Shevchenko Signed-off-by: Linus Walleij --- include/linux/gpio/consumer.h | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index e8aaf34dd65d..21ddbe440030 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -41,11 +41,8 @@ enum gpiod_flags { GPIOD_OUT_LOW = GPIOD_FLAGS_BIT_DIR_SET | GPIOD_FLAGS_BIT_DIR_OUT, GPIOD_OUT_HIGH = GPIOD_FLAGS_BIT_DIR_SET | GPIOD_FLAGS_BIT_DIR_OUT | GPIOD_FLAGS_BIT_DIR_VAL, - GPIOD_OUT_LOW_OPEN_DRAIN = GPIOD_FLAGS_BIT_DIR_SET | - GPIOD_FLAGS_BIT_DIR_OUT | GPIOD_FLAGS_BIT_OPEN_DRAIN, - GPIOD_OUT_HIGH_OPEN_DRAIN = GPIOD_FLAGS_BIT_DIR_SET | - GPIOD_FLAGS_BIT_DIR_OUT | GPIOD_FLAGS_BIT_DIR_VAL | - GPIOD_FLAGS_BIT_OPEN_DRAIN, + GPIOD_OUT_LOW_OPEN_DRAIN = GPIOD_OUT_LOW | GPIOD_FLAGS_BIT_OPEN_DRAIN, + GPIOD_OUT_HIGH_OPEN_DRAIN = GPIOD_OUT_HIGH | GPIOD_FLAGS_BIT_OPEN_DRAIN, }; #ifdef CONFIG_GPIOLIB -- cgit v1.2.3 From 222440b4e832059c0ddf18d1e409f0552ab53a7d Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 4 Jul 2018 12:48:04 +0200 Subject: netfilter: nf_tables: handle meta/lookup with direct call Currently nft uses inlined variants for common operations such as 'ip saddr 1.2.3.4' instead of an indirect call. Also handle meta get operations and lookups without indirect call, both are builtin. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables_core.h | 7 +++++++ net/netfilter/nf_tables_core.c | 16 +++++++++++++++- net/netfilter/nft_lookup.c | 6 +++--- net/netfilter/nft_meta.c | 6 +++--- 4 files changed, 28 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index a05134507e7b..8da837d2aaf9 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -71,4 +71,11 @@ extern struct nft_set_type nft_set_hash_fast_type; extern struct nft_set_type nft_set_rbtree_type; extern struct nft_set_type nft_set_bitmap_type; +struct nft_expr; +struct nft_regs; +struct nft_pktinfo; +void nft_meta_get_eval(const struct nft_expr *expr, + struct nft_regs *regs, const struct nft_pktinfo *pkt); +void nft_lookup_eval(const struct nft_expr *expr, + struct nft_regs *regs, const struct nft_pktinfo *pkt); #endif /* _NET_NF_TABLES_CORE_H */ diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index 8de912ca53d3..ffd5c0f9412b 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -120,6 +120,20 @@ struct nft_jumpstack { struct nft_rule *const *rules; }; +static void expr_call_ops_eval(const struct nft_expr *expr, + struct nft_regs *regs, + struct nft_pktinfo *pkt) +{ + unsigned long e = (unsigned long)expr->ops->eval; + + if (e == (unsigned long)nft_meta_get_eval) + nft_meta_get_eval(expr, regs, pkt); + else if (e == (unsigned long)nft_lookup_eval) + nft_lookup_eval(expr, regs, pkt); + else + expr->ops->eval(expr, regs, pkt); +} + unsigned int nft_do_chain(struct nft_pktinfo *pkt, void *priv) { @@ -153,7 +167,7 @@ next_rule: nft_cmp_fast_eval(expr, ®s); else if (expr->ops != &nft_payload_fast_ops || !nft_payload_fast_eval(expr, ®s, pkt)) - expr->ops->eval(expr, ®s, pkt); + expr_call_ops_eval(expr, ®s, pkt); if (regs.verdict.code != NFT_CONTINUE) break; diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index c2a1d84cdfc4..ad13e8643599 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -26,9 +26,9 @@ struct nft_lookup { struct nft_set_binding binding; }; -static void nft_lookup_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) +void nft_lookup_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) { const struct nft_lookup *priv = nft_expr_priv(expr); const struct nft_set *set = priv->set; diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index 2b94dcc43456..297fe7d97c18 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -41,9 +41,9 @@ static DEFINE_PER_CPU(struct rnd_state, nft_prandom_state); #include "../bridge/br_private.h" #endif -static void nft_meta_get_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) +void nft_meta_get_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) { const struct nft_meta *priv = nft_expr_priv(expr); const struct sk_buff *skb = pkt->skb; -- cgit v1.2.3 From 345a9ca37aa69bb3133c1a8390a71f993abcef0c Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 30 Jul 2018 08:46:40 +0200 Subject: ALSA: memalloc: Fix missing PAGE_SIZE definition The recent fix moved the inline snd_sgbuf_aligned_pages() outside the ifdef, and this triggered a build error on some architectures due to the undefined PAGE_SIZE, as spotted by 0day bot. Fix it by adding the missing header inclusion. Fixes: 4cae99d9b530 ("ALSA: memalloc: declare snd_sgbuf_aligned_pages() unconditionally") Reported-by: kbuild test robot Cc: Pierre-Louis Bossart Signed-off-by: Takashi Iwai Signed-off-by: Mark Brown --- include/sound/memalloc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/sound/memalloc.h b/include/sound/memalloc.h index c669900e6cbe..67561b997915 100644 --- a/include/sound/memalloc.h +++ b/include/sound/memalloc.h @@ -24,6 +24,8 @@ #ifndef __SOUND_MEMALLOC_H #define __SOUND_MEMALLOC_H +#include + struct device; /* -- cgit v1.2.3 From 6decb5b45e70d6ffff6488cc8e8bad6b9ac7f99b Mon Sep 17 00:00:00 2001 From: Jaganath Kanakkassery Date: Thu, 19 Jul 2018 17:09:32 +0530 Subject: Bluetooth: Define PHY flags in hdev and set 1M as default 1M is mandatory to be supported by LE controllers and the same would be set in power on. This patch defines hdev flags for LE PHYs and set 1M to default. Signed-off-by: Jaganath Kanakkassery Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci.h | 4 ++++ include/net/bluetooth/hci_core.h | 3 +++ net/bluetooth/hci_core.c | 9 +++++---- 3 files changed, 12 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 73e48be5bbb3..664fe1ebf2c7 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -1514,6 +1514,10 @@ struct hci_cp_le_set_default_phy { __u8 rx_phys; } __packed; +#define HCI_LE_SET_PHY_1M 0x01 +#define HCI_LE_SET_PHY_2M 0x02 +#define HCI_LE_SET_PHY_CODED 0x04 + #define HCI_OP_LE_SET_EXT_SCAN_PARAMS 0x2041 struct hci_cp_le_set_ext_scan_params { __u8 own_addr_type; diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index a74453571264..71f79df9ee05 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -315,6 +315,9 @@ struct hci_dev { unsigned long sco_last_tx; unsigned long le_last_tx; + __u8 le_tx_def_phys; + __u8 le_rx_def_phys; + struct workqueue_struct *workqueue; struct workqueue_struct *req_workqueue; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index f5c21004186c..432f89f390c0 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -830,10 +830,9 @@ static int hci_init4_req(struct hci_request *req, unsigned long opt) if (hdev->commands[35] & 0x20) { struct hci_cp_le_set_default_phy cp; - /* No transmitter PHY or receiver PHY preferences */ - cp.all_phys = 0x03; - cp.tx_phys = 0; - cp.rx_phys = 0; + cp.all_phys = 0x00; + cp.tx_phys = hdev->le_tx_def_phys; + cp.rx_phys = hdev->le_rx_def_phys; hci_req_add(req, HCI_OP_LE_SET_DEFAULT_PHY, sizeof(cp), &cp); } @@ -3027,6 +3026,8 @@ struct hci_dev *hci_alloc_dev(void) hdev->le_max_tx_time = 0x0148; hdev->le_max_rx_len = 0x001b; hdev->le_max_rx_time = 0x0148; + hdev->le_tx_def_phys = HCI_LE_SET_PHY_1M; + hdev->le_rx_def_phys = HCI_LE_SET_PHY_1M; hdev->rpa_timeout = HCI_DEFAULT_RPA_TIMEOUT; hdev->discov_interleaved_timeout = DISCOV_INTERLEAVED_TIMEOUT; -- cgit v1.2.3 From 5075b972f20ddad5bb19542ea4f5794d06673375 Mon Sep 17 00:00:00 2001 From: Jaganath Kanakkassery Date: Thu, 19 Jul 2018 17:09:33 +0530 Subject: Bluetooth: Add defines for BREDR pkt_type and LE PHYs This also add macros for checking LMP support for different pkt_types Signed-off-by: Jaganath Kanakkassery Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci.h | 14 ++++++++++++++ include/net/bluetooth/hci_core.h | 4 ++++ 2 files changed, 18 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 664fe1ebf2c7..89bf800f6eb1 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -291,6 +291,14 @@ enum { #define HCI_DH3 0x0800 #define HCI_DH5 0x8000 +/* HCI packet types inverted masks */ +#define HCI_2DH1 0x0002 +#define HCI_3DH1 0x0004 +#define HCI_2DH3 0x0100 +#define HCI_3DH3 0x0200 +#define HCI_2DH5 0x1000 +#define HCI_3DH5 0x2000 + #define HCI_HV1 0x0020 #define HCI_HV2 0x0040 #define HCI_HV3 0x0080 @@ -354,6 +362,8 @@ enum { #define LMP_PCONTROL 0x04 #define LMP_TRANSPARENT 0x08 +#define LMP_EDR_2M 0x02 +#define LMP_EDR_3M 0x04 #define LMP_RSSI_INQ 0x40 #define LMP_ESCO 0x80 @@ -361,7 +371,9 @@ enum { #define LMP_EV5 0x02 #define LMP_NO_BREDR 0x20 #define LMP_LE 0x40 +#define LMP_EDR_3SLOT 0x80 +#define LMP_EDR_5SLOT 0x01 #define LMP_SNIFF_SUBR 0x02 #define LMP_PAUSE_ENC 0x04 #define LMP_EDR_ESCO_2M 0x20 @@ -399,6 +411,8 @@ enum { #define HCI_LE_PING 0x10 #define HCI_LE_DATA_LEN_EXT 0x20 #define HCI_LE_EXT_SCAN_POLICY 0x80 +#define HCI_LE_PHY_2M 0x01 +#define HCI_LE_PHY_CODED 0x08 #define HCI_LE_CHAN_SEL_ALG2 0x40 /* Connection modes */ diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 71f79df9ee05..a64d13f91d09 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1141,6 +1141,10 @@ void hci_conn_del_sysfs(struct hci_conn *conn); #define lmp_inq_tx_pwr_capable(dev) ((dev)->features[0][7] & LMP_INQ_TX_PWR) #define lmp_ext_feat_capable(dev) ((dev)->features[0][7] & LMP_EXTFEATURES) #define lmp_transp_capable(dev) ((dev)->features[0][2] & LMP_TRANSPARENT) +#define lmp_edr_2m_capable(dev) ((dev)->features[0][3] & LMP_EDR_2M) +#define lmp_edr_3m_capable(dev) ((dev)->features[0][3] & LMP_EDR_3M) +#define lmp_edr_3slot_capable(dev) ((dev)->features[0][4] & LMP_EDR_3SLOT) +#define lmp_edr_5slot_capable(dev) ((dev)->features[0][5] & LMP_EDR_5SLOT) /* ----- Extended LMP capabilities ----- */ #define lmp_csb_master_capable(dev) ((dev)->features[2][0] & LMP_CSB_MASTER) -- cgit v1.2.3 From 6244691fec4dd0adebca255e60e0ed7ac8155b2e Mon Sep 17 00:00:00 2001 From: Jaganath Kanakkassery Date: Thu, 19 Jul 2018 17:09:34 +0530 Subject: Bluetooth: Implement Get PHY Configuration mgmt command This commands basically retrieve the supported packet types of BREDR and supported PHYs of the controller. BR_1M_1SLOT, LE_1M_TX and LE_1M_RX would be supported by default. Other PHYs are supported based on the local features. Also this sets PHY_CONFIGURATION bit in supported settings. @ MGMT Command: Get PHY Configuration (0x0044) plen 0 @ MGMT Event: Command Complete (0x0001) plen 15 Get PHY Configuration (0x0044) plen 12 Status: Success (0x00) Supported PHYs: 0x7fff BR 1M 1SLOT BR 1M 3SLOT BR 1M 5SLOT EDR 2M 1SLOT EDR 2M 3SLOT EDR 2M 5SLOT EDR 3M 1SLOT EDR 3M 3SLOT EDR 3M 5SLOT LE 1M TX LE 1M RX LE 2M TX LE 2M RX LE CODED TX LE CODED RX Configurable PHYs: 0x79fe BR 1M 3SLOT BR 1M 5SLOT EDR 2M 1SLOT EDR 2M 3SLOT EDR 2M 5SLOT EDR 3M 1SLOT EDR 3M 3SLOT EDR 3M 5SLOT LE 2M TX LE 2M RX LE CODED TX LE CODED RX Selected PHYs: 0x07ff BR 1M 1SLOT BR 1M 3SLOT BR 1M 5SLOT EDR 2M 1SLOT EDR 2M 3SLOT EDR 2M 5SLOT EDR 3M 1SLOT EDR 3M 3SLOT EDR 3M 5SLOT LE 1M TX LE 1M RX Signed-off-by: Jaganath Kanakkassery Signed-off-by: Marcel Holtmann --- include/net/bluetooth/mgmt.h | 25 ++++++++ net/bluetooth/mgmt.c | 145 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 170 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index e7303eee65cd..1c93d6e83a6c 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -101,6 +101,7 @@ struct mgmt_rp_read_index_list { #define MGMT_SETTING_PRIVACY 0x00002000 #define MGMT_SETTING_CONFIGURATION 0x00004000 #define MGMT_SETTING_STATIC_ADDRESS 0x00008000 +#define MGMT_SETTING_PHY_CONFIGURATION 0x00010000 #define MGMT_OP_READ_INFO 0x0004 #define MGMT_READ_INFO_SIZE 0 @@ -604,6 +605,30 @@ struct mgmt_cp_set_appearance { } __packed; #define MGMT_SET_APPEARANCE_SIZE 2 +#define MGMT_OP_GET_PHY_CONFIGURATION 0x0044 +struct mgmt_rp_get_phy_confguration { + __le32 supported_phys; + __le32 configurable_phys; + __le32 selected_phys; +} __packed; +#define MGMT_GET_PHY_CONFIGURATION_SIZE 0 + +#define MGMT_PHY_BR_1M_1SLOT 0x00000001 +#define MGMT_PHY_BR_1M_3SLOT 0x00000002 +#define MGMT_PHY_BR_1M_5SLOT 0x00000004 +#define MGMT_PHY_EDR_2M_1SLOT 0x00000008 +#define MGMT_PHY_EDR_2M_3SLOT 0x00000010 +#define MGMT_PHY_EDR_2M_5SLOT 0x00000020 +#define MGMT_PHY_EDR_3M_1SLOT 0x00000040 +#define MGMT_PHY_EDR_3M_3SLOT 0x00000080 +#define MGMT_PHY_EDR_3M_5SLOT 0x00000100 +#define MGMT_PHY_LE_1M_TX 0x00000200 +#define MGMT_PHY_LE_1M_RX 0x00000400 +#define MGMT_PHY_LE_2M_TX 0x00000800 +#define MGMT_PHY_LE_2M_RX 0x00001000 +#define MGMT_PHY_LE_CODED_TX 0x00002000 +#define MGMT_PHY_LE_CODED_RX 0x00004000 + #define MGMT_EV_CMD_COMPLETE 0x0001 struct mgmt_ev_cmd_complete { __le16 opcode; diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 8a80d48d89c4..c8c3b39fa9f2 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -617,6 +617,127 @@ static int read_config_info(struct sock *sk, struct hci_dev *hdev, &rp, sizeof(rp)); } +static u32 get_supported_phys(struct hci_dev *hdev) +{ + u32 supported_phys = 0; + + if (lmp_bredr_capable(hdev)) { + supported_phys |= MGMT_PHY_BR_1M_1SLOT; + + if (hdev->features[0][0] & LMP_3SLOT) + supported_phys |= MGMT_PHY_BR_1M_3SLOT; + + if (hdev->features[0][0] & LMP_5SLOT) + supported_phys |= MGMT_PHY_BR_1M_5SLOT; + + if (lmp_edr_2m_capable(hdev)) { + supported_phys |= MGMT_PHY_EDR_2M_1SLOT; + + if (lmp_edr_3slot_capable(hdev)) + supported_phys |= MGMT_PHY_EDR_2M_3SLOT; + + if (lmp_edr_5slot_capable(hdev)) + supported_phys |= MGMT_PHY_EDR_2M_5SLOT; + + if (lmp_edr_3m_capable(hdev)) { + supported_phys |= MGMT_PHY_EDR_3M_1SLOT; + + if (lmp_edr_3slot_capable(hdev)) + supported_phys |= MGMT_PHY_EDR_3M_3SLOT; + + if (lmp_edr_5slot_capable(hdev)) + supported_phys |= MGMT_PHY_EDR_3M_5SLOT; + } + } + } + + if (lmp_le_capable(hdev)) { + supported_phys |= MGMT_PHY_LE_1M_TX; + supported_phys |= MGMT_PHY_LE_1M_RX; + + if (hdev->le_features[1] & HCI_LE_PHY_2M) { + supported_phys |= MGMT_PHY_LE_2M_TX; + supported_phys |= MGMT_PHY_LE_2M_RX; + } + + if (hdev->le_features[1] & HCI_LE_PHY_CODED) { + supported_phys |= MGMT_PHY_LE_CODED_TX; + supported_phys |= MGMT_PHY_LE_CODED_RX; + } + } + + return supported_phys; +} + +static u32 get_selected_phys(struct hci_dev *hdev) +{ + u32 selected_phys = 0; + + if (lmp_bredr_capable(hdev)) { + selected_phys |= MGMT_PHY_BR_1M_1SLOT; + + if (hdev->pkt_type & (HCI_DM3 | HCI_DH3)) + selected_phys |= MGMT_PHY_BR_1M_3SLOT; + + if (hdev->pkt_type & (HCI_DM5 | HCI_DH5)) + selected_phys |= MGMT_PHY_BR_1M_5SLOT; + + if (lmp_edr_2m_capable(hdev)) { + if (!(hdev->pkt_type & HCI_2DH1)) + selected_phys |= MGMT_PHY_EDR_2M_1SLOT; + + if (lmp_edr_3slot_capable(hdev) && + !(hdev->pkt_type & HCI_2DH3)) + selected_phys |= MGMT_PHY_EDR_2M_3SLOT; + + if (lmp_edr_5slot_capable(hdev) && + !(hdev->pkt_type & HCI_2DH5)) + selected_phys |= MGMT_PHY_EDR_2M_5SLOT; + + if (lmp_edr_3m_capable(hdev)) { + if (!(hdev->pkt_type & HCI_3DH1)) + selected_phys |= MGMT_PHY_EDR_3M_1SLOT; + + if (lmp_edr_3slot_capable(hdev) && + !(hdev->pkt_type & HCI_3DH3)) + selected_phys |= MGMT_PHY_EDR_3M_3SLOT; + + if (lmp_edr_5slot_capable(hdev) && + !(hdev->pkt_type & HCI_3DH5)) + selected_phys |= MGMT_PHY_EDR_3M_5SLOT; + } + } + } + + if (lmp_le_capable(hdev)) { + if (hdev->le_tx_def_phys & HCI_LE_SET_PHY_1M) + selected_phys |= MGMT_PHY_LE_1M_TX; + + if (hdev->le_rx_def_phys & HCI_LE_SET_PHY_1M) + selected_phys |= MGMT_PHY_LE_1M_RX; + + if (hdev->le_tx_def_phys & HCI_LE_SET_PHY_2M) + selected_phys |= MGMT_PHY_LE_2M_TX; + + if (hdev->le_rx_def_phys & HCI_LE_SET_PHY_2M) + selected_phys |= MGMT_PHY_LE_2M_RX; + + if (hdev->le_tx_def_phys & HCI_LE_SET_PHY_CODED) + selected_phys |= MGMT_PHY_LE_CODED_TX; + + if (hdev->le_rx_def_phys & HCI_LE_SET_PHY_CODED) + selected_phys |= MGMT_PHY_LE_CODED_RX; + } + + return selected_phys; +} + +static u32 get_configurable_phys(struct hci_dev *hdev) +{ + return (get_supported_phys(hdev) & ~MGMT_PHY_BR_1M_1SLOT & + ~MGMT_PHY_LE_1M_TX & ~MGMT_PHY_LE_1M_RX); +} + static u32 get_supported_settings(struct hci_dev *hdev) { u32 settings = 0; @@ -654,6 +775,8 @@ static u32 get_supported_settings(struct hci_dev *hdev) hdev->set_bdaddr) settings |= MGMT_SETTING_CONFIGURATION; + settings |= MGMT_SETTING_PHY_CONFIGURATION; + return settings; } @@ -3184,6 +3307,27 @@ static int set_appearance(struct sock *sk, struct hci_dev *hdev, void *data, return err; } +static int get_phy_configuration(struct sock *sk, struct hci_dev *hdev, + void *data, u16 len) +{ + struct mgmt_rp_get_phy_confguration rp; + + BT_DBG("sock %p %s", sk, hdev->name); + + hci_dev_lock(hdev); + + memset(&rp, 0, sizeof(rp)); + + rp.supported_phys = cpu_to_le32(get_supported_phys(hdev)); + rp.selected_phys = cpu_to_le32(get_selected_phys(hdev)); + rp.configurable_phys = cpu_to_le32(get_configurable_phys(hdev)); + + hci_dev_unlock(hdev); + + return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_GET_PHY_CONFIGURATION, 0, + &rp, sizeof(rp)); +} + static void read_local_oob_data_complete(struct hci_dev *hdev, u8 status, u16 opcode, struct sk_buff *skb) { @@ -6544,6 +6688,7 @@ static const struct hci_mgmt_handler mgmt_handlers[] = { { read_ext_controller_info,MGMT_READ_EXT_INFO_SIZE, HCI_MGMT_UNTRUSTED }, { set_appearance, MGMT_SET_APPEARANCE_SIZE }, + { get_phy_configuration, MGMT_GET_PHY_CONFIGURATION_SIZE }, }; void mgmt_index_added(struct hci_dev *hdev) -- cgit v1.2.3 From 0314f2867fa0c46d0fc1c23c80e7fab9435079df Mon Sep 17 00:00:00 2001 From: Jaganath Kanakkassery Date: Thu, 19 Jul 2018 17:09:35 +0530 Subject: Bluetooth: Implement Set PHY Confguration command This enables user to set phys which will be used in all subsequent connections. Also host will use the same in LE scanning as well. @ MGMT Command: Set PHY Configuration (0x0045) plen 4 Selected PHYs: 0x7fff BR 1M 1SLOT BR 1M 3SLOT BR 1M 5SLOT EDR 2M 1SLOT EDR 2M 3SLOT EDR 2M 5SLOT EDR 3M 1SLOT EDR 3M 3SLOT EDR 3M 5SLOT LE 1M TX LE 1M RX LE 2M TX LE 2M RX LE CODED TX LE CODED RX < HCI Command: LE Set Default PHY (0x08|0x0031) plen 3 All PHYs preference: 0x00 TX PHYs preference: 0x07 LE 1M LE 2M LE Coded RX PHYs preference: 0x07 LE 1M LE 2M LE Coded > HCI Event: Command Complete (0x0e) plen 4 LE Set Default PHY (0x08|0x0031) ncmd 1 Status: Success (0x00) @ MGMT Event: Command Complete (0x0001) plen 3 Set PHY Configuration (0x0045) plen 0 Status: Success (0x00) @ MGMT Event: PHY Configuration Changed (0x0026) plen 4 Selected PHYs: 0x7fff BR 1M 1SLOT BR 1M 3SLOT BR 1M 5SLOT EDR 2M 1SLOT EDR 2M 3SLOT EDR 2M 5SLOT EDR 3M 1SLOT EDR 3M 3SLOT EDR 3M 5SLOT LE 1M TX LE 1M RX LE 2M TX LE 2M RX LE CODED TX LE CODED RX Signed-off-by: Jaganath Kanakkassery Signed-off-by: Marcel Holtmann --- include/net/bluetooth/mgmt.h | 19 +++++ net/bluetooth/hci_event.c | 26 +++++++ net/bluetooth/mgmt.c | 182 +++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 227 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index 1c93d6e83a6c..0916e203e5d9 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -629,6 +629,25 @@ struct mgmt_rp_get_phy_confguration { #define MGMT_PHY_LE_CODED_TX 0x00002000 #define MGMT_PHY_LE_CODED_RX 0x00004000 +#define MGMT_PHY_BREDR_MASK (MGMT_PHY_BR_1M_1SLOT | MGMT_PHY_BR_1M_3SLOT | \ + MGMT_PHY_BR_1M_5SLOT | MGMT_PHY_EDR_2M_1SLOT | \ + MGMT_PHY_EDR_2M_3SLOT | MGMT_PHY_EDR_2M_5SLOT | \ + MGMT_PHY_EDR_3M_1SLOT | MGMT_PHY_EDR_3M_3SLOT | \ + MGMT_PHY_EDR_3M_5SLOT) +#define MGMT_PHY_LE_MASK (MGMT_PHY_LE_1M_TX | MGMT_PHY_LE_1M_RX | \ + MGMT_PHY_LE_2M_TX | MGMT_PHY_LE_2M_RX | \ + MGMT_PHY_LE_CODED_TX | MGMT_PHY_LE_CODED_RX) +#define MGMT_PHY_LE_TX_MASK (MGMT_PHY_LE_1M_TX | MGMT_PHY_LE_2M_TX | \ + MGMT_PHY_LE_CODED_TX) +#define MGMT_PHY_LE_RX_MASK (MGMT_PHY_LE_1M_RX | MGMT_PHY_LE_2M_RX | \ + MGMT_PHY_LE_CODED_RX) + +#define MGMT_OP_SET_PHY_CONFIGURATION 0x0045 +struct mgmt_cp_set_phy_confguration { + __le32 selected_phys; +} __packed; +#define MGMT_SET_PHY_CONFIGURATION_SIZE 4 + #define MGMT_EV_CMD_COMPLETE 0x0001 struct mgmt_ev_cmd_complete { __le16 opcode; diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 68192152c23b..694231541a4c 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -1042,6 +1042,28 @@ static void hci_cc_le_set_random_addr(struct hci_dev *hdev, struct sk_buff *skb) hci_dev_unlock(hdev); } +static void hci_cc_le_set_default_phy(struct hci_dev *hdev, struct sk_buff *skb) +{ + __u8 status = *((__u8 *) skb->data); + struct hci_cp_le_set_default_phy *cp; + + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + if (status) + return; + + cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_DEFAULT_PHY); + if (!cp) + return; + + hci_dev_lock(hdev); + + hdev->le_tx_def_phys = cp->tx_phys; + hdev->le_rx_def_phys = cp->rx_phys; + + hci_dev_unlock(hdev); +} + static void hci_cc_le_set_adv_enable(struct hci_dev *hdev, struct sk_buff *skb) { __u8 *sent, status = *((__u8 *) skb->data); @@ -3163,6 +3185,10 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb, hci_cc_le_set_ext_scan_enable(hdev, skb); break; + case HCI_OP_LE_SET_DEFAULT_PHY: + hci_cc_le_set_default_phy(hdev, skb); + break; + default: BT_DBG("%s opcode 0x%4.4x", hdev->name, *opcode); break; diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index c8c3b39fa9f2..7cd6a37a63ee 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -3328,6 +3328,187 @@ static int get_phy_configuration(struct sock *sk, struct hci_dev *hdev, &rp, sizeof(rp)); } +static void set_default_phy_complete(struct hci_dev *hdev, u8 status, + u16 opcode, struct sk_buff *skb) +{ + struct mgmt_cp_set_phy_confguration *cp; + struct mgmt_pending_cmd *cmd; + + BT_DBG("status 0x%02x", status); + + hci_dev_lock(hdev); + + cmd = pending_find(MGMT_OP_SET_PHY_CONFIGURATION, hdev); + if (!cmd) + goto unlock; + + cp = cmd->param; + + if (status) { + mgmt_cmd_status(cmd->sk, hdev->id, + MGMT_OP_SET_PHY_CONFIGURATION, + mgmt_status(status)); + } else { + mgmt_cmd_complete(cmd->sk, hdev->id, + MGMT_OP_SET_PHY_CONFIGURATION, 0, + NULL, 0); + } + + mgmt_pending_remove(cmd); + +unlock: + hci_dev_unlock(hdev); +} + +static int set_phy_configuration(struct sock *sk, struct hci_dev *hdev, + void *data, u16 len) +{ + struct mgmt_cp_set_phy_confguration *cp = data; + struct hci_cp_le_set_default_phy cp_phy; + struct mgmt_pending_cmd *cmd; + struct hci_request req; + u32 selected_phys, configurable_phys, supported_phys, unconfigure_phys; + u16 pkt_type = (HCI_DH1 | HCI_DM1); + int err; + + BT_DBG("sock %p %s", sk, hdev->name); + + configurable_phys = get_configurable_phys(hdev); + supported_phys = get_supported_phys(hdev); + selected_phys = __le32_to_cpu(cp->selected_phys); + + if (selected_phys & ~supported_phys) + return mgmt_cmd_status(sk, hdev->id, + MGMT_OP_SET_PHY_CONFIGURATION, + MGMT_STATUS_INVALID_PARAMS); + + unconfigure_phys = supported_phys & ~configurable_phys; + + if ((selected_phys & unconfigure_phys) != unconfigure_phys) + return mgmt_cmd_status(sk, hdev->id, + MGMT_OP_SET_PHY_CONFIGURATION, + MGMT_STATUS_INVALID_PARAMS); + + if (selected_phys == get_selected_phys(hdev)) + return mgmt_cmd_complete(sk, hdev->id, + MGMT_OP_SET_PHY_CONFIGURATION, + 0, NULL, 0); + + hci_dev_lock(hdev); + + if (!hdev_is_powered(hdev)) { + err = mgmt_cmd_status(sk, hdev->id, + MGMT_OP_SET_PHY_CONFIGURATION, + MGMT_STATUS_REJECTED); + goto unlock; + } + + if (pending_find(MGMT_OP_SET_PHY_CONFIGURATION, hdev)) { + err = mgmt_cmd_status(sk, hdev->id, + MGMT_OP_SET_PHY_CONFIGURATION, + MGMT_STATUS_BUSY); + goto unlock; + } + + if (selected_phys & MGMT_PHY_BR_1M_3SLOT) + pkt_type |= (HCI_DH3 | HCI_DM3); + else + pkt_type &= ~(HCI_DH3 | HCI_DM3); + + if (selected_phys & MGMT_PHY_BR_1M_5SLOT) + pkt_type |= (HCI_DH5 | HCI_DM5); + else + pkt_type &= ~(HCI_DH5 | HCI_DM5); + + if (selected_phys & MGMT_PHY_EDR_2M_1SLOT) + pkt_type &= ~HCI_2DH1; + else + pkt_type |= HCI_2DH1; + + if (selected_phys & MGMT_PHY_EDR_2M_3SLOT) + pkt_type &= ~HCI_2DH3; + else + pkt_type |= HCI_2DH3; + + if (selected_phys & MGMT_PHY_EDR_2M_5SLOT) + pkt_type &= ~HCI_2DH5; + else + pkt_type |= HCI_2DH5; + + if (selected_phys & MGMT_PHY_EDR_3M_1SLOT) + pkt_type &= ~HCI_3DH1; + else + pkt_type |= HCI_3DH1; + + if (selected_phys & MGMT_PHY_EDR_3M_3SLOT) + pkt_type &= ~HCI_3DH3; + else + pkt_type |= HCI_3DH3; + + if (selected_phys & MGMT_PHY_EDR_3M_5SLOT) + pkt_type &= ~HCI_3DH5; + else + pkt_type |= HCI_3DH5; + + if (pkt_type != hdev->pkt_type) + hdev->pkt_type = pkt_type; + + if ((selected_phys & MGMT_PHY_LE_MASK) == + (get_selected_phys(hdev) & MGMT_PHY_LE_MASK)) { + err = mgmt_cmd_complete(sk, hdev->id, + MGMT_OP_SET_PHY_CONFIGURATION, + 0, NULL, 0); + + goto unlock; + } + + cmd = mgmt_pending_add(sk, MGMT_OP_SET_PHY_CONFIGURATION, hdev, data, + len); + if (!cmd) { + err = -ENOMEM; + goto unlock; + } + + hci_req_init(&req, hdev); + + memset(&cp_phy, 0, sizeof(cp_phy)); + + if (!(selected_phys & MGMT_PHY_LE_TX_MASK)) + cp_phy.all_phys |= 0x01; + + if (!(selected_phys & MGMT_PHY_LE_RX_MASK)) + cp_phy.all_phys |= 0x02; + + if (selected_phys & MGMT_PHY_LE_1M_TX) + cp_phy.tx_phys |= HCI_LE_SET_PHY_1M; + + if (selected_phys & MGMT_PHY_LE_2M_TX) + cp_phy.tx_phys |= HCI_LE_SET_PHY_2M; + + if (selected_phys & MGMT_PHY_LE_CODED_TX) + cp_phy.tx_phys |= HCI_LE_SET_PHY_CODED; + + if (selected_phys & MGMT_PHY_LE_1M_RX) + cp_phy.rx_phys |= HCI_LE_SET_PHY_1M; + + if (selected_phys & MGMT_PHY_LE_2M_RX) + cp_phy.rx_phys |= HCI_LE_SET_PHY_2M; + + if (selected_phys & MGMT_PHY_LE_CODED_RX) + cp_phy.rx_phys |= HCI_LE_SET_PHY_CODED; + + hci_req_add(&req, HCI_OP_LE_SET_DEFAULT_PHY, sizeof(cp_phy), &cp_phy); + + err = hci_req_run_skb(&req, set_default_phy_complete); + if (err < 0) + mgmt_pending_remove(cmd); + +unlock: + hci_dev_unlock(hdev); + + return err; +} + static void read_local_oob_data_complete(struct hci_dev *hdev, u8 status, u16 opcode, struct sk_buff *skb) { @@ -6689,6 +6870,7 @@ static const struct hci_mgmt_handler mgmt_handlers[] = { HCI_MGMT_UNTRUSTED }, { set_appearance, MGMT_SET_APPEARANCE_SIZE }, { get_phy_configuration, MGMT_GET_PHY_CONFIGURATION_SIZE }, + { set_phy_configuration, MGMT_SET_PHY_CONFIGURATION_SIZE }, }; void mgmt_index_added(struct hci_dev *hdev) -- cgit v1.2.3 From b7c23df85b6a1c3bcfb591cfa938d341fc3a556e Mon Sep 17 00:00:00 2001 From: Jaganath Kanakkassery Date: Thu, 19 Jul 2018 17:09:36 +0530 Subject: Bluetooth: Implement PHY changed event This defines and implement phy changed event and send it to user whenever selected PHYs changes using SET_PHY_CONFIGURATION. This will be also trigerred when BREDR pkt_type is changed using the legacy ioctl HCISETPTYPE. @ MGMT Command: Set PHY Configuration (0x0045) plen 4 Selected PHYs: 0x7fff BR 1M 1SLOT BR 1M 3SLOT BR 1M 5SLOT EDR 2M 1SLOT EDR 2M 3SLOT EDR 2M 5SLOT EDR 3M 1SLOT EDR 3M 3SLOT EDR 3M 5SLOT LE 1M TX LE 1M RX LE 2M TX LE 2M RX LE CODED TX LE CODED RX < HCI Command: LE Set Default PHY (0x08|0x0031) plen 3 All PHYs preference: 0x00 TX PHYs preference: 0x07 LE 1M LE 2M LE Coded RX PHYs preference: 0x07 LE 1M LE 2M LE Coded > HCI Event: Command Complete (0x0e) plen 4 LE Set Default PHY (0x08|0x0031) ncmd 1 Status: Success (0x00) @ MGMT Event: Command Complete (0x0001) plen 3 Set PHY Configuration (0x0045) plen 0 Status: Success (0x00) @ MGMT Event: PHY Configuration Changed (0x0026) plen 4 Selected PHYs: 0x7fff BR 1M 1SLOT BR 1M 3SLOT BR 1M 5SLOT EDR 2M 1SLOT EDR 2M 3SLOT EDR 2M 5SLOT EDR 3M 1SLOT EDR 3M 3SLOT EDR 3M 5SLOT LE 1M TX LE 1M RX LE 2M TX LE 2M RX LE CODED TX LE CODED RX Signed-off-by: Jaganath Kanakkassery Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 1 + include/net/bluetooth/mgmt.h | 5 +++++ net/bluetooth/hci_core.c | 4 ++++ net/bluetooth/mgmt.c | 22 +++++++++++++++++++++- 4 files changed, 31 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index a64d13f91d09..ab5d494a545a 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1544,6 +1544,7 @@ void mgmt_advertising_added(struct sock *sk, struct hci_dev *hdev, u8 instance); void mgmt_advertising_removed(struct sock *sk, struct hci_dev *hdev, u8 instance); +int mgmt_phy_configuration_changed(struct hci_dev *hdev, struct sock *skip); u8 hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max, u16 latency, u16 to_multiplier); diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index 0916e203e5d9..7f372e9067c9 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -868,3 +868,8 @@ struct mgmt_ev_ext_info_changed { __le16 eir_len; __u8 eir[0]; } __packed; + +#define MGMT_EV_PHY_CONFIGURATION_CHANGED 0x0026 +struct mgmt_ev_phy_configuration_changed { + __le32 selected_phys; +} __packed; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 432f89f390c0..523e91ad64d0 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1924,7 +1924,11 @@ int hci_dev_cmd(unsigned int cmd, void __user *arg) break; case HCISETPTYPE: + if (hdev->pkt_type == (__u16) dr.dev_opt) + break; + hdev->pkt_type = (__u16) dr.dev_opt; + mgmt_phy_configuration_changed(hdev, NULL); break; case HCISETACLMTU: diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 7cd6a37a63ee..1867aadc5061 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -3328,6 +3328,18 @@ static int get_phy_configuration(struct sock *sk, struct hci_dev *hdev, &rp, sizeof(rp)); } +int mgmt_phy_configuration_changed(struct hci_dev *hdev, struct sock *skip) +{ + struct mgmt_ev_phy_configuration_changed ev; + + memset(&ev, 0, sizeof(ev)); + + ev.selected_phys = cpu_to_le32(get_selected_phys(hdev)); + + return mgmt_event(MGMT_EV_PHY_CONFIGURATION_CHANGED, hdev, &ev, + sizeof(ev), skip); +} + static void set_default_phy_complete(struct hci_dev *hdev, u8 status, u16 opcode, struct sk_buff *skb) { @@ -3352,6 +3364,8 @@ static void set_default_phy_complete(struct hci_dev *hdev, u8 status, mgmt_cmd_complete(cmd->sk, hdev->id, MGMT_OP_SET_PHY_CONFIGURATION, 0, NULL, 0); + + mgmt_phy_configuration_changed(hdev, cmd->sk); } mgmt_pending_remove(cmd); @@ -3369,6 +3383,7 @@ static int set_phy_configuration(struct sock *sk, struct hci_dev *hdev, struct hci_request req; u32 selected_phys, configurable_phys, supported_phys, unconfigure_phys; u16 pkt_type = (HCI_DH1 | HCI_DM1); + bool changed = false; int err; BT_DBG("sock %p %s", sk, hdev->name); @@ -3450,11 +3465,16 @@ static int set_phy_configuration(struct sock *sk, struct hci_dev *hdev, else pkt_type |= HCI_3DH5; - if (pkt_type != hdev->pkt_type) + if (pkt_type != hdev->pkt_type) { hdev->pkt_type = pkt_type; + changed = true; + } if ((selected_phys & MGMT_PHY_LE_MASK) == (get_selected_phys(hdev) & MGMT_PHY_LE_MASK)) { + if (changed) + mgmt_phy_configuration_changed(hdev, sk); + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_SET_PHY_CONFIGURATION, 0, NULL, 0); -- cgit v1.2.3 From 45bdd86eafc7d29e0b4b6681bec9c6ab8eddc6bf Mon Sep 17 00:00:00 2001 From: Jaganath Kanakkassery Date: Thu, 19 Jul 2018 17:09:37 +0530 Subject: Bluetooth: Set Scan PHYs based on selected PHYs by user Use the PHYs selected in Set Phy Configuration management command while scanning. < HCI Command: LE Set Extended Scan Parameters (0x08|0x0041) plen 13 Own address type: Random (0x01) Filter policy: Accept all advertisement (0x00) PHYs: 0x05 Entry 0: LE 1M Type: Active (0x01) Interval: 11.250 msec (0x0012) Window: 11.250 msec (0x0012) Entry 1: LE Coded Type: Active (0x01) Interval: 11.250 msec (0x0012) Window: 11.250 msec (0x0012) > HCI Event: Command Complete (0x0e) plen 4 LE Set Extended Scan Parameters (0x08|0x0041) ncmd 1 Status: Success (0x00) < HCI Command: LE Set Extended Scan Enable (0x08|0x0042) plen 6 Extended scan: Enabled (0x01) Filter duplicates: Enabled (0x01) Duration: 0 msec (0x0000) Period: 0.00 sec (0x0000) > HCI Event: Command Complete (0x0e) plen 4 LE Set Extended Scan Enable (0x08|0x0042) ncmd 2 Status: Success (0x00) Signed-off-by: Jaganath Kanakkassery Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci.h | 4 +++- include/net/bluetooth/hci_core.h | 9 +++++++++ net/bluetooth/hci_request.c | 37 ++++++++++++++++++++++++++++--------- 3 files changed, 40 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 89bf800f6eb1..04211457367a 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -1540,7 +1540,9 @@ struct hci_cp_le_set_ext_scan_params { __u8 data[0]; } __packed; -#define LE_SCAN_PHY_1M 0x01 +#define LE_SCAN_PHY_1M 0x01 +#define LE_SCAN_PHY_2M 0x02 +#define LE_SCAN_PHY_CODED 0x04 struct hci_cp_le_scan_phy_params { __u8 type; diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index ab5d494a545a..113c9bb609c7 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1165,6 +1165,15 @@ void hci_conn_del_sysfs(struct hci_conn *conn); #define bredr_sc_enabled(dev) (lmp_sc_capable(dev) && \ hci_dev_test_flag(dev, HCI_SC_ENABLED)) +#define scan_1m(dev) (((dev)->le_tx_def_phys & HCI_LE_SET_PHY_1M) || \ + ((dev)->le_rx_def_phys & HCI_LE_SET_PHY_1M)) + +#define scan_2m(dev) (((dev)->le_tx_def_phys & HCI_LE_SET_PHY_2M) || \ + ((dev)->le_rx_def_phys & HCI_LE_SET_PHY_2M)) + +#define scan_coded(dev) (((dev)->le_tx_def_phys & HCI_LE_SET_PHY_CODED) || \ + ((dev)->le_rx_def_phys & HCI_LE_SET_PHY_CODED)) + /* Use ext scanning if set ext scan param and ext scan enable is supported */ #define use_ext_scan(dev) (((dev)->commands[37] & 0x20) && \ ((dev)->commands[37] & 0x40)) diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index faf7c711234c..215059a7646e 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -790,8 +790,8 @@ static void hci_req_start_scan(struct hci_request *req, u8 type, u16 interval, struct hci_cp_le_set_ext_scan_params *ext_param_cp; struct hci_cp_le_set_ext_scan_enable ext_enable_cp; struct hci_cp_le_scan_phy_params *phy_params; - /* Ony single PHY (1M) is supported as of now */ - u8 data[sizeof(*ext_param_cp) + sizeof(*phy_params) * 1]; + u8 data[sizeof(*ext_param_cp) + sizeof(*phy_params) * 2]; + u32 plen; ext_param_cp = (void *)data; phy_params = (void *)ext_param_cp->data; @@ -799,16 +799,35 @@ static void hci_req_start_scan(struct hci_request *req, u8 type, u16 interval, memset(ext_param_cp, 0, sizeof(*ext_param_cp)); ext_param_cp->own_addr_type = own_addr_type; ext_param_cp->filter_policy = filter_policy; - ext_param_cp->scanning_phys = LE_SCAN_PHY_1M; - memset(phy_params, 0, sizeof(*phy_params)); - phy_params->type = type; - phy_params->interval = cpu_to_le16(interval); - phy_params->window = cpu_to_le16(window); + plen = sizeof(*ext_param_cp); + + if (scan_1m(hdev) || scan_2m(hdev)) { + ext_param_cp->scanning_phys |= LE_SCAN_PHY_1M; + + memset(phy_params, 0, sizeof(*phy_params)); + phy_params->type = type; + phy_params->interval = cpu_to_le16(interval); + phy_params->window = cpu_to_le16(window); + + plen += sizeof(*phy_params); + phy_params++; + } + + if (scan_coded(hdev)) { + ext_param_cp->scanning_phys |= LE_SCAN_PHY_CODED; + + memset(phy_params, 0, sizeof(*phy_params)); + phy_params->type = type; + phy_params->interval = cpu_to_le16(interval); + phy_params->window = cpu_to_le16(window); + + plen += sizeof(*phy_params); + phy_params++; + } hci_req_add(req, HCI_OP_LE_SET_EXT_SCAN_PARAMS, - sizeof(*ext_param_cp) + sizeof(*phy_params), - ext_param_cp); + plen, ext_param_cp); memset(&ext_enable_cp, 0, sizeof(ext_enable_cp)); ext_enable_cp.enable = LE_SCAN_ENABLE; -- cgit v1.2.3 From b2cc9761f144e8ef714be8c590603073b80ddc13 Mon Sep 17 00:00:00 2001 From: Jaganath Kanakkassery Date: Thu, 19 Jul 2018 17:09:38 +0530 Subject: Bluetooth: Handle extended ADV PDU types This patch defines the extended ADV types and handle it in ADV report. Signed-off-by: Jaganath Kanakkassery Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci.h | 8 ++++++++ net/bluetooth/hci_event.c | 50 +++++++++++++++++++++++++++++++++------------ 2 files changed, 45 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 04211457367a..83a1593a128e 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -1976,6 +1976,14 @@ struct hci_ev_le_conn_complete { #define LE_LEGACY_SCAN_RSP_ADV 0x001b #define LE_LEGACY_SCAN_RSP_ADV_SCAN 0x001a +/* Extended Advertising event types */ +#define LE_EXT_ADV_NON_CONN_IND 0x0000 +#define LE_EXT_ADV_CONN_IND 0x0001 +#define LE_EXT_ADV_SCAN_IND 0x0002 +#define LE_EXT_ADV_DIRECT_IND 0x0004 +#define LE_EXT_ADV_SCAN_RSP 0x0008 +#define LE_EXT_ADV_LEGACY_PDU 0x0010 + #define ADDR_LE_DEV_PUBLIC 0x00 #define ADDR_LE_DEV_RANDOM 0x01 diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 694231541a4c..5fa00f488cfc 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -5137,21 +5137,45 @@ static void hci_le_adv_report_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_dev_unlock(hdev); } -static u8 convert_legacy_evt_type(u16 evt_type) -{ - switch (evt_type) { - case LE_LEGACY_ADV_IND: +static u8 ext_evt_type_to_legacy(u16 evt_type) +{ + if (evt_type & LE_EXT_ADV_LEGACY_PDU) { + switch (evt_type) { + case LE_LEGACY_ADV_IND: + return LE_ADV_IND; + case LE_LEGACY_ADV_DIRECT_IND: + return LE_ADV_DIRECT_IND; + case LE_LEGACY_ADV_SCAN_IND: + return LE_ADV_SCAN_IND; + case LE_LEGACY_NONCONN_IND: + return LE_ADV_NONCONN_IND; + case LE_LEGACY_SCAN_RSP_ADV: + case LE_LEGACY_SCAN_RSP_ADV_SCAN: + return LE_ADV_SCAN_RSP; + } + + BT_ERR_RATELIMITED("Unknown advertising packet type: 0x%02x", + evt_type); + + return LE_ADV_INVALID; + } + + if (evt_type & LE_EXT_ADV_CONN_IND) { + if (evt_type & LE_EXT_ADV_DIRECT_IND) + return LE_ADV_DIRECT_IND; + return LE_ADV_IND; - case LE_LEGACY_ADV_DIRECT_IND: - return LE_ADV_DIRECT_IND; - case LE_LEGACY_ADV_SCAN_IND: + } + + if (evt_type & LE_EXT_ADV_SCAN_RSP) + return LE_ADV_SCAN_RSP; + + if (evt_type & LE_EXT_ADV_SCAN_IND) return LE_ADV_SCAN_IND; - case LE_LEGACY_NONCONN_IND: + + if (evt_type == LE_EXT_ADV_NON_CONN_IND || + evt_type & LE_EXT_ADV_DIRECT_IND) return LE_ADV_NONCONN_IND; - case LE_LEGACY_SCAN_RSP_ADV: - case LE_LEGACY_SCAN_RSP_ADV_SCAN: - return LE_ADV_SCAN_RSP; - } BT_ERR_RATELIMITED("Unknown advertising packet type: 0x%02x", evt_type); @@ -5172,7 +5196,7 @@ static void hci_le_ext_adv_report_evt(struct hci_dev *hdev, struct sk_buff *skb) u16 evt_type; evt_type = __le16_to_cpu(ev->evt_type); - legacy_evt_type = convert_legacy_evt_type(evt_type); + legacy_evt_type = ext_evt_type_to_legacy(evt_type); if (legacy_evt_type != LE_ADV_INVALID) { process_adv_report(hdev, legacy_evt_type, &ev->bdaddr, ev->bdaddr_type, NULL, 0, ev->rssi, -- cgit v1.2.3 From 6b49bcb4bce2ed0f0aefe8e304a8b9cbaeeaa3f0 Mon Sep 17 00:00:00 2001 From: Jaganath Kanakkassery Date: Thu, 19 Jul 2018 17:09:40 +0530 Subject: Bluetooth: Read no of adv sets during init This patch reads the number of advertising sets in the controller during init and save it in hdev. Signed-off-by: Jaganath Kanakkassery Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci.h | 7 +++++++ include/net/bluetooth/hci_core.h | 4 ++++ net/bluetooth/hci_core.c | 16 ++++++++++++++-- net/bluetooth/hci_event.c | 18 ++++++++++++++++++ 4 files changed, 43 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 83a1593a128e..3f93ae9765a4 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -410,6 +410,7 @@ enum { #define HCI_LE_SLAVE_FEATURES 0x08 #define HCI_LE_PING 0x10 #define HCI_LE_DATA_LEN_EXT 0x20 +#define HCI_LE_EXT_ADV 0x10 #define HCI_LE_EXT_SCAN_POLICY 0x80 #define HCI_LE_PHY_2M 0x01 #define HCI_LE_PHY_CODED 0x08 @@ -1579,6 +1580,12 @@ struct hci_cp_le_ext_conn_param { __le16 max_ce_len; } __packed; +#define HCI_OP_LE_READ_NUM_SUPPORTED_ADV_SETS 0x203b +struct hci_rp_le_read_num_supported_adv_sets { + __u8 status; + __u8 num_of_sets; +} __packed; + /* ---- HCI Events ---- */ #define HCI_EV_INQUIRY_COMPLETE 0x01 diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 113c9bb609c7..2aad4a863176 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -222,6 +222,7 @@ struct hci_dev { __u8 le_features[8]; __u8 le_white_list_size; __u8 le_resolv_list_size; + __u8 le_num_of_adv_sets; __u8 le_states[8]; __u8 commands[64]; __u8 hci_ver; @@ -1180,6 +1181,9 @@ void hci_conn_del_sysfs(struct hci_conn *conn); /* Use ext create connection if command is supported */ #define use_ext_conn(dev) ((dev)->commands[37] & 0x80) +/* Extended advertising support */ +#define ext_adv_capable(dev) (((dev)->le_features[1] & HCI_LE_EXT_ADV)) + /* ----- HCI protocols ----- */ #define HCI_PROTO_DEFER 0x01 diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 523e91ad64d0..7b08b7f57418 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -715,8 +715,14 @@ static int hci_init3_req(struct hci_request *req, unsigned long opt) hci_req_add(req, HCI_OP_LE_SET_EVENT_MASK, sizeof(events), events); - if (hdev->commands[25] & 0x40) { - /* Read LE Advertising Channel TX Power */ + /* Read LE Advertising Channel TX Power */ + if ((hdev->commands[25] & 0x40) && !ext_adv_capable(hdev)) { + /* HCI TS spec forbids mixing of legacy and extended + * advertising commands wherein READ_ADV_TX_POWER is + * also included. So do not call it if extended adv + * is supported otherwise controller will return + * COMMAND_DISALLOWED for extended commands. + */ hci_req_add(req, HCI_OP_LE_READ_ADV_TX_POWER, 0, NULL); } @@ -750,6 +756,12 @@ static int hci_init3_req(struct hci_request *req, unsigned long opt) hci_req_add(req, HCI_OP_LE_READ_DEF_DATA_LEN, 0, NULL); } + if (ext_adv_capable(hdev)) { + /* Read LE Number of Supported Advertising Sets */ + hci_req_add(req, HCI_OP_LE_READ_NUM_SUPPORTED_ADV_SETS, + 0, NULL); + } + hci_set_le_support(req); } diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 5fa00f488cfc..0ceb52edc142 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -1267,6 +1267,20 @@ static void hci_cc_le_set_ext_scan_enable(struct hci_dev *hdev, le_set_scan_enable_complete(hdev, cp->enable); } +static void hci_cc_le_read_num_adv_sets(struct hci_dev *hdev, + struct sk_buff *skb) +{ + struct hci_rp_le_read_num_supported_adv_sets *rp = (void *) skb->data; + + BT_DBG("%s status 0x%2.2x No of Adv sets %u", hdev->name, rp->status, + rp->num_of_sets); + + if (rp->status) + return; + + hdev->le_num_of_adv_sets = rp->num_of_sets; +} + static void hci_cc_le_read_white_list_size(struct hci_dev *hdev, struct sk_buff *skb) { @@ -3189,6 +3203,10 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb, hci_cc_le_set_default_phy(hdev, skb); break; + case HCI_OP_LE_READ_NUM_SUPPORTED_ADV_SETS: + hci_cc_le_read_num_adv_sets(hdev, skb); + break; + default: BT_DBG("%s opcode 0x%4.4x", hdev->name, *opcode); break; -- cgit v1.2.3 From de181e887ac27dadda127c7d4c3e89c6da8fb6d2 Mon Sep 17 00:00:00 2001 From: Jaganath Kanakkassery Date: Thu, 19 Jul 2018 17:09:41 +0530 Subject: Bluetooth: Impmlement extended adv enable This patch basically replaces legacy adv with extended adv based on the controller support. Currently there is no design change. ie only one adv set will be enabled at a time. This also adds tx_power in instance and store whatever returns from Set_ext_parameter, use the same in adv data as well. For instance 0 tx_power is stored in hdev only. < HCI Command: LE Set Extended Advertising Parameters (0x08|0x0036) plen 25 Handle: 0x00 Properties: 0x0010 Use legacy advertising PDUs: ADV_NONCONN_IND Min advertising interval: 1280.000 msec (0x0800) Max advertising interval: 1280.000 msec (0x0800) Channel map: 37, 38, 39 (0x07) Own address type: Random (0x01) Peer address type: Public (0x00) Peer address: 00:00:00:00:00:00 (OUI 00-00-00) Filter policy: Allow Scan Request from Any, Allow Connect Request from Any (0x00) TX power: 127 dbm (0x7f) Primary PHY: LE 1M (0x01) Secondary max skip: 0x00 Secondary PHY: LE 1M (0x01) SID: 0x00 Scan request notifications: Disabled (0x00) > HCI Event: Command Complete (0x0e) plen 5 LE Set Extended Advertising Parameters (0x08|0x0036) ncmd 1 Status: Success (0x00) TX power (selected): 7 dbm (0x07) < HCI Command: LE Set Extended Advertising Enable (0x08|0x0039) plen 6 Extended advertising: Enabled (0x01) Number of sets: 1 (0x01) Entry 0 Handle: 0x00 Duration: 0 ms (0x00) Max ext adv events: 0 > HCI Event: Command Complete (0x0e) plen 4 LE Set Extended Advertising Enable (0x08|0x0039) ncmd 2 Status: Success (0x00) Signed-off-by: Jaganath Kanakkassery Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci.h | 39 +++++++++ include/net/bluetooth/hci_core.h | 1 + net/bluetooth/hci_core.c | 2 + net/bluetooth/hci_event.c | 72 +++++++++++++++++ net/bluetooth/hci_request.c | 171 ++++++++++++++++++++++++++++++++++----- net/bluetooth/hci_request.h | 3 + net/bluetooth/mgmt.c | 22 +++-- 7 files changed, 285 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 3f93ae9765a4..b447b127879e 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -1586,6 +1586,45 @@ struct hci_rp_le_read_num_supported_adv_sets { __u8 num_of_sets; } __packed; +#define HCI_OP_LE_SET_EXT_ADV_PARAMS 0x2036 +struct hci_cp_le_set_ext_adv_params { + __u8 handle; + __le16 evt_properties; + __u8 min_interval[3]; + __u8 max_interval[3]; + __u8 channel_map; + __u8 own_addr_type; + __u8 peer_addr_type; + bdaddr_t peer_addr; + __u8 filter_policy; + __u8 tx_power; + __u8 primary_phy; + __u8 secondary_max_skip; + __u8 secondary_phy; + __u8 sid; + __u8 notif_enable; +} __packed; + +#define HCI_ADV_PHY_1M 0X01 + +struct hci_rp_le_set_ext_adv_params { + __u8 status; + __u8 tx_power; +} __packed; + +#define HCI_OP_LE_SET_EXT_ADV_ENABLE 0x2039 +struct hci_cp_le_set_ext_adv_enable { + __u8 enable; + __u8 num_of_sets; + __u8 data[0]; +} __packed; + +struct hci_cp_ext_adv_set { + __u8 handle; + __le16 duration; + __u8 max_events; +} __packed; + /* ---- HCI Events ---- */ #define HCI_EV_INQUIRY_COMPLETE 0x01 diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 2aad4a863176..ad3518303a0c 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -171,6 +171,7 @@ struct adv_info { __u8 adv_data[HCI_MAX_AD_LENGTH]; __u16 scan_rsp_len; __u8 scan_rsp_data[HCI_MAX_AD_LENGTH]; + __s8 tx_power; }; #define HCI_MAX_ADV_INSTANCES 5 diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 7b08b7f57418..944d4fedc317 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2779,6 +2779,8 @@ int hci_add_adv_instance(struct hci_dev *hdev, u8 instance, u32 flags, else adv_instance->duration = duration; + adv_instance->tx_power = HCI_TX_POWER_INVALID; + BT_DBG("%s for %dMR", hdev->name, instance); return 0; diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 0ceb52edc142..0418a5514819 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -1099,6 +1099,41 @@ static void hci_cc_le_set_adv_enable(struct hci_dev *hdev, struct sk_buff *skb) hci_dev_unlock(hdev); } +static void hci_cc_le_set_ext_adv_enable(struct hci_dev *hdev, + struct sk_buff *skb) +{ + struct hci_cp_le_set_ext_adv_enable *cp; + struct hci_cp_ext_adv_set *adv_set; + __u8 status = *((__u8 *) skb->data); + + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + if (status) + return; + + cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_EXT_ADV_ENABLE); + if (!cp) + return; + + adv_set = (void *) cp->data; + + hci_dev_lock(hdev); + + if (cp->enable) { + struct hci_conn *conn; + + hci_dev_set_flag(hdev, HCI_LE_ADV); + + conn = hci_lookup_le_connect(hdev); + if (conn) + queue_delayed_work(hdev->workqueue, + &conn->le_conn_timeout, + conn->conn_timeout); + } + + hci_dev_unlock(hdev); +} + static void hci_cc_le_set_scan_param(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_cp_le_set_scan_param *cp; @@ -1486,6 +1521,35 @@ static void hci_cc_set_adv_param(struct hci_dev *hdev, struct sk_buff *skb) hci_dev_unlock(hdev); } +static void hci_cc_set_ext_adv_param(struct hci_dev *hdev, struct sk_buff *skb) +{ + struct hci_rp_le_set_ext_adv_params *rp = (void *) skb->data; + struct hci_cp_le_set_ext_adv_params *cp; + struct adv_info *adv_instance; + + BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); + + if (rp->status) + return; + + cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_EXT_ADV_PARAMS); + if (!cp) + return; + + hci_dev_lock(hdev); + hdev->adv_addr_type = cp->own_addr_type; + if (!hdev->cur_adv_instance) { + /* Store in hdev for instance 0 */ + hdev->adv_tx_power = rp->tx_power; + } else { + adv_instance = hci_find_adv_instance(hdev, + hdev->cur_adv_instance); + if (adv_instance) + adv_instance->tx_power = rp->tx_power; + } + hci_dev_unlock(hdev); +} + static void hci_cc_read_rssi(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_rp_read_rssi *rp = (void *) skb->data; @@ -3207,6 +3271,14 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb, hci_cc_le_read_num_adv_sets(hdev, skb); break; + case HCI_OP_LE_SET_EXT_ADV_PARAMS: + hci_cc_set_ext_adv_param(hdev, skb); + break; + + case HCI_OP_LE_SET_EXT_ADV_ENABLE: + hci_cc_le_set_ext_adv_enable(hdev, skb); + break; + default: BT_DBG("%s opcode 0x%4.4x", hdev->name, *opcode); break; diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index 215059a7646e..2ac9fd67440a 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -895,6 +895,24 @@ void hci_req_add_le_passive_scan(struct hci_request *req) hdev->le_scan_window, own_addr_type, filter_policy); } +static u8 get_adv_instance_scan_rsp_len(struct hci_dev *hdev, u8 instance) +{ + struct adv_info *adv_instance; + + /* Ignore instance 0 */ + if (instance == 0x00) + return 0; + + adv_instance = hci_find_adv_instance(hdev, instance); + if (!adv_instance) + return 0; + + /* TODO: Take into account the "appearance" and "local-name" flags here. + * These are currently being ignored as they are not supported. + */ + return adv_instance->scan_rsp_len; +} + static u8 get_cur_adv_instance_scan_rsp_len(struct hci_dev *hdev) { u8 instance = hdev->cur_adv_instance; @@ -1235,15 +1253,27 @@ static u8 create_instance_adv_data(struct hci_dev *hdev, u8 instance, u8 *ptr) ptr += adv_instance->adv_data_len; } - /* Provide Tx Power only if we can provide a valid value for it */ - if (hdev->adv_tx_power != HCI_TX_POWER_INVALID && - (instance_flags & MGMT_ADV_FLAG_TX_POWER)) { - ptr[0] = 0x02; - ptr[1] = EIR_TX_POWER; - ptr[2] = (u8)hdev->adv_tx_power; + if (instance_flags & MGMT_ADV_FLAG_TX_POWER) { + s8 adv_tx_power; - ad_len += 3; - ptr += 3; + if (ext_adv_capable(hdev)) { + if (adv_instance) + adv_tx_power = adv_instance->tx_power; + else + adv_tx_power = hdev->adv_tx_power; + } else { + adv_tx_power = hdev->adv_tx_power; + } + + /* Provide Tx Power only if we can provide a valid value for it */ + if (adv_tx_power != HCI_TX_POWER_INVALID) { + ptr[0] = 0x02; + ptr[1] = EIR_TX_POWER; + ptr[2] = (u8)adv_tx_power; + + ad_len += 3; + ptr += 3; + } } return ad_len; @@ -1304,9 +1334,13 @@ void hci_req_reenable_advertising(struct hci_dev *hdev) __hci_req_schedule_adv_instance(&req, hdev->cur_adv_instance, true); } else { - __hci_req_update_adv_data(&req, 0x00); - __hci_req_update_scan_rsp_data(&req, 0x00); - __hci_req_enable_advertising(&req); + if (ext_adv_capable(hdev)) { + __hci_req_start_ext_adv(&req, 0x00); + } else { + __hci_req_update_adv_data(&req, 0x00); + __hci_req_update_scan_rsp_data(&req, 0x00); + __hci_req_enable_advertising(&req); + } } hci_req_run(&req, adv_enable_complete); @@ -1343,6 +1377,87 @@ unlock: hci_dev_unlock(hdev); } +static int __hci_req_setup_ext_adv_instance(struct hci_request *req, + u8 instance) +{ + struct hci_cp_le_set_ext_adv_params cp; + struct hci_dev *hdev = req->hdev; + bool connectable; + u32 flags; + /* In ext adv set param interval is 3 octets */ + const u8 adv_interval[3] = { 0x00, 0x08, 0x00 }; + + flags = get_adv_instance_flags(hdev, instance); + + /* If the "connectable" instance flag was not set, then choose between + * ADV_IND and ADV_NONCONN_IND based on the global connectable setting. + */ + connectable = (flags & MGMT_ADV_FLAG_CONNECTABLE) || + mgmt_get_connectable(hdev); + + if (!is_advertising_allowed(hdev, connectable)) + return -EPERM; + + memset(&cp, 0, sizeof(cp)); + + memcpy(cp.min_interval, adv_interval, sizeof(cp.min_interval)); + memcpy(cp.max_interval, adv_interval, sizeof(cp.max_interval)); + + if (connectable) + cp.evt_properties = cpu_to_le16(LE_LEGACY_ADV_IND); + else if (get_adv_instance_scan_rsp_len(hdev, instance)) + cp.evt_properties = cpu_to_le16(LE_LEGACY_ADV_SCAN_IND); + else + cp.evt_properties = cpu_to_le16(LE_LEGACY_NONCONN_IND); + + cp.own_addr_type = BDADDR_LE_PUBLIC; + cp.channel_map = hdev->le_adv_channel_map; + cp.tx_power = 127; + cp.primary_phy = HCI_ADV_PHY_1M; + cp.secondary_phy = HCI_ADV_PHY_1M; + cp.handle = 0; + + hci_req_add(req, HCI_OP_LE_SET_EXT_ADV_PARAMS, sizeof(cp), &cp); + + return 0; +} + +void __hci_req_enable_ext_advertising(struct hci_request *req) +{ + struct hci_cp_le_set_ext_adv_enable *cp; + struct hci_cp_ext_adv_set *adv_set; + u8 data[sizeof(*cp) + sizeof(*adv_set) * 1]; + + cp = (void *) data; + adv_set = (void *) cp->data; + + memset(cp, 0, sizeof(*cp)); + + cp->enable = 0x01; + cp->num_of_sets = 0x01; + + memset(adv_set, 0, sizeof(*adv_set)); + + adv_set->handle = 0; + + hci_req_add(req, HCI_OP_LE_SET_EXT_ADV_ENABLE, + sizeof(*cp) + sizeof(*adv_set) * cp->num_of_sets, + data); +} + +int __hci_req_start_ext_adv(struct hci_request *req, u8 instance) +{ + int err; + + err = __hci_req_setup_ext_adv_instance(req, instance); + if (err < 0) + return err; + + __hci_req_enable_ext_advertising(req); + + return 0; +} + int __hci_req_schedule_adv_instance(struct hci_request *req, u8 instance, bool force) { @@ -1396,9 +1511,13 @@ int __hci_req_schedule_adv_instance(struct hci_request *req, u8 instance, return 0; hdev->cur_adv_instance = instance; - __hci_req_update_adv_data(req, instance); - __hci_req_update_scan_rsp_data(req, instance); - __hci_req_enable_advertising(req); + if (ext_adv_capable(hdev)) { + __hci_req_start_ext_adv(req, instance); + } else { + __hci_req_update_adv_data(req, instance); + __hci_req_update_scan_rsp_data(req, instance); + __hci_req_enable_advertising(req); + } return 0; } @@ -1669,8 +1788,12 @@ static int connectable_update(struct hci_request *req, unsigned long opt) /* Update the advertising parameters if necessary */ if (hci_dev_test_flag(hdev, HCI_ADVERTISING) || - !list_empty(&hdev->adv_instances)) - __hci_req_enable_advertising(req); + !list_empty(&hdev->adv_instances)) { + if (ext_adv_capable(hdev)) + __hci_req_start_ext_adv(req, hdev->cur_adv_instance); + else + __hci_req_enable_advertising(req); + } __hci_update_background_scan(req); @@ -1779,8 +1902,12 @@ static int discoverable_update(struct hci_request *req, unsigned long opt) /* Discoverable mode affects the local advertising * address in limited privacy mode. */ - if (hci_dev_test_flag(hdev, HCI_LIMITED_PRIVACY)) - __hci_req_enable_advertising(req); + if (hci_dev_test_flag(hdev, HCI_LIMITED_PRIVACY)) { + if (ext_adv_capable(hdev)) + __hci_req_start_ext_adv(req, 0x00); + else + __hci_req_enable_advertising(req); + } } hci_dev_unlock(hdev); @@ -2376,8 +2503,12 @@ static int powered_update_hci(struct hci_request *req, unsigned long opt) __hci_req_update_adv_data(req, 0x00); __hci_req_update_scan_rsp_data(req, 0x00); - if (hci_dev_test_flag(hdev, HCI_ADVERTISING)) - __hci_req_enable_advertising(req); + if (hci_dev_test_flag(hdev, HCI_ADVERTISING)) { + if (ext_adv_capable(hdev)) + __hci_req_start_ext_adv(req, 0x00); + else + __hci_req_enable_advertising(req); + } } else if (!list_empty(&hdev->adv_instances)) { struct adv_info *adv_instance; diff --git a/net/bluetooth/hci_request.h b/net/bluetooth/hci_request.h index 702beb140d9f..9b8c74df6b2b 100644 --- a/net/bluetooth/hci_request.h +++ b/net/bluetooth/hci_request.h @@ -80,6 +80,9 @@ void hci_req_clear_adv_instance(struct hci_dev *hdev, struct sock *sk, struct hci_request *req, u8 instance, bool force); +int __hci_req_start_ext_adv(struct hci_request *req, u8 instance); +void __hci_req_enable_ext_advertising(struct hci_request *req); + void __hci_req_update_class(struct hci_request *req); /* Returns true if HCI commands were queued */ diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 1867aadc5061..761a9aeaa824 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -940,7 +940,10 @@ static void rpa_expired(struct work_struct *work) * function. */ hci_req_init(&req, hdev); - __hci_req_enable_advertising(&req); + if (ext_adv_capable(hdev)) + __hci_req_start_ext_adv(&req, hdev->cur_adv_instance); + else + __hci_req_enable_advertising(&req); hci_req_run(&req, NULL); } @@ -4382,9 +4385,14 @@ static int set_advertising(struct sock *sk, struct hci_dev *hdev, void *data, * HCI_ADVERTISING flag is not yet set. */ hdev->cur_adv_instance = 0x00; - __hci_req_update_adv_data(&req, 0x00); - __hci_req_update_scan_rsp_data(&req, 0x00); - __hci_req_enable_advertising(&req); + + if (ext_adv_capable(hdev)) { + __hci_req_start_ext_adv(&req, 0x00); + } else { + __hci_req_update_adv_data(&req, 0x00); + __hci_req_update_scan_rsp_data(&req, 0x00); + __hci_req_enable_advertising(&req); + } } else { __hci_req_disable_advertising(&req); } @@ -6312,7 +6320,11 @@ static u32 get_supported_adv_flags(struct hci_dev *hdev) flags |= MGMT_ADV_FLAG_APPEARANCE; flags |= MGMT_ADV_FLAG_LOCAL_NAME; - if (hdev->adv_tx_power != HCI_TX_POWER_INVALID) + /* In extended adv TX_POWER returned from Set Adv Param + * will be always valid. + */ + if ((hdev->adv_tx_power != HCI_TX_POWER_INVALID) || + ext_adv_capable(hdev)) flags |= MGMT_ADV_FLAG_TX_POWER; return flags; -- cgit v1.2.3 From a0fb3726ba55138ef6fdd5dc67da6d9a70360696 Mon Sep 17 00:00:00 2001 From: Jaganath Kanakkassery Date: Thu, 19 Jul 2018 17:09:42 +0530 Subject: Bluetooth: Use Set ext adv/scan rsp data if controller supports This patch implements Set Ext Adv data and Set Ext Scan rsp data if controller support extended advertising. Currently the operation is set as Complete data and fragment preference is set as no fragment < HCI Command: LE Set Extended Advertising Data (0x08|0x0037) plen 35 Handle: 0x00 Operation: Complete extended advertising data (0x03) Fragment preference: Minimize fragmentation (0x01) Data length: 0x15 16-bit Service UUIDs (complete): 2 entries Heart Rate (0x180d) Battery Service (0x180f) Name (complete): Test LE Company: Google (224) Data: 0102 > HCI Event: Command Complete (0x0e) plen 4 LE Set Extended Advertising Data (0x08|0x0037) ncmd 1 Status: Success (0x00) Signed-off-by: Jaganath Kanakkassery Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci.h | 22 ++++++++ net/bluetooth/hci_event.c | 2 + net/bluetooth/hci_request.c | 126 +++++++++++++++++++++++++++++++++----------- net/bluetooth/hci_request.h | 1 + net/bluetooth/mgmt.c | 13 +++-- 5 files changed, 130 insertions(+), 34 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index b447b127879e..aace97099ead 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -1625,6 +1625,28 @@ struct hci_cp_ext_adv_set { __u8 max_events; } __packed; +#define HCI_OP_LE_SET_EXT_ADV_DATA 0x2037 +struct hci_cp_le_set_ext_adv_data { + __u8 handle; + __u8 operation; + __u8 frag_pref; + __u8 length; + __u8 data[HCI_MAX_AD_LENGTH]; +} __packed; + +#define HCI_OP_LE_SET_EXT_SCAN_RSP_DATA 0x2038 +struct hci_cp_le_set_ext_scan_rsp_data { + __u8 handle; + __u8 operation; + __u8 frag_pref; + __u8 length; + __u8 data[HCI_MAX_AD_LENGTH]; +} __packed; + +#define LE_SET_ADV_DATA_OP_COMPLETE 0x03 + +#define LE_SET_ADV_DATA_NO_FRAG 0x01 + /* ---- HCI Events ---- */ #define HCI_EV_INQUIRY_COMPLETE 0x01 diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 0418a5514819..0a92bf7e3d80 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -1547,6 +1547,8 @@ static void hci_cc_set_ext_adv_param(struct hci_dev *hdev, struct sk_buff *skb) if (adv_instance) adv_instance->tx_power = rp->tx_power; } + /* Update adv data as tx power is known now */ + hci_req_update_adv_data(hdev, hdev->cur_adv_instance); hci_dev_unlock(hdev); } diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index 2ac9fd67440a..c41e9bb7818b 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -1174,29 +1174,58 @@ static u8 create_instance_scan_rsp_data(struct hci_dev *hdev, u8 instance, void __hci_req_update_scan_rsp_data(struct hci_request *req, u8 instance) { struct hci_dev *hdev = req->hdev; - struct hci_cp_le_set_scan_rsp_data cp; u8 len; if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED)) return; - memset(&cp, 0, sizeof(cp)); + if (ext_adv_capable(hdev)) { + struct hci_cp_le_set_ext_scan_rsp_data cp; - if (instance) - len = create_instance_scan_rsp_data(hdev, instance, cp.data); - else - len = create_default_scan_rsp_data(hdev, cp.data); + memset(&cp, 0, sizeof(cp)); - if (hdev->scan_rsp_data_len == len && - !memcmp(cp.data, hdev->scan_rsp_data, len)) - return; + if (instance) + len = create_instance_scan_rsp_data(hdev, instance, + cp.data); + else + len = create_default_scan_rsp_data(hdev, cp.data); + + if (hdev->scan_rsp_data_len == len && + !memcmp(cp.data, hdev->scan_rsp_data, len)) + return; + + memcpy(hdev->scan_rsp_data, cp.data, sizeof(cp.data)); + hdev->scan_rsp_data_len = len; + + cp.handle = 0; + cp.length = len; + cp.operation = LE_SET_ADV_DATA_OP_COMPLETE; + cp.frag_pref = LE_SET_ADV_DATA_NO_FRAG; + + hci_req_add(req, HCI_OP_LE_SET_EXT_SCAN_RSP_DATA, sizeof(cp), + &cp); + } else { + struct hci_cp_le_set_scan_rsp_data cp; + + memset(&cp, 0, sizeof(cp)); + + if (instance) + len = create_instance_scan_rsp_data(hdev, instance, + cp.data); + else + len = create_default_scan_rsp_data(hdev, cp.data); + + if (hdev->scan_rsp_data_len == len && + !memcmp(cp.data, hdev->scan_rsp_data, len)) + return; - memcpy(hdev->scan_rsp_data, cp.data, sizeof(cp.data)); - hdev->scan_rsp_data_len = len; + memcpy(hdev->scan_rsp_data, cp.data, sizeof(cp.data)); + hdev->scan_rsp_data_len = len; - cp.length = len; + cp.length = len; - hci_req_add(req, HCI_OP_LE_SET_SCAN_RSP_DATA, sizeof(cp), &cp); + hci_req_add(req, HCI_OP_LE_SET_SCAN_RSP_DATA, sizeof(cp), &cp); + } } static u8 create_instance_adv_data(struct hci_dev *hdev, u8 instance, u8 *ptr) @@ -1282,27 +1311,51 @@ static u8 create_instance_adv_data(struct hci_dev *hdev, u8 instance, u8 *ptr) void __hci_req_update_adv_data(struct hci_request *req, u8 instance) { struct hci_dev *hdev = req->hdev; - struct hci_cp_le_set_adv_data cp; u8 len; if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED)) return; - memset(&cp, 0, sizeof(cp)); + if (ext_adv_capable(hdev)) { + struct hci_cp_le_set_ext_adv_data cp; - len = create_instance_adv_data(hdev, instance, cp.data); + memset(&cp, 0, sizeof(cp)); - /* There's nothing to do if the data hasn't changed */ - if (hdev->adv_data_len == len && - memcmp(cp.data, hdev->adv_data, len) == 0) - return; + len = create_instance_adv_data(hdev, instance, cp.data); + + /* There's nothing to do if the data hasn't changed */ + if (hdev->adv_data_len == len && + memcmp(cp.data, hdev->adv_data, len) == 0) + return; + + memcpy(hdev->adv_data, cp.data, sizeof(cp.data)); + hdev->adv_data_len = len; + + cp.length = len; + cp.handle = 0; + cp.operation = LE_SET_ADV_DATA_OP_COMPLETE; + cp.frag_pref = LE_SET_ADV_DATA_NO_FRAG; - memcpy(hdev->adv_data, cp.data, sizeof(cp.data)); - hdev->adv_data_len = len; + hci_req_add(req, HCI_OP_LE_SET_EXT_ADV_DATA, sizeof(cp), &cp); + } else { + struct hci_cp_le_set_adv_data cp; + + memset(&cp, 0, sizeof(cp)); - cp.length = len; + len = create_instance_adv_data(hdev, instance, cp.data); + + /* There's nothing to do if the data hasn't changed */ + if (hdev->adv_data_len == len && + memcmp(cp.data, hdev->adv_data, len) == 0) + return; - hci_req_add(req, HCI_OP_LE_SET_ADV_DATA, sizeof(cp), &cp); + memcpy(hdev->adv_data, cp.data, sizeof(cp.data)); + hdev->adv_data_len = len; + + cp.length = len; + + hci_req_add(req, HCI_OP_LE_SET_ADV_DATA, sizeof(cp), &cp); + } } int hci_req_update_adv_data(struct hci_dev *hdev, u8 instance) @@ -1377,8 +1430,7 @@ unlock: hci_dev_unlock(hdev); } -static int __hci_req_setup_ext_adv_instance(struct hci_request *req, - u8 instance) +int __hci_req_setup_ext_adv_instance(struct hci_request *req, u8 instance) { struct hci_cp_le_set_ext_adv_params cp; struct hci_dev *hdev = req->hdev; @@ -1453,6 +1505,7 @@ int __hci_req_start_ext_adv(struct hci_request *req, u8 instance) if (err < 0) return err; + __hci_req_update_scan_rsp_data(req, instance); __hci_req_enable_ext_advertising(req); return 0; @@ -2500,14 +2553,25 @@ static int powered_update_hci(struct hci_request *req, unsigned long opt) */ if (hci_dev_test_flag(hdev, HCI_ADVERTISING) || list_empty(&hdev->adv_instances)) { - __hci_req_update_adv_data(req, 0x00); - __hci_req_update_scan_rsp_data(req, 0x00); + int err; + + if (ext_adv_capable(hdev)) { + err = __hci_req_setup_ext_adv_instance(req, + 0x00); + if (!err) + __hci_req_update_scan_rsp_data(req, + 0x00); + } else { + err = 0; + __hci_req_update_adv_data(req, 0x00); + __hci_req_update_scan_rsp_data(req, 0x00); + } if (hci_dev_test_flag(hdev, HCI_ADVERTISING)) { - if (ext_adv_capable(hdev)) - __hci_req_start_ext_adv(req, 0x00); - else + if (!ext_adv_capable(hdev)) __hci_req_enable_advertising(req); + else if (!err) + __hci_req_enable_ext_advertising(req); } } else if (!list_empty(&hdev->adv_instances)) { struct adv_info *adv_instance; diff --git a/net/bluetooth/hci_request.h b/net/bluetooth/hci_request.h index 9b8c74df6b2b..6afc624605af 100644 --- a/net/bluetooth/hci_request.h +++ b/net/bluetooth/hci_request.h @@ -80,6 +80,7 @@ void hci_req_clear_adv_instance(struct hci_dev *hdev, struct sock *sk, struct hci_request *req, u8 instance, bool force); +int __hci_req_setup_ext_adv_instance(struct hci_request *req, u8 instance); int __hci_req_start_ext_adv(struct hci_request *req, u8 instance); void __hci_req_enable_ext_advertising(struct hci_request *req); diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 761a9aeaa824..142f7e72a9a2 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -1847,10 +1847,17 @@ static void le_enable_complete(struct hci_dev *hdev, u8 status, u16 opcode) */ if (hci_dev_test_flag(hdev, HCI_LE_ENABLED)) { struct hci_request req; - hci_req_init(&req, hdev); - __hci_req_update_adv_data(&req, 0x00); - __hci_req_update_scan_rsp_data(&req, 0x00); + if (ext_adv_capable(hdev)) { + int err; + + err = __hci_req_setup_ext_adv_instance(&req, 0x00); + if (!err) + __hci_req_update_scan_rsp_data(&req, 0x00); + } else { + __hci_req_update_adv_data(&req, 0x00); + __hci_req_update_scan_rsp_data(&req, 0x00); + } hci_req_run(&req, NULL); hci_update_background_scan(hdev); } -- cgit v1.2.3 From 45b7749f16aacd9ffab8e958caa77e2aa2358c0b Mon Sep 17 00:00:00 2001 From: Jaganath Kanakkassery Date: Thu, 19 Jul 2018 17:09:43 +0530 Subject: Bluetooth: Implement disable and removal of adv instance If ext adv is enabled then use ext adv to disable as well. Also remove the adv set during LE disable. < HCI Command: LE Set Extended Advertising Enable (0x08|0x0039) plen 2 Extended advertising: Disabled (0x00) Number of sets: Disable all sets (0x00) > HCI Event: Command Complete (0x0e) plen 4 LE Set Extended Advertising Enable (0x08|0x0039) ncmd 2 Status: Success (0x00) Signed-off-by: Jaganath Kanakkassery Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci.h | 2 ++ net/bluetooth/hci_event.c | 2 ++ net/bluetooth/hci_request.c | 23 +++++++++++++++++++++-- net/bluetooth/hci_request.h | 1 + net/bluetooth/mgmt.c | 3 +++ 5 files changed, 29 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index aace97099ead..faa2922a69fd 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -1647,6 +1647,8 @@ struct hci_cp_le_set_ext_scan_rsp_data { #define LE_SET_ADV_DATA_NO_FRAG 0x01 +#define HCI_OP_LE_CLEAR_ADV_SETS 0x203d + /* ---- HCI Events ---- */ #define HCI_EV_INQUIRY_COMPLETE 0x01 diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 0a92bf7e3d80..a78d1dd2f57b 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -1129,6 +1129,8 @@ static void hci_cc_le_set_ext_adv_enable(struct hci_dev *hdev, queue_delayed_work(hdev->workqueue, &conn->le_conn_timeout, conn->conn_timeout); + } else { + hci_dev_clear_flag(hdev, HCI_LE_ADV); } hci_dev_unlock(hdev); diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index c41e9bb7818b..96e1e05a92c3 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -934,9 +934,19 @@ static u8 get_cur_adv_instance_scan_rsp_len(struct hci_dev *hdev) void __hci_req_disable_advertising(struct hci_request *req) { - u8 enable = 0x00; + if (ext_adv_capable(req->hdev)) { + struct hci_cp_le_set_ext_adv_enable cp; - hci_req_add(req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), &enable); + cp.enable = 0x00; + /* Disable all sets since we only support one set at the moment */ + cp.num_of_sets = 0x00; + + hci_req_add(req, HCI_OP_LE_SET_EXT_ADV_ENABLE, sizeof(cp), &cp); + } else { + u8 enable = 0x00; + + hci_req_add(req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), &enable); + } } static u32 get_adv_instance_flags(struct hci_dev *hdev, u8 instance) @@ -1430,6 +1440,11 @@ unlock: hci_dev_unlock(hdev); } +void __hci_req_clear_ext_adv_sets(struct hci_request *req) +{ + hci_req_add(req, HCI_OP_LE_CLEAR_ADV_SETS, 0, NULL); +} + int __hci_req_setup_ext_adv_instance(struct hci_request *req, u8 instance) { struct hci_cp_le_set_ext_adv_params cp; @@ -1499,8 +1514,12 @@ void __hci_req_enable_ext_advertising(struct hci_request *req) int __hci_req_start_ext_adv(struct hci_request *req, u8 instance) { + struct hci_dev *hdev = req->hdev; int err; + if (hci_dev_test_flag(hdev, HCI_LE_ADV)) + __hci_req_disable_advertising(req); + err = __hci_req_setup_ext_adv_instance(req, instance); if (err < 0) return err; diff --git a/net/bluetooth/hci_request.h b/net/bluetooth/hci_request.h index 6afc624605af..2451861bb4f8 100644 --- a/net/bluetooth/hci_request.h +++ b/net/bluetooth/hci_request.h @@ -83,6 +83,7 @@ void hci_req_clear_adv_instance(struct hci_dev *hdev, struct sock *sk, int __hci_req_setup_ext_adv_instance(struct hci_request *req, u8 instance); int __hci_req_start_ext_adv(struct hci_request *req, u8 instance); void __hci_req_enable_ext_advertising(struct hci_request *req); +void __hci_req_clear_ext_adv_sets(struct hci_request *req); void __hci_req_update_class(struct hci_request *req); diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 142f7e72a9a2..c283f0364c0f 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -1956,6 +1956,9 @@ static int set_le(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) } else { if (hci_dev_test_flag(hdev, HCI_LE_ADV)) __hci_req_disable_advertising(&req); + + if (ext_adv_capable(hdev)) + __hci_req_clear_ext_adv_sets(&req); } hci_req_add(&req, HCI_OP_WRITE_LE_HOST_SUPPORTED, sizeof(hci_cp), -- cgit v1.2.3 From a73c046a2869048430c332a871a5b169f192c6c3 Mon Sep 17 00:00:00 2001 From: Jaganath Kanakkassery Date: Thu, 19 Jul 2018 17:09:45 +0530 Subject: Bluetooth: Implement Set ADV set random address This basically sets the random address for the adv instance Random address can be set only if the instance is created which is done in Set ext adv param. Random address and rpa expire timer and flags have been added to adv instance which will be used when the respective instance is scheduled. This introduces a hci_get_random_address() which returns the own address type and random address (rpa or nrpa) based on the instance flags and hdev flags. New function is required since own address type should be known before setting adv params but address can be set only after setting params. < HCI Command: LE Set Advertising Set Random Address (0x08|0x0035) plen 7 Advertising handle: 0x00 Advertising random address: 3C:8E:56:9B:77:84 (OUI 3C-8E-56) > HCI Event: Command Complete (0x0e) plen 4 LE Set Advertising Set Random Address (0x08|0x0035) ncmd 1 Status: Success (0x00) Signed-off-by: Jaganath Kanakkassery Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci.h | 6 ++ include/net/bluetooth/hci_core.h | 4 ++ net/bluetooth/hci_conn.c | 23 +++++++ net/bluetooth/hci_core.c | 33 +++++++++- net/bluetooth/hci_event.c | 37 ++++++++++- net/bluetooth/hci_request.c | 128 ++++++++++++++++++++++++++++++++++++++- net/bluetooth/hci_request.h | 3 + net/bluetooth/mgmt.c | 2 + 8 files changed, 233 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index faa2922a69fd..8d348d0d3eea 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -1649,6 +1649,12 @@ struct hci_cp_le_set_ext_scan_rsp_data { #define HCI_OP_LE_CLEAR_ADV_SETS 0x203d +#define HCI_OP_LE_SET_ADV_SET_RAND_ADDR 0x2035 +struct hci_cp_le_set_adv_set_rand_addr { + __u8 handle; + bdaddr_t bdaddr; +} __packed; + /* ---- HCI Events ---- */ #define HCI_EV_INQUIRY_COMPLETE 0x01 diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index ad3518303a0c..0db1b9b428b7 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -172,6 +172,9 @@ struct adv_info { __u16 scan_rsp_len; __u8 scan_rsp_data[HCI_MAX_AD_LENGTH]; __s8 tx_power; + bdaddr_t random_addr; + bool rpa_expired; + struct delayed_work rpa_expired_cb; }; #define HCI_MAX_ADV_INSTANCES 5 @@ -1113,6 +1116,7 @@ int hci_add_adv_instance(struct hci_dev *hdev, u8 instance, u32 flags, u16 scan_rsp_len, u8 *scan_rsp_data, u16 timeout, u16 duration); int hci_remove_adv_instance(struct hci_dev *hdev, u8 instance); +void hci_adv_instances_set_rpa_expired(struct hci_dev *hdev, bool rpa_expired); void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb); diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 5c37d383caa3..bd4978ce8c45 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -873,6 +873,14 @@ static void hci_req_directed_advertising(struct hci_request *req, if (ext_adv_capable(hdev)) { struct hci_cp_le_set_ext_adv_params cp; + bdaddr_t random_addr; + + /* Set require_privacy to false so that the remote device has a + * chance of identifying us. + */ + if (hci_get_random_address(hdev, false, conn_use_rpa(conn), NULL, + &own_addr_type, &random_addr) < 0) + return; memset(&cp, 0, sizeof(cp)); @@ -889,6 +897,21 @@ static void hci_req_directed_advertising(struct hci_request *req, hci_req_add(req, HCI_OP_LE_SET_EXT_ADV_PARAMS, sizeof(cp), &cp); + if (own_addr_type == ADDR_LE_DEV_RANDOM && + bacmp(&random_addr, BDADDR_ANY) && + bacmp(&random_addr, &hdev->random_addr)) { + struct hci_cp_le_set_adv_set_rand_addr cp; + + memset(&cp, 0, sizeof(cp)); + + cp.handle = 0; + bacpy(&cp.bdaddr, &random_addr); + + hci_req_add(req, + HCI_OP_LE_SET_ADV_SET_RAND_ADDR, + sizeof(cp), &cp); + } + __hci_req_enable_ext_advertising(req); } else { struct hci_cp_le_set_adv_param cp; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 944d4fedc317..840e8fd89fa5 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1471,6 +1471,7 @@ static int hci_dev_do_open(struct hci_dev *hdev) if (!ret) { hci_dev_hold(hdev); hci_dev_set_flag(hdev, HCI_RPA_EXPIRED); + hci_adv_instances_set_rpa_expired(hdev, true); set_bit(HCI_UP, &hdev->flags); hci_sock_dev_event(hdev, HCI_DEV_UP); hci_leds_update_powered(hdev, true); @@ -1626,9 +1627,15 @@ int hci_dev_do_close(struct hci_dev *hdev) if (hci_dev_test_and_clear_flag(hdev, HCI_SERVICE_CACHE)) cancel_delayed_work(&hdev->service_cache); - if (hci_dev_test_flag(hdev, HCI_MGMT)) + if (hci_dev_test_flag(hdev, HCI_MGMT)) { + struct adv_info *adv_instance; + cancel_delayed_work_sync(&hdev->rpa_expired); + list_for_each_entry(adv_instance, &hdev->adv_instances, list) + cancel_delayed_work_sync(&adv_instance->rpa_expired_cb); + } + /* Avoid potential lockdep warnings from the *_flush() calls by * ensuring the workqueue is empty up front. */ @@ -2704,6 +2711,8 @@ int hci_remove_adv_instance(struct hci_dev *hdev, u8 instance) hdev->cur_adv_instance = 0x00; } + cancel_delayed_work_sync(&adv_instance->rpa_expired_cb); + list_del(&adv_instance->list); kfree(adv_instance); @@ -2712,6 +2721,14 @@ int hci_remove_adv_instance(struct hci_dev *hdev, u8 instance) return 0; } +void hci_adv_instances_set_rpa_expired(struct hci_dev *hdev, bool rpa_expired) +{ + struct adv_info *adv_instance, *n; + + list_for_each_entry_safe(adv_instance, n, &hdev->adv_instances, list) + adv_instance->rpa_expired = rpa_expired; +} + /* This function requires the caller holds hdev->lock */ void hci_adv_instances_clear(struct hci_dev *hdev) { @@ -2723,6 +2740,7 @@ void hci_adv_instances_clear(struct hci_dev *hdev) } list_for_each_entry_safe(adv_instance, n, &hdev->adv_instances, list) { + cancel_delayed_work_sync(&adv_instance->rpa_expired_cb); list_del(&adv_instance->list); kfree(adv_instance); } @@ -2731,6 +2749,16 @@ void hci_adv_instances_clear(struct hci_dev *hdev) hdev->cur_adv_instance = 0x00; } +static void adv_instance_rpa_expired(struct work_struct *work) +{ + struct adv_info *adv_instance = container_of(work, struct adv_info, + rpa_expired_cb.work); + + BT_DBG(""); + + adv_instance->rpa_expired = true; +} + /* This function requires the caller holds hdev->lock */ int hci_add_adv_instance(struct hci_dev *hdev, u8 instance, u32 flags, u16 adv_data_len, u8 *adv_data, @@ -2781,6 +2809,9 @@ int hci_add_adv_instance(struct hci_dev *hdev, u8 instance, u32 flags, adv_instance->tx_power = HCI_TX_POWER_INVALID; + INIT_DELAYED_WORK(&adv_instance->rpa_expired_cb, + adv_instance_rpa_expired); + BT_DBG("%s for %dMR", hdev->name, instance); return 0; diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index a78d1dd2f57b..392c9d8febd0 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -1064,6 +1064,35 @@ static void hci_cc_le_set_default_phy(struct hci_dev *hdev, struct sk_buff *skb) hci_dev_unlock(hdev); } +static void hci_cc_le_set_adv_set_random_addr(struct hci_dev *hdev, + struct sk_buff *skb) +{ + __u8 status = *((__u8 *) skb->data); + struct hci_cp_le_set_adv_set_rand_addr *cp; + struct adv_info *adv_instance; + + if (status) + return; + + cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_ADV_SET_RAND_ADDR); + if (!cp) + return; + + hci_dev_lock(hdev); + + if (!hdev->cur_adv_instance) { + /* Store in hdev for instance 0 (Set adv and Directed advs) */ + bacpy(&hdev->random_addr, &cp->bdaddr); + } else { + adv_instance = hci_find_adv_instance(hdev, + hdev->cur_adv_instance); + if (adv_instance) + bacpy(&adv_instance->random_addr, &cp->bdaddr); + } + + hci_dev_unlock(hdev); +} + static void hci_cc_le_set_adv_enable(struct hci_dev *hdev, struct sk_buff *skb) { __u8 *sent, status = *((__u8 *) skb->data); @@ -2830,8 +2859,10 @@ static void hci_encrypt_change_evt(struct hci_dev *hdev, struct sk_buff *skb) /* We should disregard the current RPA and generate a new one * whenever the encryption procedure fails. */ - if (ev->status && conn->type == LE_LINK) + if (ev->status && conn->type == LE_LINK) { hci_dev_set_flag(hdev, HCI_RPA_EXPIRED); + hci_adv_instances_set_rpa_expired(hdev, true); + } clear_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags); @@ -3283,6 +3314,10 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb, hci_cc_le_set_ext_adv_enable(hdev, skb); break; + case HCI_OP_LE_SET_ADV_SET_RAND_ADDR: + hci_cc_le_set_adv_set_random_addr(hdev, skb); + break; + default: BT_DBG("%s opcode 0x%4.4x", hdev->name, *opcode); break; diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index 96e1e05a92c3..c72fd9202666 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -1440,6 +1440,87 @@ unlock: hci_dev_unlock(hdev); } +int hci_get_random_address(struct hci_dev *hdev, bool require_privacy, + bool use_rpa, struct adv_info *adv_instance, + u8 *own_addr_type, bdaddr_t *rand_addr) +{ + int err; + + bacpy(rand_addr, BDADDR_ANY); + + /* If privacy is enabled use a resolvable private address. If + * current RPA has expired then generate a new one. + */ + if (use_rpa) { + int to; + + *own_addr_type = ADDR_LE_DEV_RANDOM; + + if (adv_instance) { + if (!adv_instance->rpa_expired && + !bacmp(&adv_instance->random_addr, &hdev->rpa)) + return 0; + + adv_instance->rpa_expired = false; + } else { + if (!hci_dev_test_and_clear_flag(hdev, HCI_RPA_EXPIRED) && + !bacmp(&hdev->random_addr, &hdev->rpa)) + return 0; + } + + err = smp_generate_rpa(hdev, hdev->irk, &hdev->rpa); + if (err < 0) { + BT_ERR("%s failed to generate new RPA", hdev->name); + return err; + } + + bacpy(rand_addr, &hdev->rpa); + + to = msecs_to_jiffies(hdev->rpa_timeout * 1000); + if (adv_instance) + queue_delayed_work(hdev->workqueue, + &adv_instance->rpa_expired_cb, to); + else + queue_delayed_work(hdev->workqueue, + &hdev->rpa_expired, to); + + return 0; + } + + /* In case of required privacy without resolvable private address, + * use an non-resolvable private address. This is useful for + * non-connectable advertising. + */ + if (require_privacy) { + bdaddr_t nrpa; + + while (true) { + /* The non-resolvable private address is generated + * from random six bytes with the two most significant + * bits cleared. + */ + get_random_bytes(&nrpa, 6); + nrpa.b[5] &= 0x3f; + + /* The non-resolvable private address shall not be + * equal to the public address. + */ + if (bacmp(&hdev->bdaddr, &nrpa)) + break; + } + + *own_addr_type = ADDR_LE_DEV_RANDOM; + bacpy(rand_addr, &nrpa); + + return 0; + } + + /* No privacy so use a public address. */ + *own_addr_type = ADDR_LE_DEV_PUBLIC; + + return 0; +} + void __hci_req_clear_ext_adv_sets(struct hci_request *req) { hci_req_add(req, HCI_OP_LE_CLEAR_ADV_SETS, 0, NULL); @@ -1451,9 +1532,21 @@ int __hci_req_setup_ext_adv_instance(struct hci_request *req, u8 instance) struct hci_dev *hdev = req->hdev; bool connectable; u32 flags; + bdaddr_t random_addr; + u8 own_addr_type; + int err; + struct adv_info *adv_instance; /* In ext adv set param interval is 3 octets */ const u8 adv_interval[3] = { 0x00, 0x08, 0x00 }; + if (instance > 0) { + adv_instance = hci_find_adv_instance(hdev, instance); + if (!adv_instance) + return -EINVAL; + } else { + adv_instance = NULL; + } + flags = get_adv_instance_flags(hdev, instance); /* If the "connectable" instance flag was not set, then choose between @@ -1465,6 +1558,16 @@ int __hci_req_setup_ext_adv_instance(struct hci_request *req, u8 instance) if (!is_advertising_allowed(hdev, connectable)) return -EPERM; + /* Set require_privacy to true only when non-connectable + * advertising is used. In that case it is fine to use a + * non-resolvable private address. + */ + err = hci_get_random_address(hdev, !connectable, + adv_use_rpa(hdev, flags), adv_instance, + &own_addr_type, &random_addr); + if (err < 0) + return err; + memset(&cp, 0, sizeof(cp)); memcpy(cp.min_interval, adv_interval, sizeof(cp.min_interval)); @@ -1477,7 +1580,7 @@ int __hci_req_setup_ext_adv_instance(struct hci_request *req, u8 instance) else cp.evt_properties = cpu_to_le16(LE_LEGACY_NONCONN_IND); - cp.own_addr_type = BDADDR_LE_PUBLIC; + cp.own_addr_type = own_addr_type; cp.channel_map = hdev->le_adv_channel_map; cp.tx_power = 127; cp.primary_phy = HCI_ADV_PHY_1M; @@ -1486,6 +1589,29 @@ int __hci_req_setup_ext_adv_instance(struct hci_request *req, u8 instance) hci_req_add(req, HCI_OP_LE_SET_EXT_ADV_PARAMS, sizeof(cp), &cp); + if (own_addr_type == ADDR_LE_DEV_RANDOM && + bacmp(&random_addr, BDADDR_ANY)) { + struct hci_cp_le_set_adv_set_rand_addr cp; + + /* Check if random address need to be updated */ + if (adv_instance) { + if (!bacmp(&random_addr, &adv_instance->random_addr)) + return 0; + } else { + if (!bacmp(&random_addr, &hdev->random_addr)) + return 0; + } + + memset(&cp, 0, sizeof(cp)); + + cp.handle = 0; + bacpy(&cp.bdaddr, &random_addr); + + hci_req_add(req, + HCI_OP_LE_SET_ADV_SET_RAND_ADDR, + sizeof(cp), &cp); + } + return 0; } diff --git a/net/bluetooth/hci_request.h b/net/bluetooth/hci_request.h index 2451861bb4f8..692cc8b13368 100644 --- a/net/bluetooth/hci_request.h +++ b/net/bluetooth/hci_request.h @@ -84,6 +84,9 @@ int __hci_req_setup_ext_adv_instance(struct hci_request *req, u8 instance); int __hci_req_start_ext_adv(struct hci_request *req, u8 instance); void __hci_req_enable_ext_advertising(struct hci_request *req); void __hci_req_clear_ext_adv_sets(struct hci_request *req); +int hci_get_random_address(struct hci_dev *hdev, bool require_privacy, + bool use_rpa, struct adv_info *adv_instance, + u8 *own_addr_type, bdaddr_t *rand_addr); void __hci_req_update_class(struct hci_request *req); diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index c283f0364c0f..949986727019 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -4972,6 +4972,7 @@ static int set_privacy(struct sock *sk, struct hci_dev *hdev, void *cp_data, changed = !hci_dev_test_and_set_flag(hdev, HCI_PRIVACY); memcpy(hdev->irk, cp->irk, sizeof(hdev->irk)); hci_dev_set_flag(hdev, HCI_RPA_EXPIRED); + hci_adv_instances_set_rpa_expired(hdev, true); if (cp->privacy == 0x02) hci_dev_set_flag(hdev, HCI_LIMITED_PRIVACY); else @@ -4980,6 +4981,7 @@ static int set_privacy(struct sock *sk, struct hci_dev *hdev, void *cp_data, changed = hci_dev_test_and_clear_flag(hdev, HCI_PRIVACY); memset(hdev->irk, 0, sizeof(hdev->irk)); hci_dev_clear_flag(hdev, HCI_RPA_EXPIRED); + hci_adv_instances_set_rpa_expired(hdev, false); hci_dev_clear_flag(hdev, HCI_LIMITED_PRIVACY); } -- cgit v1.2.3 From acf0aeae431a0f1723385cd1cb50177e4cc10edd Mon Sep 17 00:00:00 2001 From: Jaganath Kanakkassery Date: Thu, 19 Jul 2018 17:09:46 +0530 Subject: Bluetooth: Handle ADv set terminated event This event comes after connection complete event for incoming connections. Since we now have different random address for each instance, conn resp address is assigned from this event. As of now only connection part is handled as we are not enabling duration or max num of events while starting ext adv. Signed-off-by: Jaganath Kanakkassery Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci.h | 8 ++++++++ net/bluetooth/hci_core.c | 8 ++++++++ net/bluetooth/hci_event.c | 43 ++++++++++++++++++++++++++++++++++++++++--- 3 files changed, 56 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 8d348d0d3eea..57e3e3675d66 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -2155,6 +2155,14 @@ struct hci_ev_le_enh_conn_complete { __u8 clk_accurancy; } __packed; +#define HCI_EV_LE_EXT_ADV_SET_TERM 0x12 +struct hci_evt_le_ext_adv_set_term { + __u8 status; + __u8 handle; + __le16 conn_handle; + __u8 num_evts; +} __packed; + /* Internal events generated by Bluetooth stack */ #define HCI_EV_STACK_INTERNAL 0xfd struct hci_ev_stack_internal { diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 840e8fd89fa5..79e02d24a215 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -712,6 +712,14 @@ static int hci_init3_req(struct hci_request *req, unsigned long opt) * Complete */ + /* If the controller supports the LE Extended Advertising + * command, enable the corresponding event. + */ + if (ext_adv_capable(hdev)) + events[2] |= 0x02; /* LE Advertising Set + * Terminated + */ + hci_req_add(req, HCI_OP_LE_SET_EVENT_MASK, sizeof(events), events); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 392c9d8febd0..754714c8d752 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -4798,10 +4798,15 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, * the advertising address type. */ conn->resp_addr_type = hdev->adv_addr_type; - if (hdev->adv_addr_type == ADDR_LE_DEV_RANDOM) - bacpy(&conn->resp_addr, &hdev->random_addr); - else + if (hdev->adv_addr_type == ADDR_LE_DEV_RANDOM) { + /* In case of ext adv, resp_addr will be updated in + * Adv Terminated event. + */ + if (!ext_adv_capable(hdev)) + bacpy(&conn->resp_addr, &hdev->random_addr); + } else { bacpy(&conn->resp_addr, &hdev->bdaddr); + } conn->init_addr_type = bdaddr_type; bacpy(&conn->init_addr, bdaddr); @@ -4931,6 +4936,34 @@ static void hci_le_enh_conn_complete_evt(struct hci_dev *hdev, le16_to_cpu(ev->supervision_timeout)); } +static void hci_le_ext_adv_term_evt(struct hci_dev *hdev, struct sk_buff *skb) +{ + struct hci_evt_le_ext_adv_set_term *ev = (void *) skb->data; + struct hci_conn *conn; + + BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); + + if (ev->status) + return; + + conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(ev->conn_handle)); + if (conn) { + struct adv_info *adv_instance; + + if (hdev->adv_addr_type != ADDR_LE_DEV_RANDOM) + return; + + if (!hdev->cur_adv_instance) { + bacpy(&conn->resp_addr, &hdev->random_addr); + return; + } + + adv_instance = hci_find_adv_instance(hdev, hdev->cur_adv_instance); + if (adv_instance) + bacpy(&conn->resp_addr, &adv_instance->random_addr); + } +} + static void hci_le_conn_update_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) { @@ -5578,6 +5611,10 @@ static void hci_le_meta_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_le_enh_conn_complete_evt(hdev, skb); break; + case HCI_EV_LE_EXT_ADV_SET_TERM: + hci_le_ext_adv_term_evt(hdev, skb); + break; + default: break; } -- cgit v1.2.3 From 85a721a8b0b6880d8cf6b9def70404ade8563225 Mon Sep 17 00:00:00 2001 From: Jaganath Kanakkassery Date: Thu, 19 Jul 2018 17:09:47 +0530 Subject: Bluetooth: Implement secondary advertising on different PHYs This patch adds support for advertising in primary and secondary channel on different PHYs. User can add the phy preference in the flag based on which phy type will be added in extended advertising parameter would be set. @ MGMT Command: Add Advertising (0x003e) plen 11 Instance: 1 Flags: 0x00000200 Advertise in CODED on Secondary channel Duration: 0 Timeout: 0 Advertising data length: 0 Scan response length: 0 < HCI Command: LE Set Extended Advertising Enable (0x08|0x0039) plen 2 Extended advertising: Disabled (0x00) Number of sets: Disable all sets (0x00) > HCI Event: Command Complete (0x0e) plen 4 LE Set Extended Advertising Enable (0x08|0x0039) ncmd 2 Status: Success (0x00) < HCI Command: LE Set Extended Advertising Parameters (0x08|0x0036) plen 25 Handle: 0x00 Properties: 0x0000 Min advertising interval: 1280.000 msec (0x0800) Max advertising interval: 1280.000 msec (0x0800) Channel map: 37, 38, 39 (0x07) Own address type: Random (0x01) Peer address type: Public (0x00) Peer address: 00:00:00:00:00:00 (OUI 00-00-00) Filter policy: Allow Scan Request from Any, Allow Connect Request from Any (0x00) TX power: 127 dbm (0x7f) Primary PHY: LE Coded (0x03) Secondary max skip: 0x00 Secondary PHY: LE Coded (0x03) SID: 0x00 Scan request notifications: Disabled (0x00) Signed-off-by: Jaganath Kanakkassery Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci.h | 4 ++++ include/net/bluetooth/mgmt.h | 6 ++++++ net/bluetooth/hci_request.c | 39 +++++++++++++++++++++++++++++++-------- net/bluetooth/mgmt.c | 18 +++++++++++++++--- 4 files changed, 56 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 57e3e3675d66..8ff36463719f 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -410,6 +410,8 @@ enum { #define HCI_LE_SLAVE_FEATURES 0x08 #define HCI_LE_PING 0x10 #define HCI_LE_DATA_LEN_EXT 0x20 +#define HCI_LE_PHY_2M 0x01 +#define HCI_LE_PHY_CODED 0x08 #define HCI_LE_EXT_ADV 0x10 #define HCI_LE_EXT_SCAN_POLICY 0x80 #define HCI_LE_PHY_2M 0x01 @@ -1606,6 +1608,8 @@ struct hci_cp_le_set_ext_adv_params { } __packed; #define HCI_ADV_PHY_1M 0X01 +#define HCI_ADV_PHY_2M 0x02 +#define HCI_ADV_PHY_CODED 0x03 struct hci_rp_le_set_ext_adv_params { __u8 status; diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index 7f372e9067c9..9cee7ddc6741 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -562,6 +562,12 @@ struct mgmt_rp_add_advertising { #define MGMT_ADV_FLAG_TX_POWER BIT(4) #define MGMT_ADV_FLAG_APPEARANCE BIT(5) #define MGMT_ADV_FLAG_LOCAL_NAME BIT(6) +#define MGMT_ADV_FLAG_SEC_1M BIT(7) +#define MGMT_ADV_FLAG_SEC_2M BIT(8) +#define MGMT_ADV_FLAG_SEC_CODED BIT(9) + +#define MGMT_ADV_FLAG_SEC_MASK (MGMT_ADV_FLAG_SEC_1M | MGMT_ADV_FLAG_SEC_2M | \ + MGMT_ADV_FLAG_SEC_CODED) #define MGMT_OP_REMOVE_ADVERTISING 0x003F struct mgmt_cp_remove_advertising { diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index c72fd9202666..e8c9ef1e1922 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -1536,6 +1536,7 @@ int __hci_req_setup_ext_adv_instance(struct hci_request *req, u8 instance) u8 own_addr_type; int err; struct adv_info *adv_instance; + bool secondary_adv; /* In ext adv set param interval is 3 octets */ const u8 adv_interval[3] = { 0x00, 0x08, 0x00 }; @@ -1573,20 +1574,42 @@ int __hci_req_setup_ext_adv_instance(struct hci_request *req, u8 instance) memcpy(cp.min_interval, adv_interval, sizeof(cp.min_interval)); memcpy(cp.max_interval, adv_interval, sizeof(cp.max_interval)); - if (connectable) - cp.evt_properties = cpu_to_le16(LE_LEGACY_ADV_IND); - else if (get_adv_instance_scan_rsp_len(hdev, instance)) - cp.evt_properties = cpu_to_le16(LE_LEGACY_ADV_SCAN_IND); - else - cp.evt_properties = cpu_to_le16(LE_LEGACY_NONCONN_IND); + secondary_adv = (flags & MGMT_ADV_FLAG_SEC_MASK); + + if (connectable) { + if (secondary_adv) + cp.evt_properties = cpu_to_le16(LE_EXT_ADV_CONN_IND); + else + cp.evt_properties = cpu_to_le16(LE_LEGACY_ADV_IND); + } else if (get_adv_instance_scan_rsp_len(hdev, instance)) { + if (secondary_adv) + cp.evt_properties = cpu_to_le16(LE_EXT_ADV_SCAN_IND); + else + cp.evt_properties = cpu_to_le16(LE_LEGACY_ADV_SCAN_IND); + } else { + if (secondary_adv) + cp.evt_properties = cpu_to_le16(LE_EXT_ADV_NON_CONN_IND); + else + cp.evt_properties = cpu_to_le16(LE_LEGACY_NONCONN_IND); + } cp.own_addr_type = own_addr_type; cp.channel_map = hdev->le_adv_channel_map; cp.tx_power = 127; - cp.primary_phy = HCI_ADV_PHY_1M; - cp.secondary_phy = HCI_ADV_PHY_1M; cp.handle = 0; + if (flags & MGMT_ADV_FLAG_SEC_2M) { + cp.primary_phy = HCI_ADV_PHY_1M; + cp.secondary_phy = HCI_ADV_PHY_2M; + } else if (flags & MGMT_ADV_FLAG_SEC_CODED) { + cp.primary_phy = HCI_ADV_PHY_CODED; + cp.secondary_phy = HCI_ADV_PHY_CODED; + } else { + /* In all other cases use 1M */ + cp.primary_phy = HCI_ADV_PHY_1M; + cp.secondary_phy = HCI_ADV_PHY_1M; + } + hci_req_add(req, HCI_OP_LE_SET_EXT_ADV_PARAMS, sizeof(cp), &cp); if (own_addr_type == ADDR_LE_DEV_RANDOM && diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 949986727019..231602f7cb66 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -6339,6 +6339,16 @@ static u32 get_supported_adv_flags(struct hci_dev *hdev) ext_adv_capable(hdev)) flags |= MGMT_ADV_FLAG_TX_POWER; + if (ext_adv_capable(hdev)) { + flags |= MGMT_ADV_FLAG_SEC_1M; + + if (hdev->le_features[1] & HCI_LE_PHY_2M) + flags |= MGMT_ADV_FLAG_SEC_2M; + + if (hdev->le_features[1] & HCI_LE_PHY_CODED) + flags |= MGMT_ADV_FLAG_SEC_CODED; + } + return flags; } @@ -6544,7 +6554,7 @@ static int add_advertising(struct sock *sk, struct hci_dev *hdev, struct mgmt_cp_add_advertising *cp = data; struct mgmt_rp_add_advertising rp; u32 flags; - u32 supported_flags; + u32 supported_flags, phy_flags; u8 status; u16 timeout, duration; unsigned int prev_instance_cnt = hdev->adv_instance_cnt; @@ -6574,10 +6584,12 @@ static int add_advertising(struct sock *sk, struct hci_dev *hdev, duration = __le16_to_cpu(cp->duration); /* The current implementation only supports a subset of the specified - * flags. + * flags. Also need to check mutual exclusiveness of sec flags. */ supported_flags = get_supported_adv_flags(hdev); - if (flags & ~supported_flags) + phy_flags = flags & MGMT_ADV_FLAG_SEC_MASK; + if (flags & ~supported_flags || + ((phy_flags && (phy_flags ^ (phy_flags & -phy_flags))))) return mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_ADVERTISING, MGMT_STATUS_INVALID_PARAMS); -- cgit v1.2.3 From 740011cfe94859df8d05f5400d589a8693b095e7 Mon Sep 17 00:00:00 2001 From: Sean Wang Date: Fri, 20 Jul 2018 13:12:28 +0800 Subject: Bluetooth: Add new quirk for non-persistent setup settings Add a new quirk HCI_QUIRK_NON_PERSISTENT_SETUP allowing that a quirk that runs setup() after every open() and not just after the first open(). Signed-off-by: Sean Wang Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci.h | 9 +++++++++ net/bluetooth/hci_core.c | 3 ++- 2 files changed, 11 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 8ff36463719f..7f008097552e 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -183,6 +183,15 @@ enum { * during the hdev->setup vendor callback. */ HCI_QUIRK_NON_PERSISTENT_DIAG, + + /* When this quirk is set, setup() would be run after every + * open() and not just after the first open(). + * + * This quirk can be set before hci_register_dev is called or + * during the hdev->setup vendor callback. + * + */ + HCI_QUIRK_NON_PERSISTENT_SETUP, }; /* HCI device flags */ diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 79e02d24a215..74b29c7d841c 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1415,7 +1415,8 @@ static int hci_dev_do_open(struct hci_dev *hdev) atomic_set(&hdev->cmd_cnt, 1); set_bit(HCI_INIT, &hdev->flags); - if (hci_dev_test_flag(hdev, HCI_SETUP)) { + if (hci_dev_test_flag(hdev, HCI_SETUP) || + test_bit(HCI_QUIRK_NON_PERSISTENT_SETUP, &hdev->quirks)) { hci_sock_dev_event(hdev, HCI_DEV_SETUP); if (hdev->setup) -- cgit v1.2.3 From 51c23b47e6b8590ea7a6a6776ffb21810ece73bf Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 13 Jul 2018 14:54:45 +0200 Subject: netfilter: nf_osf: add nf_osf_find() This new function returns the OS genre as a string. Plan is to use to from the new nft_osf extension. Note that this doesn't yet support ttl options, but it could be easily extended to do so. Tested-by: Fernando Fernandez Mancera Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nf_osf.h | 9 +++++++++ net/netfilter/nf_osf.c | 30 ++++++++++++++++++++++++++++++ 2 files changed, 39 insertions(+) (limited to 'include') diff --git a/include/linux/netfilter/nf_osf.h b/include/linux/netfilter/nf_osf.h index 0e114c492fb8..aee460fcbd31 100644 --- a/include/linux/netfilter/nf_osf.h +++ b/include/linux/netfilter/nf_osf.h @@ -1,3 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _NFOSF_H +#define _NFOSF_H + #include /* Initial window size option state machine: multiple of mss, mtu or @@ -31,3 +35,8 @@ bool nf_osf_match(const struct sk_buff *skb, u_int8_t family, int hooknum, struct net_device *in, struct net_device *out, const struct nf_osf_info *info, struct net *net, const struct list_head *nf_osf_fingers); + +const char *nf_osf_find(const struct sk_buff *skb, + const struct list_head *nf_osf_fingers); + +#endif /* _NFOSF_H */ diff --git a/net/netfilter/nf_osf.c b/net/netfilter/nf_osf.c index b44d62d5d9a9..f4c75e982902 100644 --- a/net/netfilter/nf_osf.c +++ b/net/netfilter/nf_osf.c @@ -249,4 +249,34 @@ nf_osf_match(const struct sk_buff *skb, u_int8_t family, } EXPORT_SYMBOL_GPL(nf_osf_match); +const char *nf_osf_find(const struct sk_buff *skb, + const struct list_head *nf_osf_fingers) +{ + const struct iphdr *ip = ip_hdr(skb); + const struct nf_osf_user_finger *f; + unsigned char opts[MAX_IPOPTLEN]; + const struct nf_osf_finger *kf; + struct nf_osf_hdr_ctx ctx; + const struct tcphdr *tcp; + const char *genre = NULL; + + memset(&ctx, 0, sizeof(ctx)); + + tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts); + if (!tcp) + return false; + + list_for_each_entry_rcu(kf, &nf_osf_fingers[ctx.df], finger_entry) { + f = &kf->finger; + if (!nf_osf_match_one(skb, f, -1, &ctx)) + continue; + + genre = f->genre; + break; + } + + return genre; +} +EXPORT_SYMBOL_GPL(nf_osf_find); + MODULE_LICENSE("GPL"); -- cgit v1.2.3 From f9324952088f1cd62ea4addf9ff532f1e6452a22 Mon Sep 17 00:00:00 2001 From: Fernando Fernandez Mancera Date: Wed, 25 Jul 2018 01:32:45 +0200 Subject: netfilter: nfnetlink_osf: extract nfnetlink_subsystem code from xt_osf.c Move nfnetlink osf subsystem from xt_osf.c to standalone module so we can reuse it from the new nft_ost extension. Signed-off-by: Fernando Fernandez Mancera Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_osf.h | 11 +++ include/uapi/linux/netfilter/xt_osf.h | 9 +- net/netfilter/nfnetlink_osf.c | 154 ++++++++++++++++++++++++++++++++++ net/netfilter/xt_osf.c | 149 +------------------------------- 4 files changed, 169 insertions(+), 154 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/netfilter/nf_osf.h b/include/uapi/linux/netfilter/nf_osf.h index 3738116b2bbe..cc2487ff74f6 100644 --- a/include/uapi/linux/netfilter/nf_osf.h +++ b/include/uapi/linux/netfilter/nf_osf.h @@ -70,6 +70,8 @@ struct nf_osf_nlmsg { struct tcphdr tcp; }; +extern struct list_head nf_osf_fingers[2]; + /* Defines for IANA option kinds */ enum iana_options { OSFOPT_EOL = 0, /* End of options */ @@ -94,4 +96,13 @@ enum nf_osf_attr_type { OSF_ATTR_MAX, }; +/* + * Add/remove fingerprint from the kernel. + */ +enum nf_osf_msg_types { + OSF_MSG_ADD, + OSF_MSG_REMOVE, + OSF_MSG_MAX, +}; + #endif /* _NF_OSF_H */ diff --git a/include/uapi/linux/netfilter/xt_osf.h b/include/uapi/linux/netfilter/xt_osf.h index b189007f4f28..a90e90c27cef 100644 --- a/include/uapi/linux/netfilter/xt_osf.h +++ b/include/uapi/linux/netfilter/xt_osf.h @@ -47,13 +47,6 @@ #define xt_osf_nlmsg nf_osf_nlmsg #define xt_osf_attr_type nf_osf_attr_type -/* - * Add/remove fingerprint from the kernel. - */ -enum xt_osf_msg_types { - OSF_MSG_ADD, - OSF_MSG_REMOVE, - OSF_MSG_MAX, -}; +#define xt_osf_msg_types nf_osf_msg_types #endif /* _XT_OSF_H */ diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c index f4c75e982902..ba0fa11869ce 100644 --- a/net/netfilter/nfnetlink_osf.c +++ b/net/netfilter/nfnetlink_osf.c @@ -20,6 +20,13 @@ #include #include +/* + * Indexed by dont-fragment bit. + * It is the only constant value in the fingerprint. + */ +struct list_head nf_osf_fingers[2]; +EXPORT_SYMBOL_GPL(nf_osf_fingers); + static inline int nf_osf_ttl(const struct sk_buff *skb, int ttl_check, unsigned char f_ttl) { @@ -279,4 +286,151 @@ const char *nf_osf_find(const struct sk_buff *skb, } EXPORT_SYMBOL_GPL(nf_osf_find); +static const struct nla_policy nfnl_osf_policy[OSF_ATTR_MAX + 1] = { + [OSF_ATTR_FINGER] = { .len = sizeof(struct nf_osf_user_finger) }, +}; + +static int nfnl_osf_add_callback(struct net *net, struct sock *ctnl, + struct sk_buff *skb, const struct nlmsghdr *nlh, + const struct nlattr * const osf_attrs[], + struct netlink_ext_ack *extack) +{ + struct nf_osf_user_finger *f; + struct nf_osf_finger *kf = NULL, *sf; + int err = 0; + + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + if (!osf_attrs[OSF_ATTR_FINGER]) + return -EINVAL; + + if (!(nlh->nlmsg_flags & NLM_F_CREATE)) + return -EINVAL; + + f = nla_data(osf_attrs[OSF_ATTR_FINGER]); + + kf = kmalloc(sizeof(struct nf_osf_finger), GFP_KERNEL); + if (!kf) + return -ENOMEM; + + memcpy(&kf->finger, f, sizeof(struct nf_osf_user_finger)); + + list_for_each_entry(sf, &nf_osf_fingers[!!f->df], finger_entry) { + if (memcmp(&sf->finger, f, sizeof(struct nf_osf_user_finger))) + continue; + + kfree(kf); + kf = NULL; + + if (nlh->nlmsg_flags & NLM_F_EXCL) + err = -EEXIST; + break; + } + + /* + * We are protected by nfnl mutex. + */ + if (kf) + list_add_tail_rcu(&kf->finger_entry, &nf_osf_fingers[!!f->df]); + + return err; +} + +static int nfnl_osf_remove_callback(struct net *net, struct sock *ctnl, + struct sk_buff *skb, + const struct nlmsghdr *nlh, + const struct nlattr * const osf_attrs[], + struct netlink_ext_ack *extack) +{ + struct nf_osf_user_finger *f; + struct nf_osf_finger *sf; + int err = -ENOENT; + + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + if (!osf_attrs[OSF_ATTR_FINGER]) + return -EINVAL; + + f = nla_data(osf_attrs[OSF_ATTR_FINGER]); + + list_for_each_entry(sf, &nf_osf_fingers[!!f->df], finger_entry) { + if (memcmp(&sf->finger, f, sizeof(struct nf_osf_user_finger))) + continue; + + /* + * We are protected by nfnl mutex. + */ + list_del_rcu(&sf->finger_entry); + kfree_rcu(sf, rcu_head); + + err = 0; + break; + } + + return err; +} + +static const struct nfnl_callback nfnl_osf_callbacks[OSF_MSG_MAX] = { + [OSF_MSG_ADD] = { + .call = nfnl_osf_add_callback, + .attr_count = OSF_ATTR_MAX, + .policy = nfnl_osf_policy, + }, + [OSF_MSG_REMOVE] = { + .call = nfnl_osf_remove_callback, + .attr_count = OSF_ATTR_MAX, + .policy = nfnl_osf_policy, + }, +}; + +static const struct nfnetlink_subsystem nfnl_osf_subsys = { + .name = "osf", + .subsys_id = NFNL_SUBSYS_OSF, + .cb_count = OSF_MSG_MAX, + .cb = nfnl_osf_callbacks, +}; + +static int __init nfnl_osf_init(void) +{ + int err = -EINVAL; + int i; + + for (i = 0; i < ARRAY_SIZE(nf_osf_fingers); ++i) + INIT_LIST_HEAD(&nf_osf_fingers[i]); + + err = nfnetlink_subsys_register(&nfnl_osf_subsys); + if (err < 0) { + pr_err("Failed to register OSF nsfnetlink helper (%d)\n", err); + goto err_out_exit; + } + return 0; + +err_out_exit: + return err; +} + +static void __exit nfnl_osf_fini(void) +{ + struct nf_osf_finger *f; + int i; + + nfnetlink_subsys_unregister(&nfnl_osf_subsys); + + rcu_read_lock(); + for (i = 0; i < ARRAY_SIZE(nf_osf_fingers); ++i) { + list_for_each_entry_rcu(f, &nf_osf_fingers[i], finger_entry) { + list_del_rcu(&f->finger_entry); + kfree_rcu(f, rcu_head); + } + } + rcu_read_unlock(); + + rcu_barrier(); +} + +module_init(nfnl_osf_init); +module_exit(nfnl_osf_fini); + MODULE_LICENSE("GPL"); diff --git a/net/netfilter/xt_osf.c b/net/netfilter/xt_osf.c index 9cfef73b4107..bf7bba80e24c 100644 --- a/net/netfilter/xt_osf.c +++ b/net/netfilter/xt_osf.c @@ -37,118 +37,6 @@ #include #include -/* - * Indexed by dont-fragment bit. - * It is the only constant value in the fingerprint. - */ -static struct list_head xt_osf_fingers[2]; - -static const struct nla_policy xt_osf_policy[OSF_ATTR_MAX + 1] = { - [OSF_ATTR_FINGER] = { .len = sizeof(struct xt_osf_user_finger) }, -}; - -static int xt_osf_add_callback(struct net *net, struct sock *ctnl, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const osf_attrs[], - struct netlink_ext_ack *extack) -{ - struct xt_osf_user_finger *f; - struct xt_osf_finger *kf = NULL, *sf; - int err = 0; - - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - - if (!osf_attrs[OSF_ATTR_FINGER]) - return -EINVAL; - - if (!(nlh->nlmsg_flags & NLM_F_CREATE)) - return -EINVAL; - - f = nla_data(osf_attrs[OSF_ATTR_FINGER]); - - kf = kmalloc(sizeof(struct xt_osf_finger), GFP_KERNEL); - if (!kf) - return -ENOMEM; - - memcpy(&kf->finger, f, sizeof(struct xt_osf_user_finger)); - - list_for_each_entry(sf, &xt_osf_fingers[!!f->df], finger_entry) { - if (memcmp(&sf->finger, f, sizeof(struct xt_osf_user_finger))) - continue; - - kfree(kf); - kf = NULL; - - if (nlh->nlmsg_flags & NLM_F_EXCL) - err = -EEXIST; - break; - } - - /* - * We are protected by nfnl mutex. - */ - if (kf) - list_add_tail_rcu(&kf->finger_entry, &xt_osf_fingers[!!f->df]); - - return err; -} - -static int xt_osf_remove_callback(struct net *net, struct sock *ctnl, - struct sk_buff *skb, - const struct nlmsghdr *nlh, - const struct nlattr * const osf_attrs[], - struct netlink_ext_ack *extack) -{ - struct xt_osf_user_finger *f; - struct xt_osf_finger *sf; - int err = -ENOENT; - - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - - if (!osf_attrs[OSF_ATTR_FINGER]) - return -EINVAL; - - f = nla_data(osf_attrs[OSF_ATTR_FINGER]); - - list_for_each_entry(sf, &xt_osf_fingers[!!f->df], finger_entry) { - if (memcmp(&sf->finger, f, sizeof(struct xt_osf_user_finger))) - continue; - - /* - * We are protected by nfnl mutex. - */ - list_del_rcu(&sf->finger_entry); - kfree_rcu(sf, rcu_head); - - err = 0; - break; - } - - return err; -} - -static const struct nfnl_callback xt_osf_nfnetlink_callbacks[OSF_MSG_MAX] = { - [OSF_MSG_ADD] = { - .call = xt_osf_add_callback, - .attr_count = OSF_ATTR_MAX, - .policy = xt_osf_policy, - }, - [OSF_MSG_REMOVE] = { - .call = xt_osf_remove_callback, - .attr_count = OSF_ATTR_MAX, - .policy = xt_osf_policy, - }, -}; - -static const struct nfnetlink_subsystem xt_osf_nfnetlink = { - .name = "osf", - .subsys_id = NFNL_SUBSYS_OSF, - .cb_count = OSF_MSG_MAX, - .cb = xt_osf_nfnetlink_callbacks, -}; - static bool xt_osf_match_packet(const struct sk_buff *skb, struct xt_action_param *p) { @@ -159,7 +47,7 @@ xt_osf_match_packet(const struct sk_buff *skb, struct xt_action_param *p) return false; return nf_osf_match(skb, xt_family(p), xt_hooknum(p), xt_in(p), - xt_out(p), info, net, xt_osf_fingers); + xt_out(p), info, net, nf_osf_fingers); } static struct xt_match xt_osf_match = { @@ -177,52 +65,21 @@ static struct xt_match xt_osf_match = { static int __init xt_osf_init(void) { - int err = -EINVAL; - int i; - - for (i=0; ifinger_entry); - kfree_rcu(f, rcu_head); - } - } - rcu_read_unlock(); - - rcu_barrier(); } module_init(xt_osf_init); -- cgit v1.2.3 From b96af92d6eaf9fadd77aa798c508a8a9d2e60020 Mon Sep 17 00:00:00 2001 From: Fernando Fernandez Mancera Date: Wed, 25 Jul 2018 01:32:46 +0200 Subject: netfilter: nf_tables: implement Passive OS fingerprint module in nft_osf Add basic module functions into nft_osf.[ch] in order to implement OSF module in nf_tables. Signed-off-by: Fernando Fernandez Mancera Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 7 ++ net/netfilter/Kconfig | 7 ++ net/netfilter/Makefile | 1 + net/netfilter/nft_osf.c | 106 +++++++++++++++++++++++++++++++ 4 files changed, 121 insertions(+) create mode 100644 net/netfilter/nft_osf.c (limited to 'include') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index f466860bcf75..382c32d630e9 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -1463,6 +1463,13 @@ enum nft_flowtable_hook_attributes { }; #define NFTA_FLOWTABLE_HOOK_MAX (__NFTA_FLOWTABLE_HOOK_MAX - 1) +enum nft_osf_attributes { + NFTA_OSF_UNSPEC, + NFTA_OSF_DREG, + __NFTA_OSF_MAX, +}; +#define NFTA_OSF_MAX (__NFTA_OSF_MAX - 1) + /** * enum nft_device_attributes - nf_tables device netlink attributes * diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 85333431e524..16fdfb75efb5 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -627,6 +627,13 @@ config NFT_SOCKET This option allows matching for the presence or absence of a corresponding socket and its attributes. +config NFT_OSF + tristate "Netfilter nf_tables passive OS fingerprint support" + depends on NETFILTER_ADVANCED + select NETFILTER_NETLINK_OSF + help + This option allows matching packets from an specific OS. + if NF_TABLES_NETDEV config NF_DUP_NETDEV diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index e684f9b8a9c3..5cbbf6978b55 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -110,6 +110,7 @@ obj-$(CONFIG_NFT_FIB) += nft_fib.o obj-$(CONFIG_NFT_FIB_INET) += nft_fib_inet.o obj-$(CONFIG_NFT_FIB_NETDEV) += nft_fib_netdev.o obj-$(CONFIG_NFT_SOCKET) += nft_socket.o +obj-$(CONFIG_NFT_OSF) += nft_osf.o # nf_tables netdev obj-$(CONFIG_NFT_DUP_NETDEV) += nft_dup_netdev.o diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c new file mode 100644 index 000000000000..bdacc4cffba4 --- /dev/null +++ b/net/netfilter/nft_osf.c @@ -0,0 +1,106 @@ +#include +#include + +#include +#include + +#define OSF_GENRE_SIZE 32 + +struct nft_osf { + enum nft_registers dreg:8; +}; + +static const struct nla_policy nft_osf_policy[NFTA_OSF_MAX + 1] = { + [NFTA_OSF_DREG] = { .type = NLA_U32 }, +}; + +static void nft_osf_eval(const struct nft_expr *expr, struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_osf *priv = nft_expr_priv(expr); + u32 *dest = ®s->data[priv->dreg]; + struct sk_buff *skb = pkt->skb; + const struct tcphdr *tcp; + struct tcphdr _tcph; + const char *os_name; + + tcp = skb_header_pointer(skb, ip_hdrlen(skb), + sizeof(struct tcphdr), &_tcph); + if (!tcp) { + regs->verdict.code = NFT_BREAK; + return; + } + if (!tcp->syn) { + regs->verdict.code = NFT_BREAK; + return; + } + + os_name = nf_osf_find(skb, nf_osf_fingers); + if (!os_name) + strncpy((char *)dest, "unknown", IFNAMSIZ); + else + strncpy((char *)dest, os_name, IFNAMSIZ); +} + +static int nft_osf_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_osf *priv = nft_expr_priv(expr); + int err; + + priv->dreg = nft_parse_register(tb[NFTA_OSF_DREG]); + err = nft_validate_register_store(ctx, priv->dreg, NULL, + NFTA_DATA_VALUE, OSF_GENRE_SIZE); + if (err < 0) + return err; + + return 0; +} + +static int nft_osf_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + const struct nft_osf *priv = nft_expr_priv(expr); + + if (nft_dump_register(skb, NFTA_OSF_DREG, priv->dreg)) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -1; +} + +static struct nft_expr_type nft_osf_type; +static const struct nft_expr_ops nft_osf_op = { + .eval = nft_osf_eval, + .size = NFT_EXPR_SIZE(sizeof(struct nft_osf)), + .init = nft_osf_init, + .dump = nft_osf_dump, + .type = &nft_osf_type, +}; + +static struct nft_expr_type nft_osf_type __read_mostly = { + .ops = &nft_osf_op, + .name = "osf", + .owner = THIS_MODULE, + .policy = nft_osf_policy, + .maxattr = NFTA_OSF_MAX, +}; + +static int __init nft_osf_module_init(void) +{ + return nft_register_expr(&nft_osf_type); +} + +static void __exit nft_osf_module_exit(void) +{ + return nft_unregister_expr(&nft_osf_type); +} + +module_init(nft_osf_module_init); +module_exit(nft_osf_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Fernando Fernandez "); +MODULE_ALIAS_NFT_EXPR("osf"); -- cgit v1.2.3 From 4ed8eb6570a49931c705512060acd50058d61616 Mon Sep 17 00:00:00 2001 From: Máté Eckl Date: Mon, 30 Jul 2018 11:07:32 +0200 Subject: netfilter: nf_tables: Add native tproxy support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit A great portion of the code is taken from xt_TPROXY.c There are some changes compared to the iptables implementation: - tproxy statement is not terminal here - Either address or port has to be specified, but at least one of them is necessary. If one of them is not specified, the evaluation will be performed with the original attribute of the packet (ie. target port is not specified => the packet's dport will be used). To make this work in inet tables, the tproxy structure has a family member (typically called priv->family) which is not necessarily equal to ctx->family. priv->family can have three values legally: - NFPROTO_IPV4 if the table family is ip OR if table family is inet, but an ipv4 address is specified as a target address. The rule only evaluates ipv4 packets in this case. - NFPROTO_IPV6 if the table family is ip6 OR if table family is inet, but an ipv6 address is specified as a target address. The rule only evaluates ipv6 packets in this case. - NFPROTO_UNSPEC if the table family is inet AND if only the port is specified. The rule will evaluate both ipv4 and ipv6 packets. Signed-off-by: Máté Eckl Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 16 ++ net/netfilter/Kconfig | 10 + net/netfilter/Makefile | 1 + net/netfilter/nft_tproxy.c | 314 +++++++++++++++++++++++++++++++ 4 files changed, 341 insertions(+) create mode 100644 net/netfilter/nft_tproxy.c (limited to 'include') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 382c32d630e9..f112ea52dc1a 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -1252,6 +1252,22 @@ enum nft_nat_attributes { }; #define NFTA_NAT_MAX (__NFTA_NAT_MAX - 1) +/** + * enum nft_tproxy_attributes - nf_tables tproxy expression netlink attributes + * + * NFTA_TPROXY_FAMILY: Target address family (NLA_U32: nft_registers) + * NFTA_TPROXY_REG_ADDR: Target address register (NLA_U32: nft_registers) + * NFTA_TPROXY_REG_PORT: Target port register (NLA_U32: nft_registers) + */ +enum nft_tproxy_attributes { + NFTA_TPROXY_UNSPEC, + NFTA_TPROXY_FAMILY, + NFTA_TPROXY_REG_ADDR, + NFTA_TPROXY_REG_PORT, + __NFTA_TPROXY_MAX +}; +#define NFTA_TPROXY_MAX (__NFTA_TPROXY_MAX - 1) + /** * enum nft_masq_attributes - nf_tables masquerade expression attributes * diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 16fdfb75efb5..0febf3e21f91 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -634,6 +634,16 @@ config NFT_OSF help This option allows matching packets from an specific OS. +config NFT_TPROXY + tristate "Netfilter nf_tables tproxy support" + depends on IPV6 || IPV6=n + select NF_DEFRAG_IPV4 + select NF_DEFRAG_IPV6 if NF_TABLES_IPV6 + select NF_TPROXY_IPV4 + select NF_TPROXY_IPV6 if NF_TABLES_IPV6 + help + This makes transparent proxy support available in nftables. + if NF_TABLES_NETDEV config NF_DUP_NETDEV diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 5cbbf6978b55..cf61615cc529 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -111,6 +111,7 @@ obj-$(CONFIG_NFT_FIB_INET) += nft_fib_inet.o obj-$(CONFIG_NFT_FIB_NETDEV) += nft_fib_netdev.o obj-$(CONFIG_NFT_SOCKET) += nft_socket.o obj-$(CONFIG_NFT_OSF) += nft_osf.o +obj-$(CONFIG_NFT_TPROXY) += nft_tproxy.o # nf_tables netdev obj-$(CONFIG_NFT_DUP_NETDEV) += nft_dup_netdev.o diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c new file mode 100644 index 000000000000..c6845f7baa08 --- /dev/null +++ b/net/netfilter/nft_tproxy.c @@ -0,0 +1,314 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#if IS_ENABLED(CONFIG_NF_TABLES_IPV6) +#include +#endif + +struct nft_tproxy { + enum nft_registers sreg_addr:8; + enum nft_registers sreg_port:8; + u8 family; +}; + +static void nft_tproxy_eval_v4(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + const struct nft_tproxy *priv = nft_expr_priv(expr); + struct sk_buff *skb = pkt->skb; + const struct iphdr *iph = ip_hdr(skb); + struct udphdr _hdr, *hp; + __be32 taddr = 0; + __be16 tport = 0; + struct sock *sk; + + hp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_hdr), &_hdr); + if (!hp) { + regs->verdict.code = NFT_BREAK; + return; + } + + /* check if there's an ongoing connection on the packet addresses, this + * happens if the redirect already happened and the current packet + * belongs to an already established connection + */ + sk = nf_tproxy_get_sock_v4(nft_net(pkt), skb, iph->protocol, + iph->saddr, iph->daddr, + hp->source, hp->dest, + skb->dev, NF_TPROXY_LOOKUP_ESTABLISHED); + + if (priv->sreg_addr) + taddr = regs->data[priv->sreg_addr]; + taddr = nf_tproxy_laddr4(skb, taddr, iph->daddr); + + if (priv->sreg_port) + tport = regs->data[priv->sreg_port]; + if (!tport) + tport = hp->dest; + + /* UDP has no TCP_TIME_WAIT state, so we never enter here */ + if (sk && sk->sk_state == TCP_TIME_WAIT) { + /* reopening a TIME_WAIT connection needs special handling */ + sk = nf_tproxy_handle_time_wait4(nft_net(pkt), skb, taddr, tport, sk); + } else if (!sk) { + /* no, there's no established connection, check if + * there's a listener on the redirected addr/port + */ + sk = nf_tproxy_get_sock_v4(nft_net(pkt), skb, iph->protocol, + iph->saddr, taddr, + hp->source, tport, + skb->dev, NF_TPROXY_LOOKUP_LISTENER); + } + + if (sk && nf_tproxy_sk_is_transparent(sk)) + nf_tproxy_assign_sock(skb, sk); + else + regs->verdict.code = NFT_BREAK; +} + +#if IS_ENABLED(CONFIG_NF_TABLES_IPV6) +static void nft_tproxy_eval_v6(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + const struct nft_tproxy *priv = nft_expr_priv(expr); + struct sk_buff *skb = pkt->skb; + const struct ipv6hdr *iph = ipv6_hdr(skb); + struct in6_addr taddr = {0}; + int thoff = pkt->xt.thoff; + struct udphdr _hdr, *hp; + __be16 tport = 0; + struct sock *sk; + int l4proto; + + if (!pkt->tprot_set) { + regs->verdict.code = NFT_BREAK; + return; + } + l4proto = pkt->tprot; + + hp = skb_header_pointer(skb, thoff, sizeof(_hdr), &_hdr); + if (hp == NULL) { + regs->verdict.code = NFT_BREAK; + return; + } + + /* check if there's an ongoing connection on the packet addresses, this + * happens if the redirect already happened and the current packet + * belongs to an already established connection + */ + sk = nf_tproxy_get_sock_v6(nft_net(pkt), skb, thoff, l4proto, + &iph->saddr, &iph->daddr, + hp->source, hp->dest, + nft_in(pkt), NF_TPROXY_LOOKUP_ESTABLISHED); + + if (priv->sreg_addr) + memcpy(&taddr, ®s->data[priv->sreg_addr], sizeof(taddr)); + taddr = *nf_tproxy_laddr6(skb, &taddr, &iph->daddr); + + if (priv->sreg_port) + tport = regs->data[priv->sreg_port]; + if (!tport) + tport = hp->dest; + + /* UDP has no TCP_TIME_WAIT state, so we never enter here */ + if (sk && sk->sk_state == TCP_TIME_WAIT) { + /* reopening a TIME_WAIT connection needs special handling */ + sk = nf_tproxy_handle_time_wait6(skb, l4proto, thoff, + nft_net(pkt), + &taddr, + tport, + sk); + } else if (!sk) { + /* no there's no established connection, check if + * there's a listener on the redirected addr/port + */ + sk = nf_tproxy_get_sock_v6(nft_net(pkt), skb, thoff, + l4proto, &iph->saddr, &taddr, + hp->source, tport, + nft_in(pkt), NF_TPROXY_LOOKUP_LISTENER); + } + + /* NOTE: assign_sock consumes our sk reference */ + if (sk && nf_tproxy_sk_is_transparent(sk)) + nf_tproxy_assign_sock(skb, sk); + else + regs->verdict.code = NFT_BREAK; +} +#endif + +static void nft_tproxy_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + const struct nft_tproxy *priv = nft_expr_priv(expr); + + switch (nft_pf(pkt)) { + case NFPROTO_IPV4: + switch (priv->family) { + case NFPROTO_IPV4: + case NFPROTO_UNSPEC: + nft_tproxy_eval_v4(expr, regs, pkt); + return; + } + break; +#if IS_ENABLED(CONFIG_NF_TABLES_IPV6) + case NFPROTO_IPV6: + switch (priv->family) { + case NFPROTO_IPV6: + case NFPROTO_UNSPEC: + nft_tproxy_eval_v6(expr, regs, pkt); + return; + } +#endif + } + regs->verdict.code = NFT_BREAK; +} + +static const struct nla_policy nft_tproxy_policy[NFTA_TPROXY_MAX + 1] = { + [NFTA_TPROXY_FAMILY] = { .type = NLA_U32 }, + [NFTA_TPROXY_REG_ADDR] = { .type = NLA_U32 }, + [NFTA_TPROXY_REG_PORT] = { .type = NLA_U32 }, +}; + +static int nft_tproxy_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_tproxy *priv = nft_expr_priv(expr); + unsigned int alen = 0; + int err; + + if (!tb[NFTA_TPROXY_FAMILY] || + (!tb[NFTA_TPROXY_REG_ADDR] && !tb[NFTA_TPROXY_REG_PORT])) + return -EINVAL; + + priv->family = ntohl(nla_get_be32(tb[NFTA_TPROXY_FAMILY])); + + switch (ctx->family) { + case NFPROTO_IPV4: + if (priv->family != NFPROTO_IPV4) + return -EINVAL; + break; +#if IS_ENABLED(CONFIG_NF_TABLES_IPV6) + case NFPROTO_IPV6: + if (priv->family != NFPROTO_IPV6) + return -EINVAL; + break; +#endif + case NFPROTO_INET: + break; + default: + return -EOPNOTSUPP; + } + + /* Address is specified but the rule family is not set accordingly */ + if (priv->family == NFPROTO_UNSPEC && tb[NFTA_TPROXY_REG_ADDR]) + return -EINVAL; + + switch (priv->family) { + case NFPROTO_IPV4: + alen = FIELD_SIZEOF(union nf_inet_addr, in); + err = nf_defrag_ipv4_enable(ctx->net); + if (err) + return err; + break; +#if IS_ENABLED(CONFIG_NF_TABLES_IPV6) + case NFPROTO_IPV6: + alen = FIELD_SIZEOF(union nf_inet_addr, in6); + err = nf_defrag_ipv6_enable(ctx->net); + if (err) + return err; + break; +#endif + case NFPROTO_UNSPEC: + /* No address is specified here */ + err = nf_defrag_ipv4_enable(ctx->net); + if (err) + return err; + err = nf_defrag_ipv6_enable(ctx->net); + if (err) + return err; + break; + default: + return -EOPNOTSUPP; + } + + if (tb[NFTA_TPROXY_REG_ADDR]) { + priv->sreg_addr = nft_parse_register(tb[NFTA_TPROXY_REG_ADDR]); + err = nft_validate_register_load(priv->sreg_addr, alen); + if (err < 0) + return err; + } + + if (tb[NFTA_TPROXY_REG_PORT]) { + priv->sreg_port = nft_parse_register(tb[NFTA_TPROXY_REG_PORT]); + err = nft_validate_register_load(priv->sreg_port, sizeof(u16)); + if (err < 0) + return err; + } + + return 0; +} + +static int nft_tproxy_dump(struct sk_buff *skb, + const struct nft_expr *expr) +{ + const struct nft_tproxy *priv = nft_expr_priv(expr); + + if (nla_put_be32(skb, NFTA_TPROXY_FAMILY, htonl(priv->family))) + return -1; + + if (priv->sreg_addr && + nft_dump_register(skb, NFTA_TPROXY_REG_ADDR, priv->sreg_addr)) + return -1; + + if (priv->sreg_port && + nft_dump_register(skb, NFTA_TPROXY_REG_PORT, priv->sreg_port)) + return -1; + + return 0; +} + +static struct nft_expr_type nft_tproxy_type; +static const struct nft_expr_ops nft_tproxy_ops = { + .type = &nft_tproxy_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_tproxy)), + .eval = nft_tproxy_eval, + .init = nft_tproxy_init, + .dump = nft_tproxy_dump, +}; + +static struct nft_expr_type nft_tproxy_type __read_mostly = { + .name = "tproxy", + .ops = &nft_tproxy_ops, + .policy = nft_tproxy_policy, + .maxattr = NFTA_TPROXY_MAX, + .owner = THIS_MODULE, +}; + +static int __init nft_tproxy_module_init(void) +{ + return nft_register_expr(&nft_tproxy_type); +} + +static void __exit nft_tproxy_module_exit(void) +{ + nft_unregister_expr(&nft_tproxy_type); +} + +module_init(nft_tproxy_module_init); +module_exit(nft_tproxy_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Máté Eckl"); +MODULE_DESCRIPTION("nf_tables tproxy support module"); +MODULE_ALIAS_NFT_EXPR("tproxy"); -- cgit v1.2.3 From f609e7a0f3956e3b03af735b83600a4eef2a04ec Mon Sep 17 00:00:00 2001 From: Corentin Labbe Date: Thu, 7 Jun 2018 15:55:25 -0400 Subject: media: sii9234: remove unused header The include/linux/platform_data/media/sii9234.h header file is unused, let's remove it. Signed-off-by: Corentin Labbe Signed-off-by: Mauro Carvalho Chehab --- include/linux/platform_data/media/sii9234.h | 24 ------------------------ 1 file changed, 24 deletions(-) delete mode 100644 include/linux/platform_data/media/sii9234.h (limited to 'include') diff --git a/include/linux/platform_data/media/sii9234.h b/include/linux/platform_data/media/sii9234.h deleted file mode 100644 index 6a4a809fe9a3..000000000000 --- a/include/linux/platform_data/media/sii9234.h +++ /dev/null @@ -1,24 +0,0 @@ -/* - * Driver header for SII9234 MHL converter chip. - * - * Copyright (c) 2011 Samsung Electronics, Co. Ltd - * Contact: Tomasz Stanislawski - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ - -#ifndef SII9234_H -#define SII9234_H - -/** - * @gpio_n_reset: GPIO driving nRESET pin - */ - -struct sii9234_platform_data { - int gpio_n_reset; -}; - -#endif /* SII9234_H */ -- cgit v1.2.3 From 489cae632fc04927e8ef36ac8d8847193a41df3b Mon Sep 17 00:00:00 2001 From: Jordan Crouse Date: Tue, 24 Jul 2018 10:33:19 -0600 Subject: include: Move ascii85 functions from i915 to linux/ascii85.h The i915 DRM driver very cleverly used ascii85 encoding for their GPU state file. Move the encode functions to a general header file to support other drivers that might be interested in the same functionality. v4: Make the return value const char * as suggested by Chris Wilson v3: Fix error_puts -> err_puts pointed out by the 01.org bot v2: Update API to be cleaner for the caller as suggested by Chris Wilson Reviewed-by: Chris Wilson Signed-off-by: Jordan Crouse Signed-off-by: Rob Clark --- drivers/gpu/drm/i915/i915_gpu_error.c | 34 ++++--------------------------- include/linux/ascii85.h | 38 +++++++++++++++++++++++++++++++++++ 2 files changed, 42 insertions(+), 30 deletions(-) create mode 100644 include/linux/ascii85.h (limited to 'include') diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 8c81cf3aa182..f7f2aa71d8d9 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -31,6 +31,7 @@ #include #include #include +#include #include "i915_gpu_error.h" #include "i915_drv.h" @@ -517,35 +518,12 @@ void i915_error_printf(struct drm_i915_error_state_buf *e, const char *f, ...) va_end(args); } -static int -ascii85_encode_len(int len) -{ - return DIV_ROUND_UP(len, 4); -} - -static bool -ascii85_encode(u32 in, char *out) -{ - int i; - - if (in == 0) - return false; - - out[5] = '\0'; - for (i = 5; i--; ) { - out[i] = '!' + in % 85; - in /= 85; - } - - return true; -} - static void print_error_obj(struct drm_i915_error_state_buf *m, struct intel_engine_cs *engine, const char *name, struct drm_i915_error_object *obj) { - char out[6]; + char out[ASCII85_BUFSZ]; int page; if (!obj) @@ -567,12 +545,8 @@ static void print_error_obj(struct drm_i915_error_state_buf *m, len -= obj->unused; len = ascii85_encode_len(len); - for (i = 0; i < len; i++) { - if (ascii85_encode(obj->pages[page][i], out)) - err_puts(m, out); - else - err_puts(m, "z"); - } + for (i = 0; i < len; i++) + err_puts(m, ascii85_encode(obj->pages[page][i], out)); } err_puts(m, "\n"); } diff --git a/include/linux/ascii85.h b/include/linux/ascii85.h new file mode 100644 index 000000000000..4cc40201273e --- /dev/null +++ b/include/linux/ascii85.h @@ -0,0 +1,38 @@ +/* + * SPDX-License-Identifier: GPL-2.0 + * + * Copyright (c) 2008 Intel Corporation + * Copyright (c) 2018 The Linux Foundation. All rights reserved. + */ + +#ifndef _ASCII85_H_ +#define _ASCII85_H_ + +#include + +#define ASCII85_BUFSZ 6 + +static inline long +ascii85_encode_len(long len) +{ + return DIV_ROUND_UP(len, 4); +} + +static inline const char * +ascii85_encode(u32 in, char *out) +{ + int i; + + if (in == 0) + return "z"; + + out[5] = '\0'; + for (i = 5; i--; ) { + out[i] = '!' + in % 85; + in /= 85; + } + + return out; +} + +#endif -- cgit v1.2.3 From cfc57a18a3c5dc95d06db80bddd30015162c57d2 Mon Sep 17 00:00:00 2001 From: Jordan Crouse Date: Tue, 24 Jul 2018 10:33:20 -0600 Subject: drm: drm_printer: Add printer for devcoredump Add a drm printer suitable for use with the read callback for devcoredump or other suitable buffer based output format that isn't otherwise covered by seq_file. v2: Add improved documentation per Daniel Vetter Signed-off-by: Jordan Crouse Signed-off-by: Rob Clark --- drivers/gpu/drm/drm_print.c | 74 +++++++++++++++++++++++++++++++++++++++++++++ include/drm/drm_print.h | 65 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 139 insertions(+) (limited to 'include') diff --git a/drivers/gpu/drm/drm_print.c b/drivers/gpu/drm/drm_print.c index b25f98f33f6c..03d1f98e5ac7 100644 --- a/drivers/gpu/drm/drm_print.c +++ b/drivers/gpu/drm/drm_print.c @@ -30,6 +30,80 @@ #include #include +void __drm_printfn_coredump(struct drm_printer *p, struct va_format *vaf) +{ + struct drm_print_iterator *iterator = p->arg; + ssize_t len; + + if (!iterator->remain) + return; + + /* Figure out how big the string will be */ + len = snprintf(NULL, 0, "%pV", vaf); + + if (iterator->offset < iterator->start) { + char *buf; + ssize_t copy; + + if (iterator->offset + len <= iterator->start) { + iterator->offset += len; + return; + } + + /* Print the string into a temporary buffer */ + buf = kmalloc(len + 1, + GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY); + if (!buf) + return; + + snprintf(buf, len + 1, "%pV", vaf); + + copy = len - (iterator->start - iterator->offset); + + if (copy > iterator->remain) + copy = iterator->remain; + + /* Copy out the bit of the string that we need */ + memcpy(iterator->data, + buf + (iterator->start - iterator->offset), copy); + + iterator->offset = iterator->start + copy; + iterator->remain -= copy; + + kfree(buf); + } else { + char *buf; + ssize_t pos = iterator->offset - iterator->start; + + if (len < iterator->remain) { + snprintf(((char *) iterator->data) + pos, + iterator->remain, "%pV", vaf); + + iterator->offset += len; + iterator->remain -= len; + + return; + } + + /* Print the string into a temporary buffer */ + buf = kmalloc(len + 1, + GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY); + if (!buf) + return; + + snprintf(buf, len + 1, "%pV", vaf); + + /* Copy out the remaining bits */ + memcpy(iterator->data + pos, buf, iterator->remain); + + iterator->offset += iterator->remain; + iterator->remain = 0; + + kfree(buf); + } +} +EXPORT_SYMBOL(__drm_printfn_coredump); + void __drm_printfn_seq_file(struct drm_printer *p, struct va_format *vaf) { seq_printf(p->arg, "%pV", vaf); diff --git a/include/drm/drm_print.h b/include/drm/drm_print.h index 767c90b654c5..e7570f93a21f 100644 --- a/include/drm/drm_print.h +++ b/include/drm/drm_print.h @@ -73,6 +73,7 @@ struct drm_printer { const char *prefix; }; +void __drm_printfn_coredump(struct drm_printer *p, struct va_format *vaf); void __drm_printfn_seq_file(struct drm_printer *p, struct va_format *vaf); void __drm_printfn_info(struct drm_printer *p, struct va_format *vaf); void __drm_printfn_debug(struct drm_printer *p, struct va_format *vaf); @@ -104,6 +105,70 @@ drm_vprintf(struct drm_printer *p, const char *fmt, va_list *va) #define drm_printf_indent(printer, indent, fmt, ...) \ drm_printf((printer), "%.*s" fmt, (indent), "\t\t\t\t\tX", ##__VA_ARGS__) +/** + * struct drm_print_iterator - local struct used with drm_printer_coredump + * @data: Pointer to the devcoredump output buffer + * @start: The offset within the buffer to start writing + * @remain: The number of bytes to write for this iteration + */ +struct drm_print_iterator { + void *data; + ssize_t start; + ssize_t remain; + /* private: */ + ssize_t offset; +}; + +/** + * drm_coredump_printer - construct a &drm_printer that can output to a buffer + * from the read function for devcoredump + * @iter: A pointer to a struct drm_print_iterator for the read instance + * + * This wrapper extends drm_printf() to work with a dev_coredumpm() callback + * function. The passed in drm_print_iterator struct contains the buffer + * pointer, size and offset as passed in from devcoredump. + * + * For example:: + * + * void coredump_read(char *buffer, loff_t offset, size_t count, + * void *data, size_t datalen) + * { + * struct drm_print_iterator iter; + * struct drm_printer p; + * + * iter.data = buffer; + * iter.start = offset; + * iter.remain = count; + * + * p = drm_coredump_printer(&iter); + * + * drm_printf(p, "foo=%d\n", foo); + * } + * + * void makecoredump(...) + * { + * ... + * dev_coredumpm(dev, THIS_MODULE, data, 0, GFP_KERNEL, + * coredump_read, ...) + * } + * + * RETURNS: + * The &drm_printer object + */ +static inline struct drm_printer +drm_coredump_printer(struct drm_print_iterator *iter) +{ + struct drm_printer p = { + .printfn = __drm_printfn_coredump, + .arg = iter, + }; + + /* Set the internal offset of the iterator to zero */ + iter->offset = 0; + + return p; +} + /** * drm_seq_file_printer - construct a &drm_printer that outputs to &seq_file * @f: the &struct seq_file to output to -- cgit v1.2.3 From 63f4cc015b66dd265c2fd6e7c94be1b9a3b72267 Mon Sep 17 00:00:00 2001 From: Jordan Crouse Date: Tue, 24 Jul 2018 10:33:21 -0600 Subject: drm: Add drm_puts() to complement drm_printf() Add drm_puts() for a much faster path to print constant strings into a drm_printer object with memcpy and friends. This can have seconds off of really large outputs such as GPU dumps. If the drm_printer object supports a custom puts function then use that otherwise fall back to the slower legacy printf call. v2: Add documentation for drm_puts() per Daniel Vetter Reviewed-by: Daniel Vetter Signed-off-by: Jordan Crouse [robclark fix minor htmldocs warning] Signed-off-by: Rob Clark --- drivers/gpu/drm/drm_print.c | 17 +++++++++++++++++ include/drm/drm_print.h | 2 ++ 2 files changed, 19 insertions(+) (limited to 'include') diff --git a/drivers/gpu/drm/drm_print.c b/drivers/gpu/drm/drm_print.c index 03d1f98e5ac7..01d4e5583b5d 100644 --- a/drivers/gpu/drm/drm_print.c +++ b/drivers/gpu/drm/drm_print.c @@ -122,6 +122,23 @@ void __drm_printfn_debug(struct drm_printer *p, struct va_format *vaf) } EXPORT_SYMBOL(__drm_printfn_debug); +/** + * drm_puts - print a const string to a &drm_printer stream + * @p: the &drm printer + * @str: const string + * + * Allow &drm_printer types that have a constant string + * option to use it. + */ +void drm_puts(struct drm_printer *p, const char *str) +{ + if (p->puts) + p->puts(p, str); + else + drm_printf(p, "%s", str); +} +EXPORT_SYMBOL(drm_puts); + /** * drm_printf - print to a &drm_printer stream * @p: the &drm_printer diff --git a/include/drm/drm_print.h b/include/drm/drm_print.h index e7570f93a21f..f2f42bb87ef2 100644 --- a/include/drm/drm_print.h +++ b/include/drm/drm_print.h @@ -69,6 +69,7 @@ struct drm_printer { /* private: */ void (*printfn)(struct drm_printer *p, struct va_format *vaf); + void (*puts)(struct drm_printer *p, const char *str); void *arg; const char *prefix; }; @@ -80,6 +81,7 @@ void __drm_printfn_debug(struct drm_printer *p, struct va_format *vaf); __printf(2, 3) void drm_printf(struct drm_printer *p, const char *f, ...); +void drm_puts(struct drm_printer *p, const char *str); __printf(2, 0) /** -- cgit v1.2.3 From 4538d7324507fed892a18b79ad72c8501b6e7027 Mon Sep 17 00:00:00 2001 From: Jordan Crouse Date: Tue, 24 Jul 2018 10:33:22 -0600 Subject: drm: Add a -puts() function for the seq_file printer Add a puts() function to use seq_puts() to help speed up up print time for constant strings. Reviewed-by: Daniel Vetter Signed-off-by: Jordan Crouse Signed-off-by: Rob Clark --- drivers/gpu/drm/drm_print.c | 6 ++++++ include/drm/drm_print.h | 2 ++ 2 files changed, 8 insertions(+) (limited to 'include') diff --git a/drivers/gpu/drm/drm_print.c b/drivers/gpu/drm/drm_print.c index 01d4e5583b5d..45d787611723 100644 --- a/drivers/gpu/drm/drm_print.c +++ b/drivers/gpu/drm/drm_print.c @@ -104,6 +104,12 @@ void __drm_printfn_coredump(struct drm_printer *p, struct va_format *vaf) } EXPORT_SYMBOL(__drm_printfn_coredump); +void __drm_puts_seq_file(struct drm_printer *p, const char *str) +{ + seq_puts(p->arg, str); +} +EXPORT_SYMBOL(__drm_puts_seq_file); + void __drm_printfn_seq_file(struct drm_printer *p, struct va_format *vaf) { seq_printf(p->arg, "%pV", vaf); diff --git a/include/drm/drm_print.h b/include/drm/drm_print.h index f2f42bb87ef2..b1432969b627 100644 --- a/include/drm/drm_print.h +++ b/include/drm/drm_print.h @@ -76,6 +76,7 @@ struct drm_printer { void __drm_printfn_coredump(struct drm_printer *p, struct va_format *vaf); void __drm_printfn_seq_file(struct drm_printer *p, struct va_format *vaf); +void __drm_puts_seq_file(struct drm_printer *p, const char *str); void __drm_printfn_info(struct drm_printer *p, struct va_format *vaf); void __drm_printfn_debug(struct drm_printer *p, struct va_format *vaf); @@ -182,6 +183,7 @@ static inline struct drm_printer drm_seq_file_printer(struct seq_file *f) { struct drm_printer p = { .printfn = __drm_printfn_seq_file, + .puts = __drm_puts_seq_file, .arg = f, }; return p; -- cgit v1.2.3 From 5dc634bdbfd6dd9bdf98bce0d6f64878e1d47b1f Mon Sep 17 00:00:00 2001 From: Jordan Crouse Date: Tue, 24 Jul 2018 10:33:23 -0600 Subject: drm: Add puts callback for the coredump printer Add a puts function for the coredump printer to bypass printf() for constant strings for a speed boost. Reorganize the coredump printf callback to share as much code as possible. v2: Try to reuse code between print and puts as suggested by Chris Wilson Signed-off-by: Jordan Crouse Signed-off-by: Rob Clark --- drivers/gpu/drm/drm_print.c | 84 ++++++++++++++++++++++++++------------------- include/drm/drm_print.h | 2 ++ 2 files changed, 51 insertions(+), 35 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_print.c b/drivers/gpu/drm/drm_print.c index 45d787611723..0e7fc3e7dfb4 100644 --- a/drivers/gpu/drm/drm_print.c +++ b/drivers/gpu/drm/drm_print.c @@ -30,7 +30,7 @@ #include #include -void __drm_printfn_coredump(struct drm_printer *p, struct va_format *vaf) +void __drm_puts_coredump(struct drm_printer *p, const char *str) { struct drm_print_iterator *iterator = p->arg; ssize_t len; @@ -38,26 +38,16 @@ void __drm_printfn_coredump(struct drm_printer *p, struct va_format *vaf) if (!iterator->remain) return; - /* Figure out how big the string will be */ - len = snprintf(NULL, 0, "%pV", vaf); - if (iterator->offset < iterator->start) { - char *buf; ssize_t copy; + len = strlen(str); + if (iterator->offset + len <= iterator->start) { iterator->offset += len; return; } - /* Print the string into a temporary buffer */ - buf = kmalloc(len + 1, - GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY); - if (!buf) - return; - - snprintf(buf, len + 1, "%pV", vaf); - copy = len - (iterator->start - iterator->offset); if (copy > iterator->remain) @@ -65,42 +55,66 @@ void __drm_printfn_coredump(struct drm_printer *p, struct va_format *vaf) /* Copy out the bit of the string that we need */ memcpy(iterator->data, - buf + (iterator->start - iterator->offset), copy); + str + (iterator->start - iterator->offset), copy); iterator->offset = iterator->start + copy; iterator->remain -= copy; - - kfree(buf); } else { - char *buf; ssize_t pos = iterator->offset - iterator->start; - if (len < iterator->remain) { - snprintf(((char *) iterator->data) + pos, - iterator->remain, "%pV", vaf); + len = min_t(ssize_t, strlen(str), iterator->remain); - iterator->offset += len; - iterator->remain -= len; + memcpy(iterator->data + pos, str, len); - return; - } + iterator->offset += len; + iterator->remain -= len; + } +} +EXPORT_SYMBOL(__drm_puts_coredump); - /* Print the string into a temporary buffer */ - buf = kmalloc(len + 1, - GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY); - if (!buf) - return; +void __drm_printfn_coredump(struct drm_printer *p, struct va_format *vaf) +{ + struct drm_print_iterator *iterator = p->arg; + size_t len; + char *buf; + + if (!iterator->remain) + return; + + /* Figure out how big the string will be */ + len = snprintf(NULL, 0, "%pV", vaf); + + /* This is the easiest path, we've already advanced beyond the offset */ + if (iterator->offset + len <= iterator->start) { + iterator->offset += len; + return; + } - snprintf(buf, len + 1, "%pV", vaf); + /* Then check if we can directly copy into the target buffer */ + if ((iterator->offset >= iterator->start) && (len < iterator->remain)) { + ssize_t pos = iterator->offset - iterator->start; - /* Copy out the remaining bits */ - memcpy(iterator->data + pos, buf, iterator->remain); + snprintf(((char *) iterator->data) + pos, + iterator->remain, "%pV", vaf); - iterator->offset += iterator->remain; - iterator->remain = 0; + iterator->offset += len; + iterator->remain -= len; - kfree(buf); + return; } + + /* + * Finally, hit the slow path and make a temporary string to copy over + * using _drm_puts_coredump + */ + buf = kmalloc(len + 1, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY); + if (!buf) + return; + + snprintf(buf, len + 1, "%pV", vaf); + __drm_puts_coredump(p, (const char *) buf); + + kfree(buf); } EXPORT_SYMBOL(__drm_printfn_coredump); diff --git a/include/drm/drm_print.h b/include/drm/drm_print.h index b1432969b627..f3e6eed3e79c 100644 --- a/include/drm/drm_print.h +++ b/include/drm/drm_print.h @@ -75,6 +75,7 @@ struct drm_printer { }; void __drm_printfn_coredump(struct drm_printer *p, struct va_format *vaf); +void __drm_puts_coredump(struct drm_printer *p, const char *str); void __drm_printfn_seq_file(struct drm_printer *p, struct va_format *vaf); void __drm_puts_seq_file(struct drm_printer *p, const char *str); void __drm_printfn_info(struct drm_printer *p, struct va_format *vaf); @@ -163,6 +164,7 @@ drm_coredump_printer(struct drm_print_iterator *iter) { struct drm_printer p = { .printfn = __drm_printfn_coredump, + .puts = __drm_puts_coredump, .arg = iter, }; -- cgit v1.2.3 From f7debfe54090d1a1c38e1f070be20d83bb70a8e0 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Sun, 29 Jul 2018 23:03:05 +0200 Subject: ALSA: seq: virmidi: Offload the output event processing The virmidi sequencer stuff tries to translate the rawmidi bytes to sequencer events and deliver the packets at trigger callback. The amount of the whole process of these translations and deliveries depends on the incoming rawmidi bytes, and we have no limit for that; this was the cause of a CPU soft lockup that had been reported and fixed recently. Although we've fixed the soft lockup by putting the temporary unlock and cond_resched(), it's rather a quick band aid. In this patch, meanwhile, the event parsing and delivery process is offloaded to a dedicated work, and the trigger callback just kicks it off. It has three merits, at least: - The processing is always done in a sleepable context, which can assure the event delivery with non-atomic flag without hackish is_atomic() usage. - Other relevant codes can be simplified, reducing the lines - It makes me happier Signed-off-by: Takashi Iwai --- include/sound/seq_virmidi.h | 1 + sound/core/seq/seq_virmidi.c | 100 ++++++++++++++++++++----------------------- 2 files changed, 47 insertions(+), 54 deletions(-) (limited to 'include') diff --git a/include/sound/seq_virmidi.h b/include/sound/seq_virmidi.h index 695257ae64ac..d488dcfa3a4e 100644 --- a/include/sound/seq_virmidi.h +++ b/include/sound/seq_virmidi.h @@ -41,6 +41,7 @@ struct snd_virmidi { struct snd_seq_event event; struct snd_virmidi_dev *rdev; struct snd_rawmidi_substream *substream; + struct work_struct output_work; }; #define SNDRV_VIRMIDI_SUBSCRIBE (1<<0) diff --git a/sound/core/seq/seq_virmidi.c b/sound/core/seq/seq_virmidi.c index 8ebbca554e99..67ea5d62cebc 100644 --- a/sound/core/seq/seq_virmidi.c +++ b/sound/core/seq/seq_virmidi.c @@ -154,70 +154,58 @@ static void snd_virmidi_input_trigger(struct snd_rawmidi_substream *substream, i } } -/* - * trigger rawmidi stream for output +/* process rawmidi bytes and send events; + * we need no lock here for vmidi->event since it's handled only in this work */ -static void snd_virmidi_output_trigger(struct snd_rawmidi_substream *substream, int up) +static void snd_vmidi_output_work(struct work_struct *work) { - struct snd_virmidi *vmidi = substream->runtime->private_data; - int count, res; - unsigned char buf[32], *pbuf; - unsigned long flags; - bool check_resched = !in_atomic(); + struct snd_virmidi *vmidi; + struct snd_rawmidi_substream *substream; + unsigned char input; + int ret; + + vmidi = container_of(work, struct snd_virmidi, output_work); + substream = vmidi->substream; + + /* discard the outputs in dispatch mode unless subscribed */ + if (vmidi->seq_mode == SNDRV_VIRMIDI_SEQ_DISPATCH && + !(vmidi->rdev->flags & SNDRV_VIRMIDI_SUBSCRIBE)) { + while (!snd_rawmidi_transmit_empty(substream)) + snd_rawmidi_transmit_ack(substream, 1); + return; + } - if (up) { - vmidi->trigger = 1; - if (vmidi->seq_mode == SNDRV_VIRMIDI_SEQ_DISPATCH && - !(vmidi->rdev->flags & SNDRV_VIRMIDI_SUBSCRIBE)) { - while (snd_rawmidi_transmit(substream, buf, - sizeof(buf)) > 0) { - /* ignored */ - } - return; - } - spin_lock_irqsave(&substream->runtime->lock, flags); + while (vmidi->trigger) { + if (snd_rawmidi_transmit(substream, &input, 1) != 1) + break; + if (snd_midi_event_encode_byte(vmidi->parser, input, + &vmidi->event) <= 0) + continue; if (vmidi->event.type != SNDRV_SEQ_EVENT_NONE) { - if (snd_seq_kernel_client_dispatch(vmidi->client, &vmidi->event, in_atomic(), 0) < 0) - goto out; + ret = snd_seq_kernel_client_dispatch(vmidi->client, + &vmidi->event, + false, 0); vmidi->event.type = SNDRV_SEQ_EVENT_NONE; - } - while (1) { - count = __snd_rawmidi_transmit_peek(substream, buf, sizeof(buf)); - if (count <= 0) + if (ret < 0) break; - pbuf = buf; - while (count > 0) { - res = snd_midi_event_encode(vmidi->parser, pbuf, count, &vmidi->event); - if (res < 0) { - snd_midi_event_reset_encode(vmidi->parser); - continue; - } - __snd_rawmidi_transmit_ack(substream, res); - pbuf += res; - count -= res; - if (vmidi->event.type != SNDRV_SEQ_EVENT_NONE) { - if (snd_seq_kernel_client_dispatch(vmidi->client, &vmidi->event, in_atomic(), 0) < 0) - goto out; - vmidi->event.type = SNDRV_SEQ_EVENT_NONE; - } - } - if (!check_resched) - continue; - /* do temporary unlock & cond_resched() for avoiding - * CPU soft lockup, which may happen via a write from - * a huge rawmidi buffer - */ - spin_unlock_irqrestore(&substream->runtime->lock, flags); - cond_resched(); - spin_lock_irqsave(&substream->runtime->lock, flags); } - out: - spin_unlock_irqrestore(&substream->runtime->lock, flags); - } else { - vmidi->trigger = 0; + /* rawmidi input might be huge, allow to have a break */ + cond_resched(); } } +/* + * trigger rawmidi stream for output + */ +static void snd_virmidi_output_trigger(struct snd_rawmidi_substream *substream, int up) +{ + struct snd_virmidi *vmidi = substream->runtime->private_data; + + vmidi->trigger = !!up; + if (up) + queue_work(system_highpri_wq, &vmidi->output_work); +} + /* * open rawmidi handle for input */ @@ -270,6 +258,7 @@ static int snd_virmidi_output_open(struct snd_rawmidi_substream *substream) vmidi->port = rdev->port; snd_virmidi_init_event(vmidi, &vmidi->event); vmidi->rdev = rdev; + INIT_WORK(&vmidi->output_work, snd_vmidi_output_work); runtime->private_data = vmidi; return 0; } @@ -299,6 +288,9 @@ static int snd_virmidi_input_close(struct snd_rawmidi_substream *substream) static int snd_virmidi_output_close(struct snd_rawmidi_substream *substream) { struct snd_virmidi *vmidi = substream->runtime->private_data; + + vmidi->trigger = 0; /* to be sure */ + cancel_work_sync(&vmidi->output_work); snd_midi_event_free(vmidi->parser); substream->runtime->private_data = NULL; kfree(vmidi); -- cgit v1.2.3 From 89b4ab213feb11a5bece544cfa12374f66c2c47c Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 30 Jul 2018 14:48:29 +0200 Subject: ALSA: seq: virmidi: Use READ_ONCE/WRITE_ONCE() macros The trigger flag in vmidi object can be referred in different contexts concurrently, hence it's better to be put with READ_ONCE() and WRITE_ONCE() macros to assure the accesses. Signed-off-by: Takashi Iwai --- include/sound/seq_virmidi.h | 2 +- sound/core/seq/seq_virmidi.c | 14 +++++--------- 2 files changed, 6 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/sound/seq_virmidi.h b/include/sound/seq_virmidi.h index d488dcfa3a4e..796ce7772213 100644 --- a/include/sound/seq_virmidi.h +++ b/include/sound/seq_virmidi.h @@ -36,7 +36,7 @@ struct snd_virmidi { int seq_mode; int client; int port; - unsigned int trigger: 1; + bool trigger; struct snd_midi_event *parser; struct snd_seq_event event; struct snd_virmidi_dev *rdev; diff --git a/sound/core/seq/seq_virmidi.c b/sound/core/seq/seq_virmidi.c index 67ea5d62cebc..03ac5e72dbe6 100644 --- a/sound/core/seq/seq_virmidi.c +++ b/sound/core/seq/seq_virmidi.c @@ -89,7 +89,7 @@ static int snd_virmidi_dev_receive_event(struct snd_virmidi_dev *rdev, else down_read(&rdev->filelist_sem); list_for_each_entry(vmidi, &rdev->filelist, list) { - if (!vmidi->trigger) + if (!READ_ONCE(vmidi->trigger)) continue; if (ev->type == SNDRV_SEQ_EVENT_SYSEX) { if ((ev->flags & SNDRV_SEQ_EVENT_LENGTH_MASK) != SNDRV_SEQ_EVENT_LENGTH_VARIABLE) @@ -147,11 +147,7 @@ static void snd_virmidi_input_trigger(struct snd_rawmidi_substream *substream, i { struct snd_virmidi *vmidi = substream->runtime->private_data; - if (up) { - vmidi->trigger = 1; - } else { - vmidi->trigger = 0; - } + WRITE_ONCE(vmidi->trigger, !!up); } /* process rawmidi bytes and send events; @@ -175,7 +171,7 @@ static void snd_vmidi_output_work(struct work_struct *work) return; } - while (vmidi->trigger) { + while (READ_ONCE(vmidi->trigger)) { if (snd_rawmidi_transmit(substream, &input, 1) != 1) break; if (snd_midi_event_encode_byte(vmidi->parser, input, @@ -201,7 +197,7 @@ static void snd_virmidi_output_trigger(struct snd_rawmidi_substream *substream, { struct snd_virmidi *vmidi = substream->runtime->private_data; - vmidi->trigger = !!up; + WRITE_ONCE(vmidi->trigger, !!up); if (up) queue_work(system_highpri_wq, &vmidi->output_work); } @@ -289,7 +285,7 @@ static int snd_virmidi_output_close(struct snd_rawmidi_substream *substream) { struct snd_virmidi *vmidi = substream->runtime->private_data; - vmidi->trigger = 0; /* to be sure */ + WRITE_ONCE(vmidi->trigger, false); /* to be sure */ cancel_work_sync(&vmidi->output_work); snd_midi_event_free(vmidi->parser); substream->runtime->private_data = NULL; -- cgit v1.2.3 From ea8532daee31bc72abfbc9ca7a43cbec0f6c05af Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 30 May 2018 11:07:05 -0400 Subject: media: videodev2: get rid of VIDIOC_RESERVED While this ioctl is there at least since Kernel 2.6.12-rc2, it was never used by any upstream driver. Get rid of it. Signed-off-by: Mauro Carvalho Chehab --- Documentation/media/videodev2.h.rst.exceptions | 1 - include/uapi/linux/videodev2.h | 1 - 2 files changed, 2 deletions(-) (limited to 'include') diff --git a/Documentation/media/videodev2.h.rst.exceptions b/Documentation/media/videodev2.h.rst.exceptions index a5cb0a8686ac..ca9f0edc579e 100644 --- a/Documentation/media/videodev2.h.rst.exceptions +++ b/Documentation/media/videodev2.h.rst.exceptions @@ -517,7 +517,6 @@ ignore define V4L2_CTRL_WHICH_DEF_VAL ignore define V4L2_OUT_CAP_CUSTOM_TIMINGS ignore define V4L2_CID_MAX_CTRLS -ignore ioctl VIDIOC_RESERVED ignore define BASE_VIDIOC_PRIVATE # Associate ioctls with their counterparts diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 3ea8097c2470..d8b33095abe0 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -2311,7 +2311,6 @@ struct v4l2_create_buffers { * */ #define VIDIOC_QUERYCAP _IOR('V', 0, struct v4l2_capability) -#define VIDIOC_RESERVED _IO('V', 1) #define VIDIOC_ENUM_FMT _IOWR('V', 2, struct v4l2_fmtdesc) #define VIDIOC_G_FMT _IOWR('V', 4, struct v4l2_format) #define VIDIOC_S_FMT _IOWR('V', 5, struct v4l2_format) -- cgit v1.2.3 From c454edc21b12dd7d416de6c81555e87aaec9685c Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Mon, 30 Jul 2018 10:10:01 -0400 Subject: block: don't account for split bio's size in cgroup stats We need to check in blkcg_bio_issue_check if the bio is flagged as QUEUE_ENTERED, because if it is then we've already accounted for the size of the IO in the cgroup stats. We can still however account for the extra IO since it'll be another request. Reported-by: Tejun Heo Signed-off-by: Josef Bacik Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 3bed5e02a873..f7b910768306 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -769,8 +769,14 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, if (!throtl) { blkg = blkg ?: q->root_blkg; - blkg_rwstat_add(&blkg->stat_bytes, bio->bi_opf, - bio->bi_iter.bi_size); + /* + * If the bio is flagged with BIO_QUEUE_ENTERED it means this + * is a split bio and we would have already accounted for the + * size of the bio. + */ + if (!bio_flagged(bio, BIO_QUEUE_ENTERED)) + blkg_rwstat_add(&blkg->stat_bytes, bio->bi_opf, + bio->bi_iter.bi_size); blkg_rwstat_add(&blkg->stat_ios, bio->bi_opf, 1); } -- cgit v1.2.3 From ddd0bc756983dc4d19000a4fe021b4c7f9d59aab Mon Sep 17 00:00:00 2001 From: Max Gurtovoy Date: Mon, 30 Jul 2018 00:15:31 +0300 Subject: block: move ref_tag calculation func to the block layer Currently this function is implemented in the scsi layer, but it's actual place should be the block layer since T10-PI is a general data integrity feature that is used in the nvme protocol as well. Suggested-by: Christoph Hellwig Cc: Martin K. Petersen Signed-off-by: Max Gurtovoy Signed-off-by: Jens Axboe --- drivers/infiniband/ulp/iser/iser_memory.c | 2 +- drivers/nvme/host/core.c | 3 +-- drivers/scsi/mpt3sas/mpt3sas_scsih.c | 2 +- drivers/scsi/sd_dif.c | 4 ++-- include/linux/t10-pi.h | 10 ++++++++++ include/scsi/scsi_cmnd.h | 7 +------ 6 files changed, 16 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/ulp/iser/iser_memory.c b/drivers/infiniband/ulp/iser/iser_memory.c index ca844a926e6a..130bf163f066 100644 --- a/drivers/infiniband/ulp/iser/iser_memory.c +++ b/drivers/infiniband/ulp/iser/iser_memory.c @@ -311,7 +311,7 @@ iser_set_dif_domain(struct scsi_cmnd *sc, struct ib_sig_attrs *sig_attrs, { domain->sig_type = IB_SIG_TYPE_T10_DIF; domain->sig.dif.pi_interval = scsi_prot_interval(sc); - domain->sig.dif.ref_tag = scsi_prot_ref_tag(sc); + domain->sig.dif.ref_tag = t10_pi_ref_tag(sc->request); /* * At the moment we hard code those, but in the future * we will take them from sc. diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index e77e6418a21c..16c8b86fe95d 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -611,8 +611,7 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns, case NVME_NS_DPS_PI_TYPE2: control |= NVME_RW_PRINFO_PRCHK_GUARD | NVME_RW_PRINFO_PRCHK_REF; - cmnd->rw.reftag = cpu_to_le32( - nvme_block_nr(ns, blk_rq_pos(req))); + cmnd->rw.reftag = cpu_to_le32(t10_pi_ref_tag(req)); break; } } diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index b8d131a455d0..dd738ae5c75b 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -4568,7 +4568,7 @@ _scsih_setup_eedp(struct MPT3SAS_ADAPTER *ioc, struct scsi_cmnd *scmd, MPI2_SCSIIO_EEDPFLAGS_CHECK_REFTAG | MPI2_SCSIIO_EEDPFLAGS_CHECK_GUARD; mpi_request->CDB.EEDP32.PrimaryReferenceTag = - cpu_to_be32(scsi_prot_ref_tag(scmd)); + cpu_to_be32(t10_pi_ref_tag(scmd->request)); break; case SCSI_PROT_DIF_TYPE3: diff --git a/drivers/scsi/sd_dif.c b/drivers/scsi/sd_dif.c index 9035380c0dda..d8de43d359ac 100644 --- a/drivers/scsi/sd_dif.c +++ b/drivers/scsi/sd_dif.c @@ -124,7 +124,7 @@ void sd_dif_prepare(struct scsi_cmnd *scmd) if (sdkp->protection_type == T10_PI_TYPE3_PROTECTION) return; - phys = scsi_prot_ref_tag(scmd); + phys = t10_pi_ref_tag(scmd->request); __rq_for_each_bio(bio, scmd->request) { struct bio_integrity_payload *bip = bio_integrity(bio); @@ -176,7 +176,7 @@ void sd_dif_complete(struct scsi_cmnd *scmd, unsigned int good_bytes) return; intervals = good_bytes / scsi_prot_interval(scmd); - phys = scsi_prot_ref_tag(scmd); + phys = t10_pi_ref_tag(scmd->request); __rq_for_each_bio(bio, scmd->request) { struct bio_integrity_payload *bip = bio_integrity(bio); diff --git a/include/linux/t10-pi.h b/include/linux/t10-pi.h index c6aa8a3c42ed..c40511f4e63d 100644 --- a/include/linux/t10-pi.h +++ b/include/linux/t10-pi.h @@ -37,6 +37,16 @@ struct t10_pi_tuple { #define T10_PI_APP_ESCAPE cpu_to_be16(0xffff) #define T10_PI_REF_ESCAPE cpu_to_be32(0xffffffff) +static inline u32 t10_pi_ref_tag(struct request *rq) +{ +#ifdef CONFIG_BLK_DEV_INTEGRITY + return blk_rq_pos(rq) >> + (rq->q->integrity.interval_exp - 9) & 0xffffffff; +#else + return -1U; +#endif +} + extern const struct blk_integrity_profile t10_pi_type1_crc; extern const struct blk_integrity_profile t10_pi_type1_ip; extern const struct blk_integrity_profile t10_pi_type3_crc; diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h index aaf1e971c6a3..cae229b5395c 100644 --- a/include/scsi/scsi_cmnd.h +++ b/include/scsi/scsi_cmnd.h @@ -4,6 +4,7 @@ #include #include +#include #include #include #include @@ -313,12 +314,6 @@ static inline unsigned int scsi_prot_interval(struct scsi_cmnd *scmd) return scmd->device->sector_size; } -static inline u32 scsi_prot_ref_tag(struct scsi_cmnd *scmd) -{ - return blk_rq_pos(scmd->request) >> - (ilog2(scsi_prot_interval(scmd)) - 9) & 0xffffffff; -} - static inline unsigned scsi_prot_sg_count(struct scsi_cmnd *cmd) { return cmd->prot_sdb ? cmd->prot_sdb->table.nents : 0; -- cgit v1.2.3 From 10c41ddd61323b27b447bc8e18296ac6c06107ad Mon Sep 17 00:00:00 2001 From: Max Gurtovoy Date: Mon, 30 Jul 2018 00:15:32 +0300 Subject: block: move dif_prepare/dif_complete functions to block layer Currently these functions are implemented in the scsi layer, but their actual place should be the block layer since T10-PI is a general data integrity feature that is used in the nvme protocol as well. Also, use the tuple size from the integrity profile since it may vary between integrity types. Suggested-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Signed-off-by: Max Gurtovoy Signed-off-by: Jens Axboe --- block/t10-pi.c | 110 +++++++++++++++++++++++++++++++++++++++++++++++ drivers/scsi/sd.c | 8 ++-- drivers/scsi/sd.h | 9 ---- drivers/scsi/sd_dif.c | 113 ------------------------------------------------- include/linux/t10-pi.h | 3 ++ 5 files changed, 118 insertions(+), 125 deletions(-) (limited to 'include') diff --git a/block/t10-pi.c b/block/t10-pi.c index a98db384048f..62aed77d0bb9 100644 --- a/block/t10-pi.c +++ b/block/t10-pi.c @@ -184,3 +184,113 @@ const struct blk_integrity_profile t10_pi_type3_ip = { .verify_fn = t10_pi_type3_verify_ip, }; EXPORT_SYMBOL(t10_pi_type3_ip); + +/** + * t10_pi_prepare - prepare PI prior submitting request to device + * @rq: request with PI that should be prepared + * @protection_type: PI type (Type 1/Type 2/Type 3) + * + * For Type 1/Type 2, the virtual start sector is the one that was + * originally submitted by the block layer for the ref_tag usage. Due to + * partitioning, MD/DM cloning, etc. the actual physical start sector is + * likely to be different. Remap protection information to match the + * physical LBA. + * + * Type 3 does not have a reference tag so no remapping is required. + */ +void t10_pi_prepare(struct request *rq, u8 protection_type) +{ + const int tuple_sz = rq->q->integrity.tuple_size; + u32 ref_tag = t10_pi_ref_tag(rq); + struct bio *bio; + + if (protection_type == T10_PI_TYPE3_PROTECTION) + return; + + __rq_for_each_bio(bio, rq) { + struct bio_integrity_payload *bip = bio_integrity(bio); + u32 virt = bip_get_seed(bip) & 0xffffffff; + struct bio_vec iv; + struct bvec_iter iter; + + /* Already remapped? */ + if (bip->bip_flags & BIP_MAPPED_INTEGRITY) + break; + + bip_for_each_vec(iv, bip, iter) { + void *p, *pmap; + unsigned int j; + + pmap = kmap_atomic(iv.bv_page); + p = pmap + iv.bv_offset; + for (j = 0; j < iv.bv_len; j += tuple_sz) { + struct t10_pi_tuple *pi = p; + + if (be32_to_cpu(pi->ref_tag) == virt) + pi->ref_tag = cpu_to_be32(ref_tag); + virt++; + ref_tag++; + p += tuple_sz; + } + + kunmap_atomic(pmap); + } + + bip->bip_flags |= BIP_MAPPED_INTEGRITY; + } +} +EXPORT_SYMBOL(t10_pi_prepare); + +/** + * t10_pi_complete - prepare PI prior returning request to the block layer + * @rq: request with PI that should be prepared + * @protection_type: PI type (Type 1/Type 2/Type 3) + * @intervals: total elements to prepare + * + * For Type 1/Type 2, the virtual start sector is the one that was + * originally submitted by the block layer for the ref_tag usage. Due to + * partitioning, MD/DM cloning, etc. the actual physical start sector is + * likely to be different. Since the physical start sector was submitted + * to the device, we should remap it back to virtual values expected by the + * block layer. + * + * Type 3 does not have a reference tag so no remapping is required. + */ +void t10_pi_complete(struct request *rq, u8 protection_type, + unsigned int intervals) +{ + const int tuple_sz = rq->q->integrity.tuple_size; + u32 ref_tag = t10_pi_ref_tag(rq); + struct bio *bio; + + if (protection_type == T10_PI_TYPE3_PROTECTION) + return; + + __rq_for_each_bio(bio, rq) { + struct bio_integrity_payload *bip = bio_integrity(bio); + u32 virt = bip_get_seed(bip) & 0xffffffff; + struct bio_vec iv; + struct bvec_iter iter; + + bip_for_each_vec(iv, bip, iter) { + void *p, *pmap; + unsigned int j; + + pmap = kmap_atomic(iv.bv_page); + p = pmap + iv.bv_offset; + for (j = 0; j < iv.bv_len && intervals; j += tuple_sz) { + struct t10_pi_tuple *pi = p; + + if (be32_to_cpu(pi->ref_tag) == ref_tag) + pi->ref_tag = cpu_to_be32(virt); + virt++; + ref_tag++; + intervals--; + p += tuple_sz; + } + + kunmap_atomic(pmap); + } + } +} +EXPORT_SYMBOL(t10_pi_complete); diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 9421d9877730..bbebdc3769b0 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -1119,7 +1119,7 @@ static int sd_setup_read_write_cmnd(struct scsi_cmnd *SCpnt) SCpnt->cmnd[0] = WRITE_6; if (blk_integrity_rq(rq)) - sd_dif_prepare(SCpnt); + t10_pi_prepare(SCpnt->request, sdkp->protection_type); } else if (rq_data_dir(rq) == READ) { SCpnt->cmnd[0] = READ_6; @@ -2047,8 +2047,10 @@ static int sd_done(struct scsi_cmnd *SCpnt) "sd_done: completed %d of %d bytes\n", good_bytes, scsi_bufflen(SCpnt))); - if (rq_data_dir(SCpnt->request) == READ && scsi_prot_sg_count(SCpnt)) - sd_dif_complete(SCpnt, good_bytes); + if (rq_data_dir(SCpnt->request) == READ && scsi_prot_sg_count(SCpnt) && + good_bytes) + t10_pi_complete(SCpnt->request, sdkp->protection_type, + good_bytes / scsi_prot_interval(SCpnt)); return good_bytes; } diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h index 392c7d078ae3..a7d4f50b67d4 100644 --- a/drivers/scsi/sd.h +++ b/drivers/scsi/sd.h @@ -254,21 +254,12 @@ static inline unsigned int sd_prot_flag_mask(unsigned int prot_op) #ifdef CONFIG_BLK_DEV_INTEGRITY extern void sd_dif_config_host(struct scsi_disk *); -extern void sd_dif_prepare(struct scsi_cmnd *scmd); -extern void sd_dif_complete(struct scsi_cmnd *, unsigned int); #else /* CONFIG_BLK_DEV_INTEGRITY */ static inline void sd_dif_config_host(struct scsi_disk *disk) { } -static inline int sd_dif_prepare(struct scsi_cmnd *scmd) -{ - return 0; -} -static inline void sd_dif_complete(struct scsi_cmnd *cmd, unsigned int a) -{ -} #endif /* CONFIG_BLK_DEV_INTEGRITY */ diff --git a/drivers/scsi/sd_dif.c b/drivers/scsi/sd_dif.c index d8de43d359ac..db72c82486e3 100644 --- a/drivers/scsi/sd_dif.c +++ b/drivers/scsi/sd_dif.c @@ -95,116 +95,3 @@ out: blk_integrity_register(disk, &bi); } -/* - * The virtual start sector is the one that was originally submitted - * by the block layer. Due to partitioning, MD/DM cloning, etc. the - * actual physical start sector is likely to be different. Remap - * protection information to match the physical LBA. - * - * From a protocol perspective there's a slight difference between - * Type 1 and 2. The latter uses 32-byte CDBs exclusively, and the - * reference tag is seeded in the CDB. This gives us the potential to - * avoid virt->phys remapping during write. However, at read time we - * don't know whether the virt sector is the same as when we wrote it - * (we could be reading from real disk as opposed to MD/DM device. So - * we always remap Type 2 making it identical to Type 1. - * - * Type 3 does not have a reference tag so no remapping is required. - */ -void sd_dif_prepare(struct scsi_cmnd *scmd) -{ - const int tuple_sz = sizeof(struct t10_pi_tuple); - struct bio *bio; - struct scsi_disk *sdkp; - struct t10_pi_tuple *pi; - u32 phys, virt; - - sdkp = scsi_disk(scmd->request->rq_disk); - - if (sdkp->protection_type == T10_PI_TYPE3_PROTECTION) - return; - - phys = t10_pi_ref_tag(scmd->request); - - __rq_for_each_bio(bio, scmd->request) { - struct bio_integrity_payload *bip = bio_integrity(bio); - struct bio_vec iv; - struct bvec_iter iter; - unsigned int j; - - /* Already remapped? */ - if (bip->bip_flags & BIP_MAPPED_INTEGRITY) - break; - - virt = bip_get_seed(bip) & 0xffffffff; - - bip_for_each_vec(iv, bip, iter) { - pi = kmap_atomic(iv.bv_page) + iv.bv_offset; - - for (j = 0; j < iv.bv_len; j += tuple_sz, pi++) { - - if (be32_to_cpu(pi->ref_tag) == virt) - pi->ref_tag = cpu_to_be32(phys); - - virt++; - phys++; - } - - kunmap_atomic(pi); - } - - bip->bip_flags |= BIP_MAPPED_INTEGRITY; - } -} - -/* - * Remap physical sector values in the reference tag to the virtual - * values expected by the block layer. - */ -void sd_dif_complete(struct scsi_cmnd *scmd, unsigned int good_bytes) -{ - const int tuple_sz = sizeof(struct t10_pi_tuple); - struct scsi_disk *sdkp; - struct bio *bio; - struct t10_pi_tuple *pi; - unsigned int j, intervals; - u32 phys, virt; - - sdkp = scsi_disk(scmd->request->rq_disk); - - if (sdkp->protection_type == T10_PI_TYPE3_PROTECTION || good_bytes == 0) - return; - - intervals = good_bytes / scsi_prot_interval(scmd); - phys = t10_pi_ref_tag(scmd->request); - - __rq_for_each_bio(bio, scmd->request) { - struct bio_integrity_payload *bip = bio_integrity(bio); - struct bio_vec iv; - struct bvec_iter iter; - - virt = bip_get_seed(bip) & 0xffffffff; - - bip_for_each_vec(iv, bip, iter) { - pi = kmap_atomic(iv.bv_page) + iv.bv_offset; - - for (j = 0; j < iv.bv_len; j += tuple_sz, pi++) { - - if (intervals == 0) { - kunmap_atomic(pi); - return; - } - - if (be32_to_cpu(pi->ref_tag) == phys) - pi->ref_tag = cpu_to_be32(virt); - - virt++; - phys++; - intervals--; - } - - kunmap_atomic(pi); - } - } -} - diff --git a/include/linux/t10-pi.h b/include/linux/t10-pi.h index c40511f4e63d..5a427c289f58 100644 --- a/include/linux/t10-pi.h +++ b/include/linux/t10-pi.h @@ -51,5 +51,8 @@ extern const struct blk_integrity_profile t10_pi_type1_crc; extern const struct blk_integrity_profile t10_pi_type1_ip; extern const struct blk_integrity_profile t10_pi_type3_crc; extern const struct blk_integrity_profile t10_pi_type3_ip; +extern void t10_pi_prepare(struct request *rq, u8 protection_type); +extern void t10_pi_complete(struct request *rq, u8 protection_type, + unsigned int intervals); #endif -- cgit v1.2.3 From dd979b4df817e9976f18fb6f9d134d6bc4a3c317 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 30 Jul 2018 09:42:10 +0200 Subject: net: simplify sock_poll_wait The wait_address argument is always directly derived from the filp argument, so remove it. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- crypto/af_alg.c | 2 +- include/net/sock.h | 11 ++++++----- net/atm/common.c | 2 +- net/caif/caif_socket.c | 2 +- net/core/datagram.c | 2 +- net/dccp/proto.c | 2 +- net/ipv4/tcp.c | 2 +- net/iucv/af_iucv.c | 2 +- net/nfc/llcp_sock.c | 2 +- net/rxrpc/af_rxrpc.c | 2 +- net/smc/af_smc.c | 2 +- net/tipc/socket.c | 2 +- net/unix/af_unix.c | 4 ++-- 13 files changed, 19 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/crypto/af_alg.c b/crypto/af_alg.c index c166f424871c..b053179e0bc5 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -1071,7 +1071,7 @@ __poll_t af_alg_poll(struct file *file, struct socket *sock, struct af_alg_ctx *ctx = ask->private; __poll_t mask; - sock_poll_wait(file, sk_sleep(sk), wait); + sock_poll_wait(file, wait); mask = 0; if (!ctx->more || ctx->used) diff --git a/include/net/sock.h b/include/net/sock.h index 83b747538bd0..0518f61926ec 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2057,16 +2057,17 @@ static inline bool skwq_has_sleeper(struct socket_wq *wq) /** * sock_poll_wait - place memory barrier behind the poll_wait call. * @filp: file - * @wait_address: socket wait queue * @p: poll_table * * See the comments in the wq_has_sleeper function. */ -static inline void sock_poll_wait(struct file *filp, - wait_queue_head_t *wait_address, poll_table *p) +static inline void sock_poll_wait(struct file *filp, poll_table *p) { - if (!poll_does_not_wait(p) && wait_address) { - poll_wait(filp, wait_address, p); + struct socket *sock = filp->private_data; + wait_queue_head_t *wq = sk_sleep(sock->sk); + + if (!poll_does_not_wait(p) && wq) { + poll_wait(filp, wq, p); /* We need to be sure we are in sync with the * socket flags modification. * diff --git a/net/atm/common.c b/net/atm/common.c index a7a68e509628..9f8cb0d2e71e 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -653,7 +653,7 @@ __poll_t vcc_poll(struct file *file, struct socket *sock, poll_table *wait) struct atm_vcc *vcc; __poll_t mask; - sock_poll_wait(file, sk_sleep(sk), wait); + sock_poll_wait(file, wait); mask = 0; vcc = ATM_SD(sock); diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index a6fb1b3bcad9..d18965f3291f 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -941,7 +941,7 @@ static __poll_t caif_poll(struct file *file, __poll_t mask; struct caifsock *cf_sk = container_of(sk, struct caifsock, sk); - sock_poll_wait(file, sk_sleep(sk), wait); + sock_poll_wait(file, wait); mask = 0; /* exceptional events? */ diff --git a/net/core/datagram.c b/net/core/datagram.c index 9938952c5c78..9aac0d63d53e 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -837,7 +837,7 @@ __poll_t datagram_poll(struct file *file, struct socket *sock, struct sock *sk = sock->sk; __poll_t mask; - sock_poll_wait(file, sk_sleep(sk), wait); + sock_poll_wait(file, wait); mask = 0; /* exceptional events? */ diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 0d56e36a6db7..875858c8b059 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -325,7 +325,7 @@ __poll_t dccp_poll(struct file *file, struct socket *sock, __poll_t mask; struct sock *sk = sock->sk; - sock_poll_wait(file, sk_sleep(sk), wait); + sock_poll_wait(file, wait); if (sk->sk_state == DCCP_LISTEN) return inet_csk_listen_poll(sk); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 514aaac1626f..f3bfb9f29520 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -507,7 +507,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) const struct tcp_sock *tp = tcp_sk(sk); int state; - sock_poll_wait(file, sk_sleep(sk), wait); + sock_poll_wait(file, wait); state = inet_sk_state_load(sk); if (state == TCP_LISTEN) diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 8d1c43f8fed4..92ee91e34395 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -1494,7 +1494,7 @@ __poll_t iucv_sock_poll(struct file *file, struct socket *sock, struct sock *sk = sock->sk; __poll_t mask = 0; - sock_poll_wait(file, sk_sleep(sk), wait); + sock_poll_wait(file, wait); if (sk->sk_state == IUCV_LISTEN) return iucv_accept_poll(sk); diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c index ea0c0c6f1874..dd4adf8b1167 100644 --- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -556,7 +556,7 @@ static __poll_t llcp_sock_poll(struct file *file, struct socket *sock, pr_debug("%p\n", sk); - sock_poll_wait(file, sk_sleep(sk), wait); + sock_poll_wait(file, wait); if (sk->sk_state == LLCP_LISTEN) return llcp_accept_poll(sk); diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 2b463047dd7b..ac44d8afffb1 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -741,7 +741,7 @@ static __poll_t rxrpc_poll(struct file *file, struct socket *sock, struct rxrpc_sock *rx = rxrpc_sk(sk); __poll_t mask; - sock_poll_wait(file, sk_sleep(sk), wait); + sock_poll_wait(file, wait); mask = 0; /* the socket is readable if there are any messages waiting on the Rx diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index fce7e4751151..0fc94f296e54 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -1535,7 +1535,7 @@ static __poll_t smc_poll(struct file *file, struct socket *sock, mask |= EPOLLERR; } else { if (sk->sk_state != SMC_CLOSED) - sock_poll_wait(file, sk_sleep(sk), wait); + sock_poll_wait(file, wait); if (sk->sk_err) mask |= EPOLLERR; if ((sk->sk_shutdown == SHUTDOWN_MASK) || diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 3d21414ba357..3763bedecf5f 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -716,7 +716,7 @@ static __poll_t tipc_poll(struct file *file, struct socket *sock, struct tipc_sock *tsk = tipc_sk(sk); __poll_t revents = 0; - sock_poll_wait(file, sk_sleep(sk), wait); + sock_poll_wait(file, wait); if (sk->sk_shutdown & RCV_SHUTDOWN) revents |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index e5473c03d667..1772a0e32665 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2635,7 +2635,7 @@ static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wa struct sock *sk = sock->sk; __poll_t mask; - sock_poll_wait(file, sk_sleep(sk), wait); + sock_poll_wait(file, wait); mask = 0; /* exceptional events? */ @@ -2672,7 +2672,7 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock, unsigned int writable; __poll_t mask; - sock_poll_wait(file, sk_sleep(sk), wait); + sock_poll_wait(file, wait); mask = 0; /* exceptional events? */ -- cgit v1.2.3 From d8bbd13beeaacd6494954bf5b945b54ccb2af309 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 30 Jul 2018 09:42:11 +0200 Subject: net: don not detour through struct sock to find the poll waitqueue For any open socket file descriptor sock->sk->sk_wq->wait will always point to sock->wq->wait. That means we can do the shorter dereference and removal a NULL check and don't have to not worry about any RCU protection. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/net/sock.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index 0518f61926ec..2afea5d1bdfe 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2064,10 +2064,9 @@ static inline bool skwq_has_sleeper(struct socket_wq *wq) static inline void sock_poll_wait(struct file *filp, poll_table *p) { struct socket *sock = filp->private_data; - wait_queue_head_t *wq = sk_sleep(sock->sk); - if (!poll_does_not_wait(p) && wq) { - poll_wait(filp, wq, p); + if (!poll_does_not_wait(p)) { + poll_wait(filp, &sock->wq->wait, p); /* We need to be sure we are in sync with the * socket flags modification. * -- cgit v1.2.3 From f641f13b992979b97e595b761a9ba1a64fed7c4e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 30 Jul 2018 09:42:12 +0200 Subject: net: remove sock_poll_busy_loop There is no point in hiding this logic in a helper. Also remove the useless events != 0 check and only busy loop once we know we actually have a poll method. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/net/busy_poll.h | 9 --------- net/socket.c | 5 ++++- 2 files changed, 4 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h index 9e36fda652b7..85777e68f738 100644 --- a/include/net/busy_poll.h +++ b/include/net/busy_poll.h @@ -121,15 +121,6 @@ static inline void sk_busy_loop(struct sock *sk, int nonblock) #endif } -static inline void sock_poll_busy_loop(struct socket *sock, __poll_t events) -{ - if (sk_can_busy_loop(sock->sk) && - events && (events & POLL_BUSY_LOOP)) { - /* once, only if requested by syscall */ - sk_busy_loop(sock->sk, 1); - } -} - /* if this socket can poll_ll, tell the system call */ static inline __poll_t sock_poll_busy_flag(struct socket *sock) { diff --git a/net/socket.c b/net/socket.c index 85633622c94d..674434127b3a 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1132,9 +1132,12 @@ static __poll_t sock_poll(struct file *file, poll_table *wait) struct socket *sock = file->private_data; __poll_t events = poll_requested_events(wait); - sock_poll_busy_loop(sock, events); if (!sock->ops->poll) return 0; + + /* poll once if requested by the syscall */ + if (sk_can_busy_loop(sock->sk) && (events & POLL_BUSY_LOOP)) + sk_busy_loop(sock->sk, 1); return sock->ops->poll(file, sock, wait) | sock_poll_busy_flag(sock); } -- cgit v1.2.3 From a331de3bf0e66ab2437fc8c5b99bd3c0d9da3088 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 30 Jul 2018 09:42:13 +0200 Subject: net: remove sock_poll_busy_flag Fold it into the only caller to make the code simpler and easier to read. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/net/busy_poll.h | 6 ------ net/socket.c | 16 +++++++++++----- 2 files changed, 11 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h index 85777e68f738..ba61cdd09eaa 100644 --- a/include/net/busy_poll.h +++ b/include/net/busy_poll.h @@ -121,12 +121,6 @@ static inline void sk_busy_loop(struct sock *sk, int nonblock) #endif } -/* if this socket can poll_ll, tell the system call */ -static inline __poll_t sock_poll_busy_flag(struct socket *sock) -{ - return sk_can_busy_loop(sock->sk) ? POLL_BUSY_LOOP : 0; -} - /* used in the NIC receive handler to mark the skb */ static inline void skb_mark_napi_id(struct sk_buff *skb, struct napi_struct *napi) diff --git a/net/socket.c b/net/socket.c index 674434127b3a..5b7df6695f4f 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1130,15 +1130,21 @@ EXPORT_SYMBOL(sock_create_lite); static __poll_t sock_poll(struct file *file, poll_table *wait) { struct socket *sock = file->private_data; - __poll_t events = poll_requested_events(wait); + __poll_t events = poll_requested_events(wait), flag = 0; if (!sock->ops->poll) return 0; - /* poll once if requested by the syscall */ - if (sk_can_busy_loop(sock->sk) && (events & POLL_BUSY_LOOP)) - sk_busy_loop(sock->sk, 1); - return sock->ops->poll(file, sock, wait) | sock_poll_busy_flag(sock); + if (sk_can_busy_loop(sock->sk)) { + /* poll once if requested by the syscall */ + if (events & POLL_BUSY_LOOP) + sk_busy_loop(sock->sk, 1); + + /* if this socket can poll_ll, tell the system call */ + flag = POLL_BUSY_LOOP; + } + + return sock->ops->poll(file, sock, wait) | flag; } static int sock_mmap(struct file *file, struct vm_area_struct *vma) -- cgit v1.2.3 From 802bfb19152c0fb4137c6ba72bcf042ee023e743 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Mon, 30 Jul 2018 14:30:42 +0200 Subject: net/sched: user-space can't set unknown tcfa_action values Currently, when initializing an action, the user-space can specify and use arbitrary values for the tcfa_action field. If the value is unknown by the kernel, is implicitly threaded as TC_ACT_UNSPEC. This change explicitly checks for unknown values at action creation time, and explicitly convert them to TC_ACT_UNSPEC. No functional changes are introduced, but this will allow introducing tcfa_action values not exposed to user-space in a later patch. Note: we can't use the above to hide TC_ACT_REDIRECT from user-space, as the latter is already part of uAPI. v3 -> v4: - use an helper to check for action validity (JiriP) - emit an extack for invalid actions (JiriP) v4 -> v5: - keep messages on a single line, drop net_warn (Marcelo) Signed-off-by: Paolo Abeni Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/uapi/linux/pkt_cls.h | 6 ++++-- net/sched/act_api.c | 14 ++++++++++++++ 2 files changed, 18 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index b4512254036b..48e5b5d49a34 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -45,6 +45,7 @@ enum { * the skb and act like everything * is alright. */ +#define TC_ACT_VALUE_MAX TC_ACT_TRAP /* There is a special kind of actions called "extended actions", * which need a value parameter. These have a local opcode located in @@ -55,11 +56,12 @@ enum { #define __TC_ACT_EXT_SHIFT 28 #define __TC_ACT_EXT(local) ((local) << __TC_ACT_EXT_SHIFT) #define TC_ACT_EXT_VAL_MASK ((1 << __TC_ACT_EXT_SHIFT) - 1) -#define TC_ACT_EXT_CMP(combined, opcode) \ - (((combined) & (~TC_ACT_EXT_VAL_MASK)) == opcode) +#define TC_ACT_EXT_OPCODE(combined) ((combined) & (~TC_ACT_EXT_VAL_MASK)) +#define TC_ACT_EXT_CMP(combined, opcode) (TC_ACT_EXT_OPCODE(combined) == opcode) #define TC_ACT_JUMP __TC_ACT_EXT(1) #define TC_ACT_GOTO_CHAIN __TC_ACT_EXT(2) +#define TC_ACT_EXT_OPCODE_MAX TC_ACT_GOTO_CHAIN /* Action type identifiers*/ enum { diff --git a/net/sched/act_api.c b/net/sched/act_api.c index b43df1e25c6d..229d63c99be2 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -786,6 +786,15 @@ static struct tc_cookie *nla_memdup_cookie(struct nlattr **tb) return c; } +static bool tcf_action_valid(int action) +{ + int opcode = TC_ACT_EXT_OPCODE(action); + + if (!opcode) + return action <= TC_ACT_VALUE_MAX; + return opcode <= TC_ACT_EXT_OPCODE_MAX || action == TC_ACT_UNSPEC; +} + struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, struct nlattr *nla, struct nlattr *est, char *name, int ovr, int bind, @@ -895,6 +904,11 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, } } + if (!tcf_action_valid(a->tcfa_action)) { + NL_SET_ERR_MSG(extack, "invalid action value, using TC_ACT_UNSPEC instead"); + a->tcfa_action = TC_ACT_UNSPEC; + } + return a; err_mod: -- cgit v1.2.3 From 7fd4b288ea6a3e45ad8afbcd5ec39554d57f1ae0 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Mon, 30 Jul 2018 14:30:43 +0200 Subject: tc/act: remove unneeded RCU lock in action callback Each lockless action currently does its own RCU locking in ->act(). This allows using plain RCU accessor, even if the context is really RCU BH. This change drops the per action RCU lock, replace the accessors with the _bh variant, cleans up a bit the surrounding code and documents the RCU status in the relevant header. No functional nor performance change is intended. The goal of this patch is clarifying that the RCU critical section used by the tc actions extends up to the classifier's caller. v1 -> v2: - preserve rcu lock in act_bpf: it's needed by eBPF helpers, as pointed out by Daniel v3 -> v4: - fixed some typos in the commit message (JiriP) Signed-off-by: Paolo Abeni Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/act_api.h | 2 +- include/net/sch_generic.h | 2 ++ net/sched/act_csum.c | 12 +++--------- net/sched/act_ife.c | 5 +---- net/sched/act_mirred.c | 4 +--- net/sched/act_sample.c | 4 +--- net/sched/act_skbedit.c | 10 +++------- net/sched/act_skbmod.c | 21 +++++++++------------ net/sched/act_tunnel_key.c | 6 +----- net/sched/act_vlan.c | 19 +++++++------------ 10 files changed, 29 insertions(+), 56 deletions(-) (limited to 'include') diff --git a/include/net/act_api.h b/include/net/act_api.h index 683ce41053d9..8c9bc02d05e1 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -85,7 +85,7 @@ struct tc_action_ops { size_t size; struct module *owner; int (*act)(struct sk_buff *, const struct tc_action *, - struct tcf_result *); + struct tcf_result *); /* called under RCU BH lock*/ int (*dump)(struct sk_buff *, struct tc_action *, int, int); void (*cleanup)(struct tc_action *); int (*lookup)(struct net *net, struct tc_action **a, u32 index, diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index c5432362dc26..bcae181c1857 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -285,6 +285,8 @@ struct tcf_proto { /* Fast access part */ struct tcf_proto __rcu *next; void __rcu *root; + + /* called under RCU BH lock*/ int (*classify)(struct sk_buff *, const struct tcf_proto *, struct tcf_result *); diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 4e8c383f379e..648a3a35b720 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -561,15 +561,14 @@ static int tcf_csum(struct sk_buff *skb, const struct tc_action *a, u32 update_flags; int action; - rcu_read_lock(); - params = rcu_dereference(p->params); + params = rcu_dereference_bh(p->params); tcf_lastuse_update(&p->tcf_tm); bstats_cpu_update(this_cpu_ptr(p->common.cpu_bstats), skb); action = READ_ONCE(p->tcf_action); if (unlikely(action == TC_ACT_SHOT)) - goto drop_stats; + goto drop; update_flags = params->update_flags; switch (tc_skb_protocol(skb)) { @@ -583,16 +582,11 @@ static int tcf_csum(struct sk_buff *skb, const struct tc_action *a, break; } -unlock: - rcu_read_unlock(); return action; drop: - action = TC_ACT_SHOT; - -drop_stats: qstats_drop_inc(this_cpu_ptr(p->common.cpu_qstats)); - goto unlock; + return TC_ACT_SHOT; } static int tcf_csum_dump(struct sk_buff *skb, struct tc_action *a, int bind, diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 3d6e265758c0..df4060e32d43 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -820,14 +820,11 @@ static int tcf_ife_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_ife_params *p; int ret; - rcu_read_lock(); - p = rcu_dereference(ife->params); + p = rcu_dereference_bh(ife->params); if (p->flags & IFE_ENCODE) { ret = tcf_ife_encode(skb, a, res, p); - rcu_read_unlock(); return ret; } - rcu_read_unlock(); return tcf_ife_decode(skb, a, res); } diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 6afd89a36c69..eeb335f03102 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -181,11 +181,10 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, tcf_lastuse_update(&m->tcf_tm); bstats_cpu_update(this_cpu_ptr(m->common.cpu_bstats), skb); - rcu_read_lock(); m_mac_header_xmit = READ_ONCE(m->tcfm_mac_header_xmit); m_eaction = READ_ONCE(m->tcfm_eaction); retval = READ_ONCE(m->tcf_action); - dev = rcu_dereference(m->tcfm_dev); + dev = rcu_dereference_bh(m->tcfm_dev); if (unlikely(!dev)) { pr_notice_once("tc mirred: target device is gone\n"); goto out; @@ -236,7 +235,6 @@ out: if (tcf_mirred_is_act_redirect(m_eaction)) retval = TC_ACT_SHOT; } - rcu_read_unlock(); return retval; } diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 3079e7be5bde..2608ccc83e5e 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -140,8 +140,7 @@ static int tcf_sample_act(struct sk_buff *skb, const struct tc_action *a, bstats_cpu_update(this_cpu_ptr(s->common.cpu_bstats), skb); retval = READ_ONCE(s->tcf_action); - rcu_read_lock(); - psample_group = rcu_dereference(s->psample_group); + psample_group = rcu_dereference_bh(s->psample_group); /* randomly sample packets according to rate */ if (psample_group && (prandom_u32() % s->rate == 0)) { @@ -165,7 +164,6 @@ static int tcf_sample_act(struct sk_buff *skb, const struct tc_action *a, skb_pull(skb, skb->mac_len); } - rcu_read_unlock(); return retval; } diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index da56e6938c9e..a6db47ebec11 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -43,8 +43,7 @@ static int tcf_skbedit(struct sk_buff *skb, const struct tc_action *a, tcf_lastuse_update(&d->tcf_tm); bstats_cpu_update(this_cpu_ptr(d->common.cpu_bstats), skb); - rcu_read_lock(); - params = rcu_dereference(d->params); + params = rcu_dereference_bh(d->params); action = READ_ONCE(d->tcf_action); if (params->flags & SKBEDIT_F_PRIORITY) @@ -77,14 +76,11 @@ static int tcf_skbedit(struct sk_buff *skb, const struct tc_action *a, } if (params->flags & SKBEDIT_F_PTYPE) skb->pkt_type = params->ptype; - -unlock: - rcu_read_unlock(); return action; + err: qstats_drop_inc(this_cpu_ptr(d->common.cpu_qstats)); - action = TC_ACT_SHOT; - goto unlock; + return TC_ACT_SHOT; } static const struct nla_policy skbedit_policy[TCA_SKBEDIT_MAX + 1] = { diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index cdc6bacfb190..c437c6d51a71 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -41,20 +41,14 @@ static int tcf_skbmod_run(struct sk_buff *skb, const struct tc_action *a, * then MAX_EDIT_LEN needs to change appropriately */ err = skb_ensure_writable(skb, MAX_EDIT_LEN); - if (unlikely(err)) { /* best policy is to drop on the floor */ - qstats_overlimit_inc(this_cpu_ptr(d->common.cpu_qstats)); - return TC_ACT_SHOT; - } + if (unlikely(err)) /* best policy is to drop on the floor */ + goto drop; - rcu_read_lock(); action = READ_ONCE(d->tcf_action); - if (unlikely(action == TC_ACT_SHOT)) { - qstats_overlimit_inc(this_cpu_ptr(d->common.cpu_qstats)); - rcu_read_unlock(); - return action; - } + if (unlikely(action == TC_ACT_SHOT)) + goto drop; - p = rcu_dereference(d->skbmod_p); + p = rcu_dereference_bh(d->skbmod_p); flags = p->flags; if (flags & SKBMOD_F_DMAC) ether_addr_copy(eth_hdr(skb)->h_dest, p->eth_dst); @@ -62,7 +56,6 @@ static int tcf_skbmod_run(struct sk_buff *skb, const struct tc_action *a, ether_addr_copy(eth_hdr(skb)->h_source, p->eth_src); if (flags & SKBMOD_F_ETYPE) eth_hdr(skb)->h_proto = p->eth_type; - rcu_read_unlock(); if (flags & SKBMOD_F_SWAPMAC) { u16 tmpaddr[ETH_ALEN / 2]; /* ether_addr_copy() requirement */ @@ -73,6 +66,10 @@ static int tcf_skbmod_run(struct sk_buff *skb, const struct tc_action *a, } return action; + +drop: + qstats_overlimit_inc(this_cpu_ptr(d->common.cpu_qstats)); + return TC_ACT_SHOT; } static const struct nla_policy skbmod_policy[TCA_SKBMOD_MAX + 1] = { diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index f811850fd1d0..d42d9e112789 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -31,9 +31,7 @@ static int tunnel_key_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_tunnel_key_params *params; int action; - rcu_read_lock(); - - params = rcu_dereference(t->params); + params = rcu_dereference_bh(t->params); tcf_lastuse_update(&t->tcf_tm); bstats_cpu_update(this_cpu_ptr(t->common.cpu_bstats), skb); @@ -53,8 +51,6 @@ static int tunnel_key_act(struct sk_buff *skb, const struct tc_action *a, break; } - rcu_read_unlock(); - return action; } diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index ad37f308175a..15a0ee214c9c 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -40,11 +40,9 @@ static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a, if (skb_at_tc_ingress(skb)) skb_push_rcsum(skb, skb->mac_len); - rcu_read_lock(); - action = READ_ONCE(v->tcf_action); - p = rcu_dereference(v->vlan_p); + p = rcu_dereference_bh(v->vlan_p); switch (p->tcfv_action) { case TCA_VLAN_ACT_POP: @@ -61,7 +59,7 @@ static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a, case TCA_VLAN_ACT_MODIFY: /* No-op if no vlan tag (either hw-accel or in-payload) */ if (!skb_vlan_tagged(skb)) - goto unlock; + goto out; /* extract existing tag (and guarantee no hw-accel tag) */ if (skb_vlan_tag_present(skb)) { tci = skb_vlan_tag_get(skb); @@ -86,18 +84,15 @@ static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a, BUG(); } - goto unlock; - -drop: - action = TC_ACT_SHOT; - qstats_drop_inc(this_cpu_ptr(v->common.cpu_qstats)); - -unlock: - rcu_read_unlock(); +out: if (skb_at_tc_ingress(skb)) skb_pull_rcsum(skb, skb->mac_len); return action; + +drop: + qstats_drop_inc(this_cpu_ptr(v->common.cpu_qstats)); + return TC_ACT_SHOT; } static const struct nla_policy vlan_policy[TCA_VLAN_MAX + 1] = { -- cgit v1.2.3 From cd11b164073b719203318227918f9510809d5e10 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Mon, 30 Jul 2018 14:30:44 +0200 Subject: net/tc: introduce TC_ACT_REINSERT. This is similar TC_ACT_REDIRECT, but with a slightly different semantic: - on ingress the mirred skbs are passed to the target device network stack without any additional check not scrubbing. - the rcu-protected stats provided via the tcf_result struct are updated on error conditions. This new tcfa_action value is not exposed to the user-space and can be used only internally by clsact. v1 -> v2: do not touch TC_ACT_REDIRECT code path, introduce a new action type instead v2 -> v3: - rename the new action value TC_ACT_REINJECT, update the helper accordingly - take care of uncloned reinjected packets in XDP generic hook v3 -> v4: - renamed again the new action value (JiriP) v4 -> v5: - fix build error with !NET_CLS_ACT (kbuild bot) Signed-off-by: Paolo Abeni Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/pkt_cls.h | 3 +++ include/net/sch_generic.h | 28 ++++++++++++++++++++++++++++ net/core/dev.c | 6 +++++- 3 files changed, 36 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 6d02f31abba8..22bfc3a13c25 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -7,6 +7,9 @@ #include #include +/* TC action not accessible from user space */ +#define TC_ACT_REINSERT (TC_ACT_VALUE_MAX + 1) + /* Basic packet classifier frontend definitions. */ struct tcf_walker { diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index bcae181c1857..a6d00093f35e 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -235,6 +235,12 @@ struct tcf_result { u32 classid; }; const struct tcf_proto *goto_tp; + + /* used by the TC_ACT_REINSERT action */ + struct { + bool ingress; + struct gnet_stats_queue *qstats; + }; }; }; @@ -569,6 +575,15 @@ static inline void skb_reset_tc(struct sk_buff *skb) #endif } +static inline bool skb_is_tc_redirected(const struct sk_buff *skb) +{ +#ifdef CONFIG_NET_CLS_ACT + return skb->tc_redirected; +#else + return false; +#endif +} + static inline bool skb_at_tc_ingress(const struct sk_buff *skb) { #ifdef CONFIG_NET_CLS_ACT @@ -1108,4 +1123,17 @@ void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp, void mini_qdisc_pair_init(struct mini_Qdisc_pair *miniqp, struct Qdisc *qdisc, struct mini_Qdisc __rcu **p_miniq); +static inline void skb_tc_reinsert(struct sk_buff *skb, struct tcf_result *res) +{ + struct gnet_stats_queue *stats = res->qstats; + int ret; + + if (res->ingress) + ret = netif_receive_skb(skb); + else + ret = dev_queue_xmit(skb); + if (ret && stats) + qstats_overlimit_inc(res->qstats); +} + #endif diff --git a/net/core/dev.c b/net/core/dev.c index 89031b5fef9f..38b0c414d780 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4252,7 +4252,7 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, /* Reinjected packets coming from act_mirred or similar should * not get XDP generic processing. */ - if (skb_cloned(skb)) + if (skb_cloned(skb) || skb_is_tc_redirected(skb)) return XDP_PASS; /* XDP packets must be linear and must have sufficient headroom @@ -4602,6 +4602,10 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, __skb_push(skb, skb->mac_len); skb_do_redirect(skb); return NULL; + case TC_ACT_REINSERT: + /* this does not scrub the packet, and updates stats on error */ + skb_tc_reinsert(skb, &cl_res); + return NULL; default: break; } -- cgit v1.2.3 From b41e44b4cb230747d7ad56e38c9dc65369b1d381 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 30 May 2018 11:07:03 -0400 Subject: media: dvb/video.h: get rid of unused APIs There are a number of other ioctls that aren't used anywhere inside the Kernel tree. Get rid of them. Signed-off-by: Mauro Carvalho Chehab --- .../media/uapi/dvb/video-get-frame-rate.rst | 61 ----------- Documentation/media/uapi/dvb/video-get-navi.rst | 84 --------------- .../media/uapi/dvb/video-set-attributes.rst | 93 ----------------- .../media/uapi/dvb/video-set-highlight.rst | 86 ---------------- Documentation/media/uapi/dvb/video-set-id.rst | 75 -------------- Documentation/media/uapi/dvb/video-set-spu.rst | 85 ---------------- Documentation/media/uapi/dvb/video-set-system.rst | 77 -------------- .../media/uapi/dvb/video_function_calls.rst | 6 -- Documentation/media/uapi/dvb/video_types.rst | 113 --------------------- Documentation/media/video.h.rst.exceptions | 2 - fs/compat_ioctl.c | 7 -- include/uapi/linux/dvb/video.h | 51 ---------- 12 files changed, 740 deletions(-) delete mode 100644 Documentation/media/uapi/dvb/video-get-frame-rate.rst delete mode 100644 Documentation/media/uapi/dvb/video-get-navi.rst delete mode 100644 Documentation/media/uapi/dvb/video-set-attributes.rst delete mode 100644 Documentation/media/uapi/dvb/video-set-highlight.rst delete mode 100644 Documentation/media/uapi/dvb/video-set-id.rst delete mode 100644 Documentation/media/uapi/dvb/video-set-spu.rst delete mode 100644 Documentation/media/uapi/dvb/video-set-system.rst (limited to 'include') diff --git a/Documentation/media/uapi/dvb/video-get-frame-rate.rst b/Documentation/media/uapi/dvb/video-get-frame-rate.rst deleted file mode 100644 index 400042a854cf..000000000000 --- a/Documentation/media/uapi/dvb/video-get-frame-rate.rst +++ /dev/null @@ -1,61 +0,0 @@ -.. -*- coding: utf-8; mode: rst -*- - -.. _VIDEO_GET_FRAME_RATE: - -==================== -VIDEO_GET_FRAME_RATE -==================== - -Name ----- - -VIDEO_GET_FRAME_RATE - -.. attention:: This ioctl is deprecated. - -Synopsis --------- - -.. c:function:: int ioctl(int fd, VIDEO_GET_FRAME_RATE, unsigned int *rate) - :name: VIDEO_GET_FRAME_RATE - - -Arguments ---------- - -.. flat-table:: - :header-rows: 0 - :stub-columns: 0 - - - - .. row 1 - - - int fd - - - File descriptor returned by a previous call to open(). - - - .. row 2 - - - int request - - - Equals VIDEO_GET_FRAME_RATE for this command. - - - .. row 3 - - - unsigned int \*rate - - - Returns the framerate in number of frames per 1000 seconds. - - -Description ------------ - -This ioctl call asks the Video Device to return the current framerate. - - -Return Value ------------- - -On success 0 is returned, on error -1 and the ``errno`` variable is set -appropriately. The generic error codes are described at the -:ref:`Generic Error Codes ` chapter. diff --git a/Documentation/media/uapi/dvb/video-get-navi.rst b/Documentation/media/uapi/dvb/video-get-navi.rst deleted file mode 100644 index 114a9ac48b9e..000000000000 --- a/Documentation/media/uapi/dvb/video-get-navi.rst +++ /dev/null @@ -1,84 +0,0 @@ -.. -*- coding: utf-8; mode: rst -*- - -.. _VIDEO_GET_NAVI: - -============== -VIDEO_GET_NAVI -============== - -Name ----- - -VIDEO_GET_NAVI - -.. attention:: This ioctl is deprecated. - -Synopsis --------- - -.. c:function:: int ioctl(fd, VIDEO_GET_NAVI , struct video_navi_pack *navipack) - :name: VIDEO_GET_NAVI - - -Arguments ---------- - -.. flat-table:: - :header-rows: 0 - :stub-columns: 0 - - - - .. row 1 - - - int fd - - - File descriptor returned by a previous call to open(). - - - .. row 2 - - - int request - - - Equals VIDEO_GET_NAVI for this command. - - - .. row 3 - - - video_navi_pack_t \*navipack - - - PCI or DSI pack (private stream 2) according to section ??. - - -Description ------------ - -This ioctl returns navigational information from the DVD stream. This is -especially needed if an encoded stream has to be decoded by the -hardware. - -.. c:type:: video_navi_pack - -.. code-block::c - - typedef struct video_navi_pack { - int length; /* 0 ... 1024 */ - __u8 data[1024]; - } video_navi_pack_t; - -Return Value ------------- - -On success 0 is returned, on error -1 and the ``errno`` variable is set -appropriately. The generic error codes are described at the -:ref:`Generic Error Codes ` chapter. - - - -.. flat-table:: - :header-rows: 0 - :stub-columns: 0 - - - - .. row 1 - - - ``EFAULT`` - - - driver is not able to return navigational information diff --git a/Documentation/media/uapi/dvb/video-set-attributes.rst b/Documentation/media/uapi/dvb/video-set-attributes.rst deleted file mode 100644 index b2f11a6746e9..000000000000 --- a/Documentation/media/uapi/dvb/video-set-attributes.rst +++ /dev/null @@ -1,93 +0,0 @@ -.. -*- coding: utf-8; mode: rst -*- - -.. _VIDEO_SET_ATTRIBUTES: - -==================== -VIDEO_SET_ATTRIBUTES -==================== - -Name ----- - -VIDEO_SET_ATTRIBUTES - -.. attention:: This ioctl is deprecated. - -Synopsis --------- - -.. c:function:: int ioctl(fd, VIDEO_SET_ATTRIBUTE ,video_attributes_t vattr) - :name: VIDEO_SET_ATTRIBUTE - - -Arguments ---------- - -.. flat-table:: - :header-rows: 0 - :stub-columns: 0 - - - - .. row 1 - - - int fd - - - File descriptor returned by a previous call to open(). - - - .. row 2 - - - int request - - - Equals VIDEO_SET_ATTRIBUTE for this command. - - - .. row 3 - - - video_attributes_t vattr - - - video attributes according to section ??. - - -Description ------------ - -This ioctl is intended for DVD playback and allows you to set certain -information about the stream. Some hardware may not need this -information, but the call also tells the hardware to prepare for DVD -playback. - -.. c:type:: video_attributes_t - -.. code-block::c - - typedef __u16 video_attributes_t; - /* bits: descr. */ - /* 15-14 Video compression mode (0=MPEG-1, 1=MPEG-2) */ - /* 13-12 TV system (0=525/60, 1=625/50) */ - /* 11-10 Aspect ratio (0=4:3, 3=16:9) */ - /* 9- 8 permitted display mode on 4:3 monitor (0=both, 1=only pan-sca */ - /* 7 line 21-1 data present in GOP (1=yes, 0=no) */ - /* 6 line 21-2 data present in GOP (1=yes, 0=no) */ - /* 5- 3 source resolution (0=720x480/576, 1=704x480/576, 2=352x480/57 */ - /* 2 source letterboxed (1=yes, 0=no) */ - /* 0 film/camera mode (0=camera, 1=film (625/50 only)) */ - - -Return Value ------------- - -On success 0 is returned, on error -1 and the ``errno`` variable is set -appropriately. The generic error codes are described at the -:ref:`Generic Error Codes ` chapter. - - - -.. flat-table:: - :header-rows: 0 - :stub-columns: 0 - - - - .. row 1 - - - ``EINVAL`` - - - input is not a valid attribute setting. diff --git a/Documentation/media/uapi/dvb/video-set-highlight.rst b/Documentation/media/uapi/dvb/video-set-highlight.rst deleted file mode 100644 index 90aeafd923b7..000000000000 --- a/Documentation/media/uapi/dvb/video-set-highlight.rst +++ /dev/null @@ -1,86 +0,0 @@ -.. -*- coding: utf-8; mode: rst -*- - -.. _VIDEO_SET_HIGHLIGHT: - -=================== -VIDEO_SET_HIGHLIGHT -=================== - -Name ----- - -VIDEO_SET_HIGHLIGHT - -.. attention:: This ioctl is deprecated. - -Synopsis --------- - -.. c:function:: int ioctl(fd, VIDEO_SET_HIGHLIGHT, struct video_highlight *vhilite) - :name: VIDEO_SET_HIGHLIGHT - - -Arguments ---------- - -.. flat-table:: - :header-rows: 0 - :stub-columns: 0 - - - - .. row 1 - - - int fd - - - File descriptor returned by a previous call to open(). - - - .. row 2 - - - int request - - - Equals VIDEO_SET_HIGHLIGHT for this command. - - - .. row 3 - - - video_highlight_t \*vhilite - - - SPU Highlight information according to section ??. - - -Description ------------ - -This ioctl sets the SPU highlight information for the menu access of a -DVD. - -.. c:type:: video_highlight - -.. code-block:: c - - typedef - struct video_highlight { - int active; /* 1=show highlight, 0=hide highlight */ - __u8 contrast1; /* 7- 4 Pattern pixel contrast */ - /* 3- 0 Background pixel contrast */ - __u8 contrast2; /* 7- 4 Emphasis pixel-2 contrast */ - /* 3- 0 Emphasis pixel-1 contrast */ - __u8 color1; /* 7- 4 Pattern pixel color */ - /* 3- 0 Background pixel color */ - __u8 color2; /* 7- 4 Emphasis pixel-2 color */ - /* 3- 0 Emphasis pixel-1 color */ - __u32 ypos; /* 23-22 auto action mode */ - /* 21-12 start y */ - /* 9- 0 end y */ - __u32 xpos; /* 23-22 button color number */ - /* 21-12 start x */ - /* 9- 0 end x */ - } video_highlight_t; - - - -Return Value ------------- - -On success 0 is returned, on error -1 and the ``errno`` variable is set -appropriately. The generic error codes are described at the -:ref:`Generic Error Codes ` chapter. diff --git a/Documentation/media/uapi/dvb/video-set-id.rst b/Documentation/media/uapi/dvb/video-set-id.rst deleted file mode 100644 index 18f66875ae3f..000000000000 --- a/Documentation/media/uapi/dvb/video-set-id.rst +++ /dev/null @@ -1,75 +0,0 @@ -.. -*- coding: utf-8; mode: rst -*- - -.. _VIDEO_SET_ID: - -============ -VIDEO_SET_ID -============ - -Name ----- - -VIDEO_SET_ID - -.. attention:: This ioctl is deprecated. - -Synopsis --------- - -.. c:function:: int ioctl(int fd, VIDEO_SET_ID, int id) - :name: VIDEO_SET_ID - - -Arguments ---------- - -.. flat-table:: - :header-rows: 0 - :stub-columns: 0 - - - - .. row 1 - - - int fd - - - File descriptor returned by a previous call to open(). - - - .. row 2 - - - int request - - - Equals VIDEO_SET_ID for this command. - - - .. row 3 - - - int id - - - video sub-stream id - - -Description ------------ - -This ioctl selects which sub-stream is to be decoded if a program or -system stream is sent to the video device. - - -Return Value ------------- - -On success 0 is returned, on error -1 and the ``errno`` variable is set -appropriately. The generic error codes are described at the -:ref:`Generic Error Codes ` chapter. - - - -.. flat-table:: - :header-rows: 0 - :stub-columns: 0 - - - - .. row 1 - - - ``EINVAL`` - - - Invalid sub-stream id. diff --git a/Documentation/media/uapi/dvb/video-set-spu.rst b/Documentation/media/uapi/dvb/video-set-spu.rst deleted file mode 100644 index 739e5e7bd133..000000000000 --- a/Documentation/media/uapi/dvb/video-set-spu.rst +++ /dev/null @@ -1,85 +0,0 @@ -.. -*- coding: utf-8; mode: rst -*- - -.. _VIDEO_SET_SPU: - -============= -VIDEO_SET_SPU -============= - -Name ----- - -VIDEO_SET_SPU - -.. attention:: This ioctl is deprecated. - -Synopsis --------- - -.. c:function:: int ioctl(fd, VIDEO_SET_SPU , struct video_spu *spu) - :name: VIDEO_SET_SPU - - -Arguments ---------- - -.. flat-table:: - :header-rows: 0 - :stub-columns: 0 - - - - .. row 1 - - - int fd - - - File descriptor returned by a previous call to open(). - - - .. row 2 - - - int request - - - Equals VIDEO_SET_SPU for this command. - - - .. row 3 - - - video_spu_t \*spu - - - SPU decoding (de)activation and subid setting according to section - ??. - - -Description ------------ - -This ioctl activates or deactivates SPU decoding in a DVD input stream. -It can only be used, if the driver is able to handle a DVD stream. - -.. c:type:: struct video_spu - -.. code-block:: c - - typedef struct video_spu { - int active; - int stream_id; - } video_spu_t; - - -Return Value ------------- - -On success 0 is returned, on error -1 and the ``errno`` variable is set -appropriately. The generic error codes are described at the -:ref:`Generic Error Codes ` chapter. - - - -.. flat-table:: - :header-rows: 0 - :stub-columns: 0 - - - - .. row 1 - - - ``EINVAL`` - - - input is not a valid spu setting or driver cannot handle SPU. diff --git a/Documentation/media/uapi/dvb/video-set-system.rst b/Documentation/media/uapi/dvb/video-set-system.rst deleted file mode 100644 index e39cbe080ef7..000000000000 --- a/Documentation/media/uapi/dvb/video-set-system.rst +++ /dev/null @@ -1,77 +0,0 @@ -.. -*- coding: utf-8; mode: rst -*- - -.. _VIDEO_SET_SYSTEM: - -================ -VIDEO_SET_SYSTEM -================ - -Name ----- - -VIDEO_SET_SYSTEM - -.. attention:: This ioctl is deprecated. - -Synopsis --------- - -.. c:function:: int ioctl(fd, VIDEO_SET_SYSTEM , video_system_t system) - :name: VIDEO_SET_SYSTEM - - -Arguments ---------- - -.. flat-table:: - :header-rows: 0 - :stub-columns: 0 - - - - .. row 1 - - - int fd - - - File descriptor returned by a previous call to open(). - - - .. row 2 - - - int request - - - Equals VIDEO_SET_FORMAT for this command. - - - .. row 3 - - - video_system_t system - - - video system of TV output. - - -Description ------------ - -This ioctl sets the television output format. The format (see section -??) may vary from the color format of the displayed MPEG stream. If the -hardware is not able to display the requested format the call will -return an error. - - -Return Value ------------- - -On success 0 is returned, on error -1 and the ``errno`` variable is set -appropriately. The generic error codes are described at the -:ref:`Generic Error Codes ` chapter. - - - -.. flat-table:: - :header-rows: 0 - :stub-columns: 0 - - - - .. row 1 - - - ``EINVAL`` - - - system is not a valid or supported video system. diff --git a/Documentation/media/uapi/dvb/video_function_calls.rst b/Documentation/media/uapi/dvb/video_function_calls.rst index 8d8383ffaeba..3f4f6c9ffad7 100644 --- a/Documentation/media/uapi/dvb/video_function_calls.rst +++ b/Documentation/media/uapi/dvb/video_function_calls.rst @@ -21,7 +21,6 @@ Video Function Calls video-get-status video-get-frame-count video-get-pts - video-get-frame-rate video-get-event video-command video-try-command @@ -31,12 +30,7 @@ Video Function Calls video-fast-forward video-slowmotion video-get-capabilities - video-set-id video-clear-buffer video-set-streamtype video-set-format - video-set-system - video-set-highlight - video-set-spu - video-get-navi video-set-attributes diff --git a/Documentation/media/uapi/dvb/video_types.rst b/Documentation/media/uapi/dvb/video_types.rst index 4cfa00e5c934..a0942171596c 100644 --- a/Documentation/media/uapi/dvb/video_types.rst +++ b/Documentation/media/uapi/dvb/video_types.rst @@ -246,116 +246,3 @@ following bits set according to the hardwares capabilities. #define VIDEO_CAP_SPU 16 #define VIDEO_CAP_NAVI 32 #define VIDEO_CAP_CSS 64 - - -.. _video-system: - -video_system_t -============== - -A call to VIDEO_SET_SYSTEM sets the desired video system for TV -output. The following system types can be set: - - -.. code-block:: c - - typedef enum { - VIDEO_SYSTEM_PAL, - VIDEO_SYSTEM_NTSC, - VIDEO_SYSTEM_PALN, - VIDEO_SYSTEM_PALNc, - VIDEO_SYSTEM_PALM, - VIDEO_SYSTEM_NTSC60, - VIDEO_SYSTEM_PAL60, - VIDEO_SYSTEM_PALM60 - } video_system_t; - - -.. c:type:: video_highlight - -struct video_highlight -====================== - -Calling the ioctl VIDEO_SET_HIGHLIGHTS posts the SPU highlight -information. The call expects the following format for that information: - - -.. code-block:: c - - typedef - struct video_highlight { - boolean active; /* 1=show highlight, 0=hide highlight */ - uint8_t contrast1; /* 7- 4 Pattern pixel contrast */ - /* 3- 0 Background pixel contrast */ - uint8_t contrast2; /* 7- 4 Emphasis pixel-2 contrast */ - /* 3- 0 Emphasis pixel-1 contrast */ - uint8_t color1; /* 7- 4 Pattern pixel color */ - /* 3- 0 Background pixel color */ - uint8_t color2; /* 7- 4 Emphasis pixel-2 color */ - /* 3- 0 Emphasis pixel-1 color */ - uint32_t ypos; /* 23-22 auto action mode */ - /* 21-12 start y */ - /* 9- 0 end y */ - uint32_t xpos; /* 23-22 button color number */ - /* 21-12 start x */ - /* 9- 0 end x */ - } video_highlight_t; - - -.. c:type:: video_spu - -struct video_spu -================ - -Calling VIDEO_SET_SPU deactivates or activates SPU decoding, according -to the following format: - - -.. code-block:: c - - typedef - struct video_spu { - boolean active; - int stream_id; - } video_spu_t; - - -.. c:type:: video_navi_pack - -struct video_navi_pack -====================== - -In order to get the navigational data the following structure has to be -passed to the ioctl VIDEO_GET_NAVI: - - -.. code-block:: c - - typedef - struct video_navi_pack { - int length; /* 0 ... 1024 */ - uint8_t data[1024]; - } video_navi_pack_t; - - -.. _video-attributes-t: - -video_attributes_t -================== - -The following attributes can be set by a call to VIDEO_SET_ATTRIBUTES: - - -.. code-block:: c - - typedef uint16_t video_attributes_t; - /* bits: descr. */ - /* 15-14 Video compression mode (0=MPEG-1, 1=MPEG-2) */ - /* 13-12 TV system (0=525/60, 1=625/50) */ - /* 11-10 Aspect ratio (0=4:3, 3=16:9) */ - /* 9- 8 permitted display mode on 4:3 monitor (0=both, 1=only pan-sca */ - /* 7 line 21-1 data present in GOP (1=yes, 0=no) */ - /* 6 line 21-2 data present in GOP (1=yes, 0=no) */ - /* 5- 3 source resolution (0=720x480/576, 1=704x480/576, 2=352x480/57 */ - /* 2 source letterboxed (1=yes, 0=no) */ - /* 0 film/camera mode (0=camera, 1=film (625/50 only)) */ diff --git a/Documentation/media/video.h.rst.exceptions b/Documentation/media/video.h.rst.exceptions index 89d7c3ef2da7..371cdbd7d062 100644 --- a/Documentation/media/video.h.rst.exceptions +++ b/Documentation/media/video.h.rst.exceptions @@ -34,6 +34,4 @@ replace typedef video_displayformat_t :c:type:`video_displayformat` replace typedef video_size_t :c:type:`video_size` replace typedef video_stream_source_t :c:type:`video_stream_source` replace typedef video_play_state_t :c:type:`video_play_state` -replace typedef video_highlight_t :c:type:`video_highlight` -replace typedef video_spu_t :c:type:`video_spu` replace typedef video_navi_pack_t :c:type:`video_navi_pack` diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index fdb5ef9b5d06..59216b172003 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -1205,16 +1205,9 @@ COMPATIBLE_IOCTL(VIDEO_FAST_FORWARD) COMPATIBLE_IOCTL(VIDEO_SLOWMOTION) COMPATIBLE_IOCTL(VIDEO_GET_CAPABILITIES) COMPATIBLE_IOCTL(VIDEO_CLEAR_BUFFER) -COMPATIBLE_IOCTL(VIDEO_SET_ID) COMPATIBLE_IOCTL(VIDEO_SET_STREAMTYPE) COMPATIBLE_IOCTL(VIDEO_SET_FORMAT) -COMPATIBLE_IOCTL(VIDEO_SET_SYSTEM) -COMPATIBLE_IOCTL(VIDEO_SET_HIGHLIGHT) -COMPATIBLE_IOCTL(VIDEO_SET_SPU) -COMPATIBLE_IOCTL(VIDEO_GET_NAVI) -COMPATIBLE_IOCTL(VIDEO_SET_ATTRIBUTES) COMPATIBLE_IOCTL(VIDEO_GET_SIZE) -COMPATIBLE_IOCTL(VIDEO_GET_FRAME_RATE) /* cec */ COMPATIBLE_IOCTL(CEC_ADAP_G_CAPS) COMPATIBLE_IOCTL(CEC_ADAP_G_LOG_ADDRS) diff --git a/include/uapi/linux/dvb/video.h b/include/uapi/linux/dvb/video.h index 6a0c9757b7ba..43ba8b0a3d14 100644 --- a/include/uapi/linux/dvb/video.h +++ b/include/uapi/linux/dvb/video.h @@ -37,18 +37,6 @@ typedef enum { } video_format_t; -typedef enum { - VIDEO_SYSTEM_PAL, - VIDEO_SYSTEM_NTSC, - VIDEO_SYSTEM_PALN, - VIDEO_SYSTEM_PALNc, - VIDEO_SYSTEM_PALM, - VIDEO_SYSTEM_NTSC60, - VIDEO_SYSTEM_PAL60, - VIDEO_SYSTEM_PALM60 -} video_system_t; - - typedef enum { VIDEO_PAN_SCAN, /* use pan and scan format */ VIDEO_LETTER_BOX, /* use letterbox format */ @@ -160,38 +148,6 @@ struct video_still_picture { }; -typedef -struct video_highlight { - int active; /* 1=show highlight, 0=hide highlight */ - __u8 contrast1; /* 7- 4 Pattern pixel contrast */ - /* 3- 0 Background pixel contrast */ - __u8 contrast2; /* 7- 4 Emphasis pixel-2 contrast */ - /* 3- 0 Emphasis pixel-1 contrast */ - __u8 color1; /* 7- 4 Pattern pixel color */ - /* 3- 0 Background pixel color */ - __u8 color2; /* 7- 4 Emphasis pixel-2 color */ - /* 3- 0 Emphasis pixel-1 color */ - __u32 ypos; /* 23-22 auto action mode */ - /* 21-12 start y */ - /* 9- 0 end y */ - __u32 xpos; /* 23-22 button color number */ - /* 21-12 start x */ - /* 9- 0 end x */ -} video_highlight_t; - - -typedef struct video_spu { - int active; - int stream_id; -} video_spu_t; - - -typedef struct video_navi_pack { - int length; /* 0 ... 1024 */ - __u8 data[1024]; -} video_navi_pack_t; - - typedef __u16 video_attributes_t; /* bits: descr. */ /* 15-14 Video compression mode (0=MPEG-1, 1=MPEG-2) */ @@ -236,16 +192,9 @@ typedef __u16 video_attributes_t; #define VIDEO_SLOWMOTION _IO('o', 32) #define VIDEO_GET_CAPABILITIES _IOR('o', 33, unsigned int) #define VIDEO_CLEAR_BUFFER _IO('o', 34) -#define VIDEO_SET_ID _IO('o', 35) #define VIDEO_SET_STREAMTYPE _IO('o', 36) #define VIDEO_SET_FORMAT _IO('o', 37) -#define VIDEO_SET_SYSTEM _IO('o', 38) -#define VIDEO_SET_HIGHLIGHT _IOW('o', 39, video_highlight_t) -#define VIDEO_SET_SPU _IOW('o', 50, video_spu_t) -#define VIDEO_GET_NAVI _IOR('o', 52, video_navi_pack_t) -#define VIDEO_SET_ATTRIBUTES _IO('o', 53) #define VIDEO_GET_SIZE _IOR('o', 55, video_size_t) -#define VIDEO_GET_FRAME_RATE _IOR('o', 56, unsigned int) /** * VIDEO_GET_PTS -- cgit v1.2.3 From d21c249b26311dd193b100e65fc9e7ae96233d40 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 30 May 2018 11:07:04 -0400 Subject: media: dvb/audio.h: get rid of unused APIs There are a number of other ioctls that aren't used anywhere inside the Kernel tree. Get rid of them. Signed-off-by: Mauro Carvalho Chehab --- Documentation/media/audio.h.rst.exceptions | 3 - Documentation/media/uapi/dvb/audio-get-pts.rst | 65 --------------------- .../media/uapi/dvb/audio-set-attributes.rst | 67 ---------------------- Documentation/media/uapi/dvb/audio-set-ext-id.rst | 66 --------------------- Documentation/media/uapi/dvb/audio-set-karaoke.rst | 66 --------------------- Documentation/media/uapi/dvb/audio_data_types.rst | 37 ------------ .../media/uapi/dvb/audio_function_calls.rst | 4 -- fs/compat_ioctl.c | 3 - include/uapi/linux/dvb/audio.h | 37 ------------ 9 files changed, 348 deletions(-) delete mode 100644 Documentation/media/uapi/dvb/audio-get-pts.rst delete mode 100644 Documentation/media/uapi/dvb/audio-set-attributes.rst delete mode 100644 Documentation/media/uapi/dvb/audio-set-ext-id.rst delete mode 100644 Documentation/media/uapi/dvb/audio-set-karaoke.rst (limited to 'include') diff --git a/Documentation/media/audio.h.rst.exceptions b/Documentation/media/audio.h.rst.exceptions index f40f3cbfe4c9..940458774cf6 100644 --- a/Documentation/media/audio.h.rst.exceptions +++ b/Documentation/media/audio.h.rst.exceptions @@ -1,9 +1,6 @@ # Ignore header name ignore define _DVBAUDIO_H_ -# Typedef pointing to structs -replace typedef audio_karaoke_t :c:type:`audio_karaoke` - # Undocumented audio caps, as this is a deprecated API anyway ignore define AUDIO_CAP_DTS ignore define AUDIO_CAP_LPCM diff --git a/Documentation/media/uapi/dvb/audio-get-pts.rst b/Documentation/media/uapi/dvb/audio-get-pts.rst deleted file mode 100644 index 2d1396b003de..000000000000 --- a/Documentation/media/uapi/dvb/audio-get-pts.rst +++ /dev/null @@ -1,65 +0,0 @@ -.. -*- coding: utf-8; mode: rst -*- - -.. _AUDIO_GET_PTS: - -============= -AUDIO_GET_PTS -============= - -Name ----- - -AUDIO_GET_PTS - -.. attention:: This ioctl is deprecated - -Synopsis --------- - -.. c:function:: int ioctl(int fd, AUDIO_GET_PTS, __u64 *pts) - :name: AUDIO_GET_PTS - - -Arguments ---------- - -.. flat-table:: - :header-rows: 0 - :stub-columns: 0 - - - - - - - int fd - - - File descriptor returned by a previous call to open(). - - - - - - __u64 \*pts - - - Returns the 33-bit timestamp as defined in ITU T-REC-H.222.0 / - ISO/IEC 13818-1. - - The PTS should belong to the currently played frame if possible, - but may also be a value close to it like the PTS of the last - decoded frame or the last PTS extracted by the PES parser. - - -Description ------------ - -This ioctl is obsolete. Do not use in new drivers. If you need this -functionality, then please contact the linux-media mailing list -(`https://linuxtv.org/lists.php `__). - -This ioctl call asks the Audio Device to return the current PTS -timestamp. - - -Return Value ------------- - -On success 0 is returned, on error -1 and the ``errno`` variable is set -appropriately. The generic error codes are described at the -:ref:`Generic Error Codes ` chapter. diff --git a/Documentation/media/uapi/dvb/audio-set-attributes.rst b/Documentation/media/uapi/dvb/audio-set-attributes.rst deleted file mode 100644 index f0c6153ca80f..000000000000 --- a/Documentation/media/uapi/dvb/audio-set-attributes.rst +++ /dev/null @@ -1,67 +0,0 @@ -.. -*- coding: utf-8; mode: rst -*- - -.. _AUDIO_SET_ATTRIBUTES: - -==================== -AUDIO_SET_ATTRIBUTES -==================== - -Name ----- - -AUDIO_SET_ATTRIBUTES - -.. attention:: This ioctl is deprecated - - -Synopsis --------- - -.. c:function:: int ioctl(fd, AUDIO_SET_ATTRIBUTES, struct audio_attributes *attr ) - :name: AUDIO_SET_ATTRIBUTES - -Arguments ---------- - -.. flat-table:: - :header-rows: 0 - :stub-columns: 0 - - - - - - - int fd - - - File descriptor returned by a previous call to open(). - - - - - - audio_attributes_t attr - - - audio attributes according to section ?? - - -Description ------------ - -This ioctl is intended for DVD playback and allows you to set certain -information about the audio stream. - - -Return Value ------------- - -On success 0 is returned, on error -1 and the ``errno`` variable is set -appropriately. The generic error codes are described at the -:ref:`Generic Error Codes ` chapter. - -.. flat-table:: - :header-rows: 0 - :stub-columns: 0 - - - - .. row 1 - - - ``EINVAL`` - - - attr is not a valid or supported attribute setting. diff --git a/Documentation/media/uapi/dvb/audio-set-ext-id.rst b/Documentation/media/uapi/dvb/audio-set-ext-id.rst deleted file mode 100644 index 8503c47f26bd..000000000000 --- a/Documentation/media/uapi/dvb/audio-set-ext-id.rst +++ /dev/null @@ -1,66 +0,0 @@ -.. -*- coding: utf-8; mode: rst -*- - -.. _AUDIO_SET_EXT_ID: - -================ -AUDIO_SET_EXT_ID -================ - -Name ----- - -AUDIO_SET_EXT_ID - -.. attention:: This ioctl is deprecated - -Synopsis --------- - -.. c:function:: int ioctl(fd, AUDIO_SET_EXT_ID, int id) - :name: AUDIO_SET_EXT_ID - -Arguments ---------- - -.. flat-table:: - :header-rows: 0 - :stub-columns: 0 - - - - - - - int fd - - - File descriptor returned by a previous call to open(). - - - - - - int id - - - audio sub_stream_id - - -Description ------------ - -This ioctl can be used to set the extension id for MPEG streams in DVD -playback. Only the first 3 bits are recognized. - - -Return Value ------------- - -On success 0 is returned, on error -1 and the ``errno`` variable is set -appropriately. The generic error codes are described at the -:ref:`Generic Error Codes ` chapter. - -.. flat-table:: - :header-rows: 0 - :stub-columns: 0 - - - - .. row 1 - - - ``EINVAL`` - - - id is not a valid id. diff --git a/Documentation/media/uapi/dvb/audio-set-karaoke.rst b/Documentation/media/uapi/dvb/audio-set-karaoke.rst deleted file mode 100644 index c759952d88aa..000000000000 --- a/Documentation/media/uapi/dvb/audio-set-karaoke.rst +++ /dev/null @@ -1,66 +0,0 @@ -.. -*- coding: utf-8; mode: rst -*- - -.. _AUDIO_SET_KARAOKE: - -================= -AUDIO_SET_KARAOKE -================= - -Name ----- - -AUDIO_SET_KARAOKE - -.. attention:: This ioctl is deprecated - -Synopsis --------- - -.. c:function:: int ioctl(fd, AUDIO_SET_KARAOKE, struct audio_karaoke *karaoke) - :name: AUDIO_SET_KARAOKE - - -Arguments ---------- - -.. flat-table:: - :header-rows: 0 - :stub-columns: 0 - - - - - - - int fd - - - File descriptor returned by a previous call to open(). - - - - - - audio_karaoke_t \*karaoke - - - karaoke settings according to section ??. - - -Description ------------ - -This ioctl allows one to set the mixer settings for a karaoke DVD. - - -Return Value ------------- - -On success 0 is returned, on error -1 and the ``errno`` variable is set -appropriately. The generic error codes are described at the -:ref:`Generic Error Codes ` chapter. - -.. flat-table:: - :header-rows: 0 - :stub-columns: 0 - - - - .. row 1 - - - ``EINVAL`` - - - karaoke is not a valid or supported karaoke setting. diff --git a/Documentation/media/uapi/dvb/audio_data_types.rst b/Documentation/media/uapi/dvb/audio_data_types.rst index 6b93359d64f7..5bffa2c98a24 100644 --- a/Documentation/media/uapi/dvb/audio_data_types.rst +++ b/Documentation/media/uapi/dvb/audio_data_types.rst @@ -114,40 +114,3 @@ following bits set according to the hardwares capabilities. #define AUDIO_CAP_OGG 64 #define AUDIO_CAP_SDDS 128 #define AUDIO_CAP_AC3 256 - -.. c:type:: audio_karaoke - -The ioctl AUDIO_SET_KARAOKE uses the following format: - - -.. code-block:: c - - typedef - struct audio_karaoke { - int vocal1; - int vocal2; - int melody; - } audio_karaoke_t; - -If Vocal1 or Vocal2 are non-zero, they get mixed into left and right t -at 70% each. If both, Vocal1 and Vocal2 are non-zero, Vocal1 gets mixed -into the left channel and Vocal2 into the right channel at 100% each. Ff -Melody is non-zero, the melody channel gets mixed into left and right. - - -.. c:type:: audio_attributes - -The following attributes can be set by a call to AUDIO_SET_ATTRIBUTES: - - -.. code-block:: c - - typedef uint16_t audio_attributes_t; - /* bits: descr. */ - /* 15-13 audio coding mode (0=ac3, 2=mpeg1, 3=mpeg2ext, 4=LPCM, 6=DTS, */ - /* 12 multichannel extension */ - /* 11-10 audio type (0=not spec, 1=language included) */ - /* 9- 8 audio application mode (0=not spec, 1=karaoke, 2=surround) */ - /* 7- 6 Quantization / DRC (mpeg audio: 1=DRC exists)(lpcm: 0=16bit, */ - /* 5- 4 Sample frequency fs (0=48kHz, 1=96kHz) */ - /* 2- 0 number of audio channels (n+1 channels) */ diff --git a/Documentation/media/uapi/dvb/audio_function_calls.rst b/Documentation/media/uapi/dvb/audio_function_calls.rst index 0bb56f0cfed4..7dba16285dab 100644 --- a/Documentation/media/uapi/dvb/audio_function_calls.rst +++ b/Documentation/media/uapi/dvb/audio_function_calls.rst @@ -22,13 +22,9 @@ Audio Function Calls audio-set-bypass-mode audio-channel-select audio-bilingual-channel-select - audio-get-pts audio-get-status audio-get-capabilities audio-clear-buffer audio-set-id audio-set-mixer audio-set-streamtype - audio-set-ext-id - audio-set-attributes - audio-set-karaoke diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index 59216b172003..a9b00942e87d 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -1178,9 +1178,6 @@ COMPATIBLE_IOCTL(AUDIO_CLEAR_BUFFER) COMPATIBLE_IOCTL(AUDIO_SET_ID) COMPATIBLE_IOCTL(AUDIO_SET_MIXER) COMPATIBLE_IOCTL(AUDIO_SET_STREAMTYPE) -COMPATIBLE_IOCTL(AUDIO_SET_EXT_ID) -COMPATIBLE_IOCTL(AUDIO_SET_ATTRIBUTES) -COMPATIBLE_IOCTL(AUDIO_SET_KARAOKE) COMPATIBLE_IOCTL(DMX_START) COMPATIBLE_IOCTL(DMX_STOP) COMPATIBLE_IOCTL(DMX_SET_FILTER) diff --git a/include/uapi/linux/dvb/audio.h b/include/uapi/linux/dvb/audio.h index 69f7a85d81b1..afeae063e640 100644 --- a/include/uapi/linux/dvb/audio.h +++ b/include/uapi/linux/dvb/audio.h @@ -67,27 +67,6 @@ typedef struct audio_status { } audio_status_t; /* separate decoder hardware */ -typedef -struct audio_karaoke { /* if Vocal1 or Vocal2 are non-zero, they get mixed */ - int vocal1; /* into left and right t at 70% each */ - int vocal2; /* if both, Vocal1 and Vocal2 are non-zero, Vocal1 gets*/ - int melody; /* mixed into the left channel and */ - /* Vocal2 into the right channel at 100% each. */ - /* if Melody is non-zero, the melody channel gets mixed*/ -} audio_karaoke_t; /* into left and right */ - - -typedef __u16 audio_attributes_t; -/* bits: descr. */ -/* 15-13 audio coding mode (0=ac3, 2=mpeg1, 3=mpeg2ext, 4=LPCM, 6=DTS, */ -/* 12 multichannel extension */ -/* 11-10 audio type (0=not spec, 1=language included) */ -/* 9- 8 audio application mode (0=not spec, 1=karaoke, 2=surround) */ -/* 7- 6 Quantization / DRC (mpeg audio: 1=DRC exists)(lpcm: 0=16bit, */ -/* 5- 4 Sample frequency fs (0=48kHz, 1=96kHz) */ -/* 2- 0 number of audio channels (n+1 channels) */ - - /* for GET_CAPABILITIES and SET_FORMAT, the latter should only set one bit */ #define AUDIO_CAP_DTS 1 #define AUDIO_CAP_LPCM 2 @@ -115,22 +94,6 @@ typedef __u16 audio_attributes_t; #define AUDIO_SET_ID _IO('o', 13) #define AUDIO_SET_MIXER _IOW('o', 14, audio_mixer_t) #define AUDIO_SET_STREAMTYPE _IO('o', 15) -#define AUDIO_SET_EXT_ID _IO('o', 16) -#define AUDIO_SET_ATTRIBUTES _IOW('o', 17, audio_attributes_t) -#define AUDIO_SET_KARAOKE _IOW('o', 18, audio_karaoke_t) - -/** - * AUDIO_GET_PTS - * - * Read the 33 bit presentation time stamp as defined - * in ITU T-REC-H.222.0 / ISO/IEC 13818-1. - * - * The PTS should belong to the currently played - * frame if possible, but may also be a value close to it - * like the PTS of the last decoded frame or the last PTS - * extracted by the PES parser. - */ -#define AUDIO_GET_PTS _IOR('o', 19, __u64) #define AUDIO_BILINGUAL_CHANNEL_SELECT _IO('o', 20) #endif /* _DVBAUDIO_H_ */ -- cgit v1.2.3 From a449938297e55e7e8958f8b48583f7d342da1930 Mon Sep 17 00:00:00 2001 From: Janosch Frank Date: Fri, 13 Jul 2018 11:28:31 +0100 Subject: KVM: s390: Add huge page enablement control General KVM huge page support on s390 has to be enabled via the kvm.hpage module parameter. Either nested or hpage can be enabled, as we currently do not support vSIE for huge backed guests. Once the vSIE support is added we will either drop the parameter or enable it as default. For a guest the feature has to be enabled through the new KVM_CAP_S390_HPAGE_1M capability and the hpage module parameter. Enabling it means that cmm can't be enabled for the vm and disables pfmf and storage key interpretation. This is due to the fact that in some cases, in upcoming patches, we have to split huge pages in the guest mapping to be able to set more granular memory protection on 4k pages. These split pages have fake page tables that are not visible to the Linux memory management which subsequently will not manage its PGSTEs, while the SIE will. Disabling these features lets us manage PGSTE data in a consistent matter and solve that problem. Signed-off-by: Janosch Frank Reviewed-by: David Hildenbrand --- Documentation/virtual/kvm/api.txt | 16 +++++++++++++++ arch/s390/kvm/kvm-s390.c | 42 +++++++++++++++++++++++++++++++++++++-- include/uapi/linux/kvm.h | 1 + 3 files changed, 57 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index d10944e619d3..cb8db4f9d097 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -4391,6 +4391,22 @@ all such vmexits. Do not enable KVM_FEATURE_PV_UNHALT if you disable HLT exits. +7.14 KVM_CAP_S390_HPAGE_1M + +Architectures: s390 +Parameters: none +Returns: 0 on success, -EINVAL if hpage module parameter was not set + or cmma is enabled + +With this capability the KVM support for memory backing with 1m pages +through hugetlbfs can be enabled for a VM. After the capability is +enabled, cmma can't be enabled anymore and pfmfi and the storage key +interpretation are disabled. If cmma has already been enabled or the +hpage module parameter is not set to 1, -EINVAL is returned. + +While it is generally possible to create a huge page backed VM without +this capability, the VM will not be able to run. + 8. Other capabilities. ---------------------- diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 662f4d8046db..f9d90337e64a 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -172,6 +172,10 @@ static int nested; module_param(nested, int, S_IRUGO); MODULE_PARM_DESC(nested, "Nested virtualization support"); +/* allow 1m huge page guest backing, if !nested */ +static int hpage; +module_param(hpage, int, 0444); +MODULE_PARM_DESC(hpage, "1m huge page backing support"); /* * For now we handle at most 16 double words as this is what the s390 base @@ -475,6 +479,11 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_S390_AIS_MIGRATION: r = 1; break; + case KVM_CAP_S390_HPAGE_1M: + r = 0; + if (hpage) + r = 1; + break; case KVM_CAP_S390_MEM_OP: r = MEM_OP_MAX_SIZE; break; @@ -678,6 +687,27 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) VM_EVENT(kvm, 3, "ENABLE: CAP_S390_GS %s", r ? "(not available)" : "(success)"); break; + case KVM_CAP_S390_HPAGE_1M: + mutex_lock(&kvm->lock); + if (kvm->created_vcpus) + r = -EBUSY; + else if (!hpage || kvm->arch.use_cmma) + r = -EINVAL; + else { + r = 0; + kvm->mm->context.allow_gmap_hpage_1m = 1; + /* + * We might have to create fake 4k page + * tables. To avoid that the hardware works on + * stale PGSTEs, we emulate these instructions. + */ + kvm->arch.use_skf = 0; + kvm->arch.use_pfmfi = 0; + } + mutex_unlock(&kvm->lock); + VM_EVENT(kvm, 3, "ENABLE: CAP_S390_HPAGE %s", + r ? "(not available)" : "(success)"); + break; case KVM_CAP_S390_USER_STSI: VM_EVENT(kvm, 3, "%s", "ENABLE: CAP_S390_USER_STSI"); kvm->arch.user_stsi = 1; @@ -725,10 +755,13 @@ static int kvm_s390_set_mem_control(struct kvm *kvm, struct kvm_device_attr *att if (!sclp.has_cmma) break; - ret = -EBUSY; VM_EVENT(kvm, 3, "%s", "ENABLE: CMMA support"); mutex_lock(&kvm->lock); - if (!kvm->created_vcpus) { + if (kvm->created_vcpus) + ret = -EBUSY; + else if (kvm->mm->context.allow_gmap_hpage_1m) + ret = -EINVAL; + else { kvm->arch.use_cmma = 1; /* Not compatible with cmma. */ kvm->arch.use_pfmfi = 0; @@ -4102,6 +4135,11 @@ static int __init kvm_s390_init(void) return -ENODEV; } + if (nested && hpage) { + pr_info("nested (vSIE) and hpage (huge page backing) can currently not be activated concurrently"); + return -EINVAL; + } + for (i = 0; i < 16; i++) kvm_s390_fac_base[i] |= S390_lowcore.stfle_fac_list[i] & nonhyp_mask(i); diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index b6270a3b38e9..b955b986b341 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -949,6 +949,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_GET_MSR_FEATURES 153 #define KVM_CAP_HYPERV_EVENTFD 154 #define KVM_CAP_HYPERV_TLBFLUSH 155 +#define KVM_CAP_S390_HPAGE_1M 156 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From cb0f32e12cded06e12ff19104eaf90c6f8310558 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Mon, 23 Jul 2018 14:07:45 -0500 Subject: scsi: target: add helper to check if dev is configured This just adds a helper function to check if a device is configured and it converts the target users to use it. The next patch will add a backend module user so those types of modules do not have to know the lio core details. Signed-off-by: Mike Christie Reviewed-by: Xiubo Li Signed-off-by: Martin K. Petersen --- drivers/target/target_core_configfs.c | 8 ++++---- drivers/target/target_core_device.c | 6 +++--- drivers/target/target_core_fabric_configfs.c | 3 ++- include/target/target_core_backend.h | 4 ++++ 4 files changed, 13 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c index 93d3ff34b614..f6b1549f4142 100644 --- a/drivers/target/target_core_configfs.c +++ b/drivers/target/target_core_configfs.c @@ -810,7 +810,7 @@ static ssize_t pi_prot_type_store(struct config_item *item, dev->transport->name); return -ENOSYS; } - if (!(dev->dev_flags & DF_CONFIGURED)) { + if (!target_dev_configured(dev)) { pr_err("DIF protection requires device to be configured\n"); return -ENODEV; } @@ -859,7 +859,7 @@ static ssize_t pi_prot_format_store(struct config_item *item, dev->transport->name); return -ENOSYS; } - if (!(dev->dev_flags & DF_CONFIGURED)) { + if (!target_dev_configured(dev)) { pr_err("DIF protection format requires device to be configured\n"); return -ENODEV; } @@ -1948,7 +1948,7 @@ static ssize_t target_dev_enable_show(struct config_item *item, char *page) { struct se_device *dev = to_device(item); - return snprintf(page, PAGE_SIZE, "%d\n", !!(dev->dev_flags & DF_CONFIGURED)); + return snprintf(page, PAGE_SIZE, "%d\n", target_dev_configured(dev)); } static ssize_t target_dev_enable_store(struct config_item *item, @@ -2473,7 +2473,7 @@ static ssize_t target_tg_pt_gp_alua_access_state_store(struct config_item *item, " tg_pt_gp ID: %hu\n", tg_pt_gp->tg_pt_gp_valid_id); return -EINVAL; } - if (!(dev->dev_flags & DF_CONFIGURED)) { + if (!target_dev_configured(dev)) { pr_err("Unable to set alua_access_state while device is" " not configured\n"); return -ENODEV; diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index 73675eec740d..47b5ef153135 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -900,7 +900,7 @@ static int target_devices_idr_iter(int id, void *p, void *data) * to allow other callers to access partially setup devices, * so we skip them here. */ - if (!(dev->dev_flags & DF_CONFIGURED)) + if (!target_dev_configured(dev)) return 0; iter->prev_item = config_item_get_unless_zero(&dev->dev_group.cg_item); @@ -940,7 +940,7 @@ int target_configure_device(struct se_device *dev) struct se_hba *hba = dev->se_hba; int ret, id; - if (dev->dev_flags & DF_CONFIGURED) { + if (target_dev_configured(dev)) { pr_err("se_dev->se_dev_ptr already set for storage" " object\n"); return -EEXIST; @@ -1045,7 +1045,7 @@ void target_free_device(struct se_device *dev) WARN_ON(!list_empty(&dev->dev_sep_list)); - if (dev->dev_flags & DF_CONFIGURED) { + if (target_dev_configured(dev)) { destroy_workqueue(dev->tmr_wq); dev->transport->destroy_device(dev); diff --git a/drivers/target/target_core_fabric_configfs.c b/drivers/target/target_core_fabric_configfs.c index 1fa436e865f9..aa2f4f632ebe 100644 --- a/drivers/target/target_core_fabric_configfs.c +++ b/drivers/target/target_core_fabric_configfs.c @@ -34,6 +34,7 @@ #include #include +#include #include #include "target_core_internal.h" @@ -642,7 +643,7 @@ static int target_fabric_port_link( } dev = container_of(to_config_group(se_dev_ci), struct se_device, dev_group); - if (!(dev->dev_flags & DF_CONFIGURED)) { + if (!target_dev_configured(dev)) { pr_err("se_device not configured yet, cannot port link\n"); return -ENODEV; } diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h index c3ac47255218..51b6f50eabee 100644 --- a/include/target/target_core_backend.h +++ b/include/target/target_core_backend.h @@ -111,6 +111,10 @@ sector_t target_to_linux_sector(struct se_device *dev, sector_t lb); bool target_configure_unmap_from_queue(struct se_dev_attrib *attrib, struct request_queue *q); +static inline bool target_dev_configured(struct se_device *se_dev) +{ + return !!(se_dev->dev_flags & DF_CONFIGURED); +} /* Only use get_unaligned_be24() if reading p - 1 is allowed. */ static inline uint32_t get_unaligned_be24(const uint8_t *const p) -- cgit v1.2.3 From 486cdf21583e5b1fad488a3e4f0a5242a31c0ffa Mon Sep 17 00:00:00 2001 From: Mathieu Xhonneux Date: Thu, 26 Jul 2018 02:10:40 +0000 Subject: bpf: add End.DT6 action to bpf_lwt_seg6_action helper The seg6local LWT provides the End.DT6 action, which allows to decapsulate an outer IPv6 header containing a Segment Routing Header (SRH), full specification is available here: https://tools.ietf.org/html/draft-filsfils-spring-srv6-network-programming-05 This patch adds this action now to the seg6local BPF interface. Since it is not mandatory that the inner IPv6 header also contains a SRH, seg6_bpf_srh_state has been extended with a pointer to a possible SRH of the outermost IPv6 header. This helps assessing if the validation must be triggered or not, and avoids some calls to ipv6_find_hdr. v3: s/1/true, s/0/false for boolean values v2: - changed true/false -> 1/0 - preempt_enable no longer called in first conditional block Signed-off-by: Mathieu Xhonneux Signed-off-by: Daniel Borkmann --- include/net/seg6_local.h | 4 ++- net/core/filter.c | 88 ++++++++++++++++++++++++++++++++---------------- net/ipv6/seg6_local.c | 50 +++++++++++++++++---------- 3 files changed, 94 insertions(+), 48 deletions(-) (limited to 'include') diff --git a/include/net/seg6_local.h b/include/net/seg6_local.h index 661fd5b4d3e0..08359e2d8b35 100644 --- a/include/net/seg6_local.h +++ b/include/net/seg6_local.h @@ -21,10 +21,12 @@ extern int seg6_lookup_nexthop(struct sk_buff *skb, struct in6_addr *nhaddr, u32 tbl_id); +extern bool seg6_bpf_has_valid_srh(struct sk_buff *skb); struct seg6_bpf_srh_state { - bool valid; + struct ipv6_sr_hdr *srh; u16 hdrlen; + bool valid; }; DECLARE_PER_CPU(struct seg6_bpf_srh_state, seg6_bpf_srh_states); diff --git a/net/core/filter.c b/net/core/filter.c index 104d560946da..7df1a0f1d1e1 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4542,26 +4542,28 @@ BPF_CALL_4(bpf_lwt_seg6_store_bytes, struct sk_buff *, skb, u32, offset, { struct seg6_bpf_srh_state *srh_state = this_cpu_ptr(&seg6_bpf_srh_states); + struct ipv6_sr_hdr *srh = srh_state->srh; void *srh_tlvs, *srh_end, *ptr; - struct ipv6_sr_hdr *srh; int srhoff = 0; - if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0) + if (srh == NULL) return -EINVAL; - srh = (struct ipv6_sr_hdr *)(skb->data + srhoff); srh_tlvs = (void *)((char *)srh + ((srh->first_segment + 1) << 4)); srh_end = (void *)((char *)srh + sizeof(*srh) + srh_state->hdrlen); ptr = skb->data + offset; if (ptr >= srh_tlvs && ptr + len <= srh_end) - srh_state->valid = 0; + srh_state->valid = false; else if (ptr < (void *)&srh->flags || ptr + len > (void *)&srh->segments) return -EFAULT; if (unlikely(bpf_try_make_writable(skb, offset + len))) return -EFAULT; + if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0) + return -EINVAL; + srh_state->srh = (struct ipv6_sr_hdr *)(skb->data + srhoff); memcpy(skb->data + offset, from, len); return 0; @@ -4577,52 +4579,78 @@ static const struct bpf_func_proto bpf_lwt_seg6_store_bytes_proto = { .arg4_type = ARG_CONST_SIZE }; -BPF_CALL_4(bpf_lwt_seg6_action, struct sk_buff *, skb, - u32, action, void *, param, u32, param_len) +static void bpf_update_srh_state(struct sk_buff *skb) { struct seg6_bpf_srh_state *srh_state = this_cpu_ptr(&seg6_bpf_srh_states); - struct ipv6_sr_hdr *srh; int srhoff = 0; - int err; - - if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0) - return -EINVAL; - srh = (struct ipv6_sr_hdr *)(skb->data + srhoff); - - if (!srh_state->valid) { - if (unlikely((srh_state->hdrlen & 7) != 0)) - return -EBADMSG; - - srh->hdrlen = (u8)(srh_state->hdrlen >> 3); - if (unlikely(!seg6_validate_srh(srh, (srh->hdrlen + 1) << 3))) - return -EBADMSG; - srh_state->valid = 1; + if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0) { + srh_state->srh = NULL; + } else { + srh_state->srh = (struct ipv6_sr_hdr *)(skb->data + srhoff); + srh_state->hdrlen = srh_state->srh->hdrlen << 3; + srh_state->valid = true; } +} + +BPF_CALL_4(bpf_lwt_seg6_action, struct sk_buff *, skb, + u32, action, void *, param, u32, param_len) +{ + struct seg6_bpf_srh_state *srh_state = + this_cpu_ptr(&seg6_bpf_srh_states); + int hdroff = 0; + int err; switch (action) { case SEG6_LOCAL_ACTION_END_X: + if (!seg6_bpf_has_valid_srh(skb)) + return -EBADMSG; if (param_len != sizeof(struct in6_addr)) return -EINVAL; return seg6_lookup_nexthop(skb, (struct in6_addr *)param, 0); case SEG6_LOCAL_ACTION_END_T: + if (!seg6_bpf_has_valid_srh(skb)) + return -EBADMSG; + if (param_len != sizeof(int)) + return -EINVAL; + return seg6_lookup_nexthop(skb, NULL, *(int *)param); + case SEG6_LOCAL_ACTION_END_DT6: + if (!seg6_bpf_has_valid_srh(skb)) + return -EBADMSG; if (param_len != sizeof(int)) return -EINVAL; + + if (ipv6_find_hdr(skb, &hdroff, IPPROTO_IPV6, NULL, NULL) < 0) + return -EBADMSG; + if (!pskb_pull(skb, hdroff)) + return -EBADMSG; + + skb_postpull_rcsum(skb, skb_network_header(skb), hdroff); + skb_reset_network_header(skb); + skb_reset_transport_header(skb); + skb->encapsulation = 0; + + bpf_compute_data_pointers(skb); + bpf_update_srh_state(skb); return seg6_lookup_nexthop(skb, NULL, *(int *)param); case SEG6_LOCAL_ACTION_END_B6: + if (srh_state->srh && !seg6_bpf_has_valid_srh(skb)) + return -EBADMSG; err = bpf_push_seg6_encap(skb, BPF_LWT_ENCAP_SEG6_INLINE, param, param_len); if (!err) - srh_state->hdrlen = - ((struct ipv6_sr_hdr *)param)->hdrlen << 3; + bpf_update_srh_state(skb); + return err; case SEG6_LOCAL_ACTION_END_B6_ENCAP: + if (srh_state->srh && !seg6_bpf_has_valid_srh(skb)) + return -EBADMSG; err = bpf_push_seg6_encap(skb, BPF_LWT_ENCAP_SEG6, param, param_len); if (!err) - srh_state->hdrlen = - ((struct ipv6_sr_hdr *)param)->hdrlen << 3; + bpf_update_srh_state(skb); + return err; default: return -EINVAL; @@ -4644,15 +4672,14 @@ BPF_CALL_3(bpf_lwt_seg6_adjust_srh, struct sk_buff *, skb, u32, offset, { struct seg6_bpf_srh_state *srh_state = this_cpu_ptr(&seg6_bpf_srh_states); + struct ipv6_sr_hdr *srh = srh_state->srh; void *srh_end, *srh_tlvs, *ptr; - struct ipv6_sr_hdr *srh; struct ipv6hdr *hdr; int srhoff = 0; int ret; - if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0) + if (unlikely(srh == NULL)) return -EINVAL; - srh = (struct ipv6_sr_hdr *)(skb->data + srhoff); srh_tlvs = (void *)((unsigned char *)srh + sizeof(*srh) + ((srh->first_segment + 1) << 4)); @@ -4682,8 +4709,11 @@ BPF_CALL_3(bpf_lwt_seg6_adjust_srh, struct sk_buff *, skb, u32, offset, hdr = (struct ipv6hdr *)skb->data; hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); + if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0) + return -EINVAL; + srh_state->srh = (struct ipv6_sr_hdr *)(skb->data + srhoff); srh_state->hdrlen += len; - srh_state->valid = 0; + srh_state->valid = false; return 0; } diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index e1025b493a18..60325dbfe88b 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -459,36 +459,57 @@ drop: DEFINE_PER_CPU(struct seg6_bpf_srh_state, seg6_bpf_srh_states); +bool seg6_bpf_has_valid_srh(struct sk_buff *skb) +{ + struct seg6_bpf_srh_state *srh_state = + this_cpu_ptr(&seg6_bpf_srh_states); + struct ipv6_sr_hdr *srh = srh_state->srh; + + if (unlikely(srh == NULL)) + return false; + + if (unlikely(!srh_state->valid)) { + if ((srh_state->hdrlen & 7) != 0) + return false; + + srh->hdrlen = (u8)(srh_state->hdrlen >> 3); + if (!seg6_validate_srh(srh, (srh->hdrlen + 1) << 3)) + return false; + + srh_state->valid = true; + } + + return true; +} + static int input_action_end_bpf(struct sk_buff *skb, struct seg6_local_lwt *slwt) { struct seg6_bpf_srh_state *srh_state = this_cpu_ptr(&seg6_bpf_srh_states); - struct seg6_bpf_srh_state local_srh_state; struct ipv6_sr_hdr *srh; - int srhoff = 0; int ret; srh = get_and_validate_srh(skb); - if (!srh) - goto drop; + if (!srh) { + kfree_skb(skb); + return -EINVAL; + } advance_nextseg(srh, &ipv6_hdr(skb)->daddr); /* preempt_disable is needed to protect the per-CPU buffer srh_state, * which is also accessed by the bpf_lwt_seg6_* helpers */ preempt_disable(); + srh_state->srh = srh; srh_state->hdrlen = srh->hdrlen << 3; - srh_state->valid = 1; + srh_state->valid = true; rcu_read_lock(); bpf_compute_data_pointers(skb); ret = bpf_prog_run_save_cb(slwt->bpf.prog, skb); rcu_read_unlock(); - local_srh_state = *srh_state; - preempt_enable(); - switch (ret) { case BPF_OK: case BPF_REDIRECT: @@ -500,24 +521,17 @@ static int input_action_end_bpf(struct sk_buff *skb, goto drop; } - if (unlikely((local_srh_state.hdrlen & 7) != 0)) - goto drop; - - if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0) - goto drop; - srh = (struct ipv6_sr_hdr *)(skb->data + srhoff); - srh->hdrlen = (u8)(local_srh_state.hdrlen >> 3); - - if (!local_srh_state.valid && - unlikely(!seg6_validate_srh(srh, (srh->hdrlen + 1) << 3))) + if (srh_state->srh && !seg6_bpf_has_valid_srh(skb)) goto drop; + preempt_enable(); if (ret != BPF_REDIRECT) seg6_lookup_nexthop(skb, NULL, 0); return dst_input(skb); drop: + preempt_enable(); kfree_skb(skb); return -EINVAL; } -- cgit v1.2.3 From d692f1138a4bac2efd2c8656ca15556b63479e82 Mon Sep 17 00:00:00 2001 From: Andrey Ignatov Date: Mon, 30 Jul 2018 17:42:28 -0700 Subject: bpf: Support bpf_get_socket_cookie in more prog types bpf_get_socket_cookie() helper can be used to identify skb that correspond to the same socket. Though socket cookie can be useful in many other use-cases where socket is available in program context. Specifically BPF_PROG_TYPE_CGROUP_SOCK_ADDR and BPF_PROG_TYPE_SOCK_OPS programs can benefit from it so that one of them can augment a value in a map prepared earlier by other program for the same socket. The patch adds support to call bpf_get_socket_cookie() from BPF_PROG_TYPE_CGROUP_SOCK_ADDR and BPF_PROG_TYPE_SOCK_OPS. It doesn't introduce new helpers. Instead it reuses same helper name bpf_get_socket_cookie() but adds support to this helper to accept `struct bpf_sock_addr` and `struct bpf_sock_ops`. Documentation in bpf.h is changed in a way that should not break automatic generation of markdown. Signed-off-by: Andrey Ignatov Acked-by: Yonghong Song Signed-off-by: Daniel Borkmann --- include/uapi/linux/bpf.h | 14 ++++++++++++++ net/core/filter.c | 28 ++++++++++++++++++++++++++++ 2 files changed, 42 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 870113916cac..0ebaaf7f3568 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1371,6 +1371,20 @@ union bpf_attr { * A 8-byte long non-decreasing number on success, or 0 if the * socket field is missing inside *skb*. * + * u64 bpf_get_socket_cookie(struct bpf_sock_addr *ctx) + * Description + * Equivalent to bpf_get_socket_cookie() helper that accepts + * *skb*, but gets socket from **struct bpf_sock_addr** contex. + * Return + * A 8-byte long non-decreasing number. + * + * u64 bpf_get_socket_cookie(struct bpf_sock_ops *ctx) + * Description + * Equivalent to bpf_get_socket_cookie() helper that accepts + * *skb*, but gets socket from **struct bpf_sock_ops** contex. + * Return + * A 8-byte long non-decreasing number. + * * u32 bpf_get_socket_uid(struct sk_buff *skb) * Return * The owner UID of the socket associated to *skb*. If the socket diff --git a/net/core/filter.c b/net/core/filter.c index 7df1a0f1d1e1..9bb9a4488e25 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3812,6 +3812,30 @@ static const struct bpf_func_proto bpf_get_socket_cookie_proto = { .arg1_type = ARG_PTR_TO_CTX, }; +BPF_CALL_1(bpf_get_socket_cookie_sock_addr, struct bpf_sock_addr_kern *, ctx) +{ + return sock_gen_cookie(ctx->sk); +} + +static const struct bpf_func_proto bpf_get_socket_cookie_sock_addr_proto = { + .func = bpf_get_socket_cookie_sock_addr, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, +}; + +BPF_CALL_1(bpf_get_socket_cookie_sock_ops, struct bpf_sock_ops_kern *, ctx) +{ + return sock_gen_cookie(ctx->sk); +} + +static const struct bpf_func_proto bpf_get_socket_cookie_sock_ops_proto = { + .func = bpf_get_socket_cookie_sock_ops, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, +}; + BPF_CALL_1(bpf_get_socket_uid, struct sk_buff *, skb) { struct sock *sk = sk_to_full_sk(skb->sk); @@ -4818,6 +4842,8 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) default: return NULL; } + case BPF_FUNC_get_socket_cookie: + return &bpf_get_socket_cookie_sock_addr_proto; default: return bpf_base_func_proto(func_id); } @@ -4960,6 +4986,8 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_sock_map_update_proto; case BPF_FUNC_sock_hash_update: return &bpf_sock_hash_update_proto; + case BPF_FUNC_get_socket_cookie: + return &bpf_get_socket_cookie_sock_ops_proto; default: return bpf_base_func_proto(func_id); } -- cgit v1.2.3 From 760c435e0f85ed19e48a90d746ce1de2cd02def7 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 19 Jul 2018 00:09:12 +0200 Subject: mtd: rawnand: make subop helpers return unsigned values A report from Colin Ian King pointed a CoverityScan issue where error values on these helpers where not checked in the drivers. These helpers can error out only in case of a software bug in driver code, not because of a runtime/hardware error. Hence, let's WARN_ON() in this case and return 0 which is harmless anyway. Fixes: 8878b126df76 ("mtd: nand: add ->exec_op() implementation") Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/nand_base.c | 44 ++++++++++++++++++++-------------------- include/linux/mtd/rawnand.h | 16 +++++++-------- 2 files changed, 30 insertions(+), 30 deletions(-) (limited to 'include') diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index c4b74630f4c5..ef10beab99f5 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -2668,8 +2668,8 @@ static bool nand_subop_instr_is_valid(const struct nand_subop *subop, return subop && instr_idx < subop->ninstrs; } -static int nand_subop_get_start_off(const struct nand_subop *subop, - unsigned int instr_idx) +static unsigned int nand_subop_get_start_off(const struct nand_subop *subop, + unsigned int instr_idx) { if (instr_idx) return 0; @@ -2688,12 +2688,12 @@ static int nand_subop_get_start_off(const struct nand_subop *subop, * * Given an address instruction, returns the offset of the first cycle to issue. */ -int nand_subop_get_addr_start_off(const struct nand_subop *subop, - unsigned int instr_idx) +unsigned int nand_subop_get_addr_start_off(const struct nand_subop *subop, + unsigned int instr_idx) { - if (!nand_subop_instr_is_valid(subop, instr_idx) || - subop->instrs[instr_idx].type != NAND_OP_ADDR_INSTR) - return -EINVAL; + if (WARN_ON(!nand_subop_instr_is_valid(subop, instr_idx) || + subop->instrs[instr_idx].type != NAND_OP_ADDR_INSTR)) + return 0; return nand_subop_get_start_off(subop, instr_idx); } @@ -2710,14 +2710,14 @@ EXPORT_SYMBOL_GPL(nand_subop_get_addr_start_off); * * Given an address instruction, returns the number of address cycle to issue. */ -int nand_subop_get_num_addr_cyc(const struct nand_subop *subop, - unsigned int instr_idx) +unsigned int nand_subop_get_num_addr_cyc(const struct nand_subop *subop, + unsigned int instr_idx) { int start_off, end_off; - if (!nand_subop_instr_is_valid(subop, instr_idx) || - subop->instrs[instr_idx].type != NAND_OP_ADDR_INSTR) - return -EINVAL; + if (WARN_ON(!nand_subop_instr_is_valid(subop, instr_idx) || + subop->instrs[instr_idx].type != NAND_OP_ADDR_INSTR)) + return 0; start_off = nand_subop_get_addr_start_off(subop, instr_idx); @@ -2742,12 +2742,12 @@ EXPORT_SYMBOL_GPL(nand_subop_get_num_addr_cyc); * * Given a data instruction, returns the offset to start from. */ -int nand_subop_get_data_start_off(const struct nand_subop *subop, - unsigned int instr_idx) +unsigned int nand_subop_get_data_start_off(const struct nand_subop *subop, + unsigned int instr_idx) { - if (!nand_subop_instr_is_valid(subop, instr_idx) || - !nand_instr_is_data(&subop->instrs[instr_idx])) - return -EINVAL; + if (WARN_ON(!nand_subop_instr_is_valid(subop, instr_idx) || + !nand_instr_is_data(&subop->instrs[instr_idx]))) + return 0; return nand_subop_get_start_off(subop, instr_idx); } @@ -2764,14 +2764,14 @@ EXPORT_SYMBOL_GPL(nand_subop_get_data_start_off); * * Returns the length of the chunk of data to send/receive. */ -int nand_subop_get_data_len(const struct nand_subop *subop, - unsigned int instr_idx) +unsigned int nand_subop_get_data_len(const struct nand_subop *subop, + unsigned int instr_idx) { int start_off = 0, end_off; - if (!nand_subop_instr_is_valid(subop, instr_idx) || - !nand_instr_is_data(&subop->instrs[instr_idx])) - return -EINVAL; + if (WARN_ON(!nand_subop_instr_is_valid(subop, instr_idx) || + !nand_instr_is_data(&subop->instrs[instr_idx]))) + return 0; start_off = nand_subop_get_data_start_off(subop, instr_idx); diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index f60fad29eae6..598d356de83f 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1007,14 +1007,14 @@ struct nand_subop { unsigned int last_instr_end_off; }; -int nand_subop_get_addr_start_off(const struct nand_subop *subop, - unsigned int op_id); -int nand_subop_get_num_addr_cyc(const struct nand_subop *subop, - unsigned int op_id); -int nand_subop_get_data_start_off(const struct nand_subop *subop, - unsigned int op_id); -int nand_subop_get_data_len(const struct nand_subop *subop, - unsigned int op_id); +unsigned int nand_subop_get_addr_start_off(const struct nand_subop *subop, + unsigned int op_id); +unsigned int nand_subop_get_num_addr_cyc(const struct nand_subop *subop, + unsigned int op_id); +unsigned int nand_subop_get_data_start_off(const struct nand_subop *subop, + unsigned int op_id); +unsigned int nand_subop_get_data_len(const struct nand_subop *subop, + unsigned int op_id); /** * struct nand_op_parser_addr_constraints - Constraints for address instructions -- cgit v1.2.3 From 7da45139d264f3b7ead04e00ebb29b189cf9826e Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 17 Jul 2018 09:08:02 +0200 Subject: mtd: rawnand: better name for the controller structure In the raw NAND core, a NAND chip is described by a nand_chip structure, while a NAND controller is described with a nand_hw_control structure which is not very meaningful. Rename this structure nand_controller. As the structure gets renamed, it is logical to also rename the core function initializing it from nand_hw_control_init() to nand_controller_init(). Lastly, the 'hwcontrol' entry of the nand_chip structure is not meaningful neither while it has the role of fallback when no controller structure is provided by the driver (the controller driver is dumb and can only control a single chip). Thus, it is renamed dummy_controller. Signed-off-by: Miquel Raynal Acked-by: Boris Brezillon --- drivers/mtd/nand/raw/atmel/nand-controller.c | 10 +++++----- drivers/mtd/nand/raw/brcmnand/brcmnand.c | 4 ++-- drivers/mtd/nand/raw/docg4.c | 4 ++-- drivers/mtd/nand/raw/fsl_elbc_nand.c | 4 ++-- drivers/mtd/nand/raw/fsl_ifc_nand.c | 4 ++-- drivers/mtd/nand/raw/jz4780_nand.c | 7 ++++--- drivers/mtd/nand/raw/marvell_nand.c | 6 +++--- drivers/mtd/nand/raw/mtk_nand.c | 2 +- drivers/mtd/nand/raw/nand_base.c | 4 ++-- drivers/mtd/nand/raw/ndfc.c | 4 ++-- drivers/mtd/nand/raw/omap2.c | 2 +- drivers/mtd/nand/raw/oxnas_nand.c | 4 ++-- drivers/mtd/nand/raw/qcom_nandc.c | 4 ++-- drivers/mtd/nand/raw/s3c2410.c | 4 ++-- drivers/mtd/nand/raw/sunxi_nand.c | 6 +++--- drivers/mtd/nand/raw/tango_nand.c | 4 ++-- drivers/mtd/nand/raw/tegra_nand.c | 6 +++--- drivers/mtd/nand/raw/txx9ndfmc.c | 4 ++-- include/linux/mtd/rawnand.h | 14 ++++++++------ 19 files changed, 50 insertions(+), 47 deletions(-) (limited to 'include') diff --git a/drivers/mtd/nand/raw/atmel/nand-controller.c b/drivers/mtd/nand/raw/atmel/nand-controller.c index 30dae4c9d439..855cc7729c43 100644 --- a/drivers/mtd/nand/raw/atmel/nand-controller.c +++ b/drivers/mtd/nand/raw/atmel/nand-controller.c @@ -216,7 +216,7 @@ struct atmel_nand_controller_caps { }; struct atmel_nand_controller { - struct nand_hw_control base; + struct nand_controller base; const struct atmel_nand_controller_caps *caps; struct device *dev; struct regmap *smc; @@ -227,7 +227,7 @@ struct atmel_nand_controller { }; static inline struct atmel_nand_controller * -to_nand_controller(struct nand_hw_control *ctl) +to_nand_controller(struct nand_controller *ctl) { return container_of(ctl, struct atmel_nand_controller, base); } @@ -239,7 +239,7 @@ struct atmel_smc_nand_controller { }; static inline struct atmel_smc_nand_controller * -to_smc_nand_controller(struct nand_hw_control *ctl) +to_smc_nand_controller(struct nand_controller *ctl) { return container_of(to_nand_controller(ctl), struct atmel_smc_nand_controller, base); @@ -263,7 +263,7 @@ struct atmel_hsmc_nand_controller { }; static inline struct atmel_hsmc_nand_controller * -to_hsmc_nand_controller(struct nand_hw_control *ctl) +to_hsmc_nand_controller(struct nand_controller *ctl) { return container_of(to_nand_controller(ctl), struct atmel_hsmc_nand_controller, base); @@ -1966,7 +1966,7 @@ static int atmel_nand_controller_init(struct atmel_nand_controller *nc, struct device_node *np = dev->of_node; int ret; - nand_hw_control_init(&nc->base); + nand_controller_init(&nc->base); INIT_LIST_HEAD(&nc->chips); nc->dev = dev; nc->caps = caps; diff --git a/drivers/mtd/nand/raw/brcmnand/brcmnand.c b/drivers/mtd/nand/raw/brcmnand/brcmnand.c index 1306aaa7a8bf..2e5efa0f9ea2 100644 --- a/drivers/mtd/nand/raw/brcmnand/brcmnand.c +++ b/drivers/mtd/nand/raw/brcmnand/brcmnand.c @@ -114,7 +114,7 @@ enum { struct brcmnand_controller { struct device *dev; - struct nand_hw_control controller; + struct nand_controller controller; void __iomem *nand_base; void __iomem *nand_fc; /* flash cache */ void __iomem *flash_dma_base; @@ -2433,7 +2433,7 @@ int brcmnand_probe(struct platform_device *pdev, struct brcmnand_soc *soc) init_completion(&ctrl->done); init_completion(&ctrl->dma_done); - nand_hw_control_init(&ctrl->controller); + nand_controller_init(&ctrl->controller); INIT_LIST_HEAD(&ctrl->host_list); /* NAND register range */ diff --git a/drivers/mtd/nand/raw/docg4.c b/drivers/mtd/nand/raw/docg4.c index bb96cb33cd6b..4dccdfba6140 100644 --- a/drivers/mtd/nand/raw/docg4.c +++ b/drivers/mtd/nand/raw/docg4.c @@ -1257,8 +1257,8 @@ static void __init init_mtd_structs(struct mtd_info *mtd) nand->ecc.strength = DOCG4_T; nand->options = NAND_BUSWIDTH_16 | NAND_NO_SUBPAGE_WRITE; nand->IO_ADDR_R = nand->IO_ADDR_W = doc->virtadr + DOC_IOSPACE_DATA; - nand->controller = &nand->hwcontrol; - nand_hw_control_init(nand->controller); + nand->controller = &nand->dummy_controller; + nand_controller_init(nand->controller); /* methods */ nand->cmdfunc = docg4_command; diff --git a/drivers/mtd/nand/raw/fsl_elbc_nand.c b/drivers/mtd/nand/raw/fsl_elbc_nand.c index 51f0b340bc0d..0aa54a949653 100644 --- a/drivers/mtd/nand/raw/fsl_elbc_nand.c +++ b/drivers/mtd/nand/raw/fsl_elbc_nand.c @@ -61,7 +61,7 @@ struct fsl_elbc_mtd { /* Freescale eLBC FCM controller information */ struct fsl_elbc_fcm_ctrl { - struct nand_hw_control controller; + struct nand_controller controller; struct fsl_elbc_mtd *chips[MAX_BANKS]; u8 __iomem *addr; /* Address of assigned FCM buffer */ @@ -879,7 +879,7 @@ static int fsl_elbc_nand_probe(struct platform_device *pdev) } elbc_fcm_ctrl->counter++; - nand_hw_control_init(&elbc_fcm_ctrl->controller); + nand_controller_init(&elbc_fcm_ctrl->controller); fsl_lbc_ctrl_dev->nand = elbc_fcm_ctrl; } else { elbc_fcm_ctrl = fsl_lbc_ctrl_dev->nand; diff --git a/drivers/mtd/nand/raw/fsl_ifc_nand.c b/drivers/mtd/nand/raw/fsl_ifc_nand.c index 75d3c951f61a..96130d91e32c 100644 --- a/drivers/mtd/nand/raw/fsl_ifc_nand.c +++ b/drivers/mtd/nand/raw/fsl_ifc_nand.c @@ -51,7 +51,7 @@ struct fsl_ifc_mtd { /* overview of the fsl ifc controller */ struct fsl_ifc_nand_ctrl { - struct nand_hw_control controller; + struct nand_controller controller; struct fsl_ifc_mtd *chips[FSL_IFC_BANK_COUNT]; void __iomem *addr; /* Address of assigned IFC buffer */ @@ -1004,7 +1004,7 @@ static int fsl_ifc_nand_probe(struct platform_device *dev) ifc_nand_ctrl->addr = NULL; fsl_ifc_ctrl_dev->nand = ifc_nand_ctrl; - nand_hw_control_init(&ifc_nand_ctrl->controller); + nand_controller_init(&ifc_nand_ctrl->controller); } else { ifc_nand_ctrl = fsl_ifc_ctrl_dev->nand; } diff --git a/drivers/mtd/nand/raw/jz4780_nand.c b/drivers/mtd/nand/raw/jz4780_nand.c index e69f6ae4c539..49841dad347c 100644 --- a/drivers/mtd/nand/raw/jz4780_nand.c +++ b/drivers/mtd/nand/raw/jz4780_nand.c @@ -44,7 +44,7 @@ struct jz4780_nand_cs { struct jz4780_nand_controller { struct device *dev; struct jz4780_bch *bch; - struct nand_hw_control controller; + struct nand_controller controller; unsigned int num_banks; struct list_head chips; int selected; @@ -65,7 +65,8 @@ static inline struct jz4780_nand_chip *to_jz4780_nand_chip(struct mtd_info *mtd) return container_of(mtd_to_nand(mtd), struct jz4780_nand_chip, chip); } -static inline struct jz4780_nand_controller *to_jz4780_nand_controller(struct nand_hw_control *ctrl) +static inline struct jz4780_nand_controller +*to_jz4780_nand_controller(struct nand_controller *ctrl) { return container_of(ctrl, struct jz4780_nand_controller, controller); } @@ -368,7 +369,7 @@ static int jz4780_nand_probe(struct platform_device *pdev) nfc->dev = dev; nfc->num_banks = num_banks; - nand_hw_control_init(&nfc->controller); + nand_controller_init(&nfc->controller); INIT_LIST_HEAD(&nfc->chips); ret = jz4780_nand_init_chips(nfc, pdev); diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c index 80a074cccb82..bd5f9a4b7b16 100644 --- a/drivers/mtd/nand/raw/marvell_nand.c +++ b/drivers/mtd/nand/raw/marvell_nand.c @@ -318,7 +318,7 @@ struct marvell_nfc_caps { * @dma_buf: 32-bit aligned buffer for DMA transfers (NFCv1 only) */ struct marvell_nfc { - struct nand_hw_control controller; + struct nand_controller controller; struct device *dev; void __iomem *regs; struct clk *core_clk; @@ -335,7 +335,7 @@ struct marvell_nfc { u8 *dma_buf; }; -static inline struct marvell_nfc *to_marvell_nfc(struct nand_hw_control *ctrl) +static inline struct marvell_nfc *to_marvell_nfc(struct nand_controller *ctrl) { return container_of(ctrl, struct marvell_nfc, controller); } @@ -2745,7 +2745,7 @@ static int marvell_nfc_probe(struct platform_device *pdev) return -ENOMEM; nfc->dev = dev; - nand_hw_control_init(&nfc->controller); + nand_controller_init(&nfc->controller); INIT_LIST_HEAD(&nfc->chips); r = platform_get_resource(pdev, IORESOURCE_MEM, 0); diff --git a/drivers/mtd/nand/raw/mtk_nand.c b/drivers/mtd/nand/raw/mtk_nand.c index e6b14b79c8a8..7bc6be3f6ec0 100644 --- a/drivers/mtd/nand/raw/mtk_nand.c +++ b/drivers/mtd/nand/raw/mtk_nand.c @@ -145,7 +145,7 @@ struct mtk_nfc_clk { }; struct mtk_nfc { - struct nand_hw_control controller; + struct nand_controller controller; struct mtk_ecc_config ecc_cfg; struct mtk_nfc_clk clk; struct mtk_ecc *ecc; diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index e545e03a214e..dcdf0f373100 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -5000,8 +5000,8 @@ static void nand_set_defaults(struct nand_chip *chip) chip->read_buf = busw ? nand_read_buf16 : nand_read_buf; if (!chip->controller) { - chip->controller = &chip->hwcontrol; - nand_hw_control_init(chip->controller); + chip->controller = &chip->dummy_controller; + nand_controller_init(chip->controller); } if (!chip->buf_align) diff --git a/drivers/mtd/nand/raw/ndfc.c b/drivers/mtd/nand/raw/ndfc.c index d8a806894937..540fa1a0ea24 100644 --- a/drivers/mtd/nand/raw/ndfc.c +++ b/drivers/mtd/nand/raw/ndfc.c @@ -39,7 +39,7 @@ struct ndfc_controller { void __iomem *ndfcbase; struct nand_chip chip; int chip_select; - struct nand_hw_control ndfc_control; + struct nand_controller ndfc_control; }; static struct ndfc_controller ndfc_ctrl[NDFC_MAX_CS]; @@ -218,7 +218,7 @@ static int ndfc_probe(struct platform_device *ofdev) ndfc = &ndfc_ctrl[cs]; ndfc->chip_select = cs; - nand_hw_control_init(&ndfc->ndfc_control); + nand_controller_init(&ndfc->ndfc_control); ndfc->ofdev = ofdev; dev_set_drvdata(&ofdev->dev, ndfc); diff --git a/drivers/mtd/nand/raw/omap2.c b/drivers/mtd/nand/raw/omap2.c index e50c64adc3c8..e943b2e5a5e2 100644 --- a/drivers/mtd/nand/raw/omap2.c +++ b/drivers/mtd/nand/raw/omap2.c @@ -145,7 +145,7 @@ static u_char bch8_vector[] = {0xf3, 0xdb, 0x14, 0x16, 0x8b, 0xd2, 0xbe, 0xcc, static u_char bch4_vector[] = {0x00, 0x6b, 0x31, 0xdd, 0x41, 0xbc, 0x10}; /* Shared among all NAND instances to synchronize access to the ECC Engine */ -static struct nand_hw_control omap_gpmc_controller = { +static struct nand_controller omap_gpmc_controller = { .lock = __SPIN_LOCK_UNLOCKED(omap_gpmc_controller.lock), .wq = __WAIT_QUEUE_HEAD_INITIALIZER(omap_gpmc_controller.wq), }; diff --git a/drivers/mtd/nand/raw/oxnas_nand.c b/drivers/mtd/nand/raw/oxnas_nand.c index d649d5944826..01b00bb69c1e 100644 --- a/drivers/mtd/nand/raw/oxnas_nand.c +++ b/drivers/mtd/nand/raw/oxnas_nand.c @@ -32,7 +32,7 @@ #define OXNAS_NAND_MAX_CHIPS 1 struct oxnas_nand_ctrl { - struct nand_hw_control base; + struct nand_controller base; void __iomem *io_base; struct clk *clk; struct nand_chip *chips[OXNAS_NAND_MAX_CHIPS]; @@ -96,7 +96,7 @@ static int oxnas_nand_probe(struct platform_device *pdev) if (!oxnas) return -ENOMEM; - nand_hw_control_init(&oxnas->base); + nand_controller_init(&oxnas->base); res = platform_get_resource(pdev, IORESOURCE_MEM, 0); oxnas->io_base = devm_ioremap_resource(&pdev->dev, res); diff --git a/drivers/mtd/nand/raw/qcom_nandc.c b/drivers/mtd/nand/raw/qcom_nandc.c index 645630953f38..aa6c3e026ef1 100644 --- a/drivers/mtd/nand/raw/qcom_nandc.c +++ b/drivers/mtd/nand/raw/qcom_nandc.c @@ -365,7 +365,7 @@ struct nandc_regs { * from all connected NAND devices pagesize */ struct qcom_nand_controller { - struct nand_hw_control controller; + struct nand_controller controller; struct list_head host_list; struct device *dev; @@ -2728,7 +2728,7 @@ static int qcom_nandc_alloc(struct qcom_nand_controller *nandc) INIT_LIST_HEAD(&nandc->desc_list); INIT_LIST_HEAD(&nandc->host_list); - nand_hw_control_init(&nandc->controller); + nand_controller_init(&nandc->controller); return 0; } diff --git a/drivers/mtd/nand/raw/s3c2410.c b/drivers/mtd/nand/raw/s3c2410.c index 5a4a68790653..e8bf64832213 100644 --- a/drivers/mtd/nand/raw/s3c2410.c +++ b/drivers/mtd/nand/raw/s3c2410.c @@ -162,7 +162,7 @@ enum s3c_nand_clk_state { */ struct s3c2410_nand_info { /* mtd info */ - struct nand_hw_control controller; + struct nand_controller controller; struct s3c2410_nand_mtd *mtds; struct s3c2410_platform_nand *platform; @@ -1094,7 +1094,7 @@ static int s3c24xx_nand_probe(struct platform_device *pdev) platform_set_drvdata(pdev, info); - nand_hw_control_init(&info->controller); + nand_controller_init(&info->controller); /* get the clock source and enable it */ diff --git a/drivers/mtd/nand/raw/sunxi_nand.c b/drivers/mtd/nand/raw/sunxi_nand.c index 4b11cd4a79be..07f3ff9a28f2 100644 --- a/drivers/mtd/nand/raw/sunxi_nand.c +++ b/drivers/mtd/nand/raw/sunxi_nand.c @@ -234,7 +234,7 @@ static inline struct sunxi_nand_chip *to_sunxi_nand(struct nand_chip *nand) * controller events */ struct sunxi_nfc { - struct nand_hw_control controller; + struct nand_controller controller; struct device *dev; void __iomem *regs; struct clk *ahb_clk; @@ -247,7 +247,7 @@ struct sunxi_nfc { struct dma_chan *dmac; }; -static inline struct sunxi_nfc *to_sunxi_nfc(struct nand_hw_control *ctrl) +static inline struct sunxi_nfc *to_sunxi_nfc(struct nand_controller *ctrl) { return container_of(ctrl, struct sunxi_nfc, controller); } @@ -2012,7 +2012,7 @@ static int sunxi_nfc_probe(struct platform_device *pdev) return -ENOMEM; nfc->dev = dev; - nand_hw_control_init(&nfc->controller); + nand_controller_init(&nfc->controller); INIT_LIST_HEAD(&nfc->chips); r = platform_get_resource(pdev, IORESOURCE_MEM, 0); diff --git a/drivers/mtd/nand/raw/tango_nand.c b/drivers/mtd/nand/raw/tango_nand.c index f2052fae21c7..dd7a26efdf4f 100644 --- a/drivers/mtd/nand/raw/tango_nand.c +++ b/drivers/mtd/nand/raw/tango_nand.c @@ -83,7 +83,7 @@ #define MAX_CS 4 struct tango_nfc { - struct nand_hw_control hw; + struct nand_controller hw; void __iomem *reg_base; void __iomem *mem_base; void __iomem *pbus_base; @@ -654,7 +654,7 @@ static int tango_nand_probe(struct platform_device *pdev) return PTR_ERR(nfc->chan); platform_set_drvdata(pdev, nfc); - nand_hw_control_init(&nfc->hw); + nand_controller_init(&nfc->hw); nfc->freq_kHz = clk_get_rate(clk) / 1000; for_each_child_of_node(pdev->dev.of_node, np) { diff --git a/drivers/mtd/nand/raw/tegra_nand.c b/drivers/mtd/nand/raw/tegra_nand.c index 56c0aa1bc81f..31c0d9ca9d23 100644 --- a/drivers/mtd/nand/raw/tegra_nand.c +++ b/drivers/mtd/nand/raw/tegra_nand.c @@ -164,7 +164,7 @@ HWSTATUS_RBSY_VALUE(NAND_STATUS_READY)) struct tegra_nand_controller { - struct nand_hw_control controller; + struct nand_controller controller; struct device *dev; void __iomem *regs; int irq; @@ -187,7 +187,7 @@ struct tegra_nand_chip { }; static inline struct tegra_nand_controller * - to_tegra_ctrl(struct nand_hw_control *hw_ctrl) + to_tegra_ctrl(struct nand_controller *hw_ctrl) { return container_of(hw_ctrl, struct tegra_nand_controller, controller); } @@ -1136,7 +1136,7 @@ static int tegra_nand_probe(struct platform_device *pdev) return -ENOMEM; ctrl->dev = &pdev->dev; - nand_hw_control_init(&ctrl->controller); + nand_controller_init(&ctrl->controller); res = platform_get_resource(pdev, IORESOURCE_MEM, 0); ctrl->regs = devm_ioremap_resource(&pdev->dev, res); diff --git a/drivers/mtd/nand/raw/txx9ndfmc.c b/drivers/mtd/nand/raw/txx9ndfmc.c index 5fe9da8b4a0a..8f5bbbac4612 100644 --- a/drivers/mtd/nand/raw/txx9ndfmc.c +++ b/drivers/mtd/nand/raw/txx9ndfmc.c @@ -73,7 +73,7 @@ struct txx9ndfmc_drvdata { void __iomem *base; unsigned char hold; /* in gbusclock */ unsigned char spw; /* in gbusclock */ - struct nand_hw_control hw_control; + struct nand_controller hw_control; }; static struct platform_device *mtd_to_platdev(struct mtd_info *mtd) @@ -303,7 +303,7 @@ static int __init txx9ndfmc_probe(struct platform_device *dev) dev_info(&dev->dev, "CLK:%ldMHz HOLD:%d SPW:%d\n", (gbusclk + 500000) / 1000000, hold, spw); - nand_hw_control_init(&drvdata->hw_control); + nand_controller_init(&drvdata->hw_control); platform_set_drvdata(dev, drvdata); txx9ndfmc_initialize(dev); diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 598d356de83f..93a2678e0f0d 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -510,20 +510,21 @@ struct nand_id { }; /** - * struct nand_hw_control - Control structure for hardware controller (e.g ECC generator) shared among independent devices + * struct nand_controller - Structure used to describe a NAND controller + * * @lock: protection lock * @active: the mtd device which holds the controller currently * @wq: wait queue to sleep on if a NAND operation is in * progress used instead of the per chip wait queue * when a hw controller is available. */ -struct nand_hw_control { +struct nand_controller { spinlock_t lock; struct nand_chip *active; wait_queue_head_t wq; }; -static inline void nand_hw_control_init(struct nand_hw_control *nfc) +static inline void nand_controller_init(struct nand_controller *nfc) { nfc->active = NULL; spin_lock_init(&nfc->lock); @@ -1197,7 +1198,8 @@ int nand_op_parser_exec_op(struct nand_chip *chip, * setting the read-retry mode. Mostly needed for MLC NAND. * @ecc: [BOARDSPECIFIC] ECC control structure * @buf_align: minimum buffer alignment required by a platform - * @hwcontrol: platform-specific hardware control structure + * @dummy_controller: dummy controller implementation for drivers that can + * only control a single chip * @erase: [REPLACEABLE] erase function * @chip_delay: [BOARDSPECIFIC] chip dependent delay for transferring * data from array to read regs (tR). @@ -1333,11 +1335,11 @@ struct nand_chip { flstate_t state; uint8_t *oob_poi; - struct nand_hw_control *controller; + struct nand_controller *controller; struct nand_ecc_ctrl ecc; unsigned long buf_align; - struct nand_hw_control hwcontrol; + struct nand_controller dummy_controller; uint8_t *bbt; struct nand_bbt_descr *bbt_td; -- cgit v1.2.3 From 05b54c7bac906c443fd0b23ab8954e0560b33e5c Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 19 Jul 2018 01:05:46 +0200 Subject: mtd: rawnand: add hooks that may be called during nand_scan() In order to remove the limitation that forbids dynamic allocation in nand_scan_ident(), we must create a path that will be the same for all controller drivers. The idea is to use nand_scan() instead of the widely used nand_scan_ident()/nand_scan_tail() couple. In order to achieve this, controller drivers will need to adjust some parameters between these two functions depending on the NAND chip wired on them. This takes the form of two new hooks (->{attach,detach}_chip()) that are placed in a new nand_controller_ops structure, which is then attached to the nand_controller object at driver initialization time. ->attach_chip() is called between nand_scan_ident() and nand_scan_tail(), and ->detach_chip() is called in the error path of nand_scan() and in nand_cleanup(). Note that some NAND controller drivers don't have a dedicated nand_controller object and instead rely on the default/dummy one embedded in nand_chip. If you're in this case and still want to initialize the controller ops, you'll have to manipulate chip->dummy_controller directly. Last but not least, it's worth mentioning that we plan to move some of the controller related hooks placed in nand_chip into nand_controller_ops to make the separation between NAND chip and NAND controller methods clearer. Signed-off-by: Miquel Raynal Acked-by: Boris Brezillon --- drivers/mtd/nand/raw/nand_base.c | 32 ++++++++++++++++++++++++++++++-- include/linux/mtd/rawnand.h | 21 +++++++++++++++++++++ 2 files changed, 51 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index dcdf0f373100..dea41fa25be1 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -6718,6 +6718,20 @@ err_free_buf: } EXPORT_SYMBOL(nand_scan_tail); +static int nand_attach(struct nand_chip *chip) +{ + if (chip->controller->ops && chip->controller->ops->attach_chip) + return chip->controller->ops->attach_chip(chip); + + return 0; +} + +static void nand_detach(struct nand_chip *chip) +{ + if (chip->controller->ops && chip->controller->ops->detach_chip) + chip->controller->ops->detach_chip(chip); +} + /** * nand_scan_with_ids - [NAND Interface] Scan for the NAND device * @mtd: MTD device structure @@ -6731,11 +6745,21 @@ EXPORT_SYMBOL(nand_scan_tail); int nand_scan_with_ids(struct mtd_info *mtd, int maxchips, struct nand_flash_dev *ids) { + struct nand_chip *chip = mtd_to_nand(mtd); int ret; ret = nand_scan_ident(mtd, maxchips, ids); - if (!ret) - ret = nand_scan_tail(mtd); + if (ret) + return ret; + + ret = nand_attach(chip); + if (ret) + return ret; + + ret = nand_scan_tail(mtd); + if (ret) + nand_detach(chip); + return ret; } EXPORT_SYMBOL(nand_scan_with_ids); @@ -6763,7 +6787,11 @@ void nand_cleanup(struct nand_chip *chip) /* Free manufacturer priv data. */ nand_manufacturer_cleanup(chip); + + /* Free controller specific allocations after chip identification */ + nand_detach(chip); } + EXPORT_SYMBOL_GPL(nand_cleanup); /** diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 93a2678e0f0d..fbd6b29cf22c 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -509,6 +509,25 @@ struct nand_id { int len; }; +/** + * struct nand_controller_ops - Controller operations + * + * @attach_chip: this method is called after the NAND detection phase after + * flash ID and MTD fields such as erase size, page size and OOB + * size have been set up. ECC requirements are available if + * provided by the NAND chip or device tree. Typically used to + * choose the appropriate ECC configuration and allocate + * associated resources. + * This hook is optional. + * @detach_chip: free all resources allocated/claimed in + * nand_controller_ops->attach_chip(). + * This hook is optional. + */ +struct nand_controller_ops { + int (*attach_chip)(struct nand_chip *chip); + void (*detach_chip)(struct nand_chip *chip); +}; + /** * struct nand_controller - Structure used to describe a NAND controller * @@ -517,11 +536,13 @@ struct nand_id { * @wq: wait queue to sleep on if a NAND operation is in * progress used instead of the per chip wait queue * when a hw controller is available. + * @ops: NAND controller operations. */ struct nand_controller { spinlock_t lock; struct nand_chip *active; wait_queue_head_t wq; + const struct nand_controller_ops *ops; }; static inline void nand_controller_init(struct nand_controller *nfc) -- cgit v1.2.3 From 98732da1a08ebb666983d469981a8b994e77d556 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 25 Jul 2018 15:31:50 +0200 Subject: mtd: rawnand: do not export nand_scan_[ident|tail]() anymore Both nand_scan_ident() and nand_scan_tail() helpers used to be called directly from controller drivers that needed to tweak some ECC-related parameters before nand_scan_tail(). This separation prevented dynamic allocations during the phase of NAND identification, which was inconvenient. All controller drivers have been moved to use nand_scan(), in conjunction with the chip->ecc.[attach|detach]_chip() hooks that actually do the required tweaking sequence between both ident/tail calls, allowing programmers to use dynamic allocation as they need all across the scanning sequence. Declare nand_scan_[ident|tail]() statically now. Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon --- drivers/mtd/nand/raw/nand_base.c | 16 +++++++++------- include/linux/mtd/rawnand.h | 18 ++++++------------ 2 files changed, 15 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index 42a7a934a17b..34ea44f90fd8 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -5924,7 +5924,7 @@ static int nand_dt_init(struct nand_chip *chip) } /** - * nand_scan_ident - [NAND Interface] Scan for the NAND device + * nand_scan_ident - Scan for the NAND device * @mtd: MTD device structure * @maxchips: number of chips to scan for * @table: alternative NAND ID table @@ -5932,9 +5932,13 @@ static int nand_dt_init(struct nand_chip *chip) * This is the first phase of the normal nand_scan() function. It reads the * flash ID and sets up MTD fields accordingly. * + * This helper used to be called directly from controller drivers that needed + * to tweak some ECC-related parameters before nand_scan_tail(). This separation + * prevented dynamic allocations during this phase which was unconvenient and + * as been banned for the benefit of the ->init_ecc()/cleanup_ecc() hooks. */ -int nand_scan_ident(struct mtd_info *mtd, int maxchips, - struct nand_flash_dev *table) +static int nand_scan_ident(struct mtd_info *mtd, int maxchips, + struct nand_flash_dev *table) { int i, nand_maf_id, nand_dev_id; struct nand_chip *chip = mtd_to_nand(mtd); @@ -6008,7 +6012,6 @@ int nand_scan_ident(struct mtd_info *mtd, int maxchips, return 0; } -EXPORT_SYMBOL(nand_scan_ident); static int nand_set_ecc_soft_ops(struct mtd_info *mtd) { @@ -6385,14 +6388,14 @@ static bool nand_ecc_strength_good(struct mtd_info *mtd) } /** - * nand_scan_tail - [NAND Interface] Scan for the NAND device + * nand_scan_tail - Scan for the NAND device * @mtd: MTD device structure * * This is the second phase of the normal nand_scan() function. It fills out * all the uninitialized function pointers with the defaults and scans for a * bad block table if appropriate. */ -int nand_scan_tail(struct mtd_info *mtd) +static int nand_scan_tail(struct mtd_info *mtd) { struct nand_chip *chip = mtd_to_nand(mtd); struct nand_ecc_ctrl *ecc = &chip->ecc; @@ -6716,7 +6719,6 @@ err_free_buf: return ret; } -EXPORT_SYMBOL(nand_scan_tail); static int nand_attach(struct nand_chip *chip) { diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index fbd6b29cf22c..71571ed23a20 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -35,17 +35,6 @@ static inline int nand_scan(struct mtd_info *mtd, int max_chips) return nand_scan_with_ids(mtd, max_chips, NULL); } -/* - * Separate phases of nand_scan(), allowing board driver to intervene - * and override command or ECC setup according to flash type. - */ -int nand_scan_ident(struct mtd_info *mtd, int max_chips, - struct nand_flash_dev *table); -int nand_scan_tail(struct mtd_info *mtd); - -/* Unregister the MTD device and free resources held by the NAND device */ -void nand_release(struct mtd_info *mtd); - /* Internal helper for board drivers which need to override command function */ void nand_wait_ready(struct mtd_info *mtd); @@ -1745,8 +1734,13 @@ int nand_read_data_op(struct nand_chip *chip, void *buf, unsigned int len, int nand_write_data_op(struct nand_chip *chip, const void *buf, unsigned int len, bool force_8bit); -/* Free resources held by the NAND device */ +/* + * Free resources held by the NAND device, must be called on error after a + * sucessful nand_scan(). + */ void nand_cleanup(struct nand_chip *chip); +/* Unregister the MTD device and calls nand_cleanup() */ +void nand_release(struct mtd_info *mtd); /* Default extended ID decoding function */ void nand_decode_ext_id(struct nand_chip *chip); -- cgit v1.2.3 From 2023f1fa216f30b1877d65be2057fbaf0bbd49b3 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 25 Jul 2018 15:31:51 +0200 Subject: mtd: rawnand: allocate model parameter dynamically Thanks to the migration of all drivers to use nand_scan() and the related nand_controller_ops, we can now allocate data during the detection phase. Let's do it first for the NAND model parameter which is allocated in nand_detect(). Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon --- drivers/mtd/nand/raw/nand_base.c | 52 +++++++++++++++++++++++++++++++--------- include/linux/mtd/rawnand.h | 2 +- 2 files changed, 42 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index 34ea44f90fd8..00e80781124a 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -5225,8 +5225,11 @@ static int nand_flash_detect_onfi(struct nand_chip *chip) sanitize_string(p->manufacturer, sizeof(p->manufacturer)); sanitize_string(p->model, sizeof(p->model)); - strncpy(chip->parameters.model, p->model, - sizeof(chip->parameters.model) - 1); + chip->parameters.model = kstrdup(p->model, GFP_KERNEL); + if (!chip->parameters.model) { + ret = -ENOMEM; + goto free_onfi_param_page; + } mtd->writesize = le32_to_cpu(p->byte_per_page); @@ -5356,8 +5359,11 @@ static int nand_flash_detect_jedec(struct nand_chip *chip) sanitize_string(p->manufacturer, sizeof(p->manufacturer)); sanitize_string(p->model, sizeof(p->model)); - strncpy(chip->parameters.model, p->model, - sizeof(chip->parameters.model) - 1); + chip->parameters.model = kstrdup(p->model, GFP_KERNEL); + if (!chip->parameters.model) { + ret = -ENOMEM; + goto free_jedec_param_page; + } mtd->writesize = le32_to_cpu(p->byte_per_page); @@ -5546,8 +5552,9 @@ static bool find_full_id_nand(struct nand_chip *chip, chip->onfi_timing_mode_default = type->onfi_timing_mode_default; - strncpy(chip->parameters.model, type->name, - sizeof(chip->parameters.model) - 1); + chip->parameters.model = kstrdup(type->name, GFP_KERNEL); + if (!chip->parameters.model) + return false; return true; } @@ -5706,8 +5713,9 @@ static int nand_detect(struct nand_chip *chip, struct nand_flash_dev *type) if (!type->name) return -ENODEV; - strncpy(chip->parameters.model, type->name, - sizeof(chip->parameters.model) - 1); + chip->parameters.model = kstrdup(type->name, GFP_KERNEL); + if (!chip->parameters.model) + return -ENOMEM; chip->chipsize = (uint64_t)type->chipsize << 20; @@ -5737,7 +5745,9 @@ ident_done: mtd->name); pr_warn("bus width %d instead of %d bits\n", busw ? 16 : 8, (chip->options & NAND_BUSWIDTH_16) ? 16 : 8); - return -EINVAL; + ret = -EINVAL; + + goto free_detect_allocation; } nand_decode_bbm_options(chip); @@ -5774,6 +5784,11 @@ ident_done: (int)(chip->chipsize >> 20), nand_is_slc(chip) ? "SLC" : "MLC", mtd->erasesize >> 10, mtd->writesize, mtd->oobsize); return 0; + +free_detect_allocation: + kfree(chip->parameters.model); + + return ret; } static const char * const nand_ecc_modes[] = { @@ -6013,6 +6028,11 @@ static int nand_scan_ident(struct mtd_info *mtd, int maxchips, return 0; } +static void nand_scan_ident_cleanup(struct nand_chip *chip) +{ + kfree(chip->parameters.model); +} + static int nand_set_ecc_soft_ops(struct mtd_info *mtd) { struct nand_chip *chip = mtd_to_nand(mtd); @@ -6760,11 +6780,18 @@ int nand_scan_with_ids(struct mtd_info *mtd, int maxchips, ret = nand_attach(chip); if (ret) - return ret; + goto cleanup_ident; ret = nand_scan_tail(mtd); if (ret) - nand_detach(chip); + goto detach_chip; + + return 0; + +detach_chip: + nand_detach(chip); +cleanup_ident: + nand_scan_ident_cleanup(chip); return ret; } @@ -6796,6 +6823,9 @@ void nand_cleanup(struct nand_chip *chip) /* Free controller specific allocations after chip identification */ nand_detach(chip); + + /* Free identification phase allocations */ + nand_scan_ident_cleanup(chip); } EXPORT_SYMBOL_GPL(nand_cleanup); diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 71571ed23a20..099fa166569a 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -476,7 +476,7 @@ struct onfi_params { */ struct nand_parameters { /* Generic parameters */ - char model[100]; + const char *model; bool supports_set_get_features; DECLARE_BITMAP(set_feature_list, ONFI_FEATURE_NUMBER); DECLARE_BITMAP(get_feature_list, ONFI_FEATURE_NUMBER); -- cgit v1.2.3 From 11785ef53228d23ec386f5fe4a34601536f0c891 Mon Sep 17 00:00:00 2001 From: Jorge Sanjuan Date: Tue, 31 Jul 2018 13:28:42 +0100 Subject: ALSA: usb-audio: Initial Power Domain support Thee USB Audio Class 3 (UAC3) introduces Power Domains as a new feature to let a host turn individual parts of an audio function to different power states via USB requests. This lets the device get to know a bit amore about what the host is up to in order to optimize power consumption efficiently. The Power Domains are optional for UAC3 configuration but all UAC3 devices shall include at least one BADD configuration where the support for Power Domains is compulsory. This patch adds a set of features/helpers to parse these power domains and change their status. Signed-off-by: Jorge Sanjuan Signed-off-by: Takashi Iwai --- include/linux/usb/audio-v3.h | 4 ++ sound/usb/Makefile | 1 + sound/usb/power.c | 104 +++++++++++++++++++++++++++++++++++++++++++ sound/usb/power.h | 19 ++++++++ 4 files changed, 128 insertions(+) create mode 100644 sound/usb/power.c (limited to 'include') diff --git a/include/linux/usb/audio-v3.h b/include/linux/usb/audio-v3.h index 334bfa6dfb47..6b708434b7f9 100644 --- a/include/linux/usb/audio-v3.h +++ b/include/linux/usb/audio-v3.h @@ -447,4 +447,8 @@ struct uac3_interrupt_data_msg { /* BADD sample rate is always fixed to 48kHz */ #define UAC3_BADD_SAMPLING_RATE 48000 +/* BADD power domains recovery times in 50us increments */ +#define UAC3_BADD_PD_RECOVER_D1D0 0x0258 /* 30ms */ +#define UAC3_BADD_PD_RECOVER_D2D0 0x1770 /* 300ms */ + #endif /* __LINUX_USB_AUDIO_V3_H */ diff --git a/sound/usb/Makefile b/sound/usb/Makefile index 05440e2df8d9..d330f74c90e6 100644 --- a/sound/usb/Makefile +++ b/sound/usb/Makefile @@ -13,6 +13,7 @@ snd-usb-audio-objs := card.o \ mixer_scarlett.o \ mixer_us16x08.o \ pcm.o \ + power.o \ proc.o \ quirks.o \ stream.o diff --git a/sound/usb/power.c b/sound/usb/power.c new file mode 100644 index 000000000000..bd303a1ba1b7 --- /dev/null +++ b/sound/usb/power.c @@ -0,0 +1,104 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * UAC3 Power Domain state management functions + */ + +#include +#include +#include +#include +#include + +#include "usbaudio.h" +#include "helper.h" +#include "power.h" + +struct snd_usb_power_domain * +snd_usb_find_power_domain(struct usb_host_interface *ctrl_iface, + unsigned char id) +{ + struct snd_usb_power_domain *pd; + void *p; + + pd = kzalloc(sizeof(*pd), GFP_KERNEL); + if (!pd) + return NULL; + + p = NULL; + while ((p = snd_usb_find_csint_desc(ctrl_iface->extra, + ctrl_iface->extralen, + p, UAC3_POWER_DOMAIN)) != NULL) { + struct uac3_power_domain_descriptor *pd_desc = p; + int i; + + for (i = 0; i < pd_desc->bNrEntities; i++) { + if (pd_desc->baEntityID[i] == id) { + pd->pd_id = pd_desc->bPowerDomainID; + pd->pd_d1d0_rec = + le16_to_cpu(pd_desc->waRecoveryTime1); + pd->pd_d2d0_rec = + le16_to_cpu(pd_desc->waRecoveryTime2); + return pd; + } + } + } + + kfree(pd); + return NULL; +} + +int snd_usb_power_domain_set(struct snd_usb_audio *chip, + struct snd_usb_power_domain *pd, + unsigned char state) +{ + struct usb_device *dev = chip->dev; + unsigned char current_state; + int err, idx; + + idx = snd_usb_ctrl_intf(chip) | (pd->pd_id << 8); + + err = snd_usb_ctl_msg(chip->dev, usb_rcvctrlpipe(chip->dev, 0), + UAC2_CS_CUR, + USB_RECIP_INTERFACE | USB_TYPE_CLASS | USB_DIR_IN, + UAC3_AC_POWER_DOMAIN_CONTROL << 8, idx, + ¤t_state, sizeof(current_state)); + if (err < 0) { + dev_err(&dev->dev, "Can't get UAC3 power state for id %d\n", + pd->pd_id); + return err; + } + + if (current_state == state) { + dev_dbg(&dev->dev, "UAC3 power domain id %d already in state %d\n", + pd->pd_id, state); + return 0; + } + + err = snd_usb_ctl_msg(chip->dev, usb_sndctrlpipe(chip->dev, 0), UAC2_CS_CUR, + USB_RECIP_INTERFACE | USB_TYPE_CLASS | USB_DIR_OUT, + UAC3_AC_POWER_DOMAIN_CONTROL << 8, idx, + &state, sizeof(state)); + if (err < 0) { + dev_err(&dev->dev, "Can't set UAC3 power state to %d for id %d\n", + state, pd->pd_id); + return err; + } + + if (state == UAC3_PD_STATE_D0) { + switch (current_state) { + case UAC3_PD_STATE_D2: + udelay(pd->pd_d2d0_rec * 50); + break; + case UAC3_PD_STATE_D1: + udelay(pd->pd_d1d0_rec * 50); + break; + default: + return -EINVAL; + } + } + + dev_dbg(&dev->dev, "UAC3 power domain id %d change to state %d\n", + pd->pd_id, state); + + return 0; +} diff --git a/sound/usb/power.h b/sound/usb/power.h index b2e25f60c5a2..6004231a7c75 100644 --- a/sound/usb/power.h +++ b/sound/usb/power.h @@ -2,6 +2,25 @@ #ifndef __USBAUDIO_POWER_H #define __USBAUDIO_POWER_H +struct snd_usb_power_domain { + int pd_id; /* UAC3 Power Domain ID */ + int pd_d1d0_rec; /* D1 to D0 recovery time */ + int pd_d2d0_rec; /* D2 to D0 recovery time */ +}; + +enum { + UAC3_PD_STATE_D0, + UAC3_PD_STATE_D1, + UAC3_PD_STATE_D2, +}; + +int snd_usb_power_domain_set(struct snd_usb_audio *chip, + struct snd_usb_power_domain *pd, + unsigned char state); +struct snd_usb_power_domain * +snd_usb_find_power_domain(struct usb_host_interface *ctrl_iface, + unsigned char id); + #ifdef CONFIG_PM int snd_usb_autoresume(struct snd_usb_audio *chip); void snd_usb_autosuspend(struct snd_usb_audio *chip); -- cgit v1.2.3 From 08fcf813281ebcf72c69487c1501ad91b7121cdb Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 31 Jul 2018 09:10:26 -0600 Subject: t10-pi: provide empty t10_pi_complete() for !CONFIG_BLK_DEV_INTEGRITY Fixes a link failure whtn BLK_DEV_INTEGRITY isn't defined. Fixes: 10c41ddd6132 ("block: move dif_prepare/dif_complete functions to block layer") Signed-off-by: Jens Axboe --- include/linux/t10-pi.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/t10-pi.h b/include/linux/t10-pi.h index 5a427c289f58..b9626aa7e90c 100644 --- a/include/linux/t10-pi.h +++ b/include/linux/t10-pi.h @@ -51,8 +51,19 @@ extern const struct blk_integrity_profile t10_pi_type1_crc; extern const struct blk_integrity_profile t10_pi_type1_ip; extern const struct blk_integrity_profile t10_pi_type3_crc; extern const struct blk_integrity_profile t10_pi_type3_ip; + +#ifdef CONFIG_BLK_DEV_INTEGRITY extern void t10_pi_prepare(struct request *rq, u8 protection_type); extern void t10_pi_complete(struct request *rq, u8 protection_type, unsigned int intervals); +#else +static inline void t10_pi_complete(struct request *rq, u8 protection_type, + unsigned int intervals) +{ +} +static inline void t10_pi_prepare(struct request *rq, u8 protection_type) +{ +} +#endif #endif -- cgit v1.2.3 From c29c2ebd2ae0066c026045a21aa33ccbfcd8bb3c Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 30 Jul 2018 20:43:51 -0700 Subject: net: update real_num_rx_queues even when !CONFIG_SYSFS We used to depend on real_num_rx_queues as a upper bound for sanity checks. For AF_XDP socket validation it's useful if the check behaves the same regardless of CONFIG_SYSFS setting. Signed-off-by: Jakub Kicinski Reviewed-by: Quentin Monnet Acked-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9c917467a2c7..3bf7e93c9e96 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3431,8 +3431,9 @@ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq); int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq); #else static inline int netif_set_real_num_rx_queues(struct net_device *dev, - unsigned int rxq) + unsigned int rxqs) { + dev->real_num_rx_queues = rxqs; return 0; } #endif -- cgit v1.2.3 From 84c6b86875e01a08a0daa6fdd4a01b36bf0bf0b2 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 30 Jul 2018 20:43:53 -0700 Subject: xsk: don't allow umem replace at stack level MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently drivers have to check if they already have a umem installed for a given queue and return an error if so. Make better use of XDP_QUERY_XSK_UMEM and move this functionality to the core. We need to keep rtnl across the calls now. Signed-off-by: Jakub Kicinski Reviewed-by: Quentin Monnet Acked-by: Björn Töpel Signed-off-by: David S. Miller --- include/linux/netdevice.h | 7 ++++--- net/xdp/xdp_umem.c | 37 ++++++++++++++++++++++++++++--------- 2 files changed, 32 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3bf7e93c9e96..282e2e95ad5b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -872,10 +872,10 @@ struct netdev_bpf { struct { struct bpf_offloaded_map *offmap; }; - /* XDP_SETUP_XSK_UMEM */ + /* XDP_QUERY_XSK_UMEM, XDP_SETUP_XSK_UMEM */ struct { - struct xdp_umem *umem; - u16 queue_id; + struct xdp_umem *umem; /* out for query*/ + u16 queue_id; /* in for query */ } xsk; }; }; @@ -3568,6 +3568,7 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, int fd, u32 flags); u32 __dev_xdp_query(struct net_device *dev, bpf_op_t xdp_op, enum bpf_netdev_command cmd); +int xdp_umem_query(struct net_device *dev, u16 queue_id); int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb); int dev_forward_skb(struct net_device *dev, struct sk_buff *skb); diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index c199d66b5f3f..911ca6d3cb5a 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -11,6 +11,8 @@ #include #include #include +#include +#include #include "xdp_umem.h" #include "xsk_queue.h" @@ -40,6 +42,21 @@ void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs) } } +int xdp_umem_query(struct net_device *dev, u16 queue_id) +{ + struct netdev_bpf bpf; + + ASSERT_RTNL(); + + memset(&bpf, 0, sizeof(bpf)); + bpf.command = XDP_QUERY_XSK_UMEM; + bpf.xsk.queue_id = queue_id; + + if (!dev->netdev_ops->ndo_bpf) + return 0; + return dev->netdev_ops->ndo_bpf(dev, &bpf) ?: !!bpf.xsk.umem; +} + int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, u32 queue_id, u16 flags) { @@ -62,28 +79,30 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, bpf.command = XDP_QUERY_XSK_UMEM; rtnl_lock(); - err = dev->netdev_ops->ndo_bpf(dev, &bpf); - rtnl_unlock(); - - if (err) - return force_zc ? -ENOTSUPP : 0; + err = xdp_umem_query(dev, queue_id); + if (err) { + err = err < 0 ? -ENOTSUPP : -EBUSY; + goto err_rtnl_unlock; + } bpf.command = XDP_SETUP_XSK_UMEM; bpf.xsk.umem = umem; bpf.xsk.queue_id = queue_id; - rtnl_lock(); err = dev->netdev_ops->ndo_bpf(dev, &bpf); - rtnl_unlock(); - if (err) - return force_zc ? err : 0; /* fail or fallback */ + goto err_rtnl_unlock; + rtnl_unlock(); dev_hold(dev); umem->dev = dev; umem->queue_id = queue_id; umem->zc = true; return 0; + +err_rtnl_unlock: + rtnl_unlock(); + return force_zc ? err : 0; /* fail or fallback */ } static void xdp_umem_clear_dev(struct xdp_umem *umem) -- cgit v1.2.3 From e6476c21447c4b17c47e476aade6facf050f31e8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 30 Jul 2018 09:45:07 +0200 Subject: net: remove bogus RCU annotations on socket.wq We never use RCU protection for it, just a lot of cargo-cult rcu_deference_protects calls. Note that we do keep the kfree_rcu call for it, as the references through struct sock are RCU protected and thus might require a grace period before freeing. Signed-off-by: Christoph Hellwig Reviewed-by: Eric Dumazet Acked-by: Paul E. McKenney Signed-off-by: David S. Miller --- include/linux/net.h | 2 +- include/net/sock.h | 2 +- net/socket.c | 10 ++++------ 3 files changed, 6 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/net.h b/include/linux/net.h index 6554d3ba4396..e0930678c8bf 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -114,7 +114,7 @@ struct socket { unsigned long flags; - struct socket_wq __rcu *wq; + struct socket_wq *wq; struct file *file; struct sock *sk; diff --git a/include/net/sock.h b/include/net/sock.h index 2afea5d1bdfe..433f45fc2d68 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1788,7 +1788,7 @@ static inline void sock_graft(struct sock *sk, struct socket *parent) { WARN_ON(parent->sk); write_lock_bh(&sk->sk_callback_lock); - sk->sk_wq = parent->wq; + rcu_assign_pointer(sk->sk_wq, parent->wq); parent->sk = sk; sk_set_socket(sk, parent); sk->sk_uid = SOCK_INODE(parent)->i_uid; diff --git a/net/socket.c b/net/socket.c index 5b7df6695f4f..475247e347ae 100644 --- a/net/socket.c +++ b/net/socket.c @@ -251,7 +251,7 @@ static struct inode *sock_alloc_inode(struct super_block *sb) init_waitqueue_head(&wq->wait); wq->fasync_list = NULL; wq->flags = 0; - RCU_INIT_POINTER(ei->socket.wq, wq); + ei->socket.wq = wq; ei->socket.state = SS_UNCONNECTED; ei->socket.flags = 0; @@ -265,11 +265,9 @@ static struct inode *sock_alloc_inode(struct super_block *sb) static void sock_destroy_inode(struct inode *inode) { struct socket_alloc *ei; - struct socket_wq *wq; ei = container_of(inode, struct socket_alloc, vfs_inode); - wq = rcu_dereference_protected(ei->socket.wq, 1); - kfree_rcu(wq, rcu); + kfree_rcu(ei->socket.wq, rcu); kmem_cache_free(sock_inode_cachep, ei); } @@ -603,7 +601,7 @@ static void __sock_release(struct socket *sock, struct inode *inode) module_put(owner); } - if (rcu_dereference_protected(sock->wq, 1)->fasync_list) + if (sock->wq->fasync_list) pr_err("%s: fasync list not empty!\n", __func__); if (!sock->file) { @@ -1181,7 +1179,7 @@ static int sock_fasync(int fd, struct file *filp, int on) return -EINVAL; lock_sock(sk); - wq = rcu_dereference_protected(sock->wq, lockdep_sock_is_held(sk)); + wq = sock->wq; fasync_helper(fd, filp, on, &wq->fasync_list); if (!wq->fasync_list) -- cgit v1.2.3 From 43bce41cf48eb51eab5ad9e0d40ed382a7bb61d7 Mon Sep 17 00:00:00 2001 From: Christian König Date: Thu, 26 Jul 2018 13:43:49 +0200 Subject: drm/scheduler: only kill entity if last user is killed v2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Note which task is using the entity and only kill it if the last user of the entity is killed. This should prevent problems when entities are leaked to child processes. v2: add missing kernel doc Signed-off-by: Christian König Reviewed-by: Andrey Grodzovsky Acked-by: Nayan Deshmukh Signed-off-by: Alex Deucher --- drivers/gpu/drm/scheduler/gpu_scheduler.c | 6 +++++- include/drm/gpu_scheduler.h | 2 ++ 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/gpu/drm/scheduler/gpu_scheduler.c b/drivers/gpu/drm/scheduler/gpu_scheduler.c index 3f2fc5e8242a..f563e4fbb4b6 100644 --- a/drivers/gpu/drm/scheduler/gpu_scheduler.c +++ b/drivers/gpu/drm/scheduler/gpu_scheduler.c @@ -275,6 +275,7 @@ static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f, long drm_sched_entity_flush(struct drm_sched_entity *entity, long timeout) { struct drm_gpu_scheduler *sched; + struct task_struct *last_user; long ret = timeout; sched = entity->rq->sched; @@ -295,7 +296,9 @@ long drm_sched_entity_flush(struct drm_sched_entity *entity, long timeout) /* For killed process disable any more IBs enqueue right now */ - if ((current->flags & PF_EXITING) && (current->exit_code == SIGKILL)) + last_user = cmpxchg(&entity->last_user, current->group_leader, NULL); + if ((!last_user || last_user == current->group_leader) && + (current->flags & PF_EXITING) && (current->exit_code == SIGKILL)) drm_sched_entity_set_rq(entity, NULL); return ret; @@ -541,6 +544,7 @@ void drm_sched_entity_push_job(struct drm_sched_job *sched_job, trace_drm_sched_job(sched_job, entity); + WRITE_ONCE(entity->last_user, current->group_leader); first = spsc_queue_push(&entity->job_queue, &sched_job->queue_node); /* first job wakes up scheduler */ diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index 091b9afcd184..21c648b0b2a1 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -66,6 +66,7 @@ enum drm_sched_priority { * @guilty: points to ctx's guilty. * @fini_status: contains the exit status in case the process was signalled. * @last_scheduled: points to the finished fence of the last scheduled job. + * @last_user: last group leader pushing a job into the entity. * * Entities will emit jobs in order to their corresponding hardware * ring, and the scheduler will alternate between entities based on @@ -85,6 +86,7 @@ struct drm_sched_entity { struct dma_fence_cb cb; atomic_t *guilty; struct dma_fence *last_scheduled; + struct task_struct *last_user; }; /** -- cgit v1.2.3 From 546c596cf5491fda1516536e049c6a36836eb884 Mon Sep 17 00:00:00 2001 From: Shunyong Yang Date: Wed, 18 Jul 2018 09:40:35 +0800 Subject: PCI: Unify PCI and normal DMA direction definitions Current DMA direction definitions in pci-dma-compat.h and dma-direction.h are mirrored in value. Unify them to enhance readability and avoid possible inconsistency. Signed-off-by: Shunyong Yang Signed-off-by: Bjorn Helgaas Cc: Joey Zheng --- include/linux/dma-direction.h | 6 ++---- include/linux/pci-dma-compat.h | 8 ++++---- 2 files changed, 6 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/dma-direction.h b/include/linux/dma-direction.h index 3649a031893a..9c96e30e6a0b 100644 --- a/include/linux/dma-direction.h +++ b/include/linux/dma-direction.h @@ -1,14 +1,12 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_DMA_DIRECTION_H #define _LINUX_DMA_DIRECTION_H -/* - * These definitions mirror those in pci.h, so they can be used - * interchangeably with their PCI_ counterparts. - */ + enum dma_data_direction { DMA_BIDIRECTIONAL = 0, DMA_TO_DEVICE = 1, DMA_FROM_DEVICE = 2, DMA_NONE = 3, }; + #endif diff --git a/include/linux/pci-dma-compat.h b/include/linux/pci-dma-compat.h index 0dd1a3f7b309..c3f1b44ade29 100644 --- a/include/linux/pci-dma-compat.h +++ b/include/linux/pci-dma-compat.h @@ -8,10 +8,10 @@ #include /* This defines the direction arg to the DMA mapping routines. */ -#define PCI_DMA_BIDIRECTIONAL 0 -#define PCI_DMA_TODEVICE 1 -#define PCI_DMA_FROMDEVICE 2 -#define PCI_DMA_NONE 3 +#define PCI_DMA_BIDIRECTIONAL DMA_BIDIRECTIONAL +#define PCI_DMA_TODEVICE DMA_TO_DEVICE +#define PCI_DMA_FROMDEVICE DMA_FROM_DEVICE +#define PCI_DMA_NONE DMA_NONE static inline void * pci_alloc_consistent(struct pci_dev *hwdev, size_t size, -- cgit v1.2.3 From bb276262e88dae52cc717bb636b7468f66bb234e Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Fri, 27 Jul 2018 11:33:13 -0700 Subject: mtd: spi-nor: only apply reset hacks to broken hardware Commit 59b356ffd0b0 ("mtd: m25p80: restore the status of SPI flash when exiting") is the latest from a long history of attempts to add reboot handling to handle stateful addressing modes on SPI flash. Some prior mostly-related discussions: http://lists.infradead.org/pipermail/linux-mtd/2013-March/046343.html [PATCH 1/3] mtd: m25p80: utilize dedicated 4-byte addressing commands http://lists.infradead.org/pipermail/barebox/2014-September/020682.html [RFC] MTD m25p80 3-byte addressing and boot problem http://lists.infradead.org/pipermail/linux-mtd/2015-February/057683.html [PATCH 2/2] m25p80: if supported put chip to deep power down if not used Previously, attempts to add reboot-time software reset handling were rejected, but the latest attempt was not. Quick summary of the problem: Some systems (e.g., boot ROM or bootloader) assume that they can read initial boot code from their SPI flash using 3-byte addressing. If the flash is left in 4-byte mode after reset, these systems won't boot. The above patch provided a shutdown/remove hook to attempt to reset the addressing mode before we reboot. Notably, this patch misses out on huge classes of unexpected reboots (e.g., crashes, watchdog resets). Unfortunately, it is essentially impossible to solve this problem 100%: if your system doesn't know how to reset the SPI flash to power-on defaults at initialization time, no amount of software can really rescue you -- there will always be a chance of some unexpected reset that leaves your flash in an addressing mode that your boot sequence didn't expect. While it is not directly harmful to perform hacks like the aforementioned commit on all 4-byte addressing flash, a properly-designed system should not need the hack -- and in fact, providing this hack may mask the fact that a given system is indeed broken. So this patch attempts to apply this unsound hack more narrowly, providing a strong suggestion to developers and system designers that this is truly a hack. With luck, system designers can catch their errors early on in their development cycle, rather than applying this hack long term. But apparently enough systems are out in the wild that we still have to provide this hack. Document a new device tree property to denote systems that do not have a proper hardware (or software) reset mechanism, and apply the hack (with a loud warning) only in this case. Signed-off-by: Brian Norris Reviewed-by: Guenter Roeck Signed-off-by: Boris Brezillon --- .../devicetree/bindings/mtd/jedec,spi-nor.txt | 9 +++++++++ drivers/mtd/spi-nor/spi-nor.c | 18 ++++++++++++++++-- include/linux/mtd/spi-nor.h | 1 + 3 files changed, 26 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt b/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt index 956bb046e599..f03be904d3c2 100644 --- a/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt +++ b/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt @@ -69,6 +69,15 @@ Optional properties: all chips and support for it can not be detected at runtime. Refer to your chips' datasheet to check if this is supported by your chip. +- broken-flash-reset : Some flash devices utilize stateful addressing modes + (e.g., for 32-bit addressing) which need to be managed + carefully by a system. Because these sorts of flash don't + have a standardized software reset command, and because some + systems don't toggle the flash RESET# pin upon system reset + (if the pin even exists at all), there are systems which + cannot reboot properly if the flash is left in the "wrong" + state. This boolean flag can be used on such systems, to + denote the absence of a reliable reset mechanism. Example: diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c index d9c368c44194..f028277fb1ce 100644 --- a/drivers/mtd/spi-nor/spi-nor.c +++ b/drivers/mtd/spi-nor/spi-nor.c @@ -2757,8 +2757,18 @@ static int spi_nor_init(struct spi_nor *nor) if ((nor->addr_width == 4) && (JEDEC_MFR(nor->info) != SNOR_MFR_SPANSION) && - !(nor->info->flags & SPI_NOR_4B_OPCODES)) + !(nor->info->flags & SPI_NOR_4B_OPCODES)) { + /* + * If the RESET# pin isn't hooked up properly, or the system + * otherwise doesn't perform a reset command in the boot + * sequence, it's impossible to 100% protect against unexpected + * reboots (e.g., crashes). Warn the user (or hopefully, system + * designer) that this is bad. + */ + WARN_ONCE(nor->flags & SNOR_F_BROKEN_RESET, + "enabling reset hack; may not recover from unexpected reboots\n"); set_4byte(nor, nor->info, 1); + } return 0; } @@ -2781,7 +2791,8 @@ void spi_nor_restore(struct spi_nor *nor) /* restore the addressing mode */ if ((nor->addr_width == 4) && (JEDEC_MFR(nor->info) != SNOR_MFR_SPANSION) && - !(nor->info->flags & SPI_NOR_4B_OPCODES)) + !(nor->info->flags & SPI_NOR_4B_OPCODES) && + (nor->flags & SNOR_F_BROKEN_RESET)) set_4byte(nor, nor->info, 0); } EXPORT_SYMBOL_GPL(spi_nor_restore); @@ -2911,6 +2922,9 @@ int spi_nor_scan(struct spi_nor *nor, const char *name, params.hwcaps.mask |= SNOR_HWCAPS_READ_FAST; } + if (of_property_read_bool(np, "broken-flash-reset")) + nor->flags |= SNOR_F_BROKEN_RESET; + /* Some devices cannot do fast-read, no matter what DT tells us */ if (info->flags & SPI_NOR_NO_FR) params.hwcaps.mask &= ~SNOR_HWCAPS_READ_FAST; diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index e60da0d34cc1..c922e97f205a 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -235,6 +235,7 @@ enum spi_nor_option_flags { SNOR_F_S3AN_ADDR_DEFAULT = BIT(3), SNOR_F_READY_XSR_RDY = BIT(4), SNOR_F_USE_CLSR = BIT(5), + SNOR_F_BROKEN_RESET = BIT(6), }; /** -- cgit v1.2.3 From 3d3fe3c05d5a17ebdf55b936c51017c127c0ed44 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 25 Jul 2018 15:31:52 +0200 Subject: mtd: rawnand: allocate dynamically ONFI parameters during detection Now that it is possible to do dynamic allocations during the identification phase, convert the onfi_params structure (which is only needed with ONFI compliant chips) into a pointer that will be allocated only if needed. Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon --- drivers/mtd/nand/raw/nand_base.c | 54 +++++++++++++++++++++++-------------- drivers/mtd/nand/raw/nand_micron.c | 7 ++--- drivers/mtd/nand/raw/nand_timings.c | 12 ++++----- include/linux/mtd/rawnand.h | 6 ++--- 4 files changed, 47 insertions(+), 32 deletions(-) (limited to 'include') diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index 00e80781124a..d527e448ce19 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -5151,6 +5151,8 @@ static int nand_flash_detect_onfi(struct nand_chip *chip) { struct mtd_info *mtd = nand_to_mtd(chip); struct nand_onfi_params *p; + struct onfi_params *onfi; + int onfi_version = 0; char id[4]; int i, ret, val; @@ -5206,21 +5208,19 @@ static int nand_flash_detect_onfi(struct nand_chip *chip) /* Check version */ val = le16_to_cpu(p->revision); if (val & ONFI_VERSION_2_3) - chip->parameters.onfi.version = 23; + onfi_version = 23; else if (val & ONFI_VERSION_2_2) - chip->parameters.onfi.version = 22; + onfi_version = 22; else if (val & ONFI_VERSION_2_1) - chip->parameters.onfi.version = 21; + onfi_version = 21; else if (val & ONFI_VERSION_2_0) - chip->parameters.onfi.version = 20; + onfi_version = 20; else if (val & ONFI_VERSION_1_0) - chip->parameters.onfi.version = 10; + onfi_version = 10; - if (!chip->parameters.onfi.version) { + if (!onfi_version) { pr_info("unsupported ONFI version: %d\n", val); goto free_onfi_param_page; - } else { - ret = 1; } sanitize_string(p->manufacturer, sizeof(p->manufacturer)); @@ -5257,7 +5257,7 @@ static int nand_flash_detect_onfi(struct nand_chip *chip) if (p->ecc_bits != 0xff) { chip->ecc_strength_ds = p->ecc_bits; chip->ecc_step_ds = 512; - } else if (chip->parameters.onfi.version >= 21 && + } else if (onfi_version >= 21 && (le16_to_cpu(p->features) & ONFI_FEATURE_EXT_PARAM_PAGE)) { /* @@ -5284,19 +5284,33 @@ static int nand_flash_detect_onfi(struct nand_chip *chip) bitmap_set(chip->parameters.set_feature_list, ONFI_FEATURE_ADDR_TIMING_MODE, 1); } - chip->parameters.onfi.tPROG = le16_to_cpu(p->t_prog); - chip->parameters.onfi.tBERS = le16_to_cpu(p->t_bers); - chip->parameters.onfi.tR = le16_to_cpu(p->t_r); - chip->parameters.onfi.tCCS = le16_to_cpu(p->t_ccs); - chip->parameters.onfi.async_timing_mode = - le16_to_cpu(p->async_timing_mode); - chip->parameters.onfi.vendor_revision = - le16_to_cpu(p->vendor_revision); - memcpy(chip->parameters.onfi.vendor, p->vendor, - sizeof(p->vendor)); + onfi = kzalloc(sizeof(*onfi), GFP_KERNEL); + if (!onfi) { + ret = -ENOMEM; + goto free_model; + } + + onfi->version = onfi_version; + onfi->tPROG = le16_to_cpu(p->t_prog); + onfi->tBERS = le16_to_cpu(p->t_bers); + onfi->tR = le16_to_cpu(p->t_r); + onfi->tCCS = le16_to_cpu(p->t_ccs); + onfi->async_timing_mode = le16_to_cpu(p->async_timing_mode); + onfi->vendor_revision = le16_to_cpu(p->vendor_revision); + memcpy(onfi->vendor, p->vendor, sizeof(p->vendor)); + chip->parameters.onfi = onfi; + + /* Identification done, free the full ONFI parameter page and exit */ + kfree(p); + + return 1; + +free_model: + kfree(chip->parameters.model); free_onfi_param_page: kfree(p); + return ret; } @@ -5693,7 +5707,6 @@ static int nand_detect(struct nand_chip *chip, struct nand_flash_dev *type) } } - chip->parameters.onfi.version = 0; if (!type->name || !type->pagesize) { /* Check if the chip is ONFI compliant */ ret = nand_flash_detect_onfi(chip); @@ -6031,6 +6044,7 @@ static int nand_scan_ident(struct mtd_info *mtd, int maxchips, static void nand_scan_ident_cleanup(struct nand_chip *chip) { kfree(chip->parameters.model); + kfree(chip->parameters.onfi); } static int nand_set_ecc_soft_ops(struct mtd_info *mtd) diff --git a/drivers/mtd/nand/raw/nand_micron.c b/drivers/mtd/nand/raw/nand_micron.c index 656947d91841..f5dc0a7a2456 100644 --- a/drivers/mtd/nand/raw/nand_micron.c +++ b/drivers/mtd/nand/raw/nand_micron.c @@ -88,9 +88,10 @@ static int micron_nand_setup_read_retry(struct mtd_info *mtd, int retry_mode) static int micron_nand_onfi_init(struct nand_chip *chip) { struct nand_parameters *p = &chip->parameters; - struct nand_onfi_vendor_micron *micron = (void *)p->onfi.vendor; - if (chip->parameters.onfi.version && p->onfi.vendor_revision) { + if (p->onfi) { + struct nand_onfi_vendor_micron *micron = (void *)p->onfi->vendor; + chip->read_retries = micron->read_retry_options; chip->setup_read_retry = micron_nand_setup_read_retry; } @@ -382,7 +383,7 @@ static int micron_supports_on_die_ecc(struct nand_chip *chip) u8 id[5]; int ret; - if (!chip->parameters.onfi.version) + if (!chip->parameters.onfi) return MICRON_ON_DIE_UNSUPPORTED; if (chip->bits_per_cell != 1) diff --git a/drivers/mtd/nand/raw/nand_timings.c b/drivers/mtd/nand/raw/nand_timings.c index 9bb599106a31..ebc7b5f76f77 100644 --- a/drivers/mtd/nand/raw/nand_timings.c +++ b/drivers/mtd/nand/raw/nand_timings.c @@ -294,6 +294,7 @@ int onfi_fill_data_interface(struct nand_chip *chip, int timing_mode) { struct nand_data_interface *iface = &chip->data_interface; + struct onfi_params *onfi = chip->parameters.onfi; if (type != NAND_SDR_IFACE) return -EINVAL; @@ -308,17 +309,16 @@ int onfi_fill_data_interface(struct nand_chip *chip, * tPROG, tBERS, tR and tCCS. * These information are part of the ONFI parameter page. */ - if (chip->parameters.onfi.version) { - struct nand_parameters *params = &chip->parameters; + if (onfi) { struct nand_sdr_timings *timings = &iface->timings.sdr; /* microseconds -> picoseconds */ - timings->tPROG_max = 1000000ULL * params->onfi.tPROG; - timings->tBERS_max = 1000000ULL * params->onfi.tBERS; - timings->tR_max = 1000000ULL * params->onfi.tR; + timings->tPROG_max = 1000000ULL * onfi->tPROG; + timings->tBERS_max = 1000000ULL * onfi->tBERS; + timings->tR_max = 1000000ULL * onfi->tR; /* nanoseconds -> picoseconds */ - timings->tCCS_min = 1000UL * params->onfi.tCCS; + timings->tCCS_min = 1000UL * onfi->tCCS; } else { struct nand_sdr_timings *timings = &iface->timings.sdr; /* diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 099fa166569a..efb2345359bb 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -482,7 +482,7 @@ struct nand_parameters { DECLARE_BITMAP(get_feature_list, ONFI_FEATURE_NUMBER); /* ONFI parameters */ - struct onfi_params onfi; + struct onfi_params *onfi; }; /* The maximum expected count of bytes in the NAND ID sequence */ @@ -1618,10 +1618,10 @@ struct platform_nand_data { /* return the supported asynchronous timing mode. */ static inline int onfi_get_async_timing_mode(struct nand_chip *chip) { - if (!chip->parameters.onfi.version) + if (!chip->parameters.onfi) return ONFI_TIMING_MODE_UNKNOWN; - return chip->parameters.onfi.async_timing_mode; + return chip->parameters.onfi->async_timing_mode; } int onfi_fill_data_interface(struct nand_chip *chip, -- cgit v1.2.3 From 4764c0da69dc500791c840c88dfd940d13b452e7 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 23 Jul 2018 17:18:37 +0100 Subject: rxrpc: Trace packet transmission Trace successful packet transmission (kernel_sendmsg() succeeded, that is) in AF_RXRPC. We can share the enum that defines the transmission points with the trace_rxrpc_tx_fail() tracepoint, so rename its constants to be applicable to both. Also, save the internal call->debug_id in the rxrpc_channel struct so that it can be used in retransmission trace lines. Signed-off-by: David Howells --- include/trace/events/rxrpc.h | 107 +++++++++++++++++++++++++++++-------------- net/rxrpc/ar-internal.h | 1 + net/rxrpc/conn_client.c | 1 + net/rxrpc/conn_event.c | 13 ++++-- net/rxrpc/input.c | 11 ++++- net/rxrpc/local_event.c | 5 +- net/rxrpc/output.c | 32 ++++++++++--- net/rxrpc/rxkad.c | 7 ++- 8 files changed, 127 insertions(+), 50 deletions(-) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 4fff00e9da8a..2aa6f615b60d 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -211,18 +211,18 @@ enum rxrpc_congest_change { rxrpc_cong_saw_nack, }; -enum rxrpc_tx_fail_trace { - rxrpc_tx_fail_call_abort, - rxrpc_tx_fail_call_ack, - rxrpc_tx_fail_call_data_frag, - rxrpc_tx_fail_call_data_nofrag, - rxrpc_tx_fail_call_final_resend, - rxrpc_tx_fail_conn_abort, - rxrpc_tx_fail_conn_challenge, - rxrpc_tx_fail_conn_response, - rxrpc_tx_fail_reject, - rxrpc_tx_fail_version_keepalive, - rxrpc_tx_fail_version_reply, +enum rxrpc_tx_point { + rxrpc_tx_point_call_abort, + rxrpc_tx_point_call_ack, + rxrpc_tx_point_call_data_frag, + rxrpc_tx_point_call_data_nofrag, + rxrpc_tx_point_call_final_resend, + rxrpc_tx_point_conn_abort, + rxrpc_tx_point_rxkad_challenge, + rxrpc_tx_point_rxkad_response, + rxrpc_tx_point_reject, + rxrpc_tx_point_version_keepalive, + rxrpc_tx_point_version_reply, }; #endif /* end __RXRPC_DECLARE_TRACE_ENUMS_ONCE_ONLY */ @@ -452,18 +452,18 @@ enum rxrpc_tx_fail_trace { EM(RXRPC_CALL_LOCAL_ERROR, "LocalError") \ E_(RXRPC_CALL_NETWORK_ERROR, "NetError") -#define rxrpc_tx_fail_traces \ - EM(rxrpc_tx_fail_call_abort, "CallAbort") \ - EM(rxrpc_tx_fail_call_ack, "CallAck") \ - EM(rxrpc_tx_fail_call_data_frag, "CallDataFrag") \ - EM(rxrpc_tx_fail_call_data_nofrag, "CallDataNofrag") \ - EM(rxrpc_tx_fail_call_final_resend, "CallFinalResend") \ - EM(rxrpc_tx_fail_conn_abort, "ConnAbort") \ - EM(rxrpc_tx_fail_conn_challenge, "ConnChall") \ - EM(rxrpc_tx_fail_conn_response, "ConnResp") \ - EM(rxrpc_tx_fail_reject, "Reject") \ - EM(rxrpc_tx_fail_version_keepalive, "VerKeepalive") \ - E_(rxrpc_tx_fail_version_reply, "VerReply") +#define rxrpc_tx_points \ + EM(rxrpc_tx_point_call_abort, "CallAbort") \ + EM(rxrpc_tx_point_call_ack, "CallAck") \ + EM(rxrpc_tx_point_call_data_frag, "CallDataFrag") \ + EM(rxrpc_tx_point_call_data_nofrag, "CallDataNofrag") \ + EM(rxrpc_tx_point_call_final_resend, "CallFinalResend") \ + EM(rxrpc_tx_point_conn_abort, "ConnAbort") \ + EM(rxrpc_tx_point_reject, "Reject") \ + EM(rxrpc_tx_point_rxkad_challenge, "RxkadChall") \ + EM(rxrpc_tx_point_rxkad_response, "RxkadResp") \ + EM(rxrpc_tx_point_version_keepalive, "VerKeepalive") \ + E_(rxrpc_tx_point_version_reply, "VerReply") /* * Export enum symbols via userspace. @@ -488,7 +488,7 @@ rxrpc_propose_ack_traces; rxrpc_propose_ack_outcomes; rxrpc_congest_modes; rxrpc_congest_changes; -rxrpc_tx_fail_traces; +rxrpc_tx_points; /* * Now redefine the EM() and E_() macros to map the enums to the strings that @@ -801,7 +801,7 @@ TRACE_EVENT(rxrpc_transmit, ); TRACE_EVENT(rxrpc_rx_data, - TP_PROTO(struct rxrpc_call *call, rxrpc_seq_t seq, + TP_PROTO(unsigned int call, rxrpc_seq_t seq, rxrpc_serial_t serial, u8 flags, u8 anno), TP_ARGS(call, seq, serial, flags, anno), @@ -815,7 +815,7 @@ TRACE_EVENT(rxrpc_rx_data, ), TP_fast_assign( - __entry->call = call->debug_id; + __entry->call = call; __entry->seq = seq; __entry->serial = serial; __entry->flags = flags; @@ -918,6 +918,37 @@ TRACE_EVENT(rxrpc_rx_rwind_change, __entry->wake ? " wake" : "") ); +TRACE_EVENT(rxrpc_tx_packet, + TP_PROTO(unsigned int call_id, struct rxrpc_wire_header *whdr, + enum rxrpc_tx_point where), + + TP_ARGS(call_id, whdr, where), + + TP_STRUCT__entry( + __field(unsigned int, call ) + __field(enum rxrpc_tx_point, where ) + __field_struct(struct rxrpc_wire_header, whdr ) + ), + + TP_fast_assign( + __entry->call = call_id; + memcpy(&__entry->whdr, whdr, sizeof(__entry->whdr)); + ), + + TP_printk("c=%08x %08x:%08x:%08x:%04x %08x %08x %02x %02x %s %s", + __entry->call, + ntohl(__entry->whdr.epoch), + ntohl(__entry->whdr.cid), + ntohl(__entry->whdr.callNumber), + ntohs(__entry->whdr.serviceId), + ntohl(__entry->whdr.serial), + ntohl(__entry->whdr.seq), + __entry->whdr.type, __entry->whdr.flags, + __entry->whdr.type <= 15 ? + __print_symbolic(__entry->whdr.type, rxrpc_pkts) : "?UNK", + __print_symbolic(__entry->where, rxrpc_tx_points)) + ); + TRACE_EVENT(rxrpc_tx_data, TP_PROTO(struct rxrpc_call *call, rxrpc_seq_t seq, rxrpc_serial_t serial, u8 flags, bool retrans, bool lose), @@ -928,6 +959,8 @@ TRACE_EVENT(rxrpc_tx_data, __field(unsigned int, call ) __field(rxrpc_seq_t, seq ) __field(rxrpc_serial_t, serial ) + __field(u32, cid ) + __field(u32, call_id ) __field(u8, flags ) __field(bool, retrans ) __field(bool, lose ) @@ -935,6 +968,8 @@ TRACE_EVENT(rxrpc_tx_data, TP_fast_assign( __entry->call = call->debug_id; + __entry->cid = call->cid; + __entry->call_id = call->call_id; __entry->seq = seq; __entry->serial = serial; __entry->flags = flags; @@ -942,8 +977,10 @@ TRACE_EVENT(rxrpc_tx_data, __entry->lose = lose; ), - TP_printk("c=%08x DATA %08x q=%08x fl=%02x%s%s", + TP_printk("c=%08x DATA %08x:%08x %08x q=%08x fl=%02x%s%s", __entry->call, + __entry->cid, + __entry->call_id, __entry->serial, __entry->seq, __entry->flags, @@ -952,7 +989,7 @@ TRACE_EVENT(rxrpc_tx_data, ); TRACE_EVENT(rxrpc_tx_ack, - TP_PROTO(struct rxrpc_call *call, rxrpc_serial_t serial, + TP_PROTO(unsigned int call, rxrpc_serial_t serial, rxrpc_seq_t ack_first, rxrpc_serial_t ack_serial, u8 reason, u8 n_acks), @@ -968,7 +1005,7 @@ TRACE_EVENT(rxrpc_tx_ack, ), TP_fast_assign( - __entry->call = call ? call->debug_id : 0; + __entry->call = call; __entry->serial = serial; __entry->ack_first = ack_first; __entry->ack_serial = ack_serial; @@ -1434,29 +1471,29 @@ TRACE_EVENT(rxrpc_rx_icmp, TRACE_EVENT(rxrpc_tx_fail, TP_PROTO(unsigned int debug_id, rxrpc_serial_t serial, int ret, - enum rxrpc_tx_fail_trace what), + enum rxrpc_tx_point where), - TP_ARGS(debug_id, serial, ret, what), + TP_ARGS(debug_id, serial, ret, where), TP_STRUCT__entry( __field(unsigned int, debug_id ) __field(rxrpc_serial_t, serial ) __field(int, ret ) - __field(enum rxrpc_tx_fail_trace, what ) + __field(enum rxrpc_tx_point, where ) ), TP_fast_assign( __entry->debug_id = debug_id; __entry->serial = serial; __entry->ret = ret; - __entry->what = what; + __entry->where = where; ), TP_printk("c=%08x r=%x ret=%d %s", __entry->debug_id, __entry->serial, __entry->ret, - __print_symbolic(__entry->what, rxrpc_tx_fail_traces)) + __print_symbolic(__entry->where, rxrpc_tx_points)) ); TRACE_EVENT(rxrpc_call_reset, diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 5fb7d3254d9e..7eee955a768a 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -420,6 +420,7 @@ struct rxrpc_connection { struct rxrpc_channel { unsigned long final_ack_at; /* Time at which to issue final ACK */ struct rxrpc_call __rcu *call; /* Active call */ + unsigned int call_debug_id; /* call->debug_id */ u32 call_id; /* ID of current call */ u32 call_counter; /* Call ID counter */ u32 last_call; /* ID of last call */ diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index e4bfbd7e48a8..f8f37188a932 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -590,6 +590,7 @@ static void rxrpc_activate_one_channel(struct rxrpc_connection *conn, */ smp_wmb(); chan->call_id = call_id; + chan->call_debug_id = call->debug_id; rcu_assign_pointer(chan->call, call); wake_up(&call->waitq); } diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index d46a68807f08..84d40ba9856f 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -129,7 +129,7 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, _proto("Tx ABORT %%%u { %d } [re]", serial, conn->local_abort); break; case RXRPC_PACKET_TYPE_ACK: - trace_rxrpc_tx_ack(NULL, serial, + trace_rxrpc_tx_ack(chan->call_debug_id, serial, ntohl(pkt.ack.firstPacket), ntohl(pkt.ack.serial), pkt.ack.reason, 0); @@ -140,8 +140,11 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, ioc, len); conn->params.peer->last_tx_at = ktime_get_real(); if (ret < 0) - trace_rxrpc_tx_fail(conn->debug_id, serial, ret, - rxrpc_tx_fail_call_final_resend); + trace_rxrpc_tx_fail(chan->call_debug_id, serial, ret, + rxrpc_tx_point_call_final_resend); + else + trace_rxrpc_tx_packet(chan->call_debug_id, &pkt.whdr, + rxrpc_tx_point_call_final_resend); _leave(""); } @@ -242,11 +245,13 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn, ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len); if (ret < 0) { trace_rxrpc_tx_fail(conn->debug_id, serial, ret, - rxrpc_tx_fail_conn_abort); + rxrpc_tx_point_conn_abort); _debug("sendmsg failed: %d", ret); return -EAGAIN; } + trace_rxrpc_tx_packet(conn->debug_id, &whdr, rxrpc_tx_point_conn_abort); + conn->params.peer->last_tx_at = ktime_get_real(); _leave(" = 0"); diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 608d078a4981..8989d760b6b2 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -496,7 +496,7 @@ next_subpacket: return rxrpc_proto_abort("LSA", call, seq); } - trace_rxrpc_rx_data(call, seq, serial, flags, annotation); + trace_rxrpc_rx_data(call->debug_id, seq, serial, flags, annotation); if (before_eq(seq, hard_ack)) { ack = RXRPC_ACK_DUPLICATE; ack_serial = serial; @@ -592,6 +592,10 @@ ack: rxrpc_propose_ACK(call, ack, skew, ack_serial, immediate_ack, true, rxrpc_propose_ack_input_data); + else + rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, skew, serial, + false, true, + rxrpc_propose_ack_input_data); if (sp->hdr.seq == READ_ONCE(call->rx_hard_ack) + 1) rxrpc_notify_socket(call); @@ -1262,6 +1266,11 @@ void rxrpc_data_ready(struct sock *udp_sk) /* But otherwise we need to retransmit the final packet * from data cached in the connection record. */ + if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA) + trace_rxrpc_rx_data(chan->call_debug_id, + sp->hdr.seq, + sp->hdr.serial, + sp->hdr.flags, 0); rxrpc_post_packet_to_conn(conn, skb); goto out_unlock; } diff --git a/net/rxrpc/local_event.c b/net/rxrpc/local_event.c index 8325f1b86840..13bd8a4dfac7 100644 --- a/net/rxrpc/local_event.c +++ b/net/rxrpc/local_event.c @@ -72,7 +72,10 @@ static void rxrpc_send_version_request(struct rxrpc_local *local, ret = kernel_sendmsg(local->socket, &msg, iov, 2, len); if (ret < 0) trace_rxrpc_tx_fail(local->debug_id, 0, ret, - rxrpc_tx_fail_version_reply); + rxrpc_tx_point_version_reply); + else + trace_rxrpc_tx_packet(local->debug_id, &whdr, + rxrpc_tx_point_version_reply); _leave(""); } diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index f03de1c59ba3..801dbf3d3478 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -183,7 +183,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, serial = atomic_inc_return(&conn->serial); pkt->whdr.serial = htonl(serial); - trace_rxrpc_tx_ack(call, serial, + trace_rxrpc_tx_ack(call->debug_id, serial, ntohl(pkt->ack.firstPacket), ntohl(pkt->ack.serial), pkt->ack.reason, pkt->ack.nAcks); @@ -212,7 +212,10 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, conn->params.peer->last_tx_at = ktime_get_real(); if (ret < 0) trace_rxrpc_tx_fail(call->debug_id, serial, ret, - rxrpc_tx_fail_call_ack); + rxrpc_tx_point_call_ack); + else + trace_rxrpc_tx_packet(call->debug_id, &pkt->whdr, + rxrpc_tx_point_call_ack); if (call->state < RXRPC_CALL_COMPLETE) { if (ret < 0) { @@ -299,7 +302,10 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call) conn->params.peer->last_tx_at = ktime_get_real(); if (ret < 0) trace_rxrpc_tx_fail(call->debug_id, serial, ret, - rxrpc_tx_fail_call_abort); + rxrpc_tx_point_call_abort); + else + trace_rxrpc_tx_packet(call->debug_id, &pkt.whdr, + rxrpc_tx_point_call_abort); rxrpc_put_connection(conn); @@ -396,7 +402,10 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, up_read(&conn->params.local->defrag_sem); if (ret < 0) trace_rxrpc_tx_fail(call->debug_id, serial, ret, - rxrpc_tx_fail_call_data_nofrag); + rxrpc_tx_point_call_data_nofrag); + else + trace_rxrpc_tx_packet(call->debug_id, &whdr, + rxrpc_tx_point_call_data_nofrag); if (ret == -EMSGSIZE) goto send_fragmentable; @@ -488,7 +497,10 @@ send_fragmentable: if (ret < 0) trace_rxrpc_tx_fail(call->debug_id, serial, ret, - rxrpc_tx_fail_call_data_frag); + rxrpc_tx_point_call_data_frag); + else + trace_rxrpc_tx_packet(call->debug_id, &whdr, + rxrpc_tx_point_call_data_frag); up_write(&conn->params.local->defrag_sem); goto done; @@ -545,7 +557,10 @@ void rxrpc_reject_packets(struct rxrpc_local *local) ret = kernel_sendmsg(local->socket, &msg, iov, 2, size); if (ret < 0) trace_rxrpc_tx_fail(local->debug_id, 0, ret, - rxrpc_tx_fail_reject); + rxrpc_tx_point_reject); + else + trace_rxrpc_tx_packet(local->debug_id, &whdr, + rxrpc_tx_point_reject); } rxrpc_free_skb(skb, rxrpc_skb_rx_freed); @@ -597,7 +612,10 @@ void rxrpc_send_keepalive(struct rxrpc_peer *peer) ret = kernel_sendmsg(peer->local->socket, &msg, iov, 2, len); if (ret < 0) trace_rxrpc_tx_fail(peer->debug_id, 0, ret, - rxrpc_tx_fail_version_keepalive); + rxrpc_tx_point_version_keepalive); + else + trace_rxrpc_tx_packet(peer->debug_id, &whdr, + rxrpc_tx_point_version_keepalive); peer->last_tx_at = ktime_get_real(); _leave(""); diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index 278ac0807a60..6988073ae842 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -665,11 +665,13 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn) ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len); if (ret < 0) { trace_rxrpc_tx_fail(conn->debug_id, serial, ret, - rxrpc_tx_fail_conn_challenge); + rxrpc_tx_point_rxkad_challenge); return -EAGAIN; } conn->params.peer->last_tx_at = ktime_get_real(); + trace_rxrpc_tx_packet(conn->debug_id, &whdr, + rxrpc_tx_point_rxkad_challenge); _leave(" = 0"); return 0; } @@ -721,11 +723,12 @@ static int rxkad_send_response(struct rxrpc_connection *conn, ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 3, len); if (ret < 0) { trace_rxrpc_tx_fail(conn->debug_id, serial, ret, - rxrpc_tx_fail_conn_response); + rxrpc_tx_point_rxkad_response); return -EAGAIN; } conn->params.peer->last_tx_at = ktime_get_real(); + trace_rxrpc_tx_packet(0, &whdr, rxrpc_tx_point_rxkad_response); _leave(" = 0"); return 0; } -- cgit v1.2.3 From 197445aff13c164794efb6d87a28762e843622d8 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 23 Jul 2018 17:18:37 +0100 Subject: rxrpc: Fix ACK proposal tracepoint Fix the ACK proposal tracepoint outcomes list by making the one that's an empty string not an empty string - which gets rendered as a hex number string instead. Signed-off-by: David Howells --- include/trace/events/rxrpc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 2aa6f615b60d..c1a800a6dee3 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -396,7 +396,7 @@ enum rxrpc_tx_point { #define rxrpc_propose_ack_outcomes \ EM(rxrpc_propose_ack_subsume, " Subsume") \ EM(rxrpc_propose_ack_update, " Update") \ - E_(rxrpc_propose_ack_use, "") + E_(rxrpc_propose_ack_use, " New") #define rxrpc_congest_modes \ EM(RXRPC_CALL_CONGEST_AVOIDANCE, "CongAvoid") \ -- cgit v1.2.3 From 4272d3034e69aea6e17085ba285d14f5824b430d Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 23 Jul 2018 17:18:37 +0100 Subject: rxrpc: Trace socket notification Trace notifications from the softirq side of the socket to the process-context side. Signed-off-by: David Howells --- include/trace/events/rxrpc.h | 20 ++++++++++++++++++++ net/rxrpc/input.c | 4 +++- 2 files changed, 23 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index c1a800a6dee3..196587b8f204 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -1528,6 +1528,26 @@ TRACE_EVENT(rxrpc_call_reset, __entry->tx_seq, __entry->rx_seq) ); +TRACE_EVENT(rxrpc_notify_socket, + TP_PROTO(unsigned int debug_id, rxrpc_serial_t serial), + + TP_ARGS(debug_id, serial), + + TP_STRUCT__entry( + __field(unsigned int, debug_id ) + __field(rxrpc_serial_t, serial ) + ), + + TP_fast_assign( + __entry->debug_id = debug_id; + __entry->serial = serial; + ), + + TP_printk("c=%08x r=%08x", + __entry->debug_id, + __entry->serial) + ); + #endif /* _TRACE_RXRPC_H */ /* This part must be outside protection */ diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 8989d760b6b2..cfdc199c6351 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -597,8 +597,10 @@ ack: false, true, rxrpc_propose_ack_input_data); - if (sp->hdr.seq == READ_ONCE(call->rx_hard_ack) + 1) + if (sp->hdr.seq == READ_ONCE(call->rx_hard_ack) + 1) { + trace_rxrpc_notify_socket(call->debug_id, serial); rxrpc_notify_socket(call); + } _leave(" [queued]"); } -- cgit v1.2.3 From 304d34360b099020a12af2abb7e1ac506f4ba16d Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Sat, 28 Jul 2018 10:19:13 +0200 Subject: spi: add flags parameter to txrx_word function pointers Add the capability to specify the flag parameter used in bitbang_txrx_be_cpha{0,1} through the txrx_word function pointers of spi_bitbang data structure. That feature will be used to add spi-3wire support to the spi-gpio controller Signed-off-by: Lorenzo Bianconi Signed-off-by: Mark Brown --- drivers/spi/spi-ath79.c | 2 +- drivers/spi/spi-bitbang.c | 34 +++++++++++++++++++++------------- drivers/spi/spi-butterfly.c | 4 ++-- drivers/spi/spi-gpio.c | 32 ++++++++++++++++---------------- drivers/spi/spi-lm70llp.c | 5 +++-- drivers/spi/spi-sh-sci.c | 20 ++++++++++++-------- drivers/spi/spi-xtensa-xtfpga.c | 2 +- include/linux/spi/spi_bitbang.h | 2 +- 8 files changed, 57 insertions(+), 44 deletions(-) (limited to 'include') diff --git a/drivers/spi/spi-ath79.c b/drivers/spi/spi-ath79.c index 0719bd484891..3f6b657394de 100644 --- a/drivers/spi/spi-ath79.c +++ b/drivers/spi/spi-ath79.c @@ -176,7 +176,7 @@ static void ath79_spi_cleanup(struct spi_device *spi) } static u32 ath79_spi_txrx_mode0(struct spi_device *spi, unsigned int nsecs, - u32 word, u8 bits) + u32 word, u8 bits, unsigned flags) { struct ath79_spi *sp = ath79_spidev_to_sp(spi); u32 ioc = sp->ioc_base; diff --git a/drivers/spi/spi-bitbang.c b/drivers/spi/spi-bitbang.c index 3aa9e6e3dac8..76f1b534bdd7 100644 --- a/drivers/spi/spi-bitbang.c +++ b/drivers/spi/spi-bitbang.c @@ -49,22 +49,26 @@ struct spi_bitbang_cs { unsigned nsecs; /* (clock cycle time)/2 */ u32 (*txrx_word)(struct spi_device *spi, unsigned nsecs, - u32 word, u8 bits); + u32 word, u8 bits, unsigned flags); unsigned (*txrx_bufs)(struct spi_device *, u32 (*txrx_word)( struct spi_device *spi, unsigned nsecs, - u32 word, u8 bits), - unsigned, struct spi_transfer *); + u32 word, u8 bits, + unsigned flags), + unsigned, struct spi_transfer *, + unsigned); }; static unsigned bitbang_txrx_8( struct spi_device *spi, u32 (*txrx_word)(struct spi_device *spi, unsigned nsecs, - u32 word, u8 bits), + u32 word, u8 bits, + unsigned flags), unsigned ns, - struct spi_transfer *t + struct spi_transfer *t, + unsigned flags ) { unsigned bits = t->bits_per_word; unsigned count = t->len; @@ -76,7 +80,7 @@ static unsigned bitbang_txrx_8( if (tx) word = *tx++; - word = txrx_word(spi, ns, word, bits); + word = txrx_word(spi, ns, word, bits, flags); if (rx) *rx++ = word; count -= 1; @@ -88,9 +92,11 @@ static unsigned bitbang_txrx_16( struct spi_device *spi, u32 (*txrx_word)(struct spi_device *spi, unsigned nsecs, - u32 word, u8 bits), + u32 word, u8 bits, + unsigned flags), unsigned ns, - struct spi_transfer *t + struct spi_transfer *t, + unsigned flags ) { unsigned bits = t->bits_per_word; unsigned count = t->len; @@ -102,7 +108,7 @@ static unsigned bitbang_txrx_16( if (tx) word = *tx++; - word = txrx_word(spi, ns, word, bits); + word = txrx_word(spi, ns, word, bits, flags); if (rx) *rx++ = word; count -= 2; @@ -114,9 +120,11 @@ static unsigned bitbang_txrx_32( struct spi_device *spi, u32 (*txrx_word)(struct spi_device *spi, unsigned nsecs, - u32 word, u8 bits), + u32 word, u8 bits, + unsigned flags), unsigned ns, - struct spi_transfer *t + struct spi_transfer *t, + unsigned flags ) { unsigned bits = t->bits_per_word; unsigned count = t->len; @@ -128,7 +136,7 @@ static unsigned bitbang_txrx_32( if (tx) word = *tx++; - word = txrx_word(spi, ns, word, bits); + word = txrx_word(spi, ns, word, bits, flags); if (rx) *rx++ = word; count -= 4; @@ -236,7 +244,7 @@ static int spi_bitbang_bufs(struct spi_device *spi, struct spi_transfer *t) struct spi_bitbang_cs *cs = spi->controller_state; unsigned nsecs = cs->nsecs; - return cs->txrx_bufs(spi, cs->txrx_word, nsecs, t); + return cs->txrx_bufs(spi, cs->txrx_word, nsecs, t, 0); } /*----------------------------------------------------------------------*/ diff --git a/drivers/spi/spi-butterfly.c b/drivers/spi/spi-butterfly.c index 22a31e4a1a11..1a3510215841 100644 --- a/drivers/spi/spi-butterfly.c +++ b/drivers/spi/spi-butterfly.c @@ -144,9 +144,9 @@ static void butterfly_chipselect(struct spi_device *spi, int value) static u32 butterfly_txrx_word_mode0(struct spi_device *spi, unsigned nsecs, u32 word, - u8 bits) + u8 bits, unsigned flags) { - return bitbang_txrx_be_cpha0(spi, nsecs, 0, 0, word, bits); + return bitbang_txrx_be_cpha0(spi, nsecs, 0, flags, word, bits); } /*----------------------------------------------------------------------*/ diff --git a/drivers/spi/spi-gpio.c b/drivers/spi/spi-gpio.c index 6ae92d4dca19..be68298cbd9c 100644 --- a/drivers/spi/spi-gpio.c +++ b/drivers/spi/spi-gpio.c @@ -149,27 +149,27 @@ static inline int getmiso(const struct spi_device *spi) */ static u32 spi_gpio_txrx_word_mode0(struct spi_device *spi, - unsigned nsecs, u32 word, u8 bits) + unsigned nsecs, u32 word, u8 bits, unsigned flags) { - return bitbang_txrx_be_cpha0(spi, nsecs, 0, 0, word, bits); + return bitbang_txrx_be_cpha0(spi, nsecs, 0, flags, word, bits); } static u32 spi_gpio_txrx_word_mode1(struct spi_device *spi, - unsigned nsecs, u32 word, u8 bits) + unsigned nsecs, u32 word, u8 bits, unsigned flags) { - return bitbang_txrx_be_cpha1(spi, nsecs, 0, 0, word, bits); + return bitbang_txrx_be_cpha1(spi, nsecs, 0, flags, word, bits); } static u32 spi_gpio_txrx_word_mode2(struct spi_device *spi, - unsigned nsecs, u32 word, u8 bits) + unsigned nsecs, u32 word, u8 bits, unsigned flags) { - return bitbang_txrx_be_cpha0(spi, nsecs, 1, 0, word, bits); + return bitbang_txrx_be_cpha0(spi, nsecs, 1, flags, word, bits); } static u32 spi_gpio_txrx_word_mode3(struct spi_device *spi, - unsigned nsecs, u32 word, u8 bits) + unsigned nsecs, u32 word, u8 bits, unsigned flags) { - return bitbang_txrx_be_cpha1(spi, nsecs, 1, 0, word, bits); + return bitbang_txrx_be_cpha1(spi, nsecs, 1, flags, word, bits); } /* @@ -183,30 +183,30 @@ static u32 spi_gpio_txrx_word_mode3(struct spi_device *spi, */ static u32 spi_gpio_spec_txrx_word_mode0(struct spi_device *spi, - unsigned nsecs, u32 word, u8 bits) + unsigned nsecs, u32 word, u8 bits, unsigned flags) { - unsigned flags = spi->master->flags; + flags = spi->master->flags; return bitbang_txrx_be_cpha0(spi, nsecs, 0, flags, word, bits); } static u32 spi_gpio_spec_txrx_word_mode1(struct spi_device *spi, - unsigned nsecs, u32 word, u8 bits) + unsigned nsecs, u32 word, u8 bits, unsigned flags) { - unsigned flags = spi->master->flags; + flags = spi->master->flags; return bitbang_txrx_be_cpha1(spi, nsecs, 0, flags, word, bits); } static u32 spi_gpio_spec_txrx_word_mode2(struct spi_device *spi, - unsigned nsecs, u32 word, u8 bits) + unsigned nsecs, u32 word, u8 bits, unsigned flags) { - unsigned flags = spi->master->flags; + flags = spi->master->flags; return bitbang_txrx_be_cpha0(spi, nsecs, 1, flags, word, bits); } static u32 spi_gpio_spec_txrx_word_mode3(struct spi_device *spi, - unsigned nsecs, u32 word, u8 bits) + unsigned nsecs, u32 word, u8 bits, unsigned flags) { - unsigned flags = spi->master->flags; + flags = spi->master->flags; return bitbang_txrx_be_cpha1(spi, nsecs, 1, flags, word, bits); } diff --git a/drivers/spi/spi-lm70llp.c b/drivers/spi/spi-lm70llp.c index 61ee0f4269ae..4549efd792da 100644 --- a/drivers/spi/spi-lm70llp.c +++ b/drivers/spi/spi-lm70llp.c @@ -188,9 +188,10 @@ static void lm70_chipselect(struct spi_device *spi, int value) /* * Our actual bitbanger routine. */ -static u32 lm70_txrx(struct spi_device *spi, unsigned nsecs, u32 word, u8 bits) +static u32 lm70_txrx(struct spi_device *spi, unsigned nsecs, u32 word, u8 bits, + unsigned flags) { - return bitbang_txrx_be_cpha0(spi, nsecs, 0, 0, word, bits); + return bitbang_txrx_be_cpha0(spi, nsecs, 0, flags, word, bits); } static void spi_lm70llp_attach(struct parport *p) diff --git a/drivers/spi/spi-sh-sci.c b/drivers/spi/spi-sh-sci.c index a9beeeed812c..393701cfca3c 100644 --- a/drivers/spi/spi-sh-sci.c +++ b/drivers/spi/spi-sh-sci.c @@ -80,27 +80,31 @@ static inline u32 getmiso(struct spi_device *dev) #include "spi-bitbang-txrx.h" static u32 sh_sci_spi_txrx_mode0(struct spi_device *spi, - unsigned nsecs, u32 word, u8 bits) + unsigned nsecs, u32 word, u8 bits, + unsigned flags) { - return bitbang_txrx_be_cpha0(spi, nsecs, 0, 0, word, bits); + return bitbang_txrx_be_cpha0(spi, nsecs, 0, flags, word, bits); } static u32 sh_sci_spi_txrx_mode1(struct spi_device *spi, - unsigned nsecs, u32 word, u8 bits) + unsigned nsecs, u32 word, u8 bits, + unsigned flags) { - return bitbang_txrx_be_cpha1(spi, nsecs, 0, 0, word, bits); + return bitbang_txrx_be_cpha1(spi, nsecs, 0, flags, word, bits); } static u32 sh_sci_spi_txrx_mode2(struct spi_device *spi, - unsigned nsecs, u32 word, u8 bits) + unsigned nsecs, u32 word, u8 bits, + unsigned flags) { - return bitbang_txrx_be_cpha0(spi, nsecs, 1, 0, word, bits); + return bitbang_txrx_be_cpha0(spi, nsecs, 1, flags, word, bits); } static u32 sh_sci_spi_txrx_mode3(struct spi_device *spi, - unsigned nsecs, u32 word, u8 bits) + unsigned nsecs, u32 word, u8 bits, + unsigned flags) { - return bitbang_txrx_be_cpha1(spi, nsecs, 1, 0, word, bits); + return bitbang_txrx_be_cpha1(spi, nsecs, 1, flags, word, bits); } static void sh_sci_spi_chipselect(struct spi_device *dev, int value) diff --git a/drivers/spi/spi-xtensa-xtfpga.c b/drivers/spi/spi-xtensa-xtfpga.c index be6155cba9de..8ce04f829a80 100644 --- a/drivers/spi/spi-xtensa-xtfpga.c +++ b/drivers/spi/spi-xtensa-xtfpga.c @@ -54,7 +54,7 @@ static inline void xtfpga_spi_wait_busy(struct xtfpga_spi *xspi) } static u32 xtfpga_spi_txrx_word(struct spi_device *spi, unsigned nsecs, - u32 v, u8 bits) + u32 v, u8 bits, unsigned flags) { struct xtfpga_spi *xspi = spi_master_get_devdata(spi->master); diff --git a/include/linux/spi/spi_bitbang.h b/include/linux/spi/spi_bitbang.h index c1e61641a7f1..5847f00ef9cf 100644 --- a/include/linux/spi/spi_bitbang.h +++ b/include/linux/spi/spi_bitbang.h @@ -30,7 +30,7 @@ struct spi_bitbang { /* txrx_word[SPI_MODE_*]() just looks like a shift register */ u32 (*txrx_word[4])(struct spi_device *spi, unsigned nsecs, - u32 word, u8 bits); + u32 word, u8 bits, unsigned flags); }; /* you can call these default bitbang->master methods from your custom -- cgit v1.2.3 From 4b859db2c60692560afbfef1b030d0ddef57b7ee Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Sat, 28 Jul 2018 10:19:14 +0200 Subject: spi: spi-gpio: add SPI_3WIRE support Add SPI_3WIRE support to spi-gpio controller introducing set_line_direction function pointer in spi_bitbang data structure. Spi-gpio controller has been tested using hts221 temp/rh iio sensor running in 3wire mode and lsm6dsm running in 4wire mode Signed-off-by: Lorenzo Bianconi Signed-off-by: Mark Brown --- drivers/spi/spi-bitbang.c | 16 ++++++++++++++++ drivers/spi/spi-gpio.c | 17 ++++++++++++++++- include/linux/spi/spi_bitbang.h | 1 + 3 files changed, 33 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/spi/spi-bitbang.c b/drivers/spi/spi-bitbang.c index 76f1b534bdd7..f29176000b8d 100644 --- a/drivers/spi/spi-bitbang.c +++ b/drivers/spi/spi-bitbang.c @@ -243,7 +243,23 @@ static int spi_bitbang_bufs(struct spi_device *spi, struct spi_transfer *t) { struct spi_bitbang_cs *cs = spi->controller_state; unsigned nsecs = cs->nsecs; + struct spi_bitbang *bitbang; + + bitbang = spi_master_get_devdata(spi->master); + if (bitbang->set_line_direction) { + int err; + err = bitbang->set_line_direction(spi, !!(t->tx_buf)); + if (err < 0) + return err; + } + + if (spi->mode & SPI_3WIRE) { + unsigned flags; + + flags = t->tx_buf ? SPI_MASTER_NO_RX : SPI_MASTER_NO_TX; + return cs->txrx_bufs(spi, cs->txrx_word, nsecs, t, flags); + } return cs->txrx_bufs(spi, cs->txrx_word, nsecs, t, 0); } diff --git a/drivers/spi/spi-gpio.c b/drivers/spi/spi-gpio.c index be68298cbd9c..0626e6e3ea0c 100644 --- a/drivers/spi/spi-gpio.c +++ b/drivers/spi/spi-gpio.c @@ -121,7 +121,10 @@ static inline int getmiso(const struct spi_device *spi) { struct spi_gpio *spi_gpio = spi_to_spi_gpio(spi); - return !!gpiod_get_value_cansleep(spi_gpio->miso); + if (spi->mode & SPI_3WIRE) + return !!gpiod_get_value_cansleep(spi_gpio->mosi); + else + return !!gpiod_get_value_cansleep(spi_gpio->miso); } /* @@ -250,6 +253,16 @@ static int spi_gpio_setup(struct spi_device *spi) return status; } +static int spi_gpio_set_direction(struct spi_device *spi, bool output) +{ + struct spi_gpio *spi_gpio = spi_to_spi_gpio(spi); + + if (output) + return gpiod_direction_output(spi_gpio->mosi, 1); + else + return gpiod_direction_input(spi_gpio->mosi); +} + static void spi_gpio_cleanup(struct spi_device *spi) { spi_bitbang_cleanup(spi); @@ -395,6 +408,7 @@ static int spi_gpio_probe(struct platform_device *pdev) return status; master->bits_per_word_mask = SPI_BPW_RANGE_MASK(1, 32); + master->mode_bits = SPI_3WIRE | SPI_CPHA | SPI_CPOL; master->flags = master_flags; master->bus_num = pdev->id; /* The master needs to think there is a chipselect even if not connected */ @@ -407,6 +421,7 @@ static int spi_gpio_probe(struct platform_device *pdev) spi_gpio->bitbang.master = master; spi_gpio->bitbang.chipselect = spi_gpio_chipselect; + spi_gpio->bitbang.set_line_direction = spi_gpio_set_direction; if ((master_flags & (SPI_MASTER_NO_TX | SPI_MASTER_NO_RX)) == 0) { spi_gpio->bitbang.txrx_word[SPI_MODE_0] = spi_gpio_txrx_word_mode0; diff --git a/include/linux/spi/spi_bitbang.h b/include/linux/spi/spi_bitbang.h index 5847f00ef9cf..b7e021b274dc 100644 --- a/include/linux/spi/spi_bitbang.h +++ b/include/linux/spi/spi_bitbang.h @@ -31,6 +31,7 @@ struct spi_bitbang { u32 (*txrx_word[4])(struct spi_device *spi, unsigned nsecs, u32 word, u8 bits, unsigned flags); + int (*set_line_direction)(struct spi_device *spi, bool output); }; /* you can call these default bitbang->master methods from your custom -- cgit v1.2.3 From 83ba4645152d1177c161750e1064e3a8e7cee19b Mon Sep 17 00:00:00 2001 From: Vincent Bernat Date: Tue, 31 Jul 2018 21:18:11 +0200 Subject: net: add helpers checking if socket can be bound to nonlocal address The construction "net->ipv4.sysctl_ip_nonlocal_bind || inet->freebind || inet->transparent" is present three times and its IPv6 counterpart is also present three times. We introduce two small helpers to characterize these tests uniformly. Signed-off-by: Vincent Bernat Signed-off-by: David S. Miller --- include/net/inet_sock.h | 8 ++++++++ include/net/ipv6.h | 7 +++++++ net/ipv4/af_inet.c | 3 +-- net/ipv4/ping.c | 6 ++---- net/ipv6/af_inet6.c | 6 ++---- net/ipv6/datagram.c | 3 +-- 6 files changed, 21 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 314be484c696..e03b93360f33 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -359,4 +359,12 @@ static inline bool inet_get_convert_csum(struct sock *sk) return !!inet_sk(sk)->convert_csum; } + +static inline bool inet_can_nonlocal_bind(struct net *net, + struct inet_sock *inet) +{ + return net->ipv4.sysctl_ip_nonlocal_bind || + inet->freebind || inet->transparent; +} + #endif /* _INET_SOCK_H */ diff --git a/include/net/ipv6.h b/include/net/ipv6.h index a44509f4e985..82deb684ba73 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -766,6 +766,13 @@ static inline int ip6_sk_dst_hoplimit(struct ipv6_pinfo *np, struct flowi6 *fl6, return hlimit; } +static inline bool ipv6_can_nonlocal_bind(struct net *net, + struct inet_sock *inet) +{ + return net->ipv6.sysctl.ip_nonlocal_bind || + inet->freebind || inet->transparent; +} + /* copy IPv6 saddr & daddr to flow_keys, possibly using 64bit load/store * Equivalent to : flow->v6addrs.src = iph->saddr; * flow->v6addrs.dst = iph->daddr; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index f2a0a3bab6b5..ee707b91d1a7 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -486,8 +486,7 @@ int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, * is temporarily down) */ err = -EADDRNOTAVAIL; - if (!net->ipv4.sysctl_ip_nonlocal_bind && - !(inet->freebind || inet->transparent) && + if (!inet_can_nonlocal_bind(net, inet) && addr->sin_addr.s_addr != htonl(INADDR_ANY) && chk_addr_ret != RTN_LOCAL && chk_addr_ret != RTN_MULTICAST && diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index b54c964ad925..8d7aaf118a30 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -320,8 +320,7 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, if (addr->sin_addr.s_addr == htonl(INADDR_ANY)) chk_addr_ret = RTN_LOCAL; - if ((net->ipv4.sysctl_ip_nonlocal_bind == 0 && - isk->freebind == 0 && isk->transparent == 0 && + if ((!inet_can_nonlocal_bind(net, isk) && chk_addr_ret != RTN_LOCAL) || chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST) @@ -361,8 +360,7 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, scoped); rcu_read_unlock(); - if (!(net->ipv6.sysctl.ip_nonlocal_bind || - isk->freebind || isk->transparent || has_addr || + if (!(ipv6_can_nonlocal_bind(net, isk) || has_addr || addr_type == IPV6_ADDR_ANY)) return -EADDRNOTAVAIL; diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index c9535354149f..020f6e14a7af 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -322,8 +322,7 @@ static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, /* Reproduce AF_INET checks to make the bindings consistent */ v4addr = addr->sin6_addr.s6_addr32[3]; chk_addr_ret = inet_addr_type(net, v4addr); - if (!net->ipv4.sysctl_ip_nonlocal_bind && - !(inet->freebind || inet->transparent) && + if (!inet_can_nonlocal_bind(net, inet) && v4addr != htonl(INADDR_ANY) && chk_addr_ret != RTN_LOCAL && chk_addr_ret != RTN_MULTICAST && @@ -362,8 +361,7 @@ static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, */ v4addr = LOOPBACK4_IPV6; if (!(addr_type & IPV6_ADDR_MULTICAST)) { - if (!net->ipv6.sysctl.ip_nonlocal_bind && - !(inet->freebind || inet->transparent) && + if (!ipv6_can_nonlocal_bind(net, inet) && !ipv6_chk_addr(net, &addr->sin6_addr, dev, 0)) { err = -EADDRNOTAVAIL; diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index f0264dfd38de..1ede7a16a0be 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -803,8 +803,7 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk, if (addr_type != IPV6_ADDR_ANY) { int strict = __ipv6_addr_src_scope(addr_type) <= IPV6_ADDR_SCOPE_LINKLOCAL; - if (!(net->ipv6.sysctl.ip_nonlocal_bind || - inet_sk(sk)->freebind || inet_sk(sk)->transparent) && + if (!ipv6_can_nonlocal_bind(net, inet_sk(sk)) && !ipv6_chk_addr_and_flags(net, &src_info->ipi6_addr, dev, !strict, 0, IFA_F_TENTATIVE) && -- cgit v1.2.3 From 432e05d328921c68c35bfdeff7d7b7400b8e3d1a Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Wed, 1 Aug 2018 00:36:03 +0200 Subject: net: ipv4: Control SKB reprioritization after forwarding After IPv4 packets are forwarded, the priority of the corresponding SKB is updated according to the TOS field of IPv4 header. This overrides any prioritization done earlier by e.g. an skbedit action or ingress-qos-map defined at a vlan device. Such overriding may not always be desirable. Even if the packet ends up being routed, which implies this is an L3 network node, an administrator may wish to preserve whatever prioritization was done earlier on in the pipeline. Therefore introduce a sysctl that controls this behavior. Keep the default value at 1 to maintain backward-compatible behavior. Signed-off-by: Petr Machata Reviewed-by: Ido Schimmel Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.txt | 9 +++++++++ include/net/netns/ipv4.h | 1 + net/ipv4/af_inet.c | 1 + net/ipv4/ip_forward.c | 3 ++- net/ipv4/sysctl_net_ipv4.c | 9 +++++++++ 5 files changed, 22 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 77c37fb0b6a6..e74515ecaa9c 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -81,6 +81,15 @@ fib_multipath_hash_policy - INTEGER 0 - Layer 3 1 - Layer 4 +ip_forward_update_priority - INTEGER + Whether to update SKB priority from "TOS" field in IPv4 header after it + is forwarded. The new SKB priority is mapped from TOS field value + according to an rt_tos2priority table (see e.g. man tc-prio). + Default: 1 (Update priority.) + Possible values: + 0 - Do not update priority. + 1 - Update priority. + route/max_size - INTEGER Maximum number of routes allowed in the kernel. Increase this when using large numbers of interfaces and/or routes. diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 661348f23ea5..e47503b4e4d1 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -98,6 +98,7 @@ struct netns_ipv4 { int sysctl_ip_default_ttl; int sysctl_ip_no_pmtu_disc; int sysctl_ip_fwd_use_pmtu; + int sysctl_ip_fwd_update_priority; int sysctl_ip_nonlocal_bind; /* Shall we try to damage output packets if routing dev changes? */ int sysctl_ip_dynaddr; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index ee707b91d1a7..20fda8fb8ffd 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1801,6 +1801,7 @@ static __net_init int inet_init_net(struct net *net) * We set them here, in case sysctl is not compiled. */ net->ipv4.sysctl_ip_default_ttl = IPDEFTTL; + net->ipv4.sysctl_ip_fwd_update_priority = 1; net->ipv4.sysctl_ip_dynaddr = 0; net->ipv4.sysctl_ip_early_demux = 1; net->ipv4.sysctl_udp_early_demux = 1; diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index b54b948b0596..32662e9e5d21 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -143,7 +143,8 @@ int ip_forward(struct sk_buff *skb) !skb_sec_path(skb)) ip_rt_send_redirect(skb); - skb->priority = rt_tos2priority(iph->tos); + if (net->ipv4.sysctl_ip_fwd_update_priority) + skb->priority = rt_tos2priority(iph->tos); return NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD, net, NULL, skb, skb->dev, rt->dst.dev, diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 5fa335fd3852..e21dda015513 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -663,6 +663,15 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "ip_forward_update_priority", + .data = &init_net.ipv4.sysctl_ip_fwd_update_priority, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, + }, { .procname = "ip_nonlocal_bind", .data = &init_net.ipv4.sysctl_ip_nonlocal_bind, -- cgit v1.2.3 From d18c5d1995aa322b722fa731397e28ebcd00b3c6 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Wed, 1 Aug 2018 00:36:42 +0200 Subject: net: ipv4: Notify about changes to ip_forward_update_priority Drivers may make offloading decision based on whether ip_forward_update_priority is enabled or not. Therefore distribute netevent notifications to give them a chance to react to a change. Signed-off-by: Petr Machata Reviewed-by: Ido Schimmel Signed-off-by: David S. Miller --- include/net/netevent.h | 1 + net/ipv4/sysctl_net_ipv4.c | 19 ++++++++++++++++++- 2 files changed, 19 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/netevent.h b/include/net/netevent.h index d9918261701c..4107016c3bb4 100644 --- a/include/net/netevent.h +++ b/include/net/netevent.h @@ -28,6 +28,7 @@ enum netevent_notif_type { NETEVENT_DELAY_PROBE_TIME_UPDATE, /* arg is struct neigh_parms ptr */ NETEVENT_IPV4_MPATH_HASH_UPDATE, /* arg is struct net ptr */ NETEVENT_IPV6_MPATH_HASH_UPDATE, /* arg is struct net ptr */ + NETEVENT_IPV4_FWD_UPDATE_PRIORITY_UPDATE, /* arg is struct net ptr */ }; int register_netevent_notifier(struct notifier_block *nb); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index e21dda015513..b92f422f2fa8 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -201,6 +201,23 @@ static int ipv4_ping_group_range(struct ctl_table *table, int write, return ret; } +static int ipv4_fwd_update_priority(struct ctl_table *table, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + struct net *net; + int ret; + + net = container_of(table->data, struct net, + ipv4.sysctl_ip_fwd_update_priority); + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + if (write && ret == 0) + call_netevent_notifiers(NETEVENT_IPV4_FWD_UPDATE_PRIORITY_UPDATE, + net); + + return ret; +} + static int proc_tcp_congestion_control(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -668,7 +685,7 @@ static struct ctl_table ipv4_net_table[] = { .data = &init_net.ipv4.sysctl_ip_fwd_update_priority, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = ipv4_fwd_update_priority, .extra1 = &zero, .extra2 = &one, }, -- cgit v1.2.3 From ba113c3aa79a7f941ac162d05a3620bdc985c58d Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Tue, 31 Jul 2018 17:46:21 -0700 Subject: tcp: add data bytes sent stats Introduce a new TCP stat to record the number of bytes sent (RFC4898 tcpEStatsPerfHCDataOctetsOut) and expose it in both tcp_info (TCP_INFO) and opt_stats (SOF_TIMESTAMPING_OPT_STATS). Signed-off-by: Wei Wang Signed-off-by: Eric Dumazet Acked-by: Neal Cardwell Acked-by: Soheil Hassas Yeganeh Acked-by: Yuchung Cheng Signed-off-by: David S. Miller --- include/linux/tcp.h | 3 +++ include/uapi/linux/tcp.h | 4 +++- net/ipv4/tcp.c | 6 ++++++ net/ipv4/tcp_output.c | 1 + 4 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 58a8d7d71354..d0798dcd2cab 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -181,6 +181,9 @@ struct tcp_sock { u32 data_segs_out; /* RFC4898 tcpEStatsPerfDataSegsOut * total number of data segments sent. */ + u64 bytes_sent; /* RFC4898 tcpEStatsPerfHCDataOctetsOut + * total number of data bytes sent. + */ u64 bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked * sum(delta(snd_una)), or how many bytes * were acked. diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index e3f6ed8a7064..1c70ed287c3b 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -235,6 +235,8 @@ struct tcp_info { __u32 tcpi_delivered; __u32 tcpi_delivered_ce; + + __u64 tcpi_bytes_sent; /* RFC4898 tcpEStatsPerfHCDataOctetsOut */ }; /* netlink attributes types for SCM_TIMESTAMPING_OPT_STATS */ @@ -257,7 +259,7 @@ enum { TCP_NLA_SND_SSTHRESH, /* Slow start size threshold */ TCP_NLA_DELIVERED, /* Data pkts delivered incl. out-of-order */ TCP_NLA_DELIVERED_CE, /* Like above but only ones w/ CE marks */ - + TCP_NLA_BYTES_SENT, /* Data bytes sent including retransmission */ }; /* for TCP_MD5SIG socket option */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 27bbe6a792b7..873cb9968ff5 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2594,6 +2594,7 @@ int tcp_disconnect(struct sock *sk, int flags) sk->sk_rx_dst = NULL; tcp_saved_syn_free(tp); tp->compressed_ack = 0; + tp->bytes_sent = 0; /* Clean up fastopen related fields */ tcp_free_fastopen_req(tp); @@ -3201,6 +3202,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_delivery_rate = rate64; info->tcpi_delivered = tp->delivered; info->tcpi_delivered_ce = tp->delivered_ce; + info->tcpi_bytes_sent = tp->bytes_sent; unlock_sock_fast(sk, slow); } EXPORT_SYMBOL_GPL(tcp_get_info); @@ -3225,6 +3227,7 @@ static size_t tcp_opt_stats_get_size(void) nla_total_size(sizeof(u32)) + /* TCP_NLA_SND_SSTHRESH */ nla_total_size(sizeof(u32)) + /* TCP_NLA_DELIVERED */ nla_total_size(sizeof(u32)) + /* TCP_NLA_DELIVERED_CE */ + nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BYTES_SENT */ 0; } @@ -3272,6 +3275,9 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk) nla_put_u32(stats, TCP_NLA_SNDQ_SIZE, tp->write_seq - tp->snd_una); nla_put_u8(stats, TCP_NLA_CA_STATE, inet_csk(sk)->icsk_ca_state); + nla_put_u64_64bit(stats, TCP_NLA_BYTES_SENT, tp->bytes_sent, + TCP_NLA_PAD); + return stats; } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 490df62f26d4..861531fe0e97 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1136,6 +1136,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, if (skb->len != tcp_header_size) { tcp_event_data_sent(tp, sk); tp->data_segs_out += tcp_skb_pcount(skb); + tp->bytes_sent += skb->len - tcp_header_size; tcp_internal_pacing(sk, skb); } -- cgit v1.2.3 From fb31c9b9f6c85b1bad569ecedbde78d9e37cd87b Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Tue, 31 Jul 2018 17:46:22 -0700 Subject: tcp: add data bytes retransmitted stats Introduce a new TCP stat to record the number of bytes retransmitted (RFC4898 tcpEStatsPerfOctetsRetrans) and expose it in both tcp_info (TCP_INFO) and opt_stats (SOF_TIMESTAMPING_OPT_STATS). Signed-off-by: Wei Wang Signed-off-by: Eric Dumazet Acked-by: Neal Cardwell Acked-by: Soheil Hassas Yeganeh Acked-by: Yuchung Cheng Signed-off-by: David S. Miller --- include/linux/tcp.h | 3 +++ include/uapi/linux/tcp.h | 2 ++ net/ipv4/tcp.c | 5 +++++ net/ipv4/tcp_output.c | 1 + 4 files changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index d0798dcd2cab..fb67f9a51b95 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -333,6 +333,9 @@ struct tcp_sock { * the first SYN. */ u32 undo_marker; /* snd_una upon a new recovery episode. */ int undo_retrans; /* number of undoable retransmissions. */ + u64 bytes_retrans; /* RFC4898 tcpEStatsPerfOctetsRetrans + * Total data bytes retransmitted + */ u32 total_retrans; /* Total retransmits for entire connection */ u32 urg_seq; /* Seq of received urgent pointer */ diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 1c70ed287c3b..c31f5100b744 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -237,6 +237,7 @@ struct tcp_info { __u32 tcpi_delivered_ce; __u64 tcpi_bytes_sent; /* RFC4898 tcpEStatsPerfHCDataOctetsOut */ + __u64 tcpi_bytes_retrans; /* RFC4898 tcpEStatsPerfOctetsRetrans */ }; /* netlink attributes types for SCM_TIMESTAMPING_OPT_STATS */ @@ -260,6 +261,7 @@ enum { TCP_NLA_DELIVERED, /* Data pkts delivered incl. out-of-order */ TCP_NLA_DELIVERED_CE, /* Like above but only ones w/ CE marks */ TCP_NLA_BYTES_SENT, /* Data bytes sent including retransmission */ + TCP_NLA_BYTES_RETRANS, /* Data bytes retransmitted */ }; /* for TCP_MD5SIG socket option */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 873cb9968ff5..5ed1be88e922 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2595,6 +2595,7 @@ int tcp_disconnect(struct sock *sk, int flags) tcp_saved_syn_free(tp); tp->compressed_ack = 0; tp->bytes_sent = 0; + tp->bytes_retrans = 0; /* Clean up fastopen related fields */ tcp_free_fastopen_req(tp); @@ -3203,6 +3204,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_delivered = tp->delivered; info->tcpi_delivered_ce = tp->delivered_ce; info->tcpi_bytes_sent = tp->bytes_sent; + info->tcpi_bytes_retrans = tp->bytes_retrans; unlock_sock_fast(sk, slow); } EXPORT_SYMBOL_GPL(tcp_get_info); @@ -3228,6 +3230,7 @@ static size_t tcp_opt_stats_get_size(void) nla_total_size(sizeof(u32)) + /* TCP_NLA_DELIVERED */ nla_total_size(sizeof(u32)) + /* TCP_NLA_DELIVERED_CE */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BYTES_SENT */ + nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BYTES_RETRANS */ 0; } @@ -3277,6 +3280,8 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk) nla_put_u64_64bit(stats, TCP_NLA_BYTES_SENT, tp->bytes_sent, TCP_NLA_PAD); + nla_put_u64_64bit(stats, TCP_NLA_BYTES_RETRANS, tp->bytes_retrans, + TCP_NLA_PAD); return stats; } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 861531fe0e97..50cabf7656f3 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2871,6 +2871,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN) __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); tp->total_retrans += segs; + tp->bytes_retrans += skb->len; /* make sure skb->data is aligned on arches that require it * and check if ack-trimming & collapsing extended the headroom -- cgit v1.2.3 From 7e10b6554ff2ce7f86d5d3eec3af5db8db482caa Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Tue, 31 Jul 2018 17:46:23 -0700 Subject: tcp: add dsack blocks received stats Introduce a new TCP stat to record the number of DSACK blocks received (RFC4989 tcpEStatsStackDSACKDups) and expose it in both tcp_info (TCP_INFO) and opt_stats (SOF_TIMESTAMPING_OPT_STATS). Signed-off-by: Wei Wang Signed-off-by: Eric Dumazet Acked-by: Neal Cardwell Acked-by: Soheil Hassas Yeganeh Acked-by: Yuchung Cheng Signed-off-by: David S. Miller --- include/linux/tcp.h | 3 +++ include/uapi/linux/tcp.h | 2 ++ net/ipv4/tcp.c | 4 ++++ net/ipv4/tcp_input.c | 1 + 4 files changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index fb67f9a51b95..da6281c549a5 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -188,6 +188,9 @@ struct tcp_sock { * sum(delta(snd_una)), or how many bytes * were acked. */ + u32 dsack_dups; /* RFC4898 tcpEStatsStackDSACKDups + * total number of DSACK blocks received + */ u32 snd_una; /* First byte we want an ack for */ u32 snd_sml; /* Last byte of the most recently transmitted small packet */ u32 rcv_tstamp; /* timestamp of last received ACK (for keepalives) */ diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index c31f5100b744..0e1c0aec0153 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -238,6 +238,7 @@ struct tcp_info { __u64 tcpi_bytes_sent; /* RFC4898 tcpEStatsPerfHCDataOctetsOut */ __u64 tcpi_bytes_retrans; /* RFC4898 tcpEStatsPerfOctetsRetrans */ + __u32 tcpi_dsack_dups; /* RFC4898 tcpEStatsStackDSACKDups */ }; /* netlink attributes types for SCM_TIMESTAMPING_OPT_STATS */ @@ -262,6 +263,7 @@ enum { TCP_NLA_DELIVERED_CE, /* Like above but only ones w/ CE marks */ TCP_NLA_BYTES_SENT, /* Data bytes sent including retransmission */ TCP_NLA_BYTES_RETRANS, /* Data bytes retransmitted */ + TCP_NLA_DSACK_DUPS, /* DSACK blocks received */ }; /* for TCP_MD5SIG socket option */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 5ed1be88e922..d6232b598cae 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2596,6 +2596,7 @@ int tcp_disconnect(struct sock *sk, int flags) tp->compressed_ack = 0; tp->bytes_sent = 0; tp->bytes_retrans = 0; + tp->dsack_dups = 0; /* Clean up fastopen related fields */ tcp_free_fastopen_req(tp); @@ -3205,6 +3206,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_delivered_ce = tp->delivered_ce; info->tcpi_bytes_sent = tp->bytes_sent; info->tcpi_bytes_retrans = tp->bytes_retrans; + info->tcpi_dsack_dups = tp->dsack_dups; unlock_sock_fast(sk, slow); } EXPORT_SYMBOL_GPL(tcp_get_info); @@ -3231,6 +3233,7 @@ static size_t tcp_opt_stats_get_size(void) nla_total_size(sizeof(u32)) + /* TCP_NLA_DELIVERED_CE */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BYTES_SENT */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BYTES_RETRANS */ + nla_total_size(sizeof(u32)) + /* TCP_NLA_DSACK_DUPS */ 0; } @@ -3282,6 +3285,7 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk) TCP_NLA_PAD); nla_put_u64_64bit(stats, TCP_NLA_BYTES_RETRANS, tp->bytes_retrans, TCP_NLA_PAD); + nla_put_u32(stats, TCP_NLA_DSACK_DUPS, tp->dsack_dups); return stats; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index d51fa358b2b1..fbc85ff7d71d 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -874,6 +874,7 @@ static void tcp_dsack_seen(struct tcp_sock *tp) { tp->rx_opt.sack_ok |= TCP_DSACK_SEEN; tp->rack.dsack_seen = 1; + tp->dsack_dups++; } /* It's reordering when higher sequence was delivered (i.e. sacked) before -- cgit v1.2.3 From 7ec65372ca534217b53fd208500cf7aac223a383 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Tue, 31 Jul 2018 17:46:24 -0700 Subject: tcp: add stat of data packet reordering events Introduce a new TCP stats to record the number of reordering events seen and expose it in both tcp_info (TCP_INFO) and opt_stats (SOF_TIMESTAMPING_OPT_STATS). Application can use this stats to track the frequency of the reordering events in addition to the existing reordering stats which tracks the magnitude of the latest reordering event. Note: this new stats tracks reordering events triggered by ACKs, which could often be fewer than the actual number of packets being delivered out-of-order. Signed-off-by: Wei Wang Signed-off-by: Eric Dumazet Acked-by: Neal Cardwell Acked-by: Soheil Hassas Yeganeh Acked-by: Yuchung Cheng Signed-off-by: David S. Miller --- include/linux/tcp.h | 4 ++-- include/uapi/linux/tcp.h | 2 ++ net/ipv4/tcp.c | 4 ++++ net/ipv4/tcp_input.c | 3 ++- net/ipv4/tcp_recovery.c | 2 +- 5 files changed, 11 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index da6281c549a5..263e37271afd 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -220,8 +220,7 @@ struct tcp_sock { #define TCP_RACK_RECOVERY_THRESH 16 u8 reo_wnd_persist:5, /* No. of recovery since last adj */ dsack_seen:1, /* Whether DSACK seen after last adj */ - advanced:1, /* mstamp advanced since last lost marking */ - reord:1; /* reordering detected */ + advanced:1; /* mstamp advanced since last lost marking */ } rack; u16 advmss; /* Advertised MSS */ u8 compressed_ack; @@ -267,6 +266,7 @@ struct tcp_sock { u8 ecn_flags; /* ECN status bits. */ u8 keepalive_probes; /* num of allowed keep alive probes */ u32 reordering; /* Packet reordering metric. */ + u32 reord_seen; /* number of data packet reordering events */ u32 snd_up; /* Urgent pointer */ /* diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 0e1c0aec0153..e02d31986ff9 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -239,6 +239,7 @@ struct tcp_info { __u64 tcpi_bytes_sent; /* RFC4898 tcpEStatsPerfHCDataOctetsOut */ __u64 tcpi_bytes_retrans; /* RFC4898 tcpEStatsPerfOctetsRetrans */ __u32 tcpi_dsack_dups; /* RFC4898 tcpEStatsStackDSACKDups */ + __u32 tcpi_reord_seen; /* reordering events seen */ }; /* netlink attributes types for SCM_TIMESTAMPING_OPT_STATS */ @@ -264,6 +265,7 @@ enum { TCP_NLA_BYTES_SENT, /* Data bytes sent including retransmission */ TCP_NLA_BYTES_RETRANS, /* Data bytes retransmitted */ TCP_NLA_DSACK_DUPS, /* DSACK blocks received */ + TCP_NLA_REORD_SEEN, /* reordering events seen */ }; /* for TCP_MD5SIG socket option */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index d6232b598cae..31fa1c080f28 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2597,6 +2597,7 @@ int tcp_disconnect(struct sock *sk, int flags) tp->bytes_sent = 0; tp->bytes_retrans = 0; tp->dsack_dups = 0; + tp->reord_seen = 0; /* Clean up fastopen related fields */ tcp_free_fastopen_req(tp); @@ -3207,6 +3208,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_bytes_sent = tp->bytes_sent; info->tcpi_bytes_retrans = tp->bytes_retrans; info->tcpi_dsack_dups = tp->dsack_dups; + info->tcpi_reord_seen = tp->reord_seen; unlock_sock_fast(sk, slow); } EXPORT_SYMBOL_GPL(tcp_get_info); @@ -3234,6 +3236,7 @@ static size_t tcp_opt_stats_get_size(void) nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BYTES_SENT */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BYTES_RETRANS */ nla_total_size(sizeof(u32)) + /* TCP_NLA_DSACK_DUPS */ + nla_total_size(sizeof(u32)) + /* TCP_NLA_REORD_SEEN */ 0; } @@ -3286,6 +3289,7 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk) nla_put_u64_64bit(stats, TCP_NLA_BYTES_RETRANS, tp->bytes_retrans, TCP_NLA_PAD); nla_put_u32(stats, TCP_NLA_DSACK_DUPS, tp->dsack_dups); + nla_put_u32(stats, TCP_NLA_REORD_SEEN, tp->reord_seen); return stats; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index fbc85ff7d71d..3d6156f07a8d 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -906,8 +906,8 @@ static void tcp_check_sack_reordering(struct sock *sk, const u32 low_seq, sock_net(sk)->ipv4.sysctl_tcp_max_reordering); } - tp->rack.reord = 1; /* This exciting event is worth to be remembered. 8) */ + tp->reord_seen++; NET_INC_STATS(sock_net(sk), ts ? LINUX_MIB_TCPTSREORDER : LINUX_MIB_TCPSACKREORDER); } @@ -1871,6 +1871,7 @@ static void tcp_check_reno_reordering(struct sock *sk, const int addend) tp->reordering = min_t(u32, tp->packets_out + addend, sock_net(sk)->ipv4.sysctl_tcp_max_reordering); + tp->reord_seen++; NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRENOREORDER); } diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c index 71593e4400ab..c81aadff769b 100644 --- a/net/ipv4/tcp_recovery.c +++ b/net/ipv4/tcp_recovery.c @@ -25,7 +25,7 @@ static u32 tcp_rack_reo_wnd(const struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); - if (!tp->rack.reord) { + if (!tp->reord_seen) { /* If reordering has not been observed, be aggressive during * the recovery or starting the recovery by DUPACK threshold. */ -- cgit v1.2.3 From 290b1c8b1a902c0902df9ec05577ab209296f345 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 1 Aug 2018 12:36:57 +0200 Subject: net: sched: make tcf_chain_{get,put}() static These are no longer used outside of cls_api.c so make them static. Move tcf_chain_flush() to avoid fwd declaration of tcf_chain_put(). Signed-off-by: Jiri Pirko v1->v2: - new patch Signed-off-by: David S. Miller --- include/net/pkt_cls.h | 3 --- net/sched/cls_api.c | 34 ++++++++++++++++------------------ 2 files changed, 16 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 22bfc3a13c25..ef727f71336e 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -40,11 +40,8 @@ struct tcf_block_cb; bool tcf_queue_work(struct rcu_work *rwork, work_func_t func); #ifdef CONFIG_NET_CLS -struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index, - bool create); struct tcf_chain *tcf_chain_get_by_act(struct tcf_block *block, u32 chain_index); -void tcf_chain_put(struct tcf_chain *chain); void tcf_chain_put_by_act(struct tcf_chain *chain); void tcf_block_netif_keep_dst(struct tcf_block *block); int tcf_block_get(struct tcf_block **p_block, diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index b194a5abfc6a..e8b0bbd0883f 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -232,19 +232,6 @@ static void tcf_chain0_head_change(struct tcf_chain *chain, tcf_chain_head_change_item(item, tp_head); } -static void tcf_chain_flush(struct tcf_chain *chain) -{ - struct tcf_proto *tp = rtnl_dereference(chain->filter_chain); - - tcf_chain0_head_change(chain, NULL); - while (tp) { - RCU_INIT_POINTER(chain->filter_chain, tp->next); - tcf_proto_destroy(tp, NULL); - tp = rtnl_dereference(chain->filter_chain); - tcf_chain_put(chain); - } -} - static void tcf_chain_destroy(struct tcf_chain *chain) { struct tcf_block *block = chain->block; @@ -316,12 +303,11 @@ static struct tcf_chain *__tcf_chain_get(struct tcf_block *block, return chain; } -struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index, - bool create) +static struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index, + bool create) { return __tcf_chain_get(block, chain_index, create, false); } -EXPORT_SYMBOL(tcf_chain_get); struct tcf_chain *tcf_chain_get_by_act(struct tcf_block *block, u32 chain_index) { @@ -347,11 +333,10 @@ static void __tcf_chain_put(struct tcf_chain *chain, bool by_act) } } -void tcf_chain_put(struct tcf_chain *chain) +static void tcf_chain_put(struct tcf_chain *chain) { __tcf_chain_put(chain, false); } -EXPORT_SYMBOL(tcf_chain_put); void tcf_chain_put_by_act(struct tcf_chain *chain) { @@ -365,6 +350,19 @@ static void tcf_chain_put_explicitly_created(struct tcf_chain *chain) tcf_chain_put(chain); } +static void tcf_chain_flush(struct tcf_chain *chain) +{ + struct tcf_proto *tp = rtnl_dereference(chain->filter_chain); + + tcf_chain0_head_change(chain, NULL); + while (tp) { + RCU_INIT_POINTER(chain->filter_chain, tp->next); + tcf_proto_destroy(tp, NULL); + tp = rtnl_dereference(chain->filter_chain); + tcf_chain_put(chain); + } +} + static bool tcf_block_offload_in_use(struct tcf_block *block) { return block->offloadcnt; -- cgit v1.2.3 From db57dc7c7a5c42bb653425a01b6d73c49514b5db Mon Sep 17 00:00:00 2001 From: Vincent Bernat Date: Wed, 1 Aug 2018 22:05:10 +0200 Subject: net: don't declare IPv6 non-local bind helper if CONFIG_IPV6 undefined Fixes: 83ba4645152d ("net: add helpers checking if socket can be bound to nonlocal address") Signed-off-by: Vincent Bernat Signed-off-by: David S. Miller --- include/net/ipv6.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 82deb684ba73..ff33f498c137 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -766,13 +766,6 @@ static inline int ip6_sk_dst_hoplimit(struct ipv6_pinfo *np, struct flowi6 *fl6, return hlimit; } -static inline bool ipv6_can_nonlocal_bind(struct net *net, - struct inet_sock *inet) -{ - return net->ipv6.sysctl.ip_nonlocal_bind || - inet->freebind || inet->transparent; -} - /* copy IPv6 saddr & daddr to flow_keys, possibly using 64bit load/store * Equivalent to : flow->v6addrs.src = iph->saddr; * flow->v6addrs.dst = iph->daddr; @@ -789,6 +782,13 @@ static inline void iph_to_flow_copy_v6addrs(struct flow_keys *flow, #if IS_ENABLED(CONFIG_IPV6) +static inline bool ipv6_can_nonlocal_bind(struct net *net, + struct inet_sock *inet) +{ + return net->ipv6.sysctl.ip_nonlocal_bind || + inet->freebind || inet->transparent; +} + /* Sysctl settings for net ipv6.auto_flowlabels */ #define IP6_AUTO_FLOW_LABEL_OFF 0 #define IP6_AUTO_FLOW_LABEL_OPTOUT 1 -- cgit v1.2.3 From ef965ad5a7697ff16e3be01954f5c57208e36c22 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 1 Aug 2018 14:38:18 +0200 Subject: ALSA: seq: Minor cleanup of MIDI event parser helpers snd_midi_event_encode_byte() can never fail, and it can return rather true/false. Change the return type to bool, adjust the argument to receive a MIDI byte as unsigned char, and adjust the comment accordingly. This allows callers to drop error checks, which simplifies the code. Meanwhile, snd_midi_event_encode() helper is used only in seq_midi.c, and it can be better folded into it. This will reduce the total amount of lines in the end. Signed-off-by: Takashi Iwai --- include/sound/seq_midi_event.h | 6 ++---- sound/core/seq/oss/seq_oss_midi.c | 2 +- sound/core/seq/seq_midi.c | 24 ++++++++++------------ sound/core/seq/seq_midi_event.c | 42 +++++++-------------------------------- sound/core/seq/seq_virmidi.c | 4 ++-- 5 files changed, 22 insertions(+), 56 deletions(-) (limited to 'include') diff --git a/include/sound/seq_midi_event.h b/include/sound/seq_midi_event.h index e40f43e6fc7b..2f135bccf457 100644 --- a/include/sound/seq_midi_event.h +++ b/include/sound/seq_midi_event.h @@ -43,10 +43,8 @@ void snd_midi_event_free(struct snd_midi_event *dev); void snd_midi_event_reset_encode(struct snd_midi_event *dev); void snd_midi_event_reset_decode(struct snd_midi_event *dev); void snd_midi_event_no_status(struct snd_midi_event *dev, int on); -/* encode from byte stream - return number of written bytes if success */ -long snd_midi_event_encode(struct snd_midi_event *dev, unsigned char *buf, long count, - struct snd_seq_event *ev); -int snd_midi_event_encode_byte(struct snd_midi_event *dev, int c, struct snd_seq_event *ev); +bool snd_midi_event_encode_byte(struct snd_midi_event *dev, unsigned char c, + struct snd_seq_event *ev); /* decode from event to bytes - return number of written bytes if success */ long snd_midi_event_decode(struct snd_midi_event *dev, unsigned char *buf, long count, struct snd_seq_event *ev); diff --git a/sound/core/seq/oss/seq_oss_midi.c b/sound/core/seq/oss/seq_oss_midi.c index 9debd1b8fd28..0d5f8b16d057 100644 --- a/sound/core/seq/oss/seq_oss_midi.c +++ b/sound/core/seq/oss/seq_oss_midi.c @@ -637,7 +637,7 @@ snd_seq_oss_midi_putc(struct seq_oss_devinfo *dp, int dev, unsigned char c, stru if ((mdev = get_mididev(dp, dev)) == NULL) return -ENODEV; - if (snd_midi_event_encode_byte(mdev->coder, c, ev) > 0) { + if (snd_midi_event_encode_byte(mdev->coder, c, ev)) { snd_seq_oss_fill_addr(dp, ev, mdev->client, mdev->port); snd_use_lock_free(&mdev->use_lock); return 0; diff --git a/sound/core/seq/seq_midi.c b/sound/core/seq/seq_midi.c index 5dd0ee258359..9e0dabd3ce5f 100644 --- a/sound/core/seq/seq_midi.c +++ b/sound/core/seq/seq_midi.c @@ -78,7 +78,7 @@ static void snd_midi_input_event(struct snd_rawmidi_substream *substream) struct seq_midisynth *msynth; struct snd_seq_event ev; char buf[16], *pbuf; - long res, count; + long res; if (substream == NULL) return; @@ -94,19 +94,15 @@ static void snd_midi_input_event(struct snd_rawmidi_substream *substream) if (msynth->parser == NULL) continue; pbuf = buf; - while (res > 0) { - count = snd_midi_event_encode(msynth->parser, pbuf, res, &ev); - if (count < 0) - break; - pbuf += count; - res -= count; - if (ev.type != SNDRV_SEQ_EVENT_NONE) { - ev.source.port = msynth->seq_port; - ev.dest.client = SNDRV_SEQ_ADDRESS_SUBSCRIBERS; - snd_seq_kernel_client_dispatch(msynth->seq_client, &ev, 1, 0); - /* clear event and reset header */ - memset(&ev, 0, sizeof(ev)); - } + while (res-- > 0) { + if (!snd_midi_event_encode_byte(msynth->parser, + *pbuf++, &ev)) + continue; + ev.source.port = msynth->seq_port; + ev.dest.client = SNDRV_SEQ_ADDRESS_SUBSCRIBERS; + snd_seq_kernel_client_dispatch(msynth->seq_client, &ev, 1, 0); + /* clear event and reset header */ + memset(&ev, 0, sizeof(ev)); } } } diff --git a/sound/core/seq/seq_midi_event.c b/sound/core/seq/seq_midi_event.c index 90bbbdbeba03..53c0dfab90d6 100644 --- a/sound/core/seq/seq_midi_event.c +++ b/sound/core/seq/seq_midi_event.c @@ -214,45 +214,17 @@ int snd_midi_event_resize_buffer(struct snd_midi_event *dev, int bufsize) } #endif /* 0 */ -/* - * read bytes and encode to sequencer event if finished - * return the size of encoded bytes - */ -long snd_midi_event_encode(struct snd_midi_event *dev, unsigned char *buf, long count, - struct snd_seq_event *ev) -{ - long result = 0; - int rc; - - ev->type = SNDRV_SEQ_EVENT_NONE; - - while (count-- > 0) { - rc = snd_midi_event_encode_byte(dev, *buf++, ev); - result++; - if (rc < 0) - return rc; - else if (rc > 0) - return result; - } - - return result; -} -EXPORT_SYMBOL(snd_midi_event_encode); - /* * read one byte and encode to sequencer event: - * return 1 if MIDI bytes are encoded to an event - * 0 data is not finished - * negative for error + * return true if MIDI bytes are encoded to an event + * false data is not finished */ -int snd_midi_event_encode_byte(struct snd_midi_event *dev, int c, - struct snd_seq_event *ev) +bool snd_midi_event_encode_byte(struct snd_midi_event *dev, unsigned char c, + struct snd_seq_event *ev) { - int rc = 0; + bool rc = false; unsigned long flags; - c &= 0xff; - if (c >= MIDI_CMD_COMMON_CLOCK) { /* real-time event */ ev->type = status_event[ST_SPECIAL + c - 0xf0].event; @@ -293,7 +265,7 @@ int snd_midi_event_encode_byte(struct snd_midi_event *dev, int c, status_event[dev->type].encode(dev, ev); if (dev->type >= ST_SPECIAL) dev->type = ST_INVALID; - rc = 1; + rc = true; } else if (dev->type == ST_SYSEX) { if (c == MIDI_CMD_COMMON_SYSEX_END || dev->read >= dev->bufsize) { @@ -306,7 +278,7 @@ int snd_midi_event_encode_byte(struct snd_midi_event *dev, int c, dev->read = 0; /* continue to parse */ else reset_encode(dev); /* all parsed */ - rc = 1; + rc = true; } } diff --git a/sound/core/seq/seq_virmidi.c b/sound/core/seq/seq_virmidi.c index 03ac5e72dbe6..0c84926eb726 100644 --- a/sound/core/seq/seq_virmidi.c +++ b/sound/core/seq/seq_virmidi.c @@ -174,8 +174,8 @@ static void snd_vmidi_output_work(struct work_struct *work) while (READ_ONCE(vmidi->trigger)) { if (snd_rawmidi_transmit(substream, &input, 1) != 1) break; - if (snd_midi_event_encode_byte(vmidi->parser, input, - &vmidi->event) <= 0) + if (!snd_midi_event_encode_byte(vmidi->parser, input, + &vmidi->event)) continue; if (vmidi->event.type != SNDRV_SEQ_EVENT_NONE) { ret = snd_seq_kernel_client_dispatch(vmidi->client, -- cgit v1.2.3 From dceb219fc60766006bfe8e53afa62816b94fcb11 Mon Sep 17 00:00:00 2001 From: Huang Rui Date: Wed, 1 Aug 2018 13:49:32 +0800 Subject: drm/ttm: Add ttm_set_pages_wc and ttm_set_pages_uc helper MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit These two helpers will be used on set page caching. Reviewed-by: Christian König Signed-off-by: Huang Rui Signed-off-by: Alex Deucher --- include/drm/ttm/ttm_set_memory.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include') diff --git a/include/drm/ttm/ttm_set_memory.h b/include/drm/ttm/ttm_set_memory.h index a70723cf208b..7c492b49e38c 100644 --- a/include/drm/ttm/ttm_set_memory.h +++ b/include/drm/ttm/ttm_set_memory.h @@ -57,6 +57,18 @@ static inline int ttm_set_pages_wb(struct page *page, int numpages) return set_pages_wb(page, numpages); } +static inline int ttm_set_pages_wc(struct page *page, int numpages) +{ + unsigned long addr = (unsigned long)page_address(page); + + return set_memory_wc(addr, numpages); +} + +static inline int ttm_set_pages_uc(struct page *page, int numpages) +{ + return set_pages_uc(page, numpages); +} + #else /* for CONFIG_X86 */ #if IS_ENABLED(CONFIG_AGP) @@ -123,6 +135,16 @@ static inline int ttm_set_pages_wb(struct page *page, int numpages) #endif /* for CONFIG_AGP */ +static inline int ttm_set_pages_wc(struct page *page, int numpages) +{ + return 0; +} + +static inline int ttm_set_pages_uc(struct page *page, int numpages) +{ + return 0; +} + #endif /* for CONFIG_X86 */ #endif -- cgit v1.2.3 From c971e6a006175bd0f195c6346c4e8bc4089bec00 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 28 May 2018 18:27:19 -0400 Subject: kill d_instantiate_no_diralias() The only user is fuse_create_new_entry(), and there it's used to mitigate the same mkdir/open-by-handle race as in nfs_mkdir(). The same solution applies - unhash the mkdir argument, then call d_splice_alias() and if that returns a reference to preexisting alias, dput() and report success. ->mkdir() argument left unhashed negative with the preexisting alias moved in the right place is just fine from the ->mkdir() callers point of view. Cc: Miklos Szeredi Signed-off-by: Al Viro --- fs/dcache.c | 27 --------------------------- fs/fuse/dir.c | 15 +++++++++++---- include/linux/dcache.h | 1 - 3 files changed, 11 insertions(+), 32 deletions(-) (limited to 'include') diff --git a/fs/dcache.c b/fs/dcache.c index 0e8e5de3c48a..a7d9e7a4c283 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -1899,33 +1899,6 @@ void d_instantiate_new(struct dentry *entry, struct inode *inode) } EXPORT_SYMBOL(d_instantiate_new); -/** - * d_instantiate_no_diralias - instantiate a non-aliased dentry - * @entry: dentry to complete - * @inode: inode to attach to this dentry - * - * Fill in inode information in the entry. If a directory alias is found, then - * return an error (and drop inode). Together with d_materialise_unique() this - * guarantees that a directory inode may never have more than one alias. - */ -int d_instantiate_no_diralias(struct dentry *entry, struct inode *inode) -{ - BUG_ON(!hlist_unhashed(&entry->d_u.d_alias)); - - security_d_instantiate(entry, inode); - spin_lock(&inode->i_lock); - if (S_ISDIR(inode->i_mode) && !hlist_empty(&inode->i_dentry)) { - spin_unlock(&inode->i_lock); - iput(inode); - return -EBUSY; - } - __d_instantiate(entry, inode); - spin_unlock(&inode->i_lock); - - return 0; -} -EXPORT_SYMBOL(d_instantiate_no_diralias); - struct dentry *d_make_root(struct inode *root_inode) { struct dentry *res = NULL; diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 56231b31f806..4bbae6ac75c3 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -539,6 +539,7 @@ static int create_new_entry(struct fuse_conn *fc, struct fuse_args *args, { struct fuse_entry_out outarg; struct inode *inode; + struct dentry *d; int err; struct fuse_forget_link *forget; @@ -570,11 +571,17 @@ static int create_new_entry(struct fuse_conn *fc, struct fuse_args *args, } kfree(forget); - err = d_instantiate_no_diralias(entry, inode); - if (err) - return err; + d_drop(entry); + d = d_splice_alias(inode, entry); + if (IS_ERR(d)) + return PTR_ERR(d); - fuse_change_entry_timeout(entry, &outarg); + if (d) { + fuse_change_entry_timeout(d, &outarg); + dput(d); + } else { + fuse_change_entry_timeout(entry, &outarg); + } fuse_invalidate_attr(dir); return 0; diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 66c6e17e61e5..0b83629a3d8f 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -227,7 +227,6 @@ extern void d_instantiate(struct dentry *, struct inode *); extern void d_instantiate_new(struct dentry *, struct inode *); extern struct dentry * d_instantiate_unique(struct dentry *, struct inode *); extern struct dentry * d_instantiate_anon(struct dentry *, struct inode *); -extern int d_instantiate_no_diralias(struct dentry *, struct inode *); extern void __d_drop(struct dentry *dentry); extern void d_drop(struct dentry *dentry); extern void d_delete(struct dentry *); -- cgit v1.2.3 From fdec79c18b08c68cfa079f2d3ee23c5a120a2eda Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Thu, 2 Aug 2018 01:47:30 +0000 Subject: ASoC: fsi: convert to SPDX identifiers Signed-off-by: Kuninori Morimoto Signed-off-by: Mark Brown --- include/sound/sh_fsi.h | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/sound/sh_fsi.h b/include/sound/sh_fsi.h index 7a9710b4b799..89eafe23ef88 100644 --- a/include/sound/sh_fsi.h +++ b/include/sound/sh_fsi.h @@ -1,16 +1,13 @@ -#ifndef __SOUND_FSI_H -#define __SOUND_FSI_H - -/* +/* SPDX-License-Identifier: GPL-2.0 + * * Fifo-attached Serial Interface (FSI) support for SH7724 * * Copyright (C) 2009 Renesas Solutions Corp. * Kuninori Morimoto - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ +#ifndef __SOUND_FSI_H +#define __SOUND_FSI_H + #include #include -- cgit v1.2.3 From 83b15832ab91c9a4651decb6dc40075dd979d443 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Wed, 25 Jul 2018 12:38:10 -0400 Subject: media: doc-rst: Add packed Bayer raw14 pixel formats These formats are compressed 14-bit raw bayer formats with four different pixel orders. They are similar to 10-bit variants. The formats added by this patch are V4L2_PIX_FMT_SBGGR14P V4L2_PIX_FMT_SGBRG14P V4L2_PIX_FMT_SGRBG14P V4L2_PIX_FMT_SRGGB14P Signed-off-by: Sakari Ailus Acked-by: Hans Verkuil Signed-off-by: Todor Tomov Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- Documentation/media/uapi/v4l/pixfmt-rgb.rst | 1 + Documentation/media/uapi/v4l/pixfmt-srggb14p.rst | 127 +++++++++++++++++++++++ drivers/media/v4l2-core/v4l2-ioctl.c | 4 + include/uapi/linux/videodev2.h | 5 + 4 files changed, 137 insertions(+) create mode 100644 Documentation/media/uapi/v4l/pixfmt-srggb14p.rst (limited to 'include') diff --git a/Documentation/media/uapi/v4l/pixfmt-rgb.rst b/Documentation/media/uapi/v4l/pixfmt-rgb.rst index cf2ef7df9616..1f9a7e3a07c9 100644 --- a/Documentation/media/uapi/v4l/pixfmt-rgb.rst +++ b/Documentation/media/uapi/v4l/pixfmt-rgb.rst @@ -19,4 +19,5 @@ RGB Formats pixfmt-srggb10-ipu3 pixfmt-srggb12 pixfmt-srggb12p + pixfmt-srggb14p pixfmt-srggb16 diff --git a/Documentation/media/uapi/v4l/pixfmt-srggb14p.rst b/Documentation/media/uapi/v4l/pixfmt-srggb14p.rst new file mode 100644 index 000000000000..88d20c0e4282 --- /dev/null +++ b/Documentation/media/uapi/v4l/pixfmt-srggb14p.rst @@ -0,0 +1,127 @@ +.. -*- coding: utf-8; mode: rst -*- + +.. _V4L2-PIX-FMT-SRGGB14P: +.. _v4l2-pix-fmt-sbggr14p: +.. _v4l2-pix-fmt-sgbrg14p: +.. _v4l2-pix-fmt-sgrbg14p: + +******************************************************************************************************************************* +V4L2_PIX_FMT_SRGGB14P ('pRCC'), V4L2_PIX_FMT_SGRBG14P ('pgCC'), V4L2_PIX_FMT_SGBRG14P ('pGCC'), V4L2_PIX_FMT_SBGGR14P ('pBCC'), +******************************************************************************************************************************* + +*man V4L2_PIX_FMT_SRGGB14P(2)* + +V4L2_PIX_FMT_SGRBG14P +V4L2_PIX_FMT_SGBRG14P +V4L2_PIX_FMT_SBGGR14P +14-bit packed Bayer formats + + +Description +=========== + +These four pixel formats are packed raw sRGB / Bayer formats with 14 +bits per colour. Every four consecutive samples are packed into seven +bytes. Each of the first four bytes contain the eight high order bits +of the pixels, and the three following bytes contains the six least +significants bits of each pixel, in the same order. + +Each n-pixel row contains n/2 green samples and n/2 blue or red samples, +with alternating green-red and green-blue rows. They are conventionally +described as GRGR... BGBG..., RGRG... GBGB..., etc. Below is an example +of one of these formats: + +**Byte Order.** +Each cell is one byte. + + + +.. flat-table:: + :header-rows: 0 + :stub-columns: 0 + :widths: 2 1 1 1 1 1 1 1 + + + - .. row 1 + + - start + 0: + + - B\ :sub:`00high` + + - G\ :sub:`01high` + + - B\ :sub:`02high` + + - G\ :sub:`03high` + + - G\ :sub:`01low bits 1--0`\ (bits 7--6) + B\ :sub:`00low bits 5--0`\ (bits 5--0) + + - R\ :sub:`02low bits 3--0`\ (bits 7--4) + G\ :sub:`01low bits 5--2`\ (bits 3--0) + + - G\ :sub:`03low bits 5--0`\ (bits 7--2) + R\ :sub:`02low bits 5--4`\ (bits 1--0) + + - .. row 2 + + - start + 7: + + - G\ :sub:`00high` + + - R\ :sub:`01high` + + - G\ :sub:`02high` + + - R\ :sub:`03high` + + - R\ :sub:`01low bits 1--0`\ (bits 7--6) + G\ :sub:`00low bits 5--0`\ (bits 5--0) + + - G\ :sub:`02low bits 3--0`\ (bits 7--4) + R\ :sub:`01low bits 5--2`\ (bits 3--0) + + - R\ :sub:`03low bits 5--0`\ (bits 7--2) + G\ :sub:`02low bits 5--4`\ (bits 1--0) + + - .. row 3 + + - start + 14 + + - B\ :sub:`20high` + + - G\ :sub:`21high` + + - B\ :sub:`22high` + + - G\ :sub:`23high` + + - G\ :sub:`21low bits 1--0`\ (bits 7--6) + B\ :sub:`20low bits 5--0`\ (bits 5--0) + + - R\ :sub:`22low bits 3--0`\ (bits 7--4) + G\ :sub:`21low bits 5--2`\ (bits 3--0) + + - G\ :sub:`23low bits 5--0`\ (bits 7--2) + R\ :sub:`22low bits 5--4`\ (bits 1--0) + + - .. row 4 + + - start + 21 + + - G\ :sub:`30high` + + - R\ :sub:`31high` + + - G\ :sub:`32high` + + - R\ :sub:`33high` + + - R\ :sub:`31low bits 1--0`\ (bits 7--6) + G\ :sub:`30low bits 5--0`\ (bits 5--0) + + - G\ :sub:`32low bits 3--0`\ (bits 7--4) + R\ :sub:`31low bits 5--2`\ (bits 3--0) + + - R\ :sub:`33low bits 5--0`\ (bits 7--2) + G\ :sub:`32low bits 5--4`\ (bits 1--0) diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 26d9702069fd..fd8d15f12307 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1259,6 +1259,10 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_SGBRG12P: descr = "12-bit Bayer GBGB/RGRG Packed"; break; case V4L2_PIX_FMT_SGRBG12P: descr = "12-bit Bayer GRGR/BGBG Packed"; break; case V4L2_PIX_FMT_SRGGB12P: descr = "12-bit Bayer RGRG/GBGB Packed"; break; + case V4L2_PIX_FMT_SBGGR14P: descr = "14-bit Bayer BGBG/GRGR Packed"; break; + case V4L2_PIX_FMT_SGBRG14P: descr = "14-bit Bayer GBGB/RGRG Packed"; break; + case V4L2_PIX_FMT_SGRBG14P: descr = "14-bit Bayer GRGR/BGBG Packed"; break; + case V4L2_PIX_FMT_SRGGB14P: descr = "14-bit Bayer RGRG/GBGB Packed"; break; case V4L2_PIX_FMT_SBGGR16: descr = "16-bit Bayer BGBG/GRGR"; break; case V4L2_PIX_FMT_SGBRG16: descr = "16-bit Bayer GBGB/RGRG"; break; case V4L2_PIX_FMT_SGRBG16: descr = "16-bit Bayer GRGR/BGBG"; break; diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index d8b33095abe0..2c20b6aa5335 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -609,6 +609,11 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_SGBRG12P v4l2_fourcc('p', 'G', 'C', 'C') #define V4L2_PIX_FMT_SGRBG12P v4l2_fourcc('p', 'g', 'C', 'C') #define V4L2_PIX_FMT_SRGGB12P v4l2_fourcc('p', 'R', 'C', 'C') + /* 14bit raw bayer packed, 7 bytes for every 4 pixels */ +#define V4L2_PIX_FMT_SBGGR14P v4l2_fourcc('p', 'B', 'E', 'E') +#define V4L2_PIX_FMT_SGBRG14P v4l2_fourcc('p', 'G', 'E', 'E') +#define V4L2_PIX_FMT_SGRBG14P v4l2_fourcc('p', 'g', 'E', 'E') +#define V4L2_PIX_FMT_SRGGB14P v4l2_fourcc('p', 'R', 'E', 'E') #define V4L2_PIX_FMT_SBGGR16 v4l2_fourcc('B', 'Y', 'R', '2') /* 16 BGBG.. GRGR.. */ #define V4L2_PIX_FMT_SGBRG16 v4l2_fourcc('G', 'B', '1', '6') /* 16 GBGB.. RGRG.. */ #define V4L2_PIX_FMT_SGRBG16 v4l2_fourcc('G', 'R', '1', '6') /* 16 GRGR.. BGBG.. */ -- cgit v1.2.3 From 451af0bf04bd313bbaddd67a8be09d10210780bd Mon Sep 17 00:00:00 2001 From: Todor Tomov Date: Wed, 25 Jul 2018 12:38:11 -0400 Subject: media: v4l: Add new 2X8 10-bit grayscale media bus code The code will be called MEDIA_BUS_FMT_Y10_2X8_PADHI_LE. It is similar to MEDIA_BUS_FMT_SBGGR10_2X8_PADHI_LE but MEDIA_BUS_FMT_Y10_2X8_PADHI_LE describes grayscale data. Signed-off-by: Todor Tomov Acked-by: Sakari Ailus Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- Documentation/media/uapi/v4l/subdev-formats.rst | 72 +++++++++++++++++++++++++ include/uapi/linux/media-bus-format.h | 3 +- 2 files changed, 74 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/Documentation/media/uapi/v4l/subdev-formats.rst b/Documentation/media/uapi/v4l/subdev-formats.rst index a4739f79d9c3..8e73fcfc6900 100644 --- a/Documentation/media/uapi/v4l/subdev-formats.rst +++ b/Documentation/media/uapi/v4l/subdev-formats.rst @@ -4318,6 +4318,78 @@ the following codes. - y\ :sub:`2` - y\ :sub:`1` - y\ :sub:`0` + * .. _MEDIA-BUS-FMT-Y10-2X8-PADHI_LE: + + - MEDIA_BUS_FMT_Y10_2X8_PADHI_LE + - 0x202c + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - y\ :sub:`7` + - y\ :sub:`6` + - y\ :sub:`5` + - y\ :sub:`4` + - y\ :sub:`3` + - y\ :sub:`2` + - y\ :sub:`1` + - y\ :sub:`0` + * - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - 0 + - 0 + - 0 + - 0 + - 0 + - 0 + - y\ :sub:`9` + - y\ :sub:`8` * .. _MEDIA-BUS-FMT-UYVY10-2X10: - MEDIA_BUS_FMT_UYVY10_2X10 diff --git a/include/uapi/linux/media-bus-format.h b/include/uapi/linux/media-bus-format.h index 9e3511742fdc..d6a5a3bfe6c4 100644 --- a/include/uapi/linux/media-bus-format.h +++ b/include/uapi/linux/media-bus-format.h @@ -62,7 +62,7 @@ #define MEDIA_BUS_FMT_RGB121212_1X36 0x1019 #define MEDIA_BUS_FMT_RGB161616_1X48 0x101a -/* YUV (including grey) - next is 0x202c */ +/* YUV (including grey) - next is 0x202d */ #define MEDIA_BUS_FMT_Y8_1X8 0x2001 #define MEDIA_BUS_FMT_UV8_1X8 0x2015 #define MEDIA_BUS_FMT_UYVY8_1_5X8 0x2002 @@ -74,6 +74,7 @@ #define MEDIA_BUS_FMT_YUYV8_2X8 0x2008 #define MEDIA_BUS_FMT_YVYU8_2X8 0x2009 #define MEDIA_BUS_FMT_Y10_1X10 0x200a +#define MEDIA_BUS_FMT_Y10_2X8_PADHI_LE 0x202c #define MEDIA_BUS_FMT_UYVY10_2X10 0x2018 #define MEDIA_BUS_FMT_VYUY10_2X10 0x2019 #define MEDIA_BUS_FMT_YUYV10_2X10 0x200b -- cgit v1.2.3 From 6e15bec49f366511ec024a556505316222ef4ade Mon Sep 17 00:00:00 2001 From: Todor Tomov Date: Wed, 25 Jul 2018 12:38:12 -0400 Subject: media: v4l: Add new 10-bit packed grayscale format The new format will be called V4L2_PIX_FMT_Y10P. It is similar to the V4L2_PIX_FMT_SBGGR10P family formats but V4L2_PIX_FMT_Y10P is a grayscale format. Signed-off-by: Todor Tomov Acked-by: Sakari Ailus Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- Documentation/media/uapi/v4l/pixfmt-y10p.rst | 33 ++++++++++++++++++++++++++++ Documentation/media/uapi/v4l/yuv-formats.rst | 1 + drivers/media/v4l2-core/v4l2-ioctl.c | 1 + include/uapi/linux/videodev2.h | 1 + 4 files changed, 36 insertions(+) create mode 100644 Documentation/media/uapi/v4l/pixfmt-y10p.rst (limited to 'include') diff --git a/Documentation/media/uapi/v4l/pixfmt-y10p.rst b/Documentation/media/uapi/v4l/pixfmt-y10p.rst new file mode 100644 index 000000000000..13b571306915 --- /dev/null +++ b/Documentation/media/uapi/v4l/pixfmt-y10p.rst @@ -0,0 +1,33 @@ +.. -*- coding: utf-8; mode: rst -*- + +.. _V4L2-PIX-FMT-Y10P: + +****************************** +V4L2_PIX_FMT_Y10P ('Y10P') +****************************** + +Grey-scale image as a MIPI RAW10 packed array + + +Description +=========== + +This is a packed grey-scale image format with a depth of 10 bits per +pixel. Every four consecutive pixels are packed into 5 bytes. Each of +the first 4 bytes contain the 8 high order bits of the pixels, and +the 5th byte contains the 2 least significants bits of each pixel, +in the same order. + +**Bit-packed representation.** + +.. flat-table:: + :header-rows: 0 + :stub-columns: 0 + :widths: 8 8 8 8 64 + + * - Y'\ :sub:`00[9:2]` + - Y'\ :sub:`01[9:2]` + - Y'\ :sub:`02[9:2]` + - Y'\ :sub:`03[9:2]` + - Y'\ :sub:`03[1:0]`\ (bits 7--6) Y'\ :sub:`02[1:0]`\ (bits 5--4) + Y'\ :sub:`01[1:0]`\ (bits 3--2) Y'\ :sub:`00[1:0]`\ (bits 1--0) diff --git a/Documentation/media/uapi/v4l/yuv-formats.rst b/Documentation/media/uapi/v4l/yuv-formats.rst index 3334ea445657..9ab0592d08da 100644 --- a/Documentation/media/uapi/v4l/yuv-formats.rst +++ b/Documentation/media/uapi/v4l/yuv-formats.rst @@ -29,6 +29,7 @@ to brightness information. pixfmt-y10 pixfmt-y12 pixfmt-y10b + pixfmt-y10p pixfmt-y16 pixfmt-y16-be pixfmt-y8i diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index fd8d15f12307..54afc9c7ee6e 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1184,6 +1184,7 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_Y16: descr = "16-bit Greyscale"; break; case V4L2_PIX_FMT_Y16_BE: descr = "16-bit Greyscale BE"; break; case V4L2_PIX_FMT_Y10BPACK: descr = "10-bit Greyscale (Packed)"; break; + case V4L2_PIX_FMT_Y10P: descr = "10-bit Greyscale (MIPI Packed)"; break; case V4L2_PIX_FMT_Y8I: descr = "Interleaved 8-bit Greyscale"; break; case V4L2_PIX_FMT_Y12I: descr = "Interleaved 12-bit Greyscale"; break; case V4L2_PIX_FMT_Z16: descr = "16-bit Depth"; break; diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 2c20b6aa5335..5d1a3685bea9 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -522,6 +522,7 @@ struct v4l2_pix_format { /* Grey bit-packed formats */ #define V4L2_PIX_FMT_Y10BPACK v4l2_fourcc('Y', '1', '0', 'B') /* 10 Greyscale bit-packed */ +#define V4L2_PIX_FMT_Y10P v4l2_fourcc('Y', '1', '0', 'P') /* 10 Greyscale, MIPI RAW10 packed */ /* Palette formats */ #define V4L2_PIX_FMT_PAL8 v4l2_fourcc('P', 'A', 'L', '8') /* 8 8-bit palette */ -- cgit v1.2.3 From 06bcb5168d7d49aa3ed449ff13a6d13c30afc3f0 Mon Sep 17 00:00:00 2001 From: Frieder Schrempf Date: Thu, 2 Aug 2018 14:53:52 +0200 Subject: spi: spi-mem: Fix a typo in the documentation of struct spi_mem Fix a typo in the @drvpriv description. Signed-off-by: Frieder Schrempf Acked-by: Boris Brezillon Signed-off-by: Mark Brown --- include/linux/spi/spi-mem.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h index bb4bd15ae1f6..951a2e949d5f 100644 --- a/include/linux/spi/spi-mem.h +++ b/include/linux/spi/spi-mem.h @@ -122,7 +122,7 @@ struct spi_mem_op { /** * struct spi_mem - describes a SPI memory device * @spi: the underlying SPI device - * @drvpriv: spi_mem_drviver private data + * @drvpriv: spi_mem_driver private data * * Extra information that describe the SPI memory device and may be needed by * the controller to properly handle this device should be placed here. -- cgit v1.2.3 From 5d27a9c8ea9e967d00b92a76d4bb242bf7692f2b Mon Sep 17 00:00:00 2001 From: Frieder Schrempf Date: Thu, 2 Aug 2018 14:53:53 +0200 Subject: spi: spi-mem: Extend the SPI mem interface to set a custom memory name When porting (Q)SPI controller drivers from the MTD layer to the SPI layer, the naming scheme for the memory devices changes. To be able to keep compatibility with the old drivers naming scheme, a name field is added to struct spi_mem and a hook is added to let controller drivers set a custom name for the memory device. Example for the FSL QSPI driver: Name with the old driver: 21e0000.qspi, or with multiple devices: 21e0000.qspi-0, 21e0000.qspi-1, ... Name with the new driver without spi_mem_get_name: spi4.0 Suggested-by: Boris Brezillon Signed-off-by: Frieder Schrempf Reviewed-by: Boris Brezillon Signed-off-by: Mark Brown --- drivers/spi/spi-mem.c | 28 ++++++++++++++++++++++++++++ include/linux/spi/spi-mem.h | 12 ++++++++++++ 2 files changed, 40 insertions(+) (limited to 'include') diff --git a/drivers/spi/spi-mem.c b/drivers/spi/spi-mem.c index 990770dfa5cf..e43842c7a31a 100644 --- a/drivers/spi/spi-mem.c +++ b/drivers/spi/spi-mem.c @@ -310,6 +310,24 @@ int spi_mem_exec_op(struct spi_mem *mem, const struct spi_mem_op *op) } EXPORT_SYMBOL_GPL(spi_mem_exec_op); +/** + * spi_mem_get_name() - Return the SPI mem device name to be used by the + * upper layer if necessary + * @mem: the SPI memory + * + * This function allows SPI mem users to retrieve the SPI mem device name. + * It is useful if the upper layer needs to expose a custom name for + * compatibility reasons. + * + * Return: a string containing the name of the memory device to be used + * by the SPI mem user + */ +const char *spi_mem_get_name(struct spi_mem *mem) +{ + return mem->name; +} +EXPORT_SYMBOL_GPL(spi_mem_get_name); + /** * spi_mem_adjust_op_size() - Adjust the data size of a SPI mem operation to * match controller limitations @@ -344,6 +362,7 @@ static inline struct spi_mem_driver *to_spi_mem_drv(struct device_driver *drv) static int spi_mem_probe(struct spi_device *spi) { struct spi_mem_driver *memdrv = to_spi_mem_drv(spi->dev.driver); + struct spi_controller *ctlr = spi->controller; struct spi_mem *mem; mem = devm_kzalloc(&spi->dev, sizeof(*mem), GFP_KERNEL); @@ -351,6 +370,15 @@ static int spi_mem_probe(struct spi_device *spi) return -ENOMEM; mem->spi = spi; + + if (ctlr->mem_ops && ctlr->mem_ops->get_name) + mem->name = ctlr->mem_ops->get_name(mem); + else + mem->name = dev_name(&spi->dev); + + if (IS_ERR_OR_NULL(mem->name)) + return PTR_ERR(mem->name); + spi_set_drvdata(spi, mem); return memdrv->probe(mem); diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h index 951a2e949d5f..0d64ccc4e584 100644 --- a/include/linux/spi/spi-mem.h +++ b/include/linux/spi/spi-mem.h @@ -123,6 +123,7 @@ struct spi_mem_op { * struct spi_mem - describes a SPI memory device * @spi: the underlying SPI device * @drvpriv: spi_mem_driver private data + * @name: name of the SPI memory device * * Extra information that describe the SPI memory device and may be needed by * the controller to properly handle this device should be placed here. @@ -133,6 +134,7 @@ struct spi_mem_op { struct spi_mem { struct spi_device *spi; void *drvpriv; + char *name; }; /** @@ -165,6 +167,13 @@ static inline void *spi_mem_get_drvdata(struct spi_mem *mem) * limitations) * @supports_op: check if an operation is supported by the controller * @exec_op: execute a SPI memory operation + * @get_name: get a custom name for the SPI mem device from the controller. + * This might be needed if the controller driver has been ported + * to use the SPI mem layer and a custom name is used to keep + * mtdparts compatible. + * Note that if the implementation of this function allocates memory + * dynamically, then it should do so with devm_xxx(), as we don't + * have a ->free_name() function. * * This interface should be implemented by SPI controllers providing an * high-level interface to execute SPI memory operation, which is usually the @@ -176,6 +185,7 @@ struct spi_controller_mem_ops { const struct spi_mem_op *op); int (*exec_op)(struct spi_mem *mem, const struct spi_mem_op *op); + const char *(*get_name)(struct spi_mem *mem); }; /** @@ -234,6 +244,8 @@ bool spi_mem_supports_op(struct spi_mem *mem, int spi_mem_exec_op(struct spi_mem *mem, const struct spi_mem_op *op); +const char *spi_mem_get_name(struct spi_mem *mem); + int spi_mem_driver_register_with_owner(struct spi_mem_driver *drv, struct module *owner); -- cgit v1.2.3 From 611cbc8799b672f41b6ba7afed758ad9efb959a7 Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Thu, 2 Aug 2018 16:03:38 +0100 Subject: ASoC: core: remove support for card rebind using component framework DRM based audio components get registered inside the component framework bind callback. However component framework has a big mutex lock taken for every call to component_add, component_del and bind, unbind callbacks. This can lead to deadlock situation if we are trying to add new/remove component within a bind/unbind callbacks. Which is what was happening with bcm2837 rpi 3. Revert this change till we sort out the mutex issue. Reported-by: Guillaume Tucker Reported-by: Stefan Wahren Signed-off-by: Srinivas Kandagatla Signed-off-by: Mark Brown --- include/sound/soc.h | 7 ------ sound/soc/soc-core.c | 62 ---------------------------------------------------- 2 files changed, 69 deletions(-) (limited to 'include') diff --git a/include/sound/soc.h b/include/sound/soc.h index ace474e8649e..41cec42fb456 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -17,7 +17,6 @@ #include #include #include -#include #include #include #include @@ -1091,12 +1090,6 @@ struct snd_soc_card { struct work_struct deferred_resume_work; - /* component framework related */ - bool components_added; - /* set in machine driver to enable/disable auto re-binding */ - bool auto_bind; - struct component_match *match; - /* lists of probed devices belonging to this card */ struct list_head component_dev_list; diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index 81b27923303d..82eb3868be67 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -279,28 +279,11 @@ static inline void snd_soc_debugfs_exit(void) #endif -static int snd_soc_card_comp_compare(struct device *dev, void *data) -{ - struct snd_soc_component *component; - - lockdep_assert_held(&client_mutex); - list_for_each_entry(component, &component_list, list) { - if (dev == component->dev) { - if (!strcmp(component->name, data)) - return 1; - break; - } - } - - return 0; -} - static int snd_soc_rtdcom_add(struct snd_soc_pcm_runtime *rtd, struct snd_soc_component *component) { struct snd_soc_rtdcom_list *rtdcom; struct snd_soc_rtdcom_list *new_rtdcom; - char *cname; for_each_rtdcom(rtd, rtdcom) { /* already connected */ @@ -317,13 +300,6 @@ static int snd_soc_rtdcom_add(struct snd_soc_pcm_runtime *rtd, list_add_tail(&new_rtdcom->list, &rtd->component_list); - if (rtd->card->auto_bind && !rtd->card->components_added) { - cname = devm_kasprintf(rtd->card->dev, GFP_KERNEL, - "%s", component->name); - component_match_add(rtd->card->dev, &rtd->card->match, - snd_soc_card_comp_compare, cname); - } - return 0; } @@ -859,25 +835,6 @@ static bool soc_is_dai_link_bound(struct snd_soc_card *card, return false; } -static int snd_soc_card_comp_bind(struct device *dev) -{ - struct snd_soc_card *card = dev_get_drvdata(dev); - - if (card->instantiated) - return 0; - - return snd_soc_register_card(card); -} - -static void snd_soc_card_comp_unbind(struct device *dev) -{ -} - -static const struct component_master_ops snd_soc_card_comp_ops = { - .bind = snd_soc_card_comp_bind, - .unbind = snd_soc_card_comp_unbind, -}; - static int soc_bind_dai_link(struct snd_soc_card *card, struct snd_soc_dai_link *dai_link) { @@ -2169,12 +2126,6 @@ static int snd_soc_instantiate_card(struct snd_soc_card *card) card->instantiated = 1; snd_soc_dapm_sync(&card->dapm); - if (card->auto_bind && !card->components_added) { - component_master_add_with_match(card->dev, - &snd_soc_card_comp_ops, - card->match); - card->components_added = true; - } mutex_unlock(&card->mutex); mutex_unlock(&client_mutex); @@ -2820,9 +2771,6 @@ int snd_soc_unregister_card(struct snd_soc_card *card) dev_dbg(card->dev, "ASoC: Unregistered card '%s'\n", card->name); } - if (!card->auto_bind && card->components_added) - component_master_del(card->dev, &snd_soc_card_comp_ops); - return 0; } EXPORT_SYMBOL_GPL(snd_soc_unregister_card); @@ -3235,17 +3183,8 @@ int snd_soc_add_component(struct device *dev, snd_soc_component_add(component); - ret = component_add(dev, NULL); - if (ret < 0) { - dev_err(dev, "ASoC: Failed to add Component: %d\n", ret); - goto err_comp; - } - return 0; -err_comp: - soc_remove_component(component); - snd_soc_unregister_dais(component); err_cleanup: snd_soc_component_cleanup(component); err_free: @@ -3293,7 +3232,6 @@ static int __snd_soc_unregister_component(struct device *dev) mutex_unlock(&client_mutex); if (found) { - component_del(dev, NULL); snd_soc_component_cleanup(component); } -- cgit v1.2.3 From a83c0ea79d8b5705d09a39c73224332f9170a903 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Sat, 30 Jun 2018 17:54:59 +0300 Subject: docs/mm: bootmem: add kernel-doc description of 'struct bootmem_data' Signed-off-by: Mike Rapoport Signed-off-by: Jonathan Corbet --- include/linux/bootmem.h | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 7942a96b1a9d..42515195d7d8 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -27,9 +27,20 @@ extern unsigned long max_pfn; extern unsigned long long max_possible_pfn; #ifndef CONFIG_NO_BOOTMEM -/* - * node_bootmem_map is a map pointer - the bits represent all physical - * memory pages (including holes) on the node. +/** + * struct bootmem_data - per-node information used by the bootmem allocator + * @node_min_pfn: the starting physical address of the node's memory + * @node_low_pfn: the end physical address of the directly addressable memory + * @node_bootmem_map: is a bitmap pointer - the bits represent all physical + * memory pages (including holes) on the node. + * @last_end_off: the offset within the page of the end of the last allocation; + * if 0, the page used is full + * @hint_idx: the PFN of the page used with the last allocation; + * together with using this with the @last_end_offset field, + * a test can be made to see if allocations can be merged + * with the page used for the last allocation rather than + * using up a full new page. + * @list: list entry in the linked list ordered by the memory addresses */ typedef struct bootmem_data { unsigned long node_min_pfn; -- cgit v1.2.3 From e1720fee27246dfb84f7c433e35367170a2d4436 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Sat, 30 Jun 2018 17:55:01 +0300 Subject: mm/memblock: add a name for memblock flags enumeration Since kernel-doc does not like anonymous enums the name is required for adding documentation. While on it, I've also updated all the function declarations to use 'enum memblock_flags' instead of unsigned long. Signed-off-by: Mike Rapoport Signed-off-by: Jonathan Corbet --- include/linux/memblock.h | 22 +++++++++++----------- mm/memblock.c | 37 +++++++++++++++++++++---------------- mm/nobootmem.c | 2 +- 3 files changed, 33 insertions(+), 28 deletions(-) (limited to 'include') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index ca59883c8364..8b8fbceffd4d 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -21,7 +21,7 @@ #define INIT_PHYSMEM_REGIONS 4 /* Definition of memblock flags. */ -enum { +enum memblock_flags { MEMBLOCK_NONE = 0x0, /* No special request */ MEMBLOCK_HOTPLUG = 0x1, /* hotpluggable region */ MEMBLOCK_MIRROR = 0x2, /* mirrored region */ @@ -31,7 +31,7 @@ enum { struct memblock_region { phys_addr_t base; phys_addr_t size; - unsigned long flags; + enum memblock_flags flags; #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP int nid; #endif @@ -72,7 +72,7 @@ void memblock_discard(void); phys_addr_t memblock_find_in_range_node(phys_addr_t size, phys_addr_t align, phys_addr_t start, phys_addr_t end, - int nid, ulong flags); + int nid, enum memblock_flags flags); phys_addr_t memblock_find_in_range(phys_addr_t start, phys_addr_t end, phys_addr_t size, phys_addr_t align); void memblock_allow_resize(void); @@ -89,19 +89,19 @@ int memblock_clear_hotplug(phys_addr_t base, phys_addr_t size); int memblock_mark_mirror(phys_addr_t base, phys_addr_t size); int memblock_mark_nomap(phys_addr_t base, phys_addr_t size); int memblock_clear_nomap(phys_addr_t base, phys_addr_t size); -ulong choose_memblock_flags(void); +enum memblock_flags choose_memblock_flags(void); /* Low level functions */ int memblock_add_range(struct memblock_type *type, phys_addr_t base, phys_addr_t size, - int nid, unsigned long flags); + int nid, enum memblock_flags flags); -void __next_mem_range(u64 *idx, int nid, ulong flags, +void __next_mem_range(u64 *idx, int nid, enum memblock_flags flags, struct memblock_type *type_a, struct memblock_type *type_b, phys_addr_t *out_start, phys_addr_t *out_end, int *out_nid); -void __next_mem_range_rev(u64 *idx, int nid, ulong flags, +void __next_mem_range_rev(u64 *idx, int nid, enum memblock_flags flags, struct memblock_type *type_a, struct memblock_type *type_b, phys_addr_t *out_start, phys_addr_t *out_end, int *out_nid); @@ -253,13 +253,13 @@ void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, NUMA_NO_NODE, MEMBLOCK_NONE, p_start, p_end, NULL) static inline void memblock_set_region_flags(struct memblock_region *r, - unsigned long flags) + enum memblock_flags flags) { r->flags |= flags; } static inline void memblock_clear_region_flags(struct memblock_region *r, - unsigned long flags) + enum memblock_flags flags) { r->flags &= ~flags; } @@ -317,10 +317,10 @@ static inline bool memblock_bottom_up(void) phys_addr_t __init memblock_alloc_range(phys_addr_t size, phys_addr_t align, phys_addr_t start, phys_addr_t end, - ulong flags); + enum memblock_flags flags); phys_addr_t memblock_alloc_base_nid(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr, - int nid, ulong flags); + int nid, enum memblock_flags flags); phys_addr_t memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr); phys_addr_t __memblock_alloc_base(phys_addr_t size, phys_addr_t align, diff --git a/mm/memblock.c b/mm/memblock.c index 03d48d8835ba..20f48b49821a 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -60,7 +60,7 @@ static int memblock_can_resize __initdata_memblock; static int memblock_memory_in_slab __initdata_memblock = 0; static int memblock_reserved_in_slab __initdata_memblock = 0; -ulong __init_memblock choose_memblock_flags(void) +enum memblock_flags __init_memblock choose_memblock_flags(void) { return system_has_some_mirror ? MEMBLOCK_MIRROR : MEMBLOCK_NONE; } @@ -109,7 +109,7 @@ bool __init_memblock memblock_overlaps_region(struct memblock_type *type, static phys_addr_t __init_memblock __memblock_find_range_bottom_up(phys_addr_t start, phys_addr_t end, phys_addr_t size, phys_addr_t align, int nid, - ulong flags) + enum memblock_flags flags) { phys_addr_t this_start, this_end, cand; u64 i; @@ -143,7 +143,7 @@ __memblock_find_range_bottom_up(phys_addr_t start, phys_addr_t end, static phys_addr_t __init_memblock __memblock_find_range_top_down(phys_addr_t start, phys_addr_t end, phys_addr_t size, phys_addr_t align, int nid, - ulong flags) + enum memblock_flags flags) { phys_addr_t this_start, this_end, cand; u64 i; @@ -188,7 +188,8 @@ __memblock_find_range_top_down(phys_addr_t start, phys_addr_t end, */ phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size, phys_addr_t align, phys_addr_t start, - phys_addr_t end, int nid, ulong flags) + phys_addr_t end, int nid, + enum memblock_flags flags) { phys_addr_t kernel_end, ret; @@ -251,7 +252,7 @@ phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start, phys_addr_t align) { phys_addr_t ret; - ulong flags = choose_memblock_flags(); + enum memblock_flags flags = choose_memblock_flags(); again: ret = memblock_find_in_range_node(size, align, start, end, @@ -472,7 +473,8 @@ static void __init_memblock memblock_merge_regions(struct memblock_type *type) static void __init_memblock memblock_insert_region(struct memblock_type *type, int idx, phys_addr_t base, phys_addr_t size, - int nid, unsigned long flags) + int nid, + enum memblock_flags flags) { struct memblock_region *rgn = &type->regions[idx]; @@ -504,7 +506,7 @@ static void __init_memblock memblock_insert_region(struct memblock_type *type, */ int __init_memblock memblock_add_range(struct memblock_type *type, phys_addr_t base, phys_addr_t size, - int nid, unsigned long flags) + int nid, enum memblock_flags flags) { bool insert = false; phys_addr_t obase = base; @@ -873,7 +875,8 @@ void __init_memblock __next_reserved_mem_region(u64 *idx, * As both region arrays are sorted, the function advances the two indices * in lockstep and returns each intersection. */ -void __init_memblock __next_mem_range(u64 *idx, int nid, ulong flags, +void __init_memblock __next_mem_range(u64 *idx, int nid, + enum memblock_flags flags, struct memblock_type *type_a, struct memblock_type *type_b, phys_addr_t *out_start, @@ -982,7 +985,8 @@ void __init_memblock __next_mem_range(u64 *idx, int nid, ulong flags, * * Reverse of __next_mem_range(). */ -void __init_memblock __next_mem_range_rev(u64 *idx, int nid, ulong flags, +void __init_memblock __next_mem_range_rev(u64 *idx, int nid, + enum memblock_flags flags, struct memblock_type *type_a, struct memblock_type *type_b, phys_addr_t *out_start, @@ -1140,7 +1144,8 @@ int __init_memblock memblock_set_node(phys_addr_t base, phys_addr_t size, static phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size, phys_addr_t align, phys_addr_t start, - phys_addr_t end, int nid, ulong flags) + phys_addr_t end, int nid, + enum memblock_flags flags) { phys_addr_t found; @@ -1162,7 +1167,7 @@ static phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size, phys_addr_t __init memblock_alloc_range(phys_addr_t size, phys_addr_t align, phys_addr_t start, phys_addr_t end, - ulong flags) + enum memblock_flags flags) { return memblock_alloc_range_nid(size, align, start, end, NUMA_NO_NODE, flags); @@ -1170,14 +1175,14 @@ phys_addr_t __init memblock_alloc_range(phys_addr_t size, phys_addr_t align, phys_addr_t __init memblock_alloc_base_nid(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr, - int nid, ulong flags) + int nid, enum memblock_flags flags) { return memblock_alloc_range_nid(size, align, 0, max_addr, nid, flags); } phys_addr_t __init memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int nid) { - ulong flags = choose_memblock_flags(); + enum memblock_flags flags = choose_memblock_flags(); phys_addr_t ret; again: @@ -1258,7 +1263,7 @@ static void * __init memblock_virt_alloc_internal( { phys_addr_t alloc; void *ptr; - ulong flags = choose_memblock_flags(); + enum memblock_flags flags = choose_memblock_flags(); if (WARN_ONCE(nid == MAX_NUMNODES, "Usage of MAX_NUMNODES is deprecated. Use NUMA_NO_NODE instead\n")) nid = NUMA_NO_NODE; @@ -1733,7 +1738,7 @@ phys_addr_t __init_memblock memblock_get_current_limit(void) static void __init_memblock memblock_dump(struct memblock_type *type) { phys_addr_t base, end, size; - unsigned long flags; + enum memblock_flags flags; int idx; struct memblock_region *rgn; @@ -1751,7 +1756,7 @@ static void __init_memblock memblock_dump(struct memblock_type *type) snprintf(nid_buf, sizeof(nid_buf), " on node %d", memblock_get_region_node(rgn)); #endif - pr_info(" %s[%#x]\t[%pa-%pa], %pa bytes%s flags: %#lx\n", + pr_info(" %s[%#x]\t[%pa-%pa], %pa bytes%s flags: %#x\n", type->name, idx, &base, &end, &size, nid_buf, flags); } } diff --git a/mm/nobootmem.c b/mm/nobootmem.c index c2cfa04f0231..439af3b765a7 100644 --- a/mm/nobootmem.c +++ b/mm/nobootmem.c @@ -42,7 +42,7 @@ static void * __init __alloc_memory_core_early(int nid, u64 size, u64 align, { void *ptr; u64 addr; - ulong flags = choose_memblock_flags(); + enum memblock_flags flags = choose_memblock_flags(); if (limit > memblock.current_limit) limit = memblock.current_limit; -- cgit v1.2.3 From 47cec4432ab06c4ba90c241b142a016f878ac6da Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Sat, 30 Jun 2018 17:55:02 +0300 Subject: docs/mm: memblock: update kernel-doc comments * make memblock_discard description kernel-doc compatible * add brief description for memblock_setclr_flag and describe its parameters * fixup return value descriptions Signed-off-by: Mike Rapoport Signed-off-by: Jonathan Corbet --- include/linux/memblock.h | 17 +++++++--- mm/memblock.c | 84 +++++++++++++++++++++++++++--------------------- 2 files changed, 59 insertions(+), 42 deletions(-) (limited to 'include') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 8b8fbceffd4d..63704c64583a 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -239,7 +239,6 @@ void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, /** * for_each_resv_unavail_range - iterate through reserved and unavailable memory * @i: u64 used as loop variable - * @flags: pick from blocks based on memory attributes * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL * @@ -367,8 +366,10 @@ phys_addr_t memblock_get_current_limit(void); */ /** - * memblock_region_memory_base_pfn - Return the lowest pfn intersecting with the memory region + * memblock_region_memory_base_pfn - get the lowest pfn of the memory region * @reg: memblock_region structure + * + * Return: the lowest pfn intersecting with the memory region */ static inline unsigned long memblock_region_memory_base_pfn(const struct memblock_region *reg) { @@ -376,8 +377,10 @@ static inline unsigned long memblock_region_memory_base_pfn(const struct membloc } /** - * memblock_region_memory_end_pfn - Return the end_pfn this region + * memblock_region_memory_end_pfn - get the end pfn of the memory region * @reg: memblock_region structure + * + * Return: the end_pfn of the reserved region */ static inline unsigned long memblock_region_memory_end_pfn(const struct memblock_region *reg) { @@ -385,8 +388,10 @@ static inline unsigned long memblock_region_memory_end_pfn(const struct memblock } /** - * memblock_region_reserved_base_pfn - Return the lowest pfn intersecting with the reserved region + * memblock_region_reserved_base_pfn - get the lowest pfn of the reserved region * @reg: memblock_region structure + * + * Return: the lowest pfn intersecting with the reserved region */ static inline unsigned long memblock_region_reserved_base_pfn(const struct memblock_region *reg) { @@ -394,8 +399,10 @@ static inline unsigned long memblock_region_reserved_base_pfn(const struct membl } /** - * memblock_region_reserved_end_pfn - Return the end_pfn this region + * memblock_region_reserved_end_pfn - get the end pfn of the reserved region * @reg: memblock_region structure + * + * Return: the end_pfn of the reserved region */ static inline unsigned long memblock_region_reserved_end_pfn(const struct memblock_region *reg) { diff --git a/mm/memblock.c b/mm/memblock.c index 20f48b49821a..4b9dd76f6ae6 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -92,10 +92,11 @@ bool __init_memblock memblock_overlaps_region(struct memblock_type *type, return i < type->cnt; } -/* +/** * __memblock_find_range_bottom_up - find free area utility in bottom-up * @start: start of candidate range - * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE} + * @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or + * %MEMBLOCK_ALLOC_ACCESSIBLE * @size: size of free area to find * @align: alignment of free area to find * @nid: nid of the free area to find, %NUMA_NO_NODE for any node @@ -103,7 +104,7 @@ bool __init_memblock memblock_overlaps_region(struct memblock_type *type, * * Utility called from memblock_find_in_range_node(), find free area bottom-up. * - * RETURNS: + * Return: * Found address on success, 0 on failure. */ static phys_addr_t __init_memblock @@ -129,7 +130,8 @@ __memblock_find_range_bottom_up(phys_addr_t start, phys_addr_t end, /** * __memblock_find_range_top_down - find free area utility, in top-down * @start: start of candidate range - * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE} + * @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or + * %MEMBLOCK_ALLOC_ACCESSIBLE * @size: size of free area to find * @align: alignment of free area to find * @nid: nid of the free area to find, %NUMA_NO_NODE for any node @@ -137,7 +139,7 @@ __memblock_find_range_bottom_up(phys_addr_t start, phys_addr_t end, * * Utility called from memblock_find_in_range_node(), find free area top-down. * - * RETURNS: + * Return: * Found address on success, 0 on failure. */ static phys_addr_t __init_memblock @@ -169,7 +171,8 @@ __memblock_find_range_top_down(phys_addr_t start, phys_addr_t end, * @size: size of free area to find * @align: alignment of free area to find * @start: start of candidate range - * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE} + * @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or + * %MEMBLOCK_ALLOC_ACCESSIBLE * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * @flags: pick from blocks based on memory attributes * @@ -183,7 +186,7 @@ __memblock_find_range_top_down(phys_addr_t start, phys_addr_t end, * * If bottom-up allocation failed, will try to allocate memory top-down. * - * RETURNS: + * Return: * Found address on success, 0 on failure. */ phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size, @@ -238,13 +241,14 @@ phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size, /** * memblock_find_in_range - find free area in given range * @start: start of candidate range - * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE} + * @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or + * %MEMBLOCK_ALLOC_ACCESSIBLE * @size: size of free area to find * @align: alignment of free area to find * * Find @size free area aligned to @align in the specified range. * - * RETURNS: + * Return: * Found address on success, 0 on failure. */ phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start, @@ -288,7 +292,7 @@ static void __init_memblock memblock_remove_region(struct memblock_type *type, u #ifdef CONFIG_ARCH_DISCARD_MEMBLOCK /** - * Discard memory and reserved arrays if they were allocated + * memblock_discard - discard memory and reserved arrays if they were allocated */ void __init memblock_discard(void) { @@ -318,11 +322,11 @@ void __init memblock_discard(void) * * Double the size of the @type regions array. If memblock is being used to * allocate memory for a new reserved regions array and there is a previously - * allocated memory range [@new_area_start,@new_area_start+@new_area_size] + * allocated memory range [@new_area_start, @new_area_start + @new_area_size] * waiting to be reserved, ensure the memory used by the new array does * not overlap. * - * RETURNS: + * Return: * 0 on success, -1 on failure. */ static int __init_memblock memblock_double_array(struct memblock_type *type, @@ -467,7 +471,7 @@ static void __init_memblock memblock_merge_regions(struct memblock_type *type) * @nid: node id of the new region * @flags: flags of the new region * - * Insert new memblock region [@base,@base+@size) into @type at @idx. + * Insert new memblock region [@base, @base + @size) into @type at @idx. * @type must already have extra room to accommodate the new region. */ static void __init_memblock memblock_insert_region(struct memblock_type *type, @@ -496,12 +500,12 @@ static void __init_memblock memblock_insert_region(struct memblock_type *type, * @nid: nid of the new region * @flags: flags of the new region * - * Add new memblock region [@base,@base+@size) into @type. The new region + * Add new memblock region [@base, @base + @size) into @type. The new region * is allowed to overlap with existing ones - overlaps don't affect already * existing regions. @type is guaranteed to be minimal (all neighbouring * compatible regions are merged) after the addition. * - * RETURNS: + * Return: * 0 on success, -errno on failure. */ int __init_memblock memblock_add_range(struct memblock_type *type, @@ -615,11 +619,11 @@ int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size) * @end_rgn: out parameter for the end of isolated region * * Walk @type and ensure that regions don't cross the boundaries defined by - * [@base,@base+@size). Crossing regions are split at the boundaries, + * [@base, @base + @size). Crossing regions are split at the boundaries, * which may create at most two more regions. The index of the first * region inside the range is returned in *@start_rgn and end in *@end_rgn. * - * RETURNS: + * Return: * 0 on success, -errno on failure. */ static int __init_memblock memblock_isolate_range(struct memblock_type *type, @@ -730,10 +734,15 @@ int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size) } /** + * memblock_setclr_flag - set or clear flag for a memory region + * @base: base address of the region + * @size: size of the region + * @set: set or clear the flag + * @flag: the flag to udpate * * This function isolates region [@base, @base + @size), and sets/clears flag * - * Return 0 on success, -errno on failure. + * Return: 0 on success, -errno on failure. */ static int __init_memblock memblock_setclr_flag(phys_addr_t base, phys_addr_t size, int set, int flag) @@ -760,7 +769,7 @@ static int __init_memblock memblock_setclr_flag(phys_addr_t base, * @base: the base phys addr of the region * @size: the size of the region * - * Return 0 on success, -errno on failure. + * Return: 0 on success, -errno on failure. */ int __init_memblock memblock_mark_hotplug(phys_addr_t base, phys_addr_t size) { @@ -772,7 +781,7 @@ int __init_memblock memblock_mark_hotplug(phys_addr_t base, phys_addr_t size) * @base: the base phys addr of the region * @size: the size of the region * - * Return 0 on success, -errno on failure. + * Return: 0 on success, -errno on failure. */ int __init_memblock memblock_clear_hotplug(phys_addr_t base, phys_addr_t size) { @@ -784,7 +793,7 @@ int __init_memblock memblock_clear_hotplug(phys_addr_t base, phys_addr_t size) * @base: the base phys addr of the region * @size: the size of the region * - * Return 0 on success, -errno on failure. + * Return: 0 on success, -errno on failure. */ int __init_memblock memblock_mark_mirror(phys_addr_t base, phys_addr_t size) { @@ -798,7 +807,7 @@ int __init_memblock memblock_mark_mirror(phys_addr_t base, phys_addr_t size) * @base: the base phys addr of the region * @size: the size of the region * - * Return 0 on success, -errno on failure. + * Return: 0 on success, -errno on failure. */ int __init_memblock memblock_mark_nomap(phys_addr_t base, phys_addr_t size) { @@ -810,7 +819,7 @@ int __init_memblock memblock_mark_nomap(phys_addr_t base, phys_addr_t size) * @base: the base phys addr of the region * @size: the size of the region * - * Return 0 on success, -errno on failure. + * Return: 0 on success, -errno on failure. */ int __init_memblock memblock_clear_nomap(phys_addr_t base, phys_addr_t size) { @@ -971,9 +980,6 @@ void __init_memblock __next_mem_range(u64 *idx, int nid, /** * __next_mem_range_rev - generic next function for for_each_*_range_rev() * - * Finds the next range from type_a which is not marked as unsuitable - * in type_b. - * * @idx: pointer to u64 loop variable * @nid: node selector, %NUMA_NO_NODE for all nodes * @flags: pick from blocks based on memory attributes @@ -983,6 +989,9 @@ void __init_memblock __next_mem_range(u64 *idx, int nid, * @out_end: ptr to phys_addr_t for end address of the range, can be %NULL * @out_nid: ptr to int for nid of the range, can be %NULL * + * Finds the next range from type_a which is not marked as unsuitable + * in type_b. + * * Reverse of __next_mem_range(). */ void __init_memblock __next_mem_range_rev(u64 *idx, int nid, @@ -1118,10 +1127,10 @@ void __init_memblock __next_mem_pfn_range(int *idx, int nid, * @type: memblock type to set node ID for * @nid: node ID to set * - * Set the nid of memblock @type regions in [@base,@base+@size) to @nid. + * Set the nid of memblock @type regions in [@base, @base + @size) to @nid. * Regions which cross the area boundaries are split as necessary. * - * RETURNS: + * Return: * 0 on success, -errno on failure. */ int __init_memblock memblock_set_node(phys_addr_t base, phys_addr_t size, @@ -1245,7 +1254,7 @@ phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, i * The allocation is performed from memory region limited by * memblock.current_limit if @max_addr == %BOOTMEM_ALLOC_ACCESSIBLE. * - * The memory block is aligned on SMP_CACHE_BYTES if @align == 0. + * The memory block is aligned on %SMP_CACHE_BYTES if @align == 0. * * The phys address of allocated boot memory block is converted to virtual and * allocated memory is reset to 0. @@ -1253,7 +1262,7 @@ phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, i * In addition, function sets the min_count to 0 using kmemleak_alloc for * allocated boot memory block, so that it is never reported as leaks. * - * RETURNS: + * Return: * Virtual address of allocated memory block on success, NULL on failure. */ static void * __init memblock_virt_alloc_internal( @@ -1338,7 +1347,7 @@ done: * info), if enabled. Does not zero allocated memory, does not panic if request * cannot be satisfied. * - * RETURNS: + * Return: * Virtual address of allocated memory block on success, NULL on failure. */ void * __init memblock_virt_alloc_try_nid_raw( @@ -1375,7 +1384,7 @@ void * __init memblock_virt_alloc_try_nid_raw( * Public function, provides additional debug information (including caller * info), if enabled. This function zeroes the allocated memory. * - * RETURNS: + * Return: * Virtual address of allocated memory block on success, NULL on failure. */ void * __init memblock_virt_alloc_try_nid_nopanic( @@ -1411,7 +1420,7 @@ void * __init memblock_virt_alloc_try_nid_nopanic( * which provides debug information (including caller info), if enabled, * and panics if the request can not be satisfied. * - * RETURNS: + * Return: * Virtual address of allocated memory block on success, NULL on failure. */ void * __init memblock_virt_alloc_try_nid( @@ -1668,9 +1677,9 @@ int __init_memblock memblock_search_pfn_nid(unsigned long pfn, * @base: base of region to check * @size: size of region to check * - * Check if the region [@base, @base+@size) is a subset of a memory block. + * Check if the region [@base, @base + @size) is a subset of a memory block. * - * RETURNS: + * Return: * 0 if false, non-zero if true */ bool __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t size) @@ -1689,9 +1698,10 @@ bool __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t siz * @base: base of region to check * @size: size of region to check * - * Check if the region [@base, @base+@size) intersects a reserved memory block. + * Check if the region [@base, @base + @size) intersects a reserved + * memory block. * - * RETURNS: + * Return: * True if they intersect, false if not. */ bool __init_memblock memblock_is_region_reserved(phys_addr_t base, phys_addr_t size) -- cgit v1.2.3 From 9a0de1bfe191220cb0437865261ab2f95cbb13ef Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Sat, 30 Jun 2018 17:55:04 +0300 Subject: docs/mm: memblock: add kernel-doc description for memblock types Signed-off-by: Mike Rapoport Signed-off-by: Jonathan Corbet --- include/linux/memblock.h | 37 +++++++++++++++++++++++++++++++++---- 1 file changed, 33 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 63704c64583a..516920549378 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -20,7 +20,13 @@ #define INIT_MEMBLOCK_REGIONS 128 #define INIT_PHYSMEM_REGIONS 4 -/* Definition of memblock flags. */ +/** + * enum memblock_flags - definition of memory region attributes + * @MEMBLOCK_NONE: no special request + * @MEMBLOCK_HOTPLUG: hotpluggable region + * @MEMBLOCK_MIRROR: mirrored region + * @MEMBLOCK_NOMAP: don't add to kernel direct mapping + */ enum memblock_flags { MEMBLOCK_NONE = 0x0, /* No special request */ MEMBLOCK_HOTPLUG = 0x1, /* hotpluggable region */ @@ -28,6 +34,13 @@ enum memblock_flags { MEMBLOCK_NOMAP = 0x4, /* don't add to kernel direct mapping */ }; +/** + * struct memblock_region - represents a memory region + * @base: physical address of the region + * @size: size of the region + * @flags: memory region attributes + * @nid: NUMA node id + */ struct memblock_region { phys_addr_t base; phys_addr_t size; @@ -37,14 +50,30 @@ struct memblock_region { #endif }; +/** + * struct memblock_type - collection of memory regions of certain type + * @cnt: number of regions + * @max: size of the allocated array + * @total_size: size of all regions + * @regions: array of regions + * @name: the memory type symbolic name + */ struct memblock_type { - unsigned long cnt; /* number of regions */ - unsigned long max; /* size of the allocated array */ - phys_addr_t total_size; /* size of all regions */ + unsigned long cnt; + unsigned long max; + phys_addr_t total_size; struct memblock_region *regions; char *name; }; +/** + * struct memblock - memblock allocator metadata + * @bottom_up: is bottom up direction? + * @current_limit: physical address of the current allocation limit + * @memory: usabe memory regions + * @reserved: reserved memory regions + * @physmem: all physical memory + */ struct memblock { bool bottom_up; /* is bottom up direction? */ phys_addr_t current_limit; -- cgit v1.2.3 From 3cd14285a1bb58eaa98c44aec0db4d914fdc8c13 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Thu, 2 Aug 2018 12:12:22 -0500 Subject: scsi: target: make transport_init_session_tags static transport_init_session_tags is only called from target_core_transport.c so make it static. Signed-off-by: Mike Christie Reviewed-by: Bart Van Assche Reviewed-by: Christoph Hellwig Signed-off-by: Martin K. Petersen --- drivers/target/target_core_transport.c | 7 +++---- include/target/target_core_fabric.h | 2 -- 2 files changed, 3 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index b419d4f8cb96..8044b8115dbf 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -304,9 +304,9 @@ EXPORT_SYMBOL(transport_alloc_session_tags); * each command. * @sup_prot_ops: bitmask that defines which T10-PI modes are supported. */ -struct se_session *transport_init_session_tags(unsigned int tag_num, - unsigned int tag_size, - enum target_prot_op sup_prot_ops) +static struct se_session * +transport_init_session_tags(unsigned int tag_num, unsigned int tag_size, + enum target_prot_op sup_prot_ops) { struct se_session *se_sess; int rc; @@ -334,7 +334,6 @@ struct se_session *transport_init_session_tags(unsigned int tag_num, return se_sess; } -EXPORT_SYMBOL(transport_init_session_tags); /* * Called with spin_lock_irqsave(&struct se_portal_group->session_lock called. diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h index f61aa716cfe1..d0d064212bfc 100644 --- a/include/target/target_core_fabric.h +++ b/include/target/target_core_fabric.h @@ -119,8 +119,6 @@ void transport_init_session(struct se_session *); struct se_session *transport_alloc_session(enum target_prot_op); int transport_alloc_session_tags(struct se_session *, unsigned int, unsigned int); -struct se_session *transport_init_session_tags(unsigned int, unsigned int, - enum target_prot_op); void __transport_register_session(struct se_portal_group *, struct se_node_acl *, struct se_session *, void *); void transport_register_session(struct se_portal_group *, -- cgit v1.2.3 From fa834287300ba6a89e0a590f520a3398527eb541 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Thu, 2 Aug 2018 12:12:23 -0500 Subject: scsi: target: rename target_alloc_session Rename target_alloc_session to target_setup_session to avoid confusion with the other transport session allocation function that only allocates the session and because the target_alloc_session does so much more. It allocates the session, sets up the nacl and registers the session. The next patch will then add a remove function to match the setup in this one, so it should make sense for all drivers, except iscsi, to just call those 2 functions to setup and remove a session. iscsi will continue to be the odd driver. Signed-off-by: Mike Christie Reviewed-by: Bart Van Assche Reviewed-by: Christoph Hellwig Cc: Chris Boot Cc: Bryant G. Ly Cc: Michael Cyr Cc: Cc: Johannes Thumshirn Cc: Felipe Balbi Cc: Sebastian Andrzej Siewior Cc: Andrzej Pietrasiewicz Cc: Michael S. Tsirkin Cc: Juergen Gross Signed-off-by: Martin K. Petersen --- drivers/infiniband/ulp/srpt/ib_srpt.c | 6 +++--- drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c | 2 +- drivers/scsi/qla2xxx/tcm_qla2xxx.c | 2 +- drivers/target/loopback/tcm_loop.c | 2 +- drivers/target/sbp/sbp_target.c | 2 +- drivers/target/target_core_transport.c | 4 ++-- drivers/target/tcm_fc/tfc_sess.c | 2 +- drivers/usb/gadget/function/f_tcm.c | 2 +- drivers/vhost/scsi.c | 2 +- drivers/xen/xen-scsiback.c | 2 +- include/target/target_core_fabric.h | 2 +- 11 files changed, 14 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c index 07b3e1c583bd..21435a73771a 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.c +++ b/drivers/infiniband/ulp/srpt/ib_srpt.c @@ -2221,16 +2221,16 @@ static int srpt_cm_req_recv(struct srpt_device *const sdev, pr_debug("registering session %s\n", ch->sess_name); if (sport->port_guid_tpg.se_tpg_wwn) - ch->sess = target_alloc_session(&sport->port_guid_tpg, 0, 0, + ch->sess = target_setup_session(&sport->port_guid_tpg, 0, 0, TARGET_PROT_NORMAL, ch->sess_name, ch, NULL); if (sport->port_gid_tpg.se_tpg_wwn && IS_ERR_OR_NULL(ch->sess)) - ch->sess = target_alloc_session(&sport->port_gid_tpg, 0, 0, + ch->sess = target_setup_session(&sport->port_gid_tpg, 0, 0, TARGET_PROT_NORMAL, i_port_id, ch, NULL); /* Retry without leading "0x" */ if (sport->port_gid_tpg.se_tpg_wwn && IS_ERR_OR_NULL(ch->sess)) - ch->sess = target_alloc_session(&sport->port_gid_tpg, 0, 0, + ch->sess = target_setup_session(&sport->port_gid_tpg, 0, 0, TARGET_PROT_NORMAL, i_port_id + 2, ch, NULL); if (IS_ERR_OR_NULL(ch->sess)) { diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c index fdda04e5cf94..1bdf9379c4ce 100644 --- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c +++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c @@ -2233,7 +2233,7 @@ static int ibmvscsis_make_nexus(struct ibmvscsis_tport *tport) return -ENOMEM; } - nexus->se_sess = target_alloc_session(&tport->se_tpg, 0, 0, + nexus->se_sess = target_setup_session(&tport->se_tpg, 0, 0, TARGET_PROT_NORMAL, name, nexus, NULL); if (IS_ERR(nexus->se_sess)) { diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c index cfb5d6067f9f..b9ce4e7e1c3e 100644 --- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c +++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c @@ -1539,7 +1539,7 @@ static int tcm_qla2xxx_check_initiator_node_acl( * Locate our struct se_node_acl either from an explict NodeACL created * via ConfigFS, or via running in TPG demo mode. */ - se_sess = target_alloc_session(&tpg->se_tpg, num_tags, + se_sess = target_setup_session(&tpg->se_tpg, num_tags, sizeof(struct qla_tgt_cmd), TARGET_PROT_ALL, port_name, qlat_sess, tcm_qla2xxx_session_cb); diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c index b2e7ff50ff61..54b5b94dad37 100644 --- a/drivers/target/loopback/tcm_loop.c +++ b/drivers/target/loopback/tcm_loop.c @@ -765,7 +765,7 @@ static int tcm_loop_make_nexus( if (!tl_nexus) return -ENOMEM; - tl_nexus->se_sess = target_alloc_session(&tl_tpg->tl_se_tpg, 0, 0, + tl_nexus->se_sess = target_setup_session(&tl_tpg->tl_se_tpg, 0, 0, TARGET_PROT_DIN_PASS | TARGET_PROT_DOUT_PASS, name, tl_nexus, tcm_loop_alloc_sess_cb); if (IS_ERR(tl_nexus->se_sess)) { diff --git a/drivers/target/sbp/sbp_target.c b/drivers/target/sbp/sbp_target.c index b61b79ac98ff..c4369b52a3fb 100644 --- a/drivers/target/sbp/sbp_target.c +++ b/drivers/target/sbp/sbp_target.c @@ -209,7 +209,7 @@ static struct sbp_session *sbp_session_create( INIT_DELAYED_WORK(&sess->maint_work, session_maintenance_work); sess->guid = guid; - sess->se_sess = target_alloc_session(&tpg->se_tpg, 128, + sess->se_sess = target_setup_session(&tpg->se_tpg, 128, sizeof(struct sbp_target_request), TARGET_PROT_NORMAL, guid_str, sess, NULL); diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 8044b8115dbf..57fadec2d1ae 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -416,7 +416,7 @@ void transport_register_session( EXPORT_SYMBOL(transport_register_session); struct se_session * -target_alloc_session(struct se_portal_group *tpg, +target_setup_session(struct se_portal_group *tpg, unsigned int tag_num, unsigned int tag_size, enum target_prot_op prot_op, const char *initiatorname, void *private, @@ -458,7 +458,7 @@ target_alloc_session(struct se_portal_group *tpg, transport_register_session(tpg, sess->se_node_acl, sess, private); return sess; } -EXPORT_SYMBOL(target_alloc_session); +EXPORT_SYMBOL(target_setup_session); ssize_t target_show_dynamic_sessions(struct se_portal_group *se_tpg, char *page) { diff --git a/drivers/target/tcm_fc/tfc_sess.c b/drivers/target/tcm_fc/tfc_sess.c index c91979c1463d..efd7d5e5bfc4 100644 --- a/drivers/target/tcm_fc/tfc_sess.c +++ b/drivers/target/tcm_fc/tfc_sess.c @@ -239,7 +239,7 @@ static struct ft_sess *ft_sess_create(struct ft_tport *tport, u32 port_id, sess->tport = tport; sess->port_id = port_id; - sess->se_sess = target_alloc_session(se_tpg, TCM_FC_DEFAULT_TAGS, + sess->se_sess = target_setup_session(se_tpg, TCM_FC_DEFAULT_TAGS, sizeof(struct ft_cmd), TARGET_PROT_NORMAL, &initiatorname[0], sess, ft_sess_alloc_cb); diff --git a/drivers/usb/gadget/function/f_tcm.c b/drivers/usb/gadget/function/f_tcm.c index 4f183176b0b4..ba7c5f68d38a 100644 --- a/drivers/usb/gadget/function/f_tcm.c +++ b/drivers/usb/gadget/function/f_tcm.c @@ -1592,7 +1592,7 @@ static int tcm_usbg_make_nexus(struct usbg_tpg *tpg, char *name) goto out_unlock; } - tv_nexus->tvn_se_sess = target_alloc_session(&tpg->se_tpg, + tv_nexus->tvn_se_sess = target_setup_session(&tpg->se_tpg, USB_G_DEFAULT_SESSION_TAGS, sizeof(struct usbg_cmd), TARGET_PROT_NORMAL, name, diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index c84a6edd4c25..e9368842c63f 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -1738,7 +1738,7 @@ static int vhost_scsi_make_nexus(struct vhost_scsi_tpg *tpg, * struct se_node_acl for the vhost_scsi struct se_portal_group with * the SCSI Initiator port name of the passed configfs group 'name'. */ - tv_nexus->tvn_se_sess = target_alloc_session(&tpg->se_tpg, + tv_nexus->tvn_se_sess = target_setup_session(&tpg->se_tpg, VHOST_SCSI_DEFAULT_TAGS, sizeof(struct vhost_scsi_cmd), TARGET_PROT_DIN_PASS | TARGET_PROT_DOUT_PASS, diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c index fd77ccfc7d6e..2ffc7ed944d8 100644 --- a/drivers/xen/xen-scsiback.c +++ b/drivers/xen/xen-scsiback.c @@ -1521,7 +1521,7 @@ static int scsiback_make_nexus(struct scsiback_tpg *tpg, goto out_unlock; } - tv_nexus->tvn_se_sess = target_alloc_session(&tpg->se_tpg, + tv_nexus->tvn_se_sess = target_setup_session(&tpg->se_tpg, VSCSI_DEFAULT_SESSION_TAGS, sizeof(struct vscsibk_pend), TARGET_PROT_NORMAL, name, diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h index d0d064212bfc..fbcc9a4025b9 100644 --- a/include/target/target_core_fabric.h +++ b/include/target/target_core_fabric.h @@ -109,7 +109,7 @@ void target_unregister_template(const struct target_core_fabric_ops *fo); int target_depend_item(struct config_item *item); void target_undepend_item(struct config_item *item); -struct se_session *target_alloc_session(struct se_portal_group *, +struct se_session *target_setup_session(struct se_portal_group *, unsigned int, unsigned int, enum target_prot_op prot_op, const char *, void *, int (*callback)(struct se_portal_group *, -- cgit v1.2.3 From fb7c70f2d750a462c5a9757555bc23bf35360cec Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Thu, 2 Aug 2018 12:12:24 -0500 Subject: scsi: target: add session removal function This adds a function to remove a session which should be used by drivers that use target_setup_session. The next patches will convert the target drivers to use this new function. Signed-off-by: Mike Christie Reviewed-by: Bart Van Assche Reviewed-by: Christoph Hellwig Cc: Chris Boot Cc: Bryant G. Ly Cc: Michael Cyr Cc: Cc: Johannes Thumshirn Cc: Felipe Balbi Cc: Sebastian Andrzej Siewior Cc: Andrzej Pietrasiewicz Cc: Michael S. Tsirkin Cc: Juergen Gross Signed-off-by: Martin K. Petersen --- drivers/target/target_core_transport.c | 7 +++++++ include/target/target_core_fabric.h | 1 + 2 files changed, 8 insertions(+) (limited to 'include') diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 57fadec2d1ae..86c0156e6c88 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -616,6 +616,13 @@ void transport_deregister_session(struct se_session *se_sess) } EXPORT_SYMBOL(transport_deregister_session); +void target_remove_session(struct se_session *se_sess) +{ + transport_deregister_session_configfs(se_sess); + transport_deregister_session(se_sess); +} +EXPORT_SYMBOL(target_remove_session); + static void target_remove_from_state_list(struct se_cmd *cmd) { struct se_device *dev = cmd->se_dev; diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h index fbcc9a4025b9..f4147b398431 100644 --- a/include/target/target_core_fabric.h +++ b/include/target/target_core_fabric.h @@ -114,6 +114,7 @@ struct se_session *target_setup_session(struct se_portal_group *, const char *, void *, int (*callback)(struct se_portal_group *, struct se_session *, void *)); +void target_remove_session(struct se_session *); void transport_init_session(struct se_session *); struct se_session *transport_alloc_session(enum target_prot_op); -- cgit v1.2.3 From 2afc9166f79b8f6da5f347f48515215ceee4ae37 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Thu, 2 Aug 2018 10:51:40 -0700 Subject: scsi: sysfs: Introduce sysfs_{un,}break_active_protection() Introduce these two functions and export them such that the next patch can add calls to these functions from the SCSI core. Signed-off-by: Bart Van Assche Acked-by: Tejun Heo Acked-by: Greg Kroah-Hartman Cc: Signed-off-by: Martin K. Petersen --- fs/sysfs/file.c | 44 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/sysfs.h | 14 ++++++++++++++ 2 files changed, 58 insertions(+) (limited to 'include') diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 5c13f29bfcdb..118fa197a35f 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -405,6 +405,50 @@ int sysfs_chmod_file(struct kobject *kobj, const struct attribute *attr, } EXPORT_SYMBOL_GPL(sysfs_chmod_file); +/** + * sysfs_break_active_protection - break "active" protection + * @kobj: The kernel object @attr is associated with. + * @attr: The attribute to break the "active" protection for. + * + * With sysfs, just like kernfs, deletion of an attribute is postponed until + * all active .show() and .store() callbacks have finished unless this function + * is called. Hence this function is useful in methods that implement self + * deletion. + */ +struct kernfs_node *sysfs_break_active_protection(struct kobject *kobj, + const struct attribute *attr) +{ + struct kernfs_node *kn; + + kobject_get(kobj); + kn = kernfs_find_and_get(kobj->sd, attr->name); + if (kn) + kernfs_break_active_protection(kn); + return kn; +} +EXPORT_SYMBOL_GPL(sysfs_break_active_protection); + +/** + * sysfs_unbreak_active_protection - restore "active" protection + * @kn: Pointer returned by sysfs_break_active_protection(). + * + * Undo the effects of sysfs_break_active_protection(). Since this function + * calls kernfs_put() on the kernfs node that corresponds to the 'attr' + * argument passed to sysfs_break_active_protection() that attribute may have + * been removed between the sysfs_break_active_protection() and + * sysfs_unbreak_active_protection() calls, it is not safe to access @kn after + * this function has returned. + */ +void sysfs_unbreak_active_protection(struct kernfs_node *kn) +{ + struct kobject *kobj = kn->parent->priv; + + kernfs_unbreak_active_protection(kn); + kernfs_put(kn); + kobject_put(kobj); +} +EXPORT_SYMBOL_GPL(sysfs_unbreak_active_protection); + /** * sysfs_remove_file_ns - remove an object attribute with a custom ns tag * @kobj: object we're acting for diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index b8bfdc173ec0..3c12198c0103 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -237,6 +237,9 @@ int __must_check sysfs_create_files(struct kobject *kobj, const struct attribute **attr); int __must_check sysfs_chmod_file(struct kobject *kobj, const struct attribute *attr, umode_t mode); +struct kernfs_node *sysfs_break_active_protection(struct kobject *kobj, + const struct attribute *attr); +void sysfs_unbreak_active_protection(struct kernfs_node *kn); void sysfs_remove_file_ns(struct kobject *kobj, const struct attribute *attr, const void *ns); bool sysfs_remove_file_self(struct kobject *kobj, const struct attribute *attr); @@ -350,6 +353,17 @@ static inline int sysfs_chmod_file(struct kobject *kobj, return 0; } +static inline struct kernfs_node * +sysfs_break_active_protection(struct kobject *kobj, + const struct attribute *attr) +{ + return NULL; +} + +static inline void sysfs_unbreak_active_protection(struct kernfs_node *kn) +{ +} + static inline void sysfs_remove_file_ns(struct kobject *kobj, const struct attribute *attr, const void *ns) -- cgit v1.2.3 From a3f90c75b833caeff123499e13e0e31cbecf7d5b Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 5 Jul 2018 18:59:35 -0400 Subject: media: dvb: convert tuner_info frequencies to Hz MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Right now, satellite tuner drivers specify frequencies in kHz, while terrestrial/cable ones specify in Hz. That's confusing for developers. However, the main problem is that universal tuners capable of handling both satellite and non-satelite delivery systems are appearing. We end by needing to hack the drivers in order to support such hybrid tuners. So, convert everything to specify tuner frequencies in Hz. Plese notice that a similar patch is also needed for frontends. Tested-by: Katsuhiro Suzuki Acked-by: Michael Büsch Signed-off-by: Mauro Carvalho Chehab --- drivers/media/dvb-core/dvb_frontend.c | 25 +++++++++++++++++++++---- drivers/media/dvb-frontends/ascot2e.c | 6 +++--- drivers/media/dvb-frontends/cx24113.c | 8 ++++---- drivers/media/dvb-frontends/dib0070.c | 8 ++++---- drivers/media/dvb-frontends/dib0090.c | 12 ++++++------ drivers/media/dvb-frontends/dvb-pll.c | 16 ++++++++++++++-- drivers/media/dvb-frontends/helene.c | 12 ++++++------ drivers/media/dvb-frontends/horus3a.c | 6 +++--- drivers/media/dvb-frontends/itd1000.c | 8 ++++---- drivers/media/dvb-frontends/ix2505v.c | 4 ++-- drivers/media/dvb-frontends/stb6000.c | 4 ++-- drivers/media/dvb-frontends/stb6100.c | 5 ++--- drivers/media/dvb-frontends/stv6110.c | 6 +++--- drivers/media/dvb-frontends/stv6110x.c | 7 +++---- drivers/media/dvb-frontends/stv6111.c | 5 ++--- drivers/media/dvb-frontends/tda18271c2dd.c | 6 +++--- drivers/media/dvb-frontends/tda665x.c | 6 +++--- drivers/media/dvb-frontends/tda8261.c | 9 ++++----- drivers/media/dvb-frontends/tda826x.c | 4 ++-- drivers/media/dvb-frontends/ts2020.c | 4 ++-- drivers/media/dvb-frontends/tua6100.c | 6 +++--- drivers/media/dvb-frontends/zl10036.c | 4 ++-- drivers/media/tuners/e4000.c | 6 +++--- drivers/media/tuners/fc0011.c | 6 +++--- drivers/media/tuners/fc0012.c | 7 +++---- drivers/media/tuners/fc0013.c | 7 +++---- drivers/media/tuners/fc2580.c | 6 +++--- drivers/media/tuners/it913x.c | 6 +++--- drivers/media/tuners/m88rs6000t.c | 6 +++--- drivers/media/tuners/max2165.c | 8 ++++---- drivers/media/tuners/mc44s803.c | 8 ++++---- drivers/media/tuners/mt2060.c | 8 ++++---- drivers/media/tuners/mt2063.c | 7 +++---- drivers/media/tuners/mt2131.c | 8 ++++---- drivers/media/tuners/mt2266.c | 8 ++++---- drivers/media/tuners/mxl301rf.c | 4 ++-- drivers/media/tuners/mxl5005s.c | 8 ++++---- drivers/media/tuners/qm1d1b0004.c | 4 ++-- drivers/media/tuners/qm1d1c0042.c | 4 ++-- drivers/media/tuners/qt1010.c | 8 ++++---- drivers/media/tuners/qt1010_priv.h | 14 ++++++++------ drivers/media/tuners/r820t.c | 6 +++--- drivers/media/tuners/si2157.c | 6 +++--- drivers/media/tuners/tda18212.c | 8 ++++---- drivers/media/tuners/tda18218.c | 8 ++++---- drivers/media/tuners/tda18250.c | 6 +++--- drivers/media/tuners/tda18271-fe.c | 6 +++--- drivers/media/tuners/tda827x.c | 12 ++++++------ drivers/media/tuners/tua9001.c | 6 +++--- drivers/media/tuners/tuner-xc2028.c | 6 +++--- drivers/media/tuners/xc4000.c | 12 ++++++------ drivers/media/tuners/xc5000.c | 12 ++++++------ drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.c | 6 +++--- include/media/dvb_frontend.h | 19 ++++++++++--------- 54 files changed, 221 insertions(+), 196 deletions(-) (limited to 'include') diff --git a/drivers/media/dvb-core/dvb_frontend.c b/drivers/media/dvb-core/dvb_frontend.c index ce25aef39008..75e95b56f8b3 100644 --- a/drivers/media/dvb-core/dvb_frontend.c +++ b/drivers/media/dvb-core/dvb_frontend.c @@ -896,14 +896,31 @@ static int dvb_frontend_start(struct dvb_frontend *fe) static void dvb_frontend_get_frequency_limits(struct dvb_frontend *fe, u32 *freq_min, u32 *freq_max) { - *freq_min = max(fe->ops.info.frequency_min, fe->ops.tuner_ops.info.frequency_min); + struct dtv_frontend_properties *c = &fe->dtv_property_cache; + __u32 tuner_min = fe->ops.tuner_ops.info.frequency_min_hz; + __u32 tuner_max = fe->ops.tuner_ops.info.frequency_max_hz; + + /* If the standard is for satellite, convert frequencies to kHz */ + switch (c->delivery_system) { + case SYS_DVBS: + case SYS_DVBS2: + case SYS_TURBO: + case SYS_ISDBS: + tuner_max /= kHz; + tuner_min /= kHz; + break; + default: + break; + } + + *freq_min = max(fe->ops.info.frequency_min, tuner_min); if (fe->ops.info.frequency_max == 0) - *freq_max = fe->ops.tuner_ops.info.frequency_max; - else if (fe->ops.tuner_ops.info.frequency_max == 0) + *freq_max = tuner_max; + else if (tuner_max == 0) *freq_max = fe->ops.info.frequency_max; else - *freq_max = min(fe->ops.info.frequency_max, fe->ops.tuner_ops.info.frequency_max); + *freq_max = min(fe->ops.info.frequency_max, tuner_max); if (*freq_min == 0 || *freq_max == 0) dev_warn(fe->dvb->device, diff --git a/drivers/media/dvb-frontends/ascot2e.c b/drivers/media/dvb-frontends/ascot2e.c index 9746c6dd7fb8..52ce0e6e2a15 100644 --- a/drivers/media/dvb-frontends/ascot2e.c +++ b/drivers/media/dvb-frontends/ascot2e.c @@ -468,9 +468,9 @@ static int ascot2e_get_frequency(struct dvb_frontend *fe, u32 *frequency) static const struct dvb_tuner_ops ascot2e_tuner_ops = { .info = { .name = "Sony ASCOT2E", - .frequency_min = 1000000, - .frequency_max = 1200000000, - .frequency_step = 25000, + .frequency_min_hz = 1 * MHz, + .frequency_max_hz = 1200 * MHz, + .frequency_step_hz = 25 * kHz, }, .init = ascot2e_init, .release = ascot2e_release, diff --git a/drivers/media/dvb-frontends/cx24113.c b/drivers/media/dvb-frontends/cx24113.c index 037db3e9d2dd..91a5033b6bd7 100644 --- a/drivers/media/dvb-frontends/cx24113.c +++ b/drivers/media/dvb-frontends/cx24113.c @@ -533,10 +533,10 @@ static void cx24113_release(struct dvb_frontend *fe) static const struct dvb_tuner_ops cx24113_tuner_ops = { .info = { - .name = "Conexant CX24113", - .frequency_min = 950000, - .frequency_max = 2150000, - .frequency_step = 125, + .name = "Conexant CX24113", + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2150 * MHz, + .frequency_step_hz = 125 * kHz, }, .release = cx24113_release, diff --git a/drivers/media/dvb-frontends/dib0070.c b/drivers/media/dvb-frontends/dib0070.c index 932d235118e2..37ebd5af8fd4 100644 --- a/drivers/media/dvb-frontends/dib0070.c +++ b/drivers/media/dvb-frontends/dib0070.c @@ -726,10 +726,10 @@ static void dib0070_release(struct dvb_frontend *fe) static const struct dvb_tuner_ops dib0070_ops = { .info = { - .name = "DiBcom DiB0070", - .frequency_min = 45000000, - .frequency_max = 860000000, - .frequency_step = 1000, + .name = "DiBcom DiB0070", + .frequency_min_hz = 45 * MHz, + .frequency_max_hz = 860 * MHz, + .frequency_step_hz = 1 * kHz, }, .release = dib0070_release, diff --git a/drivers/media/dvb-frontends/dib0090.c b/drivers/media/dvb-frontends/dib0090.c index ee7af34979ed..44a074261e69 100644 --- a/drivers/media/dvb-frontends/dib0090.c +++ b/drivers/media/dvb-frontends/dib0090.c @@ -2578,9 +2578,9 @@ static int dib0090_set_params(struct dvb_frontend *fe) static const struct dvb_tuner_ops dib0090_ops = { .info = { .name = "DiBcom DiB0090", - .frequency_min = 45000000, - .frequency_max = 860000000, - .frequency_step = 1000, + .frequency_min_hz = 45 * MHz, + .frequency_max_hz = 860 * MHz, + .frequency_step_hz = 1 * kHz, }, .release = dib0090_release, @@ -2593,9 +2593,9 @@ static const struct dvb_tuner_ops dib0090_ops = { static const struct dvb_tuner_ops dib0090_fw_ops = { .info = { .name = "DiBcom DiB0090", - .frequency_min = 45000000, - .frequency_max = 860000000, - .frequency_step = 1000, + .frequency_min_hz = 45 * MHz, + .frequency_max_hz = 860 * MHz, + .frequency_step_hz = 1 * kHz, }, .release = dib0090_release, diff --git a/drivers/media/dvb-frontends/dvb-pll.c b/drivers/media/dvb-frontends/dvb-pll.c index 4a663420190e..6d4b2eec67b4 100644 --- a/drivers/media/dvb-frontends/dvb-pll.c +++ b/drivers/media/dvb-frontends/dvb-pll.c @@ -799,6 +799,7 @@ struct dvb_frontend *dvb_pll_attach(struct dvb_frontend *fe, int pll_addr, struct dvb_pll_priv *priv = NULL; int ret; const struct dvb_pll_desc *desc; + struct dtv_frontend_properties *c = &fe->dtv_property_cache; b1 = kmalloc(1, GFP_KERNEL); if (!b1) @@ -844,8 +845,19 @@ struct dvb_frontend *dvb_pll_attach(struct dvb_frontend *fe, int pll_addr, strncpy(fe->ops.tuner_ops.info.name, desc->name, sizeof(fe->ops.tuner_ops.info.name)); - fe->ops.tuner_ops.info.frequency_min = desc->min; - fe->ops.tuner_ops.info.frequency_max = desc->max; + switch (c->delivery_system) { + case SYS_DVBS: + case SYS_DVBS2: + case SYS_TURBO: + case SYS_ISDBS: + fe->ops.tuner_ops.info.frequency_min_hz = desc->min * kHz; + fe->ops.tuner_ops.info.frequency_max_hz = desc->max * kHz; + break; + default: + fe->ops.tuner_ops.info.frequency_min_hz = desc->min; + fe->ops.tuner_ops.info.frequency_max_hz = desc->max; + } + if (!desc->initdata) fe->ops.tuner_ops.init = NULL; if (!desc->sleepdata) diff --git a/drivers/media/dvb-frontends/helene.c b/drivers/media/dvb-frontends/helene.c index a5de65dcf784..dc70fb684681 100644 --- a/drivers/media/dvb-frontends/helene.c +++ b/drivers/media/dvb-frontends/helene.c @@ -846,9 +846,9 @@ static int helene_get_frequency(struct dvb_frontend *fe, u32 *frequency) static const struct dvb_tuner_ops helene_tuner_ops = { .info = { .name = "Sony HELENE Ter tuner", - .frequency_min = 1000000, - .frequency_max = 1200000000, - .frequency_step = 25000, + .frequency_min_hz = 1 * MHz, + .frequency_max_hz = 1200 * MHz, + .frequency_step_hz = 25 * kHz, }, .init = helene_init, .release = helene_release, @@ -860,9 +860,9 @@ static const struct dvb_tuner_ops helene_tuner_ops = { static const struct dvb_tuner_ops helene_tuner_ops_s = { .info = { .name = "Sony HELENE Sat tuner", - .frequency_min = 500000, - .frequency_max = 2500000, - .frequency_step = 1000, + .frequency_min_hz = 500 * MHz, + .frequency_max_hz = 2500 * MHz, + .frequency_step_hz = 1 * MHz, }, .init = helene_init, .release = helene_release, diff --git a/drivers/media/dvb-frontends/horus3a.c b/drivers/media/dvb-frontends/horus3a.c index 5e7e265a52e6..02bc08081971 100644 --- a/drivers/media/dvb-frontends/horus3a.c +++ b/drivers/media/dvb-frontends/horus3a.c @@ -330,9 +330,9 @@ static int horus3a_get_frequency(struct dvb_frontend *fe, u32 *frequency) static const struct dvb_tuner_ops horus3a_tuner_ops = { .info = { .name = "Sony Horus3a", - .frequency_min = 950000, - .frequency_max = 2150000, - .frequency_step = 1000, + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2150 * MHz, + .frequency_step_hz = 1 * MHz, }, .init = horus3a_init, .release = horus3a_release, diff --git a/drivers/media/dvb-frontends/itd1000.c b/drivers/media/dvb-frontends/itd1000.c index 04f7f6854f73..c3a6e81ae87f 100644 --- a/drivers/media/dvb-frontends/itd1000.c +++ b/drivers/media/dvb-frontends/itd1000.c @@ -353,10 +353,10 @@ static void itd1000_release(struct dvb_frontend *fe) static const struct dvb_tuner_ops itd1000_tuner_ops = { .info = { - .name = "Integrant ITD1000", - .frequency_min = 950000, - .frequency_max = 2150000, - .frequency_step = 125, /* kHz for QPSK frontends */ + .name = "Integrant ITD1000", + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2150 * MHz, + .frequency_step_hz = 125 * kHz, }, .release = itd1000_release, diff --git a/drivers/media/dvb-frontends/ix2505v.c b/drivers/media/dvb-frontends/ix2505v.c index 965012ad5c59..9c055f72c416 100644 --- a/drivers/media/dvb-frontends/ix2505v.c +++ b/drivers/media/dvb-frontends/ix2505v.c @@ -256,8 +256,8 @@ static int ix2505v_get_frequency(struct dvb_frontend *fe, u32 *frequency) static const struct dvb_tuner_ops ix2505v_tuner_ops = { .info = { .name = "Sharp IX2505V (B0017)", - .frequency_min = 950000, - .frequency_max = 2175000 + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2175 * MHz }, .release = ix2505v_release, .set_params = ix2505v_set_params, diff --git a/drivers/media/dvb-frontends/stb6000.c b/drivers/media/dvb-frontends/stb6000.c index 69c03892f2da..786b9eccde00 100644 --- a/drivers/media/dvb-frontends/stb6000.c +++ b/drivers/media/dvb-frontends/stb6000.c @@ -188,8 +188,8 @@ static int stb6000_get_frequency(struct dvb_frontend *fe, u32 *frequency) static const struct dvb_tuner_ops stb6000_tuner_ops = { .info = { .name = "ST STB6000", - .frequency_min = 950000, - .frequency_max = 2150000 + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2150 * MHz }, .release = stb6000_release, .sleep = stb6000_sleep, diff --git a/drivers/media/dvb-frontends/stb6100.c b/drivers/media/dvb-frontends/stb6100.c index 3a851f524b16..30ac584dfab3 100644 --- a/drivers/media/dvb-frontends/stb6100.c +++ b/drivers/media/dvb-frontends/stb6100.c @@ -527,9 +527,8 @@ static int stb6100_set_params(struct dvb_frontend *fe) static const struct dvb_tuner_ops stb6100_ops = { .info = { .name = "STB6100 Silicon Tuner", - .frequency_min = 950000, - .frequency_max = 2150000, - .frequency_step = 0, + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2150 * MHz, }, .init = stb6100_init, diff --git a/drivers/media/dvb-frontends/stv6110.c b/drivers/media/dvb-frontends/stv6110.c index 6aad0efa3174..7db9a5bceccc 100644 --- a/drivers/media/dvb-frontends/stv6110.c +++ b/drivers/media/dvb-frontends/stv6110.c @@ -371,9 +371,9 @@ static int stv6110_get_bandwidth(struct dvb_frontend *fe, u32 *bandwidth) static const struct dvb_tuner_ops stv6110_tuner_ops = { .info = { .name = "ST STV6110", - .frequency_min = 950000, - .frequency_max = 2150000, - .frequency_step = 1000, + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2150 * MHz, + .frequency_step_hz = 1 * MHz, }, .init = stv6110_init, .release = stv6110_release, diff --git a/drivers/media/dvb-frontends/stv6110x.c b/drivers/media/dvb-frontends/stv6110x.c index d8950028d021..82c002d3833a 100644 --- a/drivers/media/dvb-frontends/stv6110x.c +++ b/drivers/media/dvb-frontends/stv6110x.c @@ -347,10 +347,9 @@ static void stv6110x_release(struct dvb_frontend *fe) static const struct dvb_tuner_ops stv6110x_ops = { .info = { - .name = "STV6110(A) Silicon Tuner", - .frequency_min = 950000, - .frequency_max = 2150000, - .frequency_step = 0, + .name = "STV6110(A) Silicon Tuner", + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2150 * MHz, }, .release = stv6110x_release }; diff --git a/drivers/media/dvb-frontends/stv6111.c b/drivers/media/dvb-frontends/stv6111.c index 9b715b6fe152..0cf460111acb 100644 --- a/drivers/media/dvb-frontends/stv6111.c +++ b/drivers/media/dvb-frontends/stv6111.c @@ -646,9 +646,8 @@ static int get_rf_strength(struct dvb_frontend *fe, u16 *st) static const struct dvb_tuner_ops tuner_ops = { .info = { .name = "ST STV6111", - .frequency_min = 950000, - .frequency_max = 2150000, - .frequency_step = 0 + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2150 * MHz, }, .set_params = set_params, .release = release, diff --git a/drivers/media/dvb-frontends/tda18271c2dd.c b/drivers/media/dvb-frontends/tda18271c2dd.c index fcffc7b4acf7..5ce58612315d 100644 --- a/drivers/media/dvb-frontends/tda18271c2dd.c +++ b/drivers/media/dvb-frontends/tda18271c2dd.c @@ -1215,9 +1215,9 @@ static int get_bandwidth(struct dvb_frontend *fe, u32 *bandwidth) static const struct dvb_tuner_ops tuner_ops = { .info = { .name = "NXP TDA18271C2D", - .frequency_min = 47125000, - .frequency_max = 865000000, - .frequency_step = 62500 + .frequency_min_hz = 47125 * kHz, + .frequency_max_hz = 865 * MHz, + .frequency_step_hz = 62500 }, .init = init, .sleep = sleep, diff --git a/drivers/media/dvb-frontends/tda665x.c b/drivers/media/dvb-frontends/tda665x.c index 3ef7140ed7f3..8766c9ff6680 100644 --- a/drivers/media/dvb-frontends/tda665x.c +++ b/drivers/media/dvb-frontends/tda665x.c @@ -231,9 +231,9 @@ struct dvb_frontend *tda665x_attach(struct dvb_frontend *fe, info = &fe->ops.tuner_ops.info; memcpy(info->name, config->name, sizeof(config->name)); - info->frequency_min = config->frequency_min; - info->frequency_max = config->frequency_max; - info->frequency_step = config->frequency_offst; + info->frequency_min_hz = config->frequency_min; + info->frequency_max_hz = config->frequency_max; + info->frequency_step_hz = config->frequency_offst; printk(KERN_DEBUG "%s: Attaching TDA665x (%s) tuner\n", __func__, info->name); diff --git a/drivers/media/dvb-frontends/tda8261.c b/drivers/media/dvb-frontends/tda8261.c index f72a54e7eb23..500f50b81b66 100644 --- a/drivers/media/dvb-frontends/tda8261.c +++ b/drivers/media/dvb-frontends/tda8261.c @@ -163,10 +163,9 @@ static void tda8261_release(struct dvb_frontend *fe) static const struct dvb_tuner_ops tda8261_ops = { .info = { - .name = "TDA8261", - .frequency_min = 950000, - .frequency_max = 2150000, - .frequency_step = 0 + .name = "TDA8261", + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2150 * MHz, }, .set_params = tda8261_set_params, @@ -190,7 +189,7 @@ struct dvb_frontend *tda8261_attach(struct dvb_frontend *fe, fe->tuner_priv = state; fe->ops.tuner_ops = tda8261_ops; - fe->ops.tuner_ops.info.frequency_step = div_tab[config->step_size]; + fe->ops.tuner_ops.info.frequency_step_hz = div_tab[config->step_size] * kHz; pr_info("%s: Attaching TDA8261 8PSK/QPSK tuner\n", __func__); diff --git a/drivers/media/dvb-frontends/tda826x.c b/drivers/media/dvb-frontends/tda826x.c index da427b4c2aaa..100da5d5fdc5 100644 --- a/drivers/media/dvb-frontends/tda826x.c +++ b/drivers/media/dvb-frontends/tda826x.c @@ -131,8 +131,8 @@ static int tda826x_get_frequency(struct dvb_frontend *fe, u32 *frequency) static const struct dvb_tuner_ops tda826x_tuner_ops = { .info = { .name = "Philips TDA826X", - .frequency_min = 950000, - .frequency_max = 2175000 + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2175 * MHz }, .release = tda826x_release, .sleep = tda826x_sleep, diff --git a/drivers/media/dvb-frontends/ts2020.c b/drivers/media/dvb-frontends/ts2020.c index c55882a8da06..3e3e40878633 100644 --- a/drivers/media/dvb-frontends/ts2020.c +++ b/drivers/media/dvb-frontends/ts2020.c @@ -498,8 +498,8 @@ static int ts2020_read_signal_strength(struct dvb_frontend *fe, static const struct dvb_tuner_ops ts2020_tuner_ops = { .info = { .name = "TS2020", - .frequency_min = 950000, - .frequency_max = 2150000 + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2150 * MHz }, .init = ts2020_init, .release = ts2020_release, diff --git a/drivers/media/dvb-frontends/tua6100.c b/drivers/media/dvb-frontends/tua6100.c index 1d41abd47f04..b233b7be0b84 100644 --- a/drivers/media/dvb-frontends/tua6100.c +++ b/drivers/media/dvb-frontends/tua6100.c @@ -155,9 +155,9 @@ static int tua6100_get_frequency(struct dvb_frontend *fe, u32 *frequency) static const struct dvb_tuner_ops tua6100_tuner_ops = { .info = { .name = "Infineon TUA6100", - .frequency_min = 950000, - .frequency_max = 2150000, - .frequency_step = 1000, + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2150 * MHz, + .frequency_step_hz = 1 * MHz, }, .release = tua6100_release, .sleep = tua6100_sleep, diff --git a/drivers/media/dvb-frontends/zl10036.c b/drivers/media/dvb-frontends/zl10036.c index 89dd65ae88ad..e5a432fd84c3 100644 --- a/drivers/media/dvb-frontends/zl10036.c +++ b/drivers/media/dvb-frontends/zl10036.c @@ -443,8 +443,8 @@ static int zl10036_init(struct dvb_frontend *fe) static const struct dvb_tuner_ops zl10036_tuner_ops = { .info = { .name = "Zarlink ZL10036", - .frequency_min = 950000, - .frequency_max = 2175000 + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2175 * MHz }, .init = zl10036_init, .release = zl10036_release, diff --git a/drivers/media/tuners/e4000.c b/drivers/media/tuners/e4000.c index b5b9d87ba75c..fbec1a13dc6a 100644 --- a/drivers/media/tuners/e4000.c +++ b/drivers/media/tuners/e4000.c @@ -610,9 +610,9 @@ static int e4000_dvb_get_if_frequency(struct dvb_frontend *fe, u32 *frequency) static const struct dvb_tuner_ops e4000_dvb_tuner_ops = { .info = { - .name = "Elonics E4000", - .frequency_min = 174000000, - .frequency_max = 862000000, + .name = "Elonics E4000", + .frequency_min_hz = 174 * MHz, + .frequency_max_hz = 862 * MHz, }, .init = e4000_dvb_init, diff --git a/drivers/media/tuners/fc0011.c b/drivers/media/tuners/fc0011.c index 145407dee3db..a983899c6b0b 100644 --- a/drivers/media/tuners/fc0011.c +++ b/drivers/media/tuners/fc0011.c @@ -472,10 +472,10 @@ static int fc0011_get_bandwidth(struct dvb_frontend *fe, u32 *bandwidth) static const struct dvb_tuner_ops fc0011_tuner_ops = { .info = { - .name = "Fitipower FC0011", + .name = "Fitipower FC0011", - .frequency_min = 45000000, - .frequency_max = 1000000000, + .frequency_min_hz = 45 * MHz, + .frequency_max_hz = 1000 * MHz, }, .release = fc0011_release, diff --git a/drivers/media/tuners/fc0012.c b/drivers/media/tuners/fc0012.c index 625ac6f51c39..e992b98ae5bc 100644 --- a/drivers/media/tuners/fc0012.c +++ b/drivers/media/tuners/fc0012.c @@ -415,11 +415,10 @@ exit: static const struct dvb_tuner_ops fc0012_tuner_ops = { .info = { - .name = "Fitipower FC0012", + .name = "Fitipower FC0012", - .frequency_min = 37000000, /* estimate */ - .frequency_max = 862000000, /* estimate */ - .frequency_step = 0, + .frequency_min_hz = 37 * MHz, /* estimate */ + .frequency_max_hz = 862 * MHz, /* estimate */ }, .release = fc0012_release, diff --git a/drivers/media/tuners/fc0013.c b/drivers/media/tuners/fc0013.c index e606118d1a9b..fc62afb1450d 100644 --- a/drivers/media/tuners/fc0013.c +++ b/drivers/media/tuners/fc0013.c @@ -574,11 +574,10 @@ exit: static const struct dvb_tuner_ops fc0013_tuner_ops = { .info = { - .name = "Fitipower FC0013", + .name = "Fitipower FC0013", - .frequency_min = 37000000, /* estimate */ - .frequency_max = 1680000000, /* CHECK */ - .frequency_step = 0, + .frequency_min_hz = 37 * MHz, /* estimate */ + .frequency_max_hz = 1680 * MHz, /* CHECK */ }, .release = fc0013_release, diff --git a/drivers/media/tuners/fc2580.c b/drivers/media/tuners/fc2580.c index 743184ae0d26..db26892aac84 100644 --- a/drivers/media/tuners/fc2580.c +++ b/drivers/media/tuners/fc2580.c @@ -355,9 +355,9 @@ static int fc2580_dvb_get_if_frequency(struct dvb_frontend *fe, u32 *frequency) static const struct dvb_tuner_ops fc2580_dvb_tuner_ops = { .info = { - .name = "FCI FC2580", - .frequency_min = 174000000, - .frequency_max = 862000000, + .name = "FCI FC2580", + .frequency_min_hz = 174 * MHz, + .frequency_max_hz = 862 * MHz, }, .init = fc2580_dvb_init, diff --git a/drivers/media/tuners/it913x.c b/drivers/media/tuners/it913x.c index 27e5bc1c3cb5..b5eb39921e95 100644 --- a/drivers/media/tuners/it913x.c +++ b/drivers/media/tuners/it913x.c @@ -375,9 +375,9 @@ err: static const struct dvb_tuner_ops it913x_tuner_ops = { .info = { - .name = "ITE IT913X", - .frequency_min = 174000000, - .frequency_max = 862000000, + .name = "ITE IT913X", + .frequency_min_hz = 174 * MHz, + .frequency_max_hz = 862 * MHz, }, .init = it913x_init, diff --git a/drivers/media/tuners/m88rs6000t.c b/drivers/media/tuners/m88rs6000t.c index 9f3e0fd4cad9..3df2f23a40be 100644 --- a/drivers/media/tuners/m88rs6000t.c +++ b/drivers/media/tuners/m88rs6000t.c @@ -569,9 +569,9 @@ err: static const struct dvb_tuner_ops m88rs6000t_tuner_ops = { .info = { - .name = "Montage M88RS6000 Internal Tuner", - .frequency_min = 950000, - .frequency_max = 2150000, + .name = "Montage M88RS6000 Internal Tuner", + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2150 * MHz, }, .init = m88rs6000t_init, diff --git a/drivers/media/tuners/max2165.c b/drivers/media/tuners/max2165.c index 20ceb72e530b..721d8f722efb 100644 --- a/drivers/media/tuners/max2165.c +++ b/drivers/media/tuners/max2165.c @@ -377,10 +377,10 @@ static void max2165_release(struct dvb_frontend *fe) static const struct dvb_tuner_ops max2165_tuner_ops = { .info = { - .name = "Maxim MAX2165", - .frequency_min = 470000000, - .frequency_max = 862000000, - .frequency_step = 50000, + .name = "Maxim MAX2165", + .frequency_min_hz = 470 * MHz, + .frequency_max_hz = 862 * MHz, + .frequency_step_hz = 50 * kHz, }, .release = max2165_release, diff --git a/drivers/media/tuners/mc44s803.c b/drivers/media/tuners/mc44s803.c index 403c6b2aa53b..2023e081d9ad 100644 --- a/drivers/media/tuners/mc44s803.c +++ b/drivers/media/tuners/mc44s803.c @@ -300,10 +300,10 @@ static int mc44s803_get_if_frequency(struct dvb_frontend *fe, u32 *frequency) static const struct dvb_tuner_ops mc44s803_tuner_ops = { .info = { - .name = "Freescale MC44S803", - .frequency_min = 48000000, - .frequency_max = 1000000000, - .frequency_step = 100000, + .name = "Freescale MC44S803", + .frequency_min_hz = 48 * MHz, + .frequency_max_hz = 1000 * MHz, + .frequency_step_hz = 100 * kHz, }, .release = mc44s803_release, diff --git a/drivers/media/tuners/mt2060.c b/drivers/media/tuners/mt2060.c index 3d3c6815b6a7..4ace77cfe285 100644 --- a/drivers/media/tuners/mt2060.c +++ b/drivers/media/tuners/mt2060.c @@ -395,10 +395,10 @@ static void mt2060_release(struct dvb_frontend *fe) static const struct dvb_tuner_ops mt2060_tuner_ops = { .info = { - .name = "Microtune MT2060", - .frequency_min = 48000000, - .frequency_max = 860000000, - .frequency_step = 50000, + .name = "Microtune MT2060", + .frequency_min_hz = 48 * MHz, + .frequency_max_hz = 860 * MHz, + .frequency_step_hz = 50 * kHz, }, .release = mt2060_release, diff --git a/drivers/media/tuners/mt2063.c b/drivers/media/tuners/mt2063.c index 80dc3e241b4a..f4c8a7293ebb 100644 --- a/drivers/media/tuners/mt2063.c +++ b/drivers/media/tuners/mt2063.c @@ -2200,10 +2200,9 @@ static int mt2063_get_bandwidth(struct dvb_frontend *fe, u32 *bw) static const struct dvb_tuner_ops mt2063_ops = { .info = { .name = "MT2063 Silicon Tuner", - .frequency_min = 45000000, - .frequency_max = 865000000, - .frequency_step = 0, - }, + .frequency_min_hz = 45 * MHz, + .frequency_max_hz = 865 * MHz, + }, .init = mt2063_init, .sleep = MT2063_Sleep, diff --git a/drivers/media/tuners/mt2131.c b/drivers/media/tuners/mt2131.c index 659bf19dc434..086a7b7cf634 100644 --- a/drivers/media/tuners/mt2131.c +++ b/drivers/media/tuners/mt2131.c @@ -235,10 +235,10 @@ static void mt2131_release(struct dvb_frontend *fe) static const struct dvb_tuner_ops mt2131_tuner_ops = { .info = { - .name = "Microtune MT2131", - .frequency_min = 48000000, - .frequency_max = 860000000, - .frequency_step = 50000, + .name = "Microtune MT2131", + .frequency_min_hz = 48 * MHz, + .frequency_max_hz = 860 * MHz, + .frequency_step_hz = 50 * kHz, }, .release = mt2131_release, diff --git a/drivers/media/tuners/mt2266.c b/drivers/media/tuners/mt2266.c index f4545b7f5da2..e6cc78720de4 100644 --- a/drivers/media/tuners/mt2266.c +++ b/drivers/media/tuners/mt2266.c @@ -304,10 +304,10 @@ static void mt2266_release(struct dvb_frontend *fe) static const struct dvb_tuner_ops mt2266_tuner_ops = { .info = { - .name = "Microtune MT2266", - .frequency_min = 174000000, - .frequency_max = 862000000, - .frequency_step = 50000, + .name = "Microtune MT2266", + .frequency_min_hz = 174 * MHz, + .frequency_max_hz = 862 * MHz, + .frequency_step_hz = 50 * kHz, }, .release = mt2266_release, .init = mt2266_init, diff --git a/drivers/media/tuners/mxl301rf.c b/drivers/media/tuners/mxl301rf.c index 57b0e4862aaf..c628435a1b06 100644 --- a/drivers/media/tuners/mxl301rf.c +++ b/drivers/media/tuners/mxl301rf.c @@ -271,8 +271,8 @@ static const struct dvb_tuner_ops mxl301rf_ops = { .info = { .name = "MaxLinear MxL301RF", - .frequency_min = 93000000, - .frequency_max = 803142857, + .frequency_min_hz = 93 * MHz, + .frequency_max_hz = 803 * MHz + 142857, }, .init = mxl301rf_init, diff --git a/drivers/media/tuners/mxl5005s.c b/drivers/media/tuners/mxl5005s.c index 355ef2959b7d..ec584316c812 100644 --- a/drivers/media/tuners/mxl5005s.c +++ b/drivers/media/tuners/mxl5005s.c @@ -4075,10 +4075,10 @@ static void mxl5005s_release(struct dvb_frontend *fe) static const struct dvb_tuner_ops mxl5005s_tuner_ops = { .info = { - .name = "MaxLinear MXL5005S", - .frequency_min = 48000000, - .frequency_max = 860000000, - .frequency_step = 50000, + .name = "MaxLinear MXL5005S", + .frequency_min_hz = 48 * MHz, + .frequency_max_hz = 860 * MHz, + .frequency_step_hz = 50 * kHz, }, .release = mxl5005s_release, diff --git a/drivers/media/tuners/qm1d1b0004.c b/drivers/media/tuners/qm1d1b0004.c index b4495cc1626b..008ad870c00f 100644 --- a/drivers/media/tuners/qm1d1b0004.c +++ b/drivers/media/tuners/qm1d1b0004.c @@ -186,8 +186,8 @@ static const struct dvb_tuner_ops qm1d1b0004_ops = { .info = { .name = "Sharp qm1d1b0004", - .frequency_min = 950000, - .frequency_max = 2150000, + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2150 * MHz, }, .init = qm1d1b0004_init, diff --git a/drivers/media/tuners/qm1d1c0042.c b/drivers/media/tuners/qm1d1c0042.c index 642a065b9a07..83ca5dc047ea 100644 --- a/drivers/media/tuners/qm1d1c0042.c +++ b/drivers/media/tuners/qm1d1c0042.c @@ -388,8 +388,8 @@ static const struct dvb_tuner_ops qm1d1c0042_ops = { .info = { .name = "Sharp QM1D1C0042", - .frequency_min = 950000, - .frequency_max = 2150000, + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2150 * MHz, }, .init = qm1d1c0042_init, diff --git a/drivers/media/tuners/qt1010.c b/drivers/media/tuners/qt1010.c index b92be882ab3c..4565c06b1617 100644 --- a/drivers/media/tuners/qt1010.c +++ b/drivers/media/tuners/qt1010.c @@ -394,10 +394,10 @@ static int qt1010_get_if_frequency(struct dvb_frontend *fe, u32 *frequency) static const struct dvb_tuner_ops qt1010_tuner_ops = { .info = { - .name = "Quantek QT1010", - .frequency_min = QT1010_MIN_FREQ, - .frequency_max = QT1010_MAX_FREQ, - .frequency_step = QT1010_STEP, + .name = "Quantek QT1010", + .frequency_min_hz = QT1010_MIN_FREQ, + .frequency_max_hz = QT1010_MAX_FREQ, + .frequency_step_hz = QT1010_STEP, }, .release = qt1010_release, diff --git a/drivers/media/tuners/qt1010_priv.h b/drivers/media/tuners/qt1010_priv.h index 4cb78ecc8985..f25324c63067 100644 --- a/drivers/media/tuners/qt1010_priv.h +++ b/drivers/media/tuners/qt1010_priv.h @@ -71,12 +71,14 @@ reg def meaning 2f 00 ? not used? */ -#define QT1010_STEP 125000 /* 125 kHz used by Windows drivers, - hw could be more precise but we don't - know how to use */ -#define QT1010_MIN_FREQ 48000000 /* 48 MHz */ -#define QT1010_MAX_FREQ 860000000 /* 860 MHz */ -#define QT1010_OFFSET 1246000000 /* 1246 MHz */ +#define QT1010_STEP (125 * kHz) /* + * used by Windows drivers, + * hw could be more precise but we don't + * know how to use + */ +#define QT1010_MIN_FREQ (48 * MHz) +#define QT1010_MAX_FREQ (860 * MHz) +#define QT1010_OFFSET (1246 * MHz) #define QT1010_WR 0 #define QT1010_RD 1 diff --git a/drivers/media/tuners/r820t.c b/drivers/media/tuners/r820t.c index 3e14b9e2e763..ba4be08a8551 100644 --- a/drivers/media/tuners/r820t.c +++ b/drivers/media/tuners/r820t.c @@ -2297,9 +2297,9 @@ static void r820t_release(struct dvb_frontend *fe) static const struct dvb_tuner_ops r820t_tuner_ops = { .info = { - .name = "Rafael Micro R820T", - .frequency_min = 42000000, - .frequency_max = 1002000000, + .name = "Rafael Micro R820T", + .frequency_min_hz = 42 * MHz, + .frequency_max_hz = 1002 * MHz, }, .init = r820t_init, .release = r820t_release, diff --git a/drivers/media/tuners/si2157.c b/drivers/media/tuners/si2157.c index 9e34d31d724d..a08d8fe2bb1b 100644 --- a/drivers/media/tuners/si2157.c +++ b/drivers/media/tuners/si2157.c @@ -387,9 +387,9 @@ static int si2157_get_if_frequency(struct dvb_frontend *fe, u32 *frequency) static const struct dvb_tuner_ops si2157_ops = { .info = { - .name = "Silicon Labs Si2141/Si2146/2147/2148/2157/2158", - .frequency_min = 42000000, - .frequency_max = 870000000, + .name = "Silicon Labs Si2141/Si2146/2147/2148/2157/2158", + .frequency_min_hz = 42 * MHz, + .frequency_max_hz = 870 * MHz, }, .init = si2157_init, diff --git a/drivers/media/tuners/tda18212.c b/drivers/media/tuners/tda18212.c index 7b8068354fea..8326106ec2e3 100644 --- a/drivers/media/tuners/tda18212.c +++ b/drivers/media/tuners/tda18212.c @@ -175,11 +175,11 @@ static int tda18212_get_if_frequency(struct dvb_frontend *fe, u32 *frequency) static const struct dvb_tuner_ops tda18212_tuner_ops = { .info = { - .name = "NXP TDA18212", + .name = "NXP TDA18212", - .frequency_min = 48000000, - .frequency_max = 864000000, - .frequency_step = 1000, + .frequency_min_hz = 48 * MHz, + .frequency_max_hz = 864 * MHz, + .frequency_step_hz = 1 * kHz, }, .set_params = tda18212_set_params, diff --git a/drivers/media/tuners/tda18218.c b/drivers/media/tuners/tda18218.c index c56fcf5d48e3..cbbd4d5e15da 100644 --- a/drivers/media/tuners/tda18218.c +++ b/drivers/media/tuners/tda18218.c @@ -269,11 +269,11 @@ static void tda18218_release(struct dvb_frontend *fe) static const struct dvb_tuner_ops tda18218_tuner_ops = { .info = { - .name = "NXP TDA18218", + .name = "NXP TDA18218", - .frequency_min = 174000000, - .frequency_max = 864000000, - .frequency_step = 1000, + .frequency_min_hz = 174 * MHz, + .frequency_max_hz = 864 * MHz, + .frequency_step_hz = 1 * kHz, }, .release = tda18218_release, diff --git a/drivers/media/tuners/tda18250.c b/drivers/media/tuners/tda18250.c index 20d12b063380..20d10ef45ab6 100644 --- a/drivers/media/tuners/tda18250.c +++ b/drivers/media/tuners/tda18250.c @@ -740,9 +740,9 @@ static int tda18250_sleep(struct dvb_frontend *fe) static const struct dvb_tuner_ops tda18250_ops = { .info = { - .name = "NXP TDA18250", - .frequency_min = 42000000, - .frequency_max = 870000000, + .name = "NXP TDA18250", + .frequency_min_hz = 42 * MHz, + .frequency_max_hz = 870 * MHz, }, .init = tda18250_init, diff --git a/drivers/media/tuners/tda18271-fe.c b/drivers/media/tuners/tda18271-fe.c index 147155553648..4d69029229e4 100644 --- a/drivers/media/tuners/tda18271-fe.c +++ b/drivers/media/tuners/tda18271-fe.c @@ -1240,9 +1240,9 @@ static int tda18271_set_config(struct dvb_frontend *fe, void *priv_cfg) static const struct dvb_tuner_ops tda18271_tuner_ops = { .info = { .name = "NXP TDA18271HD", - .frequency_min = 45000000, - .frequency_max = 864000000, - .frequency_step = 62500 + .frequency_min_hz = 45 * MHz, + .frequency_max_hz = 864 * MHz, + .frequency_step_hz = 62500 }, .init = tda18271_init, .sleep = tda18271_sleep, diff --git a/drivers/media/tuners/tda827x.c b/drivers/media/tuners/tda827x.c index 8400808f8f7f..4391dabba510 100644 --- a/drivers/media/tuners/tda827x.c +++ b/drivers/media/tuners/tda827x.c @@ -816,9 +816,9 @@ static int tda827x_initial_sleep(struct dvb_frontend *fe) static const struct dvb_tuner_ops tda827xo_tuner_ops = { .info = { .name = "Philips TDA827X", - .frequency_min = 55000000, - .frequency_max = 860000000, - .frequency_step = 250000 + .frequency_min_hz = 55 * MHz, + .frequency_max_hz = 860 * MHz, + .frequency_step_hz = 250 * kHz }, .release = tda827x_release, .init = tda827x_initial_init, @@ -832,9 +832,9 @@ static const struct dvb_tuner_ops tda827xo_tuner_ops = { static const struct dvb_tuner_ops tda827xa_tuner_ops = { .info = { .name = "Philips TDA827XA", - .frequency_min = 44000000, - .frequency_max = 906000000, - .frequency_step = 62500 + .frequency_min_hz = 44 * MHz, + .frequency_max_hz = 906 * MHz, + .frequency_step_hz = 62500 }, .release = tda827x_release, .init = tda827x_init, diff --git a/drivers/media/tuners/tua9001.c b/drivers/media/tuners/tua9001.c index 9d70378fe2d3..5c89a130b47d 100644 --- a/drivers/media/tuners/tua9001.c +++ b/drivers/media/tuners/tua9001.c @@ -164,9 +164,9 @@ static int tua9001_get_if_frequency(struct dvb_frontend *fe, u32 *frequency) static const struct dvb_tuner_ops tua9001_tuner_ops = { .info = { - .name = "Infineon TUA9001", - .frequency_min = 170000000, - .frequency_max = 862000000, + .name = "Infineon TUA9001", + .frequency_min_hz = 170 * MHz, + .frequency_max_hz = 862 * MHz, }, .init = tua9001_init, diff --git a/drivers/media/tuners/tuner-xc2028.c b/drivers/media/tuners/tuner-xc2028.c index 84744e138982..222b93ef31c0 100644 --- a/drivers/media/tuners/tuner-xc2028.c +++ b/drivers/media/tuners/tuner-xc2028.c @@ -1440,9 +1440,9 @@ unlock: static const struct dvb_tuner_ops xc2028_dvb_tuner_ops = { .info = { .name = "Xceive XC3028", - .frequency_min = 42000000, - .frequency_max = 864000000, - .frequency_step = 50000, + .frequency_min_hz = 42 * MHz, + .frequency_max_hz = 864 * MHz, + .frequency_step_hz = 50 * kHz, }, .set_config = xc2028_set_config, diff --git a/drivers/media/tuners/xc4000.c b/drivers/media/tuners/xc4000.c index f0fa8da08afa..76b3f37f24a8 100644 --- a/drivers/media/tuners/xc4000.c +++ b/drivers/media/tuners/xc4000.c @@ -398,8 +398,8 @@ static int xc_set_rf_frequency(struct xc4000_priv *priv, u32 freq_hz) dprintk(1, "%s(%u)\n", __func__, freq_hz); - if ((freq_hz > xc4000_tuner_ops.info.frequency_max) || - (freq_hz < xc4000_tuner_ops.info.frequency_min)) + if ((freq_hz > xc4000_tuner_ops.info.frequency_max_hz) || + (freq_hz < xc4000_tuner_ops.info.frequency_min_hz)) return -EINVAL; freq_code = (u16)(freq_hz / 15625); @@ -1635,10 +1635,10 @@ static void xc4000_release(struct dvb_frontend *fe) static const struct dvb_tuner_ops xc4000_tuner_ops = { .info = { - .name = "Xceive XC4000", - .frequency_min = 1000000, - .frequency_max = 1023000000, - .frequency_step = 50000, + .name = "Xceive XC4000", + .frequency_min_hz = 1 * MHz, + .frequency_max_hz = 1023 * MHz, + .frequency_step_hz = 50 * kHz, }, .release = xc4000_release, diff --git a/drivers/media/tuners/xc5000.c b/drivers/media/tuners/xc5000.c index f7a8d05d1758..f6b65278e502 100644 --- a/drivers/media/tuners/xc5000.c +++ b/drivers/media/tuners/xc5000.c @@ -460,8 +460,8 @@ static int xc_set_rf_frequency(struct xc5000_priv *priv, u32 freq_hz) dprintk(1, "%s(%u)\n", __func__, freq_hz); - if ((freq_hz > xc5000_tuner_ops.info.frequency_max) || - (freq_hz < xc5000_tuner_ops.info.frequency_min)) + if ((freq_hz > xc5000_tuner_ops.info.frequency_max_hz) || + (freq_hz < xc5000_tuner_ops.info.frequency_min_hz)) return -EINVAL; freq_code = (u16)(freq_hz / 15625); @@ -1350,10 +1350,10 @@ static int xc5000_set_config(struct dvb_frontend *fe, void *priv_cfg) static const struct dvb_tuner_ops xc5000_tuner_ops = { .info = { - .name = "Xceive XC5000", - .frequency_min = 1000000, - .frequency_max = 1023000000, - .frequency_step = 50000, + .name = "Xceive XC5000", + .frequency_min_hz = 1 * MHz, + .frequency_max_hz = 1023 * MHz, + .frequency_step_hz = 50 * kHz, }, .release = xc5000_release, diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.c b/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.c index 240d736bf1bb..92b3b9221a21 100644 --- a/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.c +++ b/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.c @@ -465,9 +465,9 @@ static const struct dvb_tuner_ops mxl111sf_tuner_tuner_ops = { .info = { .name = "MaxLinear MxL111SF", #if 0 - .frequency_min = , - .frequency_max = , - .frequency_step = , + .frequency_min_hz = , + .frequency_max_hz = , + .frequency_step_hz = , #endif }, #if 0 diff --git a/include/media/dvb_frontend.h b/include/media/dvb_frontend.h index 331c8269c00e..aebaec2dc725 100644 --- a/include/media/dvb_frontend.h +++ b/include/media/dvb_frontend.h @@ -52,6 +52,10 @@ */ #define MAX_DELSYS 8 +/* Helper definitions to be used at frontend drivers */ +#define kHz 1000UL +#define MHz 1000000UL + /** * struct dvb_frontend_tune_settings - parameters to adjust frontend tuning * @@ -73,22 +77,19 @@ struct dvb_frontend; * struct dvb_tuner_info - Frontend name and min/max ranges/bandwidths * * @name: name of the Frontend - * @frequency_min: minimal frequency supported - * @frequency_max: maximum frequency supported - * @frequency_step: frequency step + * @frequency_min_hz: minimal frequency supported in Hz + * @frequency_max_hz: maximum frequency supported in Hz + * @frequency_step_hz: frequency step in Hz * @bandwidth_min: minimal frontend bandwidth supported * @bandwidth_max: maximum frontend bandwidth supported * @bandwidth_step: frontend bandwidth step - * - * NOTE: frequency parameters are in Hz, for terrestrial/cable or kHz for - * satellite. */ struct dvb_tuner_info { char name[128]; - u32 frequency_min; - u32 frequency_max; - u32 frequency_step; + u32 frequency_min_hz; + u32 frequency_max_hz; + u32 frequency_step_hz; u32 bandwidth_min; u32 bandwidth_max; -- cgit v1.2.3 From e7d0748dd71695b94f3a35c8bdc05226a7f3d919 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 2 Aug 2018 15:22:13 -0600 Subject: block: Switch struct packet_command to use struct scsi_sense_hdr There is a lot of needless struct request_sense usage in the CDROM code. These can all be struct scsi_sense_hdr instead, to avoid any confusion over their respective structure sizes. This patch is a lot of noise changing "sense" to "sshdr", but the final code is more readable to distinguish between "sense" meaning "struct request_sense" and "sshdr" meaning "struct scsi_sense_hdr". Reviewed-by: Christoph Hellwig Signed-off-by: Kees Cook Signed-off-by: Jens Axboe --- drivers/block/pktcdvd.c | 36 ++++++++++++++++++------------------ drivers/cdrom/cdrom.c | 22 +++++++++++----------- drivers/ide/ide-cd.c | 11 ++++++----- drivers/ide/ide-cd.h | 4 ++-- drivers/ide/ide-cd_ioctl.c | 30 +++++++++++++++--------------- drivers/scsi/sr_ioctl.c | 22 +++++++++------------- include/linux/cdrom.h | 3 ++- 7 files changed, 63 insertions(+), 65 deletions(-) (limited to 'include') diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 9bb7721c26fc..e285413d4a75 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -748,13 +748,13 @@ static const char *sense_key_string(__u8 index) static void pkt_dump_sense(struct pktcdvd_device *pd, struct packet_command *cgc) { - struct request_sense *sense = cgc->sense; + struct scsi_sense_hdr *sshdr = cgc->sshdr; - if (sense) + if (sshdr) pkt_err(pd, "%*ph - sense %02x.%02x.%02x (%s)\n", CDROM_PACKET_SIZE, cgc->cmd, - sense->sense_key, sense->asc, sense->ascq, - sense_key_string(sense->sense_key)); + sshdr->sense_key, sshdr->asc, sshdr->ascq, + sense_key_string(sshdr->sense_key)); else pkt_err(pd, "%*ph - no sense\n", CDROM_PACKET_SIZE, cgc->cmd); } @@ -787,11 +787,11 @@ static noinline_for_stack int pkt_set_speed(struct pktcdvd_device *pd, unsigned write_speed, unsigned read_speed) { struct packet_command cgc; - struct request_sense sense; + struct scsi_sense_hdr sshdr; int ret; init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE); - cgc.sense = &sense; + cgc.sshdr = &sshdr; cgc.cmd[0] = GPCMD_SET_SPEED; cgc.cmd[2] = (read_speed >> 8) & 0xff; cgc.cmd[3] = read_speed & 0xff; @@ -1651,7 +1651,7 @@ static noinline_for_stack int pkt_get_last_written(struct pktcdvd_device *pd, static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd) { struct packet_command cgc; - struct request_sense sense; + struct scsi_sense_hdr sshdr; write_param_page *wp; char buffer[128]; int ret, size; @@ -1662,7 +1662,7 @@ static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd) memset(buffer, 0, sizeof(buffer)); init_cdrom_command(&cgc, buffer, sizeof(*wp), CGC_DATA_READ); - cgc.sense = &sense; + cgc.sshdr = &sshdr; ret = pkt_mode_sense(pd, &cgc, GPMODE_WRITE_PARMS_PAGE, 0); if (ret) { pkt_dump_sense(pd, &cgc); @@ -1678,7 +1678,7 @@ static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd) * now get it all */ init_cdrom_command(&cgc, buffer, size, CGC_DATA_READ); - cgc.sense = &sense; + cgc.sshdr = &sshdr; ret = pkt_mode_sense(pd, &cgc, GPMODE_WRITE_PARMS_PAGE, 0); if (ret) { pkt_dump_sense(pd, &cgc); @@ -1916,12 +1916,12 @@ static noinline_for_stack int pkt_write_caching(struct pktcdvd_device *pd, int set) { struct packet_command cgc; - struct request_sense sense; + struct scsi_sense_hdr sshdr; unsigned char buf[64]; int ret; init_cdrom_command(&cgc, buf, sizeof(buf), CGC_DATA_READ); - cgc.sense = &sense; + cgc.sshdr = &sshdr; cgc.buflen = pd->mode_offset + 12; /* @@ -1962,14 +1962,14 @@ static noinline_for_stack int pkt_get_max_speed(struct pktcdvd_device *pd, unsigned *write_speed) { struct packet_command cgc; - struct request_sense sense; + struct scsi_sense_hdr sshdr; unsigned char buf[256+18]; unsigned char *cap_buf; int ret, offset; cap_buf = &buf[sizeof(struct mode_page_header) + pd->mode_offset]; init_cdrom_command(&cgc, buf, sizeof(buf), CGC_DATA_UNKNOWN); - cgc.sense = &sense; + cgc.sshdr = &sshdr; ret = pkt_mode_sense(pd, &cgc, GPMODE_CAPABILITIES_PAGE, 0); if (ret) { @@ -2023,13 +2023,13 @@ static noinline_for_stack int pkt_media_speed(struct pktcdvd_device *pd, unsigned *speed) { struct packet_command cgc; - struct request_sense sense; + struct scsi_sense_hdr sshdr; unsigned char buf[64]; unsigned int size, st, sp; int ret; init_cdrom_command(&cgc, buf, 2, CGC_DATA_READ); - cgc.sense = &sense; + cgc.sshdr = &sshdr; cgc.cmd[0] = GPCMD_READ_TOC_PMA_ATIP; cgc.cmd[1] = 2; cgc.cmd[2] = 4; /* READ ATIP */ @@ -2044,7 +2044,7 @@ static noinline_for_stack int pkt_media_speed(struct pktcdvd_device *pd, size = sizeof(buf); init_cdrom_command(&cgc, buf, size, CGC_DATA_READ); - cgc.sense = &sense; + cgc.sshdr = &sshdr; cgc.cmd[0] = GPCMD_READ_TOC_PMA_ATIP; cgc.cmd[1] = 2; cgc.cmd[2] = 4; @@ -2095,13 +2095,13 @@ static noinline_for_stack int pkt_media_speed(struct pktcdvd_device *pd, static noinline_for_stack int pkt_perform_opc(struct pktcdvd_device *pd) { struct packet_command cgc; - struct request_sense sense; + struct scsi_sense_hdr sshdr; int ret; pkt_dbg(2, pd, "Performing OPC\n"); init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE); - cgc.sense = &sense; + cgc.sshdr = &sshdr; cgc.timeout = 60*HZ; cgc.cmd[0] = GPCMD_SEND_OPC; cgc.cmd[1] = 1; diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index a78b8e7085e9..86619472d916 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -345,10 +345,10 @@ static LIST_HEAD(cdrom_list); int cdrom_dummy_generic_packet(struct cdrom_device_info *cdi, struct packet_command *cgc) { - if (cgc->sense) { - cgc->sense->sense_key = 0x05; - cgc->sense->asc = 0x20; - cgc->sense->ascq = 0x00; + if (cgc->sshdr) { + cgc->sshdr->sense_key = 0x05; + cgc->sshdr->asc = 0x20; + cgc->sshdr->ascq = 0x00; } cgc->stat = -EIO; @@ -2943,7 +2943,7 @@ static noinline int mmc_ioctl_cdrom_read_data(struct cdrom_device_info *cdi, struct packet_command *cgc, int cmd) { - struct request_sense sense; + struct scsi_sense_hdr sshdr; struct cdrom_msf msf; int blocksize = 0, format = 0, lba; int ret; @@ -2971,13 +2971,13 @@ static noinline int mmc_ioctl_cdrom_read_data(struct cdrom_device_info *cdi, if (cgc->buffer == NULL) return -ENOMEM; - memset(&sense, 0, sizeof(sense)); - cgc->sense = &sense; + memset(&sshdr, 0, sizeof(sshdr)); + cgc->sshdr = &sshdr; cgc->data_direction = CGC_DATA_READ; ret = cdrom_read_block(cdi, cgc, lba, 1, format, blocksize); - if (ret && sense.sense_key == 0x05 && - sense.asc == 0x20 && - sense.ascq == 0x00) { + if (ret && sshdr.sense_key == 0x05 && + sshdr.asc == 0x20 && + sshdr.ascq == 0x00) { /* * SCSI-II devices are not required to support * READ_CD, so let's try switching block size @@ -2986,7 +2986,7 @@ static noinline int mmc_ioctl_cdrom_read_data(struct cdrom_device_info *cdi, ret = cdrom_switch_blocksize(cdi, blocksize); if (ret) goto out; - cgc->sense = NULL; + cgc->sshdr = NULL; ret = cdrom_read_cd(cdi, cgc, lba, blocksize, 1); ret |= cdrom_switch_blocksize(cdi, blocksize); } diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c index a37dd381d307..a24cdff01865 100644 --- a/drivers/ide/ide-cd.c +++ b/drivers/ide/ide-cd.c @@ -419,7 +419,7 @@ static void ide_cd_request_sense_fixup(ide_drive_t *drive, struct ide_cmd *cmd) int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd, int write, void *buffer, unsigned *bufflen, - struct request_sense *sense, int timeout, + struct scsi_sense_hdr *sshdr, int timeout, req_flags_t rq_flags) { struct cdrom_info *info = drive->driver_data; @@ -456,8 +456,9 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd, if (buffer) *bufflen = scsi_req(rq)->resid_len; - if (sense) - memcpy(sense, scsi_req(rq)->sense, sizeof(*sense)); + if (sshdr) + scsi_normalize_sense(scsi_req(rq)->sense, + scsi_req(rq)->sense_len, sshdr); /* * FIXME: we should probably abort/retry or something in case of @@ -864,7 +865,7 @@ static void msf_from_bcd(struct atapi_msf *msf) msf->frame = bcd2bin(msf->frame); } -int cdrom_check_status(ide_drive_t *drive, struct request_sense *sense) +int cdrom_check_status(ide_drive_t *drive, struct scsi_sense_hdr *sshdr) { struct cdrom_info *info = drive->driver_data; struct cdrom_device_info *cdi; @@ -886,7 +887,7 @@ int cdrom_check_status(ide_drive_t *drive, struct request_sense *sense) */ cmd[7] = cdi->sanyo_slot % 3; - return ide_cd_queue_pc(drive, cmd, 0, NULL, NULL, sense, 0, RQF_QUIET); + return ide_cd_queue_pc(drive, cmd, 0, NULL, NULL, sshdr, 0, RQF_QUIET); } static int cdrom_read_capacity(ide_drive_t *drive, unsigned long *capacity, diff --git a/drivers/ide/ide-cd.h b/drivers/ide/ide-cd.h index fc162fbb6629..a69dc7f61c4d 100644 --- a/drivers/ide/ide-cd.h +++ b/drivers/ide/ide-cd.h @@ -98,11 +98,11 @@ void ide_cd_log_error(const char *, struct request *, struct request_sense *); /* ide-cd.c functions used by ide-cd_ioctl.c */ int ide_cd_queue_pc(ide_drive_t *, const unsigned char *, int, void *, - unsigned *, struct request_sense *, int, req_flags_t); + unsigned *, struct scsi_sense_hdr *, int, req_flags_t); int ide_cd_read_toc(ide_drive_t *); int ide_cdrom_get_capabilities(ide_drive_t *, u8 *); void ide_cdrom_update_speed(ide_drive_t *, u8 *); -int cdrom_check_status(ide_drive_t *, struct request_sense *); +int cdrom_check_status(ide_drive_t *, struct scsi_sense_hdr *); /* ide-cd_ioctl.c */ int ide_cdrom_open_real(struct cdrom_device_info *, int); diff --git a/drivers/ide/ide-cd_ioctl.c b/drivers/ide/ide-cd_ioctl.c index 14540544413c..4a6e1a413ead 100644 --- a/drivers/ide/ide-cd_ioctl.c +++ b/drivers/ide/ide-cd_ioctl.c @@ -43,14 +43,14 @@ int ide_cdrom_drive_status(struct cdrom_device_info *cdi, int slot_nr) { ide_drive_t *drive = cdi->handle; struct media_event_desc med; - struct request_sense sense; + struct scsi_sense_hdr sshdr; int stat; if (slot_nr != CDSL_CURRENT) return -EINVAL; - stat = cdrom_check_status(drive, &sense); - if (!stat || sense.sense_key == UNIT_ATTENTION) + stat = cdrom_check_status(drive, &sshdr); + if (!stat || sshdr.sense_key == UNIT_ATTENTION) return CDS_DISC_OK; if (!cdrom_get_media_event(cdi, &med)) { @@ -62,8 +62,8 @@ int ide_cdrom_drive_status(struct cdrom_device_info *cdi, int slot_nr) return CDS_NO_DISC; } - if (sense.sense_key == NOT_READY && sense.asc == 0x04 - && sense.ascq == 0x04) + if (sshdr.sense_key == NOT_READY && sshdr.asc == 0x04 + && sshdr.ascq == 0x04) return CDS_DISC_OK; /* @@ -71,8 +71,8 @@ int ide_cdrom_drive_status(struct cdrom_device_info *cdi, int slot_nr) * just return TRAY_OPEN since ATAPI doesn't provide * any other way to detect this... */ - if (sense.sense_key == NOT_READY) { - if (sense.asc == 0x3a && sense.ascq == 1) + if (sshdr.sense_key == NOT_READY) { + if (sshdr.asc == 0x3a && sshdr.ascq == 1) return CDS_NO_DISC; else return CDS_TRAY_OPEN; @@ -135,7 +135,7 @@ int cdrom_eject(ide_drive_t *drive, int ejectflag) static int ide_cd_lockdoor(ide_drive_t *drive, int lockflag) { - struct request_sense my_sense, *sense = &my_sense; + struct scsi_sense_hdr sshdr; int stat; /* If the drive cannot lock the door, just pretend. */ @@ -150,14 +150,14 @@ int ide_cd_lockdoor(ide_drive_t *drive, int lockflag) cmd[4] = lockflag ? 1 : 0; stat = ide_cd_queue_pc(drive, cmd, 0, NULL, NULL, - sense, 0, 0); + &sshdr, 0, 0); } /* If we got an illegal field error, the drive probably cannot lock the door. */ if (stat != 0 && - sense->sense_key == ILLEGAL_REQUEST && - (sense->asc == 0x24 || sense->asc == 0x20)) { + sshdr.sense_key == ILLEGAL_REQUEST && + (sshdr.asc == 0x24 || sshdr.asc == 0x20)) { printk(KERN_ERR "%s: door locking not supported\n", drive->name); drive->dev_flags &= ~IDE_DFLAG_DOORLOCKING; @@ -165,7 +165,7 @@ int ide_cd_lockdoor(ide_drive_t *drive, int lockflag) } /* no medium, that's alright. */ - if (stat != 0 && sense->sense_key == NOT_READY && sense->asc == 0x3a) + if (stat != 0 && sshdr.sense_key == NOT_READY && sshdr.asc == 0x3a) stat = 0; if (stat == 0) { @@ -451,8 +451,8 @@ int ide_cdrom_packet(struct cdrom_device_info *cdi, layer. the packet must be complete, as we do not touch it at all. */ - if (cgc->sense) - memset(cgc->sense, 0, sizeof(struct request_sense)); + if (cgc->sshdr) + memset(cgc->sshdr, 0, sizeof(*cgc->sshdr)); if (cgc->quiet) flags |= RQF_QUIET; @@ -460,7 +460,7 @@ int ide_cdrom_packet(struct cdrom_device_info *cdi, cgc->stat = ide_cd_queue_pc(drive, cgc->cmd, cgc->data_direction == CGC_DATA_WRITE, cgc->buffer, &len, - cgc->sense, cgc->timeout, flags); + cgc->sshdr, cgc->timeout, flags); if (!cgc->stat) cgc->buflen -= len; return cgc->stat; diff --git a/drivers/scsi/sr_ioctl.c b/drivers/scsi/sr_ioctl.c index 35fab1e18adc..ffcf902da390 100644 --- a/drivers/scsi/sr_ioctl.c +++ b/drivers/scsi/sr_ioctl.c @@ -186,14 +186,13 @@ static int sr_play_trkind(struct cdrom_device_info *cdi, int sr_do_ioctl(Scsi_CD *cd, struct packet_command *cgc) { struct scsi_device *SDev; - struct scsi_sense_hdr sshdr; + struct scsi_sense_hdr local_sshdr, *sshdr = &local_sshdr; int result, err = 0, retries = 0; - unsigned char sense_buffer[SCSI_SENSE_BUFFERSIZE], *senseptr = NULL; SDev = cd->device; - if (cgc->sense) - senseptr = sense_buffer; + if (cgc->sshdr) + sshdr = cgc->sshdr; retry: if (!scsi_block_when_processing_errors(SDev)) { @@ -202,15 +201,12 @@ int sr_do_ioctl(Scsi_CD *cd, struct packet_command *cgc) } result = scsi_execute(SDev, cgc->cmd, cgc->data_direction, - cgc->buffer, cgc->buflen, senseptr, &sshdr, + cgc->buffer, cgc->buflen, NULL, sshdr, cgc->timeout, IOCTL_RETRIES, 0, 0, NULL); - if (cgc->sense) - memcpy(cgc->sense, sense_buffer, sizeof(*cgc->sense)); - /* Minimal error checking. Ignore cases we know about, and report the rest. */ if (driver_byte(result) != 0) { - switch (sshdr.sense_key) { + switch (sshdr->sense_key) { case UNIT_ATTENTION: SDev->changed = 1; if (!cgc->quiet) @@ -221,8 +217,8 @@ int sr_do_ioctl(Scsi_CD *cd, struct packet_command *cgc) err = -ENOMEDIUM; break; case NOT_READY: /* This happens if there is no disc in drive */ - if (sshdr.asc == 0x04 && - sshdr.ascq == 0x01) { + if (sshdr->asc == 0x04 && + sshdr->ascq == 0x01) { /* sense: Logical unit is in process of becoming ready */ if (!cgc->quiet) sr_printk(KERN_INFO, cd, @@ -245,8 +241,8 @@ int sr_do_ioctl(Scsi_CD *cd, struct packet_command *cgc) break; case ILLEGAL_REQUEST: err = -EIO; - if (sshdr.asc == 0x20 && - sshdr.ascq == 0x00) + if (sshdr->asc == 0x20 && + sshdr->ascq == 0x00) /* sense: Invalid command operation code */ err = -EDRIVE_CANT_DO_THIS; break; diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index e75dfd1f1dec..528271c60018 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -13,6 +13,7 @@ #include /* not really needed, later.. */ #include +#include #include struct packet_command @@ -21,7 +22,7 @@ struct packet_command unsigned char *buffer; unsigned int buflen; int stat; - struct request_sense *sense; + struct scsi_sense_hdr *sshdr; unsigned char data_direction; int quiet; int timeout; -- cgit v1.2.3 From 704f83928c8e7da6e06144569efb15dec73278e8 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 31 Jul 2018 12:51:54 -0700 Subject: scsi: Check sense buffer size at build time To avoid introducing problems like those fixed in commit f7068114d45e ("sr: pass down correctly sized SCSI sense buffer"), this creates a macro wrapper for scsi_execute() that verifies the size of the sense buffer similar to what was done for command string sizes in commit 3756f6401c30 ("exec: avoid gcc-8 warning for get_task_comm"). Another solution could be to add a length argument to scsi_execute(), but this function already takes a lot of arguments and Jens was not fond of that approach. Additionally, this moves the SCSI_SENSE_BUFFERSIZE definition into scsi_device.h, and removes a redundant include for scsi_device.h from scsi_cmnd.h. Reviewed-by: Christoph Hellwig Signed-off-by: Kees Cook Signed-off-by: Jens Axboe --- drivers/scsi/scsi_lib.c | 6 +++--- include/scsi/scsi_cmnd.h | 6 ++---- include/scsi/scsi_device.h | 14 +++++++++++++- 3 files changed, 18 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 41e9ac9fc138..9cb9a166fa0c 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -238,7 +238,7 @@ void scsi_queue_insert(struct scsi_cmnd *cmd, int reason) /** - * scsi_execute - insert request and wait for the result + * __scsi_execute - insert request and wait for the result * @sdev: scsi device * @cmd: scsi command * @data_direction: data direction @@ -255,7 +255,7 @@ void scsi_queue_insert(struct scsi_cmnd *cmd, int reason) * Returns the scsi_cmnd result field if a command was executed, or a negative * Linux error code if we didn't get that far. */ -int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd, +int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd, int data_direction, void *buffer, unsigned bufflen, unsigned char *sense, struct scsi_sense_hdr *sshdr, int timeout, int retries, u64 flags, req_flags_t rq_flags, @@ -309,7 +309,7 @@ int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd, return ret; } -EXPORT_SYMBOL(scsi_execute); +EXPORT_SYMBOL(__scsi_execute); /* * Function: scsi_init_cmd_errh() diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h index cae229b5395c..c891ada3c5c2 100644 --- a/include/scsi/scsi_cmnd.h +++ b/include/scsi/scsi_cmnd.h @@ -15,8 +15,6 @@ struct Scsi_Host; struct scsi_driver; -#include - /* * MAX_COMMAND_SIZE is: * The longest fixed-length SCSI CDB as per the SCSI standard. @@ -121,11 +119,11 @@ struct scsi_cmnd { struct request *request; /* The command we are working on */ -#define SCSI_SENSE_BUFFERSIZE 96 unsigned char *sense_buffer; /* obtained by REQUEST SENSE when * CHECK CONDITION is received on original - * command (auto-sense) */ + * command (auto-sense). Length must be + * SCSI_SENSE_BUFFERSIZE bytes. */ /* Low-level done function - can be used by low-level driver to point * to completion function. Not used by mid/upper level code. */ diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index 4c36af6edd79..202f4d6a4342 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -17,6 +17,8 @@ struct scsi_sense_hdr; typedef __u64 __bitwise blist_flags_t; +#define SCSI_SENSE_BUFFERSIZE 96 + struct scsi_mode_data { __u32 length; __u16 block_descriptor_length; @@ -426,11 +428,21 @@ extern const char *scsi_device_state_name(enum scsi_device_state); extern int scsi_is_sdev_device(const struct device *); extern int scsi_is_target_device(const struct device *); extern void scsi_sanitize_inquiry_string(unsigned char *s, int len); -extern int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd, +extern int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd, int data_direction, void *buffer, unsigned bufflen, unsigned char *sense, struct scsi_sense_hdr *sshdr, int timeout, int retries, u64 flags, req_flags_t rq_flags, int *resid); +/* Make sure any sense buffer is the correct size. */ +#define scsi_execute(sdev, cmd, data_direction, buffer, bufflen, sense, \ + sshdr, timeout, retries, flags, rq_flags, resid) \ +({ \ + BUILD_BUG_ON((sense) != NULL && \ + sizeof(sense) != SCSI_SENSE_BUFFERSIZE); \ + __scsi_execute(sdev, cmd, data_direction, buffer, bufflen, \ + sense, sshdr, timeout, retries, flags, rq_flags, \ + resid); \ +}) static inline int scsi_execute_req(struct scsi_device *sdev, const unsigned char *cmd, int data_direction, void *buffer, unsigned bufflen, struct scsi_sense_hdr *sshdr, int timeout, -- cgit v1.2.3 From 9a47249d444d344051c7c0e909fad0e88515a5c2 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Tue, 31 Jul 2018 21:11:00 +0200 Subject: random: Make crng state queryable It is very useful to be able to know whether or not get_random_bytes_wait / wait_for_random_bytes is going to block or not, or whether plain get_random_bytes is going to return good randomness or bad randomness. The particular use case is for mitigating certain attacks in WireGuard. A handshake packet arrives and is queued up. Elsewhere a worker thread takes items from the queue and processes them. In replying to these items, it needs to use some random data, and it has to be good random data. If we simply block until we can have good randomness, then it's possible for an attacker to fill the queue up with packets waiting to be processed. Upon realizing the queue is full, WireGuard will detect that it's under a denial of service attack, and behave accordingly. A better approach is just to drop incoming handshake packets if the crng is not yet initialized. This patch, therefore, makes that information directly accessible. Signed-off-by: Jason A. Donenfeld Signed-off-by: Theodore Ts'o --- drivers/char/random.c | 15 +++++++++++++++ include/linux/random.h | 1 + 2 files changed, 16 insertions(+) (limited to 'include') diff --git a/drivers/char/random.c b/drivers/char/random.c index 561082d46a82..bf5f99fc36f1 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1663,6 +1663,21 @@ int wait_for_random_bytes(void) } EXPORT_SYMBOL(wait_for_random_bytes); +/* + * Returns whether or not the urandom pool has been seeded and thus guaranteed + * to supply cryptographically secure random numbers. This applies to: the + * /dev/urandom device, the get_random_bytes function, and the get_random_{u32, + * ,u64,int,long} family of functions. + * + * Returns: true if the urandom pool has been seeded. + * false if the urandom pool has not been seeded. + */ +bool rng_is_initialized(void) +{ + return crng_ready(); +} +EXPORT_SYMBOL(rng_is_initialized); + /* * Add a callback function that will be invoked when the nonblocking * pool is initialised. diff --git a/include/linux/random.h b/include/linux/random.h index f1c9bc5cd231..445a0ea4ff49 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -36,6 +36,7 @@ extern void add_interrupt_randomness(int irq, int irq_flags) __latent_entropy; extern void get_random_bytes(void *buf, int nbytes); extern int wait_for_random_bytes(void); +extern bool rng_is_initialized(void); extern int add_random_ready_callback(struct random_ready_callback *rdy); extern void del_random_ready_callback(struct random_ready_callback *rdy); extern int __must_check get_random_bytes_arch(void *buf, int nbytes); -- cgit v1.2.3 From f1b1eabff0eb3fc46b06668de8174c0f23b271fd Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 5 Jul 2018 18:59:36 -0400 Subject: media: dvb: represent min/max/step/tolerance freqs in Hz Right now, satellite frontend drivers specify frequencies in kHz, while terrestrial/cable ones specify in Hz. That's confusing for developers. However, the main problem is that universal frontends capable of handling both satellite and non-satelite delivery systems are appearing. We end by needing to hack the drivers in order to support such hybrid frontends. So, convert everything to specify frontend frequencies in Hz. Tested-by: Katsuhiro Suzuki Signed-off-by: Mauro Carvalho Chehab --- drivers/media/common/siano/smsdvb-main.c | 6 +- drivers/media/dvb-core/dvb_frontend.c | 84 ++++++++++++++++------- drivers/media/dvb-frontends/af9013.c | 7 +- drivers/media/dvb-frontends/af9033.c | 7 +- drivers/media/dvb-frontends/as102_fe.c | 6 +- drivers/media/dvb-frontends/atbm8830.c | 6 +- drivers/media/dvb-frontends/au8522_dig.c | 6 +- drivers/media/dvb-frontends/bcm3510.c | 6 +- drivers/media/dvb-frontends/cx22700.c | 6 +- drivers/media/dvb-frontends/cx22702.c | 6 +- drivers/media/dvb-frontends/cx24110.c | 8 +-- drivers/media/dvb-frontends/cx24116.c | 8 +-- drivers/media/dvb-frontends/cx24117.c | 8 +-- drivers/media/dvb-frontends/cx24120.c | 8 +-- drivers/media/dvb-frontends/cx24123.c | 8 +-- drivers/media/dvb-frontends/cxd2820r_t.c | 4 +- drivers/media/dvb-frontends/cxd2820r_t2.c | 4 +- drivers/media/dvb-frontends/cxd2841er.c | 9 ++- drivers/media/dvb-frontends/cxd2880/cxd2880_top.c | 6 +- drivers/media/dvb-frontends/dib3000mb.c | 6 +- drivers/media/dvb-frontends/dib3000mc.c | 6 +- drivers/media/dvb-frontends/dib7000m.c | 6 +- drivers/media/dvb-frontends/dib7000p.c | 6 +- drivers/media/dvb-frontends/dib8000.c | 6 +- drivers/media/dvb-frontends/dib9000.c | 6 +- drivers/media/dvb-frontends/drx39xyj/drxj.c | 6 +- drivers/media/dvb-frontends/drxd_hard.c | 7 +- drivers/media/dvb-frontends/drxk_hard.c | 8 +-- drivers/media/dvb-frontends/ds3000.c | 8 +-- drivers/media/dvb-frontends/dvb_dummy_fe.c | 24 +++---- drivers/media/dvb-frontends/gp8psk-fe.c | 6 +- drivers/media/dvb-frontends/ix2505v.c | 4 +- drivers/media/dvb-frontends/l64781.c | 7 +- drivers/media/dvb-frontends/lg2160.c | 12 ++-- drivers/media/dvb-frontends/lgdt3305.c | 12 ++-- drivers/media/dvb-frontends/lgdt3306a.c | 6 +- drivers/media/dvb-frontends/lgdt330x.c | 12 ++-- drivers/media/dvb-frontends/lgs8gl5.c | 7 +- drivers/media/dvb-frontends/lgs8gxx.c | 6 +- drivers/media/dvb-frontends/m88ds3103.c | 6 +- drivers/media/dvb-frontends/m88rs2000.c | 8 +-- drivers/media/dvb-frontends/mb86a16.c | 7 +- drivers/media/dvb-frontends/mb86a20s.c | 6 +- drivers/media/dvb-frontends/mt312.c | 10 +-- drivers/media/dvb-frontends/mt352.c | 7 +- drivers/media/dvb-frontends/mxl5xx.c | 6 +- drivers/media/dvb-frontends/nxt200x.c | 6 +- drivers/media/dvb-frontends/nxt6000.c | 6 +- drivers/media/dvb-frontends/or51132.c | 6 +- drivers/media/dvb-frontends/or51211.c | 8 +-- drivers/media/dvb-frontends/rtl2830.c | 4 +- drivers/media/dvb-frontends/rtl2832.c | 10 +-- drivers/media/dvb-frontends/s5h1409.c | 6 +- drivers/media/dvb-frontends/s5h1411.c | 6 +- drivers/media/dvb-frontends/s5h1420.c | 8 +-- drivers/media/dvb-frontends/s5h1432.c | 6 +- drivers/media/dvb-frontends/s921.c | 7 +- drivers/media/dvb-frontends/si2165.c | 2 +- drivers/media/dvb-frontends/si21xx.c | 7 +- drivers/media/dvb-frontends/sp8870.c | 6 +- drivers/media/dvb-frontends/sp887x.c | 6 +- drivers/media/dvb-frontends/stb0899_drv.c | 6 +- drivers/media/dvb-frontends/stv0288.c | 7 +- drivers/media/dvb-frontends/stv0297.c | 6 +- drivers/media/dvb-frontends/stv0299.c | 7 +- drivers/media/dvb-frontends/stv0367.c | 20 +++--- drivers/media/dvb-frontends/stv0900_core.c | 7 +- drivers/media/dvb-frontends/stv090x.c | 6 +- drivers/media/dvb-frontends/stv0910.c | 6 +- drivers/media/dvb-frontends/tc90522.c | 10 +-- drivers/media/dvb-frontends/tda10021.c | 10 +-- drivers/media/dvb-frontends/tda10023.c | 6 +- drivers/media/dvb-frontends/tda10048.c | 6 +- drivers/media/dvb-frontends/tda1004x.c | 12 ++-- drivers/media/dvb-frontends/tda10071.c | 10 +-- drivers/media/dvb-frontends/tda10086.c | 6 +- drivers/media/dvb-frontends/tda8083.c | 7 +- drivers/media/dvb-frontends/ves1820.c | 6 +- drivers/media/dvb-frontends/ves1x93.c | 8 +-- drivers/media/dvb-frontends/zl10036.c | 4 +- drivers/media/dvb-frontends/zl10353.c | 7 +- drivers/media/firewire/firedtv-fe.c | 26 +++---- drivers/media/pci/bt8xx/dst.c | 26 +++---- drivers/media/pci/bt8xx/dvb-bt8xx.c | 8 +-- drivers/media/pci/ddbridge/ddbridge-sx8.c | 6 +- drivers/media/pci/mantis/mantis_vp3030.c | 4 +- drivers/media/tuners/mxl5007t.c | 2 - drivers/media/usb/dvb-usb-v2/mxl111sf-demod.c | 6 +- drivers/media/usb/dvb-usb/af9005-fe.c | 6 +- drivers/media/usb/dvb-usb/cinergyT2-fe.c | 6 +- drivers/media/usb/dvb-usb/dtt200u-fe.c | 6 +- drivers/media/usb/dvb-usb/friio-fe.c | 11 ++- drivers/media/usb/dvb-usb/vp702x-fe.c | 7 +- drivers/media/usb/dvb-usb/vp7045-fe.c | 6 +- drivers/media/usb/ttusb-dec/ttusbdecfe.c | 12 ++-- include/media/dvb_frontend.h | 30 +++++++- 96 files changed, 428 insertions(+), 399 deletions(-) (limited to 'include') diff --git a/drivers/media/common/siano/smsdvb-main.c b/drivers/media/common/siano/smsdvb-main.c index c0faad1ba428..43cfd1dbda01 100644 --- a/drivers/media/common/siano/smsdvb-main.c +++ b/drivers/media/common/siano/smsdvb-main.c @@ -1047,9 +1047,9 @@ static void smsdvb_release(struct dvb_frontend *fe) static const struct dvb_frontend_ops smsdvb_fe_ops = { .info = { .name = "Siano Mobile Digital MDTV Receiver", - .frequency_min = 44250000, - .frequency_max = 867250000, - .frequency_stepsize = 250000, + .frequency_min_hz = 44250 * kHz, + .frequency_max_hz = 867250 * kHz, + .frequency_stepsize_hz = 250 * kHz, .caps = FE_CAN_INVERSION_AUTO | FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO | diff --git a/drivers/media/dvb-core/dvb_frontend.c b/drivers/media/dvb-core/dvb_frontend.c index 75e95b56f8b3..fe0fae482ba4 100644 --- a/drivers/media/dvb-core/dvb_frontend.c +++ b/drivers/media/dvb-core/dvb_frontend.c @@ -894,11 +894,28 @@ static int dvb_frontend_start(struct dvb_frontend *fe) } static void dvb_frontend_get_frequency_limits(struct dvb_frontend *fe, - u32 *freq_min, u32 *freq_max) + u32 *freq_min, u32 *freq_max, + u32 *tolerance) { struct dtv_frontend_properties *c = &fe->dtv_property_cache; - __u32 tuner_min = fe->ops.tuner_ops.info.frequency_min_hz; - __u32 tuner_max = fe->ops.tuner_ops.info.frequency_max_hz; + u32 tuner_min = fe->ops.tuner_ops.info.frequency_min_hz; + u32 tuner_max = fe->ops.tuner_ops.info.frequency_max_hz; + u32 frontend_min = fe->ops.info.frequency_min_hz; + u32 frontend_max = fe->ops.info.frequency_max_hz; + + *freq_min = max(frontend_min, tuner_min); + + if (frontend_max == 0) + *freq_max = tuner_max; + else if (tuner_max == 0) + *freq_max = frontend_max; + else + *freq_max = min(frontend_max, tuner_max); + + if (*freq_min == 0 || *freq_max == 0) + dev_warn(fe->dvb->device, + "DVB: adapter %i frontend %u frequency limits undefined - fix the driver\n", + fe->dvb->num, fe->id); /* If the standard is for satellite, convert frequencies to kHz */ switch (c->delivery_system) { @@ -906,26 +923,35 @@ static void dvb_frontend_get_frequency_limits(struct dvb_frontend *fe, case SYS_DVBS2: case SYS_TURBO: case SYS_ISDBS: - tuner_max /= kHz; - tuner_min /= kHz; + *freq_min /= kHz; + *freq_max /= kHz; + if (tolerance) + *tolerance = fe->ops.info.frequency_tolerance_hz / kHz; + break; default: + if (tolerance) + *tolerance = fe->ops.info.frequency_tolerance_hz; break; } +} - *freq_min = max(fe->ops.info.frequency_min, tuner_min); - - if (fe->ops.info.frequency_max == 0) - *freq_max = tuner_max; - else if (tuner_max == 0) - *freq_max = fe->ops.info.frequency_max; - else - *freq_max = min(fe->ops.info.frequency_max, tuner_max); +static u32 dvb_frontend_get_stepsize(struct dvb_frontend *fe) +{ + struct dtv_frontend_properties *c = &fe->dtv_property_cache; + u32 step = fe->ops.info.frequency_stepsize_hz; + switch (c->delivery_system) { + case SYS_DVBS: + case SYS_DVBS2: + case SYS_TURBO: + case SYS_ISDBS: + step /= kHz; + break; + default: + break; + } - if (*freq_min == 0 || *freq_max == 0) - dev_warn(fe->dvb->device, - "DVB: adapter %i frontend %u frequency limits undefined - fix the driver\n", - fe->dvb->num, fe->id); + return step; } static int dvb_frontend_check_parameters(struct dvb_frontend *fe) @@ -935,7 +961,7 @@ static int dvb_frontend_check_parameters(struct dvb_frontend *fe) u32 freq_max; /* range check: frequency */ - dvb_frontend_get_frequency_limits(fe, &freq_min, &freq_max); + dvb_frontend_get_frequency_limits(fe, &freq_min, &freq_max, NULL); if ((freq_min && c->frequency < freq_min) || (freq_max && c->frequency > freq_max)) { dev_warn(fe->dvb->device, "DVB: adapter %i frontend %i frequency %u out of range (%u..%u)\n", @@ -2261,8 +2287,8 @@ static int dtv_set_frontend(struct dvb_frontend *fe) case SYS_ISDBT: case SYS_DTMB: fepriv->min_delay = HZ / 20; - fepriv->step_size = fe->ops.info.frequency_stepsize * 2; - fepriv->max_drift = (fe->ops.info.frequency_stepsize * 2) + 1; + fepriv->step_size = dvb_frontend_get_stepsize(fe) * 2; + fepriv->max_drift = (dvb_frontend_get_stepsize(fe) * 2) + 1; break; default: /* @@ -2391,9 +2417,17 @@ static int dvb_frontend_handle_ioctl(struct file *file, case FE_GET_INFO: { struct dvb_frontend_info *info = parg; - - memcpy(info, &fe->ops.info, sizeof(struct dvb_frontend_info)); - dvb_frontend_get_frequency_limits(fe, &info->frequency_min, &info->frequency_max); + memset(info, 0, sizeof(*info)); + + strcpy(info->name, fe->ops.info.name); + info->symbol_rate_min = fe->ops.info.symbol_rate_min; + info->symbol_rate_max = fe->ops.info.symbol_rate_max; + info->symbol_rate_tolerance = fe->ops.info.symbol_rate_tolerance; + info->caps = fe->ops.info.caps; + info->frequency_stepsize = dvb_frontend_get_stepsize(fe); + dvb_frontend_get_frequency_limits(fe, &info->frequency_min, + &info->frequency_max, + &info->frequency_tolerance); /* * Associate the 4 delivery systems supported by DVBv3 @@ -2423,10 +2457,10 @@ static int dvb_frontend_handle_ioctl(struct file *file, dev_err(fe->dvb->device, "%s: doesn't know how to handle a DVBv3 call to delivery system %i\n", __func__, c->delivery_system); - fe->ops.info.type = FE_OFDM; + info->type = FE_OFDM; } dev_dbg(fe->dvb->device, "%s: current delivery system on cache: %d, V3 type: %d\n", - __func__, c->delivery_system, fe->ops.info.type); + __func__, c->delivery_system, info->type); /* Set CAN_INVERSION_AUTO bit on in other than oneshot mode */ if (!(fepriv->tune_mode_flags & FE_TUNE_MODE_ONESHOT)) diff --git a/drivers/media/dvb-frontends/af9013.c b/drivers/media/dvb-frontends/af9013.c index 482bce49819a..f3acbb57d48c 100644 --- a/drivers/media/dvb-frontends/af9013.c +++ b/drivers/media/dvb-frontends/af9013.c @@ -1136,10 +1136,9 @@ static const struct dvb_frontend_ops af9013_ops = { .delsys = { SYS_DVBT }, .info = { .name = "Afatech AF9013", - .frequency_min = 174000000, - .frequency_max = 862000000, - .frequency_stepsize = 250000, - .frequency_tolerance = 0, + .frequency_min_hz = 174 * MHz, + .frequency_max_hz = 862 * MHz, + .frequency_stepsize_hz = 250 * kHz, .caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 | diff --git a/drivers/media/dvb-frontends/af9033.c b/drivers/media/dvb-frontends/af9033.c index aaed7cfe5f66..0cd57013ea25 100644 --- a/drivers/media/dvb-frontends/af9033.c +++ b/drivers/media/dvb-frontends/af9033.c @@ -1020,10 +1020,9 @@ static const struct dvb_frontend_ops af9033_ops = { .delsys = {SYS_DVBT}, .info = { .name = "Afatech AF9033 (DVB-T)", - .frequency_min = 174000000, - .frequency_max = 862000000, - .frequency_stepsize = 250000, - .frequency_tolerance = 0, + .frequency_min_hz = 174 * MHz, + .frequency_max_hz = 862 * MHz, + .frequency_stepsize_hz = 250 * kHz, .caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 | diff --git a/drivers/media/dvb-frontends/as102_fe.c b/drivers/media/dvb-frontends/as102_fe.c index 9b2f2da1d989..f59a102b0a64 100644 --- a/drivers/media/dvb-frontends/as102_fe.c +++ b/drivers/media/dvb-frontends/as102_fe.c @@ -419,9 +419,9 @@ static const struct dvb_frontend_ops as102_fe_ops = { .delsys = { SYS_DVBT }, .info = { .name = "Abilis AS102 DVB-T", - .frequency_min = 174000000, - .frequency_max = 862000000, - .frequency_stepsize = 166667, + .frequency_min_hz = 174 * MHz, + .frequency_max_hz = 862 * MHz, + .frequency_stepsize_hz = 166667, .caps = FE_CAN_INVERSION_AUTO | FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO diff --git a/drivers/media/dvb-frontends/atbm8830.c b/drivers/media/dvb-frontends/atbm8830.c index 7b0f3239dbba..cbcc65dc9d54 100644 --- a/drivers/media/dvb-frontends/atbm8830.c +++ b/drivers/media/dvb-frontends/atbm8830.c @@ -428,9 +428,9 @@ static const struct dvb_frontend_ops atbm8830_ops = { .delsys = { SYS_DTMB }, .info = { .name = "AltoBeam ATBM8830/8831 DMB-TH", - .frequency_min = 474000000, - .frequency_max = 858000000, - .frequency_stepsize = 10000, + .frequency_min_hz = 474 * MHz, + .frequency_max_hz = 858 * MHz, + .frequency_stepsize_hz = 10 * kHz, .caps = FE_CAN_FEC_AUTO | FE_CAN_QAM_AUTO | diff --git a/drivers/media/dvb-frontends/au8522_dig.c b/drivers/media/dvb-frontends/au8522_dig.c index 8f659bd1c79e..076f737aa8c0 100644 --- a/drivers/media/dvb-frontends/au8522_dig.c +++ b/drivers/media/dvb-frontends/au8522_dig.c @@ -897,9 +897,9 @@ static const struct dvb_frontend_ops au8522_ops = { .delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B }, .info = { .name = "Auvitek AU8522 QAM/8VSB Frontend", - .frequency_min = 54000000, - .frequency_max = 858000000, - .frequency_stepsize = 62500, + .frequency_min_hz = 54 * MHz, + .frequency_max_hz = 858 * MHz, + .frequency_stepsize_hz = 62500, .caps = FE_CAN_QAM_64 | FE_CAN_QAM_256 | FE_CAN_8VSB }, diff --git a/drivers/media/dvb-frontends/bcm3510.c b/drivers/media/dvb-frontends/bcm3510.c index 05df133dc5be..e92542b92d34 100644 --- a/drivers/media/dvb-frontends/bcm3510.c +++ b/drivers/media/dvb-frontends/bcm3510.c @@ -840,10 +840,8 @@ static const struct dvb_frontend_ops bcm3510_ops = { .delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B }, .info = { .name = "Broadcom BCM3510 VSB/QAM frontend", - .frequency_min = 54000000, - .frequency_max = 803000000, - /* stepsize is just a guess */ - .frequency_stepsize = 0, + .frequency_min_hz = 54 * MHz, + .frequency_max_hz = 803 * MHz, .caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO | diff --git a/drivers/media/dvb-frontends/cx22700.c b/drivers/media/dvb-frontends/cx22700.c index 9ffd2c7ac74a..961380162cdd 100644 --- a/drivers/media/dvb-frontends/cx22700.c +++ b/drivers/media/dvb-frontends/cx22700.c @@ -412,9 +412,9 @@ static const struct dvb_frontend_ops cx22700_ops = { .delsys = { SYS_DVBT }, .info = { .name = "Conexant CX22700 DVB-T", - .frequency_min = 470000000, - .frequency_max = 860000000, - .frequency_stepsize = 166667, + .frequency_min_hz = 470 * MHz, + .frequency_max_hz = 860 * MHz, + .frequency_stepsize_hz = 166667, .caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO | FE_CAN_QPSK | FE_CAN_QAM_16 | FE_CAN_QAM_64 | diff --git a/drivers/media/dvb-frontends/cx22702.c b/drivers/media/dvb-frontends/cx22702.c index e8b1e6b7e7e5..ab9b2924bcca 100644 --- a/drivers/media/dvb-frontends/cx22702.c +++ b/drivers/media/dvb-frontends/cx22702.c @@ -622,9 +622,9 @@ static const struct dvb_frontend_ops cx22702_ops = { .delsys = { SYS_DVBT }, .info = { .name = "Conexant CX22702 DVB-T", - .frequency_min = 177000000, - .frequency_max = 858000000, - .frequency_stepsize = 166666, + .frequency_min_hz = 177 * MHz, + .frequency_max_hz = 858 * MHz, + .frequency_stepsize_hz = 166666, .caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO | FE_CAN_QPSK | FE_CAN_QAM_16 | FE_CAN_QAM_64 | FE_CAN_QAM_AUTO | diff --git a/drivers/media/dvb-frontends/cx24110.c b/drivers/media/dvb-frontends/cx24110.c index 2f3a1c237489..9441bdc73097 100644 --- a/drivers/media/dvb-frontends/cx24110.c +++ b/drivers/media/dvb-frontends/cx24110.c @@ -629,10 +629,10 @@ static const struct dvb_frontend_ops cx24110_ops = { .delsys = { SYS_DVBS }, .info = { .name = "Conexant CX24110 DVB-S", - .frequency_min = 950000, - .frequency_max = 2150000, - .frequency_stepsize = 1011, /* kHz for QPSK frontends */ - .frequency_tolerance = 29500, + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2150 * MHz, + .frequency_stepsize_hz = 1011 * kHz, + .frequency_tolerance_hz = 29500 * kHz, .symbol_rate_min = 1000000, .symbol_rate_max = 45000000, .caps = FE_CAN_INVERSION_AUTO | diff --git a/drivers/media/dvb-frontends/cx24116.c b/drivers/media/dvb-frontends/cx24116.c index 2dbc7349d870..220f26663647 100644 --- a/drivers/media/dvb-frontends/cx24116.c +++ b/drivers/media/dvb-frontends/cx24116.c @@ -1465,10 +1465,10 @@ static const struct dvb_frontend_ops cx24116_ops = { .delsys = { SYS_DVBS, SYS_DVBS2 }, .info = { .name = "Conexant CX24116/CX24118", - .frequency_min = 950000, - .frequency_max = 2150000, - .frequency_stepsize = 1011, /* kHz for QPSK frontends */ - .frequency_tolerance = 5000, + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2150 * MHz, + .frequency_stepsize_hz = 1011 * kHz, + .frequency_tolerance_hz = 5 * MHz, .symbol_rate_min = 1000000, .symbol_rate_max = 45000000, .caps = FE_CAN_INVERSION_AUTO | diff --git a/drivers/media/dvb-frontends/cx24117.c b/drivers/media/dvb-frontends/cx24117.c index ba55d75d916c..667bc8be848d 100644 --- a/drivers/media/dvb-frontends/cx24117.c +++ b/drivers/media/dvb-frontends/cx24117.c @@ -1622,10 +1622,10 @@ static const struct dvb_frontend_ops cx24117_ops = { .delsys = { SYS_DVBS, SYS_DVBS2 }, .info = { .name = "Conexant CX24117/CX24132", - .frequency_min = 950000, - .frequency_max = 2150000, - .frequency_stepsize = 1011, /* kHz for QPSK frontends */ - .frequency_tolerance = 5000, + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2150 * MHz, + .frequency_stepsize_hz = 1011 * kHz, + .frequency_tolerance_hz = 5 * MHz, .symbol_rate_min = 1000000, .symbol_rate_max = 45000000, .caps = FE_CAN_INVERSION_AUTO | diff --git a/drivers/media/dvb-frontends/cx24120.c b/drivers/media/dvb-frontends/cx24120.c index ccbabdae6a69..dd3ec316e7c2 100644 --- a/drivers/media/dvb-frontends/cx24120.c +++ b/drivers/media/dvb-frontends/cx24120.c @@ -1555,10 +1555,10 @@ static const struct dvb_frontend_ops cx24120_ops = { .delsys = { SYS_DVBS, SYS_DVBS2 }, .info = { .name = "Conexant CX24120/CX24118", - .frequency_min = 950000, - .frequency_max = 2150000, - .frequency_stepsize = 1011, /* kHz for QPSK frontends */ - .frequency_tolerance = 5000, + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2150 * MHz, + .frequency_stepsize_hz = 1011 * kHz, + .frequency_tolerance_hz = 5 * MHz, .symbol_rate_min = 1000000, .symbol_rate_max = 45000000, .caps = FE_CAN_INVERSION_AUTO | diff --git a/drivers/media/dvb-frontends/cx24123.c b/drivers/media/dvb-frontends/cx24123.c index bf33e7390aaf..e49215020a93 100644 --- a/drivers/media/dvb-frontends/cx24123.c +++ b/drivers/media/dvb-frontends/cx24123.c @@ -1111,10 +1111,10 @@ static const struct dvb_frontend_ops cx24123_ops = { .delsys = { SYS_DVBS }, .info = { .name = "Conexant CX24123/CX24109", - .frequency_min = 950000, - .frequency_max = 2150000, - .frequency_stepsize = 1011, /* kHz for QPSK frontends */ - .frequency_tolerance = 5000, + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2150 * MHz, + .frequency_stepsize_hz = 1011 * kHz, + .frequency_tolerance_hz = 5 * MHz, .symbol_rate_min = 1000000, .symbol_rate_max = 45000000, .caps = FE_CAN_INVERSION_AUTO | diff --git a/drivers/media/dvb-frontends/cxd2820r_t.c b/drivers/media/dvb-frontends/cxd2820r_t.c index c2e7caf9b010..eb1d7478fa8d 100644 --- a/drivers/media/dvb-frontends/cxd2820r_t.c +++ b/drivers/media/dvb-frontends/cxd2820r_t.c @@ -431,8 +431,8 @@ int cxd2820r_get_tune_settings_t(struct dvb_frontend *fe, struct dvb_frontend_tune_settings *s) { s->min_delay_ms = 500; - s->step_size = fe->ops.info.frequency_stepsize * 2; - s->max_drift = (fe->ops.info.frequency_stepsize * 2) + 1; + s->step_size = fe->ops.info.frequency_stepsize_hz * 2; + s->max_drift = (fe->ops.info.frequency_stepsize_hz * 2) + 1; return 0; } diff --git a/drivers/media/dvb-frontends/cxd2820r_t2.c b/drivers/media/dvb-frontends/cxd2820r_t2.c index e641fde75379..f330ec1710b4 100644 --- a/drivers/media/dvb-frontends/cxd2820r_t2.c +++ b/drivers/media/dvb-frontends/cxd2820r_t2.c @@ -426,8 +426,8 @@ int cxd2820r_get_tune_settings_t2(struct dvb_frontend *fe, struct dvb_frontend_tune_settings *s) { s->min_delay_ms = 1500; - s->step_size = fe->ops.info.frequency_stepsize * 2; - s->max_drift = (fe->ops.info.frequency_stepsize * 2) + 1; + s->step_size = fe->ops.info.frequency_stepsize_hz * 2; + s->max_drift = (fe->ops.info.frequency_stepsize_hz * 2) + 1; return 0; } diff --git a/drivers/media/dvb-frontends/cxd2841er.c b/drivers/media/dvb-frontends/cxd2841er.c index 85905d3503ff..c98093ed3dd7 100644 --- a/drivers/media/dvb-frontends/cxd2841er.c +++ b/drivers/media/dvb-frontends/cxd2841er.c @@ -3942,9 +3942,8 @@ static const struct dvb_frontend_ops cxd2841er_dvbs_s2_ops = { .delsys = { SYS_DVBS, SYS_DVBS2 }, .info = { .name = "Sony CXD2841ER DVB-S/S2 demodulator", - .frequency_min = 500000, - .frequency_max = 2500000, - .frequency_stepsize = 0, + .frequency_min_hz = 500 * MHz, + .frequency_max_hz = 2500 * MHz, .symbol_rate_min = 1000000, .symbol_rate_max = 45000000, .symbol_rate_tolerance = 500, @@ -3988,8 +3987,8 @@ static struct dvb_frontend_ops cxd2841er_t_c_ops = { FE_CAN_HIERARCHY_AUTO | FE_CAN_MUTE_TS | FE_CAN_2G_MODULATION, - .frequency_min = 42000000, - .frequency_max = 1002000000, + .frequency_min_hz = 42 * MHz, + .frequency_max_hz = 1002 * MHz, .symbol_rate_min = 870000, .symbol_rate_max = 11700000 }, diff --git a/drivers/media/dvb-frontends/cxd2880/cxd2880_top.c b/drivers/media/dvb-frontends/cxd2880/cxd2880_top.c index bd9101e246d5..f87e27481ea7 100644 --- a/drivers/media/dvb-frontends/cxd2880/cxd2880_top.c +++ b/drivers/media/dvb-frontends/cxd2880/cxd2880_top.c @@ -1833,9 +1833,9 @@ static enum dvbfe_algo cxd2880_get_frontend_algo(struct dvb_frontend *fe) static struct dvb_frontend_ops cxd2880_dvbt_t2_ops = { .info = { .name = "Sony CXD2880", - .frequency_min = 174000000, - .frequency_max = 862000000, - .frequency_stepsize = 1000, + .frequency_min_hz = 174 * MHz, + .frequency_max_hz = 862 * MHz, + .frequency_stepsize_hz = 1 * kHz, .caps = FE_CAN_INVERSION_AUTO | FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | diff --git a/drivers/media/dvb-frontends/dib3000mb.c b/drivers/media/dvb-frontends/dib3000mb.c index 5861f346db49..bbbd53280477 100644 --- a/drivers/media/dvb-frontends/dib3000mb.c +++ b/drivers/media/dvb-frontends/dib3000mb.c @@ -786,9 +786,9 @@ static const struct dvb_frontend_ops dib3000mb_ops = { .delsys = { SYS_DVBT }, .info = { .name = "DiBcom 3000M-B DVB-T", - .frequency_min = 44250000, - .frequency_max = 867250000, - .frequency_stepsize = 62500, + .frequency_min_hz = 44250 * kHz, + .frequency_max_hz = 867250 * kHz, + .frequency_stepsize_hz = 62500, .caps = FE_CAN_INVERSION_AUTO | FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO | diff --git a/drivers/media/dvb-frontends/dib3000mc.c b/drivers/media/dvb-frontends/dib3000mc.c index 7e5d474806a5..c9e1db251723 100644 --- a/drivers/media/dvb-frontends/dib3000mc.c +++ b/drivers/media/dvb-frontends/dib3000mc.c @@ -944,9 +944,9 @@ static const struct dvb_frontend_ops dib3000mc_ops = { .delsys = { SYS_DVBT }, .info = { .name = "DiBcom 3000MC/P", - .frequency_min = 44250000, - .frequency_max = 867250000, - .frequency_stepsize = 62500, + .frequency_min_hz = 44250 * kHz, + .frequency_max_hz = 867250 * kHz, + .frequency_stepsize_hz = 62500, .caps = FE_CAN_INVERSION_AUTO | FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO | diff --git a/drivers/media/dvb-frontends/dib7000m.c b/drivers/media/dvb-frontends/dib7000m.c index 6a1d357d0c7c..b79358d09de6 100644 --- a/drivers/media/dvb-frontends/dib7000m.c +++ b/drivers/media/dvb-frontends/dib7000m.c @@ -1443,9 +1443,9 @@ static const struct dvb_frontend_ops dib7000m_ops = { .delsys = { SYS_DVBT }, .info = { .name = "DiBcom 7000MA/MB/PA/PB/MC", - .frequency_min = 44250000, - .frequency_max = 867250000, - .frequency_stepsize = 62500, + .frequency_min_hz = 44250 * kHz, + .frequency_max_hz = 867250 * kHz, + .frequency_stepsize_hz = 62500, .caps = FE_CAN_INVERSION_AUTO | FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO | diff --git a/drivers/media/dvb-frontends/dib7000p.c b/drivers/media/dvb-frontends/dib7000p.c index 5a8dbc0b25fb..58387860b62d 100644 --- a/drivers/media/dvb-frontends/dib7000p.c +++ b/drivers/media/dvb-frontends/dib7000p.c @@ -2824,9 +2824,9 @@ static const struct dvb_frontend_ops dib7000p_ops = { .delsys = { SYS_DVBT }, .info = { .name = "DiBcom 7000PC", - .frequency_min = 44250000, - .frequency_max = 867250000, - .frequency_stepsize = 62500, + .frequency_min_hz = 44250 * kHz, + .frequency_max_hz = 867250 * kHz, + .frequency_stepsize_hz = 62500, .caps = FE_CAN_INVERSION_AUTO | FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO | diff --git a/drivers/media/dvb-frontends/dib8000.c b/drivers/media/dvb-frontends/dib8000.c index 22eec8f65485..3c3f8cb14845 100644 --- a/drivers/media/dvb-frontends/dib8000.c +++ b/drivers/media/dvb-frontends/dib8000.c @@ -4390,9 +4390,9 @@ static const struct dvb_frontend_ops dib8000_ops = { .delsys = { SYS_ISDBT }, .info = { .name = "DiBcom 8000 ISDB-T", - .frequency_min = 44250000, - .frequency_max = 867250000, - .frequency_stepsize = 62500, + .frequency_min_hz = 44250 * kHz, + .frequency_max_hz = 867250 * kHz, + .frequency_stepsize_hz = 62500, .caps = FE_CAN_INVERSION_AUTO | FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO | diff --git a/drivers/media/dvb-frontends/dib9000.c b/drivers/media/dvb-frontends/dib9000.c index b8edb55696bb..0183fb1346ef 100644 --- a/drivers/media/dvb-frontends/dib9000.c +++ b/drivers/media/dvb-frontends/dib9000.c @@ -2553,9 +2553,9 @@ static const struct dvb_frontend_ops dib9000_ops = { .delsys = { SYS_DVBT }, .info = { .name = "DiBcom 9000", - .frequency_min = 44250000, - .frequency_max = 867250000, - .frequency_stepsize = 62500, + .frequency_min_hz = 44250 * kHz, + .frequency_max_hz = 867250 * kHz, + .frequency_stepsize_hz = 62500, .caps = FE_CAN_INVERSION_AUTO | FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO | diff --git a/drivers/media/dvb-frontends/drx39xyj/drxj.c b/drivers/media/dvb-frontends/drx39xyj/drxj.c index 5706898e84cc..2ddb7d218ace 100644 --- a/drivers/media/dvb-frontends/drx39xyj/drxj.c +++ b/drivers/media/dvb-frontends/drx39xyj/drxj.c @@ -12374,9 +12374,9 @@ static const struct dvb_frontend_ops drx39xxj_ops = { .delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B }, .info = { .name = "Micronas DRX39xxj family Frontend", - .frequency_stepsize = 62500, - .frequency_min = 51000000, - .frequency_max = 858000000, + .frequency_min_hz = 51 * MHz, + .frequency_max_hz = 858 * MHz, + .frequency_stepsize_hz = 62500, .caps = FE_CAN_QAM_64 | FE_CAN_QAM_256 | FE_CAN_8VSB }, diff --git a/drivers/media/dvb-frontends/drxd_hard.c b/drivers/media/dvb-frontends/drxd_hard.c index 3b7d31a22d82..11fc259e4383 100644 --- a/drivers/media/dvb-frontends/drxd_hard.c +++ b/drivers/media/dvb-frontends/drxd_hard.c @@ -2912,10 +2912,9 @@ static const struct dvb_frontend_ops drxd_ops = { .delsys = { SYS_DVBT}, .info = { .name = "Micronas DRXD DVB-T", - .frequency_min = 47125000, - .frequency_max = 855250000, - .frequency_stepsize = 166667, - .frequency_tolerance = 0, + .frequency_min_hz = 47125 * kHz, + .frequency_max_hz = 855250 * kHz, + .frequency_stepsize_hz = 166667, .caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO | diff --git a/drivers/media/dvb-frontends/drxk_hard.c b/drivers/media/dvb-frontends/drxk_hard.c index 5a26ad93be10..ac10781d3550 100644 --- a/drivers/media/dvb-frontends/drxk_hard.c +++ b/drivers/media/dvb-frontends/drxk_hard.c @@ -6744,13 +6744,13 @@ static const struct dvb_frontend_ops drxk_ops = { /* .delsys will be filled dynamically */ .info = { .name = "DRXK", - .frequency_min = 47000000, - .frequency_max = 865000000, + .frequency_min_hz = 47 * MHz, + .frequency_max_hz = 865 * MHz, /* For DVB-C */ - .symbol_rate_min = 870000, + .symbol_rate_min = 870000, .symbol_rate_max = 11700000, /* For DVB-T */ - .frequency_stepsize = 166667, + .frequency_stepsize_hz = 166667, .caps = FE_CAN_QAM_16 | FE_CAN_QAM_32 | FE_CAN_QAM_64 | FE_CAN_QAM_128 | FE_CAN_QAM_256 | FE_CAN_FEC_AUTO | diff --git a/drivers/media/dvb-frontends/ds3000.c b/drivers/media/dvb-frontends/ds3000.c index 2ff90e5eabce..46a55146cb07 100644 --- a/drivers/media/dvb-frontends/ds3000.c +++ b/drivers/media/dvb-frontends/ds3000.c @@ -1100,10 +1100,10 @@ static const struct dvb_frontend_ops ds3000_ops = { .delsys = { SYS_DVBS, SYS_DVBS2 }, .info = { .name = "Montage Technology DS3000", - .frequency_min = 950000, - .frequency_max = 2150000, - .frequency_stepsize = 1011, /* kHz for QPSK frontends */ - .frequency_tolerance = 5000, + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2150 * MHz, + .frequency_stepsize_hz = 1011 * kHz, + .frequency_tolerance_hz = 5 * MHz, .symbol_rate_min = 1000000, .symbol_rate_max = 45000000, .caps = FE_CAN_INVERSION_AUTO | diff --git a/drivers/media/dvb-frontends/dvb_dummy_fe.c b/drivers/media/dvb-frontends/dvb_dummy_fe.c index 6650d4f61ef2..a4cbcae7967d 100644 --- a/drivers/media/dvb-frontends/dvb_dummy_fe.c +++ b/drivers/media/dvb-frontends/dvb_dummy_fe.c @@ -170,9 +170,9 @@ static const struct dvb_frontend_ops dvb_dummy_fe_ofdm_ops = { .delsys = { SYS_DVBT }, .info = { .name = "Dummy DVB-T", - .frequency_min = 0, - .frequency_max = 863250000, - .frequency_stepsize = 62500, + .frequency_min_hz = 0, + .frequency_max_hz = 863250 * kHz, + .frequency_stepsize_hz = 62500, .caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 | FE_CAN_FEC_4_5 | FE_CAN_FEC_5_6 | FE_CAN_FEC_6_7 | FE_CAN_FEC_7_8 | FE_CAN_FEC_8_9 | FE_CAN_FEC_AUTO | @@ -201,11 +201,11 @@ static const struct dvb_frontend_ops dvb_dummy_fe_qam_ops = { .delsys = { SYS_DVBC_ANNEX_A }, .info = { .name = "Dummy DVB-C", - .frequency_stepsize = 62500, - .frequency_min = 51000000, - .frequency_max = 858000000, - .symbol_rate_min = (57840000/2)/64, /* SACLK/64 == (XIN/2)/64 */ - .symbol_rate_max = (57840000/2)/4, /* SACLK/4 */ + .frequency_min_hz = 51 * MHz, + .frequency_max_hz = 858 * MHz, + .frequency_stepsize_hz = 62500, + .symbol_rate_min = (57840000 / 2) / 64, /* SACLK/64 == (XIN/2)/64 */ + .symbol_rate_max = (57840000 / 2) / 4, /* SACLK/4 */ .caps = FE_CAN_QAM_16 | FE_CAN_QAM_32 | FE_CAN_QAM_64 | FE_CAN_QAM_128 | FE_CAN_QAM_256 | FE_CAN_FEC_AUTO | FE_CAN_INVERSION_AUTO @@ -230,10 +230,10 @@ static const struct dvb_frontend_ops dvb_dummy_fe_qpsk_ops = { .delsys = { SYS_DVBS }, .info = { .name = "Dummy DVB-S", - .frequency_min = 950000, - .frequency_max = 2150000, - .frequency_stepsize = 250, /* kHz for QPSK frontends */ - .frequency_tolerance = 29500, + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2150 * MHz, + .frequency_stepsize_hz = 250 * kHz, + .frequency_tolerance_hz = 29500 * kHz, .symbol_rate_min = 1000000, .symbol_rate_max = 45000000, .caps = FE_CAN_INVERSION_AUTO | diff --git a/drivers/media/dvb-frontends/gp8psk-fe.c b/drivers/media/dvb-frontends/gp8psk-fe.c index a772ef8bfe1c..238f09aa72f2 100644 --- a/drivers/media/dvb-frontends/gp8psk-fe.c +++ b/drivers/media/dvb-frontends/gp8psk-fe.c @@ -355,9 +355,9 @@ static const struct dvb_frontend_ops gp8psk_fe_ops = { .delsys = { SYS_DVBS }, .info = { .name = "Genpix DVB-S", - .frequency_min = 800000, - .frequency_max = 2250000, - .frequency_stepsize = 100, + .frequency_min_hz = 800 * MHz, + .frequency_max_hz = 2250 * MHz, + .frequency_stepsize_hz = 100 * kHz, .symbol_rate_min = 1000000, .symbol_rate_max = 45000000, .symbol_rate_tolerance = 500, /* ppm */ diff --git a/drivers/media/dvb-frontends/ix2505v.c b/drivers/media/dvb-frontends/ix2505v.c index 9c055f72c416..a30707b61b1f 100644 --- a/drivers/media/dvb-frontends/ix2505v.c +++ b/drivers/media/dvb-frontends/ix2505v.c @@ -135,8 +135,8 @@ static int ix2505v_set_params(struct dvb_frontend *fe) u8 gain, cc, ref, psc, local_osc, lpf; u8 data[4] = {0}; - if ((frequency < fe->ops.info.frequency_min) - || (frequency > fe->ops.info.frequency_max)) + if ((frequency < fe->ops.info.frequency_min_hz / kHz) + || (frequency > fe->ops.info.frequency_max_hz / kHz)) return -EINVAL; if (state->config->tuner_gain) diff --git a/drivers/media/dvb-frontends/l64781.c b/drivers/media/dvb-frontends/l64781.c index 249c18761e6e..9afb5bf6424b 100644 --- a/drivers/media/dvb-frontends/l64781.c +++ b/drivers/media/dvb-frontends/l64781.c @@ -575,10 +575,9 @@ static const struct dvb_frontend_ops l64781_ops = { .delsys = { SYS_DVBT }, .info = { .name = "LSI L64781 DVB-T", - /* .frequency_min = ???,*/ - /* .frequency_max = ???,*/ - .frequency_stepsize = 166666, - /* .frequency_tolerance = ???,*/ + /* .frequency_min_hz = ???,*/ + /* .frequency_max_hz = ???,*/ + .frequency_stepsize_hz = 166666, /* .symbol_rate_tolerance = ???,*/ .caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | diff --git a/drivers/media/dvb-frontends/lg2160.c b/drivers/media/dvb-frontends/lg2160.c index 9854096839ae..408151e33fa7 100644 --- a/drivers/media/dvb-frontends/lg2160.c +++ b/drivers/media/dvb-frontends/lg2160.c @@ -1349,9 +1349,9 @@ static const struct dvb_frontend_ops lg2160_ops = { .delsys = { SYS_ATSCMH }, .info = { .name = "LG Electronics LG2160 ATSC/MH Frontend", - .frequency_min = 54000000, - .frequency_max = 858000000, - .frequency_stepsize = 62500, + .frequency_min_hz = 54 * MHz, + .frequency_max_hz = 858 * MHz, + .frequency_stepsize_hz = 62500, }, .i2c_gate_ctrl = lg216x_i2c_gate_ctrl, #if 0 @@ -1375,9 +1375,9 @@ static const struct dvb_frontend_ops lg2161_ops = { .delsys = { SYS_ATSCMH }, .info = { .name = "LG Electronics LG2161 ATSC/MH Frontend", - .frequency_min = 54000000, - .frequency_max = 858000000, - .frequency_stepsize = 62500, + .frequency_min_hz = 54 * MHz, + .frequency_max_hz = 858 * MHz, + .frequency_stepsize_hz = 62500, }, .i2c_gate_ctrl = lg216x_i2c_gate_ctrl, #if 0 diff --git a/drivers/media/dvb-frontends/lgdt3305.c b/drivers/media/dvb-frontends/lgdt3305.c index 735d73060265..857e9b4d69b4 100644 --- a/drivers/media/dvb-frontends/lgdt3305.c +++ b/drivers/media/dvb-frontends/lgdt3305.c @@ -1164,9 +1164,9 @@ static const struct dvb_frontend_ops lgdt3304_ops = { .delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B }, .info = { .name = "LG Electronics LGDT3304 VSB/QAM Frontend", - .frequency_min = 54000000, - .frequency_max = 858000000, - .frequency_stepsize = 62500, + .frequency_min_hz = 54 * MHz, + .frequency_max_hz = 858 * MHz, + .frequency_stepsize_hz = 62500, .caps = FE_CAN_QAM_64 | FE_CAN_QAM_256 | FE_CAN_8VSB }, .i2c_gate_ctrl = lgdt3305_i2c_gate_ctrl, @@ -1187,9 +1187,9 @@ static const struct dvb_frontend_ops lgdt3305_ops = { .delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B }, .info = { .name = "LG Electronics LGDT3305 VSB/QAM Frontend", - .frequency_min = 54000000, - .frequency_max = 858000000, - .frequency_stepsize = 62500, + .frequency_min_hz = 54 * MHz, + .frequency_max_hz = 858 * MHz, + .frequency_stepsize_hz = 62500, .caps = FE_CAN_QAM_64 | FE_CAN_QAM_256 | FE_CAN_8VSB }, .i2c_gate_ctrl = lgdt3305_i2c_gate_ctrl, diff --git a/drivers/media/dvb-frontends/lgdt3306a.c b/drivers/media/dvb-frontends/lgdt3306a.c index 32de824476db..0e1f5daaf20c 100644 --- a/drivers/media/dvb-frontends/lgdt3306a.c +++ b/drivers/media/dvb-frontends/lgdt3306a.c @@ -2157,9 +2157,9 @@ static const struct dvb_frontend_ops lgdt3306a_ops = { .delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B }, .info = { .name = "LG Electronics LGDT3306A VSB/QAM Frontend", - .frequency_min = 54000000, - .frequency_max = 858000000, - .frequency_stepsize = 62500, + .frequency_min_hz = 54 * MHz, + .frequency_max_hz = 858 * MHz, + .frequency_stepsize_hz = 62500, .caps = FE_CAN_QAM_AUTO | FE_CAN_QAM_64 | FE_CAN_QAM_256 | FE_CAN_8VSB }, .i2c_gate_ctrl = lgdt3306a_i2c_gate_ctrl, diff --git a/drivers/media/dvb-frontends/lgdt330x.c b/drivers/media/dvb-frontends/lgdt330x.c index f6731738b073..10d584ce538d 100644 --- a/drivers/media/dvb-frontends/lgdt330x.c +++ b/drivers/media/dvb-frontends/lgdt330x.c @@ -944,9 +944,9 @@ static const struct dvb_frontend_ops lgdt3302_ops = { .delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B }, .info = { .name = "LG Electronics LGDT3302 VSB/QAM Frontend", - .frequency_min = 54000000, - .frequency_max = 858000000, - .frequency_stepsize = 62500, + .frequency_min_hz = 54 * MHz, + .frequency_max_hz = 858 * MHz, + .frequency_stepsize_hz = 62500, .symbol_rate_min = 5056941, /* QAM 64 */ .symbol_rate_max = 10762000, /* VSB 8 */ .caps = FE_CAN_QAM_64 | FE_CAN_QAM_256 | FE_CAN_8VSB @@ -966,9 +966,9 @@ static const struct dvb_frontend_ops lgdt3303_ops = { .delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B }, .info = { .name = "LG Electronics LGDT3303 VSB/QAM Frontend", - .frequency_min = 54000000, - .frequency_max = 858000000, - .frequency_stepsize = 62500, + .frequency_min_hz = 54 * MHz, + .frequency_max_hz = 858 * MHz, + .frequency_stepsize_hz = 62500, .symbol_rate_min = 5056941, /* QAM 64 */ .symbol_rate_max = 10762000, /* VSB 8 */ .caps = FE_CAN_QAM_64 | FE_CAN_QAM_256 | FE_CAN_8VSB diff --git a/drivers/media/dvb-frontends/lgs8gl5.c b/drivers/media/dvb-frontends/lgs8gl5.c index f47e5a1af16d..07e5bcee9c1e 100644 --- a/drivers/media/dvb-frontends/lgs8gl5.c +++ b/drivers/media/dvb-frontends/lgs8gl5.c @@ -416,10 +416,9 @@ static const struct dvb_frontend_ops lgs8gl5_ops = { .delsys = { SYS_DTMB }, .info = { .name = "Legend Silicon LGS-8GL5 DMB-TH", - .frequency_min = 474000000, - .frequency_max = 858000000, - .frequency_stepsize = 10000, - .frequency_tolerance = 0, + .frequency_min_hz = 474 * MHz, + .frequency_max_hz = 858 * MHz, + .frequency_stepsize_hz = 10 * kHz, .caps = FE_CAN_FEC_AUTO | FE_CAN_QPSK | FE_CAN_QAM_16 | FE_CAN_QAM_32 | FE_CAN_QAM_64 | FE_CAN_QAM_AUTO | diff --git a/drivers/media/dvb-frontends/lgs8gxx.c b/drivers/media/dvb-frontends/lgs8gxx.c index 84af8a12f26a..a6bcf1571d10 100644 --- a/drivers/media/dvb-frontends/lgs8gxx.c +++ b/drivers/media/dvb-frontends/lgs8gxx.c @@ -985,9 +985,9 @@ static const struct dvb_frontend_ops lgs8gxx_ops = { .delsys = { SYS_DTMB }, .info = { .name = "Legend Silicon LGS8913/LGS8GXX DMB-TH", - .frequency_min = 474000000, - .frequency_max = 858000000, - .frequency_stepsize = 10000, + .frequency_min_hz = 474 * MHz, + .frequency_max_hz = 858 * MHz, + .frequency_stepsize_hz = 10 * kHz, .caps = FE_CAN_FEC_AUTO | FE_CAN_QAM_AUTO | diff --git a/drivers/media/dvb-frontends/m88ds3103.c b/drivers/media/dvb-frontends/m88ds3103.c index 65d157fe76d1..dffd2d4bf1c8 100644 --- a/drivers/media/dvb-frontends/m88ds3103.c +++ b/drivers/media/dvb-frontends/m88ds3103.c @@ -1300,9 +1300,9 @@ static const struct dvb_frontend_ops m88ds3103_ops = { .delsys = {SYS_DVBS, SYS_DVBS2}, .info = { .name = "Montage Technology M88DS3103", - .frequency_min = 950000, - .frequency_max = 2150000, - .frequency_tolerance = 5000, + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2150 * MHz, + .frequency_tolerance_hz = 5 * MHz, .symbol_rate_min = 1000000, .symbol_rate_max = 45000000, .caps = FE_CAN_INVERSION_AUTO | diff --git a/drivers/media/dvb-frontends/m88rs2000.c b/drivers/media/dvb-frontends/m88rs2000.c index 496ce27fa63a..d5bc85501f9e 100644 --- a/drivers/media/dvb-frontends/m88rs2000.c +++ b/drivers/media/dvb-frontends/m88rs2000.c @@ -759,10 +759,10 @@ static const struct dvb_frontend_ops m88rs2000_ops = { .delsys = { SYS_DVBS }, .info = { .name = "M88RS2000 DVB-S", - .frequency_min = 950000, - .frequency_max = 2150000, - .frequency_stepsize = 1000, /* kHz for QPSK frontends */ - .frequency_tolerance = 5000, + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2150 * MHz, + .frequency_stepsize_hz = 1 * MHz, + .frequency_tolerance_hz = 5 * MHz, .symbol_rate_min = 1000000, .symbol_rate_max = 45000000, .symbol_rate_tolerance = 500, /* ppm */ diff --git a/drivers/media/dvb-frontends/mb86a16.c b/drivers/media/dvb-frontends/mb86a16.c index 377cd984b069..da505a5d035f 100644 --- a/drivers/media/dvb-frontends/mb86a16.c +++ b/drivers/media/dvb-frontends/mb86a16.c @@ -1808,10 +1808,9 @@ static const struct dvb_frontend_ops mb86a16_ops = { .delsys = { SYS_DVBS }, .info = { .name = "Fujitsu MB86A16 DVB-S", - .frequency_min = 950000, - .frequency_max = 2150000, - .frequency_stepsize = 3000, - .frequency_tolerance = 0, + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2150 * MHz, + .frequency_stepsize_hz = 3 * MHz, .symbol_rate_min = 1000000, .symbol_rate_max = 45000000, .symbol_rate_tolerance = 500, diff --git a/drivers/media/dvb-frontends/mb86a20s.c b/drivers/media/dvb-frontends/mb86a20s.c index c3b1b88e2e7a..66fc77db0e75 100644 --- a/drivers/media/dvb-frontends/mb86a20s.c +++ b/drivers/media/dvb-frontends/mb86a20s.c @@ -2111,9 +2111,9 @@ static const struct dvb_frontend_ops mb86a20s_ops = { FE_CAN_TRANSMISSION_MODE_AUTO | FE_CAN_QAM_AUTO | FE_CAN_GUARD_INTERVAL_AUTO | FE_CAN_HIERARCHY_AUTO, /* Actually, those values depend on the used tuner */ - .frequency_min = 45000000, - .frequency_max = 864000000, - .frequency_stepsize = 62500, + .frequency_min_hz = 45 * MHz, + .frequency_max_hz = 864 * MHz, + .frequency_stepsize_hz = 62500, }, .release = mb86a20s_release, diff --git a/drivers/media/dvb-frontends/mt312.c b/drivers/media/dvb-frontends/mt312.c index e2a3fc521620..aad07adda37d 100644 --- a/drivers/media/dvb-frontends/mt312.c +++ b/drivers/media/dvb-frontends/mt312.c @@ -559,8 +559,8 @@ static int mt312_set_frontend(struct dvb_frontend *fe) dprintk("%s: Freq %d\n", __func__, p->frequency); - if ((p->frequency < fe->ops.info.frequency_min) - || (p->frequency > fe->ops.info.frequency_max)) + if ((p->frequency < fe->ops.info.frequency_min_hz / kHz) + || (p->frequency > fe->ops.info.frequency_max_hz / kHz)) return -EINVAL; if (((int)p->inversion < INVERSION_OFF) @@ -755,10 +755,10 @@ static const struct dvb_frontend_ops mt312_ops = { .delsys = { SYS_DVBS }, .info = { .name = "Zarlink ???? DVB-S", - .frequency_min = 950000, - .frequency_max = 2150000, + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2150 * MHz, /* FIXME: adjust freq to real used xtal */ - .frequency_stepsize = (MT312_PLL_CLK / 1000) / 128, + .frequency_stepsize_hz = MT312_PLL_CLK / 128, .symbol_rate_min = MT312_SYS_CLK / 128, /* FIXME as above */ .symbol_rate_max = MT312_SYS_CLK / 2, .caps = diff --git a/drivers/media/dvb-frontends/mt352.c b/drivers/media/dvb-frontends/mt352.c index a440b76444d3..da3e466d50e2 100644 --- a/drivers/media/dvb-frontends/mt352.c +++ b/drivers/media/dvb-frontends/mt352.c @@ -567,10 +567,9 @@ static const struct dvb_frontend_ops mt352_ops = { .delsys = { SYS_DVBT }, .info = { .name = "Zarlink MT352 DVB-T", - .frequency_min = 174000000, - .frequency_max = 862000000, - .frequency_stepsize = 166667, - .frequency_tolerance = 0, + .frequency_min_hz = 174 * MHz, + .frequency_max_hz = 862 * MHz, + .frequency_stepsize_hz = 166667, .caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO | diff --git a/drivers/media/dvb-frontends/mxl5xx.c b/drivers/media/dvb-frontends/mxl5xx.c index 274d8fca0763..295f37d5f10e 100644 --- a/drivers/media/dvb-frontends/mxl5xx.c +++ b/drivers/media/dvb-frontends/mxl5xx.c @@ -784,10 +784,8 @@ static struct dvb_frontend_ops mxl_ops = { .delsys = { SYS_DVBS, SYS_DVBS2, SYS_DSS }, .info = { .name = "MaxLinear MxL5xx DVB-S/S2 tuner-demodulator", - .frequency_min = 300000, - .frequency_max = 2350000, - .frequency_stepsize = 0, - .frequency_tolerance = 0, + .frequency_min_hz = 300 * MHz, + .frequency_max_hz = 2350 * MHz, .symbol_rate_min = 1000000, .symbol_rate_max = 45000000, .caps = FE_CAN_INVERSION_AUTO | diff --git a/drivers/media/dvb-frontends/nxt200x.c b/drivers/media/dvb-frontends/nxt200x.c index a6cc4952eb74..0961e686ff68 100644 --- a/drivers/media/dvb-frontends/nxt200x.c +++ b/drivers/media/dvb-frontends/nxt200x.c @@ -1212,9 +1212,9 @@ static const struct dvb_frontend_ops nxt200x_ops = { .delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B }, .info = { .name = "Nextwave NXT200X VSB/QAM frontend", - .frequency_min = 54000000, - .frequency_max = 860000000, - .frequency_stepsize = 166666, /* stepsize is just a guess */ + .frequency_min_hz = 54 * MHz, + .frequency_max_hz = 860 * MHz, + .frequency_stepsize_hz = 166666, /* stepsize is just a guess */ .caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO | FE_CAN_8VSB | FE_CAN_QAM_64 | FE_CAN_QAM_256 diff --git a/drivers/media/dvb-frontends/nxt6000.c b/drivers/media/dvb-frontends/nxt6000.c index 109a635d166a..72e447e8ba64 100644 --- a/drivers/media/dvb-frontends/nxt6000.c +++ b/drivers/media/dvb-frontends/nxt6000.c @@ -596,9 +596,9 @@ static const struct dvb_frontend_ops nxt6000_ops = { .delsys = { SYS_DVBT }, .info = { .name = "NxtWave NXT6000 DVB-T", - .frequency_min = 0, - .frequency_max = 863250000, - .frequency_stepsize = 62500, + .frequency_min_hz = 0, + .frequency_max_hz = 863250 * kHz, + .frequency_stepsize_hz = 62500, /*.frequency_tolerance = *//* FIXME: 12% of SR */ .symbol_rate_min = 0, /* FIXME */ .symbol_rate_max = 9360000, /* FIXME */ diff --git a/drivers/media/dvb-frontends/or51132.c b/drivers/media/dvb-frontends/or51132.c index b4c9aadcb552..fc35f37eb3c0 100644 --- a/drivers/media/dvb-frontends/or51132.c +++ b/drivers/media/dvb-frontends/or51132.c @@ -583,9 +583,9 @@ static const struct dvb_frontend_ops or51132_ops = { .delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B }, .info = { .name = "Oren OR51132 VSB/QAM Frontend", - .frequency_min = 44000000, - .frequency_max = 958000000, - .frequency_stepsize = 166666, + .frequency_min_hz = 44 * MHz, + .frequency_max_hz = 958 * MHz, + .frequency_stepsize_hz = 166666, .caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO | FE_CAN_QAM_64 | FE_CAN_QAM_256 | FE_CAN_QAM_AUTO | diff --git a/drivers/media/dvb-frontends/or51211.c b/drivers/media/dvb-frontends/or51211.c index b65ba34fd00a..a39bbd8ff1f0 100644 --- a/drivers/media/dvb-frontends/or51211.c +++ b/drivers/media/dvb-frontends/or51211.c @@ -530,10 +530,10 @@ struct dvb_frontend* or51211_attach(const struct or51211_config* config, static const struct dvb_frontend_ops or51211_ops = { .delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B }, .info = { - .name = "Oren OR51211 VSB Frontend", - .frequency_min = 44000000, - .frequency_max = 958000000, - .frequency_stepsize = 166666, + .name = "Oren OR51211 VSB Frontend", + .frequency_min_hz = 44 * MHz, + .frequency_max_hz = 958 * MHz, + .frequency_stepsize_hz = 166666, .caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO | FE_CAN_8VSB diff --git a/drivers/media/dvb-frontends/rtl2830.c b/drivers/media/dvb-frontends/rtl2830.c index 7bbfe11d11ed..adc9046d5a90 100644 --- a/drivers/media/dvb-frontends/rtl2830.c +++ b/drivers/media/dvb-frontends/rtl2830.c @@ -159,8 +159,8 @@ static int rtl2830_get_tune_settings(struct dvb_frontend *fe, struct dvb_frontend_tune_settings *s) { s->min_delay_ms = 500; - s->step_size = fe->ops.info.frequency_stepsize * 2; - s->max_drift = (fe->ops.info.frequency_stepsize * 2) + 1; + s->step_size = fe->ops.info.frequency_stepsize_hz * 2; + s->max_drift = (fe->ops.info.frequency_stepsize_hz * 2) + 1; return 0; } diff --git a/drivers/media/dvb-frontends/rtl2832.c b/drivers/media/dvb-frontends/rtl2832.c index fa3b8169c1a5..2f1f5cbaf03c 100644 --- a/drivers/media/dvb-frontends/rtl2832.c +++ b/drivers/media/dvb-frontends/rtl2832.c @@ -408,8 +408,8 @@ static int rtl2832_get_tune_settings(struct dvb_frontend *fe, dev_dbg(&client->dev, "\n"); s->min_delay_ms = 1000; - s->step_size = fe->ops.info.frequency_stepsize * 2; - s->max_drift = (fe->ops.info.frequency_stepsize * 2) + 1; + s->step_size = fe->ops.info.frequency_stepsize_hz * 2; + s->max_drift = (fe->ops.info.frequency_stepsize_hz * 2) + 1; return 0; } @@ -841,9 +841,9 @@ static const struct dvb_frontend_ops rtl2832_ops = { .delsys = { SYS_DVBT }, .info = { .name = "Realtek RTL2832 (DVB-T)", - .frequency_min = 174000000, - .frequency_max = 862000000, - .frequency_stepsize = 166667, + .frequency_min_hz = 174 * MHz, + .frequency_max_hz = 862 * MHz, + .frequency_stepsize_hz = 166667, .caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 | diff --git a/drivers/media/dvb-frontends/s5h1409.c b/drivers/media/dvb-frontends/s5h1409.c index a23ba8727218..ceeb0c3551ce 100644 --- a/drivers/media/dvb-frontends/s5h1409.c +++ b/drivers/media/dvb-frontends/s5h1409.c @@ -999,9 +999,9 @@ static const struct dvb_frontend_ops s5h1409_ops = { .delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B }, .info = { .name = "Samsung S5H1409 QAM/8VSB Frontend", - .frequency_min = 54000000, - .frequency_max = 858000000, - .frequency_stepsize = 62500, + .frequency_min_hz = 54 * MHz, + .frequency_max_hz = 858 * MHz, + .frequency_stepsize_hz = 62500, .caps = FE_CAN_QAM_64 | FE_CAN_QAM_256 | FE_CAN_8VSB }, diff --git a/drivers/media/dvb-frontends/s5h1411.c b/drivers/media/dvb-frontends/s5h1411.c index af5962807f2c..98aeed1d2284 100644 --- a/drivers/media/dvb-frontends/s5h1411.c +++ b/drivers/media/dvb-frontends/s5h1411.c @@ -918,9 +918,9 @@ static const struct dvb_frontend_ops s5h1411_ops = { .delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B }, .info = { .name = "Samsung S5H1411 QAM/8VSB Frontend", - .frequency_min = 54000000, - .frequency_max = 858000000, - .frequency_stepsize = 62500, + .frequency_min_hz = 54 * MHz, + .frequency_max_hz = 858 * MHz, + .frequency_stepsize_hz = 62500, .caps = FE_CAN_QAM_64 | FE_CAN_QAM_256 | FE_CAN_8VSB }, diff --git a/drivers/media/dvb-frontends/s5h1420.c b/drivers/media/dvb-frontends/s5h1420.c index 8b2222530227..a65cdf8e8cd9 100644 --- a/drivers/media/dvb-frontends/s5h1420.c +++ b/drivers/media/dvb-frontends/s5h1420.c @@ -934,10 +934,10 @@ static const struct dvb_frontend_ops s5h1420_ops = { .delsys = { SYS_DVBS }, .info = { .name = "Samsung S5H1420/PnpNetwork PN1010 DVB-S", - .frequency_min = 950000, - .frequency_max = 2150000, - .frequency_stepsize = 125, /* kHz for QPSK frontends */ - .frequency_tolerance = 29500, + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2150 * MHz, + .frequency_stepsize_hz = 125 * kHz, + .frequency_tolerance_hz = 29500 * kHz, .symbol_rate_min = 1000000, .symbol_rate_max = 45000000, /* .symbol_rate_tolerance = ???,*/ diff --git a/drivers/media/dvb-frontends/s5h1432.c b/drivers/media/dvb-frontends/s5h1432.c index 740a60df0455..4dc3febc0e12 100644 --- a/drivers/media/dvb-frontends/s5h1432.c +++ b/drivers/media/dvb-frontends/s5h1432.c @@ -370,9 +370,9 @@ static const struct dvb_frontend_ops s5h1432_ops = { .delsys = { SYS_DVBT }, .info = { .name = "Samsung s5h1432 DVB-T Frontend", - .frequency_min = 177000000, - .frequency_max = 858000000, - .frequency_stepsize = 166666, + .frequency_min_hz = 177 * MHz, + .frequency_max_hz = 858 * MHz, + .frequency_stepsize_hz = 166666, .caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO | FE_CAN_QPSK | FE_CAN_QAM_16 | FE_CAN_QAM_64 | FE_CAN_QAM_AUTO | diff --git a/drivers/media/dvb-frontends/s921.c b/drivers/media/dvb-frontends/s921.c index 6c9015236655..79276871112a 100644 --- a/drivers/media/dvb-frontends/s921.c +++ b/drivers/media/dvb-frontends/s921.c @@ -510,15 +510,14 @@ static const struct dvb_frontend_ops s921_ops = { /* Use dib8000 values per default */ .info = { .name = "Sharp S921", - .frequency_min = 470000000, + .frequency_min_hz = 470 * MHz, /* * Max should be 770MHz instead, according with Sharp docs, * but Leadership doc says it works up to 806 MHz. This is * required to get channel 69, used in Brazil */ - .frequency_max = 806000000, - .frequency_tolerance = 0, - .caps = FE_CAN_INVERSION_AUTO | + .frequency_max_hz = 806 * MHz, + .caps = FE_CAN_INVERSION_AUTO | FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO | FE_CAN_QPSK | FE_CAN_QAM_16 | FE_CAN_QAM_64 | diff --git a/drivers/media/dvb-frontends/si2165.c b/drivers/media/dvb-frontends/si2165.c index 2dd336f95cbf..feacd8da421d 100644 --- a/drivers/media/dvb-frontends/si2165.c +++ b/drivers/media/dvb-frontends/si2165.c @@ -1120,7 +1120,7 @@ static const struct dvb_frontend_ops si2165_ops = { .symbol_rate_min = 1000000, .symbol_rate_max = 7200000, /* For DVB-T */ - .frequency_stepsize = 166667, + .frequency_stepsize_hz = 166667, .caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 | diff --git a/drivers/media/dvb-frontends/si21xx.c b/drivers/media/dvb-frontends/si21xx.c index 9b32a1b3205e..8546a236d452 100644 --- a/drivers/media/dvb-frontends/si21xx.c +++ b/drivers/media/dvb-frontends/si21xx.c @@ -870,10 +870,9 @@ static const struct dvb_frontend_ops si21xx_ops = { .delsys = { SYS_DVBS }, .info = { .name = "SL SI21XX DVB-S", - .frequency_min = 950000, - .frequency_max = 2150000, - .frequency_stepsize = 125, /* kHz for QPSK frontends */ - .frequency_tolerance = 0, + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2150 * MHz, + .frequency_stepsize_hz = 125 * kHz, .symbol_rate_min = 1000000, .symbol_rate_max = 45000000, .symbol_rate_tolerance = 500, /* ppm */ diff --git a/drivers/media/dvb-frontends/sp8870.c b/drivers/media/dvb-frontends/sp8870.c index 1d57a20093fc..8d31cf3f4f07 100644 --- a/drivers/media/dvb-frontends/sp8870.c +++ b/drivers/media/dvb-frontends/sp8870.c @@ -584,9 +584,9 @@ static const struct dvb_frontend_ops sp8870_ops = { .delsys = { SYS_DVBT }, .info = { .name = "Spase SP8870 DVB-T", - .frequency_min = 470000000, - .frequency_max = 860000000, - .frequency_stepsize = 166666, + .frequency_min_hz = 470 * MHz, + .frequency_max_hz = 860 * MHz, + .frequency_stepsize_hz = 166666, .caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO | diff --git a/drivers/media/dvb-frontends/sp887x.c b/drivers/media/dvb-frontends/sp887x.c index 57a0d0ae2b48..c02f50995df4 100644 --- a/drivers/media/dvb-frontends/sp887x.c +++ b/drivers/media/dvb-frontends/sp887x.c @@ -594,9 +594,9 @@ static const struct dvb_frontend_ops sp887x_ops = { .delsys = { SYS_DVBT }, .info = { .name = "Spase SP887x DVB-T", - .frequency_min = 50500000, - .frequency_max = 858000000, - .frequency_stepsize = 166666, + .frequency_min_hz = 50500 * kHz, + .frequency_max_hz = 858000 * kHz, + .frequency_stepsize_hz = 166666, .caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO | FE_CAN_QPSK | FE_CAN_QAM_16 | FE_CAN_QAM_64 | diff --git a/drivers/media/dvb-frontends/stb0899_drv.c b/drivers/media/dvb-frontends/stb0899_drv.c index 3c654ae16e78..874e9c9125d6 100644 --- a/drivers/media/dvb-frontends/stb0899_drv.c +++ b/drivers/media/dvb-frontends/stb0899_drv.c @@ -1584,10 +1584,8 @@ static const struct dvb_frontend_ops stb0899_ops = { .delsys = { SYS_DVBS, SYS_DVBS2, SYS_DSS }, .info = { .name = "STB0899 Multistandard", - .frequency_min = 950000, - .frequency_max = 2150000, - .frequency_stepsize = 0, - .frequency_tolerance = 0, + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2150 * MHz, .symbol_rate_min = 5000000, .symbol_rate_max = 45000000, diff --git a/drivers/media/dvb-frontends/stv0288.c b/drivers/media/dvb-frontends/stv0288.c index f947ed947aae..c9a9fa4e2c1b 100644 --- a/drivers/media/dvb-frontends/stv0288.c +++ b/drivers/media/dvb-frontends/stv0288.c @@ -533,10 +533,9 @@ static const struct dvb_frontend_ops stv0288_ops = { .delsys = { SYS_DVBS }, .info = { .name = "ST STV0288 DVB-S", - .frequency_min = 950000, - .frequency_max = 2150000, - .frequency_stepsize = 1000, /* kHz for QPSK frontends */ - .frequency_tolerance = 0, + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2150 * MHz, + .frequency_stepsize_hz = 1 * MHz, .symbol_rate_min = 1000000, .symbol_rate_max = 45000000, .symbol_rate_tolerance = 500, /* ppm */ diff --git a/drivers/media/dvb-frontends/stv0297.c b/drivers/media/dvb-frontends/stv0297.c index b823c04e24d3..9a9915f71483 100644 --- a/drivers/media/dvb-frontends/stv0297.c +++ b/drivers/media/dvb-frontends/stv0297.c @@ -694,9 +694,9 @@ static const struct dvb_frontend_ops stv0297_ops = { .delsys = { SYS_DVBC_ANNEX_A }, .info = { .name = "ST STV0297 DVB-C", - .frequency_min = 47000000, - .frequency_max = 862000000, - .frequency_stepsize = 62500, + .frequency_min_hz = 470 * MHz, + .frequency_max_hz = 862 * MHz, + .frequency_stepsize_hz = 62500, .symbol_rate_min = 870000, .symbol_rate_max = 11700000, .caps = FE_CAN_QAM_16 | FE_CAN_QAM_32 | FE_CAN_QAM_64 | diff --git a/drivers/media/dvb-frontends/stv0299.c b/drivers/media/dvb-frontends/stv0299.c index 633b90e6fe86..4f466394a16c 100644 --- a/drivers/media/dvb-frontends/stv0299.c +++ b/drivers/media/dvb-frontends/stv0299.c @@ -717,10 +717,9 @@ static const struct dvb_frontend_ops stv0299_ops = { .delsys = { SYS_DVBS }, .info = { .name = "ST STV0299 DVB-S", - .frequency_min = 950000, - .frequency_max = 2150000, - .frequency_stepsize = 125, /* kHz for QPSK frontends */ - .frequency_tolerance = 0, + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2150 * MHz, + .frequency_stepsize_hz = 125 * kHz, .symbol_rate_min = 1000000, .symbol_rate_max = 45000000, .symbol_rate_tolerance = 500, /* ppm */ diff --git a/drivers/media/dvb-frontends/stv0367.c b/drivers/media/dvb-frontends/stv0367.c index 5435c908e298..5b91e740e135 100644 --- a/drivers/media/dvb-frontends/stv0367.c +++ b/drivers/media/dvb-frontends/stv0367.c @@ -1693,10 +1693,9 @@ static const struct dvb_frontend_ops stv0367ter_ops = { .delsys = { SYS_DVBT }, .info = { .name = "ST STV0367 DVB-T", - .frequency_min = 47000000, - .frequency_max = 862000000, - .frequency_stepsize = 15625, - .frequency_tolerance = 0, + .frequency_min_hz = 47 * MHz, + .frequency_max_hz = 862 * MHz, + .frequency_stepsize_hz = 15625, .caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO | @@ -2867,9 +2866,9 @@ static const struct dvb_frontend_ops stv0367cab_ops = { .delsys = { SYS_DVBC_ANNEX_A }, .info = { .name = "ST STV0367 DVB-C", - .frequency_min = 47000000, - .frequency_max = 862000000, - .frequency_stepsize = 62500, + .frequency_min_hz = 47 * MHz, + .frequency_max_hz = 862 * MHz, + .frequency_stepsize_hz = 62500, .symbol_rate_min = 870000, .symbol_rate_max = 11700000, .caps = 0x400 |/* FE_CAN_QAM_4 */ @@ -3273,10 +3272,9 @@ static const struct dvb_frontend_ops stv0367ddb_ops = { .delsys = { SYS_DVBC_ANNEX_A, SYS_DVBT }, .info = { .name = "ST STV0367 DDB DVB-C/T", - .frequency_min = 47000000, - .frequency_max = 865000000, - .frequency_stepsize = 166667, - .frequency_tolerance = 0, + .frequency_min_hz = 47 * MHz, + .frequency_max_hz = 865 * MHz, + .frequency_stepsize_hz = 166667, .symbol_rate_min = 870000, .symbol_rate_max = 11700000, .caps = /* DVB-C */ diff --git a/drivers/media/dvb-frontends/stv0900_core.c b/drivers/media/dvb-frontends/stv0900_core.c index 72f17b97ca04..254618a06140 100644 --- a/drivers/media/dvb-frontends/stv0900_core.c +++ b/drivers/media/dvb-frontends/stv0900_core.c @@ -1875,10 +1875,9 @@ static const struct dvb_frontend_ops stv0900_ops = { .delsys = { SYS_DVBS, SYS_DVBS2, SYS_DSS }, .info = { .name = "STV0900 frontend", - .frequency_min = 950000, - .frequency_max = 2150000, - .frequency_stepsize = 125, - .frequency_tolerance = 0, + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2150 * MHz, + .frequency_stepsize_hz = 125 * kHz, .symbol_rate_min = 1000000, .symbol_rate_max = 45000000, .symbol_rate_tolerance = 500, diff --git a/drivers/media/dvb-frontends/stv090x.c b/drivers/media/dvb-frontends/stv090x.c index 9133f65d4623..a0622bb71803 100644 --- a/drivers/media/dvb-frontends/stv090x.c +++ b/drivers/media/dvb-frontends/stv090x.c @@ -4905,10 +4905,8 @@ static const struct dvb_frontend_ops stv090x_ops = { .delsys = { SYS_DVBS, SYS_DVBS2, SYS_DSS }, .info = { .name = "STV090x Multistandard", - .frequency_min = 950000, - .frequency_max = 2150000, - .frequency_stepsize = 0, - .frequency_tolerance = 0, + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2150 * MHz, .symbol_rate_min = 1000000, .symbol_rate_max = 45000000, .caps = FE_CAN_INVERSION_AUTO | diff --git a/drivers/media/dvb-frontends/stv0910.c b/drivers/media/dvb-frontends/stv0910.c index 91b21eb59531..4c86073f1a8d 100644 --- a/drivers/media/dvb-frontends/stv0910.c +++ b/drivers/media/dvb-frontends/stv0910.c @@ -1724,10 +1724,8 @@ static const struct dvb_frontend_ops stv0910_ops = { .delsys = { SYS_DVBS, SYS_DVBS2, SYS_DSS }, .info = { .name = "ST STV0910", - .frequency_min = 950000, - .frequency_max = 2150000, - .frequency_stepsize = 0, - .frequency_tolerance = 0, + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2150 * MHz, .symbol_rate_min = 100000, .symbol_rate_max = 70000000, .caps = FE_CAN_INVERSION_AUTO | diff --git a/drivers/media/dvb-frontends/tc90522.c b/drivers/media/dvb-frontends/tc90522.c index 7abf6b0916ed..2ad81a438d6a 100644 --- a/drivers/media/dvb-frontends/tc90522.c +++ b/drivers/media/dvb-frontends/tc90522.c @@ -714,8 +714,8 @@ static const struct dvb_frontend_ops tc90522_ops_sat = { .delsys = { SYS_ISDBS }, .info = { .name = "Toshiba TC90522 ISDB-S module", - .frequency_min = 950000, - .frequency_max = 2150000, + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2150 * MHz, .caps = FE_CAN_INVERSION_AUTO | FE_CAN_FEC_AUTO | FE_CAN_QAM_AUTO | FE_CAN_TRANSMISSION_MODE_AUTO | FE_CAN_GUARD_INTERVAL_AUTO | FE_CAN_HIERARCHY_AUTO, @@ -734,9 +734,9 @@ static const struct dvb_frontend_ops tc90522_ops_ter = { .delsys = { SYS_ISDBT }, .info = { .name = "Toshiba TC90522 ISDB-T module", - .frequency_min = 470000000, - .frequency_max = 770000000, - .frequency_stepsize = 142857, + .frequency_min_hz = 470 * MHz, + .frequency_max_hz = 770 * MHz, + .frequency_stepsize_hz = 142857, .caps = FE_CAN_INVERSION_AUTO | FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO | diff --git a/drivers/media/dvb-frontends/tda10021.c b/drivers/media/dvb-frontends/tda10021.c index 4f588ebde39d..5cd885d4ea04 100644 --- a/drivers/media/dvb-frontends/tda10021.c +++ b/drivers/media/dvb-frontends/tda10021.c @@ -487,11 +487,11 @@ static const struct dvb_frontend_ops tda10021_ops = { .delsys = { SYS_DVBC_ANNEX_A, SYS_DVBC_ANNEX_C }, .info = { .name = "Philips TDA10021 DVB-C", - .frequency_stepsize = 62500, - .frequency_min = 47000000, - .frequency_max = 862000000, - .symbol_rate_min = (XIN/2)/64, /* SACLK/64 == (XIN/2)/64 */ - .symbol_rate_max = (XIN/2)/4, /* SACLK/4 */ + .frequency_min_hz = 47 * MHz, + .frequency_max_hz = 862 * MHz, + .frequency_stepsize_hz = 62500, + .symbol_rate_min = (XIN / 2) / 64, /* SACLK/64 == (XIN/2)/64 */ + .symbol_rate_max = (XIN / 2) / 4, /* SACLK/4 */ #if 0 .frequency_tolerance = ???, .symbol_rate_tolerance = ???, /* ppm */ /* == 8% (spec p. 5) */ diff --git a/drivers/media/dvb-frontends/tda10023.c b/drivers/media/dvb-frontends/tda10023.c index 6c84916234e3..0a9a54563ebe 100644 --- a/drivers/media/dvb-frontends/tda10023.c +++ b/drivers/media/dvb-frontends/tda10023.c @@ -575,9 +575,9 @@ static const struct dvb_frontend_ops tda10023_ops = { .delsys = { SYS_DVBC_ANNEX_A, SYS_DVBC_ANNEX_C }, .info = { .name = "Philips TDA10023 DVB-C", - .frequency_stepsize = 62500, - .frequency_min = 47000000, - .frequency_max = 862000000, + .frequency_min_hz = 47 * MHz, + .frequency_max_hz = 862 * MHz, + .frequency_stepsize_hz = 62500, .symbol_rate_min = 0, /* set in tda10023_attach */ .symbol_rate_max = 0, /* set in tda10023_attach */ .caps = 0x400 | //FE_CAN_QAM_4 diff --git a/drivers/media/dvb-frontends/tda10048.c b/drivers/media/dvb-frontends/tda10048.c index de82a2558e15..c01d60a88af2 100644 --- a/drivers/media/dvb-frontends/tda10048.c +++ b/drivers/media/dvb-frontends/tda10048.c @@ -1156,9 +1156,9 @@ static const struct dvb_frontend_ops tda10048_ops = { .delsys = { SYS_DVBT }, .info = { .name = "NXP TDA10048HN DVB-T", - .frequency_min = 177000000, - .frequency_max = 858000000, - .frequency_stepsize = 166666, + .frequency_min_hz = 177 * MHz, + .frequency_max_hz = 858 * MHz, + .frequency_stepsize_hz = 166666, .caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO | FE_CAN_QPSK | FE_CAN_QAM_16 | FE_CAN_QAM_64 | FE_CAN_QAM_AUTO | diff --git a/drivers/media/dvb-frontends/tda1004x.c b/drivers/media/dvb-frontends/tda1004x.c index 7dcfb4a4b2d0..d402e4b722ca 100644 --- a/drivers/media/dvb-frontends/tda1004x.c +++ b/drivers/media/dvb-frontends/tda1004x.c @@ -1249,9 +1249,9 @@ static const struct dvb_frontend_ops tda10045_ops = { .delsys = { SYS_DVBT }, .info = { .name = "Philips TDA10045H DVB-T", - .frequency_min = 51000000, - .frequency_max = 858000000, - .frequency_stepsize = 166667, + .frequency_min_hz = 51 * MHz, + .frequency_max_hz = 858 * MHz, + .frequency_stepsize_hz = 166667, .caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO | @@ -1319,9 +1319,9 @@ static const struct dvb_frontend_ops tda10046_ops = { .delsys = { SYS_DVBT }, .info = { .name = "Philips TDA10046H DVB-T", - .frequency_min = 51000000, - .frequency_max = 858000000, - .frequency_stepsize = 166667, + .frequency_min_hz = 51 * MHz, + .frequency_max_hz = 858 * MHz, + .frequency_stepsize_hz = 166667, .caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO | diff --git a/drivers/media/dvb-frontends/tda10071.c b/drivers/media/dvb-frontends/tda10071.c index 1ed67c08e699..097c42d3f8c2 100644 --- a/drivers/media/dvb-frontends/tda10071.c +++ b/drivers/media/dvb-frontends/tda10071.c @@ -681,8 +681,8 @@ static int tda10071_set_frontend(struct dvb_frontend *fe) cmd.args[5] = (c->frequency >> 0) & 0xff; cmd.args[6] = ((c->symbol_rate / 1000) >> 8) & 0xff; cmd.args[7] = ((c->symbol_rate / 1000) >> 0) & 0xff; - cmd.args[8] = (tda10071_ops.info.frequency_tolerance >> 8) & 0xff; - cmd.args[9] = (tda10071_ops.info.frequency_tolerance >> 0) & 0xff; + cmd.args[8] = ((tda10071_ops.info.frequency_tolerance_hz / 1000) >> 8) & 0xff; + cmd.args[9] = ((tda10071_ops.info.frequency_tolerance_hz / 1000) >> 0) & 0xff; cmd.args[10] = rolloff; cmd.args[11] = inversion; cmd.args[12] = pilot; @@ -1106,9 +1106,9 @@ static const struct dvb_frontend_ops tda10071_ops = { .delsys = { SYS_DVBS, SYS_DVBS2 }, .info = { .name = "NXP TDA10071", - .frequency_min = 950000, - .frequency_max = 2150000, - .frequency_tolerance = 5000, + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2150 * MHz, + .frequency_tolerance_hz = 5 * MHz, .symbol_rate_min = 1000000, .symbol_rate_max = 45000000, .caps = FE_CAN_INVERSION_AUTO | diff --git a/drivers/media/dvb-frontends/tda10086.c b/drivers/media/dvb-frontends/tda10086.c index 1a95c521e97f..8323e4e53d66 100644 --- a/drivers/media/dvb-frontends/tda10086.c +++ b/drivers/media/dvb-frontends/tda10086.c @@ -710,9 +710,9 @@ static const struct dvb_frontend_ops tda10086_ops = { .delsys = { SYS_DVBS }, .info = { .name = "Philips TDA10086 DVB-S", - .frequency_min = 950000, - .frequency_max = 2150000, - .frequency_stepsize = 125, /* kHz for QPSK frontends */ + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2150 * MHz, + .frequency_stepsize_hz = 125 * kHz, .symbol_rate_min = 1000000, .symbol_rate_max = 45000000, .caps = FE_CAN_INVERSION_AUTO | diff --git a/drivers/media/dvb-frontends/tda8083.c b/drivers/media/dvb-frontends/tda8083.c index 29b4f64c030c..53b26060db7e 100644 --- a/drivers/media/dvb-frontends/tda8083.c +++ b/drivers/media/dvb-frontends/tda8083.c @@ -453,10 +453,9 @@ static const struct dvb_frontend_ops tda8083_ops = { .delsys = { SYS_DVBS }, .info = { .name = "Philips TDA8083 DVB-S", - .frequency_min = 920000, /* TDA8060 */ - .frequency_max = 2200000, /* TDA8060 */ - .frequency_stepsize = 125, /* kHz for QPSK frontends */ - /* .frequency_tolerance = ???,*/ + .frequency_min_hz = 920 * MHz, /* TDA8060 */ + .frequency_max_hz = 2200 * MHz, /* TDA8060 */ + .frequency_stepsize_hz = 125 * kHz, .symbol_rate_min = 12000000, .symbol_rate_max = 30000000, /* .symbol_rate_tolerance = ???,*/ diff --git a/drivers/media/dvb-frontends/ves1820.c b/drivers/media/dvb-frontends/ves1820.c index 17600989f121..eb1249d81310 100644 --- a/drivers/media/dvb-frontends/ves1820.c +++ b/drivers/media/dvb-frontends/ves1820.c @@ -412,9 +412,9 @@ static const struct dvb_frontend_ops ves1820_ops = { .delsys = { SYS_DVBC_ANNEX_A }, .info = { .name = "VLSI VES1820 DVB-C", - .frequency_stepsize = 62500, - .frequency_min = 47000000, - .frequency_max = 862000000, + .frequency_min_hz = 47 * MHz, + .frequency_max_hz = 862 * MHz, + .frequency_stepsize_hz = 62500, .caps = FE_CAN_QAM_16 | FE_CAN_QAM_32 | FE_CAN_QAM_64 | diff --git a/drivers/media/dvb-frontends/ves1x93.c b/drivers/media/dvb-frontends/ves1x93.c index 0c7b3286b04d..ddc5bfd84cd5 100644 --- a/drivers/media/dvb-frontends/ves1x93.c +++ b/drivers/media/dvb-frontends/ves1x93.c @@ -516,10 +516,10 @@ static const struct dvb_frontend_ops ves1x93_ops = { .delsys = { SYS_DVBS }, .info = { .name = "VLSI VES1x93 DVB-S", - .frequency_min = 950000, - .frequency_max = 2150000, - .frequency_stepsize = 125, /* kHz for QPSK frontends */ - .frequency_tolerance = 29500, + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2150 * MHz, + .frequency_stepsize_hz = 125 * kHz, + .frequency_tolerance_hz = 29500 * kHz, .symbol_rate_min = 1000000, .symbol_rate_max = 45000000, /* .symbol_rate_tolerance = ???,*/ diff --git a/drivers/media/dvb-frontends/zl10036.c b/drivers/media/dvb-frontends/zl10036.c index e5a432fd84c3..f1c92338015d 100644 --- a/drivers/media/dvb-frontends/zl10036.c +++ b/drivers/media/dvb-frontends/zl10036.c @@ -311,8 +311,8 @@ static int zl10036_set_params(struct dvb_frontend *fe) /* ensure correct values * maybe redundant as core already checks this */ - if ((frequency < fe->ops.info.frequency_min) - || (frequency > fe->ops.info.frequency_max)) + if ((frequency < fe->ops.info.frequency_min_hz / kHz) + || (frequency > fe->ops.info.frequency_max_hz / kHz)) return -EINVAL; /* diff --git a/drivers/media/dvb-frontends/zl10353.c b/drivers/media/dvb-frontends/zl10353.c index c9901f45deb7..42e63a3fa121 100644 --- a/drivers/media/dvb-frontends/zl10353.c +++ b/drivers/media/dvb-frontends/zl10353.c @@ -635,10 +635,9 @@ static const struct dvb_frontend_ops zl10353_ops = { .delsys = { SYS_DVBT }, .info = { .name = "Zarlink ZL10353 DVB-T", - .frequency_min = 174000000, - .frequency_max = 862000000, - .frequency_stepsize = 166667, - .frequency_tolerance = 0, + .frequency_min_hz = 174 * MHz, + .frequency_max_hz = 862 * MHz, + .frequency_stepsize_hz = 166667, .caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO | diff --git a/drivers/media/firewire/firedtv-fe.c b/drivers/media/firewire/firedtv-fe.c index a2ef4ede8ebe..69087ae6c1d0 100644 --- a/drivers/media/firewire/firedtv-fe.c +++ b/drivers/media/firewire/firedtv-fe.c @@ -152,7 +152,7 @@ static int fdtv_set_frontend(struct dvb_frontend *fe) void fdtv_frontend_init(struct firedtv *fdtv, const char *name) { struct dvb_frontend_ops *ops = &fdtv->fe.ops; - struct dvb_frontend_info *fi = &ops->info; + struct dvb_frontend_internal_info *fi = &ops->info; ops->init = fdtv_dvb_init; ops->sleep = fdtv_sleep; @@ -174,9 +174,9 @@ void fdtv_frontend_init(struct firedtv *fdtv, const char *name) case FIREDTV_DVB_S: ops->delsys[0] = SYS_DVBS; - fi->frequency_min = 950000; - fi->frequency_max = 2150000; - fi->frequency_stepsize = 125; + fi->frequency_min_hz = 950 * MHz; + fi->frequency_max_hz = 2150 * MHz; + fi->frequency_stepsize_hz = 125 * kHz; fi->symbol_rate_min = 1000000; fi->symbol_rate_max = 40000000; @@ -194,9 +194,9 @@ void fdtv_frontend_init(struct firedtv *fdtv, const char *name) ops->delsys[0] = SYS_DVBS; ops->delsys[1] = SYS_DVBS2; - fi->frequency_min = 950000; - fi->frequency_max = 2150000; - fi->frequency_stepsize = 125; + fi->frequency_min_hz = 950 * MHz; + fi->frequency_max_hz = 2150 * MHz; + fi->frequency_stepsize_hz = 125 * kHz; fi->symbol_rate_min = 1000000; fi->symbol_rate_max = 40000000; @@ -214,9 +214,9 @@ void fdtv_frontend_init(struct firedtv *fdtv, const char *name) case FIREDTV_DVB_C: ops->delsys[0] = SYS_DVBC_ANNEX_A; - fi->frequency_min = 47000000; - fi->frequency_max = 866000000; - fi->frequency_stepsize = 62500; + fi->frequency_min_hz = 47 * MHz; + fi->frequency_max_hz = 866 * MHz; + fi->frequency_stepsize_hz = 62500; fi->symbol_rate_min = 870000; fi->symbol_rate_max = 6900000; @@ -232,9 +232,9 @@ void fdtv_frontend_init(struct firedtv *fdtv, const char *name) case FIREDTV_DVB_T: ops->delsys[0] = SYS_DVBT; - fi->frequency_min = 49000000; - fi->frequency_max = 861000000; - fi->frequency_stepsize = 62500; + fi->frequency_min_hz = 49 * MHz; + fi->frequency_max_hz = 861 * MHz; + fi->frequency_stepsize_hz = 62500; fi->caps = FE_CAN_INVERSION_AUTO | FE_CAN_FEC_2_3 | diff --git a/drivers/media/pci/bt8xx/dst.c b/drivers/media/pci/bt8xx/dst.c index 2e33b7236672..b98de2a22f78 100644 --- a/drivers/media/pci/bt8xx/dst.c +++ b/drivers/media/pci/bt8xx/dst.c @@ -1739,9 +1739,9 @@ static const struct dvb_frontend_ops dst_dvbt_ops = { .delsys = { SYS_DVBT }, .info = { .name = "DST DVB-T", - .frequency_min = 137000000, - .frequency_max = 858000000, - .frequency_stepsize = 166667, + .frequency_min_hz = 137 * MHz, + .frequency_max_hz = 858 * MHz, + .frequency_stepsize_hz = 166667, .caps = FE_CAN_FEC_AUTO | FE_CAN_QAM_AUTO | FE_CAN_QAM_16 | @@ -1768,10 +1768,10 @@ static const struct dvb_frontend_ops dst_dvbs_ops = { .delsys = { SYS_DVBS }, .info = { .name = "DST DVB-S", - .frequency_min = 950000, - .frequency_max = 2150000, - .frequency_stepsize = 1000, /* kHz for QPSK frontends */ - .frequency_tolerance = 29500, + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2150 * MHz, + .frequency_stepsize_hz = 1 * MHz, + .frequency_tolerance_hz = 29500 * kHz, .symbol_rate_min = 1000000, .symbol_rate_max = 45000000, /* . symbol_rate_tolerance = ???,*/ @@ -1797,9 +1797,9 @@ static const struct dvb_frontend_ops dst_dvbc_ops = { .delsys = { SYS_DVBC_ANNEX_A }, .info = { .name = "DST DVB-C", - .frequency_stepsize = 62500, - .frequency_min = 51000000, - .frequency_max = 858000000, + .frequency_min_hz = 51 * MHz, + .frequency_max_hz = 858 * MHz, + .frequency_stepsize_hz = 62500, .symbol_rate_min = 1000000, .symbol_rate_max = 45000000, .caps = FE_CAN_FEC_AUTO | @@ -1826,9 +1826,9 @@ static const struct dvb_frontend_ops dst_atsc_ops = { .delsys = { SYS_ATSC }, .info = { .name = "DST ATSC", - .frequency_stepsize = 62500, - .frequency_min = 510000000, - .frequency_max = 858000000, + .frequency_min_hz = 510 * MHz, + .frequency_max_hz = 858 * MHz, + .frequency_stepsize_hz = 62500, .symbol_rate_min = 1000000, .symbol_rate_max = 45000000, .caps = FE_CAN_FEC_AUTO | FE_CAN_QAM_AUTO | FE_CAN_QAM_64 | FE_CAN_QAM_256 | FE_CAN_8VSB diff --git a/drivers/media/pci/bt8xx/dvb-bt8xx.c b/drivers/media/pci/bt8xx/dvb-bt8xx.c index 6b2a9e6eb6a8..2f810b7130e6 100644 --- a/drivers/media/pci/bt8xx/dvb-bt8xx.c +++ b/drivers/media/pci/bt8xx/dvb-bt8xx.c @@ -602,8 +602,8 @@ static void frontend_init(struct dvb_bt8xx_card *card, u32 type) if (card->fe != NULL) { card->fe->ops.tuner_ops.calc_regs = thomson_dtt7579_tuner_calc_regs; - card->fe->ops.info.frequency_min = 174000000; - card->fe->ops.info.frequency_max = 862000000; + card->fe->ops.info.frequency_min_hz = 174 * MHz; + card->fe->ops.info.frequency_max_hz = 862 * MHz; } break; @@ -655,8 +655,8 @@ static void frontend_init(struct dvb_bt8xx_card *card, u32 type) card->fe = dvb_attach(mt352_attach, &advbt771_samsung_tdtc9251dh0_config, card->i2c_adapter); if (card->fe != NULL) { card->fe->ops.tuner_ops.calc_regs = advbt771_samsung_tdtc9251dh0_tuner_calc_regs; - card->fe->ops.info.frequency_min = 174000000; - card->fe->ops.info.frequency_max = 862000000; + card->fe->ops.info.frequency_min_hz = 174 * MHz; + card->fe->ops.info.frequency_max_hz = 862 * MHz; } break; diff --git a/drivers/media/pci/ddbridge/ddbridge-sx8.c b/drivers/media/pci/ddbridge/ddbridge-sx8.c index 4418604258d1..64f05f5ee039 100644 --- a/drivers/media/pci/ddbridge/ddbridge-sx8.c +++ b/drivers/media/pci/ddbridge/ddbridge-sx8.c @@ -454,10 +454,8 @@ static struct dvb_frontend_ops sx8_ops = { .delsys = { SYS_DVBS, SYS_DVBS2 }, .info = { .name = "Digital Devices MaxSX8 MCI DVB-S/S2/S2X", - .frequency_min = 950000, - .frequency_max = 2150000, - .frequency_stepsize = 0, - .frequency_tolerance = 0, + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2150 * MHz, .symbol_rate_min = 100000, .symbol_rate_max = 100000000, .caps = FE_CAN_INVERSION_AUTO | diff --git a/drivers/media/pci/mantis/mantis_vp3030.c b/drivers/media/pci/mantis/mantis_vp3030.c index 14f6e153000c..9797c9fd8259 100644 --- a/drivers/media/pci/mantis/mantis_vp3030.c +++ b/drivers/media/pci/mantis/mantis_vp3030.c @@ -42,8 +42,8 @@ static struct zl10353_config mantis_vp3030_config = { static struct tda665x_config env57h12d5_config = { .name = "ENV57H12D5 (ET-50DT)", .addr = 0x60, - .frequency_min = 47000000, - .frequency_max = 862000000, + .frequency_min = 47 * MHz, + .frequency_max = 862 * MHz, .frequency_offst = 3616667, .ref_multiplier = 6, /* 1/6 MHz */ .ref_divider = 100000, /* 1/6 MHz */ diff --git a/drivers/media/tuners/mxl5007t.c b/drivers/media/tuners/mxl5007t.c index 4081fd97c3b2..54d9226aaff7 100644 --- a/drivers/media/tuners/mxl5007t.c +++ b/drivers/media/tuners/mxl5007t.c @@ -59,8 +59,6 @@ MODULE_PARM_DESC(debug, "set debug level"); /* ------------------------------------------------------------------------- */ -#define MHz 1000000 - enum mxl5007t_mode { MxL_MODE_ISDBT = 0, MxL_MODE_DVBT = 1, diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.c b/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.c index 221cf46b4140..9f74453799a2 100644 --- a/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.c +++ b/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.c @@ -554,9 +554,9 @@ static const struct dvb_frontend_ops mxl111sf_demod_ops = { .delsys = { SYS_DVBT }, .info = { .name = "MaxLinear MxL111SF DVB-T demodulator", - .frequency_min = 177000000, - .frequency_max = 858000000, - .frequency_stepsize = 166666, + .frequency_min_hz = 177 * MHz, + .frequency_max_hz = 858 * MHz, + .frequency_stepsize_hz = 166666, .caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO | FE_CAN_QPSK | FE_CAN_QAM_16 | FE_CAN_QAM_64 | diff --git a/drivers/media/usb/dvb-usb/af9005-fe.c b/drivers/media/usb/dvb-usb/af9005-fe.c index 7fbbc954da16..09cc3a21af65 100644 --- a/drivers/media/usb/dvb-usb/af9005-fe.c +++ b/drivers/media/usb/dvb-usb/af9005-fe.c @@ -1455,9 +1455,9 @@ static const struct dvb_frontend_ops af9005_fe_ops = { .delsys = { SYS_DVBT }, .info = { .name = "AF9005 USB DVB-T", - .frequency_min = 44250000, - .frequency_max = 867250000, - .frequency_stepsize = 250000, + .frequency_min_hz = 44250 * kHz, + .frequency_max_hz = 867250 * kHz, + .frequency_stepsize_hz = 250 * kHz, .caps = FE_CAN_INVERSION_AUTO | FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO | diff --git a/drivers/media/usb/dvb-usb/cinergyT2-fe.c b/drivers/media/usb/dvb-usb/cinergyT2-fe.c index 5a2f81311fb7..df71df7ed524 100644 --- a/drivers/media/usb/dvb-usb/cinergyT2-fe.c +++ b/drivers/media/usb/dvb-usb/cinergyT2-fe.c @@ -295,9 +295,9 @@ static const struct dvb_frontend_ops cinergyt2_fe_ops = { .delsys = { SYS_DVBT }, .info = { .name = DRIVER_NAME, - .frequency_min = 174000000, - .frequency_max = 862000000, - .frequency_stepsize = 166667, + .frequency_min_hz = 174 * MHz, + .frequency_max_hz = 862 * MHz, + .frequency_stepsize_hz = 166667, .caps = FE_CAN_INVERSION_AUTO | FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 diff --git a/drivers/media/usb/dvb-usb/dtt200u-fe.c b/drivers/media/usb/dvb-usb/dtt200u-fe.c index 7e75aae34fb8..1ca3a51b2ae3 100644 --- a/drivers/media/usb/dvb-usb/dtt200u-fe.c +++ b/drivers/media/usb/dvb-usb/dtt200u-fe.c @@ -230,9 +230,9 @@ static const struct dvb_frontend_ops dtt200u_fe_ops = { .delsys = { SYS_DVBT }, .info = { .name = "WideView USB DVB-T", - .frequency_min = 44250000, - .frequency_max = 867250000, - .frequency_stepsize = 250000, + .frequency_min_hz = 44250 * kHz, + .frequency_max_hz = 867250 * kHz, + .frequency_stepsize_hz = 250 * kHz, .caps = FE_CAN_INVERSION_AUTO | FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO | diff --git a/drivers/media/usb/dvb-usb/friio-fe.c b/drivers/media/usb/dvb-usb/friio-fe.c index 932f262452eb..e6bd0ed8d789 100644 --- a/drivers/media/usb/dvb-usb/friio-fe.c +++ b/drivers/media/usb/dvb-usb/friio-fe.c @@ -133,10 +133,10 @@ static int jdvbt90502_pll_set_freq(struct jdvbt90502_state *state, u32 freq) u32 f; deb_fe("%s: freq=%d, step=%d\n", __func__, freq, - state->frontend.ops.info.frequency_stepsize); + state->frontend.ops.info.frequency_stepsize_hz); /* freq -> oscilator frequency conversion. */ /* freq: 473,000,000 + n*6,000,000 [+ 142857 (center freq. shift)] */ - f = freq / state->frontend.ops.info.frequency_stepsize; + f = freq / state->frontend.ops.info.frequency_stepsize_hz; /* add 399[1/7 MHZ] = 57MHz for the IF */ f += 399; /* add center frequency shift if necessary */ @@ -413,10 +413,9 @@ static const struct dvb_frontend_ops jdvbt90502_ops = { .delsys = { SYS_ISDBT }, .info = { .name = "Comtech JDVBT90502 ISDB-T", - .frequency_min = 473000000, /* UHF 13ch, center */ - .frequency_max = 767142857, /* UHF 62ch, center */ - .frequency_stepsize = JDVBT90502_PLL_CLK / JDVBT90502_PLL_DIVIDER, - .frequency_tolerance = 0, + .frequency_min_hz = 473000000, /* UHF 13ch, center */ + .frequency_max_hz = 767142857, /* UHF 62ch, center */ + .frequency_stepsize_hz = JDVBT90502_PLL_CLK / JDVBT90502_PLL_DIVIDER, /* NOTE: this driver ignores all parameters but frequency. */ .caps = FE_CAN_INVERSION_AUTO | diff --git a/drivers/media/usb/dvb-usb/vp702x-fe.c b/drivers/media/usb/dvb-usb/vp702x-fe.c index ae48146e005c..9eb811452f2e 100644 --- a/drivers/media/usb/dvb-usb/vp702x-fe.c +++ b/drivers/media/usb/dvb-usb/vp702x-fe.c @@ -349,10 +349,9 @@ static const struct dvb_frontend_ops vp702x_fe_ops = { .delsys = { SYS_DVBS }, .info = { .name = "Twinhan DST-like frontend (VP7021/VP7020) DVB-S", - .frequency_min = 950000, - .frequency_max = 2150000, - .frequency_stepsize = 1000, /* kHz for QPSK frontends */ - .frequency_tolerance = 0, + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2150 * MHz, + .frequency_stepsize_hz = 1 * MHz, .symbol_rate_min = 1000000, .symbol_rate_max = 45000000, .symbol_rate_tolerance = 500, /* ppm */ diff --git a/drivers/media/usb/dvb-usb/vp7045-fe.c b/drivers/media/usb/dvb-usb/vp7045-fe.c index f86040173b8d..1173ae29885b 100644 --- a/drivers/media/usb/dvb-usb/vp7045-fe.c +++ b/drivers/media/usb/dvb-usb/vp7045-fe.c @@ -162,9 +162,9 @@ static const struct dvb_frontend_ops vp7045_fe_ops = { .delsys = { SYS_DVBT }, .info = { .name = "Twinhan VP7045/46 USB DVB-T", - .frequency_min = 44250000, - .frequency_max = 867250000, - .frequency_stepsize = 1000, + .frequency_min_hz = 44250 * kHz, + .frequency_max_hz = 867250 * kHz, + .frequency_stepsize_hz = 1 * kHz, .caps = FE_CAN_INVERSION_AUTO | FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO | diff --git a/drivers/media/usb/ttusb-dec/ttusbdecfe.c b/drivers/media/usb/ttusb-dec/ttusbdecfe.c index 6ea05d909024..278bf6c5855b 100644 --- a/drivers/media/usb/ttusb-dec/ttusbdecfe.c +++ b/drivers/media/usb/ttusb-dec/ttusbdecfe.c @@ -247,9 +247,9 @@ static const struct dvb_frontend_ops ttusbdecfe_dvbt_ops = { .delsys = { SYS_DVBT }, .info = { .name = "TechnoTrend/Hauppauge DEC2000-t Frontend", - .frequency_min = 51000000, - .frequency_max = 858000000, - .frequency_stepsize = 62500, + .frequency_min_hz = 51 * MHz, + .frequency_max_hz = 858 * MHz, + .frequency_stepsize_hz = 62500, .caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO | FE_CAN_QAM_16 | FE_CAN_QAM_64 | FE_CAN_QAM_AUTO | @@ -270,9 +270,9 @@ static const struct dvb_frontend_ops ttusbdecfe_dvbs_ops = { .delsys = { SYS_DVBS }, .info = { .name = "TechnoTrend/Hauppauge DEC3000-s Frontend", - .frequency_min = 950000, - .frequency_max = 2150000, - .frequency_stepsize = 125, + .frequency_min_hz = 950 * MHz, + .frequency_max_hz = 2150 * MHz, + .frequency_stepsize_hz = 125 * kHz, .symbol_rate_min = 1000000, /* guessed */ .symbol_rate_max = 45000000, /* guessed */ .caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 | diff --git a/include/media/dvb_frontend.h b/include/media/dvb_frontend.h index aebaec2dc725..6f7a85ab3541 100644 --- a/include/media/dvb_frontend.h +++ b/include/media/dvb_frontend.h @@ -317,6 +317,34 @@ struct analog_demod_ops { struct dtv_frontend_properties; +/** + * struct dvb_frontend_internal_info - Frontend properties and capabilities + * + * @name: Name of the frontend + * @frequency_min_hz: Minimal frequency supported by the frontend. + * @frequency_max_hz: Minimal frequency supported by the frontend. + * @frequency_stepsize_hz: All frequencies are multiple of this value. + * @frequency_tolerance_hz: Frequency tolerance. + * @symbol_rate_min: Minimal symbol rate, in bauds + * (for Cable/Satellite systems). + * @symbol_rate_max: Maximal symbol rate, in bauds + * (for Cable/Satellite systems). + * @symbol_rate_tolerance: Maximal symbol rate tolerance, in ppm + * (for Cable/Satellite systems). + * @caps: Capabilities supported by the frontend, + * as specified in &enum fe_caps. + */ +struct dvb_frontend_internal_info { + char name[128]; + u32 frequency_min_hz; + u32 frequency_max_hz; + u32 frequency_stepsize_hz; + u32 frequency_tolerance_hz; + u32 symbol_rate_min; + u32 symbol_rate_max; + u32 symbol_rate_tolerance; + enum fe_caps caps; +}; /** * struct dvb_frontend_ops - Demodulation information and callbacks for @@ -404,7 +432,7 @@ struct dtv_frontend_properties; * @analog_ops: pointer to &struct analog_demod_ops */ struct dvb_frontend_ops { - struct dvb_frontend_info info; + struct dvb_frontend_internal_info info; u8 delsys[MAX_DELSYS]; -- cgit v1.2.3 From 0a4c58f5702858822621fa1177c7d3475f181ccb Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Thu, 2 Aug 2018 14:27:17 -0700 Subject: bpf: add ability to charge bpf maps memory dynamically This commits extends existing bpf maps memory charging API to support dynamic charging/uncharging. This is required to account memory used by maps, if all entries are created dynamically after the map initialization. Signed-off-by: Roman Gushchin Cc: Alexei Starovoitov Cc: Daniel Borkmann Acked-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 2 ++ kernel/bpf/syscall.c | 58 ++++++++++++++++++++++++++++++++++++++-------------- 2 files changed, 45 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 5b5ad95cf339..5a4a256473c3 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -435,6 +435,8 @@ struct bpf_map * __must_check bpf_map_inc(struct bpf_map *map, bool uref); void bpf_map_put_with_uref(struct bpf_map *map); void bpf_map_put(struct bpf_map *map); int bpf_map_precharge_memlock(u32 pages); +int bpf_map_charge_memlock(struct bpf_map *map, u32 pages); +void bpf_map_uncharge_memlock(struct bpf_map *map, u32 pages); void *bpf_map_area_alloc(size_t size, int numa_node); void bpf_map_area_free(void *base); void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index a31a1ba0f8ea..7958252a4d29 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -181,32 +181,60 @@ int bpf_map_precharge_memlock(u32 pages) return 0; } -static int bpf_map_charge_memlock(struct bpf_map *map) +static int bpf_charge_memlock(struct user_struct *user, u32 pages) { - struct user_struct *user = get_current_user(); - unsigned long memlock_limit; + unsigned long memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; - memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; + if (atomic_long_add_return(pages, &user->locked_vm) > memlock_limit) { + atomic_long_sub(pages, &user->locked_vm); + return -EPERM; + } + return 0; +} - atomic_long_add(map->pages, &user->locked_vm); +static void bpf_uncharge_memlock(struct user_struct *user, u32 pages) +{ + atomic_long_sub(pages, &user->locked_vm); +} + +static int bpf_map_init_memlock(struct bpf_map *map) +{ + struct user_struct *user = get_current_user(); + int ret; - if (atomic_long_read(&user->locked_vm) > memlock_limit) { - atomic_long_sub(map->pages, &user->locked_vm); + ret = bpf_charge_memlock(user, map->pages); + if (ret) { free_uid(user); - return -EPERM; + return ret; } map->user = user; - return 0; + return ret; } -static void bpf_map_uncharge_memlock(struct bpf_map *map) +static void bpf_map_release_memlock(struct bpf_map *map) { struct user_struct *user = map->user; - - atomic_long_sub(map->pages, &user->locked_vm); + bpf_uncharge_memlock(user, map->pages); free_uid(user); } +int bpf_map_charge_memlock(struct bpf_map *map, u32 pages) +{ + int ret; + + ret = bpf_charge_memlock(map->user, pages); + if (ret) + return ret; + map->pages += pages; + return ret; +} + +void bpf_map_uncharge_memlock(struct bpf_map *map, u32 pages) +{ + bpf_uncharge_memlock(map->user, pages); + map->pages -= pages; +} + static int bpf_map_alloc_id(struct bpf_map *map) { int id; @@ -256,7 +284,7 @@ static void bpf_map_free_deferred(struct work_struct *work) { struct bpf_map *map = container_of(work, struct bpf_map, work); - bpf_map_uncharge_memlock(map); + bpf_map_release_memlock(map); security_bpf_map_free(map); /* implementation dependent freeing */ map->ops->map_free(map); @@ -492,7 +520,7 @@ static int map_create(union bpf_attr *attr) if (err) goto free_map_nouncharge; - err = bpf_map_charge_memlock(map); + err = bpf_map_init_memlock(map); if (err) goto free_map_sec; @@ -515,7 +543,7 @@ static int map_create(union bpf_attr *attr) return err; free_map: - bpf_map_uncharge_memlock(map); + bpf_map_release_memlock(map); free_map_sec: security_bpf_map_free(map); free_map_nouncharge: -- cgit v1.2.3 From de9cbbaadba5adf88a19e46df61f7054000838f6 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Thu, 2 Aug 2018 14:27:18 -0700 Subject: bpf: introduce cgroup storage maps This commit introduces BPF_MAP_TYPE_CGROUP_STORAGE maps: a special type of maps which are implementing the cgroup storage. >From the userspace point of view it's almost a generic hash map with the (cgroup inode id, attachment type) pair used as a key. The only difference is that some operations are restricted: 1) a user can't create new entries, 2) a user can't remove existing entries. The lookup from userspace is o(log(n)). Signed-off-by: Roman Gushchin Cc: Alexei Starovoitov Cc: Daniel Borkmann Acked-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann --- include/linux/bpf-cgroup.h | 38 +++++ include/linux/bpf.h | 1 + include/linux/bpf_types.h | 3 + include/uapi/linux/bpf.h | 6 + kernel/bpf/Makefile | 1 + kernel/bpf/local_storage.c | 376 +++++++++++++++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 3 + kernel/bpf/verifier.c | 12 ++ 8 files changed, 440 insertions(+) create mode 100644 kernel/bpf/local_storage.c (limited to 'include') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index d50c2f0a655a..7d00d58869ed 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -4,19 +4,39 @@ #include #include +#include #include struct sock; struct sockaddr; struct cgroup; struct sk_buff; +struct bpf_map; +struct bpf_prog; struct bpf_sock_ops_kern; +struct bpf_cgroup_storage; #ifdef CONFIG_CGROUP_BPF extern struct static_key_false cgroup_bpf_enabled_key; #define cgroup_bpf_enabled static_branch_unlikely(&cgroup_bpf_enabled_key) +struct bpf_cgroup_storage_map; + +struct bpf_storage_buffer { + struct rcu_head rcu; + char data[0]; +}; + +struct bpf_cgroup_storage { + struct bpf_storage_buffer *buf; + struct bpf_cgroup_storage_map *map; + struct bpf_cgroup_storage_key key; + struct list_head list; + struct rb_node node; + struct rcu_head rcu; +}; + struct bpf_prog_list { struct list_head node; struct bpf_prog *prog; @@ -77,6 +97,15 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, short access, enum bpf_attach_type type); +struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog); +void bpf_cgroup_storage_free(struct bpf_cgroup_storage *storage); +void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage, + struct cgroup *cgroup, + enum bpf_attach_type type); +void bpf_cgroup_storage_unlink(struct bpf_cgroup_storage *storage); +int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *map); +void bpf_cgroup_storage_release(struct bpf_prog *prog, struct bpf_map *map); + /* Wrappers for __cgroup_bpf_run_filter_skb() guarded by cgroup_bpf_enabled. */ #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb) \ ({ \ @@ -221,6 +250,15 @@ static inline int cgroup_bpf_prog_query(const union bpf_attr *attr, return -EINVAL; } +static inline int bpf_cgroup_storage_assign(struct bpf_prog *prog, + struct bpf_map *map) { return 0; } +static inline void bpf_cgroup_storage_release(struct bpf_prog *prog, + struct bpf_map *map) {} +static inline struct bpf_cgroup_storage *bpf_cgroup_storage_alloc( + struct bpf_prog *prog) { return 0; } +static inline void bpf_cgroup_storage_free( + struct bpf_cgroup_storage *storage) {} + #define cgroup_bpf_enabled (0) #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0) #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; }) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 5a4a256473c3..9d1e4727495e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -282,6 +282,7 @@ struct bpf_prog_aux { struct bpf_prog *prog; struct user_struct *user; u64 load_time; /* ns since boottime */ + struct bpf_map *cgroup_storage; char name[BPF_OBJ_NAME_LEN]; #ifdef CONFIG_SECURITY void *security; diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index c5700c2d5549..add08be53b6f 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -37,6 +37,9 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_PERF_EVENT_ARRAY, perf_event_array_map_ops) #ifdef CONFIG_CGROUPS BPF_MAP_TYPE(BPF_MAP_TYPE_CGROUP_ARRAY, cgroup_array_map_ops) #endif +#ifdef CONFIG_CGROUP_BPF +BPF_MAP_TYPE(BPF_MAP_TYPE_CGROUP_STORAGE, cgroup_storage_map_ops) +#endif BPF_MAP_TYPE(BPF_MAP_TYPE_HASH, htab_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_HASH, htab_percpu_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_LRU_HASH, htab_lru_map_ops) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 0ebaaf7f3568..b10118ee5afe 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -75,6 +75,11 @@ struct bpf_lpm_trie_key { __u8 data[0]; /* Arbitrary size */ }; +struct bpf_cgroup_storage_key { + __u64 cgroup_inode_id; /* cgroup inode id */ + __u32 attach_type; /* program attach type */ +}; + /* BPF syscall commands, see bpf(2) man-page for details. */ enum bpf_cmd { BPF_MAP_CREATE, @@ -120,6 +125,7 @@ enum bpf_map_type { BPF_MAP_TYPE_CPUMAP, BPF_MAP_TYPE_XSKMAP, BPF_MAP_TYPE_SOCKHASH, + BPF_MAP_TYPE_CGROUP_STORAGE, }; enum bpf_prog_type { diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index f27f5496d6fe..e8906cbad81f 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -3,6 +3,7 @@ obj-y := core.o obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o +obj-$(CONFIG_BPF_SYSCALL) += local_storage.o obj-$(CONFIG_BPF_SYSCALL) += disasm.o obj-$(CONFIG_BPF_SYSCALL) += btf.o ifeq ($(CONFIG_NET),y) diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c new file mode 100644 index 000000000000..f23d3fdeba23 --- /dev/null +++ b/kernel/bpf/local_storage.c @@ -0,0 +1,376 @@ +//SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include +#include + +#ifdef CONFIG_CGROUP_BPF + +#define LOCAL_STORAGE_CREATE_FLAG_MASK \ + (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) + +struct bpf_cgroup_storage_map { + struct bpf_map map; + + spinlock_t lock; + struct bpf_prog *prog; + struct rb_root root; + struct list_head list; +}; + +static struct bpf_cgroup_storage_map *map_to_storage(struct bpf_map *map) +{ + return container_of(map, struct bpf_cgroup_storage_map, map); +} + +static int bpf_cgroup_storage_key_cmp( + const struct bpf_cgroup_storage_key *key1, + const struct bpf_cgroup_storage_key *key2) +{ + if (key1->cgroup_inode_id < key2->cgroup_inode_id) + return -1; + else if (key1->cgroup_inode_id > key2->cgroup_inode_id) + return 1; + else if (key1->attach_type < key2->attach_type) + return -1; + else if (key1->attach_type > key2->attach_type) + return 1; + return 0; +} + +static struct bpf_cgroup_storage *cgroup_storage_lookup( + struct bpf_cgroup_storage_map *map, struct bpf_cgroup_storage_key *key, + bool locked) +{ + struct rb_root *root = &map->root; + struct rb_node *node; + + if (!locked) + spin_lock_bh(&map->lock); + + node = root->rb_node; + while (node) { + struct bpf_cgroup_storage *storage; + + storage = container_of(node, struct bpf_cgroup_storage, node); + + switch (bpf_cgroup_storage_key_cmp(key, &storage->key)) { + case -1: + node = node->rb_left; + break; + case 1: + node = node->rb_right; + break; + default: + if (!locked) + spin_unlock_bh(&map->lock); + return storage; + } + } + + if (!locked) + spin_unlock_bh(&map->lock); + + return NULL; +} + +static int cgroup_storage_insert(struct bpf_cgroup_storage_map *map, + struct bpf_cgroup_storage *storage) +{ + struct rb_root *root = &map->root; + struct rb_node **new = &(root->rb_node), *parent = NULL; + + while (*new) { + struct bpf_cgroup_storage *this; + + this = container_of(*new, struct bpf_cgroup_storage, node); + + parent = *new; + switch (bpf_cgroup_storage_key_cmp(&storage->key, &this->key)) { + case -1: + new = &((*new)->rb_left); + break; + case 1: + new = &((*new)->rb_right); + break; + default: + return -EEXIST; + } + } + + rb_link_node(&storage->node, parent, new); + rb_insert_color(&storage->node, root); + + return 0; +} + +static void *cgroup_storage_lookup_elem(struct bpf_map *_map, void *_key) +{ + struct bpf_cgroup_storage_map *map = map_to_storage(_map); + struct bpf_cgroup_storage_key *key = _key; + struct bpf_cgroup_storage *storage; + + storage = cgroup_storage_lookup(map, key, false); + if (!storage) + return NULL; + + return &READ_ONCE(storage->buf)->data[0]; +} + +static int cgroup_storage_update_elem(struct bpf_map *map, void *_key, + void *value, u64 flags) +{ + struct bpf_cgroup_storage_key *key = _key; + struct bpf_cgroup_storage *storage; + struct bpf_storage_buffer *new; + + if (flags & BPF_NOEXIST) + return -EINVAL; + + storage = cgroup_storage_lookup((struct bpf_cgroup_storage_map *)map, + key, false); + if (!storage) + return -ENOENT; + + new = kmalloc_node(sizeof(struct bpf_storage_buffer) + + map->value_size, __GFP_ZERO | GFP_USER, + map->numa_node); + if (!new) + return -ENOMEM; + + memcpy(&new->data[0], value, map->value_size); + + new = xchg(&storage->buf, new); + kfree_rcu(new, rcu); + + return 0; +} + +static int cgroup_storage_get_next_key(struct bpf_map *_map, void *_key, + void *_next_key) +{ + struct bpf_cgroup_storage_map *map = map_to_storage(_map); + struct bpf_cgroup_storage_key *key = _key; + struct bpf_cgroup_storage_key *next = _next_key; + struct bpf_cgroup_storage *storage; + + spin_lock_bh(&map->lock); + + if (list_empty(&map->list)) + goto enoent; + + if (key) { + storage = cgroup_storage_lookup(map, key, true); + if (!storage) + goto enoent; + + storage = list_next_entry(storage, list); + if (!storage) + goto enoent; + } else { + storage = list_first_entry(&map->list, + struct bpf_cgroup_storage, list); + } + + spin_unlock_bh(&map->lock); + next->attach_type = storage->key.attach_type; + next->cgroup_inode_id = storage->key.cgroup_inode_id; + return 0; + +enoent: + spin_unlock_bh(&map->lock); + return -ENOENT; +} + +static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr) +{ + int numa_node = bpf_map_attr_numa_node(attr); + struct bpf_cgroup_storage_map *map; + + if (attr->key_size != sizeof(struct bpf_cgroup_storage_key)) + return ERR_PTR(-EINVAL); + + if (attr->value_size > PAGE_SIZE) + return ERR_PTR(-E2BIG); + + if (attr->map_flags & ~LOCAL_STORAGE_CREATE_FLAG_MASK) + /* reserved bits should not be used */ + return ERR_PTR(-EINVAL); + + if (attr->max_entries) + /* max_entries is not used and enforced to be 0 */ + return ERR_PTR(-EINVAL); + + map = kmalloc_node(sizeof(struct bpf_cgroup_storage_map), + __GFP_ZERO | GFP_USER, numa_node); + if (!map) + return ERR_PTR(-ENOMEM); + + map->map.pages = round_up(sizeof(struct bpf_cgroup_storage_map), + PAGE_SIZE) >> PAGE_SHIFT; + + /* copy mandatory map attributes */ + bpf_map_init_from_attr(&map->map, attr); + + spin_lock_init(&map->lock); + map->root = RB_ROOT; + INIT_LIST_HEAD(&map->list); + + return &map->map; +} + +static void cgroup_storage_map_free(struct bpf_map *_map) +{ + struct bpf_cgroup_storage_map *map = map_to_storage(_map); + + WARN_ON(!RB_EMPTY_ROOT(&map->root)); + WARN_ON(!list_empty(&map->list)); + + kfree(map); +} + +static int cgroup_storage_delete_elem(struct bpf_map *map, void *key) +{ + return -EINVAL; +} + +const struct bpf_map_ops cgroup_storage_map_ops = { + .map_alloc = cgroup_storage_map_alloc, + .map_free = cgroup_storage_map_free, + .map_get_next_key = cgroup_storage_get_next_key, + .map_lookup_elem = cgroup_storage_lookup_elem, + .map_update_elem = cgroup_storage_update_elem, + .map_delete_elem = cgroup_storage_delete_elem, +}; + +int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *_map) +{ + struct bpf_cgroup_storage_map *map = map_to_storage(_map); + int ret = -EBUSY; + + spin_lock_bh(&map->lock); + + if (map->prog && map->prog != prog) + goto unlock; + if (prog->aux->cgroup_storage && prog->aux->cgroup_storage != _map) + goto unlock; + + map->prog = prog; + prog->aux->cgroup_storage = _map; + ret = 0; +unlock: + spin_unlock_bh(&map->lock); + + return ret; +} + +void bpf_cgroup_storage_release(struct bpf_prog *prog, struct bpf_map *_map) +{ + struct bpf_cgroup_storage_map *map = map_to_storage(_map); + + spin_lock_bh(&map->lock); + if (map->prog == prog) { + WARN_ON(prog->aux->cgroup_storage != _map); + map->prog = NULL; + prog->aux->cgroup_storage = NULL; + } + spin_unlock_bh(&map->lock); +} + +struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog) +{ + struct bpf_cgroup_storage *storage; + struct bpf_map *map; + u32 pages; + + map = prog->aux->cgroup_storage; + if (!map) + return NULL; + + pages = round_up(sizeof(struct bpf_cgroup_storage) + + sizeof(struct bpf_storage_buffer) + + map->value_size, PAGE_SIZE) >> PAGE_SHIFT; + if (bpf_map_charge_memlock(map, pages)) + return ERR_PTR(-EPERM); + + storage = kmalloc_node(sizeof(struct bpf_cgroup_storage), + __GFP_ZERO | GFP_USER, map->numa_node); + if (!storage) { + bpf_map_uncharge_memlock(map, pages); + return ERR_PTR(-ENOMEM); + } + + storage->buf = kmalloc_node(sizeof(struct bpf_storage_buffer) + + map->value_size, __GFP_ZERO | GFP_USER, + map->numa_node); + if (!storage->buf) { + bpf_map_uncharge_memlock(map, pages); + kfree(storage); + return ERR_PTR(-ENOMEM); + } + + storage->map = (struct bpf_cgroup_storage_map *)map; + + return storage; +} + +void bpf_cgroup_storage_free(struct bpf_cgroup_storage *storage) +{ + u32 pages; + struct bpf_map *map; + + if (!storage) + return; + + map = &storage->map->map; + pages = round_up(sizeof(struct bpf_cgroup_storage) + + sizeof(struct bpf_storage_buffer) + + map->value_size, PAGE_SIZE) >> PAGE_SHIFT; + bpf_map_uncharge_memlock(map, pages); + + kfree_rcu(storage->buf, rcu); + kfree_rcu(storage, rcu); +} + +void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage, + struct cgroup *cgroup, + enum bpf_attach_type type) +{ + struct bpf_cgroup_storage_map *map; + + if (!storage) + return; + + storage->key.attach_type = type; + storage->key.cgroup_inode_id = cgroup->kn->id.id; + + map = storage->map; + + spin_lock_bh(&map->lock); + WARN_ON(cgroup_storage_insert(map, storage)); + list_add(&storage->list, &map->list); + spin_unlock_bh(&map->lock); +} + +void bpf_cgroup_storage_unlink(struct bpf_cgroup_storage *storage) +{ + struct bpf_cgroup_storage_map *map; + struct rb_root *root; + + if (!storage) + return; + + map = storage->map; + + spin_lock_bh(&map->lock); + root = &map->root; + rb_erase(&storage->node, root); + + list_del(&storage->list); + spin_unlock_bh(&map->lock); +} + +#endif diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 7958252a4d29..5af4e9e2722d 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -957,6 +957,9 @@ static void free_used_maps(struct bpf_prog_aux *aux) { int i; + if (aux->cgroup_storage) + bpf_cgroup_storage_release(aux->prog, aux->cgroup_storage); + for (i = 0; i < aux->used_map_cnt; i++) bpf_map_put(aux->used_maps[i]); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index e948303a0ea8..7e75434a9e54 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5154,6 +5154,14 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) } env->used_maps[env->used_map_cnt++] = map; + if (map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE && + bpf_cgroup_storage_assign(env->prog, map)) { + verbose(env, + "only one cgroup storage is allowed\n"); + fdput(f); + return -EBUSY; + } + fdput(f); next_insn: insn++; @@ -5180,6 +5188,10 @@ static void release_maps(struct bpf_verifier_env *env) { int i; + if (env->prog->aux->cgroup_storage) + bpf_cgroup_storage_release(env->prog, + env->prog->aux->cgroup_storage); + for (i = 0; i < env->used_map_cnt; i++) bpf_map_put(env->used_maps[i]); } -- cgit v1.2.3 From aa0ad5b0391e268bdecf6cda31268388844f8afd Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Thu, 2 Aug 2018 14:27:19 -0700 Subject: bpf: pass a pointer to a cgroup storage using pcpu variable This commit introduces the bpf_cgroup_storage_set() helper, which will be used to pass a pointer to a cgroup storage to the bpf helper. Signed-off-by: Roman Gushchin Cc: Alexei Starovoitov Cc: Daniel Borkmann Acked-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann --- include/linux/bpf-cgroup.h | 15 +++++++++++++++ kernel/bpf/local_storage.c | 2 ++ 2 files changed, 17 insertions(+) (limited to 'include') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 7d00d58869ed..9a144ddbbc8f 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -4,6 +4,7 @@ #include #include +#include #include #include @@ -21,6 +22,8 @@ struct bpf_cgroup_storage; extern struct static_key_false cgroup_bpf_enabled_key; #define cgroup_bpf_enabled static_branch_unlikely(&cgroup_bpf_enabled_key) +DECLARE_PER_CPU(void*, bpf_cgroup_storage); + struct bpf_cgroup_storage_map; struct bpf_storage_buffer { @@ -97,6 +100,17 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, short access, enum bpf_attach_type type); +static inline void bpf_cgroup_storage_set(struct bpf_cgroup_storage *storage) +{ + struct bpf_storage_buffer *buf; + + if (!storage) + return; + + buf = READ_ONCE(storage->buf); + this_cpu_write(bpf_cgroup_storage, &buf->data[0]); +} + struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog); void bpf_cgroup_storage_free(struct bpf_cgroup_storage *storage); void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage, @@ -250,6 +264,7 @@ static inline int cgroup_bpf_prog_query(const union bpf_attr *attr, return -EINVAL; } +static inline void bpf_cgroup_storage_set(struct bpf_cgroup_storage *storage) {} static inline int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *map) { return 0; } static inline void bpf_cgroup_storage_release(struct bpf_prog *prog, diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index f23d3fdeba23..fc4e37f68f2a 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -7,6 +7,8 @@ #include #include +DEFINE_PER_CPU(void*, bpf_cgroup_storage); + #ifdef CONFIG_CGROUP_BPF #define LOCAL_STORAGE_CREATE_FLAG_MASK \ -- cgit v1.2.3 From d7bf2c10af053191e931b58704cd862fccb7f9de Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Thu, 2 Aug 2018 14:27:20 -0700 Subject: bpf: allocate cgroup storage entries on attaching bpf programs If a bpf program is using cgroup local storage, allocate a bpf_cgroup_storage structure automatically on attaching the program to a cgroup and save the pointer into the corresponding bpf_prog_list entry. Analogically, release the cgroup local storage on detaching of the bpf program. Signed-off-by: Roman Gushchin Cc: Alexei Starovoitov Cc: Daniel Borkmann Acked-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann --- include/linux/bpf-cgroup.h | 1 + kernel/bpf/cgroup.c | 35 +++++++++++++++++++++++++++++++---- 2 files changed, 32 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 9a144ddbbc8f..f91b0f8ff3a9 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -43,6 +43,7 @@ struct bpf_cgroup_storage { struct bpf_prog_list { struct list_head node; struct bpf_prog *prog; + struct bpf_cgroup_storage *storage; }; struct bpf_prog_array; diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index badabb0b435c..935274c86bfe 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -34,6 +34,8 @@ void cgroup_bpf_put(struct cgroup *cgrp) list_for_each_entry_safe(pl, tmp, progs, node) { list_del(&pl->node); bpf_prog_put(pl->prog); + bpf_cgroup_storage_unlink(pl->storage); + bpf_cgroup_storage_free(pl->storage); kfree(pl); static_branch_dec(&cgroup_bpf_enabled_key); } @@ -188,6 +190,7 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, { struct list_head *progs = &cgrp->bpf.progs[type]; struct bpf_prog *old_prog = NULL; + struct bpf_cgroup_storage *storage, *old_storage = NULL; struct cgroup_subsys_state *css; struct bpf_prog_list *pl; bool pl_was_allocated; @@ -210,31 +213,47 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, if (prog_list_length(progs) >= BPF_CGROUP_MAX_PROGS) return -E2BIG; + storage = bpf_cgroup_storage_alloc(prog); + if (IS_ERR(storage)) + return -ENOMEM; + if (flags & BPF_F_ALLOW_MULTI) { - list_for_each_entry(pl, progs, node) - if (pl->prog == prog) + list_for_each_entry(pl, progs, node) { + if (pl->prog == prog) { /* disallow attaching the same prog twice */ + bpf_cgroup_storage_free(storage); return -EINVAL; + } + } pl = kmalloc(sizeof(*pl), GFP_KERNEL); - if (!pl) + if (!pl) { + bpf_cgroup_storage_free(storage); return -ENOMEM; + } + pl_was_allocated = true; pl->prog = prog; + pl->storage = storage; list_add_tail(&pl->node, progs); } else { if (list_empty(progs)) { pl = kmalloc(sizeof(*pl), GFP_KERNEL); - if (!pl) + if (!pl) { + bpf_cgroup_storage_free(storage); return -ENOMEM; + } pl_was_allocated = true; list_add_tail(&pl->node, progs); } else { pl = list_first_entry(progs, typeof(*pl), node); old_prog = pl->prog; + old_storage = pl->storage; + bpf_cgroup_storage_unlink(old_storage); pl_was_allocated = false; } pl->prog = prog; + pl->storage = storage; } cgrp->bpf.flags[type] = flags; @@ -257,10 +276,13 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, } static_branch_inc(&cgroup_bpf_enabled_key); + if (old_storage) + bpf_cgroup_storage_free(old_storage); if (old_prog) { bpf_prog_put(old_prog); static_branch_dec(&cgroup_bpf_enabled_key); } + bpf_cgroup_storage_link(storage, cgrp, type); return 0; cleanup: @@ -276,6 +298,9 @@ cleanup: /* and cleanup the prog list */ pl->prog = old_prog; + bpf_cgroup_storage_free(pl->storage); + pl->storage = old_storage; + bpf_cgroup_storage_link(old_storage, cgrp, type); if (pl_was_allocated) { list_del(&pl->node); kfree(pl); @@ -356,6 +381,8 @@ int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, /* now can actually delete it from this cgroup list */ list_del(&pl->node); + bpf_cgroup_storage_unlink(pl->storage); + bpf_cgroup_storage_free(pl->storage); kfree(pl); if (list_empty(progs)) /* last program was detached, reset flags to zero */ -- cgit v1.2.3 From 394e40a29788820c9c0526b1c3497c9e0ec2a126 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Thu, 2 Aug 2018 14:27:21 -0700 Subject: bpf: extend bpf_prog_array to store pointers to the cgroup storage This patch converts bpf_prog_array from an array of prog pointers to the array of struct bpf_prog_array_item elements. This allows to save a cgroup storage pointer for each bpf program efficiently attached to a cgroup. Signed-off-by: Roman Gushchin Cc: Alexei Starovoitov Cc: Daniel Borkmann Acked-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann --- drivers/media/rc/bpf-lirc.c | 10 +++--- include/linux/bpf.h | 19 ++++++++---- kernel/bpf/cgroup.c | 21 +++++++------ kernel/bpf/core.c | 76 +++++++++++++++++++++++---------------------- 4 files changed, 70 insertions(+), 56 deletions(-) (limited to 'include') diff --git a/drivers/media/rc/bpf-lirc.c b/drivers/media/rc/bpf-lirc.c index fcfab6635f9c..8c26df9b96c1 100644 --- a/drivers/media/rc/bpf-lirc.c +++ b/drivers/media/rc/bpf-lirc.c @@ -195,14 +195,16 @@ void lirc_bpf_run(struct rc_dev *rcdev, u32 sample) */ void lirc_bpf_free(struct rc_dev *rcdev) { - struct bpf_prog **progs; + struct bpf_prog_array_item *item; if (!rcdev->raw->progs) return; - progs = rcu_dereference(rcdev->raw->progs)->progs; - while (*progs) - bpf_prog_put(*progs++); + item = rcu_dereference(rcdev->raw->progs)->items; + while (item->prog) { + bpf_prog_put(item->prog); + item++; + } bpf_prog_array_free(rcdev->raw->progs); } diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 9d1e4727495e..16be67888c30 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -349,9 +349,14 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, * The 'struct bpf_prog_array *' should only be replaced with xchg() * since other cpus are walking the array of pointers in parallel. */ +struct bpf_prog_array_item { + struct bpf_prog *prog; + struct bpf_cgroup_storage *cgroup_storage; +}; + struct bpf_prog_array { struct rcu_head rcu; - struct bpf_prog *progs[0]; + struct bpf_prog_array_item items[0]; }; struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags); @@ -372,7 +377,8 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array, #define __BPF_PROG_RUN_ARRAY(array, ctx, func, check_non_null) \ ({ \ - struct bpf_prog **_prog, *__prog; \ + struct bpf_prog_array_item *_item; \ + struct bpf_prog *_prog; \ struct bpf_prog_array *_array; \ u32 _ret = 1; \ preempt_disable(); \ @@ -380,10 +386,11 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array, _array = rcu_dereference(array); \ if (unlikely(check_non_null && !_array))\ goto _out; \ - _prog = _array->progs; \ - while ((__prog = READ_ONCE(*_prog))) { \ - _ret &= func(__prog, ctx); \ - _prog++; \ + _item = &_array->items[0]; \ + while ((_prog = READ_ONCE(_item->prog))) { \ + bpf_cgroup_storage_set(_item->cgroup_storage); \ + _ret &= func(_prog, ctx); \ + _item++; \ } \ _out: \ rcu_read_unlock(); \ diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 935274c86bfe..ddfa6cc13e57 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -117,15 +117,18 @@ static int compute_effective_progs(struct cgroup *cgrp, cnt = 0; p = cgrp; do { - if (cnt == 0 || (p->bpf.flags[type] & BPF_F_ALLOW_MULTI)) - list_for_each_entry(pl, - &p->bpf.progs[type], node) { - if (!pl->prog) - continue; - progs->progs[cnt++] = pl->prog; - } - p = cgroup_parent(p); - } while (p); + if (cnt > 0 && !(p->bpf.flags[type] & BPF_F_ALLOW_MULTI)) + continue; + + list_for_each_entry(pl, &p->bpf.progs[type], node) { + if (!pl->prog) + continue; + + progs->items[cnt].prog = pl->prog; + progs->items[cnt].cgroup_storage = pl->storage; + cnt++; + } + } while ((p = cgroup_parent(p))); rcu_assign_pointer(*array, progs); return 0; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 253aa8e79c7b..9abcf25ebf9f 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1542,7 +1542,8 @@ struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags) { if (prog_cnt) return kzalloc(sizeof(struct bpf_prog_array) + - sizeof(struct bpf_prog *) * (prog_cnt + 1), + sizeof(struct bpf_prog_array_item) * + (prog_cnt + 1), flags); return &empty_prog_array.hdr; @@ -1556,43 +1557,45 @@ void bpf_prog_array_free(struct bpf_prog_array __rcu *progs) kfree_rcu(progs, rcu); } -int bpf_prog_array_length(struct bpf_prog_array __rcu *progs) +int bpf_prog_array_length(struct bpf_prog_array __rcu *array) { - struct bpf_prog **prog; + struct bpf_prog_array_item *item; u32 cnt = 0; rcu_read_lock(); - prog = rcu_dereference(progs)->progs; - for (; *prog; prog++) - if (*prog != &dummy_bpf_prog.prog) + item = rcu_dereference(array)->items; + for (; item->prog; item++) + if (item->prog != &dummy_bpf_prog.prog) cnt++; rcu_read_unlock(); return cnt; } -static bool bpf_prog_array_copy_core(struct bpf_prog **prog, + +static bool bpf_prog_array_copy_core(struct bpf_prog_array __rcu *array, u32 *prog_ids, u32 request_cnt) { + struct bpf_prog_array_item *item; int i = 0; - for (; *prog; prog++) { - if (*prog == &dummy_bpf_prog.prog) + item = rcu_dereference(array)->items; + for (; item->prog; item++) { + if (item->prog == &dummy_bpf_prog.prog) continue; - prog_ids[i] = (*prog)->aux->id; + prog_ids[i] = item->prog->aux->id; if (++i == request_cnt) { - prog++; + item++; break; } } - return !!(*prog); + return !!(item->prog); } -int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs, +int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *array, __u32 __user *prog_ids, u32 cnt) { - struct bpf_prog **prog; unsigned long err = 0; bool nospc; u32 *ids; @@ -1611,8 +1614,7 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs, if (!ids) return -ENOMEM; rcu_read_lock(); - prog = rcu_dereference(progs)->progs; - nospc = bpf_prog_array_copy_core(prog, ids, cnt); + nospc = bpf_prog_array_copy_core(array, ids, cnt); rcu_read_unlock(); err = copy_to_user(prog_ids, ids, cnt * sizeof(u32)); kfree(ids); @@ -1623,14 +1625,14 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs, return 0; } -void bpf_prog_array_delete_safe(struct bpf_prog_array __rcu *progs, +void bpf_prog_array_delete_safe(struct bpf_prog_array __rcu *array, struct bpf_prog *old_prog) { - struct bpf_prog **prog = progs->progs; + struct bpf_prog_array_item *item = array->items; - for (; *prog; prog++) - if (*prog == old_prog) { - WRITE_ONCE(*prog, &dummy_bpf_prog.prog); + for (; item->prog; item++) + if (item->prog == old_prog) { + WRITE_ONCE(item->prog, &dummy_bpf_prog.prog); break; } } @@ -1641,7 +1643,7 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array, struct bpf_prog_array **new_array) { int new_prog_cnt, carry_prog_cnt = 0; - struct bpf_prog **existing_prog; + struct bpf_prog_array_item *existing; struct bpf_prog_array *array; bool found_exclude = false; int new_prog_idx = 0; @@ -1650,15 +1652,15 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array, * the new array. */ if (old_array) { - existing_prog = old_array->progs; - for (; *existing_prog; existing_prog++) { - if (*existing_prog == exclude_prog) { + existing = old_array->items; + for (; existing->prog; existing++) { + if (existing->prog == exclude_prog) { found_exclude = true; continue; } - if (*existing_prog != &dummy_bpf_prog.prog) + if (existing->prog != &dummy_bpf_prog.prog) carry_prog_cnt++; - if (*existing_prog == include_prog) + if (existing->prog == include_prog) return -EEXIST; } } @@ -1684,15 +1686,17 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array, /* Fill in the new prog array */ if (carry_prog_cnt) { - existing_prog = old_array->progs; - for (; *existing_prog; existing_prog++) - if (*existing_prog != exclude_prog && - *existing_prog != &dummy_bpf_prog.prog) - array->progs[new_prog_idx++] = *existing_prog; + existing = old_array->items; + for (; existing->prog; existing++) + if (existing->prog != exclude_prog && + existing->prog != &dummy_bpf_prog.prog) { + array->items[new_prog_idx++].prog = + existing->prog; + } } if (include_prog) - array->progs[new_prog_idx++] = include_prog; - array->progs[new_prog_idx] = NULL; + array->items[new_prog_idx++].prog = include_prog; + array->items[new_prog_idx].prog = NULL; *new_array = array; return 0; } @@ -1701,7 +1705,6 @@ int bpf_prog_array_copy_info(struct bpf_prog_array __rcu *array, u32 *prog_ids, u32 request_cnt, u32 *prog_cnt) { - struct bpf_prog **prog; u32 cnt = 0; if (array) @@ -1714,8 +1717,7 @@ int bpf_prog_array_copy_info(struct bpf_prog_array __rcu *array, return 0; /* this function is called under trace/bpf_trace.c: bpf_event_mutex */ - prog = rcu_dereference_check(array, 1)->progs; - return bpf_prog_array_copy_core(prog, prog_ids, request_cnt) ? -ENOSPC + return bpf_prog_array_copy_core(array, prog_ids, request_cnt) ? -ENOSPC : 0; } -- cgit v1.2.3 From 3e6a4b3e0289dc9540a2c1d8a20657f4707fbabb Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Thu, 2 Aug 2018 14:27:22 -0700 Subject: bpf/verifier: introduce BPF_PTR_TO_MAP_VALUE BPF_MAP_TYPE_CGROUP_STORAGE maps are special in a way that the access from the bpf program side is lookup-free. That means the result is guaranteed to be a valid pointer to the cgroup storage; no NULL-check is required. This patch introduces BPF_PTR_TO_MAP_VALUE return type, which is required to cause the verifier accept programs, which are not checking the map value pointer for being NULL. Signed-off-by: Roman Gushchin Cc: Alexei Starovoitov Cc: Daniel Borkmann Acked-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 1 + kernel/bpf/verifier.c | 8 ++++++-- 2 files changed, 7 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 16be67888c30..ca4ac2a39def 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -155,6 +155,7 @@ enum bpf_arg_type { enum bpf_return_type { RET_INTEGER, /* function returns integer */ RET_VOID, /* function doesn't return anything */ + RET_PTR_TO_MAP_VALUE, /* returns a pointer to map elem value */ RET_PTR_TO_MAP_VALUE_OR_NULL, /* returns a pointer to map elem value or NULL */ }; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 7e75434a9e54..1ede16c8bb40 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2545,8 +2545,12 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn mark_reg_unknown(env, regs, BPF_REG_0); } else if (fn->ret_type == RET_VOID) { regs[BPF_REG_0].type = NOT_INIT; - } else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL) { - regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL; + } else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL || + fn->ret_type == RET_PTR_TO_MAP_VALUE) { + if (fn->ret_type == RET_PTR_TO_MAP_VALUE) + regs[BPF_REG_0].type = PTR_TO_MAP_VALUE; + else + regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL; /* There is no offset yet applied, variable or fixed */ mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].off = 0; -- cgit v1.2.3 From cd3394317653837e2eb5c5d0904a8996102af9fc Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Thu, 2 Aug 2018 14:27:24 -0700 Subject: bpf: introduce the bpf_get_local_storage() helper function The bpf_get_local_storage() helper function is used to get a pointer to the bpf local storage from a bpf program. It takes a pointer to a storage map and flags as arguments. Right now it accepts only cgroup storage maps, and flags argument has to be 0. Further it can be extended to support other types of local storage: e.g. thread local storage etc. Signed-off-by: Roman Gushchin Cc: Alexei Starovoitov Cc: Daniel Borkmann Acked-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 2 ++ include/uapi/linux/bpf.h | 21 ++++++++++++++++++++- kernel/bpf/cgroup.c | 2 ++ kernel/bpf/core.c | 1 + kernel/bpf/helpers.c | 20 ++++++++++++++++++++ kernel/bpf/verifier.c | 18 ++++++++++++++++++ net/core/filter.c | 23 ++++++++++++++++++++++- 7 files changed, 85 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index ca4ac2a39def..cd8790d2c6ed 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -788,6 +788,8 @@ extern const struct bpf_func_proto bpf_sock_map_update_proto; extern const struct bpf_func_proto bpf_sock_hash_update_proto; extern const struct bpf_func_proto bpf_get_current_cgroup_id_proto; +extern const struct bpf_func_proto bpf_get_local_storage_proto; + /* Shared helpers among cBPF and eBPF. */ void bpf_user_rnd_init_once(void); u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index b10118ee5afe..dd5758dc35d3 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2095,6 +2095,24 @@ union bpf_attr { * Return * A 64-bit integer containing the current cgroup id based * on the cgroup within which the current task is running. + * + * void* get_local_storage(void *map, u64 flags) + * Description + * Get the pointer to the local storage area. + * The type and the size of the local storage is defined + * by the *map* argument. + * The *flags* meaning is specific for each map type, + * and has to be 0 for cgroup local storage. + * + * Depending on the bpf program type, a local storage area + * can be shared between multiple instances of the bpf program, + * running simultaneously. + * + * A user should care about the synchronization by himself. + * For example, by using the BPF_STX_XADD instruction to alter + * the shared data. + * Return + * Pointer to the local storage area. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2177,7 +2195,8 @@ union bpf_attr { FN(rc_repeat), \ FN(rc_keydown), \ FN(skb_cgroup_id), \ - FN(get_current_cgroup_id), + FN(get_current_cgroup_id), \ + FN(get_local_storage), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index ddfa6cc13e57..0a4fe5a7dc91 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -684,6 +684,8 @@ cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_map_delete_elem_proto; case BPF_FUNC_get_current_uid_gid: return &bpf_get_current_uid_gid_proto; + case BPF_FUNC_get_local_storage: + return &bpf_get_local_storage_proto; case BPF_FUNC_trace_printk: if (capable(CAP_SYS_ADMIN)) return bpf_get_trace_printk_proto(); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 9abcf25ebf9f..4d09e610777f 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1795,6 +1795,7 @@ const struct bpf_func_proto bpf_get_current_comm_proto __weak; const struct bpf_func_proto bpf_sock_map_update_proto __weak; const struct bpf_func_proto bpf_sock_hash_update_proto __weak; const struct bpf_func_proto bpf_get_current_cgroup_id_proto __weak; +const struct bpf_func_proto bpf_get_local_storage_proto __weak; const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void) { diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 73065e2d23c2..1991466b8327 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -193,4 +193,24 @@ const struct bpf_func_proto bpf_get_current_cgroup_id_proto = { .gpl_only = false, .ret_type = RET_INTEGER, }; + +DECLARE_PER_CPU(void*, bpf_cgroup_storage); + +BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags) +{ + /* map and flags arguments are not used now, + * but provide an ability to extend the API + * for other types of local storages. + * verifier checks that their values are correct. + */ + return (unsigned long) this_cpu_read(bpf_cgroup_storage); +} + +const struct bpf_func_proto bpf_get_local_storage_proto = { + .func = bpf_get_local_storage, + .gpl_only = false, + .ret_type = RET_PTR_TO_MAP_VALUE, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_ANYTHING, +}; #endif diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 1ede16c8bb40..587468a9c37d 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2127,6 +2127,10 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, func_id != BPF_FUNC_current_task_under_cgroup) goto error; break; + case BPF_MAP_TYPE_CGROUP_STORAGE: + if (func_id != BPF_FUNC_get_local_storage) + goto error; + break; /* devmap returns a pointer to a live net_device ifindex that we cannot * allow to be modified from bpf side. So do not allow lookup elements * for now. @@ -2209,6 +2213,10 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, if (map->map_type != BPF_MAP_TYPE_SOCKHASH) goto error; break; + case BPF_FUNC_get_local_storage: + if (map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE) + goto error; + break; default: break; } @@ -2533,6 +2541,16 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn } regs = cur_regs(env); + + /* check that flags argument in get_local_storage(map, flags) is 0, + * this is required because get_local_storage() can't return an error. + */ + if (func_id == BPF_FUNC_get_local_storage && + !register_is_null(®s[BPF_REG_2])) { + verbose(env, "get_local_storage() doesn't support non-zero flags\n"); + return -EINVAL; + } + /* reset caller saved regs */ for (i = 0; i < CALLER_SAVED_REGS; i++) { mark_reg_not_init(env, regs, caller_saved[i]); diff --git a/net/core/filter.c b/net/core/filter.c index 9bb9a4488e25..9f73aae2f089 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4820,6 +4820,8 @@ sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) */ case BPF_FUNC_get_current_uid_gid: return &bpf_get_current_uid_gid_proto; + case BPF_FUNC_get_local_storage: + return &bpf_get_local_storage_proto; default: return bpf_base_func_proto(func_id); } @@ -4844,6 +4846,8 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) } case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_sock_addr_proto; + case BPF_FUNC_get_local_storage: + return &bpf_get_local_storage_proto; default: return bpf_base_func_proto(func_id); } @@ -4866,6 +4870,17 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) } } +static const struct bpf_func_proto * +cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +{ + switch (func_id) { + case BPF_FUNC_get_local_storage: + return &bpf_get_local_storage_proto; + default: + return sk_filter_func_proto(func_id, prog); + } +} + static const struct bpf_func_proto * tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -4988,6 +5003,8 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_sock_hash_update_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_sock_ops_proto; + case BPF_FUNC_get_local_storage: + return &bpf_get_local_storage_proto; default: return bpf_base_func_proto(func_id); } @@ -5007,6 +5024,8 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_msg_cork_bytes_proto; case BPF_FUNC_msg_pull_data: return &bpf_msg_pull_data_proto; + case BPF_FUNC_get_local_storage: + return &bpf_get_local_storage_proto; default: return bpf_base_func_proto(func_id); } @@ -5034,6 +5053,8 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_sk_redirect_map_proto; case BPF_FUNC_sk_redirect_hash: return &bpf_sk_redirect_hash_proto; + case BPF_FUNC_get_local_storage: + return &bpf_get_local_storage_proto; default: return bpf_base_func_proto(func_id); } @@ -6838,7 +6859,7 @@ const struct bpf_prog_ops xdp_prog_ops = { }; const struct bpf_verifier_ops cg_skb_verifier_ops = { - .get_func_proto = sk_filter_func_proto, + .get_func_proto = cg_skb_func_proto, .is_valid_access = sk_filter_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, }; -- cgit v1.2.3 From 401c0d7712eb3189023efc9c0708a2ac984ed62e Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 3 Aug 2018 11:50:39 +0200 Subject: spi: spi-mem: Constify spi_mem->name There is no reason to make spi_mem->name modifiable. Moreover, spi_mem_ops->get_name() returns a const char *, which generates a gcc warning when assigning the value returned by spi_mem_ops->get_name() to spi_mem->name. Fixes: 5d27a9c8ea9e ("spi: spi-mem: Extend the SPI mem interface to set a custom memory name") Reported-by: Stephen Rothwell Signed-off-by: Boris Brezillon Signed-off-by: Mark Brown --- include/linux/spi/spi-mem.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h index 0d64ccc4e584..62722fb7472d 100644 --- a/include/linux/spi/spi-mem.h +++ b/include/linux/spi/spi-mem.h @@ -134,7 +134,7 @@ struct spi_mem_op { struct spi_mem { struct spi_device *spi; void *drvpriv; - char *name; + const char *name; }; /** -- cgit v1.2.3 From 43490e8046b5d273eb82710b04290c5997138adc Mon Sep 17 00:00:00 2001 From: Stephan Müller Date: Fri, 20 Jul 2018 19:42:01 +0200 Subject: crypto: drbg - in-place cipher operation for CTR The cipher implementations of the kernel crypto API favor in-place cipher operations. Thus, switch the CTR cipher operation in the DRBG to perform in-place operations. This is implemented by using the output buffer as input buffer and zeroizing it before the cipher operation to implement a CTR encryption of a NULL buffer. The speed improvement is quite visibile with the following comparison using the LRNG implementation. Without the patch set: 16 bytes| 12.267661 MB/s| 61338304 bytes | 5000000213 ns 32 bytes| 23.603770 MB/s| 118018848 bytes | 5000000073 ns 64 bytes| 46.732262 MB/s| 233661312 bytes | 5000000241 ns 128 bytes| 90.038042 MB/s| 450190208 bytes | 5000000244 ns 256 bytes| 160.399616 MB/s| 801998080 bytes | 5000000393 ns 512 bytes| 259.878400 MB/s| 1299392000 bytes | 5000001675 ns 1024 bytes| 386.050662 MB/s| 1930253312 bytes | 5000001661 ns 2048 bytes| 493.641728 MB/s| 2468208640 bytes | 5000001598 ns 4096 bytes| 581.835981 MB/s| 2909179904 bytes | 5000003426 ns With the patch set: 16 bytes | 17.051142 MB/s | 85255712 bytes | 5000000854 ns 32 bytes | 32.695898 MB/s | 163479488 bytes | 5000000544 ns 64 bytes | 64.490739 MB/s | 322453696 bytes | 5000000954 ns 128 bytes | 123.285043 MB/s | 616425216 bytes | 5000000201 ns 256 bytes | 233.434573 MB/s | 1167172864 bytes | 5000000573 ns 512 bytes | 384.405197 MB/s | 1922025984 bytes | 5000000671 ns 1024 bytes | 566.313370 MB/s | 2831566848 bytes | 5000001080 ns 2048 bytes | 744.518042 MB/s | 3722590208 bytes | 5000000926 ns 4096 bytes | 867.501670 MB/s | 4337508352 bytes | 5000002181 ns Signed-off-by: Stephan Mueller Signed-off-by: Herbert Xu --- crypto/drbg.c | 34 ++++++++++++++-------------------- include/crypto/drbg.h | 2 -- 2 files changed, 14 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/crypto/drbg.c b/crypto/drbg.c index ee302fd229ad..bc52d9562611 100644 --- a/crypto/drbg.c +++ b/crypto/drbg.c @@ -261,8 +261,7 @@ static int drbg_fini_sym_kernel(struct drbg_state *drbg); static int drbg_kcapi_sym_ctr(struct drbg_state *drbg, u8 *inbuf, u32 inbuflen, u8 *outbuf, u32 outlen); -#define DRBG_CTR_NULL_LEN 128 -#define DRBG_OUTSCRATCHLEN DRBG_CTR_NULL_LEN +#define DRBG_OUTSCRATCHLEN 256 /* BCC function for CTR DRBG as defined in 10.4.3 */ static int drbg_ctr_bcc(struct drbg_state *drbg, @@ -555,8 +554,7 @@ static int drbg_ctr_generate(struct drbg_state *drbg, } /* 10.2.1.5.2 step 4.1 */ - ret = drbg_kcapi_sym_ctr(drbg, drbg->ctr_null_value, DRBG_CTR_NULL_LEN, - buf, len); + ret = drbg_kcapi_sym_ctr(drbg, NULL, 0, buf, len); if (ret) return ret; @@ -1644,9 +1642,6 @@ static int drbg_fini_sym_kernel(struct drbg_state *drbg) skcipher_request_free(drbg->ctr_req); drbg->ctr_req = NULL; - kfree(drbg->ctr_null_value_buf); - drbg->ctr_null_value = NULL; - kfree(drbg->outscratchpadbuf); drbg->outscratchpadbuf = NULL; @@ -1697,15 +1692,6 @@ static int drbg_init_sym_kernel(struct drbg_state *drbg) crypto_req_done, &drbg->ctr_wait); alignmask = crypto_skcipher_alignmask(sk_tfm); - drbg->ctr_null_value_buf = kzalloc(DRBG_CTR_NULL_LEN + alignmask, - GFP_KERNEL); - if (!drbg->ctr_null_value_buf) { - drbg_fini_sym_kernel(drbg); - return -ENOMEM; - } - drbg->ctr_null_value = (u8 *)PTR_ALIGN(drbg->ctr_null_value_buf, - alignmask + 1); - drbg->outscratchpadbuf = kmalloc(DRBG_OUTSCRATCHLEN + alignmask, GFP_KERNEL); if (!drbg->outscratchpadbuf) { @@ -1716,7 +1702,7 @@ static int drbg_init_sym_kernel(struct drbg_state *drbg) alignmask + 1); sg_init_table(&drbg->sg_in, 1); - sg_init_table(&drbg->sg_out, 1); + sg_init_one(&drbg->sg_out, drbg->outscratchpad, DRBG_OUTSCRATCHLEN); return alignmask; } @@ -1747,10 +1733,18 @@ static int drbg_kcapi_sym_ctr(struct drbg_state *drbg, u8 *outbuf, u32 outlen) { struct scatterlist *sg_in = &drbg->sg_in, *sg_out = &drbg->sg_out; + u32 scratchpad_use = min_t(u32, outlen, DRBG_OUTSCRATCHLEN); int ret; - sg_set_buf(sg_in, inbuf, inlen); - sg_set_buf(sg_out, drbg->outscratchpad, DRBG_OUTSCRATCHLEN); + if (inbuf) { + /* Use caller-provided input buffer */ + sg_set_buf(sg_in, inbuf, inlen); + } else { + /* Use scratchpad for in-place operation */ + inlen = scratchpad_use; + memset(drbg->outscratchpad, 0, scratchpad_use); + sg_set_buf(sg_in, drbg->outscratchpad, scratchpad_use); + } while (outlen) { u32 cryptlen = min3(inlen, outlen, (u32)DRBG_OUTSCRATCHLEN); @@ -1766,6 +1760,7 @@ static int drbg_kcapi_sym_ctr(struct drbg_state *drbg, crypto_init_wait(&drbg->ctr_wait); memcpy(outbuf, drbg->outscratchpad, cryptlen); + memzero_explicit(drbg->outscratchpad, cryptlen); outlen -= cryptlen; outbuf += cryptlen; @@ -1773,7 +1768,6 @@ static int drbg_kcapi_sym_ctr(struct drbg_state *drbg, ret = 0; out: - memzero_explicit(drbg->outscratchpad, DRBG_OUTSCRATCHLEN); return ret; } #endif /* CONFIG_CRYPTO_DRBG_CTR */ diff --git a/include/crypto/drbg.h b/include/crypto/drbg.h index 54b9f5d375f5..3fb581bf3b87 100644 --- a/include/crypto/drbg.h +++ b/include/crypto/drbg.h @@ -122,8 +122,6 @@ struct drbg_state { struct crypto_skcipher *ctr_handle; /* CTR mode cipher handle */ struct skcipher_request *ctr_req; /* CTR mode request handle */ - __u8 *ctr_null_value_buf; /* CTR mode unaligned buffer */ - __u8 *ctr_null_value; /* CTR mode aligned zero buf */ __u8 *outscratchpadbuf; /* CTR mode output scratchpad */ __u8 *outscratchpad; /* CTR mode aligned outbuf */ struct crypto_wait ctr_wait; /* CTR mode async wait obj */ -- cgit v1.2.3 From 8c30fbe63e4eff1b221f8db70ae5c48a9331eae0 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 23 Jul 2018 10:01:33 -0700 Subject: crypto: scatterwalk - remove 'chain' argument from scatterwalk_crypto_chain() All callers pass chain=0 to scatterwalk_crypto_chain(). Remove this unneeded parameter. Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu --- crypto/lrw.c | 4 ++-- crypto/scatterwalk.c | 2 +- crypto/xts.c | 4 ++-- include/crypto/scatterwalk.h | 8 +------- net/tls/tls_device_fallback.c | 2 +- 5 files changed, 7 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/crypto/lrw.c b/crypto/lrw.c index 954a7064a179..393a782679c7 100644 --- a/crypto/lrw.c +++ b/crypto/lrw.c @@ -188,7 +188,7 @@ static int post_crypt(struct skcipher_request *req) if (rctx->dst != sg) { rctx->dst[0] = *sg; sg_unmark_end(rctx->dst); - scatterwalk_crypto_chain(rctx->dst, sg_next(sg), 0, 2); + scatterwalk_crypto_chain(rctx->dst, sg_next(sg), 2); } rctx->dst[0].length -= offset - sg->offset; rctx->dst[0].offset = offset; @@ -265,7 +265,7 @@ static int pre_crypt(struct skcipher_request *req) if (rctx->src != sg) { rctx->src[0] = *sg; sg_unmark_end(rctx->src); - scatterwalk_crypto_chain(rctx->src, sg_next(sg), 0, 2); + scatterwalk_crypto_chain(rctx->src, sg_next(sg), 2); } rctx->src[0].length -= offset - sg->offset; rctx->src[0].offset = offset; diff --git a/crypto/scatterwalk.c b/crypto/scatterwalk.c index c16c94f88733..d0b92c1cd6e9 100644 --- a/crypto/scatterwalk.c +++ b/crypto/scatterwalk.c @@ -91,7 +91,7 @@ struct scatterlist *scatterwalk_ffwd(struct scatterlist dst[2], sg_init_table(dst, 2); sg_set_page(dst, sg_page(src), src->length - len, src->offset + len); - scatterwalk_crypto_chain(dst, sg_next(src), 0, 2); + scatterwalk_crypto_chain(dst, sg_next(src), 2); return dst; } diff --git a/crypto/xts.c b/crypto/xts.c index 12284183bd20..ccf55fbb8bc2 100644 --- a/crypto/xts.c +++ b/crypto/xts.c @@ -138,7 +138,7 @@ static int post_crypt(struct skcipher_request *req) if (rctx->dst != sg) { rctx->dst[0] = *sg; sg_unmark_end(rctx->dst); - scatterwalk_crypto_chain(rctx->dst, sg_next(sg), 0, 2); + scatterwalk_crypto_chain(rctx->dst, sg_next(sg), 2); } rctx->dst[0].length -= offset - sg->offset; rctx->dst[0].offset = offset; @@ -204,7 +204,7 @@ static int pre_crypt(struct skcipher_request *req) if (rctx->src != sg) { rctx->src[0] = *sg; sg_unmark_end(rctx->src); - scatterwalk_crypto_chain(rctx->src, sg_next(sg), 0, 2); + scatterwalk_crypto_chain(rctx->src, sg_next(sg), 2); } rctx->src[0].length -= offset - sg->offset; rctx->src[0].offset = offset; diff --git a/include/crypto/scatterwalk.h b/include/crypto/scatterwalk.h index 880e6be9e95e..eac72840a7d2 100644 --- a/include/crypto/scatterwalk.h +++ b/include/crypto/scatterwalk.h @@ -22,14 +22,8 @@ #include static inline void scatterwalk_crypto_chain(struct scatterlist *head, - struct scatterlist *sg, - int chain, int num) + struct scatterlist *sg, int num) { - if (chain) { - head->length += sg->length; - sg = sg_next(sg); - } - if (sg) sg_chain(head, num, sg); else diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c index 748914abdb60..4e1ec12bc0fb 100644 --- a/net/tls/tls_device_fallback.c +++ b/net/tls/tls_device_fallback.c @@ -42,7 +42,7 @@ static void chain_to_walk(struct scatterlist *sg, struct scatter_walk *walk) sg_set_page(sg, sg_page(src), src->length - diff, walk->offset); - scatterwalk_crypto_chain(sg, sg_next(src), 0, 2); + scatterwalk_crypto_chain(sg, sg_next(src), 2); } static int tls_enc_record(struct aead_request *aead_req, -- cgit v1.2.3 From 3dd8cc00c34ab9cde4bcc808ebc607e7b9861280 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 23 Jul 2018 10:04:28 -0700 Subject: crypto: scatterwalk - remove scatterwalk_samebuf() scatterwalk_samebuf() is never used. Remove it. Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu --- include/crypto/scatterwalk.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include') diff --git a/include/crypto/scatterwalk.h b/include/crypto/scatterwalk.h index eac72840a7d2..a66c127a20ed 100644 --- a/include/crypto/scatterwalk.h +++ b/include/crypto/scatterwalk.h @@ -30,13 +30,6 @@ static inline void scatterwalk_crypto_chain(struct scatterlist *head, sg_mark_end(head); } -static inline unsigned long scatterwalk_samebuf(struct scatter_walk *walk_in, - struct scatter_walk *walk_out) -{ - return !(((sg_page(walk_in->sg) - sg_page(walk_out->sg)) << PAGE_SHIFT) + - (int)(walk_in->offset - walk_out->offset)); -} - static inline unsigned int scatterwalk_pagelen(struct scatter_walk *walk) { unsigned int len = walk->sg->offset + walk->sg->length - walk->offset; -- cgit v1.2.3 From 2ad5157650b446f14a719280ba3670303bc4f439 Mon Sep 17 00:00:00 2001 From: Suman Anna Date: Wed, 11 Jul 2018 18:42:11 -0500 Subject: mailbox/omap: switch to SPDX license identifier Use the appropriate SPDX license identifier in the OMAP Mailbox driver source files and drop the previous boilerplate license text. Signed-off-by: Suman Anna Signed-off-by: Jassi Brar --- drivers/mailbox/omap-mailbox.c | 10 +--------- include/linux/omap-mailbox.h | 5 +---- 2 files changed, 2 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/drivers/mailbox/omap-mailbox.c b/drivers/mailbox/omap-mailbox.c index e1e2c085e68e..97c7d9b7f46f 100644 --- a/drivers/mailbox/omap-mailbox.c +++ b/drivers/mailbox/omap-mailbox.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * OMAP mailbox driver * @@ -6,15 +7,6 @@ * * Contact: Hiroshi DOYU * Suman Anna - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * version 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. */ #include diff --git a/include/linux/omap-mailbox.h b/include/linux/omap-mailbox.h index c726bd833761..6dbcd2da0332 100644 --- a/include/linux/omap-mailbox.h +++ b/include/linux/omap-mailbox.h @@ -1,9 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * omap-mailbox: interprocessor communication module for OMAP - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef OMAP_MAILBOX_H -- cgit v1.2.3 From 1c82407aa302774b24bf619e56973aa97cbf25bd Mon Sep 17 00:00:00 2001 From: Houlong Wei Date: Wed, 25 Jul 2018 09:26:39 +0800 Subject: dt-bindings: soc: Add documentation for the MediaTek GCE unit This adds documentation for the MediaTek Global Command Engine (GCE) unit found in MT8173 SoCs. Signed-off-by: Houlong Wei Signed-off-by: HS Liao Reviewed-by: Rob Herring Signed-off-by: Jassi Brar --- .../devicetree/bindings/mailbox/mtk-gce.txt | 57 ++++++++++++++++++++++ include/dt-bindings/gce/mt8173-gce.h | 44 +++++++++++++++++ 2 files changed, 101 insertions(+) create mode 100644 Documentation/devicetree/bindings/mailbox/mtk-gce.txt create mode 100644 include/dt-bindings/gce/mt8173-gce.h (limited to 'include') diff --git a/Documentation/devicetree/bindings/mailbox/mtk-gce.txt b/Documentation/devicetree/bindings/mailbox/mtk-gce.txt new file mode 100644 index 000000000000..7d72b21c9e94 --- /dev/null +++ b/Documentation/devicetree/bindings/mailbox/mtk-gce.txt @@ -0,0 +1,57 @@ +MediaTek GCE +=============== + +The Global Command Engine (GCE) is used to help read/write registers with +critical time limitation, such as updating display configuration during the +vblank. The GCE can be used to implement the Command Queue (CMDQ) driver. + +CMDQ driver uses mailbox framework for communication. Please refer to +mailbox.txt for generic information about mailbox device-tree bindings. + +Required properties: +- compatible: Must be "mediatek,mt8173-gce" +- reg: Address range of the GCE unit +- interrupts: The interrupt signal from the GCE block +- clock: Clocks according to the common clock binding +- clock-names: Must be "gce" to stand for GCE clock +- #mbox-cells: Should be 3. + <&phandle channel priority atomic_exec> + phandle: Label name of a gce node. + channel: Channel of mailbox. Be equal to the thread id of GCE. + priority: Priority of GCE thread. + atomic_exec: GCE processing continuous packets of commands in atomic + way. + +Required properties for a client device: +- mboxes: Client use mailbox to communicate with GCE, it should have this + property and list of phandle, mailbox specifiers. +- mediatek,gce-subsys: u32, specify the sub-system id which is corresponding + to the register address. + +Some vaules of properties are defined in 'dt-bindings/gce/mt8173-gce.h'. Such as +sub-system ids, thread priority, event ids. + +Example: + + gce: gce@10212000 { + compatible = "mediatek,mt8173-gce"; + reg = <0 0x10212000 0 0x1000>; + interrupts = ; + clocks = <&infracfg CLK_INFRA_GCE>; + clock-names = "gce"; + thread-num = CMDQ_THR_MAX_COUNT; + #mbox-cells = <3>; + }; + +Example for a client device: + + mmsys: clock-controller@14000000 { + compatible = "mediatek,mt8173-mmsys"; + mboxes = <&gce 0 CMDQ_THR_PRIO_LOWEST 1>, + <&gce 1 CMDQ_THR_PRIO_LOWEST 1>; + mediatek,gce-subsys = ; + mutex-event-eof = ; + + ... + }; diff --git a/include/dt-bindings/gce/mt8173-gce.h b/include/dt-bindings/gce/mt8173-gce.h new file mode 100644 index 000000000000..ffcf94ba96c6 --- /dev/null +++ b/include/dt-bindings/gce/mt8173-gce.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2018 MediaTek Inc. + * Author: Houlong Wei + * + */ + +#ifndef _DT_BINDINGS_GCE_MT8173_H +#define _DT_BINDINGS_GCE_MT8173_H + +/* GCE HW thread priority */ +#define CMDQ_THR_PRIO_LOWEST 0 +#define CMDQ_THR_PRIO_HIGHEST 1 + +/* GCE SUBSYS */ +#define SUBSYS_1400XXXX 1 +#define SUBSYS_1401XXXX 2 +#define SUBSYS_1402XXXX 3 + +/* GCE HW EVENT */ +#define CMDQ_EVENT_DISP_OVL0_SOF 11 +#define CMDQ_EVENT_DISP_OVL1_SOF 12 +#define CMDQ_EVENT_DISP_RDMA0_SOF 13 +#define CMDQ_EVENT_DISP_RDMA1_SOF 14 +#define CMDQ_EVENT_DISP_RDMA2_SOF 15 +#define CMDQ_EVENT_DISP_WDMA0_SOF 16 +#define CMDQ_EVENT_DISP_WDMA1_SOF 17 +#define CMDQ_EVENT_DISP_OVL0_EOF 39 +#define CMDQ_EVENT_DISP_OVL1_EOF 40 +#define CMDQ_EVENT_DISP_RDMA0_EOF 41 +#define CMDQ_EVENT_DISP_RDMA1_EOF 42 +#define CMDQ_EVENT_DISP_RDMA2_EOF 43 +#define CMDQ_EVENT_DISP_WDMA0_EOF 44 +#define CMDQ_EVENT_DISP_WDMA1_EOF 45 +#define CMDQ_EVENT_MUTEX0_STREAM_EOF 53 +#define CMDQ_EVENT_MUTEX1_STREAM_EOF 54 +#define CMDQ_EVENT_MUTEX2_STREAM_EOF 55 +#define CMDQ_EVENT_MUTEX3_STREAM_EOF 56 +#define CMDQ_EVENT_MUTEX4_STREAM_EOF 57 +#define CMDQ_EVENT_DISP_RDMA0_UNDERRUN 63 +#define CMDQ_EVENT_DISP_RDMA1_UNDERRUN 64 +#define CMDQ_EVENT_DISP_RDMA2_UNDERRUN 65 + +#endif -- cgit v1.2.3 From 623a6143a845bd485b00ba684f0ccef11835edab Mon Sep 17 00:00:00 2001 From: Houlong Wei Date: Wed, 25 Jul 2018 09:26:40 +0800 Subject: mailbox: mediatek: Add Mediatek CMDQ driver This patch is first version of Mediatek Command Queue(CMDQ) driver. The CMDQ is used to help write registers with critical time limitation, such as updating display configuration during the vblank. It controls Global Command Engine (GCE) hardware to achieve this requirement. Currently, CMDQ only supports display related hardwares, but we expect it can be extended to other hardwares for future requirements. Signed-off-by: Houlong Wei Signed-off-by: HS Liao Signed-off-by: CK Hu Signed-off-by: Jassi Brar --- drivers/mailbox/Kconfig | 10 + drivers/mailbox/Makefile | 2 + drivers/mailbox/mtk-cmdq-mailbox.c | 569 +++++++++++++++++++++++++++++++ include/linux/mailbox/mtk-cmdq-mailbox.h | 77 +++++ 4 files changed, 658 insertions(+) create mode 100644 drivers/mailbox/mtk-cmdq-mailbox.c create mode 100644 include/linux/mailbox/mtk-cmdq-mailbox.h (limited to 'include') diff --git a/drivers/mailbox/Kconfig b/drivers/mailbox/Kconfig index e63d29a95e76..2bbabc907add 100644 --- a/drivers/mailbox/Kconfig +++ b/drivers/mailbox/Kconfig @@ -189,4 +189,14 @@ config STM32_IPCC Mailbox implementation for STMicroelectonics STM32 family chips with hardware for Inter-Processor Communication Controller (IPCC) between processors. Say Y here if you want to have this support. + +config MTK_CMDQ_MBOX + tristate "MediaTek CMDQ Mailbox Support" + depends on ARCH_MEDIATEK || COMPILE_TEST + select MTK_INFRACFG + help + Say yes here to add support for the MediaTek Command Queue (CMDQ) + mailbox driver. The CMDQ is used to help read/write registers with + critical time limitation, such as updating display configuration + during the vblank. endif diff --git a/drivers/mailbox/Makefile b/drivers/mailbox/Makefile index 4d501bea7863..4b0080480661 100644 --- a/drivers/mailbox/Makefile +++ b/drivers/mailbox/Makefile @@ -40,3 +40,5 @@ obj-$(CONFIG_QCOM_APCS_IPC) += qcom-apcs-ipc-mailbox.o obj-$(CONFIG_TEGRA_HSP_MBOX) += tegra-hsp.o obj-$(CONFIG_STM32_IPCC) += stm32-ipcc.o + +obj-$(CONFIG_MTK_CMDQ_MBOX) += mtk-cmdq-mailbox.o diff --git a/drivers/mailbox/mtk-cmdq-mailbox.c b/drivers/mailbox/mtk-cmdq-mailbox.c new file mode 100644 index 000000000000..6f92c5ee12f7 --- /dev/null +++ b/drivers/mailbox/mtk-cmdq-mailbox.c @@ -0,0 +1,569 @@ +// SPDX-License-Identifier: GPL-2.0 +// +// Copyright (c) 2018 MediaTek Inc. + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define CMDQ_OP_CODE_MASK (0xff << CMDQ_OP_CODE_SHIFT) +#define CMDQ_IRQ_MASK 0xffff +#define CMDQ_NUM_CMD(t) (t->cmd_buf_size / CMDQ_INST_SIZE) + +#define CMDQ_CURR_IRQ_STATUS 0x10 +#define CMDQ_THR_SLOT_CYCLES 0x30 +#define CMDQ_THR_BASE 0x100 +#define CMDQ_THR_SIZE 0x80 +#define CMDQ_THR_WARM_RESET 0x00 +#define CMDQ_THR_ENABLE_TASK 0x04 +#define CMDQ_THR_SUSPEND_TASK 0x08 +#define CMDQ_THR_CURR_STATUS 0x0c +#define CMDQ_THR_IRQ_STATUS 0x10 +#define CMDQ_THR_IRQ_ENABLE 0x14 +#define CMDQ_THR_CURR_ADDR 0x20 +#define CMDQ_THR_END_ADDR 0x24 +#define CMDQ_THR_WAIT_TOKEN 0x30 +#define CMDQ_THR_PRIORITY 0x40 + +#define CMDQ_THR_ACTIVE_SLOT_CYCLES 0x3200 +#define CMDQ_THR_ENABLED 0x1 +#define CMDQ_THR_DISABLED 0x0 +#define CMDQ_THR_SUSPEND 0x1 +#define CMDQ_THR_RESUME 0x0 +#define CMDQ_THR_STATUS_SUSPENDED BIT(1) +#define CMDQ_THR_DO_WARM_RESET BIT(0) +#define CMDQ_THR_IRQ_DONE 0x1 +#define CMDQ_THR_IRQ_ERROR 0x12 +#define CMDQ_THR_IRQ_EN (CMDQ_THR_IRQ_ERROR | CMDQ_THR_IRQ_DONE) +#define CMDQ_THR_IS_WAITING BIT(31) + +#define CMDQ_JUMP_BY_OFFSET 0x10000000 +#define CMDQ_JUMP_BY_PA 0x10000001 + +struct cmdq_thread { + struct mbox_chan *chan; + void __iomem *base; + struct list_head task_busy_list; + u32 priority; + bool atomic_exec; +}; + +struct cmdq_task { + struct cmdq *cmdq; + struct list_head list_entry; + dma_addr_t pa_base; + struct cmdq_thread *thread; + struct cmdq_pkt *pkt; /* the packet sent from mailbox client */ +}; + +struct cmdq { + struct mbox_controller mbox; + void __iomem *base; + u32 irq; + u32 thread_nr; + struct cmdq_thread *thread; + struct clk *clock; + bool suspended; +}; + +static int cmdq_thread_suspend(struct cmdq *cmdq, struct cmdq_thread *thread) +{ + u32 status; + + writel(CMDQ_THR_SUSPEND, thread->base + CMDQ_THR_SUSPEND_TASK); + + /* If already disabled, treat as suspended successful. */ + if (!(readl(thread->base + CMDQ_THR_ENABLE_TASK) & CMDQ_THR_ENABLED)) + return 0; + + if (readl_poll_timeout_atomic(thread->base + CMDQ_THR_CURR_STATUS, + status, status & CMDQ_THR_STATUS_SUSPENDED, 0, 10)) { + dev_err(cmdq->mbox.dev, "suspend GCE thread 0x%x failed\n", + (u32)(thread->base - cmdq->base)); + return -EFAULT; + } + + return 0; +} + +static void cmdq_thread_resume(struct cmdq_thread *thread) +{ + writel(CMDQ_THR_RESUME, thread->base + CMDQ_THR_SUSPEND_TASK); +} + +static void cmdq_init(struct cmdq *cmdq) +{ + WARN_ON(clk_enable(cmdq->clock) < 0); + writel(CMDQ_THR_ACTIVE_SLOT_CYCLES, cmdq->base + CMDQ_THR_SLOT_CYCLES); + clk_disable(cmdq->clock); +} + +static int cmdq_thread_reset(struct cmdq *cmdq, struct cmdq_thread *thread) +{ + u32 warm_reset; + + writel(CMDQ_THR_DO_WARM_RESET, thread->base + CMDQ_THR_WARM_RESET); + if (readl_poll_timeout_atomic(thread->base + CMDQ_THR_WARM_RESET, + warm_reset, !(warm_reset & CMDQ_THR_DO_WARM_RESET), + 0, 10)) { + dev_err(cmdq->mbox.dev, "reset GCE thread 0x%x failed\n", + (u32)(thread->base - cmdq->base)); + return -EFAULT; + } + + return 0; +} + +static void cmdq_thread_disable(struct cmdq *cmdq, struct cmdq_thread *thread) +{ + cmdq_thread_reset(cmdq, thread); + writel(CMDQ_THR_DISABLED, thread->base + CMDQ_THR_ENABLE_TASK); +} + +/* notify GCE to re-fetch commands by setting GCE thread PC */ +static void cmdq_thread_invalidate_fetched_data(struct cmdq_thread *thread) +{ + writel(readl(thread->base + CMDQ_THR_CURR_ADDR), + thread->base + CMDQ_THR_CURR_ADDR); +} + +static void cmdq_task_insert_into_thread(struct cmdq_task *task) +{ + struct device *dev = task->cmdq->mbox.dev; + struct cmdq_thread *thread = task->thread; + struct cmdq_task *prev_task = list_last_entry( + &thread->task_busy_list, typeof(*task), list_entry); + u64 *prev_task_base = prev_task->pkt->va_base; + + /* let previous task jump to this task */ + dma_sync_single_for_cpu(dev, prev_task->pa_base, + prev_task->pkt->cmd_buf_size, DMA_TO_DEVICE); + prev_task_base[CMDQ_NUM_CMD(prev_task->pkt) - 1] = + (u64)CMDQ_JUMP_BY_PA << 32 | task->pa_base; + dma_sync_single_for_device(dev, prev_task->pa_base, + prev_task->pkt->cmd_buf_size, DMA_TO_DEVICE); + + cmdq_thread_invalidate_fetched_data(thread); +} + +static bool cmdq_command_is_wfe(u64 cmd) +{ + u64 wfe_option = CMDQ_WFE_UPDATE | CMDQ_WFE_WAIT | CMDQ_WFE_WAIT_VALUE; + u64 wfe_op = (u64)(CMDQ_CODE_WFE << CMDQ_OP_CODE_SHIFT) << 32; + u64 wfe_mask = (u64)CMDQ_OP_CODE_MASK << 32 | 0xffffffff; + + return ((cmd & wfe_mask) == (wfe_op | wfe_option)); +} + +/* we assume tasks in the same display GCE thread are waiting the same event. */ +static void cmdq_task_remove_wfe(struct cmdq_task *task) +{ + struct device *dev = task->cmdq->mbox.dev; + u64 *base = task->pkt->va_base; + int i; + + dma_sync_single_for_cpu(dev, task->pa_base, task->pkt->cmd_buf_size, + DMA_TO_DEVICE); + for (i = 0; i < CMDQ_NUM_CMD(task->pkt); i++) + if (cmdq_command_is_wfe(base[i])) + base[i] = (u64)CMDQ_JUMP_BY_OFFSET << 32 | + CMDQ_JUMP_PASS; + dma_sync_single_for_device(dev, task->pa_base, task->pkt->cmd_buf_size, + DMA_TO_DEVICE); +} + +static bool cmdq_thread_is_in_wfe(struct cmdq_thread *thread) +{ + return readl(thread->base + CMDQ_THR_WAIT_TOKEN) & CMDQ_THR_IS_WAITING; +} + +static void cmdq_thread_wait_end(struct cmdq_thread *thread, + unsigned long end_pa) +{ + struct device *dev = thread->chan->mbox->dev; + unsigned long curr_pa; + + if (readl_poll_timeout_atomic(thread->base + CMDQ_THR_CURR_ADDR, + curr_pa, curr_pa == end_pa, 1, 20)) + dev_err(dev, "GCE thread cannot run to end.\n"); +} + +static void cmdq_task_exec_done(struct cmdq_task *task, enum cmdq_cb_status sta) +{ + struct cmdq_task_cb *cb = &task->pkt->async_cb; + struct cmdq_cb_data data; + + WARN_ON(cb->cb == (cmdq_async_flush_cb)NULL); + data.sta = sta; + data.data = cb->data; + cb->cb(data); + + list_del(&task->list_entry); +} + +static void cmdq_task_handle_error(struct cmdq_task *task) +{ + struct cmdq_thread *thread = task->thread; + struct cmdq_task *next_task; + + dev_err(task->cmdq->mbox.dev, "task 0x%p error\n", task); + WARN_ON(cmdq_thread_suspend(task->cmdq, thread) < 0); + next_task = list_first_entry_or_null(&thread->task_busy_list, + struct cmdq_task, list_entry); + if (next_task) + writel(next_task->pa_base, thread->base + CMDQ_THR_CURR_ADDR); + cmdq_thread_resume(thread); +} + +static void cmdq_thread_irq_handler(struct cmdq *cmdq, + struct cmdq_thread *thread) +{ + struct cmdq_task *task, *tmp, *curr_task = NULL; + u32 curr_pa, irq_flag, task_end_pa; + bool err; + + irq_flag = readl(thread->base + CMDQ_THR_IRQ_STATUS); + writel(~irq_flag, thread->base + CMDQ_THR_IRQ_STATUS); + + /* + * When ISR call this function, another CPU core could run + * "release task" right before we acquire the spin lock, and thus + * reset / disable this GCE thread, so we need to check the enable + * bit of this GCE thread. + */ + if (!(readl(thread->base + CMDQ_THR_ENABLE_TASK) & CMDQ_THR_ENABLED)) + return; + + if (irq_flag & CMDQ_THR_IRQ_ERROR) + err = true; + else if (irq_flag & CMDQ_THR_IRQ_DONE) + err = false; + else + return; + + curr_pa = readl(thread->base + CMDQ_THR_CURR_ADDR); + + list_for_each_entry_safe(task, tmp, &thread->task_busy_list, + list_entry) { + task_end_pa = task->pa_base + task->pkt->cmd_buf_size; + if (curr_pa >= task->pa_base && curr_pa < task_end_pa) + curr_task = task; + + if (!curr_task || curr_pa == task_end_pa - CMDQ_INST_SIZE) { + cmdq_task_exec_done(task, CMDQ_CB_NORMAL); + kfree(task); + } else if (err) { + cmdq_task_exec_done(task, CMDQ_CB_ERROR); + cmdq_task_handle_error(curr_task); + kfree(task); + } + + if (curr_task) + break; + } + + if (list_empty(&thread->task_busy_list)) { + cmdq_thread_disable(cmdq, thread); + clk_disable(cmdq->clock); + } +} + +static irqreturn_t cmdq_irq_handler(int irq, void *dev) +{ + struct cmdq *cmdq = dev; + unsigned long irq_status, flags = 0L; + int bit; + + irq_status = readl(cmdq->base + CMDQ_CURR_IRQ_STATUS) & CMDQ_IRQ_MASK; + if (!(irq_status ^ CMDQ_IRQ_MASK)) + return IRQ_NONE; + + for_each_clear_bit(bit, &irq_status, fls(CMDQ_IRQ_MASK)) { + struct cmdq_thread *thread = &cmdq->thread[bit]; + + spin_lock_irqsave(&thread->chan->lock, flags); + cmdq_thread_irq_handler(cmdq, thread); + spin_unlock_irqrestore(&thread->chan->lock, flags); + } + + return IRQ_HANDLED; +} + +static int cmdq_suspend(struct device *dev) +{ + struct cmdq *cmdq = dev_get_drvdata(dev); + struct cmdq_thread *thread; + int i; + bool task_running = false; + + cmdq->suspended = true; + + for (i = 0; i < cmdq->thread_nr; i++) { + thread = &cmdq->thread[i]; + if (!list_empty(&thread->task_busy_list)) { + task_running = true; + break; + } + } + + if (task_running) + dev_warn(dev, "exist running task(s) in suspend\n"); + + clk_unprepare(cmdq->clock); + + return 0; +} + +static int cmdq_resume(struct device *dev) +{ + struct cmdq *cmdq = dev_get_drvdata(dev); + + WARN_ON(clk_prepare(cmdq->clock) < 0); + cmdq->suspended = false; + return 0; +} + +static int cmdq_remove(struct platform_device *pdev) +{ + struct cmdq *cmdq = platform_get_drvdata(pdev); + + mbox_controller_unregister(&cmdq->mbox); + clk_unprepare(cmdq->clock); + + if (cmdq->mbox.chans) + devm_kfree(&pdev->dev, cmdq->mbox.chans); + + if (cmdq->thread) + devm_kfree(&pdev->dev, cmdq->thread); + + devm_kfree(&pdev->dev, cmdq); + + return 0; +} + +static int cmdq_mbox_send_data(struct mbox_chan *chan, void *data) +{ + struct cmdq_pkt *pkt = (struct cmdq_pkt *)data; + struct cmdq_thread *thread = (struct cmdq_thread *)chan->con_priv; + struct cmdq *cmdq = dev_get_drvdata(chan->mbox->dev); + struct cmdq_task *task; + unsigned long curr_pa, end_pa; + + /* Client should not flush new tasks if suspended. */ + WARN_ON(cmdq->suspended); + + task = kzalloc(sizeof(*task), GFP_ATOMIC); + task->cmdq = cmdq; + INIT_LIST_HEAD(&task->list_entry); + task->pa_base = pkt->pa_base; + task->thread = thread; + task->pkt = pkt; + + if (list_empty(&thread->task_busy_list)) { + WARN_ON(clk_enable(cmdq->clock) < 0); + WARN_ON(cmdq_thread_reset(cmdq, thread) < 0); + + writel(task->pa_base, thread->base + CMDQ_THR_CURR_ADDR); + writel(task->pa_base + pkt->cmd_buf_size, + thread->base + CMDQ_THR_END_ADDR); + writel(thread->priority, thread->base + CMDQ_THR_PRIORITY); + writel(CMDQ_THR_IRQ_EN, thread->base + CMDQ_THR_IRQ_ENABLE); + writel(CMDQ_THR_ENABLED, thread->base + CMDQ_THR_ENABLE_TASK); + } else { + WARN_ON(cmdq_thread_suspend(cmdq, thread) < 0); + curr_pa = readl(thread->base + CMDQ_THR_CURR_ADDR); + end_pa = readl(thread->base + CMDQ_THR_END_ADDR); + + /* + * Atomic execution should remove the following wfe, i.e. only + * wait event at first task, and prevent to pause when running. + */ + if (thread->atomic_exec) { + /* GCE is executing if command is not WFE */ + if (!cmdq_thread_is_in_wfe(thread)) { + cmdq_thread_resume(thread); + cmdq_thread_wait_end(thread, end_pa); + WARN_ON(cmdq_thread_suspend(cmdq, thread) < 0); + /* set to this task directly */ + writel(task->pa_base, + thread->base + CMDQ_THR_CURR_ADDR); + } else { + cmdq_task_insert_into_thread(task); + cmdq_task_remove_wfe(task); + smp_mb(); /* modify jump before enable thread */ + } + } else { + /* check boundary */ + if (curr_pa == end_pa - CMDQ_INST_SIZE || + curr_pa == end_pa) { + /* set to this task directly */ + writel(task->pa_base, + thread->base + CMDQ_THR_CURR_ADDR); + } else { + cmdq_task_insert_into_thread(task); + smp_mb(); /* modify jump before enable thread */ + } + } + writel(task->pa_base + pkt->cmd_buf_size, + thread->base + CMDQ_THR_END_ADDR); + cmdq_thread_resume(thread); + } + list_move_tail(&task->list_entry, &thread->task_busy_list); + + return 0; +} + +static int cmdq_mbox_startup(struct mbox_chan *chan) +{ + return 0; +} + +static void cmdq_mbox_shutdown(struct mbox_chan *chan) +{ +} + +static const struct mbox_chan_ops cmdq_mbox_chan_ops = { + .send_data = cmdq_mbox_send_data, + .startup = cmdq_mbox_startup, + .shutdown = cmdq_mbox_shutdown, +}; + +static struct mbox_chan *cmdq_xlate(struct mbox_controller *mbox, + const struct of_phandle_args *sp) +{ + int ind = sp->args[0]; + struct cmdq_thread *thread; + + if (ind >= mbox->num_chans) + return ERR_PTR(-EINVAL); + + thread = (struct cmdq_thread *)mbox->chans[ind].con_priv; + thread->priority = sp->args[1]; + thread->atomic_exec = (sp->args[2] != 0); + thread->chan = &mbox->chans[ind]; + + return &mbox->chans[ind]; +} + +static int cmdq_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct resource *res; + struct cmdq *cmdq; + int err, i; + + cmdq = devm_kzalloc(dev, sizeof(*cmdq), GFP_KERNEL); + if (!cmdq) + return -ENOMEM; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + cmdq->base = devm_ioremap_resource(dev, res); + if (IS_ERR(cmdq->base)) { + dev_err(dev, "failed to ioremap gce\n"); + return PTR_ERR(cmdq->base); + } + + cmdq->irq = platform_get_irq(pdev, 0); + if (!cmdq->irq) { + dev_err(dev, "failed to get irq\n"); + return -EINVAL; + } + err = devm_request_irq(dev, cmdq->irq, cmdq_irq_handler, IRQF_SHARED, + "mtk_cmdq", cmdq); + if (err < 0) { + dev_err(dev, "failed to register ISR (%d)\n", err); + return err; + } + + dev_dbg(dev, "cmdq device: addr:0x%p, va:0x%p, irq:%d\n", + dev, cmdq->base, cmdq->irq); + + cmdq->clock = devm_clk_get(dev, "gce"); + if (IS_ERR(cmdq->clock)) { + dev_err(dev, "failed to get gce clk\n"); + return PTR_ERR(cmdq->clock); + } + + cmdq->thread_nr = (u32)(unsigned long)of_device_get_match_data(dev); + cmdq->mbox.dev = dev; + cmdq->mbox.chans = devm_kcalloc(dev, cmdq->thread_nr, + sizeof(*cmdq->mbox.chans), GFP_KERNEL); + if (!cmdq->mbox.chans) + return -ENOMEM; + + cmdq->mbox.num_chans = cmdq->thread_nr; + cmdq->mbox.ops = &cmdq_mbox_chan_ops; + cmdq->mbox.of_xlate = cmdq_xlate; + + /* make use of TXDONE_BY_ACK */ + cmdq->mbox.txdone_irq = false; + cmdq->mbox.txdone_poll = false; + + cmdq->thread = devm_kcalloc(dev, cmdq->thread_nr, + sizeof(*cmdq->thread), GFP_KERNEL); + if (!cmdq->thread) + return -ENOMEM; + + for (i = 0; i < cmdq->thread_nr; i++) { + cmdq->thread[i].base = cmdq->base + CMDQ_THR_BASE + + CMDQ_THR_SIZE * i; + INIT_LIST_HEAD(&cmdq->thread[i].task_busy_list); + cmdq->mbox.chans[i].con_priv = (void *)&cmdq->thread[i]; + } + + err = mbox_controller_register(&cmdq->mbox); + if (err < 0) { + dev_err(dev, "failed to register mailbox: %d\n", err); + return err; + } + + platform_set_drvdata(pdev, cmdq); + WARN_ON(clk_prepare(cmdq->clock) < 0); + + cmdq_init(cmdq); + + return 0; +} + +static const struct dev_pm_ops cmdq_pm_ops = { + .suspend = cmdq_suspend, + .resume = cmdq_resume, +}; + +static const struct of_device_id cmdq_of_ids[] = { + {.compatible = "mediatek,mt8173-gce", .data = (void *)16}, + {} +}; + +static struct platform_driver cmdq_drv = { + .probe = cmdq_probe, + .remove = cmdq_remove, + .driver = { + .name = "mtk_cmdq", + .pm = &cmdq_pm_ops, + .of_match_table = cmdq_of_ids, + } +}; + +static int __init cmdq_drv_init(void) +{ + return platform_driver_register(&cmdq_drv); +} + +static void __exit cmdq_drv_exit(void) +{ + platform_driver_unregister(&cmdq_drv); +} + +subsys_initcall(cmdq_drv_init); +module_exit(cmdq_drv_exit); diff --git a/include/linux/mailbox/mtk-cmdq-mailbox.h b/include/linux/mailbox/mtk-cmdq-mailbox.h new file mode 100644 index 000000000000..ccb73422c2fa --- /dev/null +++ b/include/linux/mailbox/mtk-cmdq-mailbox.h @@ -0,0 +1,77 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2018 MediaTek Inc. + * + */ + +#ifndef __MTK_CMDQ_MAILBOX_H__ +#define __MTK_CMDQ_MAILBOX_H__ + +#include +#include +#include + +#define CMDQ_INST_SIZE 8 /* instruction is 64-bit */ +#define CMDQ_SUBSYS_SHIFT 16 +#define CMDQ_OP_CODE_SHIFT 24 +#define CMDQ_JUMP_PASS CMDQ_INST_SIZE + +#define CMDQ_WFE_UPDATE BIT(31) +#define CMDQ_WFE_WAIT BIT(15) +#define CMDQ_WFE_WAIT_VALUE 0x1 + +/* + * CMDQ_CODE_MASK: + * set write mask + * format: op mask + * CMDQ_CODE_WRITE: + * write value into target register + * format: op subsys address value + * CMDQ_CODE_JUMP: + * jump by offset + * format: op offset + * CMDQ_CODE_WFE: + * wait for event and clear + * it is just clear if no wait + * format: [wait] op event update:1 to_wait:1 wait:1 + * [clear] op event update:1 to_wait:0 wait:0 + * CMDQ_CODE_EOC: + * end of command + * format: op irq_flag + */ +enum cmdq_code { + CMDQ_CODE_MASK = 0x02, + CMDQ_CODE_WRITE = 0x04, + CMDQ_CODE_JUMP = 0x10, + CMDQ_CODE_WFE = 0x20, + CMDQ_CODE_EOC = 0x40, +}; + +enum cmdq_cb_status { + CMDQ_CB_NORMAL = 0, + CMDQ_CB_ERROR +}; + +struct cmdq_cb_data { + enum cmdq_cb_status sta; + void *data; +}; + +typedef void (*cmdq_async_flush_cb)(struct cmdq_cb_data data); + +struct cmdq_task_cb { + cmdq_async_flush_cb cb; + void *data; +}; + +struct cmdq_pkt { + void *va_base; + dma_addr_t pa_base; + size_t cmd_buf_size; /* command occupied size */ + size_t buf_size; /* real buffer size */ + struct cmdq_task_cb cb; + struct cmdq_task_cb async_cb; + void *cl; +}; + +#endif /* __MTK_CMDQ_MAILBOX_H__ */ -- cgit v1.2.3 From 285189c78eeb6f684a024b86fb5997d10c6aa564 Mon Sep 17 00:00:00 2001 From: Li RongQing Date: Wed, 25 Jul 2018 15:52:13 +0800 Subject: netfilter: use kvmalloc_array to allocate memory for hashtable nf_ct_alloc_hashtable is used to allocate memory for conntrack, NAT bysrc and expectation hashtable. Assuming 64k bucket size, which means 7th order page allocation, __get_free_pages, called by nf_ct_alloc_hashtable, will trigger the direct memory reclaim and stall for a long time, when system has lots of memory stress so replace combination of __get_free_pages and vzalloc with kvmalloc_array, which provides a overflow check and a fallback if no high order memory is available, and do not retry to reclaim memory, reduce stall and remove nf_ct_free_hashtable, since it is just a kvfree Signed-off-by: Zhang Yu Signed-off-by: Wang Li Signed-off-by: Li RongQing Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack.h | 2 -- net/netfilter/nf_conntrack_core.c | 29 ++++++----------------------- net/netfilter/nf_conntrack_expect.c | 2 +- net/netfilter/nf_conntrack_helper.c | 4 ++-- net/netfilter/nf_nat_core.c | 4 ++-- 5 files changed, 11 insertions(+), 30 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index a2b0ed025908..7e012312cd61 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -176,8 +176,6 @@ void nf_ct_netns_put(struct net *net, u8 nfproto); */ void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls); -void nf_ct_free_hashtable(void *hash, unsigned int size); - int nf_conntrack_hash_check_insert(struct nf_conn *ct); bool nf_ct_delete(struct nf_conn *ct, u32 pid, int report); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 8a113ca1eea2..a676d5f76bdc 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -2022,16 +2022,6 @@ static int kill_all(struct nf_conn *i, void *data) return net_eq(nf_ct_net(i), data); } -void nf_ct_free_hashtable(void *hash, unsigned int size) -{ - if (is_vmalloc_addr(hash)) - vfree(hash); - else - free_pages((unsigned long)hash, - get_order(sizeof(struct hlist_head) * size)); -} -EXPORT_SYMBOL_GPL(nf_ct_free_hashtable); - void nf_conntrack_cleanup_start(void) { conntrack_gc_work.exiting = true; @@ -2042,7 +2032,7 @@ void nf_conntrack_cleanup_end(void) { RCU_INIT_POINTER(nf_ct_hook, NULL); cancel_delayed_work_sync(&conntrack_gc_work.dwork); - nf_ct_free_hashtable(nf_conntrack_hash, nf_conntrack_htable_size); + kvfree(nf_conntrack_hash); nf_conntrack_proto_fini(); nf_conntrack_seqadj_fini(); @@ -2108,7 +2098,6 @@ void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls) { struct hlist_nulls_head *hash; unsigned int nr_slots, i; - size_t sz; if (*sizep > (UINT_MAX / sizeof(struct hlist_nulls_head))) return NULL; @@ -2116,14 +2105,8 @@ void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls) BUILD_BUG_ON(sizeof(struct hlist_nulls_head) != sizeof(struct hlist_head)); nr_slots = *sizep = roundup(*sizep, PAGE_SIZE / sizeof(struct hlist_nulls_head)); - if (nr_slots > (UINT_MAX / sizeof(struct hlist_nulls_head))) - return NULL; - - sz = nr_slots * sizeof(struct hlist_nulls_head); - hash = (void *)__get_free_pages(GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO, - get_order(sz)); - if (!hash) - hash = vzalloc(sz); + hash = kvmalloc_array(nr_slots, sizeof(struct hlist_nulls_head), + GFP_KERNEL | __GFP_ZERO); if (hash && nulls) for (i = 0; i < nr_slots; i++) @@ -2150,7 +2133,7 @@ int nf_conntrack_hash_resize(unsigned int hashsize) old_size = nf_conntrack_htable_size; if (old_size == hashsize) { - nf_ct_free_hashtable(hash, hashsize); + kvfree(hash); return 0; } @@ -2186,7 +2169,7 @@ int nf_conntrack_hash_resize(unsigned int hashsize) local_bh_enable(); synchronize_net(); - nf_ct_free_hashtable(old_hash, old_size); + kvfree(old_hash); return 0; } @@ -2350,7 +2333,7 @@ err_acct: err_expect: kmem_cache_destroy(nf_conntrack_cachep); err_cachep: - nf_ct_free_hashtable(nf_conntrack_hash, nf_conntrack_htable_size); + kvfree(nf_conntrack_hash); return ret; } diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 3f586ba23d92..27b84231db10 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -712,5 +712,5 @@ void nf_conntrack_expect_fini(void) { rcu_barrier(); /* Wait for call_rcu() before destroy */ kmem_cache_destroy(nf_ct_expect_cachep); - nf_ct_free_hashtable(nf_ct_expect_hash, nf_ct_expect_hsize); + kvfree(nf_ct_expect_hash); } diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index d557a425289d..e24b762ffa1d 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -562,12 +562,12 @@ int nf_conntrack_helper_init(void) return 0; out_extend: - nf_ct_free_hashtable(nf_ct_helper_hash, nf_ct_helper_hsize); + kvfree(nf_ct_helper_hash); return ret; } void nf_conntrack_helper_fini(void) { nf_ct_extend_unregister(&helper_extend); - nf_ct_free_hashtable(nf_ct_helper_hash, nf_ct_helper_hsize); + kvfree(nf_ct_helper_hash); } diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 6366f0c0b8c1..e2b196054dfc 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -1056,7 +1056,7 @@ static int __init nf_nat_init(void) ret = nf_ct_extend_register(&nat_extend); if (ret < 0) { - nf_ct_free_hashtable(nf_nat_bysource, nf_nat_htable_size); + kvfree(nf_nat_bysource); pr_err("Unable to register extension\n"); return ret; } @@ -1094,7 +1094,7 @@ static void __exit nf_nat_cleanup(void) for (i = 0; i < NFPROTO_NUMPROTO; i++) kfree(nf_nat_l4protos[i]); synchronize_net(); - nf_ct_free_hashtable(nf_nat_bysource, nf_nat_htable_size); + kvfree(nf_nat_bysource); unregister_pernet_subsys(&nat_net_ops); } -- cgit v1.2.3 From 7cca1ed0bb248b8d5768d17f5afe297a832d66c0 Mon Sep 17 00:00:00 2001 From: Fernando Fernandez Mancera Date: Tue, 31 Jul 2018 20:25:00 +0200 Subject: netfilter: nf_osf: move nf_osf_fingers to non-uapi header file All warnings (new ones prefixed by >>): >> ./usr/include/linux/netfilter/nf_osf.h:73: userspace cannot reference function or variable defined in the kernel Fixes: f9324952088f ("netfilter: nfnetlink_osf: extract nfnetlink_subsystem code from xt_osf.c") Reported-by: kbuild test robot Signed-off-by: Fernando Fernandez Mancera Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nf_osf.h | 2 ++ include/uapi/linux/netfilter/nf_osf.h | 2 -- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter/nf_osf.h b/include/linux/netfilter/nf_osf.h index aee460fcbd31..3e455d6f94d5 100644 --- a/include/linux/netfilter/nf_osf.h +++ b/include/linux/netfilter/nf_osf.h @@ -25,6 +25,8 @@ enum osf_fmatch_states { FMATCH_OPT_WRONG, }; +extern struct list_head nf_osf_fingers[2]; + struct nf_osf_finger { struct rcu_head rcu_head; struct list_head finger_entry; diff --git a/include/uapi/linux/netfilter/nf_osf.h b/include/uapi/linux/netfilter/nf_osf.h index cc2487ff74f6..3b93fbb9fc24 100644 --- a/include/uapi/linux/netfilter/nf_osf.h +++ b/include/uapi/linux/netfilter/nf_osf.h @@ -70,8 +70,6 @@ struct nf_osf_nlmsg { struct tcphdr tcp; }; -extern struct list_head nf_osf_fingers[2]; - /* Defines for IANA option kinds */ enum iana_options { OSFOPT_EOL = 0, /* End of options */ -- cgit v1.2.3 From ddba40be59c9be4059288464f8e6f38fbba27495 Mon Sep 17 00:00:00 2001 From: Fernando Fernandez Mancera Date: Tue, 31 Jul 2018 20:25:01 +0200 Subject: netfilter: nfnetlink_osf: rename nf_osf header file to nfnetlink_osf The first client of the nf_osf.h userspace header is nft_osf, coming in this batch, rename it to nfnetlink_osf.h as there are no userspace clients for this yet, hence this looks consistent with other nfnetlink subsystem. Suggested-by: Jan Engelhardt Signed-off-by: Fernando Fernandez Mancera Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nf_osf.h | 44 ----------- include/linux/netfilter/nfnetlink_osf.h | 44 +++++++++++ include/uapi/linux/netfilter/nf_osf.h | 106 --------------------------- include/uapi/linux/netfilter/nfnetlink_osf.h | 106 +++++++++++++++++++++++++++ include/uapi/linux/netfilter/xt_osf.h | 2 +- net/netfilter/nfnetlink_osf.c | 2 +- net/netfilter/nft_osf.c | 2 +- 7 files changed, 153 insertions(+), 153 deletions(-) delete mode 100644 include/linux/netfilter/nf_osf.h create mode 100644 include/linux/netfilter/nfnetlink_osf.h delete mode 100644 include/uapi/linux/netfilter/nf_osf.h create mode 100644 include/uapi/linux/netfilter/nfnetlink_osf.h (limited to 'include') diff --git a/include/linux/netfilter/nf_osf.h b/include/linux/netfilter/nf_osf.h deleted file mode 100644 index 3e455d6f94d5..000000000000 --- a/include/linux/netfilter/nf_osf.h +++ /dev/null @@ -1,44 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _NFOSF_H -#define _NFOSF_H - -#include - -/* Initial window size option state machine: multiple of mss, mtu or - * plain numeric value. Can also be made as plain numeric value which - * is not a multiple of specified value. - */ -enum nf_osf_window_size_options { - OSF_WSS_PLAIN = 0, - OSF_WSS_MSS, - OSF_WSS_MTU, - OSF_WSS_MODULO, - OSF_WSS_MAX, -}; - -enum osf_fmatch_states { - /* Packet does not match the fingerprint */ - FMATCH_WRONG = 0, - /* Packet matches the fingerprint */ - FMATCH_OK, - /* Options do not match the fingerprint, but header does */ - FMATCH_OPT_WRONG, -}; - -extern struct list_head nf_osf_fingers[2]; - -struct nf_osf_finger { - struct rcu_head rcu_head; - struct list_head finger_entry; - struct nf_osf_user_finger finger; -}; - -bool nf_osf_match(const struct sk_buff *skb, u_int8_t family, - int hooknum, struct net_device *in, struct net_device *out, - const struct nf_osf_info *info, struct net *net, - const struct list_head *nf_osf_fingers); - -const char *nf_osf_find(const struct sk_buff *skb, - const struct list_head *nf_osf_fingers); - -#endif /* _NFOSF_H */ diff --git a/include/linux/netfilter/nfnetlink_osf.h b/include/linux/netfilter/nfnetlink_osf.h new file mode 100644 index 000000000000..a7311bc03d3a --- /dev/null +++ b/include/linux/netfilter/nfnetlink_osf.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _NFOSF_H +#define _NFOSF_H + +#include + +/* Initial window size option state machine: multiple of mss, mtu or + * plain numeric value. Can also be made as plain numeric value which + * is not a multiple of specified value. + */ +enum nf_osf_window_size_options { + OSF_WSS_PLAIN = 0, + OSF_WSS_MSS, + OSF_WSS_MTU, + OSF_WSS_MODULO, + OSF_WSS_MAX, +}; + +enum osf_fmatch_states { + /* Packet does not match the fingerprint */ + FMATCH_WRONG = 0, + /* Packet matches the fingerprint */ + FMATCH_OK, + /* Options do not match the fingerprint, but header does */ + FMATCH_OPT_WRONG, +}; + +extern struct list_head nf_osf_fingers[2]; + +struct nf_osf_finger { + struct rcu_head rcu_head; + struct list_head finger_entry; + struct nf_osf_user_finger finger; +}; + +bool nf_osf_match(const struct sk_buff *skb, u_int8_t family, + int hooknum, struct net_device *in, struct net_device *out, + const struct nf_osf_info *info, struct net *net, + const struct list_head *nf_osf_fingers); + +const char *nf_osf_find(const struct sk_buff *skb, + const struct list_head *nf_osf_fingers); + +#endif /* _NFOSF_H */ diff --git a/include/uapi/linux/netfilter/nf_osf.h b/include/uapi/linux/netfilter/nf_osf.h deleted file mode 100644 index 3b93fbb9fc24..000000000000 --- a/include/uapi/linux/netfilter/nf_osf.h +++ /dev/null @@ -1,106 +0,0 @@ -#ifndef _NF_OSF_H -#define _NF_OSF_H - -#include - -#define MAXGENRELEN 32 - -#define NF_OSF_GENRE (1 << 0) -#define NF_OSF_TTL (1 << 1) -#define NF_OSF_LOG (1 << 2) -#define NF_OSF_INVERT (1 << 3) - -#define NF_OSF_LOGLEVEL_ALL 0 /* log all matched fingerprints */ -#define NF_OSF_LOGLEVEL_FIRST 1 /* log only the first matced fingerprint */ -#define NF_OSF_LOGLEVEL_ALL_KNOWN 2 /* do not log unknown packets */ - -#define NF_OSF_TTL_TRUE 0 /* True ip and fingerprint TTL comparison */ - -/* Check if ip TTL is less than fingerprint one */ -#define NF_OSF_TTL_LESS 1 - -/* Do not compare ip and fingerprint TTL at all */ -#define NF_OSF_TTL_NOCHECK 2 - -#define NF_OSF_FLAGMASK (NF_OSF_GENRE | NF_OSF_TTL | \ - NF_OSF_LOG | NF_OSF_INVERT) -/* Wildcard MSS (kind of). - * It is used to implement a state machine for the different wildcard values - * of the MSS and window sizes. - */ -struct nf_osf_wc { - __u32 wc; - __u32 val; -}; - -/* This struct represents IANA options - * http://www.iana.org/assignments/tcp-parameters - */ -struct nf_osf_opt { - __u16 kind, length; - struct nf_osf_wc wc; -}; - -struct nf_osf_info { - char genre[MAXGENRELEN]; - __u32 len; - __u32 flags; - __u32 loglevel; - __u32 ttl; -}; - -struct nf_osf_user_finger { - struct nf_osf_wc wss; - - __u8 ttl, df; - __u16 ss, mss; - __u16 opt_num; - - char genre[MAXGENRELEN]; - char version[MAXGENRELEN]; - char subtype[MAXGENRELEN]; - - /* MAX_IPOPTLEN is maximum if all options are NOPs or EOLs */ - struct nf_osf_opt opt[MAX_IPOPTLEN]; -}; - -struct nf_osf_nlmsg { - struct nf_osf_user_finger f; - struct iphdr ip; - struct tcphdr tcp; -}; - -/* Defines for IANA option kinds */ -enum iana_options { - OSFOPT_EOL = 0, /* End of options */ - OSFOPT_NOP, /* NOP */ - OSFOPT_MSS, /* Maximum segment size */ - OSFOPT_WSO, /* Window scale option */ - OSFOPT_SACKP, /* SACK permitted */ - OSFOPT_SACK, /* SACK */ - OSFOPT_ECHO, - OSFOPT_ECHOREPLY, - OSFOPT_TS, /* Timestamp option */ - OSFOPT_POCP, /* Partial Order Connection Permitted */ - OSFOPT_POSP, /* Partial Order Service Profile */ - - /* Others are not used in the current OSF */ - OSFOPT_EMPTY = 255, -}; - -enum nf_osf_attr_type { - OSF_ATTR_UNSPEC, - OSF_ATTR_FINGER, - OSF_ATTR_MAX, -}; - -/* - * Add/remove fingerprint from the kernel. - */ -enum nf_osf_msg_types { - OSF_MSG_ADD, - OSF_MSG_REMOVE, - OSF_MSG_MAX, -}; - -#endif /* _NF_OSF_H */ diff --git a/include/uapi/linux/netfilter/nfnetlink_osf.h b/include/uapi/linux/netfilter/nfnetlink_osf.h new file mode 100644 index 000000000000..3b93fbb9fc24 --- /dev/null +++ b/include/uapi/linux/netfilter/nfnetlink_osf.h @@ -0,0 +1,106 @@ +#ifndef _NF_OSF_H +#define _NF_OSF_H + +#include + +#define MAXGENRELEN 32 + +#define NF_OSF_GENRE (1 << 0) +#define NF_OSF_TTL (1 << 1) +#define NF_OSF_LOG (1 << 2) +#define NF_OSF_INVERT (1 << 3) + +#define NF_OSF_LOGLEVEL_ALL 0 /* log all matched fingerprints */ +#define NF_OSF_LOGLEVEL_FIRST 1 /* log only the first matced fingerprint */ +#define NF_OSF_LOGLEVEL_ALL_KNOWN 2 /* do not log unknown packets */ + +#define NF_OSF_TTL_TRUE 0 /* True ip and fingerprint TTL comparison */ + +/* Check if ip TTL is less than fingerprint one */ +#define NF_OSF_TTL_LESS 1 + +/* Do not compare ip and fingerprint TTL at all */ +#define NF_OSF_TTL_NOCHECK 2 + +#define NF_OSF_FLAGMASK (NF_OSF_GENRE | NF_OSF_TTL | \ + NF_OSF_LOG | NF_OSF_INVERT) +/* Wildcard MSS (kind of). + * It is used to implement a state machine for the different wildcard values + * of the MSS and window sizes. + */ +struct nf_osf_wc { + __u32 wc; + __u32 val; +}; + +/* This struct represents IANA options + * http://www.iana.org/assignments/tcp-parameters + */ +struct nf_osf_opt { + __u16 kind, length; + struct nf_osf_wc wc; +}; + +struct nf_osf_info { + char genre[MAXGENRELEN]; + __u32 len; + __u32 flags; + __u32 loglevel; + __u32 ttl; +}; + +struct nf_osf_user_finger { + struct nf_osf_wc wss; + + __u8 ttl, df; + __u16 ss, mss; + __u16 opt_num; + + char genre[MAXGENRELEN]; + char version[MAXGENRELEN]; + char subtype[MAXGENRELEN]; + + /* MAX_IPOPTLEN is maximum if all options are NOPs or EOLs */ + struct nf_osf_opt opt[MAX_IPOPTLEN]; +}; + +struct nf_osf_nlmsg { + struct nf_osf_user_finger f; + struct iphdr ip; + struct tcphdr tcp; +}; + +/* Defines for IANA option kinds */ +enum iana_options { + OSFOPT_EOL = 0, /* End of options */ + OSFOPT_NOP, /* NOP */ + OSFOPT_MSS, /* Maximum segment size */ + OSFOPT_WSO, /* Window scale option */ + OSFOPT_SACKP, /* SACK permitted */ + OSFOPT_SACK, /* SACK */ + OSFOPT_ECHO, + OSFOPT_ECHOREPLY, + OSFOPT_TS, /* Timestamp option */ + OSFOPT_POCP, /* Partial Order Connection Permitted */ + OSFOPT_POSP, /* Partial Order Service Profile */ + + /* Others are not used in the current OSF */ + OSFOPT_EMPTY = 255, +}; + +enum nf_osf_attr_type { + OSF_ATTR_UNSPEC, + OSF_ATTR_FINGER, + OSF_ATTR_MAX, +}; + +/* + * Add/remove fingerprint from the kernel. + */ +enum nf_osf_msg_types { + OSF_MSG_ADD, + OSF_MSG_REMOVE, + OSF_MSG_MAX, +}; + +#endif /* _NF_OSF_H */ diff --git a/include/uapi/linux/netfilter/xt_osf.h b/include/uapi/linux/netfilter/xt_osf.h index a90e90c27cef..c56c59605c2b 100644 --- a/include/uapi/linux/netfilter/xt_osf.h +++ b/include/uapi/linux/netfilter/xt_osf.h @@ -23,7 +23,7 @@ #include #include #include -#include +#include #define XT_OSF_GENRE NF_OSF_GENRE #define XT_OSF_INVERT NF_OSF_INVERT diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c index ba0fa11869ce..f9dba62c450f 100644 --- a/net/netfilter/nfnetlink_osf.c +++ b/net/netfilter/nfnetlink_osf.c @@ -18,7 +18,7 @@ #include #include #include -#include +#include /* * Indexed by dont-fragment bit. diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c index bdacc4cffba4..9b2f3de7be4f 100644 --- a/net/netfilter/nft_osf.c +++ b/net/netfilter/nft_osf.c @@ -2,7 +2,7 @@ #include #include -#include +#include #define OSF_GENRE_SIZE 32 -- cgit v1.2.3 From e9697e2effad50c0081b3c72002d3975f8ab4347 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Fri, 3 Aug 2018 12:38:39 +0200 Subject: l2tp: ignore L2TP_ATTR_MTU This attribute's handling is broken. It can only be used when creating Ethernet pseudo-wires, in which case its value can be used as the initial MTU for the l2tpeth device. However, when handling update requests, L2TP_ATTR_MTU only modifies session->mtu. This value is never propagated to the l2tpeth device. Dump requests also return the value of session->mtu, which is not synchronised anymore with the device MTU. The same problem occurs if the device MTU is properly updated using the generic IFLA_MTU attribute. In this case, session->mtu is not updated, and L2TP_ATTR_MTU will report an invalid value again when dumping the session. It does not seem worthwhile to complexify l2tp_eth.c to synchronise session->mtu with the device MTU. Even the ip-l2tp manpage advises to use 'ip link' to initialise the MTU of l2tpeth devices (iproute2 does not handle L2TP_ATTR_MTU at all anyway). So let's just ignore it entirely. Signed-off-by: Guillaume Nault Signed-off-by: David S. Miller --- include/uapi/linux/l2tp.h | 2 +- net/l2tp/l2tp_core.c | 1 - net/l2tp/l2tp_core.h | 2 -- net/l2tp/l2tp_debugfs.c | 3 +-- net/l2tp/l2tp_eth.c | 17 +++++++---------- net/l2tp/l2tp_netlink.c | 9 +-------- 6 files changed, 10 insertions(+), 24 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/l2tp.h b/include/uapi/linux/l2tp.h index 8bb8c7cfabe5..61158f5a1a5b 100644 --- a/include/uapi/linux/l2tp.h +++ b/include/uapi/linux/l2tp.h @@ -119,7 +119,7 @@ enum { L2TP_ATTR_IP_DADDR, /* u32 */ L2TP_ATTR_UDP_SPORT, /* u16 */ L2TP_ATTR_UDP_DPORT, /* u16 */ - L2TP_ATTR_MTU, /* u16 */ + L2TP_ATTR_MTU, /* u16 (not used) */ L2TP_ATTR_MRU, /* u16 (not used) */ L2TP_ATTR_STATS, /* nested */ L2TP_ATTR_IP6_SADDR, /* struct in6_addr */ diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index c61a467fd9b8..ac6a00bcec71 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1674,7 +1674,6 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn if (cfg) { session->pwtype = cfg->pw_type; session->debug = cfg->debug; - session->mtu = cfg->mtu; session->send_seq = cfg->send_seq; session->recv_seq = cfg->recv_seq; session->lns_mode = cfg->lns_mode; diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 1ca39629031b..5804065dfbfb 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -64,7 +64,6 @@ struct l2tp_session_cfg { int peer_cookie_len; /* 0, 4 or 8 bytes */ int reorder_timeout; /* configured reorder timeout * (in jiffies) */ - int mtu; char *ifname; }; @@ -108,7 +107,6 @@ struct l2tp_session { int reorder_timeout; /* configured reorder timeout * (in jiffies) */ int reorder_skip; /* set if skip to next nr */ - int mtu; enum l2tp_pwtype pwtype; struct l2tp_stats stats; struct hlist_node global_hlist; /* Global hash list node */ diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c index aee271741f5b..9821a1458555 100644 --- a/net/l2tp/l2tp_debugfs.c +++ b/net/l2tp/l2tp_debugfs.c @@ -191,8 +191,7 @@ static void l2tp_dfs_seq_session_show(struct seq_file *m, void *v) if (session->send_seq || session->recv_seq) seq_printf(m, " nr %hu, ns %hu\n", session->nr, session->ns); seq_printf(m, " refcnt %d\n", refcount_read(&session->ref_count)); - seq_printf(m, " config %d/0/%c/%c/-/%s %08x %u\n", - session->mtu, + seq_printf(m, " config 0/0/%c/%c/-/%s %08x %u\n", session->recv_seq ? 'R' : '-', session->send_seq ? 'S' : '-', session->lns_mode ? "LNS" : "LAC", diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index cfca5e63ae31..3728986ec885 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -234,14 +234,11 @@ static void l2tp_eth_adjust_mtu(struct l2tp_tunnel *tunnel, overhead += sizeof(struct udphdr); dev->needed_headroom += sizeof(struct udphdr); } - if (session->mtu != 0) { - dev->mtu = session->mtu; - dev->needed_headroom += session->hdr_len; - return; - } + lock_sock(tunnel->sock); l3_overhead = kernel_sock_ip_overhead(tunnel->sock); release_sock(tunnel->sock); + if (l3_overhead == 0) { /* L3 Overhead couldn't be identified, this could be * because tunnel->sock was NULL or the socket's @@ -255,12 +252,12 @@ static void l2tp_eth_adjust_mtu(struct l2tp_tunnel *tunnel, */ overhead += session->hdr_len + ETH_HLEN + l3_overhead; - /* If PMTU discovery was enabled, use discovered MTU on L2TP device */ - mtu = l2tp_tunnel_dst_mtu(tunnel); - if (mtu) + mtu = l2tp_tunnel_dst_mtu(tunnel) - overhead; + if (mtu < dev->min_mtu || mtu > dev->max_mtu) + dev->mtu = ETH_DATA_LEN - overhead; + else dev->mtu = mtu; - session->mtu = dev->mtu - overhead; - dev->mtu = session->mtu; + dev->needed_headroom += session->hdr_len; } diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index a7c409215336..2e1e92651545 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -608,9 +608,6 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf if (info->attrs[L2TP_ATTR_RECV_TIMEOUT]) cfg.reorder_timeout = nla_get_msecs(info->attrs[L2TP_ATTR_RECV_TIMEOUT]); - if (info->attrs[L2TP_ATTR_MTU]) - cfg.mtu = nla_get_u16(info->attrs[L2TP_ATTR_MTU]); - #ifdef CONFIG_MODULES if (l2tp_nl_cmd_ops[cfg.pw_type] == NULL) { genl_unlock(); @@ -698,9 +695,6 @@ static int l2tp_nl_cmd_session_modify(struct sk_buff *skb, struct genl_info *inf if (info->attrs[L2TP_ATTR_RECV_TIMEOUT]) session->reorder_timeout = nla_get_msecs(info->attrs[L2TP_ATTR_RECV_TIMEOUT]); - if (info->attrs[L2TP_ATTR_MTU]) - session->mtu = nla_get_u16(info->attrs[L2TP_ATTR_MTU]); - ret = l2tp_session_notify(&l2tp_nl_family, info, session, L2TP_CMD_SESSION_MODIFY); @@ -730,8 +724,7 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq, int fl nla_put_u32(skb, L2TP_ATTR_PEER_SESSION_ID, session->peer_session_id) || nla_put_u32(skb, L2TP_ATTR_DEBUG, session->debug) || - nla_put_u16(skb, L2TP_ATTR_PW_TYPE, session->pwtype) || - nla_put_u16(skb, L2TP_ATTR_MTU, session->mtu)) + nla_put_u16(skb, L2TP_ATTR_PW_TYPE, session->pwtype)) goto nla_put_failure; if ((session->ifname[0] && -- cgit v1.2.3 From af308b94a2a4a5a27bec9028354c4df444a7c8ba Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 2 Aug 2018 20:51:39 +0200 Subject: netfilter: nf_tables: add tunnel support This patch implements the tunnel object type that can be used to configure tunnels via metadata template through the existing lightweight API from the ingress path. Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 69 ++++- net/core/dst.c | 1 + net/netfilter/Kconfig | 6 + net/netfilter/Makefile | 1 + net/netfilter/nft_tunnel.c | 458 +++++++++++++++++++++++++++++++ 5 files changed, 534 insertions(+), 1 deletion(-) create mode 100644 net/netfilter/nft_tunnel.c (limited to 'include') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index f112ea52dc1a..3ee1198eeac1 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -1416,7 +1416,8 @@ enum nft_ct_helper_attributes { #define NFT_OBJECT_CT_HELPER 3 #define NFT_OBJECT_LIMIT 4 #define NFT_OBJECT_CONNLIMIT 5 -#define __NFT_OBJECT_MAX 6 +#define NFT_OBJECT_TUNNEL 6 +#define __NFT_OBJECT_MAX 7 #define NFT_OBJECT_MAX (__NFT_OBJECT_MAX - 1) /** @@ -1580,4 +1581,70 @@ enum nft_ng_types { }; #define NFT_NG_MAX (__NFT_NG_MAX - 1) +enum nft_tunnel_key_ip_attributes { + NFTA_TUNNEL_KEY_IP_UNSPEC, + NFTA_TUNNEL_KEY_IP_SRC, + NFTA_TUNNEL_KEY_IP_DST, + __NFTA_TUNNEL_KEY_IP_MAX +}; +#define NFTA_TUNNEL_KEY_IP_MAX (__NFTA_TUNNEL_KEY_IP_MAX - 1) + +enum nft_tunnel_ip6_attributes { + NFTA_TUNNEL_KEY_IP6_UNSPEC, + NFTA_TUNNEL_KEY_IP6_SRC, + NFTA_TUNNEL_KEY_IP6_DST, + NFTA_TUNNEL_KEY_IP6_FLOWLABEL, + __NFTA_TUNNEL_KEY_IP6_MAX +}; +#define NFTA_TUNNEL_KEY_IP6_MAX (__NFTA_TUNNEL_KEY_IP6_MAX - 1) + +enum nft_tunnel_opts_attributes { + NFTA_TUNNEL_KEY_OPTS_UNSPEC, + NFTA_TUNNEL_KEY_OPTS_VXLAN, + NFTA_TUNNEL_KEY_OPTS_ERSPAN, + __NFTA_TUNNEL_KEY_OPTS_MAX +}; +#define NFTA_TUNNEL_KEY_OPTS_MAX (__NFTA_TUNNEL_KEY_OPTS_MAX - 1) + +enum nft_tunnel_opts_vxlan_attributes { + NFTA_TUNNEL_KEY_VXLAN_UNSPEC, + NFTA_TUNNEL_KEY_VXLAN_GBP, + __NFTA_TUNNEL_KEY_VXLAN_MAX +}; +#define NFTA_TUNNEL_KEY_VXLAN_MAX (__NFTA_TUNNEL_KEY_VXLAN_MAX - 1) + +enum nft_tunnel_opts_erspan_attributes { + NFTA_TUNNEL_KEY_ERSPAN_UNSPEC, + NFTA_TUNNEL_KEY_ERSPAN_VERSION, + NFTA_TUNNEL_KEY_ERSPAN_V1_INDEX, + NFTA_TUNNEL_KEY_ERSPAN_V2_HWID, + NFTA_TUNNEL_KEY_ERSPAN_V2_DIR, + __NFTA_TUNNEL_KEY_ERSPAN_MAX +}; +#define NFTA_TUNNEL_KEY_ERSPAN_MAX (__NFTA_TUNNEL_KEY_ERSPAN_MAX - 1) + +enum nft_tunnel_flags { + NFT_TUNNEL_F_ZERO_CSUM_TX = (1 << 0), + NFT_TUNNEL_F_DONT_FRAGMENT = (1 << 1), + NFT_TUNNEL_F_SEQ_NUMBER = (1 << 2), +}; +#define NFT_TUNNEL_F_MASK (NFT_TUNNEL_F_ZERO_CSUM_TX | \ + NFT_TUNNEL_F_DONT_FRAGMENT | \ + NFT_TUNNEL_F_SEQ_NUMBER) + +enum nft_tunnel_key_attributes { + NFTA_TUNNEL_KEY_UNSPEC, + NFTA_TUNNEL_KEY_ID, + NFTA_TUNNEL_KEY_IP, + NFTA_TUNNEL_KEY_IP6, + NFTA_TUNNEL_KEY_FLAGS, + NFTA_TUNNEL_KEY_TOS, + NFTA_TUNNEL_KEY_TTL, + NFTA_TUNNEL_KEY_SPORT, + NFTA_TUNNEL_KEY_DPORT, + NFTA_TUNNEL_KEY_OPTS, + __NFTA_TUNNEL_KEY_MAX +}; +#define NFTA_TUNNEL_KEY_MAX (__NFTA_TUNNEL_KEY_MAX - 1) + #endif /* _LINUX_NF_TABLES_H */ diff --git a/net/core/dst.c b/net/core/dst.c index 2d9b37f8944a..81ccf20e2826 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -307,6 +307,7 @@ void metadata_dst_free(struct metadata_dst *md_dst) #endif kfree(md_dst); } +EXPORT_SYMBOL_GPL(metadata_dst_free); struct metadata_dst __percpu * metadata_dst_alloc_percpu(u8 optslen, enum metadata_type type, gfp_t flags) diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 55e399d5af10..654588088676 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -559,6 +559,12 @@ config NFT_NAT This option adds the "nat" expression that you can use to perform typical Network Address Translation (NAT) packet transformations. +config NFT_TUNNEL + tristate "Netfilter nf_tables tunnel module" + help + This option adds the "tunnel" expression that you can use to set + tunneling policies. + config NFT_OBJREF tristate "Netfilter nf_tables stateful object reference module" help diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index cf61615cc529..16895e045b66 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -101,6 +101,7 @@ obj-$(CONFIG_NFT_QUEUE) += nft_queue.o obj-$(CONFIG_NFT_QUOTA) += nft_quota.o obj-$(CONFIG_NFT_REJECT) += nft_reject.o obj-$(CONFIG_NFT_REJECT_INET) += nft_reject_inet.o +obj-$(CONFIG_NFT_TUNNEL) += nft_tunnel.o obj-$(CONFIG_NFT_COUNTER) += nft_counter.o obj-$(CONFIG_NFT_LOG) += nft_log.o obj-$(CONFIG_NFT_MASQ) += nft_masq.o diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c new file mode 100644 index 000000000000..715613d99c20 --- /dev/null +++ b/net/netfilter/nft_tunnel.c @@ -0,0 +1,458 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +struct nft_tunnel_opts { + union { + struct vxlan_metadata vxlan; + struct erspan_metadata erspan; + } u; + u32 len; + u32 flags; +}; + +struct nft_tunnel_obj { + struct metadata_dst *md; + struct nft_tunnel_opts opts; +}; + +static const struct nla_policy nft_tunnel_ip_policy[NFTA_TUNNEL_KEY_IP_MAX + 1] = { + [NFTA_TUNNEL_KEY_IP_SRC] = { .type = NLA_U32 }, + [NFTA_TUNNEL_KEY_IP_DST] = { .type = NLA_U32 }, +}; + +static int nft_tunnel_obj_ip_init(const struct nft_ctx *ctx, + const struct nlattr *attr, + struct ip_tunnel_info *info) +{ + struct nlattr *tb[NFTA_TUNNEL_KEY_IP_MAX + 1]; + int err; + + err = nla_parse_nested(tb, NFTA_TUNNEL_KEY_IP_MAX, attr, + nft_tunnel_ip_policy, NULL); + if (err < 0) + return err; + + if (!tb[NFTA_TUNNEL_KEY_IP_DST]) + return -EINVAL; + + if (tb[NFTA_TUNNEL_KEY_IP_SRC]) + info->key.u.ipv4.src = nla_get_be32(tb[NFTA_TUNNEL_KEY_IP_SRC]); + if (tb[NFTA_TUNNEL_KEY_IP_DST]) + info->key.u.ipv4.dst = nla_get_be32(tb[NFTA_TUNNEL_KEY_IP_DST]); + + return 0; +} + +static const struct nla_policy nft_tunnel_ip6_policy[NFTA_TUNNEL_KEY_IP6_MAX + 1] = { + [NFTA_TUNNEL_KEY_IP6_SRC] = { .len = sizeof(struct in6_addr), }, + [NFTA_TUNNEL_KEY_IP6_DST] = { .len = sizeof(struct in6_addr), }, + [NFTA_TUNNEL_KEY_IP6_FLOWLABEL] = { .type = NLA_U32, } +}; + +static int nft_tunnel_obj_ip6_init(const struct nft_ctx *ctx, + const struct nlattr *attr, + struct ip_tunnel_info *info) +{ + struct nlattr *tb[NFTA_TUNNEL_KEY_IP6_MAX + 1]; + int err; + + err = nla_parse_nested(tb, NFTA_TUNNEL_KEY_IP6_MAX, attr, + nft_tunnel_ip6_policy, NULL); + if (err < 0) + return err; + + if (!tb[NFTA_TUNNEL_KEY_IP6_DST]) + return -EINVAL; + + if (tb[NFTA_TUNNEL_KEY_IP6_SRC]) { + memcpy(&info->key.u.ipv6.src, + nla_data(tb[NFTA_TUNNEL_KEY_IP6_SRC]), + sizeof(struct in6_addr)); + } + if (tb[NFTA_TUNNEL_KEY_IP6_DST]) { + memcpy(&info->key.u.ipv6.dst, + nla_data(tb[NFTA_TUNNEL_KEY_IP6_DST]), + sizeof(struct in6_addr)); + } + if (tb[NFTA_TUNNEL_KEY_IP6_FLOWLABEL]) + info->key.label = nla_get_be32(tb[NFTA_TUNNEL_KEY_IP6_FLOWLABEL]); + + info->mode |= IP_TUNNEL_INFO_IPV6; + + return 0; +} + +static const struct nla_policy nft_tunnel_opts_vxlan_policy[NFTA_TUNNEL_KEY_VXLAN_MAX + 1] = { + [NFTA_TUNNEL_KEY_VXLAN_GBP] = { .type = NLA_U32 }, +}; + +static int nft_tunnel_obj_vxlan_init(const struct nlattr *attr, + struct nft_tunnel_opts *opts) +{ + struct nlattr *tb[NFTA_TUNNEL_KEY_VXLAN_MAX + 1]; + int err; + + err = nla_parse_nested(tb, NFTA_TUNNEL_KEY_VXLAN_MAX, attr, + nft_tunnel_opts_vxlan_policy, NULL); + if (err < 0) + return err; + + if (!tb[NFTA_TUNNEL_KEY_VXLAN_GBP]) + return -EINVAL; + + opts->u.vxlan.gbp = ntohl(nla_get_be32(tb[NFTA_TUNNEL_KEY_VXLAN_GBP])); + + opts->len = sizeof(struct vxlan_metadata); + opts->flags = TUNNEL_VXLAN_OPT; + + return 0; +} + +static const struct nla_policy nft_tunnel_opts_erspan_policy[NFTA_TUNNEL_KEY_ERSPAN_MAX + 1] = { + [NFTA_TUNNEL_KEY_ERSPAN_V1_INDEX] = { .type = NLA_U32 }, + [NFTA_TUNNEL_KEY_ERSPAN_V2_DIR] = { .type = NLA_U8 }, + [NFTA_TUNNEL_KEY_ERSPAN_V2_HWID] = { .type = NLA_U8 }, +}; + +static int nft_tunnel_obj_erspan_init(const struct nlattr *attr, + struct nft_tunnel_opts *opts) +{ + struct nlattr *tb[NFTA_TUNNEL_KEY_ERSPAN_MAX + 1]; + uint8_t hwid, dir; + int err, version; + + err = nla_parse_nested(tb, NFTA_TUNNEL_KEY_ERSPAN_MAX, attr, + nft_tunnel_opts_erspan_policy, NULL); + if (err < 0) + return err; + + version = ntohl(nla_get_be32(tb[NFTA_TUNNEL_KEY_ERSPAN_VERSION])); + switch (version) { + case ERSPAN_VERSION: + if (!tb[NFTA_TUNNEL_KEY_ERSPAN_V1_INDEX]) + return -EINVAL; + + opts->u.erspan.u.index = + nla_get_be32(tb[NFTA_TUNNEL_KEY_ERSPAN_V1_INDEX]); + break; + case ERSPAN_VERSION2: + if (!tb[NFTA_TUNNEL_KEY_ERSPAN_V2_DIR] || + !tb[NFTA_TUNNEL_KEY_ERSPAN_V2_HWID]) + return -EINVAL; + + hwid = nla_get_u8(tb[NFTA_TUNNEL_KEY_ERSPAN_V2_HWID]); + dir = nla_get_u8(tb[NFTA_TUNNEL_KEY_ERSPAN_V2_DIR]); + + set_hwid(&opts->u.erspan.u.md2, hwid); + opts->u.erspan.u.md2.dir = dir; + break; + default: + return -EOPNOTSUPP; + } + opts->u.erspan.version = version; + + opts->len = sizeof(struct erspan_metadata); + opts->flags = TUNNEL_ERSPAN_OPT; + + return 0; +} + +static const struct nla_policy nft_tunnel_opts_policy[NFTA_TUNNEL_KEY_OPTS_MAX + 1] = { + [NFTA_TUNNEL_KEY_OPTS_VXLAN] = { .type = NLA_NESTED, }, + [NFTA_TUNNEL_KEY_OPTS_ERSPAN] = { .type = NLA_NESTED, }, +}; + +static int nft_tunnel_obj_opts_init(const struct nft_ctx *ctx, + const struct nlattr *attr, + struct ip_tunnel_info *info, + struct nft_tunnel_opts *opts) +{ + struct nlattr *tb[NFTA_TUNNEL_KEY_OPTS_MAX + 1]; + int err; + + err = nla_parse_nested(tb, NFTA_TUNNEL_KEY_OPTS_MAX, attr, + nft_tunnel_opts_policy, NULL); + if (err < 0) + return err; + + if (tb[NFTA_TUNNEL_KEY_OPTS_VXLAN]) { + err = nft_tunnel_obj_vxlan_init(tb[NFTA_TUNNEL_KEY_OPTS_VXLAN], + opts); + } else if (tb[NFTA_TUNNEL_KEY_OPTS_ERSPAN]) { + err = nft_tunnel_obj_erspan_init(tb[NFTA_TUNNEL_KEY_OPTS_ERSPAN], + opts); + } else { + return -EOPNOTSUPP; + } + + return err; +} + +static const struct nla_policy nft_tunnel_key_policy[NFTA_TUNNEL_KEY_MAX + 1] = { + [NFTA_TUNNEL_KEY_IP] = { .type = NLA_NESTED, }, + [NFTA_TUNNEL_KEY_IP6] = { .type = NLA_NESTED, }, + [NFTA_TUNNEL_KEY_ID] = { .type = NLA_U32, }, + [NFTA_TUNNEL_KEY_FLAGS] = { .type = NLA_U32, }, + [NFTA_TUNNEL_KEY_TOS] = { .type = NLA_U8, }, + [NFTA_TUNNEL_KEY_TTL] = { .type = NLA_U8, }, + [NFTA_TUNNEL_KEY_OPTS] = { .type = NLA_NESTED, }, +}; + +static int nft_tunnel_obj_init(const struct nft_ctx *ctx, + const struct nlattr * const tb[], + struct nft_object *obj) +{ + struct nft_tunnel_obj *priv = nft_obj_data(obj); + struct ip_tunnel_info info; + struct metadata_dst *md; + int err; + + if (!tb[NFTA_TUNNEL_KEY_ID]) + return -EINVAL; + + memset(&info, 0, sizeof(info)); + info.mode = IP_TUNNEL_INFO_TX; + info.key.tun_id = key32_to_tunnel_id(nla_get_be32(tb[NFTA_TUNNEL_KEY_ID])); + info.key.tun_flags = TUNNEL_KEY | TUNNEL_CSUM | TUNNEL_NOCACHE; + + if (tb[NFTA_TUNNEL_KEY_IP]) { + err = nft_tunnel_obj_ip_init(ctx, tb[NFTA_TUNNEL_KEY_IP], &info); + if (err < 0) + return err; + } else if (tb[NFTA_TUNNEL_KEY_IP6]) { + err = nft_tunnel_obj_ip6_init(ctx, tb[NFTA_TUNNEL_KEY_IP6], &info); + if (err < 0) + return err; + } else { + return -EINVAL; + } + + if (tb[NFTA_TUNNEL_KEY_SPORT]) { + info.key.tp_src = + ntohs(nla_get_be16(tb[NFTA_TUNNEL_KEY_SPORT])); + } + if (tb[NFTA_TUNNEL_KEY_DPORT]) { + info.key.tp_dst = + ntohs(nla_get_be16(tb[NFTA_TUNNEL_KEY_DPORT])); + } + + if (tb[NFTA_TUNNEL_KEY_FLAGS]) { + u32 tun_flags; + + tun_flags = ntohl(nla_get_be32(tb[NFTA_TUNNEL_KEY_FLAGS])); + if (tun_flags & ~NFT_TUNNEL_F_MASK) + return -EOPNOTSUPP; + + if (tun_flags & NFT_TUNNEL_F_ZERO_CSUM_TX) + info.key.tun_flags &= ~TUNNEL_CSUM; + if (tun_flags & NFT_TUNNEL_F_DONT_FRAGMENT) + info.key.tun_flags |= TUNNEL_DONT_FRAGMENT; + if (tun_flags & NFT_TUNNEL_F_SEQ_NUMBER) + info.key.tun_flags |= TUNNEL_SEQ; + } + if (tb[NFTA_TUNNEL_KEY_TOS]) + info.key.tos = nla_get_u8(tb[NFTA_TUNNEL_KEY_TOS]); + if (tb[NFTA_TUNNEL_KEY_TTL]) + info.key.ttl = nla_get_u8(tb[NFTA_TUNNEL_KEY_TTL]); + else + info.key.ttl = U8_MAX; + + if (tb[NFTA_TUNNEL_KEY_OPTS]) { + err = nft_tunnel_obj_opts_init(ctx, tb[NFTA_TUNNEL_KEY_OPTS], + &info, &priv->opts); + if (err < 0) + return err; + } + + md = metadata_dst_alloc(priv->opts.len, METADATA_IP_TUNNEL, GFP_KERNEL); + if (!md) + return -ENOMEM; + + memcpy(&md->u.tun_info, &info, sizeof(info)); + ip_tunnel_info_opts_set(&md->u.tun_info, &priv->opts.u, priv->opts.len, + priv->opts.flags); + priv->md = md; + + return 0; +} + +static inline void nft_tunnel_obj_eval(struct nft_object *obj, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_tunnel_obj *priv = nft_obj_data(obj); + struct sk_buff *skb = pkt->skb; + + skb_dst_drop(skb); + dst_hold((struct dst_entry *) priv->md); + skb_dst_set(skb, (struct dst_entry *) priv->md); +} + +static int nft_tunnel_ip_dump(struct sk_buff *skb, struct ip_tunnel_info *info) +{ + struct nlattr *nest; + + if (info->mode & IP_TUNNEL_INFO_IPV6) { + nest = nla_nest_start(skb, NFTA_TUNNEL_KEY_IP6); + if (!nest) + return -1; + + if (nla_put_in6_addr(skb, NFTA_TUNNEL_KEY_IP6_SRC, &info->key.u.ipv6.src) < 0 || + nla_put_in6_addr(skb, NFTA_TUNNEL_KEY_IP6_DST, &info->key.u.ipv6.dst) < 0 || + nla_put_be32(skb, NFTA_TUNNEL_KEY_IP6_FLOWLABEL, info->key.label)) + return -1; + + nla_nest_end(skb, nest); + } else { + nest = nla_nest_start(skb, NFTA_TUNNEL_KEY_IP); + if (!nest) + return -1; + + if (nla_put_in_addr(skb, NFTA_TUNNEL_KEY_IP_SRC, info->key.u.ipv4.src) < 0 || + nla_put_in_addr(skb, NFTA_TUNNEL_KEY_IP_DST, info->key.u.ipv4.dst) < 0) + return -1; + + nla_nest_end(skb, nest); + } + + return 0; +} + +static int nft_tunnel_opts_dump(struct sk_buff *skb, + struct nft_tunnel_obj *priv) +{ + struct nft_tunnel_opts *opts = &priv->opts; + struct nlattr *nest; + + nest = nla_nest_start(skb, NFTA_TUNNEL_KEY_OPTS); + if (!nest) + return -1; + + if (opts->flags & TUNNEL_VXLAN_OPT) { + if (nla_put_be32(skb, NFTA_TUNNEL_KEY_VXLAN_GBP, + htonl(opts->u.vxlan.gbp))) + return -1; + } else if (opts->flags & TUNNEL_ERSPAN_OPT) { + switch (opts->u.erspan.version) { + case ERSPAN_VERSION: + if (nla_put_be32(skb, NFTA_TUNNEL_KEY_ERSPAN_V1_INDEX, + opts->u.erspan.u.index)) + return -1; + break; + case ERSPAN_VERSION2: + if (nla_put_u8(skb, NFTA_TUNNEL_KEY_ERSPAN_V2_HWID, + get_hwid(&opts->u.erspan.u.md2)) || + nla_put_u8(skb, NFTA_TUNNEL_KEY_ERSPAN_V2_DIR, + opts->u.erspan.u.md2.dir)) + return -1; + break; + } + } + nla_nest_end(skb, nest); + + return 0; +} + +static int nft_tunnel_ports_dump(struct sk_buff *skb, + struct ip_tunnel_info *info) +{ + if (nla_put_be16(skb, NFTA_TUNNEL_KEY_SPORT, htons(info->key.tp_src)) < 0 || + nla_put_be16(skb, NFTA_TUNNEL_KEY_DPORT, htons(info->key.tp_dst)) < 0) + return -1; + + return 0; +} + +static int nft_tunnel_flags_dump(struct sk_buff *skb, + struct ip_tunnel_info *info) +{ + u32 flags = 0; + + if (info->key.tun_flags & TUNNEL_DONT_FRAGMENT) + flags |= NFT_TUNNEL_F_DONT_FRAGMENT; + if (!(info->key.tun_flags & TUNNEL_CSUM)) + flags |= NFT_TUNNEL_F_ZERO_CSUM_TX; + if (info->key.tun_flags & TUNNEL_SEQ) + flags |= NFT_TUNNEL_F_SEQ_NUMBER; + + if (nla_put_be32(skb, NFTA_TUNNEL_KEY_FLAGS, htonl(flags)) < 0) + return -1; + + return 0; +} + +static int nft_tunnel_obj_dump(struct sk_buff *skb, + struct nft_object *obj, bool reset) +{ + struct nft_tunnel_obj *priv = nft_obj_data(obj); + struct ip_tunnel_info *info = &priv->md->u.tun_info; + + if (nla_put_be32(skb, NFTA_TUNNEL_KEY_ID, + tunnel_id_to_key32(info->key.tun_id)) || + nft_tunnel_ip_dump(skb, info) < 0 || + nft_tunnel_ports_dump(skb, info) < 0 || + nft_tunnel_flags_dump(skb, info) < 0 || + nla_put_u8(skb, NFTA_TUNNEL_KEY_TOS, info->key.tos) || + nla_put_u8(skb, NFTA_TUNNEL_KEY_TTL, info->key.ttl) || + nft_tunnel_opts_dump(skb, priv) < 0) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -1; +} + +static void nft_tunnel_obj_destroy(const struct nft_ctx *ctx, + struct nft_object *obj) +{ + struct nft_tunnel_obj *priv = nft_obj_data(obj); + + metadata_dst_free(priv->md); +} + +static struct nft_object_type nft_tunnel_obj_type; +static const struct nft_object_ops nft_tunnel_obj_ops = { + .type = &nft_tunnel_obj_type, + .size = sizeof(struct nft_tunnel_obj), + .eval = nft_tunnel_obj_eval, + .init = nft_tunnel_obj_init, + .destroy = nft_tunnel_obj_destroy, + .dump = nft_tunnel_obj_dump, +}; + +static struct nft_object_type nft_tunnel_obj_type __read_mostly = { + .type = NFT_OBJECT_TUNNEL, + .ops = &nft_tunnel_obj_ops, + .maxattr = NFTA_TUNNEL_KEY_MAX, + .policy = nft_tunnel_key_policy, + .owner = THIS_MODULE, +}; + +static int __init nft_tunnel_module_init(void) +{ + return nft_register_obj(&nft_tunnel_obj_type); +} + +static void __exit nft_tunnel_module_exit(void) +{ + nft_unregister_obj(&nft_tunnel_obj_type); +} + +module_init(nft_tunnel_module_init); +module_exit(nft_tunnel_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Pablo Neira Ayuso "); +MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_TUNNEL); -- cgit v1.2.3 From aaecfdb5c5dd8bac2dfd112166844a9f2d5711f0 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 2 Aug 2018 20:51:46 +0200 Subject: netfilter: nf_tables: match on tunnel metadata This patch allows us to match on the tunnel metadata that is available of the packet. We can use this to validate if the packet comes from/goes to tunnel and the corresponding tunnel ID. Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 15 +++++ net/netfilter/nft_tunnel.c | 112 ++++++++++++++++++++++++++++++- 2 files changed, 126 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 3ee1198eeac1..357862d948de 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -1647,4 +1647,19 @@ enum nft_tunnel_key_attributes { }; #define NFTA_TUNNEL_KEY_MAX (__NFTA_TUNNEL_KEY_MAX - 1) +enum nft_tunnel_keys { + NFT_TUNNEL_PATH, + NFT_TUNNEL_ID, + __NFT_TUNNEL_MAX +}; +#define NFT_TUNNEL_MAX (__NFT_TUNNEL_MAX - 1) + +enum nft_tunnel_attributes { + NFTA_TUNNEL_UNSPEC, + NFTA_TUNNEL_KEY, + NFTA_TUNNEL_DREG, + __NFTA_TUNNEL_MAX +}; +#define NFTA_TUNNEL_MAX (__NFTA_TUNNEL_MAX - 1) + #endif /* _LINUX_NF_TABLES_H */ diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c index 715613d99c20..9332d7933dd5 100644 --- a/net/netfilter/nft_tunnel.c +++ b/net/netfilter/nft_tunnel.c @@ -12,6 +12,104 @@ #include #include +struct nft_tunnel { + enum nft_tunnel_keys key:8; + enum nft_registers dreg:8; +}; + +static void nft_tunnel_get_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + const struct nft_tunnel *priv = nft_expr_priv(expr); + u32 *dest = ®s->data[priv->dreg]; + struct ip_tunnel_info *tun_info; + + tun_info = skb_tunnel_info(pkt->skb); + + switch (priv->key) { + case NFT_TUNNEL_PATH: + nft_reg_store8(dest, !!tun_info); + break; + case NFT_TUNNEL_ID: + if (!tun_info) { + regs->verdict.code = NFT_BREAK; + return; + } + *dest = ntohl(tunnel_id_to_key32(tun_info->key.tun_id)); + break; + default: + WARN_ON(1); + regs->verdict.code = NFT_BREAK; + } +} + +static const struct nla_policy nft_tunnel_policy[NFTA_TUNNEL_MAX + 1] = { + [NFTA_TUNNEL_KEY] = { .type = NLA_U32 }, + [NFTA_TUNNEL_DREG] = { .type = NLA_U32 }, +}; + +static int nft_tunnel_get_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_tunnel *priv = nft_expr_priv(expr); + u32 len; + + if (!tb[NFTA_TUNNEL_KEY] && + !tb[NFTA_TUNNEL_DREG]) + return -EINVAL; + + priv->key = ntohl(nla_get_be32(tb[NFTA_TUNNEL_KEY])); + switch (priv->key) { + case NFT_TUNNEL_PATH: + len = sizeof(u8); + break; + case NFT_TUNNEL_ID: + len = sizeof(u32); + break; + default: + return -EOPNOTSUPP; + } + + priv->dreg = nft_parse_register(tb[NFTA_TUNNEL_DREG]); + + return nft_validate_register_store(ctx, priv->dreg, NULL, + NFT_DATA_VALUE, len); +} + +static int nft_tunnel_get_dump(struct sk_buff *skb, + const struct nft_expr *expr) +{ + const struct nft_tunnel *priv = nft_expr_priv(expr); + + if (nla_put_be32(skb, NFTA_TUNNEL_KEY, htonl(priv->key))) + goto nla_put_failure; + if (nft_dump_register(skb, NFTA_TUNNEL_DREG, priv->dreg)) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -1; +} + +static struct nft_expr_type nft_tunnel_type; +static const struct nft_expr_ops nft_tunnel_get_ops = { + .type = &nft_tunnel_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_tunnel)), + .eval = nft_tunnel_get_eval, + .init = nft_tunnel_get_init, + .dump = nft_tunnel_get_dump, +}; + +static struct nft_expr_type nft_tunnel_type __read_mostly = { + .name = "tunnel", + .ops = &nft_tunnel_get_ops, + .policy = nft_tunnel_policy, + .maxattr = NFTA_TUNNEL_MAX, + .owner = THIS_MODULE, +}; + struct nft_tunnel_opts { union { struct vxlan_metadata vxlan; @@ -442,12 +540,23 @@ static struct nft_object_type nft_tunnel_obj_type __read_mostly = { static int __init nft_tunnel_module_init(void) { - return nft_register_obj(&nft_tunnel_obj_type); + int err; + + err = nft_register_expr(&nft_tunnel_type); + if (err < 0) + return err; + + err = nft_register_obj(&nft_tunnel_obj_type); + if (err < 0) + nft_unregister_expr(&nft_tunnel_type); + + return err; } static void __exit nft_tunnel_module_exit(void) { nft_unregister_obj(&nft_tunnel_obj_type); + nft_unregister_expr(&nft_tunnel_type); } module_init(nft_tunnel_module_init); @@ -455,4 +564,5 @@ module_exit(nft_tunnel_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso "); +MODULE_ALIAS_NFT_EXPR("tunnel"); MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_TUNNEL); -- cgit v1.2.3 From 94276fa8a2a4c08ccb2e9d55e88b95dc972ccea3 Mon Sep 17 00:00:00 2001 From: Máté Eckl Date: Fri, 3 Aug 2018 13:36:13 +0200 Subject: netfilter: bridge: Expose nf_tables bridge hook priorities through uapi MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Netfilter exposes standard hook priorities in case of ipv4, ipv6 and arp but not in case of bridge. This patch exposes the hook priority values of the bridge family (which are different from the formerly mentioned) via uapi so that they can be used by user-space applications just like the others. Signed-off-by: Máté Eckl Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_bridge.h | 11 ----------- include/uapi/linux/netfilter_bridge.h | 11 +++++++++++ net/bridge/br_netfilter_hooks.c | 1 + net/bridge/netfilter/ebtable_filter.c | 1 + net/bridge/netfilter/ebtable_nat.c | 1 + 5 files changed, 14 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter_bridge.h b/include/linux/netfilter_bridge.h index b671fdfd212b..fa0686500970 100644 --- a/include/linux/netfilter_bridge.h +++ b/include/linux/netfilter_bridge.h @@ -5,17 +5,6 @@ #include #include -enum nf_br_hook_priorities { - NF_BR_PRI_FIRST = INT_MIN, - NF_BR_PRI_NAT_DST_BRIDGED = -300, - NF_BR_PRI_FILTER_BRIDGED = -200, - NF_BR_PRI_BRNF = 0, - NF_BR_PRI_NAT_DST_OTHER = 100, - NF_BR_PRI_FILTER_OTHER = 200, - NF_BR_PRI_NAT_SRC = 300, - NF_BR_PRI_LAST = INT_MAX, -}; - #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb); diff --git a/include/uapi/linux/netfilter_bridge.h b/include/uapi/linux/netfilter_bridge.h index 12fb77633f83..156ccd089df1 100644 --- a/include/uapi/linux/netfilter_bridge.h +++ b/include/uapi/linux/netfilter_bridge.h @@ -26,4 +26,15 @@ #define NF_BR_BROUTING 5 #define NF_BR_NUMHOOKS 6 +enum nf_br_hook_priorities { + NF_BR_PRI_FIRST = INT_MIN, + NF_BR_PRI_NAT_DST_BRIDGED = -300, + NF_BR_PRI_FILTER_BRIDGED = -200, + NF_BR_PRI_BRNF = 0, + NF_BR_PRI_NAT_DST_OTHER = 100, + NF_BR_PRI_FILTER_OTHER = 200, + NF_BR_PRI_NAT_SRC = 300, + NF_BR_PRI_LAST = INT_MAX, +}; + #endif /* _UAPI__LINUX_BRIDGE_NETFILTER_H */ diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 9b16eaf33819..6e0dc6bcd32a 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include #include diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c index c41da5fac84f..550324c516ee 100644 --- a/net/bridge/netfilter/ebtable_filter.c +++ b/net/bridge/netfilter/ebtable_filter.c @@ -9,6 +9,7 @@ */ #include +#include #include #define FILTER_VALID_HOOKS ((1 << NF_BR_LOCAL_IN) | (1 << NF_BR_FORWARD) | \ diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c index 08df7406ecb3..c0fb3ca518af 100644 --- a/net/bridge/netfilter/ebtable_nat.c +++ b/net/bridge/netfilter/ebtable_nat.c @@ -9,6 +9,7 @@ */ #include +#include #include #define NAT_VALID_HOOKS ((1 << NF_BR_PRE_ROUTING) | (1 << NF_BR_LOCAL_OUT) | \ -- cgit v1.2.3 From eb9950eb31f56e57582a61c92073336d04a26542 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Aug 2018 17:06:56 +0100 Subject: rxrpc: Push iov_iter up from rxrpc_kernel_recv_data() to caller Push iov_iter up from rxrpc_kernel_recv_data() to its caller to allow non-contiguous iovs to be passed down, thereby permitting file reading to be simplified in the AFS filesystem in a future patch. Signed-off-by: David Howells Signed-off-by: David S. Miller --- fs/afs/rxrpc.c | 28 +++++++++++++++++----------- include/net/af_rxrpc.h | 2 +- net/rxrpc/recvmsg.c | 33 +++++++++++---------------------- 3 files changed, 29 insertions(+), 34 deletions(-) (limited to 'include') diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index a1b18082991b..19db5f672a9d 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -346,7 +346,6 @@ long afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, struct rxrpc_call *rxcall; struct msghdr msg; struct kvec iov[1]; - size_t offset; s64 tx_total_len; int ret; @@ -433,10 +432,10 @@ error_do_abort: rxrpc_kernel_abort_call(call->net->socket, rxcall, RX_USER_ABORT, ret, "KSD"); } else { - offset = 0; - rxrpc_kernel_recv_data(call->net->socket, rxcall, NULL, - 0, &offset, false, &call->abort_code, - &call->service_id); + iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, NULL, 0, 0); + rxrpc_kernel_recv_data(call->net->socket, rxcall, + &msg.msg_iter, false, + &call->abort_code, &call->service_id); ac->abort_code = call->abort_code; ac->responded = true; } @@ -467,13 +466,14 @@ static void afs_deliver_to_call(struct afs_call *call) state == AFS_CALL_SV_AWAIT_ACK ) { if (state == AFS_CALL_SV_AWAIT_ACK) { - size_t offset = 0; + struct iov_iter iter; + + iov_iter_kvec(&iter, READ | ITER_KVEC, NULL, 0, 0); ret = rxrpc_kernel_recv_data(call->net->socket, - call->rxcall, - NULL, 0, &offset, false, + call->rxcall, &iter, false, &remote_abort, &call->service_id); - trace_afs_recv_data(call, 0, offset, false, ret); + trace_afs_recv_data(call, 0, 0, false, ret); if (ret == -EINPROGRESS || ret == -EAGAIN) return; @@ -894,6 +894,8 @@ int afs_extract_data(struct afs_call *call, void *buf, size_t count, bool want_more) { struct afs_net *net = call->net; + struct iov_iter iter; + struct kvec iov; enum afs_call_state state; u32 remote_abort = 0; int ret; @@ -903,10 +905,14 @@ int afs_extract_data(struct afs_call *call, void *buf, size_t count, ASSERTCMP(call->offset, <=, count); - ret = rxrpc_kernel_recv_data(net->socket, call->rxcall, - buf, count, &call->offset, + iov.iov_base = buf + call->offset; + iov.iov_len = count - call->offset; + iov_iter_kvec(&iter, ITER_KVEC | READ, &iov, 1, count - call->offset); + + ret = rxrpc_kernel_recv_data(net->socket, call->rxcall, &iter, want_more, &remote_abort, &call->service_id); + call->offset += (count - call->offset) - iov_iter_count(&iter); trace_afs_recv_data(call, count, call->offset, want_more, ret); if (ret == 0 || ret == -EAGAIN) return ret; diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h index 8ae8ee004258..f53edb3754bc 100644 --- a/include/net/af_rxrpc.h +++ b/include/net/af_rxrpc.h @@ -61,7 +61,7 @@ int rxrpc_kernel_send_data(struct socket *, struct rxrpc_call *, struct msghdr *, size_t, rxrpc_notify_end_tx_t); int rxrpc_kernel_recv_data(struct socket *, struct rxrpc_call *, - void *, size_t, size_t *, bool, u32 *, u16 *); + struct iov_iter *, bool, u32 *, u16 *); bool rxrpc_kernel_abort_call(struct socket *, struct rxrpc_call *, u32, int, const char *); void rxrpc_kernel_end_call(struct socket *, struct rxrpc_call *); diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index a57ea96c84ea..816b19a78809 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -611,9 +611,7 @@ wait_error: * rxrpc_kernel_recv_data - Allow a kernel service to receive data/info * @sock: The socket that the call exists on * @call: The call to send data through - * @buf: The buffer to receive into - * @size: The size of the buffer, including data already read - * @_offset: The running offset into the buffer. + * @iter: The buffer to receive into * @want_more: True if more data is expected to be read * @_abort: Where the abort code is stored if -ECONNABORTED is returned * @_service: Where to store the actual service ID (may be upgraded) @@ -626,39 +624,30 @@ wait_error: * Note that we may return -EAGAIN to drain empty packets at the end of the * data, even if we've already copied over the requested data. * - * This function adds the amount it transfers to *_offset, so this should be - * precleared as appropriate. Note that the amount remaining in the buffer is - * taken to be size - *_offset. - * * *_abort should also be initialised to 0. */ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call, - void *buf, size_t size, size_t *_offset, + struct iov_iter *iter, bool want_more, u32 *_abort, u16 *_service) { - struct iov_iter iter; - struct kvec iov; + size_t offset = 0; int ret; - _enter("{%d,%s},%zu/%zu,%d", + _enter("{%d,%s},%zu,%d", call->debug_id, rxrpc_call_states[call->state], - *_offset, size, want_more); + iov_iter_count(iter), want_more); - ASSERTCMP(*_offset, <=, size); ASSERTCMP(call->state, !=, RXRPC_CALL_SERVER_ACCEPTING); - iov.iov_base = buf + *_offset; - iov.iov_len = size - *_offset; - iov_iter_kvec(&iter, ITER_KVEC | READ, &iov, 1, size - *_offset); - mutex_lock(&call->user_mutex); switch (READ_ONCE(call->state)) { case RXRPC_CALL_CLIENT_RECV_REPLY: case RXRPC_CALL_SERVER_RECV_REQUEST: case RXRPC_CALL_SERVER_ACK_REQUEST: - ret = rxrpc_recvmsg_data(sock, call, NULL, &iter, size, 0, - _offset); + ret = rxrpc_recvmsg_data(sock, call, NULL, iter, + iov_iter_count(iter), 0, + &offset); if (ret < 0) goto out; @@ -667,7 +656,7 @@ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call, * full buffer or have been given -EAGAIN. */ if (ret == 1) { - if (*_offset < size) + if (iov_iter_count(iter) > 0) goto short_data; if (!want_more) goto read_phase_complete; @@ -704,7 +693,7 @@ out: if (_service) *_service = call->service_id; mutex_unlock(&call->user_mutex); - _leave(" = %d [%zu,%d]", ret, *_offset, *_abort); + _leave(" = %d [%zu,%d]", ret, iov_iter_count(iter), *_abort); return ret; short_data: @@ -720,7 +709,7 @@ call_complete: ret = call->error; if (call->completion == RXRPC_CALL_SUCCEEDED) { ret = 1; - if (size > 0) + if (iov_iter_count(iter) > 0) ret = -ECONNRESET; } goto out; -- cgit v1.2.3 From c2b6d621c4ffe9936adf7a55c8b1c769672c306f Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 28 Jun 2018 15:53:17 -0400 Subject: new primitive: discard_new_inode() We don't want open-by-handle picking half-set-up in-core struct inode from e.g. mkdir() having failed halfway through. In other words, we don't want such inodes returned by iget_locked() on their way to extinction. However, we can't just have them unhashed - otherwise open-by-handle immediately *after* that would've ended up creating a new in-core inode over the on-disk one that is in process of being freed right under us. Solution: new flag (I_CREATING) set by insert_inode_locked() and removed by unlock_new_inode() and a new primitive (discard_new_inode()) to be used by such halfway-through-setup failure exits instead of unlock_new_inode() / iput() combinations. That primitive unlocks new inode, but leaves I_CREATING in place. iget_locked() treats finding an I_CREATING inode as failure (-ESTALE, once we sort out the error propagation). insert_inode_locked() treats the same as instant -EBUSY. ilookup() treats those as icache miss. [Fix by Dan Carpenter folded in] Signed-off-by: Al Viro --- fs/dcache.c | 2 +- fs/inode.c | 45 +++++++++++++++++++++++++++++++++++++++++---- include/linux/fs.h | 6 +++++- 3 files changed, 47 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/fs/dcache.c b/fs/dcache.c index a7d9e7a4c283..11b753d29409 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -1892,7 +1892,7 @@ void d_instantiate_new(struct dentry *entry, struct inode *inode) spin_lock(&inode->i_lock); __d_instantiate(entry, inode); WARN_ON(!(inode->i_state & I_NEW)); - inode->i_state &= ~I_NEW; + inode->i_state &= ~I_NEW & ~I_CREATING; smp_mb(); wake_up_bit(&inode->i_state, __I_NEW); spin_unlock(&inode->i_lock); diff --git a/fs/inode.c b/fs/inode.c index 2c300e981796..6cd2e7ba9f4d 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -804,6 +804,10 @@ repeat: __wait_on_freeing_inode(inode); goto repeat; } + if (unlikely(inode->i_state & I_CREATING)) { + spin_unlock(&inode->i_lock); + return ERR_PTR(-ESTALE); + } __iget(inode); spin_unlock(&inode->i_lock); return inode; @@ -831,6 +835,10 @@ repeat: __wait_on_freeing_inode(inode); goto repeat; } + if (unlikely(inode->i_state & I_CREATING)) { + spin_unlock(&inode->i_lock); + return ERR_PTR(-ESTALE); + } __iget(inode); spin_unlock(&inode->i_lock); return inode; @@ -961,13 +969,26 @@ void unlock_new_inode(struct inode *inode) lockdep_annotate_inode_mutex_key(inode); spin_lock(&inode->i_lock); WARN_ON(!(inode->i_state & I_NEW)); - inode->i_state &= ~I_NEW; + inode->i_state &= ~I_NEW & ~I_CREATING; smp_mb(); wake_up_bit(&inode->i_state, __I_NEW); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(unlock_new_inode); +void discard_new_inode(struct inode *inode) +{ + lockdep_annotate_inode_mutex_key(inode); + spin_lock(&inode->i_lock); + WARN_ON(!(inode->i_state & I_NEW)); + inode->i_state &= ~I_NEW; + smp_mb(); + wake_up_bit(&inode->i_state, __I_NEW); + spin_unlock(&inode->i_lock); + iput(inode); +} +EXPORT_SYMBOL(discard_new_inode); + /** * lock_two_nondirectories - take two i_mutexes on non-directory objects * @@ -1039,6 +1060,8 @@ again: * Use the old inode instead of the preallocated one. */ spin_unlock(&inode_hash_lock); + if (IS_ERR(old)) + return NULL; wait_on_inode(old); if (unlikely(inode_unhashed(old))) { iput(old); @@ -1128,6 +1151,8 @@ again: inode = find_inode_fast(sb, head, ino); spin_unlock(&inode_hash_lock); if (inode) { + if (IS_ERR(inode)) + return NULL; wait_on_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); @@ -1165,6 +1190,8 @@ again: */ spin_unlock(&inode_hash_lock); destroy_inode(inode); + if (IS_ERR(old)) + return NULL; inode = old; wait_on_inode(inode); if (unlikely(inode_unhashed(inode))) { @@ -1282,7 +1309,7 @@ struct inode *ilookup5_nowait(struct super_block *sb, unsigned long hashval, inode = find_inode(sb, head, test, data); spin_unlock(&inode_hash_lock); - return inode; + return IS_ERR(inode) ? NULL : inode; } EXPORT_SYMBOL(ilookup5_nowait); @@ -1338,6 +1365,8 @@ again: spin_unlock(&inode_hash_lock); if (inode) { + if (IS_ERR(inode)) + return NULL; wait_on_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); @@ -1421,12 +1450,17 @@ int insert_inode_locked(struct inode *inode) } if (likely(!old)) { spin_lock(&inode->i_lock); - inode->i_state |= I_NEW; + inode->i_state |= I_NEW | I_CREATING; hlist_add_head(&inode->i_hash, head); spin_unlock(&inode->i_lock); spin_unlock(&inode_hash_lock); return 0; } + if (unlikely(old->i_state & I_CREATING)) { + spin_unlock(&old->i_lock); + spin_unlock(&inode_hash_lock); + return -EBUSY; + } __iget(old); spin_unlock(&old->i_lock); spin_unlock(&inode_hash_lock); @@ -1443,7 +1477,10 @@ EXPORT_SYMBOL(insert_inode_locked); int insert_inode_locked4(struct inode *inode, unsigned long hashval, int (*test)(struct inode *, void *), void *data) { - struct inode *old = inode_insert5(inode, hashval, test, NULL, data); + struct inode *old; + + inode->i_state |= I_CREATING; + old = inode_insert5(inode, hashval, test, NULL, data); if (old != inode) { iput(old); diff --git a/include/linux/fs.h b/include/linux/fs.h index 5c91108846db..a42600565925 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2016,6 +2016,8 @@ static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) * I_OVL_INUSE Used by overlayfs to get exclusive ownership on upper * and work dirs among overlayfs mounts. * + * I_CREATING New object's inode in the middle of setting up. + * * Q: What is the difference between I_WILL_FREE and I_FREEING? */ #define I_DIRTY_SYNC (1 << 0) @@ -2036,7 +2038,8 @@ static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) #define __I_DIRTY_TIME_EXPIRED 12 #define I_DIRTY_TIME_EXPIRED (1 << __I_DIRTY_TIME_EXPIRED) #define I_WB_SWITCH (1 << 13) -#define I_OVL_INUSE (1 << 14) +#define I_OVL_INUSE (1 << 14) +#define I_CREATING (1 << 15) #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) @@ -2919,6 +2922,7 @@ extern void lockdep_annotate_inode_mutex_key(struct inode *inode); static inline void lockdep_annotate_inode_mutex_key(struct inode *inode) { }; #endif extern void unlock_new_inode(struct inode *); +extern void discard_new_inode(struct inode *); extern unsigned int get_next_ino(void); extern void evict_inodes(struct super_block *sb); -- cgit v1.2.3 From e90561d40f830f1266d9531ae95eae8252dd8fa1 Mon Sep 17 00:00:00 2001 From: Kieran Bingham Date: Fri, 3 Aug 2018 07:37:29 -0400 Subject: media: vsp1: Support Interlaced display pipelines Calculate the top and bottom fields for the interlaced frames and utilise the extended display list command feature to implement the auto-field operations. This allows the DU to update the VSP2 registers dynamically based upon the currently processing field. Signed-off-by: Kieran Bingham Signed-off-by: Laurent Pinchart Signed-off-by: Mauro Carvalho Chehab --- drivers/media/platform/vsp1/vsp1_dl.c | 10 +++++ drivers/media/platform/vsp1/vsp1_drm.c | 6 ++- drivers/media/platform/vsp1/vsp1_pipe.h | 2 + drivers/media/platform/vsp1/vsp1_regs.h | 3 ++ drivers/media/platform/vsp1/vsp1_rpf.c | 72 +++++++++++++++++++++++++++++++-- include/media/vsp1.h | 2 + 6 files changed, 90 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/media/platform/vsp1/vsp1_dl.c b/drivers/media/platform/vsp1/vsp1_dl.c index 6021c43c53b4..9255b5ee2cb8 100644 --- a/drivers/media/platform/vsp1/vsp1_dl.c +++ b/drivers/media/platform/vsp1/vsp1_dl.c @@ -947,6 +947,8 @@ void vsp1_dl_list_commit(struct vsp1_dl_list *dl, bool internal) */ unsigned int vsp1_dlm_irq_frame_end(struct vsp1_dl_manager *dlm) { + struct vsp1_device *vsp1 = dlm->vsp1; + u32 status = vsp1_read(vsp1, VI6_STATUS); unsigned int flags = 0; spin_lock(&dlm->lock); @@ -971,6 +973,14 @@ unsigned int vsp1_dlm_irq_frame_end(struct vsp1_dl_manager *dlm) if (vsp1_dl_list_hw_update_pending(dlm)) goto done; + /* + * Progressive streams report only TOP fields. If we have a BOTTOM + * field, we are interlaced, and expect the frame to complete on the + * next frame end interrupt. + */ + if (status & VI6_STATUS_FLD_STD(dlm->index)) + goto done; + /* * The device starts processing the queued display list right after the * frame end interrupt. The display list thus becomes active. diff --git a/drivers/media/platform/vsp1/vsp1_drm.c b/drivers/media/platform/vsp1/vsp1_drm.c index a16856856789..87dc3ddbe2d3 100644 --- a/drivers/media/platform/vsp1/vsp1_drm.c +++ b/drivers/media/platform/vsp1/vsp1_drm.c @@ -670,9 +670,11 @@ int vsp1_du_setup_lif(struct device *dev, unsigned int pipe_index, drm_pipe->width = cfg->width; drm_pipe->height = cfg->height; + pipe->interlaced = cfg->interlaced; - dev_dbg(vsp1->dev, "%s: configuring LIF%u with format %ux%u\n", - __func__, pipe_index, cfg->width, cfg->height); + dev_dbg(vsp1->dev, "%s: configuring LIF%u with format %ux%u%s\n", + __func__, pipe_index, cfg->width, cfg->height, + pipe->interlaced ? "i" : ""); mutex_lock(&vsp1->drm->lock); diff --git a/drivers/media/platform/vsp1/vsp1_pipe.h b/drivers/media/platform/vsp1/vsp1_pipe.h index 743d8f0db45c..ae646c9ef337 100644 --- a/drivers/media/platform/vsp1/vsp1_pipe.h +++ b/drivers/media/platform/vsp1/vsp1_pipe.h @@ -104,6 +104,7 @@ struct vsp1_partition { * @entities: list of entities in the pipeline * @stream_config: cached stream configuration for video pipelines * @configured: when false the @stream_config shall be written to the hardware + * @interlaced: True when the pipeline is configured in interlaced mode * @partitions: The number of partitions used to process one frame * @partition: The current partition for configuration to process * @part_table: The pre-calculated partitions used by the pipeline @@ -142,6 +143,7 @@ struct vsp1_pipeline { struct vsp1_dl_body *stream_config; bool configured; + bool interlaced; unsigned int partitions; struct vsp1_partition *partition; diff --git a/drivers/media/platform/vsp1/vsp1_regs.h b/drivers/media/platform/vsp1/vsp1_regs.h index 5ea9f9070cf3..3738ff2f7b85 100644 --- a/drivers/media/platform/vsp1/vsp1_regs.h +++ b/drivers/media/platform/vsp1/vsp1_regs.h @@ -28,6 +28,7 @@ #define VI6_SRESET_SRTS(n) (1 << (n)) #define VI6_STATUS 0x0038 +#define VI6_STATUS_FLD_STD(n) (1 << ((n) + 28)) #define VI6_STATUS_SYS_ACT(n) (1 << ((n) + 8)) #define VI6_WPF_IRQ_ENB(n) (0x0048 + (n) * 12) @@ -80,6 +81,8 @@ #define VI6_DL_EXT_CTRL_EXPRI (1 << 4) #define VI6_DL_EXT_CTRL_EXT (1 << 0) +#define VI6_DL_EXT_AUTOFLD_INT BIT(0) + #define VI6_DL_BODY_SIZE 0x0120 #define VI6_DL_BODY_SIZE_UPD (1 << 24) #define VI6_DL_BODY_SIZE_BS_MASK (0x1ffff << 0) diff --git a/drivers/media/platform/vsp1/vsp1_rpf.c b/drivers/media/platform/vsp1/vsp1_rpf.c index 69e5fe6e6b50..f8005b60b9d2 100644 --- a/drivers/media/platform/vsp1/vsp1_rpf.c +++ b/drivers/media/platform/vsp1/vsp1_rpf.c @@ -20,6 +20,18 @@ #define RPF_MAX_WIDTH 8190 #define RPF_MAX_HEIGHT 8190 +/* Pre extended display list command data structure. */ +struct vsp1_extcmd_auto_fld_body { + u32 top_y0; + u32 bottom_y0; + u32 top_c0; + u32 bottom_c0; + u32 top_c1; + u32 bottom_c1; + u32 reserved0; + u32 reserved1; +} __packed; + /* ----------------------------------------------------------------------------- * Device Access */ @@ -64,6 +76,14 @@ static void rpf_configure_stream(struct vsp1_entity *entity, pstride |= format->plane_fmt[1].bytesperline << VI6_RPF_SRCM_PSTRIDE_C_SHIFT; + /* + * pstride has both STRIDE_Y and STRIDE_C, but multiplying the whole + * of pstride by 2 is conveniently OK here as we are multiplying both + * values. + */ + if (pipe->interlaced) + pstride *= 2; + vsp1_rpf_write(rpf, dlb, VI6_RPF_SRCM_PSTRIDE, pstride); /* Format */ @@ -100,6 +120,9 @@ static void rpf_configure_stream(struct vsp1_entity *entity, top = compose->top; } + if (pipe->interlaced) + top /= 2; + vsp1_rpf_write(rpf, dlb, VI6_RPF_LOC, (left << VI6_RPF_LOC_HCOORD_SHIFT) | (top << VI6_RPF_LOC_VCOORD_SHIFT)); @@ -169,6 +192,36 @@ static void rpf_configure_stream(struct vsp1_entity *entity, } +static void vsp1_rpf_configure_autofld(struct vsp1_rwpf *rpf, + struct vsp1_dl_list *dl) +{ + const struct v4l2_pix_format_mplane *format = &rpf->format; + struct vsp1_dl_ext_cmd *cmd; + struct vsp1_extcmd_auto_fld_body *auto_fld; + u32 offset_y, offset_c; + + cmd = vsp1_dl_get_pre_cmd(dl); + if (WARN_ONCE(!cmd, "Failed to obtain an autofld cmd")) + return; + + /* Re-index our auto_fld to match the current RPF. */ + auto_fld = cmd->data; + auto_fld = &auto_fld[rpf->entity.index]; + + auto_fld->top_y0 = rpf->mem.addr[0]; + auto_fld->top_c0 = rpf->mem.addr[1]; + auto_fld->top_c1 = rpf->mem.addr[2]; + + offset_y = format->plane_fmt[0].bytesperline; + offset_c = format->plane_fmt[1].bytesperline; + + auto_fld->bottom_y0 = rpf->mem.addr[0] + offset_y; + auto_fld->bottom_c0 = rpf->mem.addr[1] + offset_c; + auto_fld->bottom_c1 = rpf->mem.addr[2] + offset_c; + + cmd->flags |= VI6_DL_EXT_AUTOFLD_INT | BIT(16 + rpf->entity.index); +} + static void rpf_configure_frame(struct vsp1_entity *entity, struct vsp1_pipeline *pipe, struct vsp1_dl_list *dl, @@ -221,6 +274,11 @@ static void rpf_configure_partition(struct vsp1_entity *entity, crop.left += pipe->partition->rpf.left; } + if (pipe->interlaced) { + crop.height = round_down(crop.height / 2, fmtinfo->vsub); + crop.top = round_down(crop.top / 2, fmtinfo->vsub); + } + vsp1_rpf_write(rpf, dlb, VI6_RPF_SRC_BSIZE, (crop.width << VI6_RPF_SRC_BSIZE_BHSIZE_SHIFT) | (crop.height << VI6_RPF_SRC_BSIZE_BVSIZE_SHIFT)); @@ -249,9 +307,17 @@ static void rpf_configure_partition(struct vsp1_entity *entity, fmtinfo->swap_uv) swap(mem.addr[1], mem.addr[2]); - vsp1_rpf_write(rpf, dlb, VI6_RPF_SRCM_ADDR_Y, mem.addr[0]); - vsp1_rpf_write(rpf, dlb, VI6_RPF_SRCM_ADDR_C0, mem.addr[1]); - vsp1_rpf_write(rpf, dlb, VI6_RPF_SRCM_ADDR_C1, mem.addr[2]); + /* + * Interlaced pipelines will use the extended pre-cmd to process + * SRCM_ADDR_{Y,C0,C1} + */ + if (pipe->interlaced) { + vsp1_rpf_configure_autofld(rpf, dl); + } else { + vsp1_rpf_write(rpf, dlb, VI6_RPF_SRCM_ADDR_Y, mem.addr[0]); + vsp1_rpf_write(rpf, dlb, VI6_RPF_SRCM_ADDR_C0, mem.addr[1]); + vsp1_rpf_write(rpf, dlb, VI6_RPF_SRCM_ADDR_C1, mem.addr[2]); + } } static void rpf_partition(struct vsp1_entity *entity, diff --git a/include/media/vsp1.h b/include/media/vsp1.h index 678c24de1ac6..3093b9cb9067 100644 --- a/include/media/vsp1.h +++ b/include/media/vsp1.h @@ -25,6 +25,7 @@ int vsp1_du_init(struct device *dev); * struct vsp1_du_lif_config - VSP LIF configuration * @width: output frame width * @height: output frame height + * @interlaced: true for interlaced pipelines * @callback: frame completion callback function (optional). When a callback * is provided, the VSP driver guarantees that it will be called once * and only once for each vsp1_du_atomic_flush() call. @@ -33,6 +34,7 @@ int vsp1_du_init(struct device *dev); struct vsp1_du_lif_config { unsigned int width; unsigned int height; + bool interlaced; void (*callback)(void *data, bool completed, u32 crc); void *callback_data; -- cgit v1.2.3 From 5bef915104f32c9d0bb5df6e86a98e31cb524e9a Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 29 Jun 2018 19:36:57 -0400 Subject: new helper: inode_fake_hash() open-coded in a quite a few places... Signed-off-by: Al Viro --- fs/hfs/inode.c | 2 +- fs/jfs/jfs_imap.c | 8 +------- fs/jfs/super.c | 2 +- fs/xfs/xfs_iops.c | 2 +- include/linux/fs.h | 11 +++++++++++ 5 files changed, 15 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index 2a16111d312f..a2dfa1b2a89c 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -541,7 +541,7 @@ static struct dentry *hfs_file_lookup(struct inode *dir, struct dentry *dentry, HFS_I(inode)->rsrc_inode = dir; HFS_I(dir)->rsrc_inode = inode; igrab(dir); - hlist_add_fake(&inode->i_hash); + inode_fake_hash(inode); mark_inode_dirty(inode); dont_mount(dentry); out: diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c index f36ef68905a7..93e8c590ff5c 100644 --- a/fs/jfs/jfs_imap.c +++ b/fs/jfs/jfs_imap.c @@ -491,13 +491,7 @@ struct inode *diReadSpecial(struct super_block *sb, ino_t inum, int secondary) /* release the page */ release_metapage(mp); - /* - * __mark_inode_dirty expects inodes to be hashed. Since we don't - * want special inodes in the fileset inode space, we make them - * appear hashed, but do not put on any lists. hlist_del() - * will work fine and require no locking. - */ - hlist_add_fake(&ip->i_hash); + inode_fake_hash(ip); return (ip); } diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 1b9264fd54b6..5403ece57dba 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -581,7 +581,7 @@ static int jfs_fill_super(struct super_block *sb, void *data, int silent) inode->i_ino = 0; inode->i_size = i_size_read(sb->s_bdev->bd_inode); inode->i_mapping->a_ops = &jfs_metapage_aops; - hlist_add_fake(&inode->i_hash); + inode_fake_hash(inode); mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS); sbi->direct_inode = inode; diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 0fa29f39d658..3a75de777843 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -1253,7 +1253,7 @@ xfs_setup_inode( inode_sb_list_add(inode); /* make the inode look hashed for the writeback code */ - hlist_add_fake(&inode->i_hash); + inode_fake_hash(inode); inode->i_uid = xfs_uid_to_kuid(ip->i_d.di_uid); inode->i_gid = xfs_gid_to_kgid(ip->i_d.di_gid); diff --git a/include/linux/fs.h b/include/linux/fs.h index a42600565925..43941e230e2b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -684,6 +684,17 @@ static inline int inode_unhashed(struct inode *inode) return hlist_unhashed(&inode->i_hash); } +/* + * __mark_inode_dirty expects inodes to be hashed. Since we don't + * want special inodes in the fileset inode space, we make them + * appear hashed, but do not put on any lists. hlist_del() + * will work fine and require no locking. + */ +static inline void inode_fake_hash(struct inode *inode) +{ + hlist_add_fake(&inode->i_hash); +} + /* * inode->i_mutex nesting subclasses for the lock validator: * -- cgit v1.2.3 From 31ba191bf5ab2975c1955f1adf771a5a0b57afaa Mon Sep 17 00:00:00 2001 From: zhong jiang Date: Fri, 3 Aug 2018 14:53:15 +0800 Subject: include/net/bond_3ad: Simplify the code by using the ARRAY_SIZE We prefer to ARRAY_SIZE rather than the open code to calculate size. Signed-off-by: zhong jiang Signed-off-by: David S. Miller --- include/net/bond_3ad.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h index f358ad5e4214..fc3111515f5c 100644 --- a/include/net/bond_3ad.h +++ b/include/net/bond_3ad.h @@ -283,7 +283,7 @@ static inline const char *bond_3ad_churn_desc(churn_state_t state) "none", "unknown" }; - int max_size = sizeof(churn_description) / sizeof(churn_description[0]); + int max_size = ARRAY_SIZE(churn_description); if (state >= max_size) state = max_size - 1; -- cgit v1.2.3 From d89d41556141a527030a15233135ba622ba3350d Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Sat, 4 Aug 2018 14:20:40 -0700 Subject: ethtool: Remove trailing semicolon for static inline Android's header sanitization tool chokes on static inline functions having a trailing semicolon, leading to an incorrectly parsed header file. While the tool should obviously be fixed, also fix the header files for the two affected functions: ethtool_get_flow_spec_ring() and ethtool_get_flow_spec_ring_vf(). Fixes: 8cf6f497de40 ("ethtool: Add helper routines to pass vf to rx_flow_spec") Reporetd-by: Blair Prescott Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/uapi/linux/ethtool.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 7363f18e65a5..813282cc8af6 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -902,13 +902,13 @@ struct ethtool_rx_flow_spec { static inline __u64 ethtool_get_flow_spec_ring(__u64 ring_cookie) { return ETHTOOL_RX_FLOW_SPEC_RING & ring_cookie; -}; +} static inline __u64 ethtool_get_flow_spec_ring_vf(__u64 ring_cookie) { return (ETHTOOL_RX_FLOW_SPEC_RING_VF & ring_cookie) >> ETHTOOL_RX_FLOW_SPEC_RING_VF_OFF; -}; +} /** * struct ethtool_rxnfc - command to get or set RX flow classification rules -- cgit v1.2.3 From 91305f2812624c0cf7ccbb44133b66d3b24676e4 Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Wed, 1 Aug 2018 18:05:54 +0800 Subject: ptp_qoriq: support automatic configuration for ptp timer This patch is to support automatic configuration for ptp timer. If required ptp dts properties are not provided, driver could try to calculate a set of default configurations to initialize the ptp timer. This makes the driver work for many boards which don't have the required ptp dts properties in current kernel. Also the users could set dts properties by themselves according to their requirement. Signed-off-by: Yangbo Lu Signed-off-by: David S. Miller --- drivers/ptp/ptp_qoriq.c | 111 ++++++++++++++++++++++++++++++++++++++++-- include/linux/fsl/ptp_qoriq.h | 6 ++- 2 files changed, 113 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/ptp/ptp_qoriq.c b/drivers/ptp/ptp_qoriq.c index a14c317b5a38..095c18532dc7 100644 --- a/drivers/ptp/ptp_qoriq.c +++ b/drivers/ptp/ptp_qoriq.c @@ -29,6 +29,7 @@ #include #include #include +#include #include @@ -317,6 +318,105 @@ static const struct ptp_clock_info ptp_qoriq_caps = { .enable = ptp_qoriq_enable, }; +/** + * qoriq_ptp_nominal_freq - calculate nominal frequency according to + * reference clock frequency + * + * @clk_src: reference clock frequency + * + * The nominal frequency is the desired clock frequency. + * It should be less than the reference clock frequency. + * It should be a factor of 1000MHz. + * + * Return the nominal frequency + */ +static u32 qoriq_ptp_nominal_freq(u32 clk_src) +{ + u32 remainder = 0; + + clk_src /= 1000000; + remainder = clk_src % 100; + if (remainder) { + clk_src -= remainder; + clk_src += 100; + } + + do { + clk_src -= 100; + + } while (1000 % clk_src); + + return clk_src * 1000000; +} + +/** + * qoriq_ptp_auto_config - calculate a set of default configurations + * + * @qoriq_ptp: pointer to qoriq_ptp + * @node: pointer to device_node + * + * If below dts properties are not provided, this function will be + * called to calculate a set of default configurations for them. + * "fsl,tclk-period" + * "fsl,tmr-prsc" + * "fsl,tmr-add" + * "fsl,tmr-fiper1" + * "fsl,tmr-fiper2" + * "fsl,max-adj" + * + * Return 0 if success + */ +static int qoriq_ptp_auto_config(struct qoriq_ptp *qoriq_ptp, + struct device_node *node) +{ + struct clk *clk; + u64 freq_comp; + u64 max_adj; + u32 nominal_freq; + u32 clk_src = 0; + + qoriq_ptp->cksel = DEFAULT_CKSEL; + + clk = of_clk_get(node, 0); + if (!IS_ERR(clk)) { + clk_src = clk_get_rate(clk); + clk_put(clk); + } + + if (clk_src <= 100000000UL) { + pr_err("error reference clock value, or lower than 100MHz\n"); + return -EINVAL; + } + + nominal_freq = qoriq_ptp_nominal_freq(clk_src); + if (!nominal_freq) + return -EINVAL; + + qoriq_ptp->tclk_period = 1000000000UL / nominal_freq; + qoriq_ptp->tmr_prsc = DEFAULT_TMR_PRSC; + + /* Calculate initial frequency compensation value for TMR_ADD register. + * freq_comp = ceil(2^32 / freq_ratio) + * freq_ratio = reference_clock_freq / nominal_freq + */ + freq_comp = ((u64)1 << 32) * nominal_freq; + if (do_div(freq_comp, clk_src)) + freq_comp++; + + qoriq_ptp->tmr_add = freq_comp; + qoriq_ptp->tmr_fiper1 = DEFAULT_FIPER1_PERIOD - qoriq_ptp->tclk_period; + qoriq_ptp->tmr_fiper2 = DEFAULT_FIPER2_PERIOD - qoriq_ptp->tclk_period; + + /* max_adj = 1000000000 * (freq_ratio - 1.0) - 1 + * freq_ratio = reference_clock_freq / nominal_freq + */ + max_adj = 1000000000ULL * (clk_src - nominal_freq); + max_adj = max_adj / nominal_freq - 1; + qoriq_ptp->caps.max_adj = max_adj; + + return 0; +} + static int qoriq_ptp_probe(struct platform_device *dev) { struct device_node *node = dev->dev.of_node; @@ -332,7 +432,7 @@ static int qoriq_ptp_probe(struct platform_device *dev) if (!qoriq_ptp) goto no_memory; - err = -ENODEV; + err = -EINVAL; qoriq_ptp->caps = ptp_qoriq_caps; @@ -351,10 +451,14 @@ static int qoriq_ptp_probe(struct platform_device *dev) "fsl,tmr-fiper2", &qoriq_ptp->tmr_fiper2) || of_property_read_u32(node, "fsl,max-adj", &qoriq_ptp->caps.max_adj)) { - pr_err("device tree node missing required elements\n"); - goto no_node; + pr_warn("device tree node missing required elements, try automatic configuration\n"); + + if (qoriq_ptp_auto_config(qoriq_ptp, node)) + goto no_config; } + err = -ENODEV; + qoriq_ptp->irq = platform_get_irq(dev, 0); if (qoriq_ptp->irq < 0) { @@ -436,6 +540,7 @@ no_ioremap: release_resource(qoriq_ptp->rsrc); no_resource: free_irq(qoriq_ptp->irq, qoriq_ptp); +no_config: no_node: kfree(qoriq_ptp); no_memory: diff --git a/include/linux/fsl/ptp_qoriq.h b/include/linux/fsl/ptp_qoriq.h index dc3dac40f069..c1f003aadcce 100644 --- a/include/linux/fsl/ptp_qoriq.h +++ b/include/linux/fsl/ptp_qoriq.h @@ -127,9 +127,13 @@ struct qoriq_ptp_registers { #define DRIVER "ptp_qoriq" -#define DEFAULT_CKSEL 1 #define N_EXT_TS 2 +#define DEFAULT_CKSEL 1 +#define DEFAULT_TMR_PRSC 2 +#define DEFAULT_FIPER1_PERIOD 1000000000 +#define DEFAULT_FIPER2_PERIOD 100000 + struct qoriq_ptp { void __iomem *base; struct qoriq_ptp_registers regs; -- cgit v1.2.3 From 7969e5c40dfd04799d4341f1b7cd266b6e47f227 Mon Sep 17 00:00:00 2001 From: Peter Oskolkov Date: Thu, 2 Aug 2018 23:34:37 +0000 Subject: ip: discard IPv4 datagrams with overlapping segments. This behavior is required in IPv6, and there is little need to tolerate overlapping fragments in IPv4. This change simplifies the code and eliminates potential DDoS attack vectors. Tested: ran ip_defrag selftest (not yet available uptream). Suggested-by: David S. Miller Signed-off-by: Peter Oskolkov Signed-off-by: Eric Dumazet Cc: Florian Westphal Acked-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/uapi/linux/snmp.h | 1 + net/ipv4/ip_fragment.c | 75 ++++++++++++----------------------------------- net/ipv4/proc.c | 1 + 3 files changed, 21 insertions(+), 56 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index e5ebc83827ab..f80135e5feaa 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -56,6 +56,7 @@ enum IPSTATS_MIB_ECT1PKTS, /* InECT1Pkts */ IPSTATS_MIB_ECT0PKTS, /* InECT0Pkts */ IPSTATS_MIB_CEPKTS, /* InCEPkts */ + IPSTATS_MIB_REASM_OVERLAPS, /* ReasmOverlaps */ __IPSTATS_MIB_MAX }; diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index d14d741fb05e..960bf5eab59f 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -277,6 +277,7 @@ static int ip_frag_reinit(struct ipq *qp) /* Add new segment to existing queue. */ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) { + struct net *net = container_of(qp->q.net, struct net, ipv4.frags); struct sk_buff *prev, *next; struct net_device *dev; unsigned int fragsize; @@ -357,65 +358,23 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) } found: - /* We found where to put this one. Check for overlap with - * preceding fragment, and, if needed, align things so that - * any overlaps are eliminated. + /* RFC5722, Section 4, amended by Errata ID : 3089 + * When reassembling an IPv6 datagram, if + * one or more its constituent fragments is determined to be an + * overlapping fragment, the entire datagram (and any constituent + * fragments) MUST be silently discarded. + * + * We do the same here for IPv4. */ - if (prev) { - int i = (prev->ip_defrag_offset + prev->len) - offset; - if (i > 0) { - offset += i; - err = -EINVAL; - if (end <= offset) - goto err; - err = -ENOMEM; - if (!pskb_pull(skb, i)) - goto err; - if (skb->ip_summed != CHECKSUM_UNNECESSARY) - skb->ip_summed = CHECKSUM_NONE; - } - } + /* Is there an overlap with the previous fragment? */ + if (prev && + (prev->ip_defrag_offset + prev->len) > offset) + goto discard_qp; - err = -ENOMEM; - - while (next && next->ip_defrag_offset < end) { - int i = end - next->ip_defrag_offset; /* overlap is 'i' bytes */ - - if (i < next->len) { - int delta = -next->truesize; - - /* Eat head of the next overlapped fragment - * and leave the loop. The next ones cannot overlap. - */ - if (!pskb_pull(next, i)) - goto err; - delta += next->truesize; - if (delta) - add_frag_mem_limit(qp->q.net, delta); - next->ip_defrag_offset += i; - qp->q.meat -= i; - if (next->ip_summed != CHECKSUM_UNNECESSARY) - next->ip_summed = CHECKSUM_NONE; - break; - } else { - struct sk_buff *free_it = next; - - /* Old fragment is completely overridden with - * new one drop it. - */ - next = next->next; - - if (prev) - prev->next = next; - else - qp->q.fragments = next; - - qp->q.meat -= free_it->len; - sub_frag_mem_limit(qp->q.net, free_it->truesize); - kfree_skb(free_it); - } - } + /* Is there an overlap with the next fragment? */ + if (next && next->ip_defrag_offset < end) + goto discard_qp; /* Note : skb->ip_defrag_offset and skb->dev share the same location */ dev = skb->dev; @@ -463,6 +422,10 @@ found: skb_dst_drop(skb); return -EINPROGRESS; +discard_qp: + inet_frag_kill(&qp->q); + err = -EINVAL; + __IP_INC_STATS(net, IPSTATS_MIB_REASM_OVERLAPS); err: kfree_skb(skb); return err; diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index b46e4cf9a55a..70289682a670 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -119,6 +119,7 @@ static const struct snmp_mib snmp4_ipextstats_list[] = { SNMP_MIB_ITEM("InECT1Pkts", IPSTATS_MIB_ECT1PKTS), SNMP_MIB_ITEM("InECT0Pkts", IPSTATS_MIB_ECT0PKTS), SNMP_MIB_ITEM("InCEPkts", IPSTATS_MIB_CEPKTS), + SNMP_MIB_ITEM("ReasmOverlaps", IPSTATS_MIB_REASM_OVERLAPS), SNMP_MIB_SENTINEL }; -- cgit v1.2.3 From 385114dec8a49b5e5945e77ba7de6356106713f4 Mon Sep 17 00:00:00 2001 From: Peter Oskolkov Date: Thu, 2 Aug 2018 23:34:38 +0000 Subject: net: modify skb_rbtree_purge to return the truesize of all purged skbs. Tested: see the next patch is the series. Suggested-by: Eric Dumazet Signed-off-by: Peter Oskolkov Signed-off-by: Eric Dumazet Cc: Florian Westphal Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 +- net/core/skbuff.c | 6 +++++- 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index fd3cb1b247df..47848367c816 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2585,7 +2585,7 @@ static inline void __skb_queue_purge(struct sk_buff_head *list) kfree_skb(skb); } -void skb_rbtree_purge(struct rb_root *root); +unsigned int skb_rbtree_purge(struct rb_root *root); void *netdev_alloc_frag(unsigned int fragsz); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 51b0a9126e12..8d574a88125d 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2858,23 +2858,27 @@ EXPORT_SYMBOL(skb_queue_purge); /** * skb_rbtree_purge - empty a skb rbtree * @root: root of the rbtree to empty + * Return value: the sum of truesizes of all purged skbs. * * Delete all buffers on an &sk_buff rbtree. Each buffer is removed from * the list and one reference dropped. This function does not take * any lock. Synchronization should be handled by the caller (e.g., TCP * out-of-order queue is protected by the socket lock). */ -void skb_rbtree_purge(struct rb_root *root) +unsigned int skb_rbtree_purge(struct rb_root *root) { struct rb_node *p = rb_first(root); + unsigned int sum = 0; while (p) { struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode); p = rb_next(p); rb_erase(&skb->rbnode, root); + sum += skb->truesize; kfree_skb(skb); } + return sum; } /** -- cgit v1.2.3 From fa0f527358bd900ef92f925878ed6bfbd51305cc Mon Sep 17 00:00:00 2001 From: Peter Oskolkov Date: Thu, 2 Aug 2018 23:34:39 +0000 Subject: ip: use rb trees for IP frag queue. Similar to TCP OOO RX queue, it makes sense to use rb trees to store IP fragments, so that OOO fragments are inserted faster. Tested: - a follow-up patch contains a rather comprehensive ip defrag self-test (functional) - ran neper `udp_stream -c -H -F 100 -l 300 -T 20`: netstat --statistics Ip: 282078937 total packets received 0 forwarded 0 incoming packets discarded 946760 incoming packets delivered 18743456 requests sent out 101 fragments dropped after timeout 282077129 reassemblies required 944952 packets reassembled ok 262734239 packet reassembles failed (The numbers/stats above are somewhat better re: reassemblies vs a kernel without this patchset. More comprehensive performance testing TBD). Reported-by: Jann Horn Reported-by: Juha-Matti Tilli Suggested-by: Eric Dumazet Signed-off-by: Peter Oskolkov Signed-off-by: Eric Dumazet Cc: Florian Westphal Signed-off-by: David S. Miller --- include/linux/skbuff.h | 9 +- include/net/inet_frag.h | 3 +- net/ipv4/inet_fragment.c | 16 +-- net/ipv4/ip_fragment.c | 182 ++++++++++++++++++-------------- net/ipv6/netfilter/nf_conntrack_reasm.c | 1 + net/ipv6/reassembly.c | 1 + 6 files changed, 121 insertions(+), 91 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 47848367c816..7ebdf158a795 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -676,13 +676,16 @@ struct sk_buff { * UDP receive path is one user. */ unsigned long dev_scratch; - int ip_defrag_offset; }; }; - struct rb_node rbnode; /* used in netem & tcp stack */ + struct rb_node rbnode; /* used in netem, ip4 defrag, and tcp stack */ struct list_head list; }; - struct sock *sk; + + union { + struct sock *sk; + int ip_defrag_offset; + }; union { ktime_t tstamp; diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index f4272a29dc44..b86d14528188 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -75,7 +75,8 @@ struct inet_frag_queue { struct timer_list timer; spinlock_t lock; refcount_t refcnt; - struct sk_buff *fragments; + struct sk_buff *fragments; /* Used in IPv6. */ + struct rb_root rb_fragments; /* Used in IPv4. */ struct sk_buff *fragments_tail; ktime_t stamp; int len; diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index ccd140e4082d..6d258a5669e7 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -137,12 +137,16 @@ void inet_frag_destroy(struct inet_frag_queue *q) fp = q->fragments; nf = q->net; f = nf->f; - while (fp) { - struct sk_buff *xp = fp->next; - - sum_truesize += fp->truesize; - kfree_skb(fp); - fp = xp; + if (fp) { + do { + struct sk_buff *xp = fp->next; + + sum_truesize += fp->truesize; + kfree_skb(fp); + fp = xp; + } while (fp); + } else { + sum_truesize = skb_rbtree_purge(&q->rb_fragments); } sum = sum_truesize + f->qsize; diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 960bf5eab59f..0e8f8de77e71 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -136,7 +136,7 @@ static void ip_expire(struct timer_list *t) { struct inet_frag_queue *frag = from_timer(frag, t, timer); const struct iphdr *iph; - struct sk_buff *head; + struct sk_buff *head = NULL; struct net *net; struct ipq *qp; int err; @@ -152,14 +152,31 @@ static void ip_expire(struct timer_list *t) ipq_kill(qp); __IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS); - - head = qp->q.fragments; - __IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT); - if (!(qp->q.flags & INET_FRAG_FIRST_IN) || !head) + if (!qp->q.flags & INET_FRAG_FIRST_IN) goto out; + /* sk_buff::dev and sk_buff::rbnode are unionized. So we + * pull the head out of the tree in order to be able to + * deal with head->dev. + */ + if (qp->q.fragments) { + head = qp->q.fragments; + qp->q.fragments = head->next; + } else { + head = skb_rb_first(&qp->q.rb_fragments); + if (!head) + goto out; + rb_erase(&head->rbnode, &qp->q.rb_fragments); + memset(&head->rbnode, 0, sizeof(head->rbnode)); + barrier(); + } + if (head == qp->q.fragments_tail) + qp->q.fragments_tail = NULL; + + sub_frag_mem_limit(qp->q.net, head->truesize); + head->dev = dev_get_by_index_rcu(net, qp->iif); if (!head->dev) goto out; @@ -179,16 +196,16 @@ static void ip_expire(struct timer_list *t) (skb_rtable(head)->rt_type != RTN_LOCAL)) goto out; - skb_get(head); spin_unlock(&qp->q.lock); icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0); - kfree_skb(head); goto out_rcu_unlock; out: spin_unlock(&qp->q.lock); out_rcu_unlock: rcu_read_unlock(); + if (head) + kfree_skb(head); ipq_put(qp); } @@ -231,7 +248,7 @@ static int ip_frag_too_far(struct ipq *qp) end = atomic_inc_return(&peer->rid); qp->rid = end; - rc = qp->q.fragments && (end - start) > max; + rc = qp->q.fragments_tail && (end - start) > max; if (rc) { struct net *net; @@ -245,7 +262,6 @@ static int ip_frag_too_far(struct ipq *qp) static int ip_frag_reinit(struct ipq *qp) { - struct sk_buff *fp; unsigned int sum_truesize = 0; if (!mod_timer(&qp->q.timer, jiffies + qp->q.net->timeout)) { @@ -253,20 +269,14 @@ static int ip_frag_reinit(struct ipq *qp) return -ETIMEDOUT; } - fp = qp->q.fragments; - do { - struct sk_buff *xp = fp->next; - - sum_truesize += fp->truesize; - kfree_skb(fp); - fp = xp; - } while (fp); + sum_truesize = skb_rbtree_purge(&qp->q.rb_fragments); sub_frag_mem_limit(qp->q.net, sum_truesize); qp->q.flags = 0; qp->q.len = 0; qp->q.meat = 0; qp->q.fragments = NULL; + qp->q.rb_fragments = RB_ROOT; qp->q.fragments_tail = NULL; qp->iif = 0; qp->ecn = 0; @@ -278,7 +288,8 @@ static int ip_frag_reinit(struct ipq *qp) static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) { struct net *net = container_of(qp->q.net, struct net, ipv4.frags); - struct sk_buff *prev, *next; + struct rb_node **rbn, *parent; + struct sk_buff *skb1; struct net_device *dev; unsigned int fragsize; int flags, offset; @@ -341,58 +352,58 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) if (err) goto err; - /* Find out which fragments are in front and at the back of us - * in the chain of fragments so far. We must know where to put - * this fragment, right? - */ - prev = qp->q.fragments_tail; - if (!prev || prev->ip_defrag_offset < offset) { - next = NULL; - goto found; - } - prev = NULL; - for (next = qp->q.fragments; next != NULL; next = next->next) { - if (next->ip_defrag_offset >= offset) - break; /* bingo! */ - prev = next; - } + /* Note : skb->rbnode and skb->dev share the same location. */ + dev = skb->dev; + /* Makes sure compiler wont do silly aliasing games */ + barrier(); -found: /* RFC5722, Section 4, amended by Errata ID : 3089 * When reassembling an IPv6 datagram, if * one or more its constituent fragments is determined to be an * overlapping fragment, the entire datagram (and any constituent * fragments) MUST be silently discarded. * - * We do the same here for IPv4. + * We do the same here for IPv4 (and increment an snmp counter). */ - /* Is there an overlap with the previous fragment? */ - if (prev && - (prev->ip_defrag_offset + prev->len) > offset) - goto discard_qp; - - /* Is there an overlap with the next fragment? */ - if (next && next->ip_defrag_offset < end) - goto discard_qp; + /* Find out where to put this fragment. */ + skb1 = qp->q.fragments_tail; + if (!skb1) { + /* This is the first fragment we've received. */ + rb_link_node(&skb->rbnode, NULL, &qp->q.rb_fragments.rb_node); + qp->q.fragments_tail = skb; + } else if ((skb1->ip_defrag_offset + skb1->len) < end) { + /* This is the common/special case: skb goes to the end. */ + /* Detect and discard overlaps. */ + if (offset < (skb1->ip_defrag_offset + skb1->len)) + goto discard_qp; + /* Insert after skb1. */ + rb_link_node(&skb->rbnode, &skb1->rbnode, &skb1->rbnode.rb_right); + qp->q.fragments_tail = skb; + } else { + /* Binary search. Note that skb can become the first fragment, but + * not the last (covered above). */ + rbn = &qp->q.rb_fragments.rb_node; + do { + parent = *rbn; + skb1 = rb_to_skb(parent); + if (end <= skb1->ip_defrag_offset) + rbn = &parent->rb_left; + else if (offset >= skb1->ip_defrag_offset + skb1->len) + rbn = &parent->rb_right; + else /* Found an overlap with skb1. */ + goto discard_qp; + } while (*rbn); + /* Here we have parent properly set, and rbn pointing to + * one of its NULL left/right children. Insert skb. */ + rb_link_node(&skb->rbnode, parent, rbn); + } + rb_insert_color(&skb->rbnode, &qp->q.rb_fragments); - /* Note : skb->ip_defrag_offset and skb->dev share the same location */ - dev = skb->dev; if (dev) qp->iif = dev->ifindex; - /* Makes sure compiler wont do silly aliasing games */ - barrier(); skb->ip_defrag_offset = offset; - /* Insert this fragment in the chain of fragments. */ - skb->next = next; - if (!next) - qp->q.fragments_tail = skb; - if (prev) - prev->next = skb; - else - qp->q.fragments = skb; - qp->q.stamp = skb->tstamp; qp->q.meat += skb->len; qp->ecn |= ecn; @@ -414,7 +425,7 @@ found: unsigned long orefdst = skb->_skb_refdst; skb->_skb_refdst = 0UL; - err = ip_frag_reasm(qp, prev, dev); + err = ip_frag_reasm(qp, skb, dev); skb->_skb_refdst = orefdst; return err; } @@ -431,15 +442,15 @@ err: return err; } - /* Build a new IP datagram from all its fragments. */ - -static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, +static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, struct net_device *dev) { struct net *net = container_of(qp->q.net, struct net, ipv4.frags); struct iphdr *iph; - struct sk_buff *fp, *head = qp->q.fragments; + struct sk_buff *fp, *head = skb_rb_first(&qp->q.rb_fragments); + struct sk_buff **nextp; /* To build frag_list. */ + struct rb_node *rbn; int len; int ihlen; int err; @@ -453,25 +464,20 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, goto out_fail; } /* Make the one we just received the head. */ - if (prev) { - head = prev->next; - fp = skb_clone(head, GFP_ATOMIC); + if (head != skb) { + fp = skb_clone(skb, GFP_ATOMIC); if (!fp) goto out_nomem; - - fp->next = head->next; - if (!fp->next) + rb_replace_node(&skb->rbnode, &fp->rbnode, &qp->q.rb_fragments); + if (qp->q.fragments_tail == skb) qp->q.fragments_tail = fp; - prev->next = fp; - - skb_morph(head, qp->q.fragments); - head->next = qp->q.fragments->next; - - consume_skb(qp->q.fragments); - qp->q.fragments = head; + skb_morph(skb, head); + rb_replace_node(&head->rbnode, &skb->rbnode, + &qp->q.rb_fragments); + consume_skb(head); + head = skb; } - WARN_ON(!head); WARN_ON(head->ip_defrag_offset != 0); /* Allocate a new buffer for the datagram. */ @@ -496,24 +502,35 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, clone = alloc_skb(0, GFP_ATOMIC); if (!clone) goto out_nomem; - clone->next = head->next; - head->next = clone; skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; skb_frag_list_init(head); for (i = 0; i < skb_shinfo(head)->nr_frags; i++) plen += skb_frag_size(&skb_shinfo(head)->frags[i]); clone->len = clone->data_len = head->data_len - plen; - head->data_len -= clone->len; - head->len -= clone->len; + skb->truesize += clone->truesize; clone->csum = 0; clone->ip_summed = head->ip_summed; add_frag_mem_limit(qp->q.net, clone->truesize); + skb_shinfo(head)->frag_list = clone; + nextp = &clone->next; + } else { + nextp = &skb_shinfo(head)->frag_list; } - skb_shinfo(head)->frag_list = head->next; skb_push(head, head->data - skb_network_header(head)); - for (fp=head->next; fp; fp = fp->next) { + /* Traverse the tree in order, to build frag_list. */ + rbn = rb_next(&head->rbnode); + rb_erase(&head->rbnode, &qp->q.rb_fragments); + while (rbn) { + struct rb_node *rbnext = rb_next(rbn); + fp = rb_to_skb(rbn); + rb_erase(rbn, &qp->q.rb_fragments); + rbn = rbnext; + *nextp = fp; + nextp = &fp->next; + fp->prev = NULL; + memset(&fp->rbnode, 0, sizeof(fp->rbnode)); head->data_len += fp->len; head->len += fp->len; if (head->ip_summed != fp->ip_summed) @@ -524,7 +541,9 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, } sub_frag_mem_limit(qp->q.net, head->truesize); + *nextp = NULL; head->next = NULL; + head->prev = NULL; head->dev = dev; head->tstamp = qp->q.stamp; IPCB(head)->frag_max_size = max(qp->max_df_size, qp->q.max_size); @@ -552,6 +571,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, __IP_INC_STATS(net, IPSTATS_MIB_REASMOKS); qp->q.fragments = NULL; + qp->q.rb_fragments = RB_ROOT; qp->q.fragments_tail = NULL; return 0; diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 0610bdab721c..38d69ef516d5 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -463,6 +463,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev, struct net_devic head->csum); fq->q.fragments = NULL; + fq->q.rb_fragments = RB_ROOT; fq->q.fragments_tail = NULL; return true; diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 6edd2ac8ae4b..b4e558ab39fa 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -405,6 +405,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMOKS); rcu_read_unlock(); fq->q.fragments = NULL; + fq->q.rb_fragments = RB_ROOT; fq->q.fragments_tail = NULL; return 1; -- cgit v1.2.3 From bfe4037e722ec672c9dafd5730d9132afeeb76e9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 16 Jul 2018 09:08:20 +0200 Subject: aio: implement IOCB_CMD_POLL Simple one-shot poll through the io_submit() interface. To poll for a file descriptor the application should submit an iocb of type IOCB_CMD_POLL. It will poll the fd for the events specified in the the first 32 bits of the aio_buf field of the iocb. Unlike poll or epoll without EPOLLONESHOT this interface always works in one shot mode, that is once the iocb is completed, it will have to be resubmitted. Signed-off-by: Christoph Hellwig Tested-by: Avi Kivity --- fs/aio.c | 178 +++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/aio_abi.h | 6 +- 2 files changed, 180 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/fs/aio.c b/fs/aio.c index fe2018ada32c..2fd19521d8a8 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -5,6 +5,7 @@ * Implements an efficient asynchronous io interface. * * Copyright 2000, 2001, 2002 Red Hat, Inc. All Rights Reserved. + * Copyright 2018 Christoph Hellwig. * * See ../COPYING for licensing terms. */ @@ -165,10 +166,21 @@ struct fsync_iocb { bool datasync; }; +struct poll_iocb { + struct file *file; + struct wait_queue_head *head; + __poll_t events; + bool woken; + bool cancelled; + struct wait_queue_entry wait; + struct work_struct work; +}; + struct aio_kiocb { union { struct kiocb rw; struct fsync_iocb fsync; + struct poll_iocb poll; }; struct kioctx *ki_ctx; @@ -1601,6 +1613,169 @@ static int aio_fsync(struct fsync_iocb *req, struct iocb *iocb, bool datasync) return 0; } +static inline void aio_poll_complete(struct aio_kiocb *iocb, __poll_t mask) +{ + struct file *file = iocb->poll.file; + + aio_complete(iocb, mangle_poll(mask), 0); + fput(file); +} + +static void aio_poll_complete_work(struct work_struct *work) +{ + struct poll_iocb *req = container_of(work, struct poll_iocb, work); + struct aio_kiocb *iocb = container_of(req, struct aio_kiocb, poll); + struct poll_table_struct pt = { ._key = req->events }; + struct kioctx *ctx = iocb->ki_ctx; + __poll_t mask = 0; + + if (!READ_ONCE(req->cancelled)) + mask = vfs_poll(req->file, &pt) & req->events; + + /* + * Note that ->ki_cancel callers also delete iocb from active_reqs after + * calling ->ki_cancel. We need the ctx_lock roundtrip here to + * synchronize with them. In the cancellation case the list_del_init + * itself is not actually needed, but harmless so we keep it in to + * avoid further branches in the fast path. + */ + spin_lock_irq(&ctx->ctx_lock); + if (!mask && !READ_ONCE(req->cancelled)) { + add_wait_queue(req->head, &req->wait); + spin_unlock_irq(&ctx->ctx_lock); + return; + } + list_del_init(&iocb->ki_list); + spin_unlock_irq(&ctx->ctx_lock); + + aio_poll_complete(iocb, mask); +} + +/* assumes we are called with irqs disabled */ +static int aio_poll_cancel(struct kiocb *iocb) +{ + struct aio_kiocb *aiocb = container_of(iocb, struct aio_kiocb, rw); + struct poll_iocb *req = &aiocb->poll; + + spin_lock(&req->head->lock); + WRITE_ONCE(req->cancelled, true); + if (!list_empty(&req->wait.entry)) { + list_del_init(&req->wait.entry); + schedule_work(&aiocb->poll.work); + } + spin_unlock(&req->head->lock); + + return 0; +} + +static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, + void *key) +{ + struct poll_iocb *req = container_of(wait, struct poll_iocb, wait); + __poll_t mask = key_to_poll(key); + + req->woken = true; + + /* for instances that support it check for an event match first: */ + if (mask && !(mask & req->events)) + return 0; + + list_del_init(&req->wait.entry); + schedule_work(&req->work); + return 1; +} + +struct aio_poll_table { + struct poll_table_struct pt; + struct aio_kiocb *iocb; + int error; +}; + +static void +aio_poll_queue_proc(struct file *file, struct wait_queue_head *head, + struct poll_table_struct *p) +{ + struct aio_poll_table *pt = container_of(p, struct aio_poll_table, pt); + + /* multiple wait queues per file are not supported */ + if (unlikely(pt->iocb->poll.head)) { + pt->error = -EINVAL; + return; + } + + pt->error = 0; + pt->iocb->poll.head = head; + add_wait_queue(head, &pt->iocb->poll.wait); +} + +static ssize_t aio_poll(struct aio_kiocb *aiocb, struct iocb *iocb) +{ + struct kioctx *ctx = aiocb->ki_ctx; + struct poll_iocb *req = &aiocb->poll; + struct aio_poll_table apt; + __poll_t mask; + + /* reject any unknown events outside the normal event mask. */ + if ((u16)iocb->aio_buf != iocb->aio_buf) + return -EINVAL; + /* reject fields that are not defined for poll */ + if (iocb->aio_offset || iocb->aio_nbytes || iocb->aio_rw_flags) + return -EINVAL; + + INIT_WORK(&req->work, aio_poll_complete_work); + req->events = demangle_poll(iocb->aio_buf) | EPOLLERR | EPOLLHUP; + req->file = fget(iocb->aio_fildes); + if (unlikely(!req->file)) + return -EBADF; + + apt.pt._qproc = aio_poll_queue_proc; + apt.pt._key = req->events; + apt.iocb = aiocb; + apt.error = -EINVAL; /* same as no support for IOCB_CMD_POLL */ + + /* initialized the list so that we can do list_empty checks */ + INIT_LIST_HEAD(&req->wait.entry); + init_waitqueue_func_entry(&req->wait, aio_poll_wake); + + /* one for removal from waitqueue, one for this function */ + refcount_set(&aiocb->ki_refcnt, 2); + + mask = vfs_poll(req->file, &apt.pt) & req->events; + if (unlikely(!req->head)) { + /* we did not manage to set up a waitqueue, done */ + goto out; + } + + spin_lock_irq(&ctx->ctx_lock); + spin_lock(&req->head->lock); + if (req->woken) { + /* wake_up context handles the rest */ + mask = 0; + apt.error = 0; + } else if (mask || apt.error) { + /* if we get an error or a mask we are done */ + WARN_ON_ONCE(list_empty(&req->wait.entry)); + list_del_init(&req->wait.entry); + } else { + /* actually waiting for an event */ + list_add_tail(&aiocb->ki_list, &ctx->active_reqs); + aiocb->ki_cancel = aio_poll_cancel; + } + spin_unlock(&req->head->lock); + spin_unlock_irq(&ctx->ctx_lock); + +out: + if (unlikely(apt.error)) { + fput(req->file); + return apt.error; + } + + if (mask) + aio_poll_complete(aiocb, mask); + iocb_put(aiocb); + return 0; +} + static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, bool compat) { @@ -1674,6 +1849,9 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, case IOCB_CMD_FDSYNC: ret = aio_fsync(&req->fsync, &iocb, true); break; + case IOCB_CMD_POLL: + ret = aio_poll(req, &iocb); + break; default: pr_debug("invalid aio operation %d\n", iocb.aio_lio_opcode); ret = -EINVAL; diff --git a/include/uapi/linux/aio_abi.h b/include/uapi/linux/aio_abi.h index d4593a6062ef..ce43d340f010 100644 --- a/include/uapi/linux/aio_abi.h +++ b/include/uapi/linux/aio_abi.h @@ -38,10 +38,8 @@ enum { IOCB_CMD_PWRITE = 1, IOCB_CMD_FSYNC = 2, IOCB_CMD_FDSYNC = 3, - /* These two are experimental. - * IOCB_CMD_PREADX = 4, - * IOCB_CMD_POLL = 5, - */ + /* 4 was the experimental IOCB_CMD_PREADX */ + IOCB_CMD_POLL = 5, IOCB_CMD_NOOP = 6, IOCB_CMD_PREADV = 7, IOCB_CMD_PWRITEV = 8, -- cgit v1.2.3 From 55f2503c3b69328735e88031ff8d6ba291bd952b Mon Sep 17 00:00:00 2001 From: Pingfan Liu Date: Tue, 31 Jul 2018 16:51:32 +0800 Subject: PM / reboot: Eliminate race between reboot and suspend At present, "systemctl suspend" and "shutdown" can run in parrallel. A system can suspend after devices_shutdown(), and resume. Then the shutdown task goes on to power off. This causes many devices are not really shut off. Hence replacing reboot_mutex with system_transition_mutex (renamed from pm_mutex) to achieve the exclusion. The renaming of pm_mutex as system_transition_mutex can be better to reflect the purpose of the mutex. Signed-off-by: Pingfan Liu Acked-by: Pavel Machek Signed-off-by: Rafael J. Wysocki --- Documentation/power/freezing-of-tasks.txt | 12 ++++++------ Documentation/power/suspend-and-cpuhotplug.txt | 6 +++--- include/linux/suspend.h | 2 +- kernel/freezer.c | 4 +++- kernel/power/hibernate.c | 15 ++++++++------- kernel/power/main.c | 12 ++++++------ kernel/power/suspend.c | 4 ++-- kernel/power/user.c | 4 ++-- kernel/reboot.c | 6 +++--- mm/page_alloc.c | 11 ++++++----- 10 files changed, 40 insertions(+), 36 deletions(-) (limited to 'include') diff --git a/Documentation/power/freezing-of-tasks.txt b/Documentation/power/freezing-of-tasks.txt index af005770e767..cd283190855a 100644 --- a/Documentation/power/freezing-of-tasks.txt +++ b/Documentation/power/freezing-of-tasks.txt @@ -204,26 +204,26 @@ VI. Are there any precautions to be taken to prevent freezing failures? Yes, there are. -First of all, grabbing the 'pm_mutex' lock to mutually exclude a piece of code +First of all, grabbing the 'system_transition_mutex' lock to mutually exclude a piece of code from system-wide sleep such as suspend/hibernation is not encouraged. If possible, that piece of code must instead hook onto the suspend/hibernation notifiers to achieve mutual exclusion. Look at the CPU-Hotplug code (kernel/cpu.c) for an example. -However, if that is not feasible, and grabbing 'pm_mutex' is deemed necessary, -it is strongly discouraged to directly call mutex_[un]lock(&pm_mutex) since +However, if that is not feasible, and grabbing 'system_transition_mutex' is deemed necessary, +it is strongly discouraged to directly call mutex_[un]lock(&system_transition_mutex) since that could lead to freezing failures, because if the suspend/hibernate code -successfully acquired the 'pm_mutex' lock, and hence that other entity failed +successfully acquired the 'system_transition_mutex' lock, and hence that other entity failed to acquire the lock, then that task would get blocked in TASK_UNINTERRUPTIBLE state. As a consequence, the freezer would not be able to freeze that task, leading to freezing failure. However, the [un]lock_system_sleep() APIs are safe to use in this scenario, since they ask the freezer to skip freezing this task, since it is anyway -"frozen enough" as it is blocked on 'pm_mutex', which will be released +"frozen enough" as it is blocked on 'system_transition_mutex', which will be released only after the entire suspend/hibernation sequence is complete. So, to summarize, use [un]lock_system_sleep() instead of directly using -mutex_[un]lock(&pm_mutex). That would prevent freezing failures. +mutex_[un]lock(&system_transition_mutex). That would prevent freezing failures. V. Miscellaneous /sys/power/pm_freeze_timeout controls how long it will cost at most to freeze diff --git a/Documentation/power/suspend-and-cpuhotplug.txt b/Documentation/power/suspend-and-cpuhotplug.txt index 6f55eb960a6d..a8751b8df10e 100644 --- a/Documentation/power/suspend-and-cpuhotplug.txt +++ b/Documentation/power/suspend-and-cpuhotplug.txt @@ -32,7 +32,7 @@ More details follow: sysfs file | v - Acquire pm_mutex lock + Acquire system_transition_mutex lock | v Send PM_SUSPEND_PREPARE @@ -96,10 +96,10 @@ execution during resume): * thaw tasks * send PM_POST_SUSPEND notifications -* Release pm_mutex lock. +* Release system_transition_mutex lock. -It is to be noted here that the pm_mutex lock is acquired at the very +It is to be noted here that the system_transition_mutex lock is acquired at the very beginning, when we are just starting out to suspend, and then released only after the entire cycle is complete (i.e., suspend + resume). diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 440b62f7502e..5a28ac9284f0 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -414,7 +414,7 @@ static inline bool hibernation_available(void) { return false; } #define PM_RESTORE_PREPARE 0x0005 /* Going to restore a saved image */ #define PM_POST_RESTORE 0x0006 /* Restore failed */ -extern struct mutex pm_mutex; +extern struct mutex system_transition_mutex; #ifdef CONFIG_PM_SLEEP void save_processor_state(void); diff --git a/kernel/freezer.c b/kernel/freezer.c index 6f56a9e219fa..b162b74611e4 100644 --- a/kernel/freezer.c +++ b/kernel/freezer.c @@ -15,7 +15,9 @@ atomic_t system_freezing_cnt = ATOMIC_INIT(0); EXPORT_SYMBOL(system_freezing_cnt); -/* indicate whether PM freezing is in effect, protected by pm_mutex */ +/* indicate whether PM freezing is in effect, protected by + * system_transition_mutex + */ bool pm_freezing; bool pm_nosig_freezing; diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 38f3f96b4b12..abef759de7c8 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -338,7 +338,7 @@ static int create_image(int platform_mode) * hibernation_snapshot - Quiesce devices and create a hibernation image. * @platform_mode: If set, use platform driver to prepare for the transition. * - * This routine must be called with pm_mutex held. + * This routine must be called with system_transition_mutex held. */ int hibernation_snapshot(int platform_mode) { @@ -500,8 +500,9 @@ static int resume_target_kernel(bool platform_mode) * hibernation_restore - Quiesce devices and restore from a hibernation image. * @platform_mode: If set, use platform driver to prepare for the transition. * - * This routine must be called with pm_mutex held. If it is successful, control - * reappears in the restored target kernel in hibernation_snapshot(). + * This routine must be called with system_transition_mutex held. If it is + * successful, control reappears in the restored target kernel in + * hibernation_snapshot(). */ int hibernation_restore(int platform_mode) { @@ -806,13 +807,13 @@ static int software_resume(void) * name_to_dev_t() below takes a sysfs buffer mutex when sysfs * is configured into the kernel. Since the regular hibernate * trigger path is via sysfs which takes a buffer mutex before - * calling hibernate functions (which take pm_mutex) this can - * cause lockdep to complain about a possible ABBA deadlock + * calling hibernate functions (which take system_transition_mutex) + * this can cause lockdep to complain about a possible ABBA deadlock * which cannot happen since we're in the boot code here and * sysfs can't be invoked yet. Therefore, we use a subclass * here to avoid lockdep complaining. */ - mutex_lock_nested(&pm_mutex, SINGLE_DEPTH_NESTING); + mutex_lock_nested(&system_transition_mutex, SINGLE_DEPTH_NESTING); if (swsusp_resume_device) goto Check_image; @@ -900,7 +901,7 @@ static int software_resume(void) atomic_inc(&snapshot_device_available); /* For success case, the suspend path will release the lock */ Unlock: - mutex_unlock(&pm_mutex); + mutex_unlock(&system_transition_mutex); pm_pr_dbg("Hibernation image not present or could not be loaded.\n"); return error; Close_Finish: diff --git a/kernel/power/main.c b/kernel/power/main.c index d9706da10930..35b50823d83b 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -15,17 +15,16 @@ #include #include #include +#include #include "power.h" -DEFINE_MUTEX(pm_mutex); - #ifdef CONFIG_PM_SLEEP void lock_system_sleep(void) { current->flags |= PF_FREEZER_SKIP; - mutex_lock(&pm_mutex); + mutex_lock(&system_transition_mutex); } EXPORT_SYMBOL_GPL(lock_system_sleep); @@ -37,8 +36,9 @@ void unlock_system_sleep(void) * * Reason: * Fundamentally, we just don't need it, because freezing condition - * doesn't come into effect until we release the pm_mutex lock, - * since the freezer always works with pm_mutex held. + * doesn't come into effect until we release the + * system_transition_mutex lock, since the freezer always works with + * system_transition_mutex held. * * More importantly, in the case of hibernation, * unlock_system_sleep() gets called in snapshot_read() and @@ -47,7 +47,7 @@ void unlock_system_sleep(void) * enter the refrigerator, thus causing hibernation to lockup. */ current->flags &= ~PF_FREEZER_SKIP; - mutex_unlock(&pm_mutex); + mutex_unlock(&system_transition_mutex); } EXPORT_SYMBOL_GPL(unlock_system_sleep); diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 87331565e505..9e13afe65a14 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -556,7 +556,7 @@ static int enter_state(suspend_state_t state) } else if (!valid_state(state)) { return -EINVAL; } - if (!mutex_trylock(&pm_mutex)) + if (!mutex_trylock(&system_transition_mutex)) return -EBUSY; if (state == PM_SUSPEND_TO_IDLE) @@ -590,7 +590,7 @@ static int enter_state(suspend_state_t state) pm_pr_dbg("Finishing wakeup.\n"); suspend_finish(); Unlock: - mutex_unlock(&pm_mutex); + mutex_unlock(&system_transition_mutex); return error; } diff --git a/kernel/power/user.c b/kernel/power/user.c index abd225550271..2d8b60a3c86b 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -216,7 +216,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd, if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!mutex_trylock(&pm_mutex)) + if (!mutex_trylock(&system_transition_mutex)) return -EBUSY; lock_device_hotplug(); @@ -394,7 +394,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd, } unlock_device_hotplug(); - mutex_unlock(&pm_mutex); + mutex_unlock(&system_transition_mutex); return error; } diff --git a/kernel/reboot.c b/kernel/reboot.c index e4ced883d8de..8fb44dec9ad7 100644 --- a/kernel/reboot.c +++ b/kernel/reboot.c @@ -294,7 +294,7 @@ void kernel_power_off(void) } EXPORT_SYMBOL_GPL(kernel_power_off); -static DEFINE_MUTEX(reboot_mutex); +DEFINE_MUTEX(system_transition_mutex); /* * Reboot system call: for obvious reasons only root may call it, @@ -338,7 +338,7 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd, if ((cmd == LINUX_REBOOT_CMD_POWER_OFF) && !pm_power_off) cmd = LINUX_REBOOT_CMD_HALT; - mutex_lock(&reboot_mutex); + mutex_lock(&system_transition_mutex); switch (cmd) { case LINUX_REBOOT_CMD_RESTART: kernel_restart(NULL); @@ -389,7 +389,7 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd, ret = -EINVAL; break; } - mutex_unlock(&reboot_mutex); + mutex_unlock(&system_transition_mutex); return ret; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 1521100f1e63..e47f9e467408 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -155,16 +155,17 @@ static inline void set_pcppage_migratetype(struct page *page, int migratetype) * The following functions are used by the suspend/hibernate code to temporarily * change gfp_allowed_mask in order to avoid using I/O during memory allocations * while devices are suspended. To avoid races with the suspend/hibernate code, - * they should always be called with pm_mutex held (gfp_allowed_mask also should - * only be modified with pm_mutex held, unless the suspend/hibernate code is - * guaranteed not to run in parallel with that modification). + * they should always be called with system_transition_mutex held + * (gfp_allowed_mask also should only be modified with system_transition_mutex + * held, unless the suspend/hibernate code is guaranteed not to run in parallel + * with that modification). */ static gfp_t saved_gfp_mask; void pm_restore_gfp_mask(void) { - WARN_ON(!mutex_is_locked(&pm_mutex)); + WARN_ON(!mutex_is_locked(&system_transition_mutex)); if (saved_gfp_mask) { gfp_allowed_mask = saved_gfp_mask; saved_gfp_mask = 0; @@ -173,7 +174,7 @@ void pm_restore_gfp_mask(void) void pm_restrict_gfp_mask(void) { - WARN_ON(!mutex_is_locked(&pm_mutex)); + WARN_ON(!mutex_is_locked(&system_transition_mutex)); WARN_ON(saved_gfp_mask); saved_gfp_mask = gfp_allowed_mask; gfp_allowed_mask &= ~(__GFP_IO | __GFP_FS); -- cgit v1.2.3 From 5636cf7d6dc86f47fd66757dae088e35014da464 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Wed, 23 May 2018 11:58:36 -0400 Subject: btrfs: remove the logged extents infrastructure This is no longer used anywhere, remove all of it. Signed-off-by: Josef Bacik Reviewed-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/ordered-data.c | 123 ------------------------------------------- fs/btrfs/ordered-data.h | 20 ++----- fs/btrfs/tree-log.c | 16 ------ include/trace/events/btrfs.h | 1 - 4 files changed, 3 insertions(+), 157 deletions(-) (limited to 'include') diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 2e1a1694a33d..c35d2aed5ff8 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -421,129 +421,6 @@ out: return ret == 0; } -/* Needs to either be called under a log transaction or the log_mutex */ -void btrfs_get_logged_extents(struct btrfs_inode *inode, - struct list_head *logged_list, - const loff_t start, - const loff_t end) -{ - struct btrfs_ordered_inode_tree *tree; - struct btrfs_ordered_extent *ordered; - struct rb_node *n; - struct rb_node *prev; - - tree = &inode->ordered_tree; - spin_lock_irq(&tree->lock); - n = __tree_search(&tree->tree, end, &prev); - if (!n) - n = prev; - for (; n; n = rb_prev(n)) { - ordered = rb_entry(n, struct btrfs_ordered_extent, rb_node); - if (ordered->file_offset > end) - continue; - if (entry_end(ordered) <= start) - break; - if (test_and_set_bit(BTRFS_ORDERED_LOGGED, &ordered->flags)) - continue; - list_add(&ordered->log_list, logged_list); - refcount_inc(&ordered->refs); - } - spin_unlock_irq(&tree->lock); -} - -void btrfs_put_logged_extents(struct list_head *logged_list) -{ - struct btrfs_ordered_extent *ordered; - - while (!list_empty(logged_list)) { - ordered = list_first_entry(logged_list, - struct btrfs_ordered_extent, - log_list); - list_del_init(&ordered->log_list); - btrfs_put_ordered_extent(ordered); - } -} - -void btrfs_submit_logged_extents(struct list_head *logged_list, - struct btrfs_root *log) -{ - int index = log->log_transid % 2; - - spin_lock_irq(&log->log_extents_lock[index]); - list_splice_tail(logged_list, &log->logged_list[index]); - spin_unlock_irq(&log->log_extents_lock[index]); -} - -void btrfs_wait_logged_extents(struct btrfs_trans_handle *trans, - struct btrfs_root *log, u64 transid) -{ - struct btrfs_ordered_extent *ordered; - int index = transid % 2; - - spin_lock_irq(&log->log_extents_lock[index]); - while (!list_empty(&log->logged_list[index])) { - struct inode *inode; - ordered = list_first_entry(&log->logged_list[index], - struct btrfs_ordered_extent, - log_list); - list_del_init(&ordered->log_list); - inode = ordered->inode; - spin_unlock_irq(&log->log_extents_lock[index]); - - if (!test_bit(BTRFS_ORDERED_IO_DONE, &ordered->flags) && - !test_bit(BTRFS_ORDERED_DIRECT, &ordered->flags)) { - u64 start = ordered->file_offset; - u64 end = ordered->file_offset + ordered->len - 1; - - WARN_ON(!inode); - filemap_fdatawrite_range(inode->i_mapping, start, end); - } - wait_event(ordered->wait, test_bit(BTRFS_ORDERED_IO_DONE, - &ordered->flags)); - - /* - * In order to keep us from losing our ordered extent - * information when committing the transaction we have to make - * sure that any logged extents are completed when we go to - * commit the transaction. To do this we simply increase the - * current transactions pending_ordered counter and decrement it - * when the ordered extent completes. - */ - if (!test_bit(BTRFS_ORDERED_COMPLETE, &ordered->flags)) { - struct btrfs_ordered_inode_tree *tree; - - tree = &BTRFS_I(inode)->ordered_tree; - spin_lock_irq(&tree->lock); - if (!test_bit(BTRFS_ORDERED_COMPLETE, &ordered->flags)) { - set_bit(BTRFS_ORDERED_PENDING, &ordered->flags); - atomic_inc(&trans->transaction->pending_ordered); - } - spin_unlock_irq(&tree->lock); - } - btrfs_put_ordered_extent(ordered); - spin_lock_irq(&log->log_extents_lock[index]); - } - spin_unlock_irq(&log->log_extents_lock[index]); -} - -void btrfs_free_logged_extents(struct btrfs_root *log, u64 transid) -{ - struct btrfs_ordered_extent *ordered; - int index = transid % 2; - - spin_lock_irq(&log->log_extents_lock[index]); - while (!list_empty(&log->logged_list[index])) { - ordered = list_first_entry(&log->logged_list[index], - struct btrfs_ordered_extent, - log_list); - list_del_init(&ordered->log_list); - spin_unlock_irq(&log->log_extents_lock[index]); - btrfs_put_ordered_extent(ordered); - spin_lock_irq(&log->log_extents_lock[index]); - } - spin_unlock_irq(&log->log_extents_lock[index]); -} - /* * used to drop a reference on an ordered extent. This will free * the extent if the last reference is dropped diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h index 3be443fb3001..b2d3f6a091f7 100644 --- a/fs/btrfs/ordered-data.h +++ b/fs/btrfs/ordered-data.h @@ -54,15 +54,11 @@ struct btrfs_ordered_sum { #define BTRFS_ORDERED_UPDATED_ISIZE 7 /* indicates whether this ordered extent * has done its due diligence in updating * the isize. */ -#define BTRFS_ORDERED_LOGGED_CSUM 8 /* We've logged the csums on this ordered - ordered extent */ -#define BTRFS_ORDERED_TRUNCATED 9 /* Set when we have to truncate an extent */ +#define BTRFS_ORDERED_TRUNCATED 8 /* Set when we have to truncate an extent */ -#define BTRFS_ORDERED_LOGGED 10 /* Set when we've waited on this ordered extent - * in the logging code. */ -#define BTRFS_ORDERED_PENDING 11 /* We are waiting for this ordered extent to +#define BTRFS_ORDERED_PENDING 9 /* We are waiting for this ordered extent to * complete in the current transaction. */ -#define BTRFS_ORDERED_REGULAR 12 /* Regular IO for COW */ +#define BTRFS_ORDERED_REGULAR 10 /* Regular IO for COW */ struct btrfs_ordered_extent { /* logical offset in the file */ @@ -193,16 +189,6 @@ u64 btrfs_wait_ordered_extents(struct btrfs_root *root, u64 nr, const u64 range_start, const u64 range_len); u64 btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr, const u64 range_start, const u64 range_len); -void btrfs_get_logged_extents(struct btrfs_inode *inode, - struct list_head *logged_list, - const loff_t start, - const loff_t end); -void btrfs_put_logged_extents(struct list_head *logged_list); -void btrfs_submit_logged_extents(struct list_head *logged_list, - struct btrfs_root *log); -void btrfs_wait_logged_extents(struct btrfs_trans_handle *trans, - struct btrfs_root *log, u64 transid); -void btrfs_free_logged_extents(struct btrfs_root *log, u64 transid); int __init ordered_data_init(void); void __cold ordered_data_exit(void); diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index dce499071c86..daf32dc94dc3 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -2933,7 +2933,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, /* bail out if we need to do a full commit */ if (btrfs_need_log_full_commit(fs_info, trans)) { ret = -EAGAIN; - btrfs_free_logged_extents(log, log_transid); mutex_unlock(&root->log_mutex); goto out; } @@ -2951,7 +2950,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, if (ret) { blk_finish_plug(&plug); btrfs_abort_transaction(trans, ret); - btrfs_free_logged_extents(log, log_transid); btrfs_set_log_full_commit(fs_info, trans); mutex_unlock(&root->log_mutex); goto out; @@ -3002,7 +3000,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, goto out; } btrfs_wait_tree_log_extents(log, mark); - btrfs_free_logged_extents(log, log_transid); mutex_unlock(&log_root_tree->log_mutex); ret = -EAGAIN; goto out; @@ -3020,7 +3017,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, if (atomic_read(&log_root_tree->log_commit[index2])) { blk_finish_plug(&plug); ret = btrfs_wait_tree_log_extents(log, mark); - btrfs_wait_logged_extents(trans, log, log_transid); wait_log_commit(log_root_tree, root_log_ctx.log_transid); mutex_unlock(&log_root_tree->log_mutex); @@ -3045,7 +3041,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, if (btrfs_need_log_full_commit(fs_info, trans)) { blk_finish_plug(&plug); btrfs_wait_tree_log_extents(log, mark); - btrfs_free_logged_extents(log, log_transid); mutex_unlock(&log_root_tree->log_mutex); ret = -EAGAIN; goto out_wake_log_root; @@ -3058,7 +3053,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, if (ret) { btrfs_set_log_full_commit(fs_info, trans); btrfs_abort_transaction(trans, ret); - btrfs_free_logged_extents(log, log_transid); mutex_unlock(&log_root_tree->log_mutex); goto out_wake_log_root; } @@ -3068,11 +3062,9 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, EXTENT_NEW | EXTENT_DIRTY); if (ret) { btrfs_set_log_full_commit(fs_info, trans); - btrfs_free_logged_extents(log, log_transid); mutex_unlock(&log_root_tree->log_mutex); goto out_wake_log_root; } - btrfs_wait_logged_extents(trans, log, log_transid); btrfs_set_super_log_root(fs_info->super_for_commit, log_root_tree->node->start); @@ -3159,14 +3151,6 @@ static void free_log_tree(struct btrfs_trans_handle *trans, EXTENT_DIRTY | EXTENT_NEW | EXTENT_NEED_WAIT); } - /* - * We may have short-circuited the log tree with the full commit logic - * and left ordered extents on our list, so clear these out to keep us - * from leaking inodes and memory. - */ - btrfs_free_logged_extents(log, 0); - btrfs_free_logged_extents(log, 1); - free_extent_buffer(log->node); kfree(log); } diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index 39b94ec965be..7057cc99d267 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -433,7 +433,6 @@ DEFINE_EVENT( { (1 << BTRFS_ORDERED_DIRECT), "DIRECT" }, \ { (1 << BTRFS_ORDERED_IOERR), "IOERR" }, \ { (1 << BTRFS_ORDERED_UPDATED_ISIZE), "UPDATED_ISIZE" }, \ - { (1 << BTRFS_ORDERED_LOGGED_CSUM), "LOGGED_CSUM" }, \ { (1 << BTRFS_ORDERED_TRUNCATED), "TRUNCATED" }) -- cgit v1.2.3 From e41ca5897489b1c18af75ff0cc8f5c80260b3281 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Wed, 6 Jun 2018 15:41:49 +0800 Subject: btrfs: Get rid of the confusing btrfs_file_extent_inline_len We used to call btrfs_file_extent_inline_len() to get the uncompressed data size of an inlined extent. However this function is hiding evil, for compressed extent, it has no choice but to directly read out ram_bytes from btrfs_file_extent_item. While for uncompressed extent, it uses item size to calculate the real data size, and ignoring ram_bytes completely. In fact, for corrupted ram_bytes, due to above behavior kernel btrfs_print_leaf() can't even print correct ram_bytes to expose the bug. Since we have the tree-checker to verify all EXTENT_DATA, such mismatch can be detected pretty easily, thus we can trust ram_bytes without the evil btrfs_file_extent_inline_len(). Signed-off-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/ctree.h | 26 -------------------------- fs/btrfs/file-item.c | 2 +- fs/btrfs/file.c | 3 +-- fs/btrfs/inode.c | 12 ++++++------ fs/btrfs/print-tree.c | 4 ++-- fs/btrfs/send.c | 17 +++++++---------- fs/btrfs/tree-log.c | 12 ++++-------- include/trace/events/btrfs.h | 2 +- 8 files changed, 22 insertions(+), 56 deletions(-) (limited to 'include') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 12cb327cd16e..41ba770b9db9 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2428,32 +2428,6 @@ static inline u32 btrfs_file_extent_inline_item_len( return btrfs_item_size(eb, e) - BTRFS_FILE_EXTENT_INLINE_DATA_START; } -/* this returns the number of file bytes represented by the inline item. - * If an item is compressed, this is the uncompressed size - */ -static inline u32 btrfs_file_extent_inline_len(const struct extent_buffer *eb, - int slot, - const struct btrfs_file_extent_item *fi) -{ - struct btrfs_map_token token; - - btrfs_init_map_token(&token); - /* - * return the space used on disk if this item isn't - * compressed or encoded - */ - if (btrfs_token_file_extent_compression(eb, fi, &token) == 0 && - btrfs_token_file_extent_encryption(eb, fi, &token) == 0 && - btrfs_token_file_extent_other_encoding(eb, fi, &token) == 0) { - return btrfs_file_extent_inline_item_len(eb, - btrfs_item_nr(slot)); - } - - /* otherwise use the ram bytes field */ - return btrfs_token_file_extent_ram_bytes(eb, fi, &token); -} - - /* btrfs_dev_stats_item */ static inline u64 btrfs_dev_stats_value(const struct extent_buffer *eb, const struct btrfs_dev_stats_item *ptr, diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index f9dd6d1836a3..8c3cd7072caf 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -942,7 +942,7 @@ void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode, btrfs_file_extent_num_bytes(leaf, fi); } else if (type == BTRFS_FILE_EXTENT_INLINE) { size_t size; - size = btrfs_file_extent_inline_len(leaf, slot, fi); + size = btrfs_file_extent_ram_bytes(leaf, fi); extent_end = ALIGN(extent_start + size, fs_info->sectorsize); } diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 975c590c50d8..4cd8af14f915 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -833,8 +833,7 @@ next_slot: btrfs_file_extent_num_bytes(leaf, fi); } else if (extent_type == BTRFS_FILE_EXTENT_INLINE) { extent_end = key.offset + - btrfs_file_extent_inline_len(leaf, - path->slots[0], fi); + btrfs_file_extent_ram_bytes(leaf, fi); } else { /* can't happen */ BUG(); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index eba61bcb9bb3..1ade43c02b81 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1443,8 +1443,7 @@ next_slot: nocow = 1; } else if (extent_type == BTRFS_FILE_EXTENT_INLINE) { extent_end = found_key.offset + - btrfs_file_extent_inline_len(leaf, - path->slots[0], fi); + btrfs_file_extent_ram_bytes(leaf, fi); extent_end = ALIGN(extent_end, fs_info->sectorsize); } else { @@ -4643,8 +4642,8 @@ search_again: BTRFS_I(inode), leaf, fi, found_key.offset); } else if (extent_type == BTRFS_FILE_EXTENT_INLINE) { - item_end += btrfs_file_extent_inline_len(leaf, - path->slots[0], fi); + item_end += btrfs_file_extent_ram_bytes(leaf, + fi); trace_btrfs_truncate_show_fi_inline( BTRFS_I(inode), leaf, fi, path->slots[0], @@ -6943,7 +6942,8 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode, extent_start); } else if (found_type == BTRFS_FILE_EXTENT_INLINE) { size_t size; - size = btrfs_file_extent_inline_len(leaf, path->slots[0], item); + + size = btrfs_file_extent_ram_bytes(leaf, item); extent_end = ALIGN(extent_start + size, fs_info->sectorsize); @@ -6994,7 +6994,7 @@ next: if (new_inline) goto out; - size = btrfs_file_extent_inline_len(leaf, path->slots[0], item); + size = btrfs_file_extent_ram_bytes(leaf, item); extent_offset = page_offset(page) + pg_offset - extent_start; copy_size = min_t(u64, PAGE_SIZE - pg_offset, size - extent_offset); diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c index a4e11cf04671..59efcf2e0de8 100644 --- a/fs/btrfs/print-tree.c +++ b/fs/btrfs/print-tree.c @@ -267,8 +267,8 @@ void btrfs_print_leaf(struct extent_buffer *l) struct btrfs_file_extent_item); if (btrfs_file_extent_type(l, fi) == BTRFS_FILE_EXTENT_INLINE) { - pr_info("\t\tinline extent data size %u\n", - btrfs_file_extent_inline_len(l, i, fi)); + pr_info("\t\tinline extent data size %llu\n", + btrfs_file_extent_ram_bytes(l, fi)); break; } pr_info("\t\textent data disk bytenr %llu nr %llu\n", diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index c47f62b19226..6ff7a1315e52 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -1500,7 +1500,7 @@ static int read_symlink(struct btrfs_root *root, BUG_ON(compression); off = btrfs_file_extent_inline_start(ei); - len = btrfs_file_extent_inline_len(path->nodes[0], path->slots[0], ei); + len = btrfs_file_extent_ram_bytes(path->nodes[0], ei); ret = fs_path_add_from_extent_buffer(dest, path->nodes[0], off, len); @@ -5160,7 +5160,7 @@ static int clone_range(struct send_ctx *sctx, ei = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item); type = btrfs_file_extent_type(leaf, ei); if (type == BTRFS_FILE_EXTENT_INLINE) { - ext_len = btrfs_file_extent_inline_len(leaf, slot, ei); + ext_len = btrfs_file_extent_ram_bytes(leaf, ei); ext_len = PAGE_ALIGN(ext_len); } else { ext_len = btrfs_file_extent_num_bytes(leaf, ei); @@ -5236,8 +5236,7 @@ static int send_write_or_clone(struct send_ctx *sctx, struct btrfs_file_extent_item); type = btrfs_file_extent_type(path->nodes[0], ei); if (type == BTRFS_FILE_EXTENT_INLINE) { - len = btrfs_file_extent_inline_len(path->nodes[0], - path->slots[0], ei); + len = btrfs_file_extent_ram_bytes(path->nodes[0], ei); /* * it is possible the inline item won't cover the whole page, * but there may be items after this page. Make @@ -5375,7 +5374,7 @@ static int is_extent_unchanged(struct send_ctx *sctx, } if (right_type == BTRFS_FILE_EXTENT_INLINE) { - right_len = btrfs_file_extent_inline_len(eb, slot, ei); + right_len = btrfs_file_extent_ram_bytes(eb, ei); right_len = PAGE_ALIGN(right_len); } else { right_len = btrfs_file_extent_num_bytes(eb, ei); @@ -5496,8 +5495,7 @@ static int get_last_extent(struct send_ctx *sctx, u64 offset) struct btrfs_file_extent_item); type = btrfs_file_extent_type(path->nodes[0], fi); if (type == BTRFS_FILE_EXTENT_INLINE) { - u64 size = btrfs_file_extent_inline_len(path->nodes[0], - path->slots[0], fi); + u64 size = btrfs_file_extent_ram_bytes(path->nodes[0], fi); extent_end = ALIGN(key.offset + size, sctx->send_root->fs_info->sectorsize); } else { @@ -5560,7 +5558,7 @@ static int range_is_hole_in_parent(struct send_ctx *sctx, fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item); if (btrfs_file_extent_type(leaf, fi) == BTRFS_FILE_EXTENT_INLINE) { - u64 size = btrfs_file_extent_inline_len(leaf, slot, fi); + u64 size = btrfs_file_extent_ram_bytes(leaf, fi); extent_end = ALIGN(key.offset + size, root->fs_info->sectorsize); @@ -5606,8 +5604,7 @@ static int maybe_send_hole(struct send_ctx *sctx, struct btrfs_path *path, struct btrfs_file_extent_item); type = btrfs_file_extent_type(path->nodes[0], fi); if (type == BTRFS_FILE_EXTENT_INLINE) { - u64 size = btrfs_file_extent_inline_len(path->nodes[0], - path->slots[0], fi); + u64 size = btrfs_file_extent_ram_bytes(path->nodes[0], fi); extent_end = ALIGN(key->offset + size, sctx->send_root->fs_info->sectorsize); } else { diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index b3b1d424f2d8..6bca8f88ade0 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -597,7 +597,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans, if (btrfs_file_extent_disk_bytenr(eb, item) == 0) nbytes = 0; } else if (found_type == BTRFS_FILE_EXTENT_INLINE) { - size = btrfs_file_extent_inline_len(eb, slot, item); + size = btrfs_file_extent_ram_bytes(eb, item); nbytes = btrfs_file_extent_ram_bytes(eb, item); extent_end = ALIGN(start + size, fs_info->sectorsize); @@ -3920,9 +3920,7 @@ static noinline int copy_items(struct btrfs_trans_handle *trans, struct btrfs_file_extent_item); if (btrfs_file_extent_type(src, extent) == BTRFS_FILE_EXTENT_INLINE) { - len = btrfs_file_extent_inline_len(src, - src_path->slots[0], - extent); + len = btrfs_file_extent_ram_bytes(src, extent); *last_extent = ALIGN(key.offset + len, fs_info->sectorsize); } else { @@ -3987,7 +3985,7 @@ fill_holes: extent = btrfs_item_ptr(src, i, struct btrfs_file_extent_item); if (btrfs_file_extent_type(src, extent) == BTRFS_FILE_EXTENT_INLINE) { - len = btrfs_file_extent_inline_len(src, i, extent); + len = btrfs_file_extent_ram_bytes(src, extent); extent_end = ALIGN(key.offset + len, fs_info->sectorsize); } else { @@ -4572,9 +4570,7 @@ static int btrfs_log_trailing_hole(struct btrfs_trans_handle *trans, if (btrfs_file_extent_type(leaf, extent) == BTRFS_FILE_EXTENT_INLINE) { - len = btrfs_file_extent_inline_len(leaf, - path->slots[0], - extent); + len = btrfs_file_extent_ram_bytes(leaf, extent); ASSERT(len == i_size || (len == fs_info->sectorsize && btrfs_file_extent_compression(leaf, extent) != diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index 7057cc99d267..b401c4e36394 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -374,7 +374,7 @@ DECLARE_EVENT_CLASS( __entry->extent_type = btrfs_file_extent_type(l, fi); __entry->compression = btrfs_file_extent_compression(l, fi); __entry->extent_start = start; - __entry->extent_end = (start + btrfs_file_extent_inline_len(l, slot, fi)); + __entry->extent_end = (start + btrfs_file_extent_ram_bytes(l, fi)); ), TP_printk_btrfs( -- cgit v1.2.3 From c883da313ebf459efd33d262ca963e3a5f0ac024 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Mon, 30 Jul 2018 07:54:56 -0400 Subject: locks: add tracepoint in flock codepath Signed-off-by: Jeff Layton --- fs/locks.c | 1 + include/trace/events/filelock.h | 5 ++++- 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/fs/locks.c b/fs/locks.c index e533623e2e99..6138a9bcd924 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -990,6 +990,7 @@ out: if (new_fl) locks_free_lock(new_fl); locks_dispose_list(&dispose); + trace_flock_lock_inode(inode, request, error); return error; } diff --git a/include/trace/events/filelock.h b/include/trace/events/filelock.h index d1faf3597b9d..68b17c116907 100644 --- a/include/trace/events/filelock.h +++ b/include/trace/events/filelock.h @@ -112,8 +112,11 @@ DEFINE_EVENT(filelock_lock, locks_remove_posix, TP_PROTO(struct inode *inode, struct file_lock *fl, int ret), TP_ARGS(inode, fl, ret)); -DECLARE_EVENT_CLASS(filelock_lease, +DEFINE_EVENT(filelock_lock, flock_lock_inode, + TP_PROTO(struct inode *inode, struct file_lock *fl, int ret), + TP_ARGS(inode, fl, ret)); +DECLARE_EVENT_CLASS(filelock_lease, TP_PROTO(struct inode *inode, struct file_lock *fl), TP_ARGS(inode, fl), -- cgit v1.2.3 From 429711aec282c4b5fe5bbd7b2f0bbbff4110ffb2 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Mon, 6 Aug 2018 11:17:47 +0800 Subject: vhost: switch to use new message format We use to have message like: struct vhost_msg { int type; union { struct vhost_iotlb_msg iotlb; __u8 padding[64]; }; }; Unfortunately, there will be a hole of 32bit in 64bit machine because of the alignment. This leads a different formats between 32bit API and 64bit API. What's more it will break 32bit program running on 64bit machine. So fixing this by introducing a new message type with an explicit 32bit reserved field after type like: struct vhost_msg_v2 { __u32 type; __u32 reserved; union { struct vhost_iotlb_msg iotlb; __u8 padding[64]; }; }; We will have a consistent ABI after switching to use this. To enable this capability, introduce a new ioctl (VHOST_SET_BAKCEND_FEATURE) for userspace to enable this feature (VHOST_BACKEND_F_IOTLB_V2). Fixes: 6b1e6cc7855b ("vhost: new device IOTLB API") Signed-off-by: Jason Wang Signed-off-by: David S. Miller --- drivers/vhost/net.c | 30 ++++++++++++++++++++ drivers/vhost/vhost.c | 71 ++++++++++++++++++++++++++++++++++------------ drivers/vhost/vhost.h | 11 ++++++- include/uapi/linux/vhost.h | 18 ++++++++++++ 4 files changed, 111 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 367d8023b54d..4e656f89cb22 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -77,6 +77,10 @@ enum { (1ULL << VIRTIO_F_IOMMU_PLATFORM) }; +enum { + VHOST_NET_BACKEND_FEATURES = (1ULL << VHOST_BACKEND_F_IOTLB_MSG_V2) +}; + enum { VHOST_NET_VQ_RX = 0, VHOST_NET_VQ_TX = 1, @@ -1399,6 +1403,21 @@ done: return err; } +static int vhost_net_set_backend_features(struct vhost_net *n, u64 features) +{ + int i; + + mutex_lock(&n->dev.mutex); + for (i = 0; i < VHOST_NET_VQ_MAX; ++i) { + mutex_lock(&n->vqs[i].vq.mutex); + n->vqs[i].vq.acked_backend_features = features; + mutex_unlock(&n->vqs[i].vq.mutex); + } + mutex_unlock(&n->dev.mutex); + + return 0; +} + static int vhost_net_set_features(struct vhost_net *n, u64 features) { size_t vhost_hlen, sock_hlen, hdr_len; @@ -1489,6 +1508,17 @@ static long vhost_net_ioctl(struct file *f, unsigned int ioctl, if (features & ~VHOST_NET_FEATURES) return -EOPNOTSUPP; return vhost_net_set_features(n, features); + case VHOST_GET_BACKEND_FEATURES: + features = VHOST_NET_BACKEND_FEATURES; + if (copy_to_user(featurep, &features, sizeof(features))) + return -EFAULT; + return 0; + case VHOST_SET_BACKEND_FEATURES: + if (copy_from_user(&features, featurep, sizeof(features))) + return -EFAULT; + if (features & ~VHOST_NET_BACKEND_FEATURES) + return -EOPNOTSUPP; + return vhost_net_set_backend_features(n, features); case VHOST_RESET_OWNER: return vhost_net_reset_owner(n); case VHOST_SET_OWNER: diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index a502f1af4a21..6f6c42d5e4be 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -315,6 +315,7 @@ static void vhost_vq_reset(struct vhost_dev *dev, vq->log_addr = -1ull; vq->private_data = NULL; vq->acked_features = 0; + vq->acked_backend_features = 0; vq->log_base = NULL; vq->error_ctx = NULL; vq->kick = NULL; @@ -1027,28 +1028,40 @@ static int vhost_process_iotlb_msg(struct vhost_dev *dev, ssize_t vhost_chr_write_iter(struct vhost_dev *dev, struct iov_iter *from) { - struct vhost_msg_node node; - unsigned size = sizeof(struct vhost_msg); - size_t ret; - int err; + struct vhost_iotlb_msg msg; + size_t offset; + int type, ret; - if (iov_iter_count(from) < size) - return 0; - ret = copy_from_iter(&node.msg, size, from); - if (ret != size) + ret = copy_from_iter(&type, sizeof(type), from); + if (ret != sizeof(type)) goto done; - switch (node.msg.type) { + switch (type) { case VHOST_IOTLB_MSG: - err = vhost_process_iotlb_msg(dev, &node.msg.iotlb); - if (err) - ret = err; + /* There maybe a hole after type for V1 message type, + * so skip it here. + */ + offset = offsetof(struct vhost_msg, iotlb) - sizeof(int); + break; + case VHOST_IOTLB_MSG_V2: + offset = sizeof(__u32); break; default: ret = -EINVAL; - break; + goto done; + } + + iov_iter_advance(from, offset); + ret = copy_from_iter(&msg, sizeof(msg), from); + if (ret != sizeof(msg)) + goto done; + if (vhost_process_iotlb_msg(dev, &msg)) { + ret = -EFAULT; + goto done; } + ret = (type == VHOST_IOTLB_MSG) ? sizeof(struct vhost_msg) : + sizeof(struct vhost_msg_v2); done: return ret; } @@ -1107,13 +1120,28 @@ ssize_t vhost_chr_read_iter(struct vhost_dev *dev, struct iov_iter *to, finish_wait(&dev->wait, &wait); if (node) { - ret = copy_to_iter(&node->msg, size, to); + struct vhost_iotlb_msg *msg; + void *start = &node->msg; + + switch (node->msg.type) { + case VHOST_IOTLB_MSG: + size = sizeof(node->msg); + msg = &node->msg.iotlb; + break; + case VHOST_IOTLB_MSG_V2: + size = sizeof(node->msg_v2); + msg = &node->msg_v2.iotlb; + break; + default: + BUG(); + break; + } - if (ret != size || node->msg.type != VHOST_IOTLB_MISS) { + ret = copy_to_iter(start, size, to); + if (ret != size || msg->type != VHOST_IOTLB_MISS) { kfree(node); return ret; } - vhost_enqueue_msg(dev, &dev->pending_list, node); } @@ -1126,12 +1154,19 @@ static int vhost_iotlb_miss(struct vhost_virtqueue *vq, u64 iova, int access) struct vhost_dev *dev = vq->dev; struct vhost_msg_node *node; struct vhost_iotlb_msg *msg; + bool v2 = vhost_backend_has_feature(vq, VHOST_BACKEND_F_IOTLB_MSG_V2); - node = vhost_new_msg(vq, VHOST_IOTLB_MISS); + node = vhost_new_msg(vq, v2 ? VHOST_IOTLB_MSG_V2 : VHOST_IOTLB_MSG); if (!node) return -ENOMEM; - msg = &node->msg.iotlb; + if (v2) { + node->msg_v2.type = VHOST_IOTLB_MSG_V2; + msg = &node->msg_v2.iotlb; + } else { + msg = &node->msg.iotlb; + } + msg->type = VHOST_IOTLB_MISS; msg->iova = iova; msg->perm = access; diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index 6c844b90a168..466ef7542291 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -132,6 +132,7 @@ struct vhost_virtqueue { struct vhost_umem *iotlb; void *private_data; u64 acked_features; + u64 acked_backend_features; /* Log write descriptors */ void __user *log_base; struct vhost_log *log; @@ -147,7 +148,10 @@ struct vhost_virtqueue { }; struct vhost_msg_node { - struct vhost_msg msg; + union { + struct vhost_msg msg; + struct vhost_msg_v2 msg_v2; + }; struct vhost_virtqueue *vq; struct list_head node; }; @@ -238,6 +242,11 @@ static inline bool vhost_has_feature(struct vhost_virtqueue *vq, int bit) return vq->acked_features & (1ULL << bit); } +static inline bool vhost_backend_has_feature(struct vhost_virtqueue *vq, int bit) +{ + return vq->acked_backend_features & (1ULL << bit); +} + #ifdef CONFIG_VHOST_CROSS_ENDIAN_LEGACY static inline bool vhost_is_little_endian(struct vhost_virtqueue *vq) { diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h index c51f8e5cc608..b1e22c40c4b6 100644 --- a/include/uapi/linux/vhost.h +++ b/include/uapi/linux/vhost.h @@ -65,6 +65,7 @@ struct vhost_iotlb_msg { }; #define VHOST_IOTLB_MSG 0x1 +#define VHOST_IOTLB_MSG_V2 0x2 struct vhost_msg { int type; @@ -74,6 +75,15 @@ struct vhost_msg { }; }; +struct vhost_msg_v2 { + __u32 type; + __u32 reserved; + union { + struct vhost_iotlb_msg iotlb; + __u8 padding[64]; + }; +}; + struct vhost_memory_region { __u64 guest_phys_addr; __u64 memory_size; /* bytes */ @@ -160,6 +170,14 @@ struct vhost_memory { #define VHOST_GET_VRING_BUSYLOOP_TIMEOUT _IOW(VHOST_VIRTIO, 0x24, \ struct vhost_vring_state) +/* Set or get vhost backend capability */ + +/* Use message type V2 */ +#define VHOST_BACKEND_F_IOTLB_MSG_V2 0x1 + +#define VHOST_SET_BACKEND_FEATURES _IOW(VHOST_VIRTIO, 0x25, __u64) +#define VHOST_GET_BACKEND_FEATURES _IOW(VHOST_VIRTIO, 0x26, __u64) + /* VHOST_NET specific defines */ /* Attach virtio net ring to a raw socket, or tap device. -- cgit v1.2.3 From e4cc5a1873ac1297615962185f94adbbfaf6456b Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Mon, 6 Aug 2018 17:58:40 +0200 Subject: Bluetooth: btqca: Introduce HCI_EV_VENDOR and use it Using HCI_VENDOR_PKT for vendor specific events does work since it has also the value 0xff, but it is actually the packet type indicator constant and not the event constant. So introduce HCI_EV_VENDOR and use it. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- drivers/bluetooth/btqca.c | 6 +++--- include/net/bluetooth/hci.h | 2 ++ 2 files changed, 5 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/bluetooth/btqca.c b/drivers/bluetooth/btqca.c index 488f5e7521dd..ec9e03a6b778 100644 --- a/drivers/bluetooth/btqca.c +++ b/drivers/bluetooth/btqca.c @@ -39,7 +39,7 @@ int qca_read_soc_version(struct hci_dev *hdev, u32 *soc_version) cmd = EDL_PATCH_VER_REQ_CMD; skb = __hci_cmd_sync_ev(hdev, EDL_PATCH_CMD_OPCODE, EDL_PATCH_CMD_LEN, - &cmd, HCI_VENDOR_PKT, HCI_INIT_TIMEOUT); + &cmd, HCI_EV_VENDOR, HCI_INIT_TIMEOUT); if (IS_ERR(skb)) { err = PTR_ERR(skb); bt_dev_err(hdev, "Reading QCA version information failed (%d)", @@ -229,7 +229,7 @@ static int qca_tlv_send_segment(struct hci_dev *hdev, int seg_size, cmd); skb = __hci_cmd_sync_ev(hdev, EDL_PATCH_CMD_OPCODE, seg_size + 2, cmd, - HCI_VENDOR_PKT, HCI_INIT_TIMEOUT); + HCI_EV_VENDOR, HCI_INIT_TIMEOUT); if (IS_ERR(skb)) { err = PTR_ERR(skb); bt_dev_err(hdev, "QCA Failed to send TLV segment (%d)", err); @@ -318,7 +318,7 @@ int qca_set_bdaddr_rome(struct hci_dev *hdev, const bdaddr_t *bdaddr) cmd[2] = sizeof(bdaddr_t); /* size */ memcpy(cmd + 3, bdaddr, sizeof(bdaddr_t)); skb = __hci_cmd_sync_ev(hdev, EDL_NVM_ACCESS_OPCODE, sizeof(cmd), cmd, - HCI_VENDOR_PKT, HCI_INIT_TIMEOUT); + HCI_EV_VENDOR, HCI_INIT_TIMEOUT); if (IS_ERR(skb)) { err = PTR_ERR(skb); bt_dev_err(hdev, "QCA Change address command failed (%d)", err); diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 7f008097552e..4619a79b1bbb 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -2176,6 +2176,8 @@ struct hci_evt_le_ext_adv_set_term { __u8 num_evts; } __packed; +#define HCI_EV_VENDOR 0xff + /* Internal events generated by Bluetooth stack */ #define HCI_EV_STACK_INTERNAL 0xfd struct hci_ev_stack_internal { -- cgit v1.2.3 From bc2d8d262cba5736332cbc866acb11b1c5748aa9 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 7 Aug 2018 08:19:57 +0200 Subject: cpu/hotplug: Fix SMT supported evaluation Josh reported that the late SMT evaluation in cpu_smt_state_init() sets cpu_smt_control to CPU_SMT_NOT_SUPPORTED in case that 'nosmt' was supplied on the kernel command line as it cannot differentiate between SMT disabled by BIOS and SMT soft disable via 'nosmt'. That wreckages the state and makes the sysfs interface unusable. Rework this so that during bringup of the non boot CPUs the availability of SMT is determined in cpu_smt_allowed(). If a newly booted CPU is not a 'primary' thread then set the local cpu_smt_available marker and evaluate this explicitely right after the initial SMP bringup has finished. SMT evaulation on x86 is a trainwreck as the firmware has all the information _before_ booting the kernel, but there is no interface to query it. Fixes: 73d5e2b47264 ("cpu/hotplug: detect SMT disabled by BIOS") Reported-by: Josh Poimboeuf Signed-off-by: Thomas Gleixner --- arch/x86/kernel/cpu/bugs.c | 2 +- include/linux/cpu.h | 2 ++ kernel/cpu.c | 41 ++++++++++++++++++++++++++++------------- kernel/smp.c | 2 ++ 4 files changed, 33 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 86f4549b7c9f..be79b7599dda 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -63,7 +63,7 @@ void __init check_bugs(void) * identify_boot_cpu() initialized SMT support information, let the * core code know. */ - cpu_smt_check_topology(); + cpu_smt_check_topology_early(); if (!IS_ENABLED(CONFIG_SMP)) { pr_info("CPU: "); diff --git a/include/linux/cpu.h b/include/linux/cpu.h index ccdf3a67ce56..b216bd5bfd20 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -178,10 +178,12 @@ enum cpuhp_smt_control { #if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_SMT) extern enum cpuhp_smt_control cpu_smt_control; extern void cpu_smt_disable(bool force); +extern void cpu_smt_check_topology_early(void); extern void cpu_smt_check_topology(void); #else # define cpu_smt_control (CPU_SMT_ENABLED) static inline void cpu_smt_disable(bool force) { } +static inline void cpu_smt_check_topology_early(void) { } static inline void cpu_smt_check_topology(void) { } #endif diff --git a/kernel/cpu.c b/kernel/cpu.c index 2bc3d2f5b2a5..9d2512dd263c 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -347,6 +347,8 @@ EXPORT_SYMBOL_GPL(cpu_hotplug_enable); enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED; EXPORT_SYMBOL_GPL(cpu_smt_control); +static bool cpu_smt_available __read_mostly; + void __init cpu_smt_disable(bool force) { if (cpu_smt_control == CPU_SMT_FORCE_DISABLED || @@ -363,14 +365,28 @@ void __init cpu_smt_disable(bool force) /* * The decision whether SMT is supported can only be done after the full - * CPU identification. Called from architecture code. + * CPU identification. Called from architecture code before non boot CPUs + * are brought up. */ -void __init cpu_smt_check_topology(void) +void __init cpu_smt_check_topology_early(void) { if (!topology_smt_supported()) cpu_smt_control = CPU_SMT_NOT_SUPPORTED; } +/* + * If SMT was disabled by BIOS, detect it here, after the CPUs have been + * brought online. This ensures the smt/l1tf sysfs entries are consistent + * with reality. cpu_smt_available is set to true during the bringup of non + * boot CPUs when a SMT sibling is detected. Note, this may overwrite + * cpu_smt_control's previous setting. + */ +void __init cpu_smt_check_topology(void) +{ + if (!cpu_smt_available) + cpu_smt_control = CPU_SMT_NOT_SUPPORTED; +} + static int __init smt_cmdline_disable(char *str) { cpu_smt_disable(str && !strcmp(str, "force")); @@ -380,10 +396,18 @@ early_param("nosmt", smt_cmdline_disable); static inline bool cpu_smt_allowed(unsigned int cpu) { - if (cpu_smt_control == CPU_SMT_ENABLED) + if (topology_is_primary_thread(cpu)) return true; - if (topology_is_primary_thread(cpu)) + /* + * If the CPU is not a 'primary' thread and the booted_once bit is + * set then the processor has SMT support. Store this information + * for the late check of SMT support in cpu_smt_check_topology(). + */ + if (per_cpu(cpuhp_state, cpu).booted_once) + cpu_smt_available = true; + + if (cpu_smt_control == CPU_SMT_ENABLED) return true; /* @@ -2125,15 +2149,6 @@ static const struct attribute_group cpuhp_smt_attr_group = { static int __init cpu_smt_state_init(void) { - /* - * If SMT was disabled by BIOS, detect it here, after the CPUs have - * been brought online. This ensures the smt/l1tf sysfs entries are - * consistent with reality. Note this may overwrite cpu_smt_control's - * previous setting. - */ - if (topology_max_smt_threads() == 1) - cpu_smt_control = CPU_SMT_NOT_SUPPORTED; - return sysfs_create_group(&cpu_subsys.dev_root->kobj, &cpuhp_smt_attr_group); } diff --git a/kernel/smp.c b/kernel/smp.c index 084c8b3a2681..d86eec5f51c1 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -584,6 +584,8 @@ void __init smp_init(void) num_nodes, (num_nodes > 1 ? "s" : ""), num_cpus, (num_cpus > 1 ? "s" : "")); + /* Final decision about SMT support */ + cpu_smt_check_topology(); /* Any cleanup work */ smp_cpus_done(setup_max_cpus); } -- cgit v1.2.3 From 35a8a3bd1c2e29bb6baec501c6f56abaaa10a48a Mon Sep 17 00:00:00 2001 From: Fernando Fernandez Mancera Date: Tue, 7 Aug 2018 11:43:02 +0200 Subject: netfilter: nft_osf: use NFT_OSF_MAXGENRELEN instead of IFNAMSIZ As no "genre" on pf.os exceed 16 bytes of length, we reduce NFT_OSF_MAXGENRELEN parameter to 16 bytes and use it instead of IFNAMSIZ. Signed-off-by: Fernando Fernandez Mancera Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 1 + net/netfilter/nft_osf.c | 8 +++----- 2 files changed, 4 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 357862d948de..94657c701f22 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -8,6 +8,7 @@ #define NFT_SET_MAXNAMELEN NFT_NAME_MAXLEN #define NFT_OBJ_MAXNAMELEN NFT_NAME_MAXLEN #define NFT_USERDATA_MAXLEN 256 +#define NFT_OSF_MAXGENRELEN 16 /** * enum nft_registers - nf_tables registers diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c index 9b2f3de7be4f..5af74b37f423 100644 --- a/net/netfilter/nft_osf.c +++ b/net/netfilter/nft_osf.c @@ -4,8 +4,6 @@ #include #include -#define OSF_GENRE_SIZE 32 - struct nft_osf { enum nft_registers dreg:8; }; @@ -37,9 +35,9 @@ static void nft_osf_eval(const struct nft_expr *expr, struct nft_regs *regs, os_name = nf_osf_find(skb, nf_osf_fingers); if (!os_name) - strncpy((char *)dest, "unknown", IFNAMSIZ); + strncpy((char *)dest, "unknown", NFT_OSF_MAXGENRELEN); else - strncpy((char *)dest, os_name, IFNAMSIZ); + strncpy((char *)dest, os_name, NFT_OSF_MAXGENRELEN); } static int nft_osf_init(const struct nft_ctx *ctx, @@ -51,7 +49,7 @@ static int nft_osf_init(const struct nft_ctx *ctx, priv->dreg = nft_parse_register(tb[NFTA_OSF_DREG]); err = nft_validate_register_store(ctx, priv->dreg, NULL, - NFTA_DATA_VALUE, OSF_GENRE_SIZE); + NFTA_DATA_VALUE, NFT_OSF_MAXGENRELEN); if (err < 0) return err; -- cgit v1.2.3 From 4e665afbd7bee29b44b5d22821b56207f8459e39 Mon Sep 17 00:00:00 2001 From: Harsha Sharma Date: Tue, 7 Aug 2018 17:14:10 +0200 Subject: netfilter: cttimeout: move ctnl_untimeout to nf_conntrack As, ctnl_untimeout is required by nft_ct, so move ctnl_timeout from nfnetlink_cttimeout to nf_conntrack_timeout and rename as nf_ct_timeout. Signed-off-by: Harsha Sharma Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_timeout.h | 1 + net/netfilter/nf_conntrack_timeout.c | 17 +++++++++++++++++ net/netfilter/nfnetlink_cttimeout.c | 20 ++------------------ 3 files changed, 20 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_timeout.h b/include/net/netfilter/nf_conntrack_timeout.h index 80ceb3d0291d..7a21bc0f00eb 100644 --- a/include/net/netfilter/nf_conntrack_timeout.h +++ b/include/net/netfilter/nf_conntrack_timeout.h @@ -83,6 +83,7 @@ static inline unsigned int *nf_ct_timeout_lookup(const struct nf_conn *ct) #ifdef CONFIG_NF_CONNTRACK_TIMEOUT int nf_conntrack_timeout_init(void); void nf_conntrack_timeout_fini(void); +void nf_ct_untimeout(struct net *net, struct ctnl_timeout *timeout); #else static inline int nf_conntrack_timeout_init(void) { diff --git a/net/netfilter/nf_conntrack_timeout.c b/net/netfilter/nf_conntrack_timeout.c index 46aee65f339b..401c2cce4a61 100644 --- a/net/netfilter/nf_conntrack_timeout.c +++ b/net/netfilter/nf_conntrack_timeout.c @@ -31,6 +31,23 @@ EXPORT_SYMBOL_GPL(nf_ct_timeout_find_get_hook); void (*nf_ct_timeout_put_hook)(struct ctnl_timeout *timeout) __read_mostly; EXPORT_SYMBOL_GPL(nf_ct_timeout_put_hook); +static int untimeout(struct nf_conn *ct, void *timeout) +{ + struct nf_conn_timeout *timeout_ext = nf_ct_timeout_find(ct); + + if (timeout_ext && (!timeout || timeout_ext->timeout == timeout)) + RCU_INIT_POINTER(timeout_ext->timeout, NULL); + + /* We are not intended to delete this conntrack. */ + return 0; +} + +void nf_ct_untimeout(struct net *net, struct ctnl_timeout *timeout) +{ + nf_ct_iterate_cleanup_net(net, untimeout, timeout, 0, 0); +} +EXPORT_SYMBOL_GPL(nf_ct_untimeout); + static const struct nf_ct_ext_type timeout_extend = { .len = sizeof(struct nf_conn_timeout), .align = __alignof__(struct nf_conn_timeout), diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index 4199e5300575..df53aef2d642 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -297,22 +297,6 @@ static int cttimeout_get_timeout(struct net *net, struct sock *ctnl, return ret; } -static int untimeout(struct nf_conn *ct, void *timeout) -{ - struct nf_conn_timeout *timeout_ext = nf_ct_timeout_find(ct); - - if (timeout_ext && (!timeout || timeout_ext->timeout == timeout)) - RCU_INIT_POINTER(timeout_ext->timeout, NULL); - - /* We are not intended to delete this conntrack. */ - return 0; -} - -static void ctnl_untimeout(struct net *net, struct ctnl_timeout *timeout) -{ - nf_ct_iterate_cleanup_net(net, untimeout, timeout, 0, 0); -} - /* try to delete object, fail if it is still in use. */ static int ctnl_timeout_try_del(struct net *net, struct ctnl_timeout *timeout) { @@ -325,7 +309,7 @@ static int ctnl_timeout_try_del(struct net *net, struct ctnl_timeout *timeout) /* We are protected by nfnl mutex. */ list_del_rcu(&timeout->head); nf_ct_l4proto_put(timeout->l4proto); - ctnl_untimeout(net, timeout); + nf_ct_untimeout(net, timeout); kfree_rcu(timeout, rcu_head); } else { ret = -EBUSY; @@ -573,7 +557,7 @@ static void __net_exit cttimeout_net_exit(struct net *net) struct ctnl_timeout *cur, *tmp; nf_ct_unconfirmed_destroy(net); - ctnl_untimeout(net, NULL); + nf_ct_untimeout(net, NULL); list_for_each_entry_safe(cur, tmp, &net->nfct_timeout_list, head) { list_del_rcu(&cur->head); -- cgit v1.2.3 From 6c1fd7dc489d9bf64196f5b0fa33e059f64460c8 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 7 Aug 2018 17:14:15 +0200 Subject: netfilter: cttimeout: decouple timeout policy from nfnetlink_cttimeout object The timeout policy is currently embedded into the nfnetlink_cttimeout object, move the policy into an independent object. This allows us to reuse part of the existing conntrack timeout extension from nf_tables without adding dependencies with the nfnetlink_cttimeout object layout. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_timeout.h | 22 ++++++++++------- net/netfilter/nf_conntrack_timeout.c | 6 ++--- net/netfilter/nfnetlink_cttimeout.c | 37 ++++++++++++++++------------ net/netfilter/xt_CT.c | 4 +-- 4 files changed, 39 insertions(+), 30 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_timeout.h b/include/net/netfilter/nf_conntrack_timeout.h index 7a21bc0f00eb..d5f62cc6c2ae 100644 --- a/include/net/netfilter/nf_conntrack_timeout.h +++ b/include/net/netfilter/nf_conntrack_timeout.h @@ -11,24 +11,28 @@ #define CTNL_TIMEOUT_NAME_MAX 32 +struct nf_ct_timeout { + __u16 l3num; + const struct nf_conntrack_l4proto *l4proto; + char data[0]; +}; + struct ctnl_timeout { struct list_head head; struct rcu_head rcu_head; refcount_t refcnt; char name[CTNL_TIMEOUT_NAME_MAX]; - __u16 l3num; - const struct nf_conntrack_l4proto *l4proto; - char data[0]; + struct nf_ct_timeout timeout; }; struct nf_conn_timeout { - struct ctnl_timeout __rcu *timeout; + struct nf_ct_timeout __rcu *timeout; }; static inline unsigned int * nf_ct_timeout_data(struct nf_conn_timeout *t) { - struct ctnl_timeout *timeout; + struct nf_ct_timeout *timeout; timeout = rcu_dereference(t->timeout); if (timeout == NULL) @@ -49,7 +53,7 @@ struct nf_conn_timeout *nf_ct_timeout_find(const struct nf_conn *ct) static inline struct nf_conn_timeout *nf_ct_timeout_ext_add(struct nf_conn *ct, - struct ctnl_timeout *timeout, + struct nf_ct_timeout *timeout, gfp_t gfp) { #ifdef CONFIG_NF_CONNTRACK_TIMEOUT @@ -83,7 +87,7 @@ static inline unsigned int *nf_ct_timeout_lookup(const struct nf_conn *ct) #ifdef CONFIG_NF_CONNTRACK_TIMEOUT int nf_conntrack_timeout_init(void); void nf_conntrack_timeout_fini(void); -void nf_ct_untimeout(struct net *net, struct ctnl_timeout *timeout); +void nf_ct_untimeout(struct net *net, struct nf_ct_timeout *timeout); #else static inline int nf_conntrack_timeout_init(void) { @@ -97,8 +101,8 @@ static inline void nf_conntrack_timeout_fini(void) #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ #ifdef CONFIG_NF_CONNTRACK_TIMEOUT -extern struct ctnl_timeout *(*nf_ct_timeout_find_get_hook)(struct net *net, const char *name); -extern void (*nf_ct_timeout_put_hook)(struct ctnl_timeout *timeout); +extern struct nf_ct_timeout *(*nf_ct_timeout_find_get_hook)(struct net *net, const char *name); +extern void (*nf_ct_timeout_put_hook)(struct nf_ct_timeout *timeout); #endif #endif /* _NF_CONNTRACK_TIMEOUT_H */ diff --git a/net/netfilter/nf_conntrack_timeout.c b/net/netfilter/nf_conntrack_timeout.c index 401c2cce4a61..91fbd183da2d 100644 --- a/net/netfilter/nf_conntrack_timeout.c +++ b/net/netfilter/nf_conntrack_timeout.c @@ -24,11 +24,11 @@ #include #include -struct ctnl_timeout * +struct nf_ct_timeout * (*nf_ct_timeout_find_get_hook)(struct net *net, const char *name) __read_mostly; EXPORT_SYMBOL_GPL(nf_ct_timeout_find_get_hook); -void (*nf_ct_timeout_put_hook)(struct ctnl_timeout *timeout) __read_mostly; +void (*nf_ct_timeout_put_hook)(struct nf_ct_timeout *timeout) __read_mostly; EXPORT_SYMBOL_GPL(nf_ct_timeout_put_hook); static int untimeout(struct nf_conn *ct, void *timeout) @@ -42,7 +42,7 @@ static int untimeout(struct nf_conn *ct, void *timeout) return 0; } -void nf_ct_untimeout(struct net *net, struct ctnl_timeout *timeout) +void nf_ct_untimeout(struct net *net, struct nf_ct_timeout *timeout) { nf_ct_iterate_cleanup_net(net, untimeout, timeout, 0, 0); } diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index df53aef2d642..d46a236cdf31 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -113,13 +113,13 @@ static int cttimeout_new_timeout(struct net *net, struct sock *ctnl, /* You cannot replace one timeout policy by another of * different kind, sorry. */ - if (matching->l3num != l3num || - matching->l4proto->l4proto != l4num) + if (matching->timeout.l3num != l3num || + matching->timeout.l4proto->l4proto != l4num) return -EINVAL; - return ctnl_timeout_parse_policy(&matching->data, - matching->l4proto, net, - cda[CTA_TIMEOUT_DATA]); + return ctnl_timeout_parse_policy(&matching->timeout.data, + matching->timeout.l4proto, + net, cda[CTA_TIMEOUT_DATA]); } return -EBUSY; @@ -140,14 +140,14 @@ static int cttimeout_new_timeout(struct net *net, struct sock *ctnl, goto err_proto_put; } - ret = ctnl_timeout_parse_policy(&timeout->data, l4proto, net, + ret = ctnl_timeout_parse_policy(&timeout->timeout.data, l4proto, net, cda[CTA_TIMEOUT_DATA]); if (ret < 0) goto err; strcpy(timeout->name, nla_data(cda[CTA_TIMEOUT_NAME])); - timeout->l3num = l3num; - timeout->l4proto = l4proto; + timeout->timeout.l3num = l3num; + timeout->timeout.l4proto = l4proto; refcount_set(&timeout->refcnt, 1); list_add_tail_rcu(&timeout->head, &net->nfct_timeout_list); @@ -166,7 +166,7 @@ ctnl_timeout_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; unsigned int flags = portid ? NLM_F_MULTI : 0; - const struct nf_conntrack_l4proto *l4proto = timeout->l4proto; + const struct nf_conntrack_l4proto *l4proto = timeout->timeout.l4proto; event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK_TIMEOUT, event); nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); @@ -179,8 +179,9 @@ ctnl_timeout_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, nfmsg->res_id = 0; if (nla_put_string(skb, CTA_TIMEOUT_NAME, timeout->name) || - nla_put_be16(skb, CTA_TIMEOUT_L3PROTO, htons(timeout->l3num)) || - nla_put_u8(skb, CTA_TIMEOUT_L4PROTO, timeout->l4proto->l4proto) || + nla_put_be16(skb, CTA_TIMEOUT_L3PROTO, + htons(timeout->timeout.l3num)) || + nla_put_u8(skb, CTA_TIMEOUT_L4PROTO, l4proto->l4proto) || nla_put_be32(skb, CTA_TIMEOUT_USE, htonl(refcount_read(&timeout->refcnt)))) goto nla_put_failure; @@ -194,7 +195,8 @@ ctnl_timeout_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, if (!nest_parms) goto nla_put_failure; - ret = l4proto->ctnl_timeout.obj_to_nlattr(skb, &timeout->data); + ret = l4proto->ctnl_timeout.obj_to_nlattr(skb, + &timeout->timeout.data); if (ret < 0) goto nla_put_failure; @@ -308,8 +310,8 @@ static int ctnl_timeout_try_del(struct net *net, struct ctnl_timeout *timeout) if (refcount_dec_if_one(&timeout->refcnt)) { /* We are protected by nfnl mutex. */ list_del_rcu(&timeout->head); - nf_ct_l4proto_put(timeout->l4proto); - nf_ct_untimeout(net, timeout); + nf_ct_l4proto_put(timeout->timeout.l4proto); + nf_ct_untimeout(net, &timeout->timeout); kfree_rcu(timeout, rcu_head); } else { ret = -EBUSY; @@ -510,8 +512,11 @@ err: return matching; } -static void ctnl_timeout_put(struct ctnl_timeout *timeout) +static void ctnl_timeout_put(struct nf_ct_timeout *t) { + struct ctnl_timeout *timeout = + container_of(t, struct ctnl_timeout, timeout); + if (refcount_dec_and_test(&timeout->refcnt)) kfree_rcu(timeout, rcu_head); @@ -561,7 +566,7 @@ static void __net_exit cttimeout_net_exit(struct net *net) list_for_each_entry_safe(cur, tmp, &net->nfct_timeout_list, head) { list_del_rcu(&cur->head); - nf_ct_l4proto_put(cur->l4proto); + nf_ct_l4proto_put(cur->timeout.l4proto); if (refcount_dec_and_test(&cur->refcnt)) kfree_rcu(cur, rcu_head); diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index 7ba454e9e3fa..89457efd2e00 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -104,7 +104,7 @@ xt_ct_set_helper(struct nf_conn *ct, const char *helper_name, } #ifdef CONFIG_NF_CONNTRACK_TIMEOUT -static void __xt_ct_tg_timeout_put(struct ctnl_timeout *timeout) +static void __xt_ct_tg_timeout_put(struct nf_ct_timeout *timeout) { typeof(nf_ct_timeout_put_hook) timeout_put; @@ -121,7 +121,7 @@ xt_ct_set_timeout(struct nf_conn *ct, const struct xt_tgchk_param *par, #ifdef CONFIG_NF_CONNTRACK_TIMEOUT typeof(nf_ct_timeout_find_get_hook) timeout_find_get; const struct nf_conntrack_l4proto *l4proto; - struct ctnl_timeout *timeout; + struct nf_ct_timeout *timeout; struct nf_conn_timeout *timeout_ext; const char *errmsg = NULL; int ret = 0; -- cgit v1.2.3 From ad83f2a9ce37a264202f48f4fd8889ee9056b703 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 7 Aug 2018 17:14:19 +0200 Subject: netfilter: remove ifdef around cttimeout in struct nf_conntrack_l4proto Simplify this, include it inconditionally in this structure layout as we do with ctnetlink. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_l4proto.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index 6068c6da3eac..8465263b297d 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -77,7 +77,6 @@ struct nf_conntrack_l4proto { struct nf_conntrack_tuple *t); const struct nla_policy *nla_policy; -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) struct { int (*nlattr_to_obj)(struct nlattr *tb[], struct net *net, void *data); @@ -87,7 +86,6 @@ struct nf_conntrack_l4proto { u16 nlattr_max; const struct nla_policy *nla_policy; } ctnl_timeout; -#endif #ifdef CONFIG_NF_CONNTRACK_PROCFS /* Print out the private part of the conntrack. */ void (*print_conntrack)(struct seq_file *s, struct nf_conn *); -- cgit v1.2.3 From 7e0b2b57f01d183e1c84114f1f2287737358d748 Mon Sep 17 00:00:00 2001 From: Harsha Sharma Date: Tue, 7 Aug 2018 17:14:23 +0200 Subject: netfilter: nft_ct: add ct timeout support This patch allows to add, list and delete connection tracking timeout policies via nft objref infrastructure and assigning these timeout via nft rule. %./libnftnl/examples/nft-ct-timeout-add ip raw cttime tcp Ruleset: table ip raw { ct timeout cttime { protocol tcp; policy = {established: 111, close: 13 } } chain output { type filter hook output priority -300; policy accept; ct timeout set "cttime" } } %./libnftnl/examples/nft-rule-ct-timeout-add ip raw output cttime %conntrack -E [NEW] tcp 6 111 ESTABLISHED src=172.16.19.128 dst=172.16.19.1 sport=22 dport=41360 [UNREPLIED] src=172.16.19.1 dst=172.16.19.128 sport=41360 dport=22 %nft delete rule ip raw output handle %./libnftnl/examples/nft-ct-timeout-del ip raw cttime Joint work with Pablo Neira. Signed-off-by: Harsha Sharma Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 14 ++- net/netfilter/nft_ct.c | 204 ++++++++++++++++++++++++++++++- 2 files changed, 216 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 94657c701f22..e23290ffdc77 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -958,6 +958,7 @@ enum nft_socket_keys { * @NFT_CT_DST_IP: conntrack layer 3 protocol destination (IPv4 address) * @NFT_CT_SRC_IP6: conntrack layer 3 protocol source (IPv6 address) * @NFT_CT_DST_IP6: conntrack layer 3 protocol destination (IPv6 address) + * @NFT_CT_TIMEOUT: connection tracking timeout policy assigned to conntrack */ enum nft_ct_keys { NFT_CT_STATE, @@ -983,6 +984,7 @@ enum nft_ct_keys { NFT_CT_DST_IP, NFT_CT_SRC_IP6, NFT_CT_DST_IP6, + NFT_CT_TIMEOUT, __NFT_CT_MAX }; #define NFT_CT_MAX (__NFT_CT_MAX - 1) @@ -1411,6 +1413,15 @@ enum nft_ct_helper_attributes { }; #define NFTA_CT_HELPER_MAX (__NFTA_CT_HELPER_MAX - 1) +enum nft_ct_timeout_timeout_attributes { + NFTA_CT_TIMEOUT_UNSPEC, + NFTA_CT_TIMEOUT_L3PROTO, + NFTA_CT_TIMEOUT_L4PROTO, + NFTA_CT_TIMEOUT_DATA, + __NFTA_CT_TIMEOUT_MAX, +}; +#define NFTA_CT_TIMEOUT_MAX (__NFTA_CT_TIMEOUT_MAX - 1) + #define NFT_OBJECT_UNSPEC 0 #define NFT_OBJECT_COUNTER 1 #define NFT_OBJECT_QUOTA 2 @@ -1418,7 +1429,8 @@ enum nft_ct_helper_attributes { #define NFT_OBJECT_LIMIT 4 #define NFT_OBJECT_CONNLIMIT 5 #define NFT_OBJECT_TUNNEL 6 -#define __NFT_OBJECT_MAX 7 +#define NFT_OBJECT_CT_TIMEOUT 7 +#define __NFT_OBJECT_MAX 8 #define NFT_OBJECT_MAX (__NFT_OBJECT_MAX - 1) /** diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 3bc82ee5464d..4788458a0931 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -22,6 +22,8 @@ #include #include #include +#include +#include struct nft_ct { enum nft_ct_keys key:8; @@ -765,6 +767,194 @@ static struct nft_expr_type nft_notrack_type __read_mostly = { .owner = THIS_MODULE, }; +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT +static int +nft_ct_timeout_parse_policy(void *timeouts, + const struct nf_conntrack_l4proto *l4proto, + struct net *net, const struct nlattr *attr) +{ + struct nlattr **tb; + int ret = 0; + + if (!l4proto->ctnl_timeout.nlattr_to_obj) + return 0; + + tb = kcalloc(l4proto->ctnl_timeout.nlattr_max + 1, sizeof(*tb), + GFP_KERNEL); + + if (!tb) + return -ENOMEM; + + ret = nla_parse_nested(tb, l4proto->ctnl_timeout.nlattr_max, + attr, l4proto->ctnl_timeout.nla_policy, + NULL); + if (ret < 0) + goto err; + + ret = l4proto->ctnl_timeout.nlattr_to_obj(tb, net, timeouts); + +err: + kfree(tb); + return ret; +} + +struct nft_ct_timeout_obj { + struct nf_conn *tmpl; + u8 l4proto; +}; + +static void nft_ct_timeout_obj_eval(struct nft_object *obj, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + const struct nft_ct_timeout_obj *priv = nft_obj_data(obj); + struct nf_conn *ct = (struct nf_conn *)skb_nfct(pkt->skb); + struct sk_buff *skb = pkt->skb; + + if (ct || + priv->l4proto != pkt->tprot) + return; + + nf_ct_set(skb, priv->tmpl, IP_CT_NEW); +} + +static int nft_ct_timeout_obj_init(const struct nft_ctx *ctx, + const struct nlattr * const tb[], + struct nft_object *obj) +{ + const struct nf_conntrack_zone *zone = &nf_ct_zone_dflt; + struct nft_ct_timeout_obj *priv = nft_obj_data(obj); + const struct nf_conntrack_l4proto *l4proto; + struct nf_conn_timeout *timeout_ext; + struct nf_ct_timeout *timeout; + int l3num = ctx->family; + struct nf_conn *tmpl; + __u8 l4num; + int ret; + + if (!tb[NFTA_CT_TIMEOUT_L3PROTO] || + !tb[NFTA_CT_TIMEOUT_L4PROTO] || + !tb[NFTA_CT_TIMEOUT_DATA]) + return -EINVAL; + + l3num = ntohs(nla_get_be16(tb[NFTA_CT_TIMEOUT_L3PROTO])); + l4num = nla_get_u8(tb[NFTA_CT_TIMEOUT_L4PROTO]); + priv->l4proto = l4num; + + l4proto = nf_ct_l4proto_find_get(l3num, l4num); + + if (l4proto->l4proto != l4num) { + ret = -EOPNOTSUPP; + goto err_proto_put; + } + + timeout = kzalloc(sizeof(struct nf_ct_timeout) + + l4proto->ctnl_timeout.obj_size, GFP_KERNEL); + if (timeout == NULL) { + ret = -ENOMEM; + goto err_proto_put; + } + + ret = nft_ct_timeout_parse_policy(&timeout->data, l4proto, ctx->net, + tb[NFTA_CT_TIMEOUT_DATA]); + if (ret < 0) + goto err_free_timeout; + + timeout->l3num = l3num; + timeout->l4proto = l4proto; + tmpl = nf_ct_tmpl_alloc(ctx->net, zone, GFP_ATOMIC); + if (!tmpl) { + ret = -ENOMEM; + goto err_free_timeout; + } + + timeout_ext = nf_ct_timeout_ext_add(tmpl, timeout, GFP_ATOMIC); + if (!timeout_ext) { + ret = -ENOMEM; + goto err_free_tmpl; + } + + ret = nf_ct_netns_get(ctx->net, ctx->family); + if (ret < 0) + goto err_free_tmpl; + + priv->tmpl = tmpl; + + return 0; + +err_free_tmpl: + nf_ct_tmpl_free(tmpl); +err_free_timeout: + kfree(timeout); +err_proto_put: + nf_ct_l4proto_put(l4proto); + return ret; +} + +static void nft_ct_timeout_obj_destroy(const struct nft_ctx *ctx, + struct nft_object *obj) +{ + struct nft_ct_timeout_obj *priv = nft_obj_data(obj); + struct nf_conn_timeout *t = nf_ct_timeout_find(priv->tmpl); + struct nf_ct_timeout *timeout; + + timeout = rcu_dereference_raw(t->timeout); + nf_ct_untimeout(ctx->net, timeout); + nf_ct_l4proto_put(timeout->l4proto); + nf_ct_netns_put(ctx->net, ctx->family); + nf_ct_tmpl_free(priv->tmpl); +} + +static int nft_ct_timeout_obj_dump(struct sk_buff *skb, + struct nft_object *obj, bool reset) +{ + const struct nft_ct_timeout_obj *priv = nft_obj_data(obj); + const struct nf_conn_timeout *t = nf_ct_timeout_find(priv->tmpl); + const struct nf_ct_timeout *timeout = rcu_dereference_raw(t->timeout); + struct nlattr *nest_params; + int ret; + + if (nla_put_u8(skb, NFTA_CT_TIMEOUT_L4PROTO, timeout->l4proto->l4proto) || + nla_put_be16(skb, NFTA_CT_TIMEOUT_L3PROTO, htons(timeout->l3num))) + return -1; + + nest_params = nla_nest_start(skb, NFTA_CT_TIMEOUT_DATA | NLA_F_NESTED); + if (!nest_params) + return -1; + + ret = timeout->l4proto->ctnl_timeout.obj_to_nlattr(skb, &timeout->data); + if (ret < 0) + return -1; + nla_nest_end(skb, nest_params); + return 0; +} + +static const struct nla_policy nft_ct_timeout_policy[NFTA_CT_TIMEOUT_MAX + 1] = { + [NFTA_CT_TIMEOUT_L3PROTO] = {.type = NLA_U16 }, + [NFTA_CT_TIMEOUT_L4PROTO] = {.type = NLA_U8 }, + [NFTA_CT_TIMEOUT_DATA] = {.type = NLA_NESTED }, +}; + +static struct nft_object_type nft_ct_timeout_obj_type; + +static const struct nft_object_ops nft_ct_timeout_obj_ops = { + .type = &nft_ct_timeout_obj_type, + .size = sizeof(struct nft_ct_timeout_obj), + .eval = nft_ct_timeout_obj_eval, + .init = nft_ct_timeout_obj_init, + .destroy = nft_ct_timeout_obj_destroy, + .dump = nft_ct_timeout_obj_dump, +}; + +static struct nft_object_type nft_ct_timeout_obj_type __read_mostly = { + .type = NFT_OBJECT_CT_TIMEOUT, + .ops = &nft_ct_timeout_obj_ops, + .maxattr = NFTA_CT_TIMEOUT_MAX, + .policy = nft_ct_timeout_policy, + .owner = THIS_MODULE, +}; +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ + static int nft_ct_helper_obj_init(const struct nft_ctx *ctx, const struct nlattr * const tb[], struct nft_object *obj) @@ -949,9 +1139,17 @@ static int __init nft_ct_module_init(void) err = nft_register_obj(&nft_ct_helper_obj_type); if (err < 0) goto err2; - +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT + err = nft_register_obj(&nft_ct_timeout_obj_type); + if (err < 0) + goto err3; +#endif return 0; +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT +err3: + nft_unregister_obj(&nft_ct_helper_obj_type); +#endif err2: nft_unregister_expr(&nft_notrack_type); err1: @@ -961,6 +1159,9 @@ err1: static void __exit nft_ct_module_exit(void) { +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT + nft_unregister_obj(&nft_ct_timeout_obj_type); +#endif nft_unregister_obj(&nft_ct_helper_obj_type); nft_unregister_expr(&nft_notrack_type); nft_unregister_expr(&nft_ct_type); @@ -974,3 +1175,4 @@ MODULE_AUTHOR("Patrick McHardy "); MODULE_ALIAS_NFT_EXPR("ct"); MODULE_ALIAS_NFT_EXPR("notrack"); MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_CT_HELPER); +MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_CT_TIMEOUT); -- cgit v1.2.3 From 6cfef793b558eee47bac720574aff0d36b89d20a Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Tue, 7 Aug 2018 10:50:20 -0700 Subject: ethtool: Add WAKE_FILTER and RX_CLS_FLOW_WAKE Add the ability to specify through ethtool::rxnfc that a rule location is special and will be used to participate in Wake-on-LAN, by e.g: having a specific pattern be matched. When this is the case, fs->ring_cookie must be set to the special value RX_CLS_FLOW_WAKE. We also define an additional ethtool::wolinfo flag: WAKE_FILTER which can be used to configure an Ethernet adapter to allow Wake-on-LAN using previously programmed filters. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/uapi/linux/ethtool.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 813282cc8af6..dc69391d2bba 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -870,7 +870,8 @@ struct ethtool_flow_ext { * includes the %FLOW_EXT or %FLOW_MAC_EXT flag * (see &struct ethtool_flow_ext description). * @ring_cookie: RX ring/queue index to deliver to, or %RX_CLS_FLOW_DISC - * if packets should be discarded + * if packets should be discarded, or %RX_CLS_FLOW_WAKE if the + * packets should be used for Wake-on-LAN with %WAKE_FILTER * @location: Location of rule in the table. Locations must be * numbered such that a flow matching multiple rules will be * classified according to the first (lowest numbered) rule. @@ -1634,6 +1635,7 @@ static inline int ethtool_validate_duplex(__u8 duplex) #define WAKE_ARP (1 << 4) #define WAKE_MAGIC (1 << 5) #define WAKE_MAGICSECURE (1 << 6) /* only meaningful if WAKE_MAGIC */ +#define WAKE_FILTER (1 << 7) /* L2-L4 network traffic flow types */ #define TCP_V4_FLOW 0x01 /* hash or spec (tcp_ip4_spec) */ @@ -1671,6 +1673,7 @@ static inline int ethtool_validate_duplex(__u8 duplex) #define RXH_DISCARD (1 << 31) #define RX_CLS_FLOW_DISC 0xffffffffffffffffULL +#define RX_CLS_FLOW_WAKE 0xfffffffffffffffeULL /* Special RX classification rule insert location values */ #define RX_CLS_LOC_SPECIAL 0x80000000 /* flag */ -- cgit v1.2.3 From 92e2c4053623f21d61a683f7ef7bd61c8300ac7d Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Tue, 7 Aug 2018 17:36:00 +0200 Subject: flow_dissector: allow dissection of tunnel options from metadata Allow the existing 'dissection' of tunnel metadata to 'dissect' options already present in tunnel metadata. This dissection is controlled by a new dissector key, FLOW_DISSECTOR_KEY_ENC_OPTS. This dissection only occurs when skb_flow_dissect_tunnel_info() is called, currently only the Flower classifier makes that call. So there should be no impact on other users of the flow dissector. This is in preparation for allowing the flower classifier to match on Geneve options. Signed-off-by: Simon Horman Signed-off-by: Pieter Jansen van Vuuren Reviewed-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/net/flow_dissector.h | 17 +++++++++++++++++ net/core/flow_dissector.c | 19 ++++++++++++++++++- 2 files changed, 35 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index 2a17f041f7a1..6a4586dcdede 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -57,6 +57,21 @@ struct flow_dissector_key_mpls { mpls_label:20; }; +#define FLOW_DIS_TUN_OPTS_MAX 255 +/** + * struct flow_dissector_key_enc_opts: + * @data: tunnel option data + * @len: length of tunnel option data + * @dst_opt_type: tunnel option type + */ +struct flow_dissector_key_enc_opts { + u8 data[FLOW_DIS_TUN_OPTS_MAX]; /* Using IP_TUNNEL_OPTS_MAX is desired + * here but seems difficult to #include + */ + u8 len; + __be16 dst_opt_type; +}; + struct flow_dissector_key_keyid { __be32 keyid; }; @@ -208,6 +223,8 @@ enum flow_dissector_key_id { FLOW_DISSECTOR_KEY_IP, /* struct flow_dissector_key_ip */ FLOW_DISSECTOR_KEY_CVLAN, /* struct flow_dissector_key_flow_vlan */ FLOW_DISSECTOR_KEY_ENC_IP, /* struct flow_dissector_key_ip */ + FLOW_DISSECTOR_KEY_ENC_OPTS, /* struct flow_dissector_key_enc_opts */ + FLOW_DISSECTOR_KEY_MAX, }; diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 08a5184f4b34..ce9eeeb7c024 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -154,7 +154,9 @@ skb_flow_dissect_tunnel_info(const struct sk_buff *skb, !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_PORTS) && !dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_ENC_IP)) + FLOW_DISSECTOR_KEY_ENC_IP) && + !dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_ENC_OPTS)) return; info = skb_tunnel_info(skb); @@ -224,6 +226,21 @@ skb_flow_dissect_tunnel_info(const struct sk_buff *skb, ip->tos = key->tos; ip->ttl = key->ttl; } + + if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_OPTS)) { + struct flow_dissector_key_enc_opts *enc_opt; + + enc_opt = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_ENC_OPTS, + target_container); + + if (info->options_len) { + enc_opt->len = info->options_len; + ip_tunnel_info_opts_get(enc_opt->data, info); + enc_opt->dst_opt_type = info->key.tun_flags & + TUNNEL_OPTIONS_PRESENT; + } + } } EXPORT_SYMBOL(skb_flow_dissect_tunnel_info); -- cgit v1.2.3 From 0a6e77784f490912d81b92cfd48424541c04691e Mon Sep 17 00:00:00 2001 From: Pieter Jansen van Vuuren Date: Tue, 7 Aug 2018 17:36:01 +0200 Subject: net/sched: allow flower to match tunnel options Allow matching on options in Geneve tunnel headers. This makes use of existing tunnel metadata support. The options can be described in the form CLASS:TYPE:DATA/CLASS_MASK:TYPE_MASK:DATA_MASK, where CLASS is represented as a 16bit hexadecimal value, TYPE as an 8bit hexadecimal value and DATA as a variable length hexadecimal value. e.g. # ip link add name geneve0 type geneve dstport 0 external # tc qdisc add dev geneve0 ingress # tc filter add dev geneve0 protocol ip parent ffff: \ flower \ enc_src_ip 10.0.99.192 \ enc_dst_ip 10.0.99.193 \ enc_key_id 11 \ geneve_opts 0102:80:1122334421314151/ffff:ff:ffffffffffffffff \ ip_proto udp \ action mirred egress redirect dev eth1 This patch adds support for matching Geneve options in the order supplied by the user. This leads to an efficient implementation in the software datapath (and in our opinion hardware datapaths that offload this feature). It is also compatible with Geneve options matching provided by the Open vSwitch kernel datapath which is relevant here as the Flower classifier may be used as a mechanism to program flows into hardware as a form of Open vSwitch datapath offload (sometimes referred to as OVS-TC). The netlink Kernel/Userspace API may be extended, for example by adding a flag, if other matching options are desired, for example matching given options in any order. This would require an implementation in the TC software datapath. And be done in a way that drivers that facilitate offload of the Flower classifier can reject or accept such flows based on hardware datapath capabilities. This approach was discussed and agreed on at Netconf 2017 in Seoul. Signed-off-by: Simon Horman Signed-off-by: Pieter Jansen van Vuuren Acked-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/uapi/linux/pkt_cls.h | 26 +++++ net/sched/cls_flower.c | 244 ++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 269 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 48e5b5d49a34..be382fb0592d 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -480,11 +480,37 @@ enum { TCA_FLOWER_KEY_ENC_IP_TTL, /* u8 */ TCA_FLOWER_KEY_ENC_IP_TTL_MASK, /* u8 */ + TCA_FLOWER_KEY_ENC_OPTS, + TCA_FLOWER_KEY_ENC_OPTS_MASK, + __TCA_FLOWER_MAX, }; #define TCA_FLOWER_MAX (__TCA_FLOWER_MAX - 1) +enum { + TCA_FLOWER_KEY_ENC_OPTS_UNSPEC, + TCA_FLOWER_KEY_ENC_OPTS_GENEVE, /* Nested + * TCA_FLOWER_KEY_ENC_OPT_GENEVE_ + * attributes + */ + __TCA_FLOWER_KEY_ENC_OPTS_MAX, +}; + +#define TCA_FLOWER_KEY_ENC_OPTS_MAX (__TCA_FLOWER_KEY_ENC_OPTS_MAX - 1) + +enum { + TCA_FLOWER_KEY_ENC_OPT_GENEVE_UNSPEC, + TCA_FLOWER_KEY_ENC_OPT_GENEVE_CLASS, /* u16 */ + TCA_FLOWER_KEY_ENC_OPT_GENEVE_TYPE, /* u8 */ + TCA_FLOWER_KEY_ENC_OPT_GENEVE_DATA, /* 4 to 128 bytes */ + + __TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX, +}; + +#define TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX \ + (__TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX - 1) + enum { TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT = (1 << 0), TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST = (1 << 1), diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index a3b69bb6f4b0..9da244235170 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include @@ -53,6 +54,7 @@ struct fl_flow_key { struct flow_dissector_key_tcp tcp; struct flow_dissector_key_ip ip; struct flow_dissector_key_ip enc_ip; + struct flow_dissector_key_enc_opts enc_opts; } __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */ struct fl_flow_mask_range { @@ -482,6 +484,21 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { [TCA_FLOWER_KEY_ENC_IP_TOS_MASK] = { .type = NLA_U8 }, [TCA_FLOWER_KEY_ENC_IP_TTL] = { .type = NLA_U8 }, [TCA_FLOWER_KEY_ENC_IP_TTL_MASK] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_ENC_OPTS] = { .type = NLA_NESTED }, + [TCA_FLOWER_KEY_ENC_OPTS_MASK] = { .type = NLA_NESTED }, +}; + +static const struct nla_policy +enc_opts_policy[TCA_FLOWER_KEY_ENC_OPTS_MAX + 1] = { + [TCA_FLOWER_KEY_ENC_OPTS_GENEVE] = { .type = NLA_NESTED }, +}; + +static const struct nla_policy +geneve_opt_policy[TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX + 1] = { + [TCA_FLOWER_KEY_ENC_OPT_GENEVE_CLASS] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_ENC_OPT_GENEVE_TYPE] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_ENC_OPT_GENEVE_DATA] = { .type = NLA_BINARY, + .len = 128 }, }; static void fl_set_key_val(struct nlattr **tb, @@ -603,6 +620,145 @@ static void fl_set_key_ip(struct nlattr **tb, bool encap, fl_set_key_val(tb, &key->ttl, ttl_key, &mask->ttl, ttl_mask, sizeof(key->ttl)); } +static int fl_set_geneve_opt(const struct nlattr *nla, struct fl_flow_key *key, + int depth, int option_len, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX + 1]; + struct nlattr *class = NULL, *type = NULL, *data = NULL; + struct geneve_opt *opt; + int err, data_len = 0; + + if (option_len > sizeof(struct geneve_opt)) + data_len = option_len - sizeof(struct geneve_opt); + + opt = (struct geneve_opt *)&key->enc_opts.data[key->enc_opts.len]; + memset(opt, 0xff, option_len); + opt->length = data_len / 4; + opt->r1 = 0; + opt->r2 = 0; + opt->r3 = 0; + + /* If no mask has been prodived we assume an exact match. */ + if (!depth) + return sizeof(struct geneve_opt) + data_len; + + if (nla_type(nla) != TCA_FLOWER_KEY_ENC_OPTS_GENEVE) { + NL_SET_ERR_MSG(extack, "Non-geneve option type for mask"); + return -EINVAL; + } + + err = nla_parse_nested(tb, TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX, + nla, geneve_opt_policy, extack); + if (err < 0) + return err; + + /* We are not allowed to omit any of CLASS, TYPE or DATA + * fields from the key. + */ + if (!option_len && + (!tb[TCA_FLOWER_KEY_ENC_OPT_GENEVE_CLASS] || + !tb[TCA_FLOWER_KEY_ENC_OPT_GENEVE_TYPE] || + !tb[TCA_FLOWER_KEY_ENC_OPT_GENEVE_DATA])) { + NL_SET_ERR_MSG(extack, "Missing tunnel key geneve option class, type or data"); + return -EINVAL; + } + + /* Omitting any of CLASS, TYPE or DATA fields is allowed + * for the mask. + */ + if (tb[TCA_FLOWER_KEY_ENC_OPT_GENEVE_DATA]) { + int new_len = key->enc_opts.len; + + data = tb[TCA_FLOWER_KEY_ENC_OPT_GENEVE_DATA]; + data_len = nla_len(data); + if (data_len < 4) { + NL_SET_ERR_MSG(extack, "Tunnel key geneve option data is less than 4 bytes long"); + return -ERANGE; + } + if (data_len % 4) { + NL_SET_ERR_MSG(extack, "Tunnel key geneve option data is not a multiple of 4 bytes long"); + return -ERANGE; + } + + new_len += sizeof(struct geneve_opt) + data_len; + BUILD_BUG_ON(FLOW_DIS_TUN_OPTS_MAX != IP_TUNNEL_OPTS_MAX); + if (new_len > FLOW_DIS_TUN_OPTS_MAX) { + NL_SET_ERR_MSG(extack, "Tunnel options exceeds max size"); + return -ERANGE; + } + opt->length = data_len / 4; + memcpy(opt->opt_data, nla_data(data), data_len); + } + + if (tb[TCA_FLOWER_KEY_ENC_OPT_GENEVE_CLASS]) { + class = tb[TCA_FLOWER_KEY_ENC_OPT_GENEVE_CLASS]; + opt->opt_class = nla_get_be16(class); + } + + if (tb[TCA_FLOWER_KEY_ENC_OPT_GENEVE_TYPE]) { + type = tb[TCA_FLOWER_KEY_ENC_OPT_GENEVE_TYPE]; + opt->type = nla_get_u8(type); + } + + return sizeof(struct geneve_opt) + data_len; +} + +static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, + struct fl_flow_key *mask, + struct netlink_ext_ack *extack) +{ + const struct nlattr *nla_enc_key, *nla_opt_key, *nla_opt_msk = NULL; + int option_len, key_depth, msk_depth = 0; + + nla_enc_key = nla_data(tb[TCA_FLOWER_KEY_ENC_OPTS]); + + if (tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]) { + nla_opt_msk = nla_data(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]); + msk_depth = nla_len(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]); + } + + nla_for_each_attr(nla_opt_key, nla_enc_key, + nla_len(tb[TCA_FLOWER_KEY_ENC_OPTS]), key_depth) { + switch (nla_type(nla_opt_key)) { + case TCA_FLOWER_KEY_ENC_OPTS_GENEVE: + option_len = 0; + key->enc_opts.dst_opt_type = TUNNEL_GENEVE_OPT; + option_len = fl_set_geneve_opt(nla_opt_key, key, + key_depth, option_len, + extack); + if (option_len < 0) + return option_len; + + key->enc_opts.len += option_len; + /* At the same time we need to parse through the mask + * in order to verify exact and mask attribute lengths. + */ + mask->enc_opts.dst_opt_type = TUNNEL_GENEVE_OPT; + option_len = fl_set_geneve_opt(nla_opt_msk, mask, + msk_depth, option_len, + extack); + if (option_len < 0) + return option_len; + + mask->enc_opts.len += option_len; + if (key->enc_opts.len != mask->enc_opts.len) { + NL_SET_ERR_MSG(extack, "Key and mask miss aligned"); + return -EINVAL; + } + + if (msk_depth) + nla_opt_msk = nla_next(nla_opt_msk, &msk_depth); + break; + default: + NL_SET_ERR_MSG(extack, "Unknown tunnel option type"); + return -EINVAL; + } + } + + return 0; +} + static int fl_set_key(struct net *net, struct nlattr **tb, struct fl_flow_key *key, struct fl_flow_key *mask, struct netlink_ext_ack *extack) @@ -799,6 +955,12 @@ static int fl_set_key(struct net *net, struct nlattr **tb, fl_set_key_ip(tb, true, &key->enc_ip, &mask->enc_ip); + if (tb[TCA_FLOWER_KEY_ENC_OPTS]) { + ret = fl_set_enc_opt(tb, key, mask, extack); + if (ret) + return ret; + } + if (tb[TCA_FLOWER_KEY_FLAGS]) ret = fl_set_key_flags(tb, &key->control.flags, &mask->control.flags); @@ -894,6 +1056,8 @@ static void fl_init_dissector(struct flow_dissector *dissector, FLOW_DISSECTOR_KEY_ENC_PORTS, enc_tp); FL_KEY_SET_IF_MASKED(mask, keys, cnt, FLOW_DISSECTOR_KEY_ENC_IP, enc_ip); + FL_KEY_SET_IF_MASKED(mask, keys, cnt, + FLOW_DISSECTOR_KEY_ENC_OPTS, enc_opts); skb_flow_dissector_init(dissector, keys, cnt); } @@ -1414,6 +1578,83 @@ static int fl_dump_key_flags(struct sk_buff *skb, u32 flags_key, u32 flags_mask) return nla_put(skb, TCA_FLOWER_KEY_FLAGS_MASK, 4, &_mask); } +static int fl_dump_key_geneve_opt(struct sk_buff *skb, + struct flow_dissector_key_enc_opts *enc_opts) +{ + struct geneve_opt *opt; + struct nlattr *nest; + int opt_off = 0; + + nest = nla_nest_start(skb, TCA_FLOWER_KEY_ENC_OPTS_GENEVE); + if (!nest) + goto nla_put_failure; + + while (enc_opts->len > opt_off) { + opt = (struct geneve_opt *)&enc_opts->data[opt_off]; + + if (nla_put_be16(skb, TCA_FLOWER_KEY_ENC_OPT_GENEVE_CLASS, + opt->opt_class)) + goto nla_put_failure; + if (nla_put_u8(skb, TCA_FLOWER_KEY_ENC_OPT_GENEVE_TYPE, + opt->type)) + goto nla_put_failure; + if (nla_put(skb, TCA_FLOWER_KEY_ENC_OPT_GENEVE_DATA, + opt->length * 4, opt->opt_data)) + goto nla_put_failure; + + opt_off += sizeof(struct geneve_opt) + opt->length * 4; + } + nla_nest_end(skb, nest); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + +static int fl_dump_key_options(struct sk_buff *skb, int enc_opt_type, + struct flow_dissector_key_enc_opts *enc_opts) +{ + struct nlattr *nest; + int err; + + if (!enc_opts->len) + return 0; + + nest = nla_nest_start(skb, enc_opt_type); + if (!nest) + goto nla_put_failure; + + switch (enc_opts->dst_opt_type) { + case TUNNEL_GENEVE_OPT: + err = fl_dump_key_geneve_opt(skb, enc_opts); + if (err) + goto nla_put_failure; + break; + default: + goto nla_put_failure; + } + nla_nest_end(skb, nest); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + +static int fl_dump_key_enc_opt(struct sk_buff *skb, + struct flow_dissector_key_enc_opts *key_opts, + struct flow_dissector_key_enc_opts *msk_opts) +{ + int err; + + err = fl_dump_key_options(skb, TCA_FLOWER_KEY_ENC_OPTS, key_opts); + if (err) + return err; + + return fl_dump_key_options(skb, TCA_FLOWER_KEY_ENC_OPTS_MASK, msk_opts); +} + static int fl_dump_key(struct sk_buff *skb, struct net *net, struct fl_flow_key *key, struct fl_flow_key *mask) { @@ -1594,7 +1835,8 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net, &mask->enc_tp.dst, TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK, sizeof(key->enc_tp.dst)) || - fl_dump_key_ip(skb, true, &key->enc_ip, &mask->enc_ip)) + fl_dump_key_ip(skb, true, &key->enc_ip, &mask->enc_ip) || + fl_dump_key_enc_opt(skb, &key->enc_opts, &mask->enc_opts)) goto nla_put_failure; if (fl_dump_key_flags(skb, key->control.flags, mask->control.flags)) -- cgit v1.2.3 From 6fdecfe32f903d9f5f35ee4464fd32ede470dcad Mon Sep 17 00:00:00 2001 From: Arun Parameswaran Date: Tue, 7 Aug 2018 10:02:44 -0700 Subject: net: phy: Add support for Broadcom Omega internal Combo GPHY Add support for the Broadcom Omega SoC internal Combo Ethernet GPHY to the bcm7xxx phy driver. Signed-off-by: Arun Parameswaran Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/phy/bcm7xxx.c | 2 ++ include/linux/brcmphy.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include') diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c index 01d2ff2f6241..b2b6307d64a4 100644 --- a/drivers/net/phy/bcm7xxx.c +++ b/drivers/net/phy/bcm7xxx.c @@ -229,6 +229,7 @@ static int bcm7xxx_28nm_config_init(struct phy_device *phydev) phy_read(phydev, MII_BMSR); switch (rev) { + case 0xa0: case 0xb0: ret = bcm7xxx_28nm_b0_afe_config_init(phydev); break; @@ -659,6 +660,7 @@ static struct phy_driver bcm7xxx_driver[] = { BCM7XXX_28NM_GPHY(PHY_ID_BCM7439, "Broadcom BCM7439"), BCM7XXX_28NM_GPHY(PHY_ID_BCM7439_2, "Broadcom BCM7439 (2)"), BCM7XXX_28NM_GPHY(PHY_ID_BCM7445, "Broadcom BCM7445"), + BCM7XXX_28NM_GPHY(PHY_ID_BCM_OMEGA, "Broadcom Omega Combo GPHY"), BCM7XXX_40NM_EPHY(PHY_ID_BCM7346, "Broadcom BCM7346"), BCM7XXX_40NM_EPHY(PHY_ID_BCM7362, "Broadcom BCM7362"), BCM7XXX_40NM_EPHY(PHY_ID_BCM7425, "Broadcom BCM7425"), diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index daa9234a9baf..949e9af8d9d6 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -45,6 +45,7 @@ #define PHY_ID_BCM7445 0x600d8510 #define PHY_ID_BCM_CYGNUS 0xae025200 +#define PHY_ID_BCM_OMEGA 0xae025100 #define PHY_BCM_OUI_MASK 0xfffffc00 #define PHY_BCM_OUI_1 0x00206000 -- cgit v1.2.3 From 5e9384c705fcfa6bf6d3937967df3ab1f5e414cb Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 7 Aug 2018 18:18:25 +0200 Subject: regulator: maxim: Add SPDX license identifiers Replace GPL v2.0 and v2.0+ license statements with SPDX license identifiers. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Mark Brown --- drivers/regulator/max14577-regulator.c | 22 +++++------------ drivers/regulator/max77686-regulator.c | 32 +++++++----------------- drivers/regulator/max77693-regulator.c | 32 +++++++----------------- drivers/regulator/max77802-regulator.c | 34 +++++++++----------------- drivers/regulator/max8997-regulator.c | 30 ++++++----------------- drivers/regulator/max8998.c | 28 ++++++--------------- include/dt-bindings/regulator/maxim,max77802.h | 5 +--- 7 files changed, 52 insertions(+), 131 deletions(-) (limited to 'include') diff --git a/drivers/regulator/max14577-regulator.c b/drivers/regulator/max14577-regulator.c index 0db288ce319c..bc7f4751bf9c 100644 --- a/drivers/regulator/max14577-regulator.c +++ b/drivers/regulator/max14577-regulator.c @@ -1,19 +1,9 @@ -/* - * max14577.c - Regulator driver for the Maxim 14577/77836 - * - * Copyright (C) 2013,2014 Samsung Electronics - * Krzysztof Kozlowski - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - */ +// SPDX-License-Identifier: GPL-2.0+ +// +// max14577.c - Regulator driver for the Maxim 14577/77836 +// +// Copyright (C) 2013,2014 Samsung Electronics +// Krzysztof Kozlowski #include #include diff --git a/drivers/regulator/max77686-regulator.c b/drivers/regulator/max77686-regulator.c index c301f3733475..bee060937f56 100644 --- a/drivers/regulator/max77686-regulator.c +++ b/drivers/regulator/max77686-regulator.c @@ -1,26 +1,12 @@ -/* - * max77686.c - Regulator driver for the Maxim 77686 - * - * Copyright (C) 2012 Samsung Electronics - * Chiwoong Byun - * Jonghwa Lee - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * - * This driver is based on max8997.c - */ +// SPDX-License-Identifier: GPL-2.0+ +// +// max77686.c - Regulator driver for the Maxim 77686 +// +// Copyright (C) 2012 Samsung Electronics +// Chiwoong Byun +// Jonghwa Lee +// +// This driver is based on max8997.c #include #include diff --git a/drivers/regulator/max77693-regulator.c b/drivers/regulator/max77693-regulator.c index e7000e777292..077ecbbfdf76 100644 --- a/drivers/regulator/max77693-regulator.c +++ b/drivers/regulator/max77693-regulator.c @@ -1,26 +1,12 @@ -/* - * max77693.c - Regulator driver for the Maxim 77693 and 77843 - * - * Copyright (C) 2013-2015 Samsung Electronics - * Jonghwa Lee - * Krzysztof Kozlowski - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * - * This driver is based on max77686.c - */ +// SPDX-License-Identifier: GPL-2.0+ +// +// max77693.c - Regulator driver for the Maxim 77693 and 77843 +// +// Copyright (C) 2013-2015 Samsung Electronics +// Jonghwa Lee +// Krzysztof Kozlowski +// +// This driver is based on max77686.c #include #include diff --git a/drivers/regulator/max77802-regulator.c b/drivers/regulator/max77802-regulator.c index b6261903818c..c30cf5c9f2de 100644 --- a/drivers/regulator/max77802-regulator.c +++ b/drivers/regulator/max77802-regulator.c @@ -1,25 +1,15 @@ -/* - * max77802.c - Regulator driver for the Maxim 77802 - * - * Copyright (C) 2013-2014 Google, Inc - * Simon Glass - * - * Copyright (C) 2012 Samsung Electronics - * Chiwoong Byun - * Jonghwa Lee - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * This driver is based on max8997.c - */ +// SPDX-License-Identifier: GPL-2.0+ +// +// max77802.c - Regulator driver for the Maxim 77802 +// +// Copyright (C) 2013-2014 Google, Inc +// Simon Glass +// +// Copyright (C) 2012 Samsung Electronics +// Chiwoong Byun +// Jonghwa Lee +// +// This driver is based on max8997.c #include #include diff --git a/drivers/regulator/max8997-regulator.c b/drivers/regulator/max8997-regulator.c index 029a6ee426ab..ad0c806b0737 100644 --- a/drivers/regulator/max8997-regulator.c +++ b/drivers/regulator/max8997-regulator.c @@ -1,25 +1,11 @@ -/* - * max8997.c - Regulator driver for the Maxim 8997/8966 - * - * Copyright (C) 2011 Samsung Electronics - * MyungJoo Ham - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * - * This driver is based on max8998.c - */ +// SPDX-License-Identifier: GPL-2.0+ +// +// max8997.c - Regulator driver for the Maxim 8997/8966 +// +// Copyright (C) 2011 Samsung Electronics +// MyungJoo Ham +// +// This driver is based on max8998.c #include #include diff --git a/drivers/regulator/max8998.c b/drivers/regulator/max8998.c index 6b9f262ebbb0..271bb736f3f5 100644 --- a/drivers/regulator/max8998.c +++ b/drivers/regulator/max8998.c @@ -1,24 +1,10 @@ -/* - * max8998.c - Voltage regulator driver for the Maxim 8998 - * - * Copyright (C) 2009-2010 Samsung Electronics - * Kyungmin Park - * Marek Szyprowski - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ +// SPDX-License-Identifier: GPL-2.0+ +// +// max8998.c - Voltage regulator driver for the Maxim 8998 +// +// Copyright (C) 2009-2010 Samsung Electronics +// Kyungmin Park +// Marek Szyprowski #include #include diff --git a/include/dt-bindings/regulator/maxim,max77802.h b/include/dt-bindings/regulator/maxim,max77802.h index cf28631d7109..d0baba1973d4 100644 --- a/include/dt-bindings/regulator/maxim,max77802.h +++ b/include/dt-bindings/regulator/maxim,max77802.h @@ -1,10 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2014 Google, Inc * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * * Device Tree binding constants for the Maxim 77802 PMIC regulators */ -- cgit v1.2.3 From 8b92d0e3d400390660a26ef7f475524700fb86cf Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Wed, 8 Aug 2018 08:35:29 +0200 Subject: nvme.h: fixup ANA group descriptor format ANA Phase 3 draft had the 'reserved' field in the group descriptor format set to '23:17' (so that the first namespace identifier started at byte 24), but that got move with the approved TP to '31:17' (so that the first namespace identifier started at byte 32). Signed-off-by: Hannes Reinecke Signed-off-by: Christoph Hellwig --- include/linux/nvme.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 64c9175723de..a661861e9d56 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -446,7 +446,7 @@ struct nvme_ana_group_desc { __le32 nnsids; __le64 chgcnt; __u8 state; - __u8 rsvd17[7]; + __u8 rsvd17[15]; __le32 nsids[]; }; -- cgit v1.2.3 From 93045d5942da60801e71764597d448cf37a798c1 Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Tue, 7 Aug 2018 23:01:05 -0700 Subject: nvme.h: add support for ns write protect definitions Add various definitions from NVMe 1.3 TP 4005. Signed-off-by: Chaitanya Kulkarni Signed-off-by: Christoph Hellwig --- include/linux/nvme.h | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index a661861e9d56..68e91ef5494c 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -259,7 +259,7 @@ struct nvme_id_ctrl { __le16 awun; __le16 awupf; __u8 nvscc; - __u8 rsvd531; + __u8 nwpc; __le16 acwu; __u8 rsvd534[2]; __le32 sgls; @@ -320,7 +320,9 @@ struct nvme_id_ns { __u8 nvmcap[16]; __u8 rsvd64[28]; __le32 anagrpid; - __u8 rsvd96[8]; + __u8 rsvd96[3]; + __u8 nsattr; + __u8 rsvd100[4]; __u8 nguid[16]; __u8 eui64[8]; struct nvme_lbaf lbaf[16]; @@ -794,6 +796,7 @@ enum { NVME_FEAT_HOST_ID = 0x81, NVME_FEAT_RESV_MASK = 0x82, NVME_FEAT_RESV_PERSIST = 0x83, + NVME_FEAT_WRITE_PROTECT = 0x84, NVME_LOG_ERROR = 0x01, NVME_LOG_SMART = 0x02, NVME_LOG_FW_SLOT = 0x03, @@ -807,6 +810,14 @@ enum { NVME_FWACT_ACTV = (2 << 3), }; +/* NVMe Namespace Write Protect State */ +enum { + NVME_NS_NO_WRITE_PROTECT = 0, + NVME_NS_WRITE_PROTECT, + NVME_NS_WRITE_PROTECT_POWER_CYCLE, + NVME_NS_WRITE_PROTECT_PERMANENT, +}; + #define NVME_MAX_CHANGED_NAMESPACES 1024 struct nvme_identify { @@ -1153,6 +1164,8 @@ enum { NVME_SC_SGL_INVALID_OFFSET = 0x16, NVME_SC_SGL_INVALID_SUBTYPE = 0x17, + NVME_SC_NS_WRITE_PROTECTED = 0x20, + NVME_SC_LBA_RANGE = 0x80, NVME_SC_CAP_EXCEEDED = 0x81, NVME_SC_NS_NOT_READY = 0x82, -- cgit v1.2.3 From 212dfd909ea8b630e5d6fa4d25aeec9c4b4b14a5 Mon Sep 17 00:00:00 2001 From: Fernando Fernandez Mancera Date: Tue, 7 Aug 2018 22:06:52 +0200 Subject: netfilter: nfnetlink_osf: add missing enum in nfnetlink_osf uapi header xt_osf_window_size_options was originally part of include/uapi/linux/netfilter/xt_osf.h, restore it. Fixes: bfb15f2a95cb ("netfilter: extract Passive OS fingerprint infrastructure from xt_osf") Signed-off-by: Fernando Fernandez Mancera Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nfnetlink_osf.h | 12 ------------ include/uapi/linux/netfilter/nfnetlink_osf.h | 12 ++++++++++++ include/uapi/linux/netfilter/xt_osf.h | 1 + 3 files changed, 13 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter/nfnetlink_osf.h b/include/linux/netfilter/nfnetlink_osf.h index a7311bc03d3a..ecf7dab81e9e 100644 --- a/include/linux/netfilter/nfnetlink_osf.h +++ b/include/linux/netfilter/nfnetlink_osf.h @@ -4,18 +4,6 @@ #include -/* Initial window size option state machine: multiple of mss, mtu or - * plain numeric value. Can also be made as plain numeric value which - * is not a multiple of specified value. - */ -enum nf_osf_window_size_options { - OSF_WSS_PLAIN = 0, - OSF_WSS_MSS, - OSF_WSS_MTU, - OSF_WSS_MODULO, - OSF_WSS_MAX, -}; - enum osf_fmatch_states { /* Packet does not match the fingerprint */ FMATCH_WRONG = 0, diff --git a/include/uapi/linux/netfilter/nfnetlink_osf.h b/include/uapi/linux/netfilter/nfnetlink_osf.h index 3b93fbb9fc24..76a3527df5dd 100644 --- a/include/uapi/linux/netfilter/nfnetlink_osf.h +++ b/include/uapi/linux/netfilter/nfnetlink_osf.h @@ -88,6 +88,18 @@ enum iana_options { OSFOPT_EMPTY = 255, }; +/* Initial window size option state machine: multiple of mss, mtu or + * plain numeric value. Can also be made as plain numeric value which + * is not a multiple of specified value. + */ +enum nf_osf_window_size_options { + OSF_WSS_PLAIN = 0, + OSF_WSS_MSS, + OSF_WSS_MTU, + OSF_WSS_MODULO, + OSF_WSS_MAX, +}; + enum nf_osf_attr_type { OSF_ATTR_UNSPEC, OSF_ATTR_FINGER, diff --git a/include/uapi/linux/netfilter/xt_osf.h b/include/uapi/linux/netfilter/xt_osf.h index c56c59605c2b..24102b5286ec 100644 --- a/include/uapi/linux/netfilter/xt_osf.h +++ b/include/uapi/linux/netfilter/xt_osf.h @@ -46,6 +46,7 @@ #define xt_osf_finger nf_osf_finger #define xt_osf_nlmsg nf_osf_nlmsg +#define xt_osf_window_size_options nf_osf_window_size_options #define xt_osf_attr_type nf_osf_attr_type #define xt_osf_msg_types nf_osf_msg_types -- cgit v1.2.3 From 342ac8448f1fb213908656ae5581d0f37a5954e8 Mon Sep 17 00:00:00 2001 From: Denis Drozdov Date: Wed, 8 Aug 2018 16:23:48 -0700 Subject: net/mlx5: Use max_num_eqs for calculation of required MSIX vectors New firmware has defined new HCA capability field called "max_num_eqs", that is the number of available EQs after subtracting reserved FW EQs. Before this capability the FW reported the EQ number in "log_max_eqs", the reported value also contained FW reserved EQs, but the driver might be failing to load on 320 cpus systems due to the fact that FW reserved EQs were not available to the driver. Now the driver has to obtain max_num_eqs value from new FW to get real number of EQs available. Signed-off-by: Denis Drozdov Reviewed-by: Alex Vesker Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/main.c | 4 +++- include/linux/mlx5/mlx5_ifc.h | 5 ++++- 2 files changed, 7 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 03b9c6733eed..cf3e4a659052 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -323,7 +323,9 @@ static int mlx5_alloc_irq_vectors(struct mlx5_core_dev *dev) { struct mlx5_priv *priv = &dev->priv; struct mlx5_eq_table *table = &priv->eq_table; - int num_eqs = 1 << MLX5_CAP_GEN(dev, log_max_eq); + int num_eqs = MLX5_CAP_GEN(dev, max_num_eqs) ? + MLX5_CAP_GEN(dev, max_num_eqs) : + 1 << MLX5_CAP_GEN(dev, log_max_eq); int nvec; int err; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 60c2308fe062..63e1ce4c4826 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1133,7 +1133,10 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 general_obj_types[0x40]; - u8 reserved_at_440[0x40]; + u8 reserved_at_440[0x20]; + + u8 reserved_at_460[0x10]; + u8 max_num_eqs[0x10]; u8 reserved_at_480[0x3]; u8 log_max_l2_table[0x5]; -- cgit v1.2.3 From cc9c82a8668cf98748bfbaa83c5c092d5115c25b Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Wed, 8 Aug 2018 16:23:49 -0700 Subject: net/mlx5: Rename modify/query_vport state related enums Modify and query vport state commands share the same admin_state and op_mod values, rename the enums to fit them both. In addition, remove the esw prefix from the admin state enum as this also applied for vnic. Signed-off-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 12 ++++++------ drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 8 ++++---- drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 10 +++++----- include/linux/mlx5/device.h | 6 +++--- include/linux/mlx5/mlx5_ifc.h | 4 ++-- 6 files changed, 21 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index a2fb21ca5767..2731ba2d8049 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -228,7 +228,7 @@ static void mlx5e_update_carrier(struct mlx5e_priv *priv) u8 port_state; port_state = mlx5_query_vport_state(mdev, - MLX5_QUERY_VPORT_STATE_IN_OP_MOD_VNIC_VPORT, + MLX5_VPORT_STATE_OP_MOD_VNIC_VPORT, 0); if (port_state == VPORT_STATE_UP) { @@ -3916,9 +3916,9 @@ static int mlx5e_set_vf_rate(struct net_device *dev, int vf, int min_tx_rate, static int mlx5_vport_link2ifla(u8 esw_link) { switch (esw_link) { - case MLX5_ESW_VPORT_ADMIN_STATE_DOWN: + case MLX5_VPORT_ADMIN_STATE_DOWN: return IFLA_VF_LINK_STATE_DISABLE; - case MLX5_ESW_VPORT_ADMIN_STATE_UP: + case MLX5_VPORT_ADMIN_STATE_UP: return IFLA_VF_LINK_STATE_ENABLE; } return IFLA_VF_LINK_STATE_AUTO; @@ -3928,11 +3928,11 @@ static int mlx5_ifla_link2vport(u8 ifla_link) { switch (ifla_link) { case IFLA_VF_LINK_STATE_DISABLE: - return MLX5_ESW_VPORT_ADMIN_STATE_DOWN; + return MLX5_VPORT_ADMIN_STATE_DOWN; case IFLA_VF_LINK_STATE_ENABLE: - return MLX5_ESW_VPORT_ADMIN_STATE_UP; + return MLX5_VPORT_ADMIN_STATE_UP; } - return MLX5_ESW_VPORT_ADMIN_STATE_AUTO; + return MLX5_VPORT_ADMIN_STATE_AUTO; } static int mlx5e_set_vf_link_state(struct net_device *dev, int vf, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 8e3c5b4b90ab..c9cc9747d21d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -698,8 +698,8 @@ static int mlx5e_rep_open(struct net_device *dev) goto unlock; if (!mlx5_modify_vport_admin_state(priv->mdev, - MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT, - rep->vport, MLX5_ESW_VPORT_ADMIN_STATE_UP)) + MLX5_VPORT_STATE_OP_MOD_ESW_VPORT, + rep->vport, MLX5_VPORT_ADMIN_STATE_UP)) netif_carrier_on(dev); unlock: @@ -716,8 +716,8 @@ static int mlx5e_rep_close(struct net_device *dev) mutex_lock(&priv->state_lock); mlx5_modify_vport_admin_state(priv->mdev, - MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT, - rep->vport, MLX5_ESW_VPORT_ADMIN_STATE_DOWN); + MLX5_VPORT_STATE_OP_MOD_ESW_VPORT, + rep->vport, MLX5_VPORT_ADMIN_STATE_DOWN); ret = mlx5e_close_locked(dev); mutex_unlock(&priv->state_lock); return ret; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c index 4d316cc9b008..35ded91203f5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c @@ -74,7 +74,7 @@ static int mlx5e_test_link_state(struct mlx5e_priv *priv) if (!netif_carrier_ok(priv->netdev)) return 1; - port_state = mlx5_query_vport_state(priv->mdev, MLX5_QUERY_VPORT_STATE_IN_OP_MOD_VNIC_VPORT, 0); + port_state = mlx5_query_vport_state(priv->mdev, MLX5_VPORT_STATE_OP_MOD_VNIC_VPORT, 0); return port_state == VPORT_STATE_UP ? 0 : 1; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 40dba9e8af92..cd0760a8d45a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1469,7 +1469,7 @@ static void esw_apply_vport_conf(struct mlx5_eswitch *esw, return; mlx5_modify_vport_admin_state(esw->dev, - MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT, + MLX5_VPORT_STATE_OP_MOD_ESW_VPORT, vport_num, vport->info.link_state); mlx5_modify_nic_vport_mac_address(esw->dev, vport_num, vport->info.mac); @@ -1582,9 +1582,9 @@ static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num) esw_vport_disable_qos(esw, vport_num); if (vport_num && esw->mode == SRIOV_LEGACY) { mlx5_modify_vport_admin_state(esw->dev, - MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT, + MLX5_VPORT_STATE_OP_MOD_ESW_VPORT, vport_num, - MLX5_ESW_VPORT_ADMIN_STATE_DOWN); + MLX5_VPORT_ADMIN_STATE_DOWN); esw_vport_disable_egress_acl(esw, vport); esw_vport_disable_ingress_acl(esw, vport); esw_vport_destroy_drop_counters(vport); @@ -1736,7 +1736,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) struct mlx5_vport *vport = &esw->vports[vport_num]; vport->vport = vport_num; - vport->info.link_state = MLX5_ESW_VPORT_ADMIN_STATE_AUTO; + vport->info.link_state = MLX5_VPORT_ADMIN_STATE_AUTO; vport->dev = dev; INIT_WORK(&vport->vport_change_handler, esw_vport_change_handler); @@ -1860,7 +1860,7 @@ int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw, evport = &esw->vports[vport]; err = mlx5_modify_vport_admin_state(esw->dev, - MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT, + MLX5_VPORT_STATE_OP_MOD_ESW_VPORT, vport, link_state); if (err) { mlx5_core_warn(esw->dev, diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index d489494b0a84..11fa4e66afc5 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -946,9 +946,9 @@ enum { }; enum { - MLX5_ESW_VPORT_ADMIN_STATE_DOWN = 0x0, - MLX5_ESW_VPORT_ADMIN_STATE_UP = 0x1, - MLX5_ESW_VPORT_ADMIN_STATE_AUTO = 0x2, + MLX5_VPORT_ADMIN_STATE_DOWN = 0x0, + MLX5_VPORT_ADMIN_STATE_UP = 0x1, + MLX5_VPORT_ADMIN_STATE_AUTO = 0x2, }; enum { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 63e1ce4c4826..6ead9c1a5396 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -3764,8 +3764,8 @@ struct mlx5_ifc_query_vport_state_out_bits { }; enum { - MLX5_QUERY_VPORT_STATE_IN_OP_MOD_VNIC_VPORT = 0x0, - MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT = 0x1, + MLX5_VPORT_STATE_OP_MOD_VNIC_VPORT = 0x0, + MLX5_VPORT_STATE_OP_MOD_ESW_VPORT = 0x1, }; struct mlx5_ifc_query_vport_state_in_bits { -- cgit v1.2.3 From 29d8ebd44de8999e292dbb4de76744d4a41039ec Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Wed, 8 Aug 2018 16:23:51 -0700 Subject: net/mlx5: Remove unused mlx5_query_vport_admin_state mlx5_query_vport_admin_state() is not used anywhere. Remove it. Signed-off-by: Eli Cohen Reviewed-by: Or Gerlitz Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/vport.c | 10 ---------- include/linux/mlx5/vport.h | 2 -- 2 files changed, 12 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index 7eecd5b07bb1..fa6fa171b94c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -64,16 +64,6 @@ u8 mlx5_query_vport_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport) } EXPORT_SYMBOL_GPL(mlx5_query_vport_state); -u8 mlx5_query_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport) -{ - u32 out[MLX5_ST_SZ_DW(query_vport_state_out)] = {0}; - - _mlx5_query_vport_state(mdev, opmod, vport, out, sizeof(out)); - - return MLX5_GET(query_vport_state_out, out, admin_state); -} -EXPORT_SYMBOL_GPL(mlx5_query_vport_admin_state); - int mlx5_modify_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport, u8 state) { diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index 9208cb8809ac..7e7c6dfcfb09 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -43,8 +43,6 @@ enum { }; u8 mlx5_query_vport_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport); -u8 mlx5_query_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod, - u16 vport); int mlx5_modify_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport, u8 state); int mlx5_query_nic_vport_mac_address(struct mlx5_core_dev *mdev, -- cgit v1.2.3 From 1035a0783523d8c730c44944a71b254f3a649e25 Mon Sep 17 00:00:00 2001 From: Dongjiu Geng Date: Tue, 7 Aug 2018 12:26:15 -0400 Subject: arm64 / ACPI: clean the additional checks before calling ghes_notify_sea() In order to remove the additional check before calling the ghes_notify_sea(), make stub definition when !CONFIG_ACPI_APEI_SEA. After this cleanup, we can simply call the ghes_notify_sea() to let APEI driver handle the SEA notification. Signed-off-by: Dongjiu Geng Acked-by: Will Deacon Signed-off-by: Rafael J. Wysocki --- arch/arm64/mm/fault.c | 7 +------ include/acpi/ghes.h | 4 ++++ 2 files changed, 5 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index b8eecc7b9531..9ffe01d7042a 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -727,12 +727,7 @@ static const struct fault_info fault_info[] = { int handle_guest_sea(phys_addr_t addr, unsigned int esr) { - int ret = -ENOENT; - - if (IS_ENABLED(CONFIG_ACPI_APEI_SEA)) - ret = ghes_notify_sea(); - - return ret; + return ghes_notify_sea(); } asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr, diff --git a/include/acpi/ghes.h b/include/acpi/ghes.h index 1624e2be485c..82cb4eb225a4 100644 --- a/include/acpi/ghes.h +++ b/include/acpi/ghes.h @@ -118,6 +118,10 @@ static inline void *acpi_hest_get_next(struct acpi_hest_generic_data *gdata) (void *)section - (void *)(estatus + 1) < estatus->data_length; \ section = acpi_hest_get_next(section)) +#ifdef CONFIG_ACPI_APEI_SEA int ghes_notify_sea(void); +#else +static inline int ghes_notify_sea(void) { return -ENOENT; } +#endif #endif /* GHES_H */ -- cgit v1.2.3 From 74fe7b551f3385fa585d92616c85b3a575b2b2cb Mon Sep 17 00:00:00 2001 From: Crestez Dan Leonard Date: Tue, 7 Aug 2018 17:52:17 +0300 Subject: regmap: Add regmap_noinc_read API The regmap API usually assumes that bulk read operations will read a range of registers but some I2C/SPI devices have certain registers for which a such a read operation will return data from an internal FIFO instead. Add an explicit API to support bulk read without range semantics. Some linux drivers use regmap_bulk_read or regmap_raw_read for such registers, for example mpu6050 or bmi150 from IIO. This only happens to work because when caching is disabled a single regmap read op will map to a single bus read op (as desired). This breaks if caching is enabled and reg+1 happens to be a cacheable register. Without regmap support refactoring a driver to enable regmap caching requires separate I2C and SPI paths. This is exactly what regmap is supposed to help avoid. Suggested-by: Jonathan Cameron Signed-off-by: Crestez Dan Leonard Signed-off-by: Stefan Popa Signed-off-by: Mark Brown --- drivers/base/regmap/internal.h | 3 ++ drivers/base/regmap/regmap.c | 79 +++++++++++++++++++++++++++++++++++++++++- include/linux/regmap.h | 19 ++++++++++ 3 files changed, 100 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h index 53785e0e297a..a6bf34d6394e 100644 --- a/drivers/base/regmap/internal.h +++ b/drivers/base/regmap/internal.h @@ -94,10 +94,12 @@ struct regmap { bool (*readable_reg)(struct device *dev, unsigned int reg); bool (*volatile_reg)(struct device *dev, unsigned int reg); bool (*precious_reg)(struct device *dev, unsigned int reg); + bool (*readable_noinc_reg)(struct device *dev, unsigned int reg); const struct regmap_access_table *wr_table; const struct regmap_access_table *rd_table; const struct regmap_access_table *volatile_table; const struct regmap_access_table *precious_table; + const struct regmap_access_table *rd_noinc_table; int (*reg_read)(void *context, unsigned int reg, unsigned int *val); int (*reg_write)(void *context, unsigned int reg, unsigned int val); @@ -181,6 +183,7 @@ bool regmap_writeable(struct regmap *map, unsigned int reg); bool regmap_readable(struct regmap *map, unsigned int reg); bool regmap_volatile(struct regmap *map, unsigned int reg); bool regmap_precious(struct regmap *map, unsigned int reg); +bool regmap_readable_noinc(struct regmap *map, unsigned int reg); int _regmap_write(struct regmap *map, unsigned int reg, unsigned int val); diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index 3bc84885eb91..0360a90ad6b6 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -168,6 +168,17 @@ bool regmap_precious(struct regmap *map, unsigned int reg) return false; } +bool regmap_readable_noinc(struct regmap *map, unsigned int reg) +{ + if (map->readable_noinc_reg) + return map->readable_noinc_reg(map->dev, reg); + + if (map->rd_noinc_table) + return regmap_check_range_table(map, reg, map->rd_noinc_table); + + return true; +} + static bool regmap_volatile_range(struct regmap *map, unsigned int reg, size_t num) { @@ -766,10 +777,12 @@ struct regmap *__regmap_init(struct device *dev, map->rd_table = config->rd_table; map->volatile_table = config->volatile_table; map->precious_table = config->precious_table; + map->rd_noinc_table = config->rd_noinc_table; map->writeable_reg = config->writeable_reg; map->readable_reg = config->readable_reg; map->volatile_reg = config->volatile_reg; map->precious_reg = config->precious_reg; + map->readable_noinc_reg = config->readable_noinc_reg; map->cache_type = config->cache_type; spin_lock_init(&map->async_lock); @@ -1285,6 +1298,7 @@ int regmap_reinit_cache(struct regmap *map, const struct regmap_config *config) map->readable_reg = config->readable_reg; map->volatile_reg = config->volatile_reg; map->precious_reg = config->precious_reg; + map->readable_noinc_reg = config->readable_noinc_reg; map->cache_type = config->cache_type; regmap_debugfs_init(map, config->name); @@ -2564,7 +2578,70 @@ int regmap_raw_read(struct regmap *map, unsigned int reg, void *val, EXPORT_SYMBOL_GPL(regmap_raw_read); /** - * regmap_field_read() - Read a value to a single register field + * regmap_noinc_read(): Read data from a register without incrementing the + * register number + * + * @map: Register map to read from + * @reg: Register to read from + * @val: Pointer to data buffer + * @val_len: Length of output buffer in bytes. + * + * The regmap API usually assumes that bulk bus read operations will read a + * range of registers. Some devices have certain registers for which a read + * operation read will read from an internal FIFO. + * + * The target register must be volatile but registers after it can be + * completely unrelated cacheable registers. + * + * This will attempt multiple reads as required to read val_len bytes. + * + * A value of zero will be returned on success, a negative errno will be + * returned in error cases. + */ +int regmap_noinc_read(struct regmap *map, unsigned int reg, + void *val, size_t val_len) +{ + size_t read_len; + int ret; + + if (!map->bus) + return -EINVAL; + if (!map->bus->read) + return -ENOTSUPP; + if (val_len % map->format.val_bytes) + return -EINVAL; + if (!IS_ALIGNED(reg, map->reg_stride)) + return -EINVAL; + if (val_len == 0) + return -EINVAL; + + map->lock(map->lock_arg); + + if (!regmap_volatile(map, reg) || !regmap_readable_noinc(map, reg)) { + ret = -EINVAL; + goto out_unlock; + } + + while (val_len) { + if (map->max_raw_read && map->max_raw_read < val_len) + read_len = map->max_raw_read; + else + read_len = val_len; + ret = _regmap_raw_read(map, reg, val, read_len); + if (ret) + goto out_unlock; + val = ((u8 *)val) + read_len; + val_len -= read_len; + } + +out_unlock: + map->unlock(map->lock_arg); + return ret; +} +EXPORT_SYMBOL_GPL(regmap_noinc_read); + +/** + * regmap_field_read(): Read a value to a single register field * * @field: Register field to read from * @val: Pointer to store read value diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 4f38068ffb71..19df946499d2 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -268,6 +268,13 @@ typedef void (*regmap_unlock)(void *); * field is NULL but precious_table (see below) is not, the * check is performed on such table (a register is precious if * it belongs to one of the ranges specified by precious_table). + * @readable_noinc_reg: Optional callback returning true if the register + * supports multiple read operations without incrementing + * the register number. If this field is NULL but + * rd_noinc_table (see below) is not, the check is + * performed on such table (a register is no increment + * readable if it belongs to one of the ranges specified + * by rd_noinc_table). * @disable_locking: This regmap is either protected by external means or * is guaranteed not be be accessed from multiple threads. * Don't use any locking mechanisms. @@ -295,6 +302,7 @@ typedef void (*regmap_unlock)(void *); * @rd_table: As above, for read access. * @volatile_table: As above, for volatile registers. * @precious_table: As above, for precious registers. + * @rd_noinc_table: As above, for no increment readable registers. * @reg_defaults: Power on reset values for registers (for use with * register cache support). * @num_reg_defaults: Number of elements in reg_defaults. @@ -344,6 +352,7 @@ struct regmap_config { bool (*readable_reg)(struct device *dev, unsigned int reg); bool (*volatile_reg)(struct device *dev, unsigned int reg); bool (*precious_reg)(struct device *dev, unsigned int reg); + bool (*readable_noinc_reg)(struct device *dev, unsigned int reg); bool disable_locking; regmap_lock lock; @@ -360,6 +369,7 @@ struct regmap_config { const struct regmap_access_table *rd_table; const struct regmap_access_table *volatile_table; const struct regmap_access_table *precious_table; + const struct regmap_access_table *rd_noinc_table; const struct reg_default *reg_defaults; unsigned int num_reg_defaults; enum regcache_type cache_type; @@ -946,6 +956,8 @@ int regmap_raw_write_async(struct regmap *map, unsigned int reg, int regmap_read(struct regmap *map, unsigned int reg, unsigned int *val); int regmap_raw_read(struct regmap *map, unsigned int reg, void *val, size_t val_len); +int regmap_noinc_read(struct regmap *map, unsigned int reg, + void *val, size_t val_len); int regmap_bulk_read(struct regmap *map, unsigned int reg, void *val, size_t val_count); int regmap_update_bits_base(struct regmap *map, unsigned int reg, @@ -1196,6 +1208,13 @@ static inline int regmap_raw_read(struct regmap *map, unsigned int reg, return -EINVAL; } +static inline int regmap_noinc_read(struct regmap *map, unsigned int reg, + void *val, size_t val_len) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + static inline int regmap_bulk_read(struct regmap *map, unsigned int reg, void *val, size_t val_count) { -- cgit v1.2.3 From b1f4267cc5448d20ae0c515a74141e74365e78a3 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Thu, 9 Aug 2018 07:47:28 -0700 Subject: block: Remove two superfluous #include directives Commit 12f5b9314545 ("blk-mq: Remove generation seqeunce") removed the only seqcount_t and u64_stats_sync instances from but did not remove the corresponding #include directives. Since these include directives are no longer needed, remove them. Signed-off-by: Bart Van Assche Cc: Christoph Hellwig Cc: Keith Busch Cc: Ming Lei Cc: Jianchao Wang Cc: Hannes Reinecke , Cc: Johannes Thumshirn Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 050d599f5ea9..d6869e0e2b64 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -27,8 +27,6 @@ #include #include #include -#include -#include struct module; struct scsi_ioctl_command; -- cgit v1.2.3 From 6bad9b210a228d2fe0e0efe26d9b115348529cee Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Thu, 9 Aug 2018 07:53:36 -0700 Subject: blkcg: Introduce blkg_root_lookup() This new function will be used in a later patch to verify whether a queue has been dissociated from the cgroup controller before being released. Signed-off-by: Bart Van Assche Cc: Tejun Heo Cc: Christoph Hellwig Cc: Ming Lei Cc: Omar Sandoval Cc: Johannes Thumshirn Cc: Alexandru Moise <00moses.alexander00@gmail.com> Cc: Joseph Qi Cc: Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index f7b910768306..1361cfc9b878 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -341,6 +341,23 @@ static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, return __blkg_lookup(blkcg, q, false); } +/** + * blkg_lookup - look up blkg for the specified request queue + * @q: request_queue of interest + * + * Lookup blkg for @q at the root level. See also blkg_lookup(). + */ +static inline struct blkcg_gq *blkg_root_lookup(struct request_queue *q) +{ + struct blkcg_gq *blkg; + + rcu_read_lock(); + blkg = blkg_lookup(&blkcg_root, q); + rcu_read_unlock(); + + return blkg; +} + /** * blkg_to_pdata - get policy private data * @blkg: blkg of interest @@ -864,6 +881,7 @@ static inline bool blk_cgroup_congested(void) { return false; } static inline void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay) { } static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; } +static inline struct blkcg_gq *blkg_root_lookup(struct request_queue *q) { return NULL; } static inline int blkcg_init_queue(struct request_queue *q) { return 0; } static inline void blkcg_drain_queue(struct request_queue *q) { } static inline void blkcg_exit_queue(struct request_queue *q) { } -- cgit v1.2.3 From 209b43759d65b2cc99ce7757249aacc82b03c4e2 Mon Sep 17 00:00:00 2001 From: Michael Büsch Date: Tue, 31 Jul 2018 22:15:09 +0200 Subject: ssb: Remove SSB_WARN_ON, SSB_BUG_ON and SSB_DEBUG Use the standard WARN_ON instead. If a small kernel is desired, WARN_ON can be disabled globally. Also remove SSB_DEBUG. Besides WARN_ON it only adds a tiny debug check. Include this check unconditionally. Signed-off-by: Michael Buesch Signed-off-by: Kalle Valo --- arch/mips/configs/bcm47xx_defconfig | 1 - arch/powerpc/configs/wii_defconfig | 1 - drivers/ssb/Kconfig | 9 --------- drivers/ssb/driver_chipcommon.c | 8 ++++---- drivers/ssb/driver_chipcommon_pmu.c | 10 +++++----- drivers/ssb/driver_gpio.c | 4 ++-- drivers/ssb/driver_pcicore.c | 6 +++--- drivers/ssb/embedded.c | 10 +++++----- drivers/ssb/host_soc.c | 12 ++++++------ drivers/ssb/main.c | 38 +++++++++++++++++-------------------- drivers/ssb/pci.c | 19 ++++++------------- drivers/ssb/pcmcia.c | 14 +++++++------- drivers/ssb/scan.c | 4 ++-- drivers/ssb/sdio.c | 12 ++++++------ drivers/ssb/ssb_private.h | 9 --------- include/linux/ssb/ssb.h | 2 -- 16 files changed, 63 insertions(+), 96 deletions(-) (limited to 'include') diff --git a/arch/mips/configs/bcm47xx_defconfig b/arch/mips/configs/bcm47xx_defconfig index fad8e964f14c..ba800a892384 100644 --- a/arch/mips/configs/bcm47xx_defconfig +++ b/arch/mips/configs/bcm47xx_defconfig @@ -66,7 +66,6 @@ CONFIG_HW_RANDOM=y CONFIG_GPIO_SYSFS=y CONFIG_WATCHDOG=y CONFIG_BCM47XX_WDT=y -CONFIG_SSB_DEBUG=y CONFIG_SSB_DRIVER_GIGE=y CONFIG_BCMA_DRIVER_GMAC_CMN=y CONFIG_USB=y diff --git a/arch/powerpc/configs/wii_defconfig b/arch/powerpc/configs/wii_defconfig index 10940533da71..f5c366b02828 100644 --- a/arch/powerpc/configs/wii_defconfig +++ b/arch/powerpc/configs/wii_defconfig @@ -78,7 +78,6 @@ CONFIG_GPIO_HLWD=y CONFIG_POWER_RESET=y CONFIG_POWER_RESET_GPIO=y # CONFIG_HWMON is not set -CONFIG_SSB_DEBUG=y CONFIG_FB=y # CONFIG_VGA_CONSOLE is not set CONFIG_FRAMEBUFFER_CONSOLE=y diff --git a/drivers/ssb/Kconfig b/drivers/ssb/Kconfig index 6c438c819eb9..df30e1323252 100644 --- a/drivers/ssb/Kconfig +++ b/drivers/ssb/Kconfig @@ -89,15 +89,6 @@ config SSB_HOST_SOC If unsure, say N -config SSB_DEBUG - bool "SSB debugging" - depends on SSB - help - This turns on additional runtime checks and debugging - messages. Turn this on for SSB troubleshooting. - - If unsure, say N - config SSB_SERIAL bool depends on SSB diff --git a/drivers/ssb/driver_chipcommon.c b/drivers/ssb/driver_chipcommon.c index 48050c6fd847..99a4656d113d 100644 --- a/drivers/ssb/driver_chipcommon.c +++ b/drivers/ssb/driver_chipcommon.c @@ -56,7 +56,7 @@ void ssb_chipco_set_clockmode(struct ssb_chipcommon *cc, if (cc->capabilities & SSB_CHIPCO_CAP_PMU) return; /* PMU controls clockmode, separated function needed */ - SSB_WARN_ON(ccdev->id.revision >= 20); + WARN_ON(ccdev->id.revision >= 20); /* chipcommon cores prior to rev6 don't support dynamic clock control */ if (ccdev->id.revision < 6) @@ -111,7 +111,7 @@ void ssb_chipco_set_clockmode(struct ssb_chipcommon *cc, } break; default: - SSB_WARN_ON(1); + WARN_ON(1); } } @@ -164,7 +164,7 @@ static int chipco_pctl_clockfreqlimit(struct ssb_chipcommon *cc, int get_max) divisor = 32; break; default: - SSB_WARN_ON(1); + WARN_ON(1); } } else if (cc->dev->id.revision < 10) { switch (clocksrc) { @@ -277,7 +277,7 @@ static void calc_fast_powerup_delay(struct ssb_chipcommon *cc) minfreq = chipco_pctl_clockfreqlimit(cc, 0); pll_on_delay = chipco_read32(cc, SSB_CHIPCO_PLLONDELAY); tmp = (((pll_on_delay + 2) * 1000000) + (minfreq - 1)) / minfreq; - SSB_WARN_ON(tmp & ~0xFFFF); + WARN_ON(tmp & ~0xFFFF); cc->fast_pwrup_delay = tmp; } diff --git a/drivers/ssb/driver_chipcommon_pmu.c b/drivers/ssb/driver_chipcommon_pmu.c index e28682a53cdf..0f60e90ded26 100644 --- a/drivers/ssb/driver_chipcommon_pmu.c +++ b/drivers/ssb/driver_chipcommon_pmu.c @@ -128,7 +128,7 @@ static void ssb_pmu0_pllinit_r0(struct ssb_chipcommon *cc, ~(1 << SSB_PMURES_5354_BB_PLL_PU)); break; default: - SSB_WARN_ON(1); + WARN_ON(1); } for (i = 1500; i; i--) { tmp = chipco_read32(cc, SSB_CHIPCO_CLKCTLST); @@ -265,7 +265,7 @@ static void ssb_pmu1_pllinit_r0(struct ssb_chipcommon *cc, buffer_strength = 0x222222; break; default: - SSB_WARN_ON(1); + WARN_ON(1); } for (i = 1500; i; i--) { tmp = chipco_read32(cc, SSB_CHIPCO_CLKCTLST); @@ -501,7 +501,7 @@ static void ssb_pmu_resources_init(struct ssb_chipcommon *cc) ~(depend_tab[i].depend)); break; default: - SSB_WARN_ON(1); + WARN_ON(1); } } } @@ -568,12 +568,12 @@ void ssb_pmu_set_ldo_voltage(struct ssb_chipcommon *cc, mask = 0x3F; break; default: - SSB_WARN_ON(1); + WARN_ON(1); return; } break; case 0x4312: - if (SSB_WARN_ON(id != LDO_PAREF)) + if (WARN_ON(id != LDO_PAREF)) return; addr = 0; shift = 21; diff --git a/drivers/ssb/driver_gpio.c b/drivers/ssb/driver_gpio.c index 6ce4abf7d473..e809dae4c470 100644 --- a/drivers/ssb/driver_gpio.c +++ b/drivers/ssb/driver_gpio.c @@ -461,7 +461,7 @@ int ssb_gpio_init(struct ssb_bus *bus) else if (ssb_extif_available(&bus->extif)) return ssb_gpio_extif_init(bus); else - SSB_WARN_ON(1); + WARN_ON(1); return -1; } @@ -473,7 +473,7 @@ int ssb_gpio_unregister(struct ssb_bus *bus) gpiochip_remove(&bus->gpio); return 0; } else { - SSB_WARN_ON(1); + WARN_ON(1); } return -1; diff --git a/drivers/ssb/driver_pcicore.c b/drivers/ssb/driver_pcicore.c index ae80b3171523..6a5622e0ded5 100644 --- a/drivers/ssb/driver_pcicore.c +++ b/drivers/ssb/driver_pcicore.c @@ -115,7 +115,7 @@ static int ssb_extpci_read_config(struct ssb_pcicore *pc, u32 addr, val; void __iomem *mmio; - SSB_WARN_ON(!pc->hostmode); + WARN_ON(!pc->hostmode); if (unlikely(len != 1 && len != 2 && len != 4)) goto out; addr = get_cfgspace_addr(pc, bus, dev, func, off); @@ -161,7 +161,7 @@ static int ssb_extpci_write_config(struct ssb_pcicore *pc, u32 addr, val = 0; void __iomem *mmio; - SSB_WARN_ON(!pc->hostmode); + WARN_ON(!pc->hostmode); if (unlikely(len != 1 && len != 2 && len != 4)) goto out; addr = get_cfgspace_addr(pc, bus, dev, func, off); @@ -702,7 +702,7 @@ int ssb_pcicore_dev_irqvecs_enable(struct ssb_pcicore *pc, /* Calculate the "coremask" for the device. */ coremask = (1 << dev->core_index); - SSB_WARN_ON(bus->bustype != SSB_BUSTYPE_PCI); + WARN_ON(bus->bustype != SSB_BUSTYPE_PCI); err = pci_read_config_dword(bus->host_pci, SSB_PCI_IRQMASK, &tmp); if (err) goto out; diff --git a/drivers/ssb/embedded.c b/drivers/ssb/embedded.c index c39ddf8988c1..8254ed25e063 100644 --- a/drivers/ssb/embedded.c +++ b/drivers/ssb/embedded.c @@ -77,7 +77,7 @@ u32 ssb_gpio_in(struct ssb_bus *bus, u32 mask) else if (ssb_extif_available(&bus->extif)) res = ssb_extif_gpio_in(&bus->extif, mask); else - SSB_WARN_ON(1); + WARN_ON(1); spin_unlock_irqrestore(&bus->gpio_lock, flags); return res; @@ -95,7 +95,7 @@ u32 ssb_gpio_out(struct ssb_bus *bus, u32 mask, u32 value) else if (ssb_extif_available(&bus->extif)) res = ssb_extif_gpio_out(&bus->extif, mask, value); else - SSB_WARN_ON(1); + WARN_ON(1); spin_unlock_irqrestore(&bus->gpio_lock, flags); return res; @@ -113,7 +113,7 @@ u32 ssb_gpio_outen(struct ssb_bus *bus, u32 mask, u32 value) else if (ssb_extif_available(&bus->extif)) res = ssb_extif_gpio_outen(&bus->extif, mask, value); else - SSB_WARN_ON(1); + WARN_ON(1); spin_unlock_irqrestore(&bus->gpio_lock, flags); return res; @@ -145,7 +145,7 @@ u32 ssb_gpio_intmask(struct ssb_bus *bus, u32 mask, u32 value) else if (ssb_extif_available(&bus->extif)) res = ssb_extif_gpio_intmask(&bus->extif, mask, value); else - SSB_WARN_ON(1); + WARN_ON(1); spin_unlock_irqrestore(&bus->gpio_lock, flags); return res; @@ -163,7 +163,7 @@ u32 ssb_gpio_polarity(struct ssb_bus *bus, u32 mask, u32 value) else if (ssb_extif_available(&bus->extif)) res = ssb_extif_gpio_polarity(&bus->extif, mask, value); else - SSB_WARN_ON(1); + WARN_ON(1); spin_unlock_irqrestore(&bus->gpio_lock, flags); return res; diff --git a/drivers/ssb/host_soc.c b/drivers/ssb/host_soc.c index eadaedf466f6..3b438480515c 100644 --- a/drivers/ssb/host_soc.c +++ b/drivers/ssb/host_soc.c @@ -61,7 +61,7 @@ static void ssb_host_soc_block_read(struct ssb_device *dev, void *buffer, case sizeof(u16): { __le16 *buf = buffer; - SSB_WARN_ON(count & 1); + WARN_ON(count & 1); while (count) { *buf = (__force __le16)__raw_readw(addr); buf++; @@ -72,7 +72,7 @@ static void ssb_host_soc_block_read(struct ssb_device *dev, void *buffer, case sizeof(u32): { __le32 *buf = buffer; - SSB_WARN_ON(count & 3); + WARN_ON(count & 3); while (count) { *buf = (__force __le32)__raw_readl(addr); buf++; @@ -81,7 +81,7 @@ static void ssb_host_soc_block_read(struct ssb_device *dev, void *buffer, break; } default: - SSB_WARN_ON(1); + WARN_ON(1); } } #endif /* CONFIG_SSB_BLOCKIO */ @@ -134,7 +134,7 @@ static void ssb_host_soc_block_write(struct ssb_device *dev, const void *buffer, case sizeof(u16): { const __le16 *buf = buffer; - SSB_WARN_ON(count & 1); + WARN_ON(count & 1); while (count) { __raw_writew((__force u16)(*buf), addr); buf++; @@ -145,7 +145,7 @@ static void ssb_host_soc_block_write(struct ssb_device *dev, const void *buffer, case sizeof(u32): { const __le32 *buf = buffer; - SSB_WARN_ON(count & 3); + WARN_ON(count & 3); while (count) { __raw_writel((__force u32)(*buf), addr); buf++; @@ -154,7 +154,7 @@ static void ssb_host_soc_block_write(struct ssb_device *dev, const void *buffer, break; } default: - SSB_WARN_ON(1); + WARN_ON(1); } } #endif /* CONFIG_SSB_BLOCKIO */ diff --git a/drivers/ssb/main.c b/drivers/ssb/main.c index 9da56d2fdbd3..0a26984acb2c 100644 --- a/drivers/ssb/main.c +++ b/drivers/ssb/main.c @@ -209,7 +209,7 @@ int ssb_devices_freeze(struct ssb_bus *bus, struct ssb_freeze_context *ctx) memset(ctx, 0, sizeof(*ctx)); ctx->bus = bus; - SSB_WARN_ON(bus->nr_devices > ARRAY_SIZE(ctx->device_frozen)); + WARN_ON(bus->nr_devices > ARRAY_SIZE(ctx->device_frozen)); for (i = 0; i < bus->nr_devices; i++) { sdev = ssb_device_get(&bus->devices[i]); @@ -220,7 +220,7 @@ int ssb_devices_freeze(struct ssb_bus *bus, struct ssb_freeze_context *ctx) continue; } sdrv = drv_to_ssb_drv(sdev->dev->driver); - if (SSB_WARN_ON(!sdrv->remove)) + if (WARN_ON(!sdrv->remove)) continue; sdrv->remove(sdev); ctx->device_frozen[i] = 1; @@ -248,10 +248,10 @@ int ssb_devices_thaw(struct ssb_freeze_context *ctx) continue; sdev = &bus->devices[i]; - if (SSB_WARN_ON(!sdev->dev || !sdev->dev->driver)) + if (WARN_ON(!sdev->dev || !sdev->dev->driver)) continue; sdrv = drv_to_ssb_drv(sdev->dev->driver); - if (SSB_WARN_ON(!sdrv || !sdrv->probe)) + if (WARN_ON(!sdrv || !sdrv->probe)) continue; err = sdrv->probe(sdev, &sdev->id); @@ -861,13 +861,13 @@ u32 ssb_calc_clock_rate(u32 plltype, u32 n, u32 m) case SSB_PLLTYPE_2: /* 48Mhz, 4 dividers */ n1 += SSB_CHIPCO_CLK_T2_BIAS; n2 += SSB_CHIPCO_CLK_T2_BIAS; - SSB_WARN_ON(!((n1 >= 2) && (n1 <= 7))); - SSB_WARN_ON(!((n2 >= 5) && (n2 <= 23))); + WARN_ON(!((n1 >= 2) && (n1 <= 7))); + WARN_ON(!((n2 >= 5) && (n2 <= 23))); break; case SSB_PLLTYPE_5: /* 25Mhz, 4 dividers */ return 100000000; default: - SSB_WARN_ON(1); + WARN_ON(1); } switch (plltype) { @@ -916,9 +916,9 @@ u32 ssb_calc_clock_rate(u32 plltype, u32 n, u32 m) m1 += SSB_CHIPCO_CLK_T2_BIAS; m2 += SSB_CHIPCO_CLK_T2M2_BIAS; m3 += SSB_CHIPCO_CLK_T2_BIAS; - SSB_WARN_ON(!((m1 >= 2) && (m1 <= 7))); - SSB_WARN_ON(!((m2 >= 3) && (m2 <= 10))); - SSB_WARN_ON(!((m3 >= 2) && (m3 <= 7))); + WARN_ON(!((m1 >= 2) && (m1 <= 7))); + WARN_ON(!((m2 >= 3) && (m2 <= 10))); + WARN_ON(!((m3 >= 2) && (m3 <= 7))); if (!(mc & SSB_CHIPCO_CLK_T2MC_M1BYP)) clock /= m1; @@ -928,7 +928,7 @@ u32 ssb_calc_clock_rate(u32 plltype, u32 n, u32 m) clock /= m3; return clock; default: - SSB_WARN_ON(1); + WARN_ON(1); } return 0; } @@ -1169,9 +1169,7 @@ int ssb_bus_may_powerdown(struct ssb_bus *bus) if (err) goto error; out: -#ifdef CONFIG_SSB_DEBUG bus->powered_up = 0; -#endif return err; error: pr_err("Bus powerdown failed\n"); @@ -1188,9 +1186,7 @@ int ssb_bus_powerup(struct ssb_bus *bus, bool dynamic_pctl) if (err) goto error; -#ifdef CONFIG_SSB_DEBUG bus->powered_up = 1; -#endif mode = dynamic_pctl ? SSB_CLKMODE_DYNAMIC : SSB_CLKMODE_FAST; ssb_chipco_set_clockmode(&bus->chipco, mode); @@ -1242,15 +1238,15 @@ u32 ssb_admatch_base(u32 adm) base = (adm & SSB_ADM_BASE0); break; case SSB_ADM_TYPE1: - SSB_WARN_ON(adm & SSB_ADM_NEG); /* unsupported */ + WARN_ON(adm & SSB_ADM_NEG); /* unsupported */ base = (adm & SSB_ADM_BASE1); break; case SSB_ADM_TYPE2: - SSB_WARN_ON(adm & SSB_ADM_NEG); /* unsupported */ + WARN_ON(adm & SSB_ADM_NEG); /* unsupported */ base = (adm & SSB_ADM_BASE2); break; default: - SSB_WARN_ON(1); + WARN_ON(1); } return base; @@ -1266,15 +1262,15 @@ u32 ssb_admatch_size(u32 adm) size = ((adm & SSB_ADM_SZ0) >> SSB_ADM_SZ0_SHIFT); break; case SSB_ADM_TYPE1: - SSB_WARN_ON(adm & SSB_ADM_NEG); /* unsupported */ + WARN_ON(adm & SSB_ADM_NEG); /* unsupported */ size = ((adm & SSB_ADM_SZ1) >> SSB_ADM_SZ1_SHIFT); break; case SSB_ADM_TYPE2: - SSB_WARN_ON(adm & SSB_ADM_NEG); /* unsupported */ + WARN_ON(adm & SSB_ADM_NEG); /* unsupported */ size = ((adm & SSB_ADM_SZ2) >> SSB_ADM_SZ2_SHIFT); break; default: - SSB_WARN_ON(1); + WARN_ON(1); } size = (1 << (size + 1)); diff --git a/drivers/ssb/pci.c b/drivers/ssb/pci.c index ad4308529eba..84807a9b4b13 100644 --- a/drivers/ssb/pci.c +++ b/drivers/ssb/pci.c @@ -946,7 +946,6 @@ out: return err; } -#ifdef CONFIG_SSB_DEBUG static int ssb_pci_assert_buspower(struct ssb_bus *bus) { if (likely(bus->powered_up)) @@ -960,12 +959,6 @@ static int ssb_pci_assert_buspower(struct ssb_bus *bus) return -ENODEV; } -#else /* DEBUG */ -static inline int ssb_pci_assert_buspower(struct ssb_bus *bus) -{ - return 0; -} -#endif /* DEBUG */ static u8 ssb_pci_read8(struct ssb_device *dev, u16 offset) { @@ -1024,15 +1017,15 @@ static void ssb_pci_block_read(struct ssb_device *dev, void *buffer, ioread8_rep(addr, buffer, count); break; case sizeof(u16): - SSB_WARN_ON(count & 1); + WARN_ON(count & 1); ioread16_rep(addr, buffer, count >> 1); break; case sizeof(u32): - SSB_WARN_ON(count & 3); + WARN_ON(count & 3); ioread32_rep(addr, buffer, count >> 2); break; default: - SSB_WARN_ON(1); + WARN_ON(1); } return; @@ -1098,15 +1091,15 @@ static void ssb_pci_block_write(struct ssb_device *dev, const void *buffer, iowrite8_rep(addr, buffer, count); break; case sizeof(u16): - SSB_WARN_ON(count & 1); + WARN_ON(count & 1); iowrite16_rep(addr, buffer, count >> 1); break; case sizeof(u32): - SSB_WARN_ON(count & 3); + WARN_ON(count & 3); iowrite32_rep(addr, buffer, count >> 2); break; default: - SSB_WARN_ON(1); + WARN_ON(1); } } #endif /* CONFIG_SSB_BLOCKIO */ diff --git a/drivers/ssb/pcmcia.c b/drivers/ssb/pcmcia.c index 20f63cc88e70..567013f8a8be 100644 --- a/drivers/ssb/pcmcia.c +++ b/drivers/ssb/pcmcia.c @@ -169,7 +169,7 @@ int ssb_pcmcia_switch_segment(struct ssb_bus *bus, u8 seg) int err; u8 val; - SSB_WARN_ON((seg != 0) && (seg != 1)); + WARN_ON((seg != 0) && (seg != 1)); while (1) { err = ssb_pcmcia_cfg_write(bus, SSB_PCMCIA_MEMSEG, seg); if (err) @@ -299,7 +299,7 @@ static void ssb_pcmcia_block_read(struct ssb_device *dev, void *buffer, case sizeof(u16): { __le16 *buf = buffer; - SSB_WARN_ON(count & 1); + WARN_ON(count & 1); while (count) { *buf = (__force __le16)__raw_readw(addr); buf++; @@ -310,7 +310,7 @@ static void ssb_pcmcia_block_read(struct ssb_device *dev, void *buffer, case sizeof(u32): { __le16 *buf = buffer; - SSB_WARN_ON(count & 3); + WARN_ON(count & 3); while (count) { *buf = (__force __le16)__raw_readw(addr); buf++; @@ -321,7 +321,7 @@ static void ssb_pcmcia_block_read(struct ssb_device *dev, void *buffer, break; } default: - SSB_WARN_ON(1); + WARN_ON(1); } unlock: spin_unlock_irqrestore(&bus->bar_lock, flags); @@ -399,7 +399,7 @@ static void ssb_pcmcia_block_write(struct ssb_device *dev, const void *buffer, case sizeof(u16): { const __le16 *buf = buffer; - SSB_WARN_ON(count & 1); + WARN_ON(count & 1); while (count) { __raw_writew((__force u16)(*buf), addr); buf++; @@ -410,7 +410,7 @@ static void ssb_pcmcia_block_write(struct ssb_device *dev, const void *buffer, case sizeof(u32): { const __le16 *buf = buffer; - SSB_WARN_ON(count & 3); + WARN_ON(count & 3); while (count) { __raw_writew((__force u16)(*buf), addr); buf++; @@ -421,7 +421,7 @@ static void ssb_pcmcia_block_write(struct ssb_device *dev, const void *buffer, break; } default: - SSB_WARN_ON(1); + WARN_ON(1); } unlock: mmiowb(); diff --git a/drivers/ssb/scan.c b/drivers/ssb/scan.c index 71fbb4b3eb6a..6ceee98ed6ff 100644 --- a/drivers/ssb/scan.c +++ b/drivers/ssb/scan.c @@ -210,7 +210,7 @@ void ssb_iounmap(struct ssb_bus *bus) #ifdef CONFIG_SSB_PCIHOST pci_iounmap(bus->host_pci, bus->mmio); #else - SSB_BUG_ON(1); /* Can't reach this code. */ + WARN_ON(1); /* Can't reach this code. */ #endif break; case SSB_BUSTYPE_SDIO: @@ -236,7 +236,7 @@ static void __iomem *ssb_ioremap(struct ssb_bus *bus, #ifdef CONFIG_SSB_PCIHOST mmio = pci_iomap(bus->host_pci, 0, ~0UL); #else - SSB_BUG_ON(1); /* Can't reach this code. */ + WARN_ON(1); /* Can't reach this code. */ #endif break; case SSB_BUSTYPE_SDIO: diff --git a/drivers/ssb/sdio.c b/drivers/ssb/sdio.c index 1aedc5fbb62f..7fe0afb42234 100644 --- a/drivers/ssb/sdio.c +++ b/drivers/ssb/sdio.c @@ -316,18 +316,18 @@ static void ssb_sdio_block_read(struct ssb_device *dev, void *buffer, break; } case sizeof(u16): { - SSB_WARN_ON(count & 1); + WARN_ON(count & 1); error = sdio_readsb(bus->host_sdio, buffer, offset, count); break; } case sizeof(u32): { - SSB_WARN_ON(count & 3); + WARN_ON(count & 3); offset |= SBSDIO_SB_ACCESS_2_4B_FLAG; /* 32 bit data access */ error = sdio_readsb(bus->host_sdio, buffer, offset, count); break; } default: - SSB_WARN_ON(1); + WARN_ON(1); } if (!error) goto out; @@ -423,18 +423,18 @@ static void ssb_sdio_block_write(struct ssb_device *dev, const void *buffer, (void *)buffer, count); break; case sizeof(u16): - SSB_WARN_ON(count & 1); + WARN_ON(count & 1); error = sdio_writesb(bus->host_sdio, offset, (void *)buffer, count); break; case sizeof(u32): - SSB_WARN_ON(count & 3); + WARN_ON(count & 3); offset |= SBSDIO_SB_ACCESS_2_4B_FLAG; /* 32 bit data access */ error = sdio_writesb(bus->host_sdio, offset, (void *)buffer, count); break; default: - SSB_WARN_ON(1); + WARN_ON(1); } if (!error) goto out; diff --git a/drivers/ssb/ssb_private.h b/drivers/ssb/ssb_private.h index 885e278c4487..5f31bdfbe77f 100644 --- a/drivers/ssb/ssb_private.h +++ b/drivers/ssb/ssb_private.h @@ -9,15 +9,6 @@ #include #include -#ifdef CONFIG_SSB_DEBUG -# define SSB_WARN_ON(x) WARN_ON(x) -# define SSB_BUG_ON(x) BUG_ON(x) -#else -static inline int __ssb_do_nothing(int x) { return x; } -# define SSB_WARN_ON(x) __ssb_do_nothing(unlikely(!!(x))) -# define SSB_BUG_ON(x) __ssb_do_nothing(unlikely(!!(x))) -#endif - /* pci.c */ #ifdef CONFIG_SSB_PCIHOST diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h index 3b43655cabe6..0d5a2691e7e9 100644 --- a/include/linux/ssb/ssb.h +++ b/include/linux/ssb/ssb.h @@ -499,11 +499,9 @@ struct ssb_bus { /* Internal-only stuff follows. Do not touch. */ struct list_head list; -#ifdef CONFIG_SSB_DEBUG /* Is the bus already powered up? */ bool powered_up; int power_warn_count; -#endif /* DEBUG */ }; enum ssb_quirks { -- cgit v1.2.3 From 624c0f0239f04cce78c86afa95eb2841c84fbab1 Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 9 Aug 2018 15:38:38 +0200 Subject: phylink: add helper for configuring 2500BaseX modes Add a helper for MAC drivers to use in their validate callback to deal with 2500BaseX vs 1000BaseX modes, where the hardware supports both but it is not possible to automatically select between them. This helper defaults to 1000BaseX, as that is the 802.3 standard, and will allow users to select 2500BaseX either by forcing the speed if AN is disabled, or by changing the advertising mask if AN is enabled. Disabling AN is not recommended as it is only the speed that we're interested in controlling, not the duplex or pause mode parameters. Signed-off-by: Russell King Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/phy/phylink.c | 30 ++++++++++++++++++++++++++++++ include/linux/phylink.h | 1 + 2 files changed, 31 insertions(+) (limited to 'include') diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index af4dc4425be2..3ba5cf2a8a5f 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -1688,4 +1688,34 @@ static const struct sfp_upstream_ops sfp_phylink_ops = { .disconnect_phy = phylink_sfp_disconnect_phy, }; +/* Helpers for MAC drivers */ + +/** + * phylink_helper_basex_speed() - 1000BaseX/2500BaseX helper + * @state: a pointer to a &struct phylink_link_state + * + * Inspect the interface mode, advertising mask or forced speed and + * decide whether to run at 2.5Gbit or 1Gbit appropriately, switching + * the interface mode to suit. @state->interface is appropriately + * updated, and the advertising mask has the "other" baseX_Full flag + * cleared. + */ +void phylink_helper_basex_speed(struct phylink_link_state *state) +{ + if (phy_interface_mode_is_8023z(state->interface)) { + bool want_2500 = state->an_enabled ? + phylink_test(state->advertising, 2500baseX_Full) : + state->speed == SPEED_2500; + + if (want_2500) { + phylink_clear(state->advertising, 1000baseX_Full); + state->interface = PHY_INTERFACE_MODE_2500BASEX; + } else { + phylink_clear(state->advertising, 2500baseX_Full); + state->interface = PHY_INTERFACE_MODE_1000BASEX; + } + } +} +EXPORT_SYMBOL_GPL(phylink_helper_basex_speed); + MODULE_LICENSE("GPL"); diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 50eeae025f1e..021fc6595856 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -234,5 +234,6 @@ int phylink_mii_ioctl(struct phylink *, struct ifreq *, int); #define phylink_test(bm, mode) __phylink_do_bit(test_bit, bm, mode) void phylink_set_port_modes(unsigned long *bits); +void phylink_helper_basex_speed(struct phylink_link_state *state); #endif -- cgit v1.2.3 From 48ae5554a076c1bca31448d60263e4038def9f6f Mon Sep 17 00:00:00 2001 From: Jose Abreu Date: Wed, 8 Aug 2018 09:04:29 +0100 Subject: net: stmmac: Add XGMAC 2.10 HWIF entry Add a new entry to HWIF table for XGMAC 2.10. For now we fill it with empty callbacks which will be added in posterior patches. Signed-off-by: Jose Abreu Cc: David S. Miller Cc: Joao Pinto Cc: Giuseppe Cavallaro Cc: Alexandre Torgue Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/common.h | 14 +++++++------ drivers/net/ethernet/stmicro/stmmac/hwif.c | 31 ++++++++++++++++++++++++++-- include/linux/stmmac.h | 1 + 3 files changed, 38 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 78fd0f8b8e81..3fb81acbd274 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -36,12 +36,14 @@ #include "mmc.h" /* Synopsys Core versions */ -#define DWMAC_CORE_3_40 0x34 -#define DWMAC_CORE_3_50 0x35 -#define DWMAC_CORE_4_00 0x40 -#define DWMAC_CORE_4_10 0x41 -#define DWMAC_CORE_5_00 0x50 -#define DWMAC_CORE_5_10 0x51 +#define DWMAC_CORE_3_40 0x34 +#define DWMAC_CORE_3_50 0x35 +#define DWMAC_CORE_4_00 0x40 +#define DWMAC_CORE_4_10 0x41 +#define DWMAC_CORE_5_00 0x50 +#define DWMAC_CORE_5_10 0x51 +#define DWXGMAC_CORE_2_10 0x21 + #define STMMAC_CHAN0 0 /* Always supported and default for all chips */ /* These need to be power of two, and >= 4 */ diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.c b/drivers/net/ethernet/stmicro/stmmac/hwif.c index 1f50e83cafb2..24f5ff175aa4 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.c +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.c @@ -72,6 +72,7 @@ static int stmmac_dwmac4_quirks(struct stmmac_priv *priv) static const struct stmmac_hwif_entry { bool gmac; bool gmac4; + bool xgmac; u32 min_id; const struct stmmac_regs_off regs; const void *desc; @@ -87,6 +88,7 @@ static const struct stmmac_hwif_entry { { .gmac = false, .gmac4 = false, + .xgmac = false, .min_id = 0, .regs = { .ptp_off = PTP_GMAC3_X_OFFSET, @@ -103,6 +105,7 @@ static const struct stmmac_hwif_entry { }, { .gmac = true, .gmac4 = false, + .xgmac = false, .min_id = 0, .regs = { .ptp_off = PTP_GMAC3_X_OFFSET, @@ -119,6 +122,7 @@ static const struct stmmac_hwif_entry { }, { .gmac = false, .gmac4 = true, + .xgmac = false, .min_id = 0, .regs = { .ptp_off = PTP_GMAC4_OFFSET, @@ -135,6 +139,7 @@ static const struct stmmac_hwif_entry { }, { .gmac = false, .gmac4 = true, + .xgmac = false, .min_id = DWMAC_CORE_4_00, .regs = { .ptp_off = PTP_GMAC4_OFFSET, @@ -151,6 +156,7 @@ static const struct stmmac_hwif_entry { }, { .gmac = false, .gmac4 = true, + .xgmac = false, .min_id = DWMAC_CORE_4_10, .regs = { .ptp_off = PTP_GMAC4_OFFSET, @@ -167,6 +173,7 @@ static const struct stmmac_hwif_entry { }, { .gmac = false, .gmac4 = true, + .xgmac = false, .min_id = DWMAC_CORE_5_10, .regs = { .ptp_off = PTP_GMAC4_OFFSET, @@ -180,11 +187,29 @@ static const struct stmmac_hwif_entry { .tc = &dwmac510_tc_ops, .setup = dwmac4_setup, .quirks = NULL, - } + }, { + .gmac = false, + .gmac4 = false, + .xgmac = true, + .min_id = DWXGMAC_CORE_2_10, + .regs = { + .ptp_off = 0, + .mmc_off = 0, + }, + .desc = NULL, + .dma = NULL, + .mac = NULL, + .hwtimestamp = NULL, + .mode = NULL, + .tc = NULL, + .setup = NULL, + .quirks = NULL, + }, }; int stmmac_hwif_init(struct stmmac_priv *priv) { + bool needs_xgmac = priv->plat->has_xgmac; bool needs_gmac4 = priv->plat->has_gmac4; bool needs_gmac = priv->plat->has_gmac; const struct stmmac_hwif_entry *entry; @@ -195,7 +220,7 @@ int stmmac_hwif_init(struct stmmac_priv *priv) if (needs_gmac) { id = stmmac_get_id(priv, GMAC_VERSION); - } else if (needs_gmac4) { + } else if (needs_gmac4 || needs_xgmac) { id = stmmac_get_id(priv, GMAC4_VERSION); } else { id = 0; @@ -229,6 +254,8 @@ int stmmac_hwif_init(struct stmmac_priv *priv) continue; if (needs_gmac4 ^ entry->gmac4) continue; + if (needs_xgmac ^ entry->xgmac) + continue; /* Use synopsys_id var because some setups can override this */ if (priv->synopsys_id < entry->min_id) continue; diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 32feac5bbd75..c43e9a01b892 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -190,5 +190,6 @@ struct plat_stmmacenet_data { bool tso_en; int mac_port_sel_speed; bool en_tx_lpi_clockgating; + int has_xgmac; }; #endif -- cgit v1.2.3 From 2d2917f7747805a1f4188672f308d82a8ba01700 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Thu, 9 Aug 2018 14:04:14 -0600 Subject: PCI: Export pcie_has_flr() pcie_flr() suggests pcie_has_flr() to ensure that PCIe FLR support is present prior to calling. pcie_flr() is exported while pcie_has_flr() is not. Resolve this. Signed-off-by: Alex Williamson Signed-off-by: Bjorn Helgaas --- drivers/pci/pci.c | 3 ++- include/linux/pci.h | 1 + 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index d123c2b173da..85e5b80a69a7 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -4039,7 +4039,7 @@ static int pci_dev_wait(struct pci_dev *dev, char *reset_type, int timeout) * Returns true if the device advertises support for PCIe function level * resets. */ -static bool pcie_has_flr(struct pci_dev *dev) +bool pcie_has_flr(struct pci_dev *dev) { u32 cap; @@ -4049,6 +4049,7 @@ static bool pcie_has_flr(struct pci_dev *dev) pcie_capability_read_dword(dev, PCI_EXP_DEVCAP, &cap); return cap & PCI_EXP_DEVCAP_FLR; } +EXPORT_SYMBOL_GPL(pcie_has_flr); /** * pcie_flr - initiate a PCIe function level reset diff --git a/include/linux/pci.h b/include/linux/pci.h index 307b336496f6..bace761deff2 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1090,6 +1090,7 @@ u32 pcie_bandwidth_available(struct pci_dev *dev, struct pci_dev **limiting_dev, enum pci_bus_speed *speed, enum pcie_link_width *width); void pcie_print_link_status(struct pci_dev *dev); +bool pcie_has_flr(struct pci_dev *dev); int pcie_flr(struct pci_dev *dev); int __pci_reset_function_locked(struct pci_dev *dev); int pci_reset_function(struct pci_dev *dev); -- cgit v1.2.3 From 5e7baf0fcb2a3aef7329f3c7543d4695a46bd321 Mon Sep 17 00:00:00 2001 From: Manish Chopra Date: Thu, 9 Aug 2018 11:13:49 -0700 Subject: qed/qede: Multi CoS support. This patch adds support for tc mqprio offload, using this different traffic classes on the adapter can be utilized based on configured priority to tc map. For example - tc qdisc add dev eth0 root mqprio num_tc 4 map 0 1 2 3 This will cause SKBs with priority 0,1,2,3 to transmit over tc 0,1,2,3 hardware queues respectively. Signed-off-by: Manish Chopra Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_l2.c | 9 +- drivers/net/ethernet/qlogic/qed/qed_main.c | 5 +- drivers/net/ethernet/qlogic/qede/qede.h | 13 +++ drivers/net/ethernet/qlogic/qede/qede_ethtool.c | 48 ++++++-- drivers/net/ethernet/qlogic/qede/qede_fp.c | 29 +++-- drivers/net/ethernet/qlogic/qede/qede_main.c | 139 +++++++++++++++++++----- include/linux/qed/qed_eth_if.h | 6 + 7 files changed, 200 insertions(+), 49 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index 5ede6408649d..82a1bd1f8a8c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -2188,16 +2188,17 @@ out: static int qed_fill_eth_dev_info(struct qed_dev *cdev, struct qed_dev_eth_info *info) { + struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev); int i; memset(info, 0, sizeof(*info)); - info->num_tc = 1; - if (IS_PF(cdev)) { int max_vf_vlan_filters = 0; int max_vf_mac_filters = 0; + info->num_tc = p_hwfn->hw_info.num_hw_tc; + if (cdev->int_params.out.int_mode == QED_INT_MODE_MSIX) { u16 num_queues = 0; @@ -2248,6 +2249,8 @@ static int qed_fill_eth_dev_info(struct qed_dev *cdev, } else { u16 total_cids = 0; + info->num_tc = 1; + /* Determine queues & XDP support */ for_each_hwfn(cdev, i) { struct qed_hwfn *p_hwfn = &cdev->hwfns[i]; @@ -2554,7 +2557,7 @@ static int qed_start_txq(struct qed_dev *cdev, rc = qed_eth_tx_queue_start(p_hwfn, p_hwfn->hw_info.opaque_fid, - p_params, 0, + p_params, p_params->tc, pbl_addr, pbl_size, ret_params); if (rc) { diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index dbe81310c0b6..2094d86a7a08 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -948,13 +948,14 @@ static void qed_update_pf_params(struct qed_dev *cdev, params->eth_pf_params.num_arfs_filters = 0; /* In case we might support RDMA, don't allow qede to be greedy - * with the L2 contexts. Allow for 64 queues [rx, tx, xdp] per hwfn. + * with the L2 contexts. Allow for 64 queues [rx, tx cos, xdp] + * per hwfn. */ if (QED_IS_RDMA_PERSONALITY(QED_LEADING_HWFN(cdev))) { u16 *num_cons; num_cons = ¶ms->eth_pf_params.num_cons; - *num_cons = min_t(u16, *num_cons, 192); + *num_cons = min_t(u16, *num_cons, QED_MAX_L2_CONS); } for (i = 0; i < cdev->num_hwfns; i++) { diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h index d7ed0d3dbf71..e90c60a8fb01 100644 --- a/drivers/net/ethernet/qlogic/qede/qede.h +++ b/drivers/net/ethernet/qlogic/qede/qede.h @@ -386,6 +386,15 @@ struct qede_tx_queue { #define QEDE_TXQ_XDP_TO_IDX(edev, txq) ((txq)->index - \ QEDE_MAX_TSS_CNT(edev)) #define QEDE_TXQ_IDX_TO_XDP(edev, idx) ((idx) + QEDE_MAX_TSS_CNT(edev)) +#define QEDE_NDEV_TXQ_ID_TO_FP_ID(edev, idx) ((edev)->fp_num_rx + \ + ((idx) % QEDE_TSS_COUNT(edev))) +#define QEDE_NDEV_TXQ_ID_TO_TXQ_COS(edev, idx) ((idx) / QEDE_TSS_COUNT(edev)) +#define QEDE_TXQ_TO_NDEV_TXQ_ID(edev, txq) ((QEDE_TSS_COUNT(edev) * \ + (txq)->cos) + (txq)->index) +#define QEDE_NDEV_TXQ_ID_TO_TXQ(edev, idx) \ + (&((edev)->fp_array[QEDE_NDEV_TXQ_ID_TO_FP_ID(edev, idx)].txq \ + [QEDE_NDEV_TXQ_ID_TO_TXQ_COS(edev, idx)])) +#define QEDE_FP_TC0_TXQ(fp) (&((fp)->txq[0])) /* Regular Tx requires skb + metadata for release purpose, * while XDP requires the pages and the mapped address. @@ -399,6 +408,8 @@ struct qede_tx_queue { /* Slowpath; Should be kept in end [unless missing padding] */ void *handle; + u16 cos; + u16 ndev_txq_id; }; #define BD_UNMAP_ADDR(bd) HILO_U64(le32_to_cpu((bd)->addr.hi), \ @@ -541,5 +552,7 @@ void qede_update_rx_prod(struct qede_dev *edev, struct qede_rx_queue *rxq); #define QEDE_RX_HDR_SIZE 256 #define QEDE_MAX_JUMBO_PACKET_SIZE 9600 #define for_each_queue(i) for (i = 0; i < edev->num_queues; i++) +#define for_each_cos_in_txq(edev, var) \ + for ((var) = 0; (var) < (edev)->dev_info.num_tc; (var)++) #endif /* _QEDE_H_ */ diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c index b37857f3f950..2bd84d6d9b15 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c @@ -222,7 +222,7 @@ static void qede_get_strings_stats_txq(struct qede_dev *edev, QEDE_TXQ_XDP_TO_IDX(edev, txq), qede_tqstats_arr[i].string); else - sprintf(*buf, "%d: %s", txq->index, + sprintf(*buf, "%d_%d: %s", txq->index, txq->cos, qede_tqstats_arr[i].string); *buf += ETH_GSTRING_LEN; } @@ -262,8 +262,13 @@ static void qede_get_strings_stats(struct qede_dev *edev, u8 *buf) if (fp->type & QEDE_FASTPATH_XDP) qede_get_strings_stats_txq(edev, fp->xdp_tx, &buf); - if (fp->type & QEDE_FASTPATH_TX) - qede_get_strings_stats_txq(edev, fp->txq, &buf); + if (fp->type & QEDE_FASTPATH_TX) { + int cos; + + for_each_cos_in_txq(edev, cos) + qede_get_strings_stats_txq(edev, + &fp->txq[cos], &buf); + } } /* Account for non-queue statistics */ @@ -338,8 +343,12 @@ static void qede_get_ethtool_stats(struct net_device *dev, if (fp->type & QEDE_FASTPATH_XDP) qede_get_ethtool_stats_txq(fp->xdp_tx, &buf); - if (fp->type & QEDE_FASTPATH_TX) - qede_get_ethtool_stats_txq(fp->txq, &buf); + if (fp->type & QEDE_FASTPATH_TX) { + int cos; + + for_each_cos_in_txq(edev, cos) + qede_get_ethtool_stats_txq(&fp->txq[cos], &buf); + } } for (i = 0; i < QEDE_NUM_STATS; i++) { @@ -366,7 +375,8 @@ static int qede_get_sset_count(struct net_device *dev, int stringset) num_stats--; /* Account for the Regular Tx statistics */ - num_stats += QEDE_TSS_COUNT(edev) * QEDE_NUM_TQSTATS; + num_stats += QEDE_TSS_COUNT(edev) * QEDE_NUM_TQSTATS * + edev->dev_info.num_tc; /* Account for the Regular Rx statistics */ num_stats += QEDE_RSS_COUNT(edev) * QEDE_NUM_RQSTATS; @@ -741,9 +751,17 @@ static int qede_get_coalesce(struct net_device *dev, } for_each_queue(i) { + struct qede_tx_queue *txq; + fp = &edev->fp_array[i]; + + /* All TX queues of given fastpath uses same + * coalescing value, so no need to iterate over + * all TCs, TC0 txq should suffice. + */ if (fp->type & QEDE_FASTPATH_TX) { - tx_handle = fp->txq->handle; + txq = QEDE_FP_TC0_TXQ(fp); + tx_handle = txq->handle; break; } } @@ -801,9 +819,17 @@ static int qede_set_coalesce(struct net_device *dev, } if (edev->fp_array[i].type & QEDE_FASTPATH_TX) { + struct qede_tx_queue *txq; + + /* All TX queues of given fastpath uses same + * coalescing value, so no need to iterate over + * all TCs, TC0 txq should suffice. + */ + txq = QEDE_FP_TC0_TXQ(fp); + rc = edev->ops->common->set_coalesce(edev->cdev, 0, txc, - fp->txq->handle); + txq->handle); if (rc) { DP_INFO(edev, "Set TX coalesce error, rc = %d\n", rc); @@ -1385,8 +1411,10 @@ static int qede_selftest_transmit_traffic(struct qede_dev *edev, u16 val; for_each_queue(i) { - if (edev->fp_array[i].type & QEDE_FASTPATH_TX) { - txq = edev->fp_array[i].txq; + struct qede_fastpath *fp = &edev->fp_array[i]; + + if (fp->type & QEDE_FASTPATH_TX) { + txq = QEDE_FP_TC0_TXQ(fp); break; } } diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c index 8c9e95ba9917..1a78027de071 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_fp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c @@ -408,12 +408,12 @@ static void qede_xdp_tx_int(struct qede_dev *edev, struct qede_tx_queue *txq) static int qede_tx_int(struct qede_dev *edev, struct qede_tx_queue *txq) { + unsigned int pkts_compl = 0, bytes_compl = 0; struct netdev_queue *netdev_txq; u16 hw_bd_cons; - unsigned int pkts_compl = 0, bytes_compl = 0; int rc; - netdev_txq = netdev_get_tx_queue(edev->ndev, txq->index); + netdev_txq = netdev_get_tx_queue(edev->ndev, txq->ndev_txq_id); hw_bd_cons = le16_to_cpu(*txq->hw_cons_ptr); barrier(); @@ -1365,9 +1365,14 @@ static bool qede_poll_is_more_work(struct qede_fastpath *fp) if (qede_txq_has_work(fp->xdp_tx)) return true; - if (likely(fp->type & QEDE_FASTPATH_TX)) - if (qede_txq_has_work(fp->txq)) - return true; + if (likely(fp->type & QEDE_FASTPATH_TX)) { + int cos; + + for_each_cos_in_txq(fp->edev, cos) { + if (qede_txq_has_work(&fp->txq[cos])) + return true; + } + } return false; } @@ -1382,8 +1387,14 @@ int qede_poll(struct napi_struct *napi, int budget) struct qede_dev *edev = fp->edev; int rx_work_done = 0; - if (likely(fp->type & QEDE_FASTPATH_TX) && qede_txq_has_work(fp->txq)) - qede_tx_int(edev, fp->txq); + if (likely(fp->type & QEDE_FASTPATH_TX)) { + int cos; + + for_each_cos_in_txq(fp->edev, cos) { + if (qede_txq_has_work(&fp->txq[cos])) + qede_tx_int(edev, &fp->txq[cos]); + } + } if ((fp->type & QEDE_FASTPATH_XDP) && qede_txq_has_work(fp->xdp_tx)) qede_xdp_tx_int(edev, fp->xdp_tx); @@ -1444,8 +1455,8 @@ netdev_tx_t qede_start_xmit(struct sk_buff *skb, struct net_device *ndev) /* Get tx-queue context and netdev index */ txq_index = skb_get_queue_mapping(skb); - WARN_ON(txq_index >= QEDE_TSS_COUNT(edev)); - txq = edev->fp_array[edev->fp_num_rx + txq_index].txq; + WARN_ON(txq_index >= QEDE_TSS_COUNT(edev) * edev->dev_info.num_tc); + txq = QEDE_NDEV_TXQ_ID_TO_TXQ(edev, txq_index); netdev_txq = netdev_get_tx_queue(ndev, txq_index); WARN_ON(qed_chain_get_elem_left(&txq->tx_pbl) < (MAX_SKB_FRAGS + 1)); diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 6a796040a32c..d7299afa902c 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -536,6 +536,43 @@ static int qede_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) return 0; } +int qede_setup_tc(struct net_device *ndev, u8 num_tc) +{ + struct qede_dev *edev = netdev_priv(ndev); + int cos, count, offset; + + if (num_tc > edev->dev_info.num_tc) + return -EINVAL; + + netdev_reset_tc(ndev); + netdev_set_num_tc(ndev, num_tc); + + for_each_cos_in_txq(edev, cos) { + count = QEDE_TSS_COUNT(edev); + offset = cos * QEDE_TSS_COUNT(edev); + netdev_set_tc_queue(ndev, cos, count, offset); + } + + return 0; +} + +static int +qede_setup_tc_offload(struct net_device *dev, enum tc_setup_type type, + void *type_data) +{ + struct tc_mqprio_qopt *mqprio; + + switch (type) { + case TC_SETUP_QDISC_MQPRIO: + mqprio = type_data; + + mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + return qede_setup_tc(dev, mqprio->num_tc); + default: + return -EOPNOTSUPP; + } +} + static const struct net_device_ops qede_netdev_ops = { .ndo_open = qede_open, .ndo_stop = qede_close, @@ -568,6 +605,7 @@ static const struct net_device_ops qede_netdev_ops = { #ifdef CONFIG_RFS_ACCEL .ndo_rx_flow_steer = qede_rx_flow_steer, #endif + .ndo_setup_tc = qede_setup_tc_offload, }; static const struct net_device_ops qede_netdev_vf_ops = { @@ -621,7 +659,8 @@ static struct qede_dev *qede_alloc_etherdev(struct qed_dev *cdev, struct qede_dev *edev; ndev = alloc_etherdev_mqs(sizeof(*edev), - info->num_queues, info->num_queues); + info->num_queues * info->num_tc, + info->num_queues); if (!ndev) { pr_err("etherdev allocation failed\n"); return NULL; @@ -830,7 +869,8 @@ static int qede_alloc_fp_array(struct qede_dev *edev) } if (fp->type & QEDE_FASTPATH_TX) { - fp->txq = kzalloc(sizeof(*fp->txq), GFP_KERNEL); + fp->txq = kcalloc(edev->dev_info.num_tc, + sizeof(*fp->txq), GFP_KERNEL); if (!fp->txq) goto err; } @@ -879,10 +919,15 @@ static void qede_sp_task(struct work_struct *work) static void qede_update_pf_params(struct qed_dev *cdev) { struct qed_pf_params pf_params; + u16 num_cons; /* 64 rx + 64 tx + 64 XDP */ memset(&pf_params, 0, sizeof(struct qed_pf_params)); - pf_params.eth_pf_params.num_cons = (MAX_SB_PER_PF_MIMD - 1) * 3; + + /* 1 rx + 1 xdp + max tx cos */ + num_cons = QED_MIN_L2_CONS; + + pf_params.eth_pf_params.num_cons = (MAX_SB_PER_PF_MIMD - 1) * num_cons; /* Same for VFs - make sure they'll have sufficient connections * to support XDP Tx queues. @@ -1363,8 +1408,12 @@ static void qede_free_mem_fp(struct qede_dev *edev, struct qede_fastpath *fp) if (fp->type & QEDE_FASTPATH_XDP) qede_free_mem_txq(edev, fp->xdp_tx); - if (fp->type & QEDE_FASTPATH_TX) - qede_free_mem_txq(edev, fp->txq); + if (fp->type & QEDE_FASTPATH_TX) { + int cos; + + for_each_cos_in_txq(edev, cos) + qede_free_mem_txq(edev, &fp->txq[cos]); + } } /* This function allocates all memory needed for a single fp (i.e. an entity @@ -1391,9 +1440,13 @@ static int qede_alloc_mem_fp(struct qede_dev *edev, struct qede_fastpath *fp) } if (fp->type & QEDE_FASTPATH_TX) { - rc = qede_alloc_mem_txq(edev, fp->txq); - if (rc) - goto out; + int cos; + + for_each_cos_in_txq(edev, cos) { + rc = qede_alloc_mem_txq(edev, &fp->txq[cos]); + if (rc) + goto out; + } } out: @@ -1466,10 +1519,23 @@ static void qede_init_fp(struct qede_dev *edev) } if (fp->type & QEDE_FASTPATH_TX) { - fp->txq->index = txq_index++; - if (edev->dev_info.is_legacy) - fp->txq->is_legacy = 1; - fp->txq->dev = &edev->pdev->dev; + int cos; + + for_each_cos_in_txq(edev, cos) { + struct qede_tx_queue *txq = &fp->txq[cos]; + u16 ndev_tx_id; + + txq->cos = cos; + txq->index = txq_index; + ndev_tx_id = QEDE_TXQ_TO_NDEV_TXQ_ID(edev, txq); + txq->ndev_txq_id = ndev_tx_id; + + if (edev->dev_info.is_legacy) + txq->is_legacy = 1; + txq->dev = &edev->pdev->dev; + } + + txq_index++; } snprintf(fp->name, sizeof(fp->name), "%s-fp-%d", @@ -1483,7 +1549,9 @@ static int qede_set_real_num_queues(struct qede_dev *edev) { int rc = 0; - rc = netif_set_real_num_tx_queues(edev->ndev, QEDE_TSS_COUNT(edev)); + rc = netif_set_real_num_tx_queues(edev->ndev, + QEDE_TSS_COUNT(edev) * + edev->dev_info.num_tc); if (rc) { DP_NOTICE(edev, "Failed to set real number of Tx queues\n"); return rc; @@ -1685,9 +1753,13 @@ static int qede_stop_queues(struct qede_dev *edev) fp = &edev->fp_array[i]; if (fp->type & QEDE_FASTPATH_TX) { - rc = qede_drain_txq(edev, fp->txq, true); - if (rc) - return rc; + int cos; + + for_each_cos_in_txq(edev, cos) { + rc = qede_drain_txq(edev, &fp->txq[cos], true); + if (rc) + return rc; + } } if (fp->type & QEDE_FASTPATH_XDP) { @@ -1703,9 +1775,13 @@ static int qede_stop_queues(struct qede_dev *edev) /* Stop the Tx Queue(s) */ if (fp->type & QEDE_FASTPATH_TX) { - rc = qede_stop_txq(edev, fp->txq, i); - if (rc) - return rc; + int cos; + + for_each_cos_in_txq(edev, cos) { + rc = qede_stop_txq(edev, &fp->txq[cos], i); + if (rc) + return rc; + } } /* Stop the Rx Queue */ @@ -1758,6 +1834,7 @@ static int qede_start_txq(struct qede_dev *edev, params.p_sb = fp->sb_info; params.sb_idx = sb_idx; + params.tc = txq->cos; rc = edev->ops->q_tx_start(edev->cdev, rss_id, ¶ms, phys_table, page_cnt, &ret_params); @@ -1877,9 +1954,14 @@ static int qede_start_queues(struct qede_dev *edev, bool clear_stats) } if (fp->type & QEDE_FASTPATH_TX) { - rc = qede_start_txq(edev, fp, fp->txq, i, TX_PI(0)); - if (rc) - goto out; + int cos; + + for_each_cos_in_txq(edev, cos) { + rc = qede_start_txq(edev, fp, &fp->txq[cos], i, + TX_PI(cos)); + if (rc) + goto out; + } } } @@ -1973,6 +2055,7 @@ static int qede_load(struct qede_dev *edev, enum qede_load_mode mode, bool is_locked) { struct qed_link_params link_params; + u8 num_tc; int rc; DP_INFO(edev, "Starting qede load\n"); @@ -2019,6 +2102,10 @@ static int qede_load(struct qede_dev *edev, enum qede_load_mode mode, goto err4; DP_INFO(edev, "Start VPORT, RXQ and TXQ succeeded\n"); + num_tc = netdev_get_num_tc(edev->ndev); + num_tc = num_tc ? num_tc : edev->dev_info.num_tc; + qede_setup_tc(edev->ndev, num_tc); + /* Program un-configured VLANs */ qede_configure_vlan_filters(edev); @@ -2143,7 +2230,7 @@ static bool qede_is_txq_full(struct qede_dev *edev, struct qede_tx_queue *txq) { struct netdev_queue *netdev_txq; - netdev_txq = netdev_get_tx_queue(edev->ndev, txq->index); + netdev_txq = netdev_get_tx_queue(edev->ndev, txq->ndev_txq_id); if (netif_xmit_stopped(netdev_txq)) return true; @@ -2208,9 +2295,11 @@ static void qede_get_eth_tlv_data(void *dev, void *data) for_each_queue(i) { fp = &edev->fp_array[i]; if (fp->type & QEDE_FASTPATH_TX) { - if (fp->txq->sw_tx_cons != fp->txq->sw_tx_prod) + struct qede_tx_queue *txq = QEDE_FP_TC0_TXQ(fp); + + if (txq->sw_tx_cons != txq->sw_tx_prod) etlv->txqs_empty = false; - if (qede_is_txq_full(edev, fp->txq)) + if (qede_is_txq_full(edev, txq)) etlv->num_txqs_full++; } if (fp->type & QEDE_FASTPATH_RX) { diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h index 2978fa4add42..a1310482c4ed 100644 --- a/include/linux/qed/qed_eth_if.h +++ b/include/linux/qed/qed_eth_if.h @@ -39,6 +39,10 @@ #include #include +/* 64 max queues * (1 rx + 4 tx-cos + 1 xdp) */ +#define QED_MIN_L2_CONS (2 + NUM_PHYS_TCS_4PORT_K2) +#define QED_MAX_L2_CONS (64 * (QED_MIN_L2_CONS)) + struct qed_queue_start_common_params { /* Should always be relative to entity sending this. */ u8 vport_id; @@ -49,6 +53,8 @@ struct qed_queue_start_common_params { struct qed_sb_info *p_sb; u8 sb_idx; + + u8 tc; }; struct qed_rxq_start_ret_params { -- cgit v1.2.3 From 15693fd37fc3a49da356164ed15b571c175efc34 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Wed, 8 Aug 2018 19:40:31 +0800 Subject: net: skbuff.h: fix using plain integer as NULL warning Fixes the following sparse warning: ./include/linux/skbuff.h:2365:58: warning: Using plain integer as NULL pointer Signed-off-by: YueHaibing Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 7ebdf158a795..7e237a63a70c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2362,7 +2362,7 @@ static inline void skb_probe_transport_header(struct sk_buff *skb, if (skb_transport_header_was_set(skb)) return; - if (skb_flow_dissect_flow_keys_basic(skb, &keys, 0, 0, 0, 0, 0)) + if (skb_flow_dissect_flow_keys_basic(skb, &keys, NULL, 0, 0, 0, 0)) skb_set_transport_header(skb, keys.control.thoff); else skb_set_transport_header(skb, offset_hint); -- cgit v1.2.3 From bd2e9567db72e37f7f4b90faa5133bc7365b5f65 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Thu, 9 Aug 2018 16:19:52 -0500 Subject: PCI: Hide ACS quirk declarations inside PCI core Move declarations for these functions: pci_dev_specific_acs_enabled() pci_dev_specific_enable_acs() from include/linux/pci.h to drivers/pci/pci.h because nothing outside the PCI core needs to use them. Signed-off-by: Bjorn Helgaas --- drivers/pci/pci.h | 14 ++++++++++++++ include/linux/pci.h | 11 ----------- 2 files changed, 14 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index c358e7a07f3f..a1224fef3409 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -352,6 +352,20 @@ static inline resource_size_t pci_resource_alignment(struct pci_dev *dev, } void pci_enable_acs(struct pci_dev *dev); +#ifdef CONFIG_PCI_QUIRKS +int pci_dev_specific_acs_enabled(struct pci_dev *dev, u16 acs_flags); +int pci_dev_specific_enable_acs(struct pci_dev *dev); +#else +static inline int pci_dev_specific_acs_enabled(struct pci_dev *dev, + u16 acs_flags) +{ + return -ENOTTY; +} +static inline int pci_dev_specific_enable_acs(struct pci_dev *dev) +{ + return -ENOTTY; +} +#endif /* PCI error reporting and recovery */ void pcie_do_fatal_recovery(struct pci_dev *dev, u32 service); diff --git a/include/linux/pci.h b/include/linux/pci.h index 340029b2fb38..1e1ed049dd1c 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1876,20 +1876,9 @@ enum pci_fixup_pass { #ifdef CONFIG_PCI_QUIRKS void pci_fixup_device(enum pci_fixup_pass pass, struct pci_dev *dev); -int pci_dev_specific_acs_enabled(struct pci_dev *dev, u16 acs_flags); -int pci_dev_specific_enable_acs(struct pci_dev *dev); #else static inline void pci_fixup_device(enum pci_fixup_pass pass, struct pci_dev *dev) { } -static inline int pci_dev_specific_acs_enabled(struct pci_dev *dev, - u16 acs_flags) -{ - return -ENOTTY; -} -static inline int pci_dev_specific_enable_acs(struct pci_dev *dev) -{ - return -ENOTTY; -} #endif void __iomem *pcim_iomap(struct pci_dev *pdev, int bar, unsigned long maxlen); -- cgit v1.2.3 From b0768a86585d4d951a30ff565f19598dbbd67897 Mon Sep 17 00:00:00 2001 From: Toshiaki Makita Date: Fri, 3 Aug 2018 16:58:09 +0900 Subject: net: Export skb_headers_offset_update This is needed for veth XDP which does skb_copy_expand()-like operation. v2: - Drop skb_copy_header part because it has already been exported now. Signed-off-by: Toshiaki Makita Signed-off-by: Daniel Borkmann --- include/linux/skbuff.h | 1 + net/core/skbuff.c | 3 ++- 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 7ebdf158a795..e93b157f526c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1038,6 +1038,7 @@ static inline struct sk_buff *alloc_skb_fclone(unsigned int size, } struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src); +void skb_headers_offset_update(struct sk_buff *skb, int off); int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask); struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t priority); void skb_copy_header(struct sk_buff *new, const struct sk_buff *old); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 8d574a88125d..c996c09d095f 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1291,7 +1291,7 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask) } EXPORT_SYMBOL(skb_clone); -static void skb_headers_offset_update(struct sk_buff *skb, int off) +void skb_headers_offset_update(struct sk_buff *skb, int off) { /* Only adjust this if it actually is csum_start rather than csum */ if (skb->ip_summed == CHECKSUM_PARTIAL) @@ -1305,6 +1305,7 @@ static void skb_headers_offset_update(struct sk_buff *skb, int off) skb->inner_network_header += off; skb->inner_mac_header += off; } +EXPORT_SYMBOL(skb_headers_offset_update); void skb_copy_header(struct sk_buff *new, const struct sk_buff *old) { -- cgit v1.2.3 From a8d5b4ab353738e16e5f9d21ab1e3d44b37983d0 Mon Sep 17 00:00:00 2001 From: Toshiaki Makita Date: Fri, 3 Aug 2018 16:58:12 +0900 Subject: xdp: Helper function to clear kernel pointers in xdp_frame xdp_frame has kernel pointers which should not be readable from bpf programs. When we want to reuse xdp_frame region but it may be read by bpf programs later, we can use this helper to clear kernel pointers. This is more efficient than calling memset() for the entire struct. Signed-off-by: Toshiaki Makita Acked-by: Jesper Dangaard Brouer Signed-off-by: Daniel Borkmann --- include/net/xdp.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/net/xdp.h b/include/net/xdp.h index fcb033f51d8c..76b95256c266 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -84,6 +84,13 @@ struct xdp_frame { struct net_device *dev_rx; /* used by cpumap */ }; +/* Clear kernel pointers in xdp_frame */ +static inline void xdp_scrub_frame(struct xdp_frame *frame) +{ + frame->data = NULL; + frame->dev_rx = NULL; +} + /* Convert xdp_buff to xdp_frame */ static inline struct xdp_frame *convert_to_xdp_frame(struct xdp_buff *xdp) -- cgit v1.2.3 From 0b19cc0a8694d4295383f88bc3441765875a57bc Mon Sep 17 00:00:00 2001 From: Toshiaki Makita Date: Fri, 3 Aug 2018 16:58:15 +0900 Subject: bpf: Make redirect_info accessible from modules We are going to add kern_flags field in redirect_info for kernel internal use. In order to avoid function call to access the flags, make redirect_info accessible from modules. Also as it is now non-static, add prefix bpf_ to redirect_info. v6: - Fix sparse warning around EXPORT_SYMBOL. Signed-off-by: Toshiaki Makita Signed-off-by: Daniel Borkmann --- include/linux/filter.h | 10 ++++++++++ net/core/filter.c | 29 +++++++++++------------------ 2 files changed, 21 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index c73dd7396886..4717af8b95e6 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -537,6 +537,16 @@ struct sk_msg_buff { struct list_head list; }; +struct bpf_redirect_info { + u32 ifindex; + u32 flags; + struct bpf_map *map; + struct bpf_map *map_to_flush; + unsigned long map_owner; +}; + +DECLARE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info); + /* Compute the linear packet data range [data, data_end) which * will be accessed by various program types (cls_bpf, act_bpf, * lwt, ...). Subsystems allowing direct data access must (!) diff --git a/net/core/filter.c b/net/core/filter.c index 587bbfbd7db3..2de7dd9f2a57 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2082,19 +2082,12 @@ static const struct bpf_func_proto bpf_clone_redirect_proto = { .arg3_type = ARG_ANYTHING, }; -struct redirect_info { - u32 ifindex; - u32 flags; - struct bpf_map *map; - struct bpf_map *map_to_flush; - unsigned long map_owner; -}; - -static DEFINE_PER_CPU(struct redirect_info, redirect_info); +DEFINE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info); +EXPORT_PER_CPU_SYMBOL_GPL(bpf_redirect_info); BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags) { - struct redirect_info *ri = this_cpu_ptr(&redirect_info); + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); if (unlikely(flags & ~(BPF_F_INGRESS))) return TC_ACT_SHOT; @@ -2107,7 +2100,7 @@ BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags) int skb_do_redirect(struct sk_buff *skb) { - struct redirect_info *ri = this_cpu_ptr(&redirect_info); + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); struct net_device *dev; dev = dev_get_by_index_rcu(dev_net(skb->dev), ri->ifindex); @@ -3200,7 +3193,7 @@ static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd, void xdp_do_flush_map(void) { - struct redirect_info *ri = this_cpu_ptr(&redirect_info); + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); struct bpf_map *map = ri->map_to_flush; ri->map_to_flush = NULL; @@ -3245,7 +3238,7 @@ static inline bool xdp_map_invalid(const struct bpf_prog *xdp_prog, static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { - struct redirect_info *ri = this_cpu_ptr(&redirect_info); + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); unsigned long map_owner = ri->map_owner; struct bpf_map *map = ri->map; u32 index = ri->ifindex; @@ -3285,7 +3278,7 @@ err: int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { - struct redirect_info *ri = this_cpu_ptr(&redirect_info); + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); struct net_device *fwd; u32 index = ri->ifindex; int err; @@ -3317,7 +3310,7 @@ static int xdp_do_generic_redirect_map(struct net_device *dev, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { - struct redirect_info *ri = this_cpu_ptr(&redirect_info); + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); unsigned long map_owner = ri->map_owner; struct bpf_map *map = ri->map; u32 index = ri->ifindex; @@ -3368,7 +3361,7 @@ err: int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { - struct redirect_info *ri = this_cpu_ptr(&redirect_info); + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); u32 index = ri->ifindex; struct net_device *fwd; int err = 0; @@ -3399,7 +3392,7 @@ EXPORT_SYMBOL_GPL(xdp_do_generic_redirect); BPF_CALL_2(bpf_xdp_redirect, u32, ifindex, u64, flags) { - struct redirect_info *ri = this_cpu_ptr(&redirect_info); + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); if (unlikely(flags)) return XDP_ABORTED; @@ -3423,7 +3416,7 @@ static const struct bpf_func_proto bpf_xdp_redirect_proto = { BPF_CALL_4(bpf_xdp_redirect_map, struct bpf_map *, map, u32, ifindex, u64, flags, unsigned long, map_owner) { - struct redirect_info *ri = this_cpu_ptr(&redirect_info); + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); if (unlikely(flags)) return XDP_ABORTED; -- cgit v1.2.3 From 2539650fadbf63a431e76535a9de7bff6ea5e409 Mon Sep 17 00:00:00 2001 From: Toshiaki Makita Date: Fri, 3 Aug 2018 16:58:16 +0900 Subject: xdp: Helpers for disabling napi_direct of xdp_return_frame We need some mechanism to disable napi_direct on calling xdp_return_frame_rx_napi() from some context. When veth gets support of XDP_REDIRECT, it will redirects packets which are redirected from other devices. On redirection veth will reuse xdp_mem_info of the redirection source device to make return_frame work. But in this case .ndo_xdp_xmit() called from veth redirection uses xdp_mem_info which is not guarded by NAPI, because the .ndo_xdp_xmit() is not called directly from the rxq which owns the xdp_mem_info. This approach introduces a flag in bpf_redirect_info to indicate that napi_direct should be disabled even when _rx_napi variant is used as well as helper functions to use it. A NAPI handler who wants to use this flag needs to call xdp_set_return_frame_no_direct() before processing packets, and call xdp_clear_return_frame_no_direct() after xdp_do_flush_map() before exiting NAPI. v4: - Use bpf_redirect_info for storing the flag instead of xdp_mem_info to avoid per-frame copy cost. Signed-off-by: Toshiaki Makita Signed-off-by: Daniel Borkmann --- include/linux/filter.h | 25 +++++++++++++++++++++++++ net/core/xdp.c | 6 ++++-- 2 files changed, 29 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index 4717af8b95e6..2b072dab32c0 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -543,10 +543,14 @@ struct bpf_redirect_info { struct bpf_map *map; struct bpf_map *map_to_flush; unsigned long map_owner; + u32 kern_flags; }; DECLARE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info); +/* flags for bpf_redirect_info kern_flags */ +#define BPF_RI_F_RF_NO_DIRECT BIT(0) /* no napi_direct on return_frame */ + /* Compute the linear packet data range [data, data_end) which * will be accessed by various program types (cls_bpf, act_bpf, * lwt, ...). Subsystems allowing direct data access must (!) @@ -775,6 +779,27 @@ static inline bool bpf_dump_raw_ok(void) struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len); +static inline bool xdp_return_frame_no_direct(void) +{ + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + + return ri->kern_flags & BPF_RI_F_RF_NO_DIRECT; +} + +static inline void xdp_set_return_frame_no_direct(void) +{ + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + + ri->kern_flags |= BPF_RI_F_RF_NO_DIRECT; +} + +static inline void xdp_clear_return_frame_no_direct(void) +{ + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + + ri->kern_flags &= ~BPF_RI_F_RF_NO_DIRECT; +} + static inline int xdp_ok_fwd_dev(const struct net_device *fwd, unsigned int pktlen) { diff --git a/net/core/xdp.c b/net/core/xdp.c index 57285383ed00..3dd99e1c04f5 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -330,10 +330,12 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct, /* mem->id is valid, checked in xdp_rxq_info_reg_mem_model() */ xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params); page = virt_to_head_page(data); - if (xa) + if (xa) { + napi_direct &= !xdp_return_frame_no_direct(); page_pool_put_page(xa->page_pool, page, napi_direct); - else + } else { put_page(page); + } rcu_read_unlock(); break; case MEM_TYPE_PAGE_SHARED: -- cgit v1.2.3 From aa12af77aae05008b3e637b85944dcd512f75eba Mon Sep 17 00:00:00 2001 From: Ankit Navik Date: Tue, 7 Aug 2018 13:16:35 +0530 Subject: Bluetooth: Add definitions for LE set address resolution Add the definitions for LE address resolution enable HCI commands. When the LE address resolution enable gets changed via HCI commands make sure that flag gets updated. Signed-off-by: Ankit Navik Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci.h | 3 +++ net/bluetooth/hci_event.c | 28 ++++++++++++++++++++++++++++ 2 files changed, 31 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 4619a79b1bbb..cdd9f1fe7cfa 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -269,6 +269,7 @@ enum { HCI_VENDOR_DIAG, HCI_FORCE_BREDR_SMP, HCI_FORCE_STATIC_ADDR, + HCI_LL_RPA_RESOLUTION, __HCI_NUM_FLAGS, }; @@ -1524,6 +1525,8 @@ struct hci_rp_le_read_resolv_list_size { __u8 size; } __packed; +#define HCI_OP_LE_SET_ADDR_RESOLV_ENABLE 0x202d + #define HCI_OP_LE_READ_MAX_DATA_LEN 0x202f struct hci_rp_le_read_max_data_len { __u8 status; diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 8078587572fe..f12555f23a49 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -1480,6 +1480,30 @@ static void hci_cc_le_read_resolv_list_size(struct hci_dev *hdev, hdev->le_resolv_list_size = rp->size; } +static void hci_cc_le_set_addr_resolution_enable(struct hci_dev *hdev, + struct sk_buff *skb) +{ + __u8 *sent, status = *((__u8 *) skb->data); + + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + if (status) + return; + + sent = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_ADDR_RESOLV_ENABLE); + if (!sent) + return; + + hci_dev_lock(hdev); + + if (*sent) + hci_dev_set_flag(hdev, HCI_LL_RPA_RESOLUTION); + else + hci_dev_clear_flag(hdev, HCI_LL_RPA_RESOLUTION); + + hci_dev_unlock(hdev); +} + static void hci_cc_le_read_max_data_len(struct hci_dev *hdev, struct sk_buff *skb) { @@ -3263,6 +3287,10 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb, hci_cc_le_read_resolv_list_size(hdev, skb); break; + case HCI_OP_LE_SET_ADDR_RESOLV_ENABLE: + hci_cc_le_set_addr_resolution_enable(hdev, skb); + break; + case HCI_OP_LE_READ_MAX_DATA_LEN: hci_cc_le_read_max_data_len(hdev, skb); break; -- cgit v1.2.3 From 0db021f7a2731cc559f0c5beb19ff3f677ff8626 Mon Sep 17 00:00:00 2001 From: David Collins Date: Fri, 13 Jul 2018 18:50:58 -0700 Subject: regulator: dt-bindings: add QCOM RPMh regulator bindings Introduce bindings for RPMh regulator devices found on some Qualcomm Technlogies, Inc. SoCs. These devices allow a given processor within the SoC to make PMIC regulator requests which are aggregated within the RPMh hardware block along with requests from other processors in the SoC to determine the final PMIC regulator hardware state. Signed-off-by: David Collins Reviewed-by: Rob Herring Reviewed-by: Douglas Anderson Signed-off-by: Mark Brown --- .../bindings/regulator/qcom,rpmh-regulator.txt | 160 +++++++++++++++++++++ .../dt-bindings/regulator/qcom,rpmh-regulator.h | 36 +++++ 2 files changed, 196 insertions(+) create mode 100644 Documentation/devicetree/bindings/regulator/qcom,rpmh-regulator.txt create mode 100644 include/dt-bindings/regulator/qcom,rpmh-regulator.h (limited to 'include') diff --git a/Documentation/devicetree/bindings/regulator/qcom,rpmh-regulator.txt b/Documentation/devicetree/bindings/regulator/qcom,rpmh-regulator.txt new file mode 100644 index 000000000000..7ef2dbe48e8a --- /dev/null +++ b/Documentation/devicetree/bindings/regulator/qcom,rpmh-regulator.txt @@ -0,0 +1,160 @@ +Qualcomm Technologies, Inc. RPMh Regulators + +rpmh-regulator devices support PMIC regulator management via the Voltage +Regulator Manager (VRM) and Oscillator Buffer (XOB) RPMh accelerators. The APPS +processor communicates with these hardware blocks via a Resource State +Coordinator (RSC) using command packets. The VRM allows changing three +parameters for a given regulator: enable state, output voltage, and operating +mode. The XOB allows changing only a single parameter for a given regulator: +its enable state. Despite its name, the XOB is capable of controlling the +enable state of any PMIC peripheral. It is used for clock buffers, low-voltage +switches, and LDO/SMPS regulators which have a fixed voltage and mode. + +======================= +Required Node Structure +======================= + +RPMh regulators must be described in two levels of device nodes. The first +level describes the PMIC containing the regulators and must reside within an +RPMh device node. The second level describes each regulator within the PMIC +which is to be used on the board. Each of these regulators maps to a single +RPMh resource. + +The names used for regulator nodes must match those supported by a given PMIC. +Supported regulator node names: + PM8998: smps1 - smps13, ldo1 - ldo28, lvs1 - lvs2 + PMI8998: bob + PM8005: smps1 - smps4 + +======================== +First Level Nodes - PMIC +======================== + +- compatible + Usage: required + Value type: + Definition: Must be one of: "qcom,pm8998-rpmh-regulators", + "qcom,pmi8998-rpmh-regulators" or + "qcom,pm8005-rpmh-regulators". + +- qcom,pmic-id + Usage: required + Value type: + Definition: RPMh resource name suffix used for the regulators found on + this PMIC. Typical values: "a", "b", "c", "d", "e", "f". + +- vdd-s1-supply +- vdd-s2-supply +- vdd-s3-supply +- vdd-s4-supply + Usage: optional (PM8998 and PM8005 only) + Value type: + Definition: phandle of the parent supply regulator of one or more of the + regulators for this PMIC. + +- vdd-s5-supply +- vdd-s6-supply +- vdd-s7-supply +- vdd-s8-supply +- vdd-s9-supply +- vdd-s10-supply +- vdd-s11-supply +- vdd-s12-supply +- vdd-s13-supply +- vdd-l1-l27-supply +- vdd-l2-l8-l17-supply +- vdd-l3-l11-supply +- vdd-l4-l5-supply +- vdd-l6-supply +- vdd-l7-l12-l14-l15-supply +- vdd-l9-supply +- vdd-l10-l23-l25-supply +- vdd-l13-l19-l21-supply +- vdd-l16-l28-supply +- vdd-l18-l22-supply +- vdd-l20-l24-supply +- vdd-l26-supply +- vin-lvs-1-2-supply + Usage: optional (PM8998 only) + Value type: + Definition: phandle of the parent supply regulator of one or more of the + regulators for this PMIC. + +- vdd-bob-supply + Usage: optional (PMI8998 only) + Value type: + Definition: BOB regulator parent supply phandle + +=============================== +Second Level Nodes - Regulators +=============================== + +- qcom,always-wait-for-ack + Usage: optional + Value type: + Definition: Boolean flag which indicates that the application processor + must wait for an ACK or a NACK from RPMh for every request + sent for this regulator including those which are for a + strictly lower power state. + +Other properties defined in Documentation/devicetree/bindings/regulator.txt +may also be used. regulator-initial-mode and regulator-allowed-modes may be +specified for VRM regulators using mode values from +include/dt-bindings/regulator/qcom,rpmh-regulator.h. regulator-allow-bypass +may be specified for BOB type regulators managed via VRM. +regulator-allow-set-load may be specified for LDO type regulators managed via +VRM. + +======== +Examples +======== + +#include + +&apps_rsc { + pm8998-rpmh-regulators { + compatible = "qcom,pm8998-rpmh-regulators"; + qcom,pmic-id = "a"; + + vdd-l7-l12-l14-l15-supply = <&pm8998_s5>; + + smps2 { + regulator-min-microvolt = <1100000>; + regulator-max-microvolt = <1100000>; + }; + + pm8998_s5: smps5 { + regulator-min-microvolt = <1904000>; + regulator-max-microvolt = <2040000>; + }; + + ldo7 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + regulator-allowed-modes = + ; + regulator-allow-set-load; + }; + + lvs1 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + }; + }; + + pmi8998-rpmh-regulators { + compatible = "qcom,pmi8998-rpmh-regulators"; + qcom,pmic-id = "b"; + + bob { + regulator-min-microvolt = <3312000>; + regulator-max-microvolt = <3600000>; + regulator-allowed-modes = + ; + regulator-initial-mode = ; + }; + }; +}; diff --git a/include/dt-bindings/regulator/qcom,rpmh-regulator.h b/include/dt-bindings/regulator/qcom,rpmh-regulator.h new file mode 100644 index 000000000000..86713dcf9e02 --- /dev/null +++ b/include/dt-bindings/regulator/qcom,rpmh-regulator.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018, The Linux Foundation. All rights reserved. */ + +#ifndef __QCOM_RPMH_REGULATOR_H +#define __QCOM_RPMH_REGULATOR_H + +/* + * These mode constants may be used to specify modes for various RPMh regulator + * device tree properties (e.g. regulator-initial-mode). Each type of regulator + * supports a subset of the possible modes. + * + * %RPMH_REGULATOR_MODE_RET: Retention mode in which only an extremely small + * load current is allowed. This mode is supported + * by LDO and SMPS type regulators. + * %RPMH_REGULATOR_MODE_LPM: Low power mode in which a small load current is + * allowed. This mode corresponds to PFM for SMPS + * and BOB type regulators. This mode is supported + * by LDO, HFSMPS, BOB, and PMIC4 FTSMPS type + * regulators. + * %RPMH_REGULATOR_MODE_AUTO: Auto mode in which the regulator hardware + * automatically switches between LPM and HPM based + * upon the real-time load current. This mode is + * supported by HFSMPS, BOB, and PMIC4 FTSMPS type + * regulators. + * %RPMH_REGULATOR_MODE_HPM: High power mode in which the full rated current + * of the regulator is allowed. This mode + * corresponds to PWM for SMPS and BOB type + * regulators. This mode is supported by all types + * of regulators. + */ +#define RPMH_REGULATOR_MODE_RET 0 +#define RPMH_REGULATOR_MODE_LPM 1 +#define RPMH_REGULATOR_MODE_AUTO 2 +#define RPMH_REGULATOR_MODE_HPM 3 + +#endif -- cgit v1.2.3 From c9fbb2d25295a566b97d62e6904741e8e1702d83 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 10 Aug 2018 10:47:43 +0200 Subject: net: Provide stub for __netif_set_xps_queue if there is no CONFIG_XPS MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Building virtio_net driver without CONFIG_XPS fails with: drivers/net/virtio_net.c: In function ‘virtnet_set_affinity’: drivers/net/virtio_net.c:1910:3: error: implicit declaration of function ‘__netif_set_xps_queue’ [-Werror=implicit-function-declaration] __netif_set_xps_queue(vi->dev, mask, i, false); ^ Fixes: 4d99f6602cb5 ("net: allow to call netif_reset_xps_queues() under cpus_read_lock") Signed-off-by: Krzysztof Kozlowski Signed-off-by: David S. Miller --- include/linux/netdevice.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 282e2e95ad5b..ca5ab98053c8 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3412,6 +3412,13 @@ static inline int netif_set_xps_queue(struct net_device *dev, { return 0; } + +static inline int __netif_set_xps_queue(struct net_device *dev, + const unsigned long *mask, + u16 index, bool is_rxqs_map) +{ + return 0; +} #endif /** -- cgit v1.2.3 From d799a4de0a250f1bdd99765bb8e55a5e2f469a1f Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 3 Aug 2018 00:52:18 +0200 Subject: gpio: mmio: Fix up inverted direction registers The bgpio_init() takes one of two arguments to specify a register to set the direction of the GPIO line: either dirout that indicates that a 1 in the bit in that register sets the corresponding line to output, or dirin which indicates that a 1 in the bit in that register sets the corresponding line to input. Conversely setting the bit to 0 on these will turn the line into input and output respectively. One of these can be defined but not both. This means that a platform that sets a bit to 1 for output only defines dirout and a platform that sets a bit to 0 for output only defines dirin. In short this defines the polarity of the direction register. Both can also be left as NULL meaning the GPIO chip is either input only or output only. Tomer Maimon discovered that for get/set chips (those where the get and set registers are defined but no separate clear register, and specifying BGPIOF_READ_OUTPUT_REG_SET so that we say we want to read the output value from the SET register) we are unconditionally reading the value from the SET register when the direction bit is 1 and from the DAT register when the direction bit is 0, not taking the direction bit polarity into account. It would be expected that when the direction bit is inverted (dirin is defined but not dirout) we read the current value from the DAT register when the bit is 1 and from the SET register when the bit is 0. Currently only some versions of ATH79, brcmstb, some versions of CLP711x, GE, IOP and Loongson use the dirin mode (a 1 in the register means input). They are unaffected because BGPIOF_READ_OUTPUT_REG_SET is not set on any of them. (They do not read back the SET register to figure out the output value.) So this is no regression with current drivers. However the behaviour is wrong and does not work with Tomer's new driver where he needs to use the BGIOF_READ_OUTPUT_REG_SET. This fixes the above issue by: - Instead of defining separate functions for the inverted case, set up a flag in the gpio_chip that indicates that the direction is inverted. - Remove the special inverted functions for setting input/output and getting the direction, rely on the flag instead. - Respect this flag in bgpio_get_set() and bgpio_get_set_multiple() Reported-by: Tomer Maimon Signed-off-by: Linus Walleij --- drivers/gpio/gpio-mmio.c | 108 ++++++++++++++++++++++++++------------------ include/linux/gpio/driver.h | 3 ++ 2 files changed, 66 insertions(+), 45 deletions(-) (limited to 'include') diff --git a/drivers/gpio/gpio-mmio.c b/drivers/gpio/gpio-mmio.c index 7b14d6280e44..935292a30c99 100644 --- a/drivers/gpio/gpio-mmio.c +++ b/drivers/gpio/gpio-mmio.c @@ -136,8 +136,20 @@ static unsigned long bgpio_line2mask(struct gpio_chip *gc, unsigned int line) static int bgpio_get_set(struct gpio_chip *gc, unsigned int gpio) { unsigned long pinmask = bgpio_line2mask(gc, gpio); + bool dir = !!(gc->bgpio_dir & pinmask); - if (gc->bgpio_dir & pinmask) + /* + * If the direction is OUT we read the value from the SET + * register, and if the direction is IN we read the value + * from the DAT register. + * + * If the direction bits are inverted, naturally this gets + * inverted too. + */ + if (gc->bgpio_dir_inverted) + dir = !dir; + + if (dir) return !!(gc->read_reg(gc->reg_set) & pinmask); else return !!(gc->read_reg(gc->reg_dat) & pinmask); @@ -157,8 +169,13 @@ static int bgpio_get_set_multiple(struct gpio_chip *gc, unsigned long *mask, *bits &= ~*mask; /* Exploit the fact that we know which directions are set */ - set_mask = *mask & gc->bgpio_dir; - get_mask = *mask & ~gc->bgpio_dir; + if (gc->bgpio_dir_inverted) { + set_mask = *mask & ~gc->bgpio_dir; + get_mask = *mask & gc->bgpio_dir; + } else { + set_mask = *mask & gc->bgpio_dir; + get_mask = *mask & ~gc->bgpio_dir; + } if (set_mask) *bits |= gc->read_reg(gc->reg_set) & set_mask; @@ -359,7 +376,10 @@ static int bgpio_dir_in(struct gpio_chip *gc, unsigned int gpio) spin_lock_irqsave(&gc->bgpio_lock, flags); - gc->bgpio_dir &= ~bgpio_line2mask(gc, gpio); + if (gc->bgpio_dir_inverted) + gc->bgpio_dir |= bgpio_line2mask(gc, gpio); + else + gc->bgpio_dir &= ~bgpio_line2mask(gc, gpio); gc->write_reg(gc->reg_dir, gc->bgpio_dir); spin_unlock_irqrestore(&gc->bgpio_lock, flags); @@ -370,7 +390,10 @@ static int bgpio_dir_in(struct gpio_chip *gc, unsigned int gpio) static int bgpio_get_dir(struct gpio_chip *gc, unsigned int gpio) { /* Return 0 if output, 1 of input */ - return !(gc->read_reg(gc->reg_dir) & bgpio_line2mask(gc, gpio)); + if (gc->bgpio_dir_inverted) + return !!(gc->read_reg(gc->reg_dir) & bgpio_line2mask(gc, gpio)); + else + return !(gc->read_reg(gc->reg_dir) & bgpio_line2mask(gc, gpio)); } static int bgpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val) @@ -381,37 +404,10 @@ static int bgpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val) spin_lock_irqsave(&gc->bgpio_lock, flags); - gc->bgpio_dir |= bgpio_line2mask(gc, gpio); - gc->write_reg(gc->reg_dir, gc->bgpio_dir); - - spin_unlock_irqrestore(&gc->bgpio_lock, flags); - - return 0; -} - -static int bgpio_dir_in_inv(struct gpio_chip *gc, unsigned int gpio) -{ - unsigned long flags; - - spin_lock_irqsave(&gc->bgpio_lock, flags); - - gc->bgpio_dir |= bgpio_line2mask(gc, gpio); - gc->write_reg(gc->reg_dir, gc->bgpio_dir); - - spin_unlock_irqrestore(&gc->bgpio_lock, flags); - - return 0; -} - -static int bgpio_dir_out_inv(struct gpio_chip *gc, unsigned int gpio, int val) -{ - unsigned long flags; - - gc->set(gc, gpio, val); - - spin_lock_irqsave(&gc->bgpio_lock, flags); - - gc->bgpio_dir &= ~bgpio_line2mask(gc, gpio); + if (gc->bgpio_dir_inverted) + gc->bgpio_dir &= ~bgpio_line2mask(gc, gpio); + else + gc->bgpio_dir |= bgpio_line2mask(gc, gpio); gc->write_reg(gc->reg_dir, gc->bgpio_dir); spin_unlock_irqrestore(&gc->bgpio_lock, flags); @@ -419,12 +415,6 @@ static int bgpio_dir_out_inv(struct gpio_chip *gc, unsigned int gpio, int val) return 0; } -static int bgpio_get_dir_inv(struct gpio_chip *gc, unsigned int gpio) -{ - /* Return 0 if output, 1 if input */ - return !!(gc->read_reg(gc->reg_dir) & bgpio_line2mask(gc, gpio)); -} - static int bgpio_setup_accessors(struct device *dev, struct gpio_chip *gc, bool byte_be) @@ -560,9 +550,10 @@ static int bgpio_setup_direction(struct gpio_chip *gc, gc->get_direction = bgpio_get_dir; } else if (dirin) { gc->reg_dir = dirin; - gc->direction_output = bgpio_dir_out_inv; - gc->direction_input = bgpio_dir_in_inv; - gc->get_direction = bgpio_get_dir_inv; + gc->direction_output = bgpio_dir_out; + gc->direction_input = bgpio_dir_in; + gc->get_direction = bgpio_get_dir; + gc->bgpio_dir_inverted = true; } else { if (flags & BGPIOF_NO_OUTPUT) gc->direction_output = bgpio_dir_out_err; @@ -582,6 +573,33 @@ static int bgpio_request(struct gpio_chip *chip, unsigned gpio_pin) return -EINVAL; } +/** + * bgpio_init() - Initialize generic GPIO accessor functions + * @gc: the GPIO chip to set up + * @dev: the parent device of the new GPIO chip (compulsory) + * @sz: the size (width) of the MMIO registers in bytes, typically 1, 2 or 4 + * @dat: MMIO address for the register to READ the value of the GPIO lines, it + * is expected that a 1 in the corresponding bit in this register means the + * line is asserted + * @set: MMIO address for the register to SET the value of the GPIO lines, it is + * expected that we write the line with 1 in this register to drive the GPIO line + * high. + * @clr: MMIO address for the register to CLEAR the value of the GPIO lines, it is + * expected that we write the line with 1 in this register to drive the GPIO line + * low. It is allowed to leave this address as NULL, in that case the SET register + * will be assumed to also clear the GPIO lines, by actively writing the line + * with 0. + * @dirout: MMIO address for the register to set the line as OUTPUT. It is assumed + * that setting a line to 1 in this register will turn that line into an + * output line. Conversely, setting the line to 0 will turn that line into + * an input. Either this or @dirin can be defined, but never both. + * @dirin: MMIO address for the register to set this line as INPUT. It is assumed + * that setting a line to 1 in this register will turn that line into an + * input line. Conversely, setting the line to 0 will turn that line into + * an output. Either this or @dirout can be defined, but never both. + * @flags: Different flags that will affect the behaviour of the device, such as + * endianness etc. + */ int bgpio_init(struct gpio_chip *gc, struct device *dev, unsigned long sz, void __iomem *dat, void __iomem *set, void __iomem *clr, void __iomem *dirout, void __iomem *dirin, diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 5382b5183b7e..0ea328e71ec9 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -201,6 +201,8 @@ static inline struct gpio_irq_chip *to_gpio_irq_chip(struct irq_chip *chip) * @reg_set: output set register (out=high) for generic GPIO * @reg_clr: output clear register (out=low) for generic GPIO * @reg_dir: direction setting register for generic GPIO + * @bgpio_dir_inverted: indicates that the direction register is inverted + * (gpiolib private state variable) * @bgpio_bits: number of register bits used for a generic GPIO i.e. * * 8 * @bgpio_lock: used to lock chip->bgpio_data. Also, this is needed to keep @@ -267,6 +269,7 @@ struct gpio_chip { void __iomem *reg_set; void __iomem *reg_clr; void __iomem *reg_dir; + bool bgpio_dir_inverted; int bgpio_bits; spinlock_t bgpio_lock; unsigned long bgpio_data; -- cgit v1.2.3 From 40a1227ea845a37ab197dd1caffb60b047fa36b1 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 8 Aug 2018 01:01:21 -0700 Subject: tcp: Avoid TCP syncookie rejected by SO_REUSEPORT socket Although the actual cookie check "__cookie_v[46]_check()" does not involve sk specific info, it checks whether the sk has recent synq overflow event in "tcp_synq_no_recent_overflow()". The tcp_sk(sk)->rx_opt.ts_recent_stamp is updated every second when it has sent out a syncookie (through "tcp_synq_overflow()"). The above per sk "recent synq overflow event timestamp" works well for non SO_REUSEPORT use case. However, it may cause random connection request reject/discard when SO_REUSEPORT is used with syncookie because it fails the "tcp_synq_no_recent_overflow()" test. When SO_REUSEPORT is used, it usually has multiple listening socks serving TCP connection requests destinated to the same local IP:PORT. There are cases that the TCP-ACK-COOKIE may not be received by the same sk that sent out the syncookie. For example, if reuse->socks[] began with {sk0, sk1}, 1) sk1 sent out syncookies and tcp_sk(sk1)->rx_opt.ts_recent_stamp was updated. 2) the reuse->socks[] became {sk1, sk2} later. e.g. sk0 was first closed and then sk2 was added. Here, sk2 does not have ts_recent_stamp set. There are other ordering that will trigger the similar situation below but the idea is the same. 3) When the TCP-ACK-COOKIE comes back, sk2 was selected. "tcp_synq_no_recent_overflow(sk2)" returns true. In this case, all syncookies sent by sk1 will be handled (and rejected) by sk2 while sk1 is still alive. The userspace may create and remove listening SO_REUSEPORT sockets as it sees fit. E.g. Adding new thread (and SO_REUSEPORT sock) to handle incoming requests, old process stopping and new process starting...etc. With or without SO_ATTACH_REUSEPORT_[CB]BPF, the sockets leaving and joining a reuseport group makes picking the same sk to check the syncookie very difficult (if not impossible). The later patches will allow bpf prog more flexibility in deciding where a sk should be located in a bpf map and selecting a particular SO_REUSEPORT sock as it sees fit. e.g. Without closing any sock, replace the whole bpf reuseport_array in one map_update() by using map-in-map. Getting the syncookie check working smoothly across socks in the same "reuse->socks[]" is important. A partial solution is to set the newly added sk's ts_recent_stamp to the max ts_recent_stamp of a reuseport group but that will require to iterate through reuse->socks[] OR pessimistically set it to "now - TCP_SYNCOOKIE_VALID" when a sk is joining a reuseport group. However, neither of them will solve the existing sk getting moved around the reuse->socks[] and that sk may not have ts_recent_stamp updated, unlikely under continuous synflood but not impossible. This patch opts to treat the reuseport group as a whole when considering the last synq overflow timestamp since they are serving the same IP:PORT from the userspace (and BPF program) perspective. "synq_overflow_ts" is added to "struct sock_reuseport". The tcp_synq_overflow() and tcp_synq_no_recent_overflow() will update/check reuse->synq_overflow_ts if the sk is in a reuseport group. Similar to the reuseport decision in __inet_lookup_listener(), both sk->sk_reuseport and sk->sk_reuseport_cb are tested for SO_REUSEPORT usage. Update on "synq_overflow_ts" happens at roughly once every second. A synflood test was done with a 16 rx-queues and 16 reuseport sockets. No meaningful performance change is observed. Before and after the change is ~9Mpps in IPv4. Cc: Eric Dumazet Signed-off-by: Martin KaFai Lau Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/net/sock_reuseport.h | 4 ++++ include/net/tcp.h | 30 ++++++++++++++++++++++++++++-- net/core/sock_reuseport.c | 1 + 3 files changed, 33 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/sock_reuseport.h b/include/net/sock_reuseport.h index 0054b3a9b923..6bef7a0052f2 100644 --- a/include/net/sock_reuseport.h +++ b/include/net/sock_reuseport.h @@ -12,6 +12,10 @@ struct sock_reuseport { u16 max_socks; /* length of socks */ u16 num_socks; /* elements in socks */ + /* The last synq overflow event timestamp of this + * reuse->socks[] group. + */ + unsigned int synq_overflow_ts; struct bpf_prog __rcu *prog; /* optional BPF sock selector */ struct sock *socks[0]; /* array of sock pointers */ }; diff --git a/include/net/tcp.h b/include/net/tcp.h index d769dc20359b..d196901c9dba 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -36,6 +36,7 @@ #include #include #include +#include #include #include #include @@ -473,9 +474,22 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb); */ static inline void tcp_synq_overflow(const struct sock *sk) { - unsigned int last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp; + unsigned int last_overflow; unsigned int now = jiffies; + if (sk->sk_reuseport) { + struct sock_reuseport *reuse; + + reuse = rcu_dereference(sk->sk_reuseport_cb); + if (likely(reuse)) { + last_overflow = READ_ONCE(reuse->synq_overflow_ts); + if (time_after32(now, last_overflow + HZ)) + WRITE_ONCE(reuse->synq_overflow_ts, now); + return; + } + } + + last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp; if (time_after32(now, last_overflow + HZ)) tcp_sk(sk)->rx_opt.ts_recent_stamp = now; } @@ -483,9 +497,21 @@ static inline void tcp_synq_overflow(const struct sock *sk) /* syncookies: no recent synqueue overflow on this listening socket? */ static inline bool tcp_synq_no_recent_overflow(const struct sock *sk) { - unsigned int last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp; + unsigned int last_overflow; unsigned int now = jiffies; + if (sk->sk_reuseport) { + struct sock_reuseport *reuse; + + reuse = rcu_dereference(sk->sk_reuseport_cb); + if (likely(reuse)) { + last_overflow = READ_ONCE(reuse->synq_overflow_ts); + return time_after32(now, last_overflow + + TCP_SYNCOOKIE_VALID); + } + } + + last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp; return time_after32(now, last_overflow + TCP_SYNCOOKIE_VALID); } diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c index 064acb04be0f..3f188fad0162 100644 --- a/net/core/sock_reuseport.c +++ b/net/core/sock_reuseport.c @@ -81,6 +81,7 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse) memcpy(more_reuse->socks, reuse->socks, reuse->num_socks * sizeof(struct sock *)); + more_reuse->synq_overflow_ts = READ_ONCE(reuse->synq_overflow_ts); for (i = 0; i < reuse->num_socks; ++i) rcu_assign_pointer(reuse->socks[i]->sk_reuseport_cb, -- cgit v1.2.3 From 736b46027eb4a4c602d3b8b93d2f48c9facbd915 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 8 Aug 2018 01:01:22 -0700 Subject: net: Add ID (if needed) to sock_reuseport and expose reuseport_lock A later patch will introduce a BPF_MAP_TYPE_REUSEPORT_ARRAY which allows a SO_REUSEPORT sk to be added to a bpf map. When a sk is removed from reuse->socks[], it also needs to be removed from the bpf map. Also, when adding a sk to a bpf map, the bpf map needs to ensure it is indeed in a reuse->socks[]. Hence, reuseport_lock is needed by the bpf map to ensure its map_update_elem() and map_delete_elem() operations are in-sync with the reuse->socks[]. The BPF_MAP_TYPE_REUSEPORT_ARRAY map will only acquire the reuseport_lock after ensuring the adding sk is already in a reuseport group (i.e. reuse->socks[]). The map_lookup_elem() will be lockless. This patch also adds an ID to sock_reuseport. A later patch will introduce BPF_PROG_TYPE_SK_REUSEPORT which allows a bpf prog to select a sk from a bpf map. It is inflexible to statically enforce a bpf map can only contain the sk belonging to a particular reuse->socks[] (i.e. same IP:PORT) during the bpf verification time. For example, think about the the map-in-map situation where the inner map can be dynamically changed in runtime and the outer map may have inner maps belonging to different reuseport groups. Hence, when the bpf prog (in the new BPF_PROG_TYPE_SK_REUSEPORT type) selects a sk, this selected sk has to be checked to ensure it belongs to the requesting reuseport group (i.e. the group serving that IP:PORT). The "sk->sk_reuseport_cb" pointer cannot be used for this checking purpose because the pointer value will change after reuseport_grow(). Instead of saving all checking conditions like the ones preced calling "reuseport_add_sock()" and compare them everytime a bpf_prog is run, a 32bits ID is introduced to survive the reuseport_grow(). The ID is only acquired if any of the reuse->socks[] is added to the newly introduced "BPF_MAP_TYPE_REUSEPORT_ARRAY" map. If "BPF_MAP_TYPE_REUSEPORT_ARRAY" is not used, the changes in this patch is a no-op. Signed-off-by: Martin KaFai Lau Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/net/sock_reuseport.h | 6 ++++++ net/core/sock_reuseport.c | 27 ++++++++++++++++++++++++++- 2 files changed, 32 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/sock_reuseport.h b/include/net/sock_reuseport.h index 6bef7a0052f2..e1a7681856f7 100644 --- a/include/net/sock_reuseport.h +++ b/include/net/sock_reuseport.h @@ -5,8 +5,11 @@ #include #include #include +#include #include +extern spinlock_t reuseport_lock; + struct sock_reuseport { struct rcu_head rcu; @@ -16,6 +19,8 @@ struct sock_reuseport { * reuse->socks[] group. */ unsigned int synq_overflow_ts; + /* ID stays the same even after the size of socks[] grows. */ + unsigned int reuseport_id; struct bpf_prog __rcu *prog; /* optional BPF sock selector */ struct sock *socks[0]; /* array of sock pointers */ }; @@ -29,5 +34,6 @@ extern struct sock *reuseport_select_sock(struct sock *sk, int hdr_len); extern struct bpf_prog *reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog); +int reuseport_get_id(struct sock_reuseport *reuse); #endif /* _SOCK_REUSEPORT_H */ diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c index 3f188fad0162..cf2e4d305af9 100644 --- a/net/core/sock_reuseport.c +++ b/net/core/sock_reuseport.c @@ -8,11 +8,33 @@ #include #include +#include #include #define INIT_SOCKS 128 -static DEFINE_SPINLOCK(reuseport_lock); +DEFINE_SPINLOCK(reuseport_lock); + +#define REUSEPORT_MIN_ID 1 +static DEFINE_IDA(reuseport_ida); + +int reuseport_get_id(struct sock_reuseport *reuse) +{ + int id; + + if (reuse->reuseport_id) + return reuse->reuseport_id; + + id = ida_simple_get(&reuseport_ida, REUSEPORT_MIN_ID, 0, + /* Called under reuseport_lock */ + GFP_ATOMIC); + if (id < 0) + return id; + + reuse->reuseport_id = id; + + return reuse->reuseport_id; +} static struct sock_reuseport *__reuseport_alloc(unsigned int max_socks) { @@ -78,6 +100,7 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse) more_reuse->max_socks = more_socks_size; more_reuse->num_socks = reuse->num_socks; more_reuse->prog = reuse->prog; + more_reuse->reuseport_id = reuse->reuseport_id; memcpy(more_reuse->socks, reuse->socks, reuse->num_socks * sizeof(struct sock *)); @@ -102,6 +125,8 @@ static void reuseport_free_rcu(struct rcu_head *head) reuse = container_of(head, struct sock_reuseport, rcu); if (reuse->prog) bpf_prog_destroy(reuse->prog); + if (reuse->reuseport_id) + ida_simple_remove(&reuseport_ida, reuse->reuseport_id); kfree(reuse); } -- cgit v1.2.3 From 5dc4c4b7d4e8115e7cde96a030f98cb3ab2e458c Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 8 Aug 2018 01:01:24 -0700 Subject: bpf: Introduce BPF_MAP_TYPE_REUSEPORT_SOCKARRAY This patch introduces a new map type BPF_MAP_TYPE_REUSEPORT_SOCKARRAY. To unleash the full potential of a bpf prog, it is essential for the userspace to be capable of directly setting up a bpf map which can then be consumed by the bpf prog to make decision. In this case, decide which SO_REUSEPORT sk to serve the incoming request. By adding BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, the userspace has total control and visibility on where a SO_REUSEPORT sk should be located in a bpf map. The later patch will introduce BPF_PROG_TYPE_SK_REUSEPORT such that the bpf prog can directly select a sk from the bpf map. That will raise the programmability of the bpf prog attached to a reuseport group (a group of sk serving the same IP:PORT). For example, in UDP, the bpf prog can peek into the payload (e.g. through the "data" pointer introduced in the later patch) to learn the application level's connection information and then decide which sk to pick from a bpf map. The userspace can tightly couple the sk's location in a bpf map with the application logic in generating the UDP payload's connection information. This connection info contact/API stays within the userspace. Also, when used with map-in-map, the userspace can switch the old-server-process's inner map to a new-server-process's inner map in one call "bpf_map_update_elem(outer_map, &index, &new_reuseport_array)". The bpf prog will then direct incoming requests to the new process instead of the old process. The old process can finish draining the pending requests (e.g. by "accept()") before closing the old-fds. [Note that deleting a fd from a bpf map does not necessary mean the fd is closed] During map_update_elem(), Only SO_REUSEPORT sk (i.e. which has already been added to a reuse->socks[]) can be used. That means a SO_REUSEPORT sk that is "bind()" for UDP or "bind()+listen()" for TCP. These conditions are ensured in "reuseport_array_update_check()". A SO_REUSEPORT sk can only be added once to a map (i.e. the same sk cannot be added twice even to the same map). SO_REUSEPORT already allows another sk to be created for the same IP:PORT. There is no need to re-create a similar usage in the BPF side. When a SO_REUSEPORT is deleted from the "reuse->socks[]" (e.g. "close()"), it will notify the bpf map to remove it from the map also. It is done through "bpf_sk_reuseport_detach()" and it will only be called if >=1 of the "reuse->sock[]" has ever been added to a bpf map. The map_update()/map_delete() has to be in-sync with the "reuse->socks[]". Hence, the same "reuseport_lock" used by "reuse->socks[]" has to be used here also. Care has been taken to ensure the lock is only acquired when the adding sk passes some strict tests. and freeing the map does not require the reuseport_lock. The reuseport_array will also support lookup from the syscall side. It will return a sock_gen_cookie(). The sock_gen_cookie() is on-demand (i.e. a sk's cookie is not generated until the very first map_lookup_elem()). The lookup cookie is 64bits but it goes against the logical userspace expectation on 32bits sizeof(fd) (and as other fd based bpf maps do also). It may catch user in surprise if we enforce value_size=8 while userspace still pass a 32bits fd during update. Supporting different value_size between lookup and update seems unintuitive also. We also need to consider what if other existing fd based maps want to return 64bits value from syscall's lookup in the future. Hence, reuseport_array supports both value_size 4 and 8, and assuming user will usually use value_size=4. The syscall's lookup will return ENOSPC on value_size=4. It will will only return 64bits value from sock_gen_cookie() when user consciously choose value_size=8 (as a signal that lookup is desired) which then requires a 64bits value in both lookup and update. Signed-off-by: Martin KaFai Lau Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 28 ++++ include/linux/bpf_types.h | 3 + include/uapi/linux/bpf.h | 1 + kernel/bpf/Makefile | 3 + kernel/bpf/arraymap.c | 2 +- kernel/bpf/reuseport_array.c | 363 +++++++++++++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 6 + net/core/sock_reuseport.c | 8 + 8 files changed, 413 insertions(+), 1 deletion(-) create mode 100644 kernel/bpf/reuseport_array.c (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index cd8790d2c6ed..db11662faea6 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -524,6 +524,7 @@ static inline int bpf_map_attr_numa_node(const union bpf_attr *attr) } struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type); +int array_map_alloc_check(union bpf_attr *attr); #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) @@ -769,6 +770,33 @@ static inline void __xsk_map_flush(struct bpf_map *map) } #endif +#if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) +void bpf_sk_reuseport_detach(struct sock *sk); +int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key, + void *value); +int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key, + void *value, u64 map_flags); +#else +static inline void bpf_sk_reuseport_detach(struct sock *sk) +{ +} + +#ifdef CONFIG_BPF_SYSCALL +static inline int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, + void *key, void *value) +{ + return -EOPNOTSUPP; +} + +static inline int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, + void *key, void *value, + u64 map_flags) +{ + return -EOPNOTSUPP; +} +#endif /* CONFIG_BPF_SYSCALL */ +#endif /* defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) */ + /* verifier prototypes for helper functions called from eBPF programs */ extern const struct bpf_func_proto bpf_map_lookup_elem_proto; extern const struct bpf_func_proto bpf_map_update_elem_proto; diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index add08be53b6f..14fd6c02d258 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -60,4 +60,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops) #if defined(CONFIG_XDP_SOCKETS) BPF_MAP_TYPE(BPF_MAP_TYPE_XSKMAP, xsk_map_ops) #endif +#ifdef CONFIG_INET +BPF_MAP_TYPE(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, reuseport_array_ops) +#endif #endif diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index dd5758dc35d3..40f584bc7da0 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -126,6 +126,7 @@ enum bpf_map_type { BPF_MAP_TYPE_XSKMAP, BPF_MAP_TYPE_SOCKHASH, BPF_MAP_TYPE_CGROUP_STORAGE, + BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, }; enum bpf_prog_type { diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index e8906cbad81f..0488b8258321 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -23,3 +23,6 @@ ifeq ($(CONFIG_PERF_EVENTS),y) obj-$(CONFIG_BPF_SYSCALL) += stackmap.o endif obj-$(CONFIG_CGROUP_BPF) += cgroup.o +ifeq ($(CONFIG_INET),y) +obj-$(CONFIG_BPF_SYSCALL) += reuseport_array.o +endif diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 2aa55d030c77..f6ca3e712831 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -54,7 +54,7 @@ static int bpf_array_alloc_percpu(struct bpf_array *array) } /* Called from syscall */ -static int array_map_alloc_check(union bpf_attr *attr) +int array_map_alloc_check(union bpf_attr *attr) { bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY; int numa_node = bpf_map_attr_numa_node(attr); diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c new file mode 100644 index 000000000000..18e225de80ff --- /dev/null +++ b/kernel/bpf/reuseport_array.c @@ -0,0 +1,363 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2018 Facebook + */ +#include +#include +#include +#include + +struct reuseport_array { + struct bpf_map map; + struct sock __rcu *ptrs[]; +}; + +static struct reuseport_array *reuseport_array(struct bpf_map *map) +{ + return (struct reuseport_array *)map; +} + +/* The caller must hold the reuseport_lock */ +void bpf_sk_reuseport_detach(struct sock *sk) +{ + struct sock __rcu **socks; + + write_lock_bh(&sk->sk_callback_lock); + socks = sk->sk_user_data; + if (socks) { + WRITE_ONCE(sk->sk_user_data, NULL); + /* + * Do not move this NULL assignment outside of + * sk->sk_callback_lock because there is + * a race with reuseport_array_free() + * which does not hold the reuseport_lock. + */ + RCU_INIT_POINTER(*socks, NULL); + } + write_unlock_bh(&sk->sk_callback_lock); +} + +static int reuseport_array_alloc_check(union bpf_attr *attr) +{ + if (attr->value_size != sizeof(u32) && + attr->value_size != sizeof(u64)) + return -EINVAL; + + return array_map_alloc_check(attr); +} + +static void *reuseport_array_lookup_elem(struct bpf_map *map, void *key) +{ + struct reuseport_array *array = reuseport_array(map); + u32 index = *(u32 *)key; + + if (unlikely(index >= array->map.max_entries)) + return NULL; + + return rcu_dereference(array->ptrs[index]); +} + +/* Called from syscall only */ +static int reuseport_array_delete_elem(struct bpf_map *map, void *key) +{ + struct reuseport_array *array = reuseport_array(map); + u32 index = *(u32 *)key; + struct sock *sk; + int err; + + if (index >= map->max_entries) + return -E2BIG; + + if (!rcu_access_pointer(array->ptrs[index])) + return -ENOENT; + + spin_lock_bh(&reuseport_lock); + + sk = rcu_dereference_protected(array->ptrs[index], + lockdep_is_held(&reuseport_lock)); + if (sk) { + write_lock_bh(&sk->sk_callback_lock); + WRITE_ONCE(sk->sk_user_data, NULL); + RCU_INIT_POINTER(array->ptrs[index], NULL); + write_unlock_bh(&sk->sk_callback_lock); + err = 0; + } else { + err = -ENOENT; + } + + spin_unlock_bh(&reuseport_lock); + + return err; +} + +static void reuseport_array_free(struct bpf_map *map) +{ + struct reuseport_array *array = reuseport_array(map); + struct sock *sk; + u32 i; + + synchronize_rcu(); + + /* + * ops->map_*_elem() will not be able to access this + * array now. Hence, this function only races with + * bpf_sk_reuseport_detach() which was triggerred by + * close() or disconnect(). + * + * This function and bpf_sk_reuseport_detach() are + * both removing sk from "array". Who removes it + * first does not matter. + * + * The only concern here is bpf_sk_reuseport_detach() + * may access "array" which is being freed here. + * bpf_sk_reuseport_detach() access this "array" + * through sk->sk_user_data _and_ with sk->sk_callback_lock + * held which is enough because this "array" is not freed + * until all sk->sk_user_data has stopped referencing this "array". + * + * Hence, due to the above, taking "reuseport_lock" is not + * needed here. + */ + + /* + * Since reuseport_lock is not taken, sk is accessed under + * rcu_read_lock() + */ + rcu_read_lock(); + for (i = 0; i < map->max_entries; i++) { + sk = rcu_dereference(array->ptrs[i]); + if (sk) { + write_lock_bh(&sk->sk_callback_lock); + /* + * No need for WRITE_ONCE(). At this point, + * no one is reading it without taking the + * sk->sk_callback_lock. + */ + sk->sk_user_data = NULL; + write_unlock_bh(&sk->sk_callback_lock); + RCU_INIT_POINTER(array->ptrs[i], NULL); + } + } + rcu_read_unlock(); + + /* + * Once reaching here, all sk->sk_user_data is not + * referenceing this "array". "array" can be freed now. + */ + bpf_map_area_free(array); +} + +static struct bpf_map *reuseport_array_alloc(union bpf_attr *attr) +{ + int err, numa_node = bpf_map_attr_numa_node(attr); + struct reuseport_array *array; + u64 cost, array_size; + + if (!capable(CAP_SYS_ADMIN)) + return ERR_PTR(-EPERM); + + array_size = sizeof(*array); + array_size += (u64)attr->max_entries * sizeof(struct sock *); + + /* make sure there is no u32 overflow later in round_up() */ + cost = array_size; + if (cost >= U32_MAX - PAGE_SIZE) + return ERR_PTR(-ENOMEM); + cost = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; + + err = bpf_map_precharge_memlock(cost); + if (err) + return ERR_PTR(err); + + /* allocate all map elements and zero-initialize them */ + array = bpf_map_area_alloc(array_size, numa_node); + if (!array) + return ERR_PTR(-ENOMEM); + + /* copy mandatory map attributes */ + bpf_map_init_from_attr(&array->map, attr); + array->map.pages = cost; + + return &array->map; +} + +int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key, + void *value) +{ + struct sock *sk; + int err; + + if (map->value_size != sizeof(u64)) + return -ENOSPC; + + rcu_read_lock(); + sk = reuseport_array_lookup_elem(map, key); + if (sk) { + *(u64 *)value = sock_gen_cookie(sk); + err = 0; + } else { + err = -ENOENT; + } + rcu_read_unlock(); + + return err; +} + +static int +reuseport_array_update_check(const struct reuseport_array *array, + const struct sock *nsk, + const struct sock *osk, + const struct sock_reuseport *nsk_reuse, + u32 map_flags) +{ + if (osk && map_flags == BPF_NOEXIST) + return -EEXIST; + + if (!osk && map_flags == BPF_EXIST) + return -ENOENT; + + if (nsk->sk_protocol != IPPROTO_UDP && nsk->sk_protocol != IPPROTO_TCP) + return -ENOTSUPP; + + if (nsk->sk_family != AF_INET && nsk->sk_family != AF_INET6) + return -ENOTSUPP; + + if (nsk->sk_type != SOCK_STREAM && nsk->sk_type != SOCK_DGRAM) + return -ENOTSUPP; + + /* + * sk must be hashed (i.e. listening in the TCP case or binded + * in the UDP case) and + * it must also be a SO_REUSEPORT sk (i.e. reuse cannot be NULL). + * + * Also, sk will be used in bpf helper that is protected by + * rcu_read_lock(). + */ + if (!sock_flag(nsk, SOCK_RCU_FREE) || !sk_hashed(nsk) || !nsk_reuse) + return -EINVAL; + + /* READ_ONCE because the sk->sk_callback_lock may not be held here */ + if (READ_ONCE(nsk->sk_user_data)) + return -EBUSY; + + return 0; +} + +/* + * Called from syscall only. + * The "nsk" in the fd refcnt. + * The "osk" and "reuse" are protected by reuseport_lock. + */ +int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key, + void *value, u64 map_flags) +{ + struct reuseport_array *array = reuseport_array(map); + struct sock *free_osk = NULL, *osk, *nsk; + struct sock_reuseport *reuse; + u32 index = *(u32 *)key; + struct socket *socket; + int err, fd; + + if (map_flags > BPF_EXIST) + return -EINVAL; + + if (index >= map->max_entries) + return -E2BIG; + + if (map->value_size == sizeof(u64)) { + u64 fd64 = *(u64 *)value; + + if (fd64 > S32_MAX) + return -EINVAL; + fd = fd64; + } else { + fd = *(int *)value; + } + + socket = sockfd_lookup(fd, &err); + if (!socket) + return err; + + nsk = socket->sk; + if (!nsk) { + err = -EINVAL; + goto put_file; + } + + /* Quick checks before taking reuseport_lock */ + err = reuseport_array_update_check(array, nsk, + rcu_access_pointer(array->ptrs[index]), + rcu_access_pointer(nsk->sk_reuseport_cb), + map_flags); + if (err) + goto put_file; + + spin_lock_bh(&reuseport_lock); + /* + * Some of the checks only need reuseport_lock + * but it is done under sk_callback_lock also + * for simplicity reason. + */ + write_lock_bh(&nsk->sk_callback_lock); + + osk = rcu_dereference_protected(array->ptrs[index], + lockdep_is_held(&reuseport_lock)); + reuse = rcu_dereference_protected(nsk->sk_reuseport_cb, + lockdep_is_held(&reuseport_lock)); + err = reuseport_array_update_check(array, nsk, osk, reuse, map_flags); + if (err) + goto put_file_unlock; + + /* Ensure reuse->reuseport_id is set */ + err = reuseport_get_id(reuse); + if (err < 0) + goto put_file_unlock; + + WRITE_ONCE(nsk->sk_user_data, &array->ptrs[index]); + rcu_assign_pointer(array->ptrs[index], nsk); + free_osk = osk; + err = 0; + +put_file_unlock: + write_unlock_bh(&nsk->sk_callback_lock); + + if (free_osk) { + write_lock_bh(&free_osk->sk_callback_lock); + WRITE_ONCE(free_osk->sk_user_data, NULL); + write_unlock_bh(&free_osk->sk_callback_lock); + } + + spin_unlock_bh(&reuseport_lock); +put_file: + fput(socket->file); + return err; +} + +/* Called from syscall */ +static int reuseport_array_get_next_key(struct bpf_map *map, void *key, + void *next_key) +{ + struct reuseport_array *array = reuseport_array(map); + u32 index = key ? *(u32 *)key : U32_MAX; + u32 *next = (u32 *)next_key; + + if (index >= array->map.max_entries) { + *next = 0; + return 0; + } + + if (index == array->map.max_entries - 1) + return -ENOENT; + + *next = index + 1; + return 0; +} + +const struct bpf_map_ops reuseport_array_ops = { + .map_alloc_check = reuseport_array_alloc_check, + .map_alloc = reuseport_array_alloc, + .map_free = reuseport_array_free, + .map_lookup_elem = reuseport_array_lookup_elem, + .map_get_next_key = reuseport_array_get_next_key, + .map_delete_elem = reuseport_array_delete_elem, +}; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 5af4e9e2722d..57f4d076141b 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -684,6 +684,8 @@ static int map_lookup_elem(union bpf_attr *attr) err = bpf_fd_array_map_lookup_elem(map, key, value); } else if (IS_FD_HASH(map)) { err = bpf_fd_htab_map_lookup_elem(map, key, value); + } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { + err = bpf_fd_reuseport_array_lookup_elem(map, key, value); } else { rcu_read_lock(); ptr = map->ops->map_lookup_elem(map, key); @@ -790,6 +792,10 @@ static int map_update_elem(union bpf_attr *attr) err = bpf_fd_htab_map_update_elem(map, f.file, key, value, attr->flags); rcu_read_unlock(); + } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { + /* rcu_read_lock() is not needed */ + err = bpf_fd_reuseport_array_update_elem(map, key, value, + attr->flags); } else { rcu_read_lock(); err = map->ops->map_update_elem(map, key, value, attr->flags); diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c index cf2e4d305af9..8235f2439816 100644 --- a/net/core/sock_reuseport.c +++ b/net/core/sock_reuseport.c @@ -186,6 +186,14 @@ void reuseport_detach_sock(struct sock *sk) spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); + + /* At least one of the sk in this reuseport group is added to + * a bpf map. Notify the bpf side. The bpf map logic will + * remove the sk if it is indeed added to a bpf map. + */ + if (reuse->reuseport_id) + bpf_sk_reuseport_detach(sk); + rcu_assign_pointer(sk->sk_reuseport_cb, NULL); for (i = 0; i < reuse->num_socks; i++) { -- cgit v1.2.3 From 2dbb9b9e6df67d444fbe425c7f6014858d337adf Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 8 Aug 2018 01:01:25 -0700 Subject: bpf: Introduce BPF_PROG_TYPE_SK_REUSEPORT This patch adds a BPF_PROG_TYPE_SK_REUSEPORT which can select a SO_REUSEPORT sk from a BPF_MAP_TYPE_REUSEPORT_ARRAY. Like other non SK_FILTER/CGROUP_SKB program, it requires CAP_SYS_ADMIN. BPF_PROG_TYPE_SK_REUSEPORT introduces "struct sk_reuseport_kern" to store the bpf context instead of using the skb->cb[48]. At the SO_REUSEPORT sk lookup time, it is in the middle of transiting from a lower layer (ipv4/ipv6) to a upper layer (udp/tcp). At this point, it is not always clear where the bpf context can be appended in the skb->cb[48] to avoid saving-and-restoring cb[]. Even putting aside the difference between ipv4-vs-ipv6 and udp-vs-tcp. It is not clear if the lower layer is only ipv4 and ipv6 in the future and will it not touch the cb[] again before transiting to the upper layer. For example, in udp_gro_receive(), it uses the 48 byte NAPI_GRO_CB instead of IP[6]CB and it may still modify the cb[] after calling the udp[46]_lib_lookup_skb(). Because of the above reason, if sk->cb is used for the bpf ctx, saving-and-restoring is needed and likely the whole 48 bytes cb[] has to be saved and restored. Instead of saving, setting and restoring the cb[], this patch opts to create a new "struct sk_reuseport_kern" and setting the needed values in there. The new BPF_PROG_TYPE_SK_REUSEPORT and "struct sk_reuseport_(kern|md)" will serve all ipv4/ipv6 + udp/tcp combinations. There is no protocol specific usage at this point and it is also inline with the current sock_reuseport.c implementation (i.e. no protocol specific requirement). In "struct sk_reuseport_md", this patch exposes data/data_end/len with semantic similar to other existing usages. Together with "bpf_skb_load_bytes()" and "bpf_skb_load_bytes_relative()", the bpf prog can peek anywhere in the skb. The "bind_inany" tells the bpf prog that the reuseport group is bind-ed to a local INANY address which cannot be learned from skb. The new "bind_inany" is added to "struct sock_reuseport" which will be used when running the new "BPF_PROG_TYPE_SK_REUSEPORT" bpf prog in order to avoid repeating the "bind INANY" test on "sk_v6_rcv_saddr/sk->sk_rcv_saddr" every time a bpf prog is run. It can only be properly initialized when a "sk->sk_reuseport" enabled sk is adding to a hashtable (i.e. during "reuseport_alloc()" and "reuseport_add_sock()"). The new "sk_select_reuseport()" is the main helper that the bpf prog will use to select a SO_REUSEPORT sk. It is the only function that can use the new BPF_MAP_TYPE_REUSEPORT_ARRAY. As mentioned in the earlier patch, the validity of a selected sk is checked in run time in "sk_select_reuseport()". Doing the check in verification time is difficult and inflexible (consider the map-in-map use case). The runtime check is to compare the selected sk's reuseport_id with the reuseport_id that we want. This helper will return -EXXX if the selected sk cannot serve the incoming request (e.g. reuseport_id not match). The bpf prog can decide if it wants to do SK_DROP as its discretion. When the bpf prog returns SK_PASS, the kernel will check if a valid sk has been selected (i.e. "reuse_kern->selected_sk != NULL"). If it does , it will use the selected sk. If not, the kernel will select one from "reuse->socks[]" (as before this patch). The SK_DROP and SK_PASS handling logic will be in the next patch. Signed-off-by: Martin KaFai Lau Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/bpf_types.h | 3 + include/linux/filter.h | 15 +++ include/net/addrconf.h | 1 + include/net/sock_reuseport.h | 6 +- include/uapi/linux/bpf.h | 36 +++++- kernel/bpf/verifier.c | 9 ++ net/core/filter.c | 269 +++++++++++++++++++++++++++++++++++++++- net/core/sock_reuseport.c | 20 ++- net/ipv4/inet_connection_sock.c | 9 ++ net/ipv4/inet_hashtables.c | 5 +- net/ipv4/udp.c | 5 +- 11 files changed, 365 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 14fd6c02d258..cd26c090e7c0 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -29,6 +29,9 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev) #ifdef CONFIG_BPF_LIRC_MODE2 BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2) #endif +#ifdef CONFIG_INET +BPF_PROG_TYPE(BPF_PROG_TYPE_SK_REUSEPORT, sk_reuseport) +#endif BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_ARRAY, percpu_array_map_ops) diff --git a/include/linux/filter.h b/include/linux/filter.h index 2b072dab32c0..70e9d57677fe 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -32,6 +32,7 @@ struct seccomp_data; struct bpf_prog_aux; struct xdp_rxq_info; struct xdp_buff; +struct sock_reuseport; /* ArgX, context and stack frame pointer register positions. Note, * Arg1, Arg2, Arg3, etc are used as argument mappings of function @@ -833,6 +834,20 @@ void bpf_warn_invalid_xdp_action(u32 act); struct sock *do_sk_redirect_map(struct sk_buff *skb); struct sock *do_msg_redirect_map(struct sk_msg_buff *md); +#ifdef CONFIG_INET +struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, + struct bpf_prog *prog, struct sk_buff *skb, + u32 hash); +#else +static inline struct sock * +bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, + struct bpf_prog *prog, struct sk_buff *skb, + u32 hash) +{ + return NULL; +} +#endif + #ifdef CONFIG_BPF_JIT extern int bpf_jit_enable; extern int bpf_jit_harden; diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 5f43f7a70fe6..6def0351bcc3 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -108,6 +108,7 @@ int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr, u32 banned_flags); bool inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2, bool match_wildcard); +bool inet_rcv_saddr_any(const struct sock *sk); void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr); void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr); diff --git a/include/net/sock_reuseport.h b/include/net/sock_reuseport.h index e1a7681856f7..73b569556be6 100644 --- a/include/net/sock_reuseport.h +++ b/include/net/sock_reuseport.h @@ -21,12 +21,14 @@ struct sock_reuseport { unsigned int synq_overflow_ts; /* ID stays the same even after the size of socks[] grows. */ unsigned int reuseport_id; + bool bind_inany; struct bpf_prog __rcu *prog; /* optional BPF sock selector */ struct sock *socks[0]; /* array of sock pointers */ }; -extern int reuseport_alloc(struct sock *sk); -extern int reuseport_add_sock(struct sock *sk, struct sock *sk2); +extern int reuseport_alloc(struct sock *sk, bool bind_inany); +extern int reuseport_add_sock(struct sock *sk, struct sock *sk2, + bool bind_inany); extern void reuseport_detach_sock(struct sock *sk); extern struct sock *reuseport_select_sock(struct sock *sk, u32 hash, diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 40f584bc7da0..3102a2a23c31 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -151,6 +151,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_PROG_TYPE_LWT_SEG6LOCAL, BPF_PROG_TYPE_LIRC_MODE2, + BPF_PROG_TYPE_SK_REUSEPORT, }; enum bpf_attach_type { @@ -2114,6 +2115,14 @@ union bpf_attr { * the shared data. * Return * Pointer to the local storage area. + * + * int bpf_sk_select_reuseport(struct sk_reuseport_md *reuse, struct bpf_map *map, void *key, u64 flags) + * Description + * Select a SO_REUSEPORT sk from a BPF_MAP_TYPE_REUSEPORT_ARRAY map + * It checks the selected sk is matching the incoming + * request in the skb. + * Return + * 0 on success, or a negative error in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2197,7 +2206,8 @@ union bpf_attr { FN(rc_keydown), \ FN(skb_cgroup_id), \ FN(get_current_cgroup_id), \ - FN(get_local_storage), + FN(get_local_storage), \ + FN(sk_select_reuseport), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -2414,6 +2424,30 @@ struct sk_msg_md { __u32 local_port; /* stored in host byte order */ }; +struct sk_reuseport_md { + /* + * Start of directly accessible data. It begins from + * the tcp/udp header. + */ + void *data; + void *data_end; /* End of directly accessible data */ + /* + * Total length of packet (starting from the tcp/udp header). + * Note that the directly accessible bytes (data_end - data) + * could be less than this "len". Those bytes could be + * indirectly read by a helper "bpf_skb_load_bytes()". + */ + __u32 len; + /* + * Eth protocol in the mac header (network byte order). e.g. + * ETH_P_IP(0x0800) and ETH_P_IPV6(0x86DD) + */ + __u32 eth_protocol; + __u32 ip_protocol; /* IP protocol. e.g. IPPROTO_TCP, IPPROTO_UDP */ + __u32 bind_inany; /* Is sock bound to an INANY address? */ + __u32 hash; /* A hash of the packet 4 tuples */ +}; + #define BPF_TAG_SIZE 8 struct bpf_prog_info { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 587468a9c37d..ca90679a7fe5 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1310,6 +1310,7 @@ static bool may_access_direct_pkt_data(struct bpf_verifier_env *env, case BPF_PROG_TYPE_LWT_IN: case BPF_PROG_TYPE_LWT_OUT: case BPF_PROG_TYPE_LWT_SEG6LOCAL: + case BPF_PROG_TYPE_SK_REUSEPORT: /* dst_input() and dst_output() can't write for now */ if (t == BPF_WRITE) return false; @@ -2166,6 +2167,10 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, func_id != BPF_FUNC_msg_redirect_hash) goto error; break; + case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY: + if (func_id != BPF_FUNC_sk_select_reuseport) + goto error; + break; default: break; } @@ -2217,6 +2222,10 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, if (map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE) goto error; break; + case BPF_FUNC_sk_select_reuseport: + if (map->map_type != BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) + goto error; + break; default: break; } diff --git a/net/core/filter.c b/net/core/filter.c index 2de7dd9f2a57..142595b4e0d1 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1462,7 +1462,7 @@ static int __reuseport_attach_prog(struct bpf_prog *prog, struct sock *sk) return -ENOMEM; if (sk_unhashed(sk) && sk->sk_reuseport) { - err = reuseport_alloc(sk); + err = reuseport_alloc(sk, false); if (err) return err; } else if (!rcu_access_pointer(sk->sk_reuseport_cb)) { @@ -7013,3 +7013,270 @@ out: release_sock(sk); return ret; } + +#ifdef CONFIG_INET +struct sk_reuseport_kern { + struct sk_buff *skb; + struct sock *sk; + struct sock *selected_sk; + void *data_end; + u32 hash; + u32 reuseport_id; + bool bind_inany; +}; + +static void bpf_init_reuseport_kern(struct sk_reuseport_kern *reuse_kern, + struct sock_reuseport *reuse, + struct sock *sk, struct sk_buff *skb, + u32 hash) +{ + reuse_kern->skb = skb; + reuse_kern->sk = sk; + reuse_kern->selected_sk = NULL; + reuse_kern->data_end = skb->data + skb_headlen(skb); + reuse_kern->hash = hash; + reuse_kern->reuseport_id = reuse->reuseport_id; + reuse_kern->bind_inany = reuse->bind_inany; +} + +struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, + struct bpf_prog *prog, struct sk_buff *skb, + u32 hash) +{ + struct sk_reuseport_kern reuse_kern; + enum sk_action action; + + bpf_init_reuseport_kern(&reuse_kern, reuse, sk, skb, hash); + action = BPF_PROG_RUN(prog, &reuse_kern); + + if (action == SK_PASS) + return reuse_kern.selected_sk; + else + return ERR_PTR(-ECONNREFUSED); +} + +BPF_CALL_4(sk_select_reuseport, struct sk_reuseport_kern *, reuse_kern, + struct bpf_map *, map, void *, key, u32, flags) +{ + struct sock_reuseport *reuse; + struct sock *selected_sk; + + selected_sk = map->ops->map_lookup_elem(map, key); + if (!selected_sk) + return -ENOENT; + + reuse = rcu_dereference(selected_sk->sk_reuseport_cb); + if (!reuse) + /* selected_sk is unhashed (e.g. by close()) after the + * above map_lookup_elem(). Treat selected_sk has already + * been removed from the map. + */ + return -ENOENT; + + if (unlikely(reuse->reuseport_id != reuse_kern->reuseport_id)) { + struct sock *sk; + + if (unlikely(!reuse_kern->reuseport_id)) + /* There is a small race between adding the + * sk to the map and setting the + * reuse_kern->reuseport_id. + * Treat it as the sk has not been added to + * the bpf map yet. + */ + return -ENOENT; + + sk = reuse_kern->sk; + if (sk->sk_protocol != selected_sk->sk_protocol) + return -EPROTOTYPE; + else if (sk->sk_family != selected_sk->sk_family) + return -EAFNOSUPPORT; + + /* Catch all. Likely bound to a different sockaddr. */ + return -EBADFD; + } + + reuse_kern->selected_sk = selected_sk; + + return 0; +} + +static const struct bpf_func_proto sk_select_reuseport_proto = { + .func = sk_select_reuseport, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_CONST_MAP_PTR, + .arg3_type = ARG_PTR_TO_MAP_KEY, + .arg4_type = ARG_ANYTHING, +}; + +BPF_CALL_4(sk_reuseport_load_bytes, + const struct sk_reuseport_kern *, reuse_kern, u32, offset, + void *, to, u32, len) +{ + return ____bpf_skb_load_bytes(reuse_kern->skb, offset, to, len); +} + +static const struct bpf_func_proto sk_reuseport_load_bytes_proto = { + .func = sk_reuseport_load_bytes, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_UNINIT_MEM, + .arg4_type = ARG_CONST_SIZE, +}; + +BPF_CALL_5(sk_reuseport_load_bytes_relative, + const struct sk_reuseport_kern *, reuse_kern, u32, offset, + void *, to, u32, len, u32, start_header) +{ + return ____bpf_skb_load_bytes_relative(reuse_kern->skb, offset, to, + len, start_header); +} + +static const struct bpf_func_proto sk_reuseport_load_bytes_relative_proto = { + .func = sk_reuseport_load_bytes_relative, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_UNINIT_MEM, + .arg4_type = ARG_CONST_SIZE, + .arg5_type = ARG_ANYTHING, +}; + +static const struct bpf_func_proto * +sk_reuseport_func_proto(enum bpf_func_id func_id, + const struct bpf_prog *prog) +{ + switch (func_id) { + case BPF_FUNC_sk_select_reuseport: + return &sk_select_reuseport_proto; + case BPF_FUNC_skb_load_bytes: + return &sk_reuseport_load_bytes_proto; + case BPF_FUNC_skb_load_bytes_relative: + return &sk_reuseport_load_bytes_relative_proto; + default: + return bpf_base_func_proto(func_id); + } +} + +static bool +sk_reuseport_is_valid_access(int off, int size, + enum bpf_access_type type, + const struct bpf_prog *prog, + struct bpf_insn_access_aux *info) +{ + const u32 size_default = sizeof(__u32); + + if (off < 0 || off >= sizeof(struct sk_reuseport_md) || + off % size || type != BPF_READ) + return false; + + switch (off) { + case offsetof(struct sk_reuseport_md, data): + info->reg_type = PTR_TO_PACKET; + return size == sizeof(__u64); + + case offsetof(struct sk_reuseport_md, data_end): + info->reg_type = PTR_TO_PACKET_END; + return size == sizeof(__u64); + + case offsetof(struct sk_reuseport_md, hash): + return size == size_default; + + /* Fields that allow narrowing */ + case offsetof(struct sk_reuseport_md, eth_protocol): + if (size < FIELD_SIZEOF(struct sk_buff, protocol)) + return false; + case offsetof(struct sk_reuseport_md, ip_protocol): + case offsetof(struct sk_reuseport_md, bind_inany): + case offsetof(struct sk_reuseport_md, len): + bpf_ctx_record_field_size(info, size_default); + return bpf_ctx_narrow_access_ok(off, size, size_default); + + default: + return false; + } +} + +#define SK_REUSEPORT_LOAD_FIELD(F) ({ \ + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_reuseport_kern, F), \ + si->dst_reg, si->src_reg, \ + bpf_target_off(struct sk_reuseport_kern, F, \ + FIELD_SIZEOF(struct sk_reuseport_kern, F), \ + target_size)); \ + }) + +#define SK_REUSEPORT_LOAD_SKB_FIELD(SKB_FIELD) \ + SOCK_ADDR_LOAD_NESTED_FIELD(struct sk_reuseport_kern, \ + struct sk_buff, \ + skb, \ + SKB_FIELD) + +#define SK_REUSEPORT_LOAD_SK_FIELD_SIZE_OFF(SK_FIELD, BPF_SIZE, EXTRA_OFF) \ + SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF(struct sk_reuseport_kern, \ + struct sock, \ + sk, \ + SK_FIELD, BPF_SIZE, EXTRA_OFF) + +static u32 sk_reuseport_convert_ctx_access(enum bpf_access_type type, + const struct bpf_insn *si, + struct bpf_insn *insn_buf, + struct bpf_prog *prog, + u32 *target_size) +{ + struct bpf_insn *insn = insn_buf; + + switch (si->off) { + case offsetof(struct sk_reuseport_md, data): + SK_REUSEPORT_LOAD_SKB_FIELD(data); + break; + + case offsetof(struct sk_reuseport_md, len): + SK_REUSEPORT_LOAD_SKB_FIELD(len); + break; + + case offsetof(struct sk_reuseport_md, eth_protocol): + SK_REUSEPORT_LOAD_SKB_FIELD(protocol); + break; + + case offsetof(struct sk_reuseport_md, ip_protocol): + BUILD_BUG_ON(hweight_long(SK_FL_PROTO_MASK) != BITS_PER_BYTE); + SK_REUSEPORT_LOAD_SK_FIELD_SIZE_OFF(__sk_flags_offset, + BPF_W, 0); + *insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, SK_FL_PROTO_MASK); + *insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, + SK_FL_PROTO_SHIFT); + /* SK_FL_PROTO_MASK and SK_FL_PROTO_SHIFT are endian + * aware. No further narrowing or masking is needed. + */ + *target_size = 1; + break; + + case offsetof(struct sk_reuseport_md, data_end): + SK_REUSEPORT_LOAD_FIELD(data_end); + break; + + case offsetof(struct sk_reuseport_md, hash): + SK_REUSEPORT_LOAD_FIELD(hash); + break; + + case offsetof(struct sk_reuseport_md, bind_inany): + SK_REUSEPORT_LOAD_FIELD(bind_inany); + break; + } + + return insn - insn_buf; +} + +const struct bpf_verifier_ops sk_reuseport_verifier_ops = { + .get_func_proto = sk_reuseport_func_proto, + .is_valid_access = sk_reuseport_is_valid_access, + .convert_ctx_access = sk_reuseport_convert_ctx_access, +}; + +const struct bpf_prog_ops sk_reuseport_prog_ops = { +}; +#endif /* CONFIG_INET */ diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c index 8235f2439816..d260167f5f77 100644 --- a/net/core/sock_reuseport.c +++ b/net/core/sock_reuseport.c @@ -51,7 +51,7 @@ static struct sock_reuseport *__reuseport_alloc(unsigned int max_socks) return reuse; } -int reuseport_alloc(struct sock *sk) +int reuseport_alloc(struct sock *sk, bool bind_inany) { struct sock_reuseport *reuse; @@ -63,9 +63,17 @@ int reuseport_alloc(struct sock *sk) /* Allocation attempts can occur concurrently via the setsockopt path * and the bind/hash path. Nothing to do when we lose the race. */ - if (rcu_dereference_protected(sk->sk_reuseport_cb, - lockdep_is_held(&reuseport_lock))) + reuse = rcu_dereference_protected(sk->sk_reuseport_cb, + lockdep_is_held(&reuseport_lock)); + if (reuse) { + /* Only set reuse->bind_inany if the bind_inany is true. + * Otherwise, it will overwrite the reuse->bind_inany + * which was set by the bind/hash path. + */ + if (bind_inany) + reuse->bind_inany = bind_inany; goto out; + } reuse = __reuseport_alloc(INIT_SOCKS); if (!reuse) { @@ -75,6 +83,7 @@ int reuseport_alloc(struct sock *sk) reuse->socks[0] = sk; reuse->num_socks = 1; + reuse->bind_inany = bind_inany; rcu_assign_pointer(sk->sk_reuseport_cb, reuse); out: @@ -101,6 +110,7 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse) more_reuse->num_socks = reuse->num_socks; more_reuse->prog = reuse->prog; more_reuse->reuseport_id = reuse->reuseport_id; + more_reuse->bind_inany = reuse->bind_inany; memcpy(more_reuse->socks, reuse->socks, reuse->num_socks * sizeof(struct sock *)); @@ -136,12 +146,12 @@ static void reuseport_free_rcu(struct rcu_head *head) * @sk2: Socket belonging to the existing reuseport group. * May return ENOMEM and not add socket to group under memory pressure. */ -int reuseport_add_sock(struct sock *sk, struct sock *sk2) +int reuseport_add_sock(struct sock *sk, struct sock *sk2, bool bind_inany) { struct sock_reuseport *old_reuse, *reuse; if (!rcu_access_pointer(sk2->sk_reuseport_cb)) { - int err = reuseport_alloc(sk2); + int err = reuseport_alloc(sk2, bind_inany); if (err) return err; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 33a88e045efd..dfd5009f96ef 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -107,6 +107,15 @@ bool inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2, } EXPORT_SYMBOL(inet_rcv_saddr_equal); +bool inet_rcv_saddr_any(const struct sock *sk) +{ +#if IS_ENABLED(CONFIG_IPV6) + if (sk->sk_family == AF_INET6) + return ipv6_addr_any(&sk->sk_v6_rcv_saddr); +#endif + return !sk->sk_rcv_saddr; +} + void inet_get_local_port_range(struct net *net, int *low, int *high) { unsigned int seq; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 3647167c8fa3..370e24463fb7 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -567,10 +567,11 @@ static int inet_reuseport_add_sock(struct sock *sk, inet_csk(sk2)->icsk_bind_hash == tb && sk2->sk_reuseport && uid_eq(uid, sock_i_uid(sk2)) && inet_rcv_saddr_equal(sk, sk2, false)) - return reuseport_add_sock(sk, sk2); + return reuseport_add_sock(sk, sk2, + inet_rcv_saddr_any(sk)); } - return reuseport_alloc(sk); + return reuseport_alloc(sk, inet_rcv_saddr_any(sk)); } int __inet_hash(struct sock *sk, struct sock *osk) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 060e841dde40..038dd7909051 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -221,11 +221,12 @@ static int udp_reuseport_add_sock(struct sock *sk, struct udp_hslot *hslot) (sk2->sk_bound_dev_if == sk->sk_bound_dev_if) && sk2->sk_reuseport && uid_eq(uid, sock_i_uid(sk2)) && inet_rcv_saddr_equal(sk, sk2, false)) { - return reuseport_add_sock(sk, sk2); + return reuseport_add_sock(sk, sk2, + inet_rcv_saddr_any(sk)); } } - return reuseport_alloc(sk); + return reuseport_alloc(sk, inet_rcv_saddr_any(sk)); } /** -- cgit v1.2.3 From 8217ca653ec601246832d562207bc24bdf652d2f Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 8 Aug 2018 01:01:26 -0700 Subject: bpf: Enable BPF_PROG_TYPE_SK_REUSEPORT bpf prog in reuseport selection This patch allows a BPF_PROG_TYPE_SK_REUSEPORT bpf prog to select a SO_REUSEPORT sk from a BPF_MAP_TYPE_REUSEPORT_ARRAY introduced in the earlier patch. "bpf_run_sk_reuseport()" will return -ECONNREFUSED when the BPF_PROG_TYPE_SK_REUSEPORT prog returns SK_DROP. The callers, in inet[6]_hashtable.c and ipv[46]/udp.c, are modified to handle this case and return NULL immediately instead of continuing the sk search from its hashtable. It re-uses the existing SO_ATTACH_REUSEPORT_EBPF setsockopt to attach BPF_PROG_TYPE_SK_REUSEPORT. The "sk_reuseport_attach_bpf()" will check if the attaching bpf prog is in the new SK_REUSEPORT or the existing SOCKET_FILTER type and then check different things accordingly. One level of "__reuseport_attach_prog()" call is removed. The "sk_unhashed() && ..." and "sk->sk_reuseport_cb" tests are pushed back to "reuseport_attach_prog()" in sock_reuseport.c. sock_reuseport.c seems to have more knowledge on those test requirements than filter.c. In "reuseport_attach_prog()", after new_prog is attached to reuse->prog, the old_prog (if any) is also directly freed instead of returning the old_prog to the caller and asking the caller to free. The sysctl_optmem_max check is moved back to the "sk_reuseport_attach_filter()" and "sk_reuseport_attach_bpf()". As of other bpf prog types, the new BPF_PROG_TYPE_SK_REUSEPORT is only bounded by the usual "bpf_prog_charge_memlock()" during load time instead of bounded by both bpf_prog_charge_memlock and sysctl_optmem_max. Signed-off-by: Martin KaFai Lau Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/filter.h | 1 + include/net/sock_reuseport.h | 3 +- net/core/filter.c | 87 ++++++++++++++++++++++++++------------------ net/core/sock_reuseport.c | 36 +++++++++++++----- net/ipv4/inet_hashtables.c | 14 ++++--- net/ipv4/udp.c | 4 ++ net/ipv6/inet6_hashtables.c | 14 ++++--- net/ipv6/udp.c | 4 ++ 8 files changed, 106 insertions(+), 57 deletions(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index 70e9d57677fe..5d565c50bcb2 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -753,6 +753,7 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk); int sk_attach_bpf(u32 ufd, struct sock *sk); int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk); int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk); +void sk_reuseport_prog_free(struct bpf_prog *prog); int sk_detach_filter(struct sock *sk); int sk_get_filter(struct sock *sk, struct sock_filter __user *filter, unsigned int len); diff --git a/include/net/sock_reuseport.h b/include/net/sock_reuseport.h index 73b569556be6..8a5f70c7cdf2 100644 --- a/include/net/sock_reuseport.h +++ b/include/net/sock_reuseport.h @@ -34,8 +34,7 @@ extern struct sock *reuseport_select_sock(struct sock *sk, u32 hash, struct sk_buff *skb, int hdr_len); -extern struct bpf_prog *reuseport_attach_prog(struct sock *sk, - struct bpf_prog *prog); +extern int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog); int reuseport_get_id(struct sock_reuseport *reuse); #endif /* _SOCK_REUSEPORT_H */ diff --git a/net/core/filter.c b/net/core/filter.c index 142595b4e0d1..22906b31d43f 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1453,30 +1453,6 @@ static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk) return 0; } -static int __reuseport_attach_prog(struct bpf_prog *prog, struct sock *sk) -{ - struct bpf_prog *old_prog; - int err; - - if (bpf_prog_size(prog->len) > sysctl_optmem_max) - return -ENOMEM; - - if (sk_unhashed(sk) && sk->sk_reuseport) { - err = reuseport_alloc(sk, false); - if (err) - return err; - } else if (!rcu_access_pointer(sk->sk_reuseport_cb)) { - /* The socket wasn't bound with SO_REUSEPORT */ - return -EINVAL; - } - - old_prog = reuseport_attach_prog(sk, prog); - if (old_prog) - bpf_prog_destroy(old_prog); - - return 0; -} - static struct bpf_prog *__get_filter(struct sock_fprog *fprog, struct sock *sk) { @@ -1550,13 +1526,15 @@ int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk) if (IS_ERR(prog)) return PTR_ERR(prog); - err = __reuseport_attach_prog(prog, sk); - if (err < 0) { + if (bpf_prog_size(prog->len) > sysctl_optmem_max) + err = -ENOMEM; + else + err = reuseport_attach_prog(sk, prog); + + if (err) __bpf_prog_release(prog); - return err; - } - return 0; + return err; } static struct bpf_prog *__get_bpf(u32 ufd, struct sock *sk) @@ -1586,19 +1564,58 @@ int sk_attach_bpf(u32 ufd, struct sock *sk) int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk) { - struct bpf_prog *prog = __get_bpf(ufd, sk); + struct bpf_prog *prog; int err; + if (sock_flag(sk, SOCK_FILTER_LOCKED)) + return -EPERM; + + prog = bpf_prog_get_type(ufd, BPF_PROG_TYPE_SOCKET_FILTER); + if (IS_ERR(prog) && PTR_ERR(prog) == -EINVAL) + prog = bpf_prog_get_type(ufd, BPF_PROG_TYPE_SK_REUSEPORT); if (IS_ERR(prog)) return PTR_ERR(prog); - err = __reuseport_attach_prog(prog, sk); - if (err < 0) { - bpf_prog_put(prog); - return err; + if (prog->type == BPF_PROG_TYPE_SK_REUSEPORT) { + /* Like other non BPF_PROG_TYPE_SOCKET_FILTER + * bpf prog (e.g. sockmap). It depends on the + * limitation imposed by bpf_prog_load(). + * Hence, sysctl_optmem_max is not checked. + */ + if ((sk->sk_type != SOCK_STREAM && + sk->sk_type != SOCK_DGRAM) || + (sk->sk_protocol != IPPROTO_UDP && + sk->sk_protocol != IPPROTO_TCP) || + (sk->sk_family != AF_INET && + sk->sk_family != AF_INET6)) { + err = -ENOTSUPP; + goto err_prog_put; + } + } else { + /* BPF_PROG_TYPE_SOCKET_FILTER */ + if (bpf_prog_size(prog->len) > sysctl_optmem_max) { + err = -ENOMEM; + goto err_prog_put; + } } - return 0; + err = reuseport_attach_prog(sk, prog); +err_prog_put: + if (err) + bpf_prog_put(prog); + + return err; +} + +void sk_reuseport_prog_free(struct bpf_prog *prog) +{ + if (!prog) + return; + + if (prog->type == BPF_PROG_TYPE_SK_REUSEPORT) + bpf_prog_put(prog); + else + bpf_prog_destroy(prog); } struct bpf_scratchpad { diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c index d260167f5f77..ba5cba56f574 100644 --- a/net/core/sock_reuseport.c +++ b/net/core/sock_reuseport.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #define INIT_SOCKS 128 @@ -133,8 +134,7 @@ static void reuseport_free_rcu(struct rcu_head *head) struct sock_reuseport *reuse; reuse = container_of(head, struct sock_reuseport, rcu); - if (reuse->prog) - bpf_prog_destroy(reuse->prog); + sk_reuseport_prog_free(rcu_dereference_protected(reuse->prog, 1)); if (reuse->reuseport_id) ida_simple_remove(&reuseport_ida, reuse->reuseport_id); kfree(reuse); @@ -219,9 +219,9 @@ void reuseport_detach_sock(struct sock *sk) } EXPORT_SYMBOL(reuseport_detach_sock); -static struct sock *run_bpf(struct sock_reuseport *reuse, u16 socks, - struct bpf_prog *prog, struct sk_buff *skb, - int hdr_len) +static struct sock *run_bpf_filter(struct sock_reuseport *reuse, u16 socks, + struct bpf_prog *prog, struct sk_buff *skb, + int hdr_len) { struct sk_buff *nskb = NULL; u32 index; @@ -282,9 +282,15 @@ struct sock *reuseport_select_sock(struct sock *sk, /* paired with smp_wmb() in reuseport_add_sock() */ smp_rmb(); - if (prog && skb) - sk2 = run_bpf(reuse, socks, prog, skb, hdr_len); + if (!prog || !skb) + goto select_by_hash; + + if (prog->type == BPF_PROG_TYPE_SK_REUSEPORT) + sk2 = bpf_run_sk_reuseport(reuse, sk, prog, skb, hash); + else + sk2 = run_bpf_filter(reuse, socks, prog, skb, hdr_len); +select_by_hash: /* no bpf or invalid bpf result: fall back to hash usage */ if (!sk2) sk2 = reuse->socks[reciprocal_scale(hash, socks)]; @@ -296,12 +302,21 @@ out: } EXPORT_SYMBOL(reuseport_select_sock); -struct bpf_prog * -reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog) +int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog) { struct sock_reuseport *reuse; struct bpf_prog *old_prog; + if (sk_unhashed(sk) && sk->sk_reuseport) { + int err = reuseport_alloc(sk, false); + + if (err) + return err; + } else if (!rcu_access_pointer(sk->sk_reuseport_cb)) { + /* The socket wasn't bound with SO_REUSEPORT */ + return -EINVAL; + } + spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); @@ -310,6 +325,7 @@ reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog) rcu_assign_pointer(reuse->prog, prog); spin_unlock_bh(&reuseport_lock); - return old_prog; + sk_reuseport_prog_free(old_prog); + return 0; } EXPORT_SYMBOL(reuseport_attach_prog); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 370e24463fb7..f5c9ef2586de 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -328,7 +328,7 @@ struct sock *__inet_lookup_listener(struct net *net, saddr, sport, daddr, hnum, dif, sdif); if (result) - return result; + goto done; /* Lookup lhash2 with INADDR_ANY */ @@ -337,9 +337,10 @@ struct sock *__inet_lookup_listener(struct net *net, if (ilb2->count > ilb->count) goto port_lookup; - return inet_lhash2_lookup(net, ilb2, skb, doff, - saddr, sport, daddr, hnum, - dif, sdif); + result = inet_lhash2_lookup(net, ilb2, skb, doff, + saddr, sport, daddr, hnum, + dif, sdif); + goto done; port_lookup: sk_for_each_rcu(sk, &ilb->head) { @@ -352,12 +353,15 @@ port_lookup: result = reuseport_select_sock(sk, phash, skb, doff); if (result) - return result; + goto done; } result = sk; hiscore = score; } } +done: + if (unlikely(IS_ERR(result))) + return NULL; return result; } EXPORT_SYMBOL_GPL(__inet_lookup_listener); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 038dd7909051..f4e35b2ff8b8 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -499,6 +499,8 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, daddr, hnum, dif, sdif, exact_dif, hslot2, skb); } + if (unlikely(IS_ERR(result))) + return NULL; return result; } begin: @@ -513,6 +515,8 @@ begin: saddr, sport); result = reuseport_select_sock(sk, hash, skb, sizeof(struct udphdr)); + if (unlikely(IS_ERR(result))) + return NULL; if (result) return result; } diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 595ad408dba0..3d7c7460a0c5 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -191,7 +191,7 @@ struct sock *inet6_lookup_listener(struct net *net, saddr, sport, daddr, hnum, dif, sdif); if (result) - return result; + goto done; /* Lookup lhash2 with in6addr_any */ @@ -200,9 +200,10 @@ struct sock *inet6_lookup_listener(struct net *net, if (ilb2->count > ilb->count) goto port_lookup; - return inet6_lhash2_lookup(net, ilb2, skb, doff, - saddr, sport, daddr, hnum, - dif, sdif); + result = inet6_lhash2_lookup(net, ilb2, skb, doff, + saddr, sport, daddr, hnum, + dif, sdif); + goto done; port_lookup: sk_for_each(sk, &ilb->head) { @@ -214,12 +215,15 @@ port_lookup: result = reuseport_select_sock(sk, phash, skb, doff); if (result) - return result; + goto done; } result = sk; hiscore = score; } } +done: + if (unlikely(IS_ERR(result))) + return NULL; return result; } EXPORT_SYMBOL_GPL(inet6_lookup_listener); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index f6b96956a8ed..83f4c77c79d8 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -235,6 +235,8 @@ struct sock *__udp6_lib_lookup(struct net *net, exact_dif, hslot2, skb); } + if (unlikely(IS_ERR(result))) + return NULL; return result; } begin: @@ -249,6 +251,8 @@ begin: saddr, sport); result = reuseport_select_sock(sk, hash, skb, sizeof(struct udphdr)); + if (unlikely(IS_ERR(result))) + return NULL; if (result) return result; } -- cgit v1.2.3 From 466466dc6c28ca9dc401f10e235b9cde9a7c9162 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Thu, 9 Aug 2018 09:38:09 -0700 Subject: tcp: mandate a one-time immediate ACK Add a new flag to indicate a one-time immediate ACK. This flag is occasionaly set under specific TCP protocol states in addition to the more common quickack mechanism for interactive application. In several cases in the TCP code we want to force an immediate ACK but do not want to call tcp_enter_quickack_mode() because we do not want to forget the icsk_ack.pingpong or icsk_ack.ato state. Signed-off-by: Yuchung Cheng Signed-off-by: Neal Cardwell Signed-off-by: Wei Wang Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 3 ++- net/ipv4/tcp_input.c | 4 +++- 2 files changed, 5 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 0a6c9e0f2b5a..fa43b82607d9 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -167,7 +167,8 @@ enum inet_csk_ack_state_t { ICSK_ACK_SCHED = 1, ICSK_ACK_TIMER = 2, ICSK_ACK_PUSHED = 4, - ICSK_ACK_PUSHED2 = 8 + ICSK_ACK_PUSHED2 = 8, + ICSK_ACK_NOW = 16 /* Send the next ACK immediately (once) */ }; void inet_csk_init_xmit_timers(struct sock *sk, diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 715d541b52dd..b8849588c440 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5179,7 +5179,9 @@ static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible) (tp->rcv_nxt - tp->copied_seq < sk->sk_rcvlowat || __tcp_select_window(sk) >= tp->rcv_wnd)) || /* We ACK each frame or... */ - tcp_in_quickack_mode(sk)) { + tcp_in_quickack_mode(sk) || + /* Protocol state mandates a one-time immediate ACK */ + inet_csk(sk)->icsk_ack.pending & ICSK_ACK_NOW) { send_now: tcp_send_ack(sk); return; -- cgit v1.2.3 From 19e226e8cc5da02f17ed119f9137036c0f0f5d80 Mon Sep 17 00:00:00 2001 From: Caleb Raitto Date: Thu, 9 Aug 2018 18:18:28 -0700 Subject: virtio: Make vp_set_vq_affinity() take a mask. Make vp_set_vq_affinity() take a cpumask instead of taking a single CPU. If there are fewer queues than cores, queue affinity should be able to map to multiple cores. Link: https://patchwork.ozlabs.org/patch/948149/ Suggested-by: Willem de Bruijn Signed-off-by: Caleb Raitto Acked-by: Gonglei Signed-off-by: David S. Miller --- drivers/crypto/virtio/virtio_crypto_core.c | 4 ++-- drivers/net/virtio_net.c | 8 ++++---- drivers/virtio/virtio_pci_common.c | 7 +++---- drivers/virtio/virtio_pci_common.h | 2 +- include/linux/virtio_config.h | 7 ++++--- 5 files changed, 14 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/drivers/crypto/virtio/virtio_crypto_core.c b/drivers/crypto/virtio/virtio_crypto_core.c index 83326986c113..7c7198553699 100644 --- a/drivers/crypto/virtio/virtio_crypto_core.c +++ b/drivers/crypto/virtio/virtio_crypto_core.c @@ -146,7 +146,7 @@ static void virtcrypto_clean_affinity(struct virtio_crypto *vi, long hcpu) if (vi->affinity_hint_set) { for (i = 0; i < vi->max_data_queues; i++) - virtqueue_set_affinity(vi->data_vq[i].vq, -1); + virtqueue_set_affinity(vi->data_vq[i].vq, NULL); vi->affinity_hint_set = false; } @@ -173,7 +173,7 @@ static void virtcrypto_set_affinity(struct virtio_crypto *vcrypto) * */ for_each_online_cpu(cpu) { - virtqueue_set_affinity(vcrypto->data_vq[i].vq, cpu); + virtqueue_set_affinity(vcrypto->data_vq[i].vq, cpumask_of(cpu)); if (++i >= vcrypto->max_data_queues) break; } diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 39a7f4452587..43fabc0eb4d2 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -1878,8 +1878,8 @@ static void virtnet_clean_affinity(struct virtnet_info *vi, long hcpu) if (vi->affinity_hint_set) { for (i = 0; i < vi->max_queue_pairs; i++) { - virtqueue_set_affinity(vi->rq[i].vq, -1); - virtqueue_set_affinity(vi->sq[i].vq, -1); + virtqueue_set_affinity(vi->rq[i].vq, NULL); + virtqueue_set_affinity(vi->sq[i].vq, NULL); } vi->affinity_hint_set = false; @@ -1905,8 +1905,8 @@ static void virtnet_set_affinity(struct virtnet_info *vi) for_each_online_cpu(cpu) { const unsigned long *mask = cpumask_bits(cpumask_of(cpu)); - virtqueue_set_affinity(vi->rq[i].vq, cpu); - virtqueue_set_affinity(vi->sq[i].vq, cpu); + virtqueue_set_affinity(vi->rq[i].vq, cpumask_of(cpu)); + virtqueue_set_affinity(vi->sq[i].vq, cpumask_of(cpu)); __netif_set_xps_queue(vi->dev, mask, i, false); i++; } diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c index 705aebd74e56..465a6f5142cc 100644 --- a/drivers/virtio/virtio_pci_common.c +++ b/drivers/virtio/virtio_pci_common.c @@ -421,7 +421,7 @@ const char *vp_bus_name(struct virtio_device *vdev) * - OR over all affinities for shared MSI * - ignore the affinity request if we're using INTX */ -int vp_set_vq_affinity(struct virtqueue *vq, int cpu) +int vp_set_vq_affinity(struct virtqueue *vq, const struct cpumask *cpu_mask) { struct virtio_device *vdev = vq->vdev; struct virtio_pci_device *vp_dev = to_vp_device(vdev); @@ -435,11 +435,10 @@ int vp_set_vq_affinity(struct virtqueue *vq, int cpu) if (vp_dev->msix_enabled) { mask = vp_dev->msix_affinity_masks[info->msix_vector]; irq = pci_irq_vector(vp_dev->pci_dev, info->msix_vector); - if (cpu == -1) + if (!cpu_mask) irq_set_affinity_hint(irq, NULL); else { - cpumask_clear(mask); - cpumask_set_cpu(cpu, mask); + cpumask_copy(mask, cpu_mask); irq_set_affinity_hint(irq, mask); } } diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h index 135ee3cf7175..02271002c2f3 100644 --- a/drivers/virtio/virtio_pci_common.h +++ b/drivers/virtio/virtio_pci_common.h @@ -141,7 +141,7 @@ const char *vp_bus_name(struct virtio_device *vdev); * - OR over all affinities for shared MSI * - ignore the affinity request if we're using INTX */ -int vp_set_vq_affinity(struct virtqueue *vq, int cpu); +int vp_set_vq_affinity(struct virtqueue *vq, const struct cpumask *cpu_mask); const struct cpumask *vp_get_vq_affinity(struct virtio_device *vdev, int index); diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 5559a2d31c46..32baf8e26735 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -79,7 +79,8 @@ struct virtio_config_ops { u64 (*get_features)(struct virtio_device *vdev); int (*finalize_features)(struct virtio_device *vdev); const char *(*bus_name)(struct virtio_device *vdev); - int (*set_vq_affinity)(struct virtqueue *vq, int cpu); + int (*set_vq_affinity)(struct virtqueue *vq, + const struct cpumask *cpu_mask); const struct cpumask *(*get_vq_affinity)(struct virtio_device *vdev, int index); }; @@ -236,11 +237,11 @@ const char *virtio_bus_name(struct virtio_device *vdev) * */ static inline -int virtqueue_set_affinity(struct virtqueue *vq, int cpu) +int virtqueue_set_affinity(struct virtqueue *vq, const struct cpumask *cpu_mask) { struct virtio_device *vdev = vq->vdev; if (vdev->config->set_vq_affinity) - return vdev->config->set_vq_affinity(vq, cpu); + return vdev->config->set_vq_affinity(vq, cpu_mask); return 0; } -- cgit v1.2.3 From b0e29063dcb3bf14f515f95e748b60e4bab45e7c Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Fri, 10 Aug 2018 13:22:01 +0200 Subject: l2tp: remove pppol2tp_session_ioctl() pppol2tp_ioctl() has everything in place for handling PPPIOCGL2TPSTATS on session sockets. We just need to copy the stats and set ->session_id. As a side effect of sharing session and tunnel code, ->using_ipsec is properly set even when the request was made using a session socket. Signed-off-by: Guillaume Nault Signed-off-by: David S. Miller --- include/uapi/linux/ppp-ioctl.h | 2 +- net/l2tp/l2tp_ppp.c | 50 +++--------------------------------------- 2 files changed, 4 insertions(+), 48 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/ppp-ioctl.h b/include/uapi/linux/ppp-ioctl.h index 784c2e3e572e..88b5f9990320 100644 --- a/include/uapi/linux/ppp-ioctl.h +++ b/include/uapi/linux/ppp-ioctl.h @@ -68,7 +68,7 @@ struct ppp_option_data { struct pppol2tp_ioc_stats { __u16 tunnel_id; /* redundant */ __u16 session_id; /* if zero, get tunnel stats */ - __u32 using_ipsec:1; /* valid only for session_id == 0 */ + __u32 using_ipsec:1; __aligned_u64 tx_packets; __aligned_u64 tx_bytes; __aligned_u64 tx_errors; diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 2afd3ab8a551..bdfbd3ed7e14 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -1068,52 +1068,6 @@ static int pppol2tp_tunnel_copy_stats(struct pppol2tp_ioc_stats *stats, return 0; } -/* Session ioctl helper. - */ -static int pppol2tp_session_ioctl(struct l2tp_session *session, - unsigned int cmd, unsigned long arg) -{ - int err = 0; - struct sock *sk; - struct l2tp_tunnel *tunnel = session->tunnel; - struct pppol2tp_ioc_stats stats; - - l2tp_dbg(session, L2TP_MSG_CONTROL, - "%s: pppol2tp_session_ioctl(cmd=%#x, arg=%#lx)\n", - session->name, cmd, arg); - - sk = pppol2tp_session_get_sock(session); - if (!sk) - return -EBADR; - - switch (cmd) { - case PPPIOCGL2TPSTATS: - err = -ENXIO; - if (!(sk->sk_state & PPPOX_CONNECTED)) - break; - - memset(&stats, 0, sizeof(stats)); - stats.tunnel_id = tunnel->tunnel_id; - stats.session_id = session->session_id; - pppol2tp_copy_stats(&stats, &session->stats); - if (copy_to_user((void __user *) arg, &stats, - sizeof(stats))) - break; - l2tp_info(session, L2TP_MSG_CONTROL, "%s: get L2TP stats\n", - session->name); - err = 0; - break; - - default: - err = -ENOSYS; - break; - } - - sock_put(sk); - - return err; -} - static int pppol2tp_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { @@ -1172,7 +1126,9 @@ static int pppol2tp_ioctl(struct socket *sock, unsigned int cmd, stats.session_id = session_id; } else { - return pppol2tp_session_ioctl(session, cmd, arg); + memset(&stats, 0, sizeof(stats)); + pppol2tp_copy_stats(&stats, &session->stats); + stats.session_id = session->session_id; } stats.tunnel_id = session->tunnel->tunnel_id; stats.using_ipsec = l2tp_tunnel_uses_xfrm(session->tunnel); -- cgit v1.2.3 From 05364ca03cfd419caecb292fede20eb39667eaae Mon Sep 17 00:00:00 2001 From: Konstantin Khorenko Date: Fri, 10 Aug 2018 20:11:42 +0300 Subject: net/sctp: Make wrappers for accessing in/out streams This patch introduces wrappers for accessing in/out streams indirectly. This will enable to replace physically contiguous memory arrays of streams with flexible arrays (or maybe any other appropriate mechanism) which do memory allocation on a per-page basis. Signed-off-by: Oleg Babin Signed-off-by: Konstantin Khorenko Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 35 +++++++++++++++++------- net/sctp/chunk.c | 6 ++-- net/sctp/outqueue.c | 11 ++++---- net/sctp/socket.c | 4 +-- net/sctp/stream.c | 65 +++++++++++++++++++++++--------------------- net/sctp/stream_interleave.c | 20 +++++++------- net/sctp/stream_sched.c | 13 +++++---- net/sctp/stream_sched_prio.c | 22 +++++++-------- net/sctp/stream_sched_rr.c | 8 +++--- 9 files changed, 103 insertions(+), 81 deletions(-) (limited to 'include') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index ab869e0d8326..6b2b8df8a1d2 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -398,37 +398,35 @@ void sctp_stream_update(struct sctp_stream *stream, struct sctp_stream *new); /* What is the current SSN number for this stream? */ #define sctp_ssn_peek(stream, type, sid) \ - ((stream)->type[sid].ssn) + (sctp_stream_##type((stream), (sid))->ssn) /* Return the next SSN number for this stream. */ #define sctp_ssn_next(stream, type, sid) \ - ((stream)->type[sid].ssn++) + (sctp_stream_##type((stream), (sid))->ssn++) /* Skip over this ssn and all below. */ #define sctp_ssn_skip(stream, type, sid, ssn) \ - ((stream)->type[sid].ssn = ssn + 1) + (sctp_stream_##type((stream), (sid))->ssn = ssn + 1) /* What is the current MID number for this stream? */ #define sctp_mid_peek(stream, type, sid) \ - ((stream)->type[sid].mid) + (sctp_stream_##type((stream), (sid))->mid) /* Return the next MID number for this stream. */ #define sctp_mid_next(stream, type, sid) \ - ((stream)->type[sid].mid++) + (sctp_stream_##type((stream), (sid))->mid++) /* Skip over this mid and all below. */ #define sctp_mid_skip(stream, type, sid, mid) \ - ((stream)->type[sid].mid = mid + 1) - -#define sctp_stream_in(asoc, sid) (&(asoc)->stream.in[sid]) + (sctp_stream_##type((stream), (sid))->mid = mid + 1) /* What is the current MID_uo number for this stream? */ #define sctp_mid_uo_peek(stream, type, sid) \ - ((stream)->type[sid].mid_uo) + (sctp_stream_##type((stream), (sid))->mid_uo) /* Return the next MID_uo number for this stream. */ #define sctp_mid_uo_next(stream, type, sid) \ - ((stream)->type[sid].mid_uo++) + (sctp_stream_##type((stream), (sid))->mid_uo++) /* * Pointers to address related SCTP functions. @@ -1463,6 +1461,23 @@ struct sctp_stream { struct sctp_stream_interleave *si; }; +static inline struct sctp_stream_out *sctp_stream_out( + const struct sctp_stream *stream, + __u16 sid) +{ + return ((struct sctp_stream_out *)(stream->out)) + sid; +} + +static inline struct sctp_stream_in *sctp_stream_in( + const struct sctp_stream *stream, + __u16 sid) +{ + return ((struct sctp_stream_in *)(stream->in)) + sid; +} + +#define SCTP_SO(s, i) sctp_stream_out((s), (i)) +#define SCTP_SI(s, i) sctp_stream_in((s), (i)) + #define SCTP_STREAM_CLOSED 0x00 #define SCTP_STREAM_OPEN 0x01 diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c index bfb9f812e2ef..ce8087846f05 100644 --- a/net/sctp/chunk.c +++ b/net/sctp/chunk.c @@ -325,7 +325,8 @@ int sctp_chunk_abandoned(struct sctp_chunk *chunk) if (SCTP_PR_TTL_ENABLED(chunk->sinfo.sinfo_flags) && time_after(jiffies, chunk->msg->expires_at)) { struct sctp_stream_out *streamout = - &chunk->asoc->stream.out[chunk->sinfo.sinfo_stream]; + SCTP_SO(&chunk->asoc->stream, + chunk->sinfo.sinfo_stream); if (chunk->sent_count) { chunk->asoc->abandoned_sent[SCTP_PR_INDEX(TTL)]++; @@ -339,7 +340,8 @@ int sctp_chunk_abandoned(struct sctp_chunk *chunk) } else if (SCTP_PR_RTX_ENABLED(chunk->sinfo.sinfo_flags) && chunk->sent_count > chunk->sinfo.sinfo_timetolive) { struct sctp_stream_out *streamout = - &chunk->asoc->stream.out[chunk->sinfo.sinfo_stream]; + SCTP_SO(&chunk->asoc->stream, + chunk->sinfo.sinfo_stream); chunk->asoc->abandoned_sent[SCTP_PR_INDEX(RTX)]++; streamout->ext->abandoned_sent[SCTP_PR_INDEX(RTX)]++; diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index d68aa33485a9..d74d00b29942 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -80,7 +80,7 @@ static inline void sctp_outq_head_data(struct sctp_outq *q, q->out_qlen += ch->skb->len; stream = sctp_chunk_stream_no(ch); - oute = q->asoc->stream.out[stream].ext; + oute = SCTP_SO(&q->asoc->stream, stream)->ext; list_add(&ch->stream_list, &oute->outq); } @@ -101,7 +101,7 @@ static inline void sctp_outq_tail_data(struct sctp_outq *q, q->out_qlen += ch->skb->len; stream = sctp_chunk_stream_no(ch); - oute = q->asoc->stream.out[stream].ext; + oute = SCTP_SO(&q->asoc->stream, stream)->ext; list_add_tail(&ch->stream_list, &oute->outq); } @@ -372,7 +372,7 @@ static int sctp_prsctp_prune_sent(struct sctp_association *asoc, sctp_insert_list(&asoc->outqueue.abandoned, &chk->transmitted_list); - streamout = &asoc->stream.out[chk->sinfo.sinfo_stream]; + streamout = SCTP_SO(&asoc->stream, chk->sinfo.sinfo_stream); asoc->sent_cnt_removable--; asoc->abandoned_sent[SCTP_PR_INDEX(PRIO)]++; streamout->ext->abandoned_sent[SCTP_PR_INDEX(PRIO)]++; @@ -416,7 +416,7 @@ static int sctp_prsctp_prune_unsent(struct sctp_association *asoc, asoc->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++; if (chk->sinfo.sinfo_stream < asoc->stream.outcnt) { struct sctp_stream_out *streamout = - &asoc->stream.out[chk->sinfo.sinfo_stream]; + SCTP_SO(&asoc->stream, chk->sinfo.sinfo_stream); streamout->ext->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++; } @@ -1082,6 +1082,7 @@ static void sctp_outq_flush_data(struct sctp_flush_ctx *ctx, /* Finally, transmit new packets. */ while ((chunk = sctp_outq_dequeue_data(ctx->q)) != NULL) { __u32 sid = ntohs(chunk->subh.data_hdr->stream); + __u8 stream_state = SCTP_SO(&ctx->asoc->stream, sid)->state; /* Has this chunk expired? */ if (sctp_chunk_abandoned(chunk)) { @@ -1091,7 +1092,7 @@ static void sctp_outq_flush_data(struct sctp_flush_ctx *ctx, continue; } - if (ctx->asoc->stream.out[sid].state == SCTP_STREAM_CLOSED) { + if (stream_state == SCTP_STREAM_CLOSED) { sctp_outq_head_data(ctx->q, chunk); break; } diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 502c0d7cb105..e96b15a66aba 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -1911,7 +1911,7 @@ static int sctp_sendmsg_to_asoc(struct sctp_association *asoc, goto err; } - if (unlikely(!asoc->stream.out[sinfo->sinfo_stream].ext)) { + if (unlikely(!SCTP_SO(&asoc->stream, sinfo->sinfo_stream)->ext)) { err = sctp_stream_init_ext(&asoc->stream, sinfo->sinfo_stream); if (err) goto err; @@ -7154,7 +7154,7 @@ static int sctp_getsockopt_pr_streamstatus(struct sock *sk, int len, if (!asoc || params.sprstat_sid >= asoc->stream.outcnt) goto out; - streamoute = asoc->stream.out[params.sprstat_sid].ext; + streamoute = SCTP_SO(&asoc->stream, params.sprstat_sid)->ext; if (!streamoute) { /* Not allocated yet, means all stats are 0 */ params.sprstat_abandoned_unsent = 0; diff --git a/net/sctp/stream.c b/net/sctp/stream.c index f1f1d1b232ba..7ca6fe4e7882 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -162,7 +162,7 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt, stream->outcnt = outcnt; for (i = 0; i < stream->outcnt; i++) - stream->out[i].state = SCTP_STREAM_OPEN; + SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN; sched->init(stream); @@ -193,7 +193,7 @@ int sctp_stream_init_ext(struct sctp_stream *stream, __u16 sid) soute = kzalloc(sizeof(*soute), GFP_KERNEL); if (!soute) return -ENOMEM; - stream->out[sid].ext = soute; + SCTP_SO(stream, sid)->ext = soute; return sctp_sched_init_sid(stream, sid, GFP_KERNEL); } @@ -205,7 +205,7 @@ void sctp_stream_free(struct sctp_stream *stream) sched->free(stream); for (i = 0; i < stream->outcnt; i++) - kfree(stream->out[i].ext); + kfree(SCTP_SO(stream, i)->ext); kfree(stream->out); kfree(stream->in); } @@ -215,12 +215,12 @@ void sctp_stream_clear(struct sctp_stream *stream) int i; for (i = 0; i < stream->outcnt; i++) { - stream->out[i].mid = 0; - stream->out[i].mid_uo = 0; + SCTP_SO(stream, i)->mid = 0; + SCTP_SO(stream, i)->mid_uo = 0; } for (i = 0; i < stream->incnt; i++) - stream->in[i].mid = 0; + SCTP_SI(stream, i)->mid = 0; } void sctp_stream_update(struct sctp_stream *stream, struct sctp_stream *new) @@ -273,8 +273,8 @@ static bool sctp_stream_outq_is_empty(struct sctp_stream *stream, for (i = 0; i < str_nums; i++) { __u16 sid = ntohs(str_list[i]); - if (stream->out[sid].ext && - !list_empty(&stream->out[sid].ext->outq)) + if (SCTP_SO(stream, sid)->ext && + !list_empty(&SCTP_SO(stream, sid)->ext->outq)) return false; } @@ -361,11 +361,11 @@ int sctp_send_reset_streams(struct sctp_association *asoc, if (out) { if (str_nums) for (i = 0; i < str_nums; i++) - stream->out[str_list[i]].state = + SCTP_SO(stream, str_list[i])->state = SCTP_STREAM_CLOSED; else for (i = 0; i < stream->outcnt; i++) - stream->out[i].state = SCTP_STREAM_CLOSED; + SCTP_SO(stream, i)->state = SCTP_STREAM_CLOSED; } asoc->strreset_chunk = chunk; @@ -380,11 +380,11 @@ int sctp_send_reset_streams(struct sctp_association *asoc, if (str_nums) for (i = 0; i < str_nums; i++) - stream->out[str_list[i]].state = + SCTP_SO(stream, str_list[i])->state = SCTP_STREAM_OPEN; else for (i = 0; i < stream->outcnt; i++) - stream->out[i].state = SCTP_STREAM_OPEN; + SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN; goto out; } @@ -418,7 +418,7 @@ int sctp_send_reset_assoc(struct sctp_association *asoc) /* Block further xmit of data until this request is completed */ for (i = 0; i < stream->outcnt; i++) - stream->out[i].state = SCTP_STREAM_CLOSED; + SCTP_SO(stream, i)->state = SCTP_STREAM_CLOSED; asoc->strreset_chunk = chunk; sctp_chunk_hold(asoc->strreset_chunk); @@ -429,7 +429,7 @@ int sctp_send_reset_assoc(struct sctp_association *asoc) asoc->strreset_chunk = NULL; for (i = 0; i < stream->outcnt; i++) - stream->out[i].state = SCTP_STREAM_OPEN; + SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN; return retval; } @@ -609,10 +609,10 @@ struct sctp_chunk *sctp_process_strreset_outreq( } for (i = 0; i < nums; i++) - stream->in[ntohs(str_p[i])].mid = 0; + SCTP_SI(stream, ntohs(str_p[i]))->mid = 0; } else { for (i = 0; i < stream->incnt; i++) - stream->in[i].mid = 0; + SCTP_SI(stream, i)->mid = 0; } result = SCTP_STRRESET_PERFORMED; @@ -683,11 +683,11 @@ struct sctp_chunk *sctp_process_strreset_inreq( if (nums) for (i = 0; i < nums; i++) - stream->out[ntohs(str_p[i])].state = + SCTP_SO(stream, ntohs(str_p[i]))->state = SCTP_STREAM_CLOSED; else for (i = 0; i < stream->outcnt; i++) - stream->out[i].state = SCTP_STREAM_CLOSED; + SCTP_SO(stream, i)->state = SCTP_STREAM_CLOSED; asoc->strreset_chunk = chunk; asoc->strreset_outstanding = 1; @@ -786,11 +786,11 @@ struct sctp_chunk *sctp_process_strreset_tsnreq( * incoming and outgoing streams. */ for (i = 0; i < stream->outcnt; i++) { - stream->out[i].mid = 0; - stream->out[i].mid_uo = 0; + SCTP_SO(stream, i)->mid = 0; + SCTP_SO(stream, i)->mid_uo = 0; } for (i = 0; i < stream->incnt; i++) - stream->in[i].mid = 0; + SCTP_SI(stream, i)->mid = 0; result = SCTP_STRRESET_PERFORMED; @@ -979,15 +979,18 @@ struct sctp_chunk *sctp_process_strreset_resp( sizeof(__u16); if (result == SCTP_STRRESET_PERFORMED) { + struct sctp_stream_out *sout; if (nums) { for (i = 0; i < nums; i++) { - stream->out[ntohs(str_p[i])].mid = 0; - stream->out[ntohs(str_p[i])].mid_uo = 0; + sout = SCTP_SO(stream, ntohs(str_p[i])); + sout->mid = 0; + sout->mid_uo = 0; } } else { for (i = 0; i < stream->outcnt; i++) { - stream->out[i].mid = 0; - stream->out[i].mid_uo = 0; + sout = SCTP_SO(stream, i); + sout->mid = 0; + sout->mid_uo = 0; } } @@ -995,7 +998,7 @@ struct sctp_chunk *sctp_process_strreset_resp( } for (i = 0; i < stream->outcnt; i++) - stream->out[i].state = SCTP_STREAM_OPEN; + SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN; *evp = sctp_ulpevent_make_stream_reset_event(asoc, flags, nums, str_p, GFP_ATOMIC); @@ -1050,15 +1053,15 @@ struct sctp_chunk *sctp_process_strreset_resp( asoc->adv_peer_ack_point = asoc->ctsn_ack_point; for (i = 0; i < stream->outcnt; i++) { - stream->out[i].mid = 0; - stream->out[i].mid_uo = 0; + SCTP_SO(stream, i)->mid = 0; + SCTP_SO(stream, i)->mid_uo = 0; } for (i = 0; i < stream->incnt; i++) - stream->in[i].mid = 0; + SCTP_SI(stream, i)->mid = 0; } for (i = 0; i < stream->outcnt; i++) - stream->out[i].state = SCTP_STREAM_OPEN; + SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN; *evp = sctp_ulpevent_make_assoc_reset_event(asoc, flags, stsn, rtsn, GFP_ATOMIC); @@ -1072,7 +1075,7 @@ struct sctp_chunk *sctp_process_strreset_resp( if (result == SCTP_STRRESET_PERFORMED) for (i = number; i < stream->outcnt; i++) - stream->out[i].state = SCTP_STREAM_OPEN; + SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN; else stream->outcnt = number; diff --git a/net/sctp/stream_interleave.c b/net/sctp/stream_interleave.c index d3764c181299..0a78cdf86463 100644 --- a/net/sctp/stream_interleave.c +++ b/net/sctp/stream_interleave.c @@ -197,7 +197,7 @@ static struct sctp_ulpevent *sctp_intl_retrieve_partial( __u32 next_fsn = 0; int is_last = 0; - sin = sctp_stream_in(ulpq->asoc, event->stream); + sin = sctp_stream_in(&ulpq->asoc->stream, event->stream); skb_queue_walk(&ulpq->reasm, pos) { struct sctp_ulpevent *cevent = sctp_skb2event(pos); @@ -278,7 +278,7 @@ static struct sctp_ulpevent *sctp_intl_retrieve_reassembled( __u32 pd_len = 0; __u32 mid = 0; - sin = sctp_stream_in(ulpq->asoc, event->stream); + sin = sctp_stream_in(&ulpq->asoc->stream, event->stream); skb_queue_walk(&ulpq->reasm, pos) { struct sctp_ulpevent *cevent = sctp_skb2event(pos); @@ -368,7 +368,7 @@ static struct sctp_ulpevent *sctp_intl_reasm(struct sctp_ulpq *ulpq, sctp_intl_store_reasm(ulpq, event); - sin = sctp_stream_in(ulpq->asoc, event->stream); + sin = sctp_stream_in(&ulpq->asoc->stream, event->stream); if (sin->pd_mode && event->mid == sin->mid && event->fsn == sin->fsn) retval = sctp_intl_retrieve_partial(ulpq, event); @@ -575,7 +575,7 @@ static struct sctp_ulpevent *sctp_intl_retrieve_partial_uo( __u32 next_fsn = 0; int is_last = 0; - sin = sctp_stream_in(ulpq->asoc, event->stream); + sin = sctp_stream_in(&ulpq->asoc->stream, event->stream); skb_queue_walk(&ulpq->reasm_uo, pos) { struct sctp_ulpevent *cevent = sctp_skb2event(pos); @@ -659,7 +659,7 @@ static struct sctp_ulpevent *sctp_intl_retrieve_reassembled_uo( __u32 pd_len = 0; __u32 mid = 0; - sin = sctp_stream_in(ulpq->asoc, event->stream); + sin = sctp_stream_in(&ulpq->asoc->stream, event->stream); skb_queue_walk(&ulpq->reasm_uo, pos) { struct sctp_ulpevent *cevent = sctp_skb2event(pos); @@ -750,7 +750,7 @@ static struct sctp_ulpevent *sctp_intl_reasm_uo(struct sctp_ulpq *ulpq, sctp_intl_store_reasm_uo(ulpq, event); - sin = sctp_stream_in(ulpq->asoc, event->stream); + sin = sctp_stream_in(&ulpq->asoc->stream, event->stream); if (sin->pd_mode_uo && event->mid == sin->mid_uo && event->fsn == sin->fsn_uo) retval = sctp_intl_retrieve_partial_uo(ulpq, event); @@ -774,7 +774,7 @@ static struct sctp_ulpevent *sctp_intl_retrieve_first_uo(struct sctp_ulpq *ulpq) skb_queue_walk(&ulpq->reasm_uo, pos) { struct sctp_ulpevent *cevent = sctp_skb2event(pos); - csin = sctp_stream_in(ulpq->asoc, cevent->stream); + csin = sctp_stream_in(&ulpq->asoc->stream, cevent->stream); if (csin->pd_mode_uo) continue; @@ -875,7 +875,7 @@ static struct sctp_ulpevent *sctp_intl_retrieve_first(struct sctp_ulpq *ulpq) skb_queue_walk(&ulpq->reasm, pos) { struct sctp_ulpevent *cevent = sctp_skb2event(pos); - csin = sctp_stream_in(ulpq->asoc, cevent->stream); + csin = sctp_stream_in(&ulpq->asoc->stream, cevent->stream); if (csin->pd_mode) continue; @@ -1053,7 +1053,7 @@ static void sctp_intl_abort_pd(struct sctp_ulpq *ulpq, gfp_t gfp) __u16 sid; for (sid = 0; sid < stream->incnt; sid++) { - struct sctp_stream_in *sin = &stream->in[sid]; + struct sctp_stream_in *sin = SCTP_SI(stream, sid); __u32 mid; if (sin->pd_mode_uo) { @@ -1247,7 +1247,7 @@ static void sctp_handle_fwdtsn(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk) static void sctp_intl_skip(struct sctp_ulpq *ulpq, __u16 sid, __u32 mid, __u8 flags) { - struct sctp_stream_in *sin = sctp_stream_in(ulpq->asoc, sid); + struct sctp_stream_in *sin = sctp_stream_in(&ulpq->asoc->stream, sid); struct sctp_stream *stream = &ulpq->asoc->stream; if (flags & SCTP_FTSN_U_BIT) { diff --git a/net/sctp/stream_sched.c b/net/sctp/stream_sched.c index f5fcd425232a..a6c04a94b08f 100644 --- a/net/sctp/stream_sched.c +++ b/net/sctp/stream_sched.c @@ -161,7 +161,7 @@ int sctp_sched_set_sched(struct sctp_association *asoc, /* Give the next scheduler a clean slate. */ for (i = 0; i < asoc->stream.outcnt; i++) { - void *p = asoc->stream.out[i].ext; + void *p = SCTP_SO(&asoc->stream, i)->ext; if (!p) continue; @@ -175,7 +175,7 @@ int sctp_sched_set_sched(struct sctp_association *asoc, asoc->outqueue.sched = n; n->init(&asoc->stream); for (i = 0; i < asoc->stream.outcnt; i++) { - if (!asoc->stream.out[i].ext) + if (!SCTP_SO(&asoc->stream, i)->ext) continue; ret = n->init_sid(&asoc->stream, i, GFP_KERNEL); @@ -217,7 +217,7 @@ int sctp_sched_set_value(struct sctp_association *asoc, __u16 sid, if (sid >= asoc->stream.outcnt) return -EINVAL; - if (!asoc->stream.out[sid].ext) { + if (!SCTP_SO(&asoc->stream, sid)->ext) { int ret; ret = sctp_stream_init_ext(&asoc->stream, sid); @@ -234,7 +234,7 @@ int sctp_sched_get_value(struct sctp_association *asoc, __u16 sid, if (sid >= asoc->stream.outcnt) return -EINVAL; - if (!asoc->stream.out[sid].ext) + if (!SCTP_SO(&asoc->stream, sid)->ext) return 0; return asoc->outqueue.sched->get(&asoc->stream, sid, value); @@ -252,7 +252,7 @@ void sctp_sched_dequeue_done(struct sctp_outq *q, struct sctp_chunk *ch) * priority stream comes in. */ sid = sctp_chunk_stream_no(ch); - sout = &q->asoc->stream.out[sid]; + sout = SCTP_SO(&q->asoc->stream, sid); q->asoc->stream.out_curr = sout; return; } @@ -272,8 +272,9 @@ void sctp_sched_dequeue_common(struct sctp_outq *q, struct sctp_chunk *ch) int sctp_sched_init_sid(struct sctp_stream *stream, __u16 sid, gfp_t gfp) { struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream); + struct sctp_stream_out_ext *ext = SCTP_SO(stream, sid)->ext; - INIT_LIST_HEAD(&stream->out[sid].ext->outq); + INIT_LIST_HEAD(&ext->outq); return sched->init_sid(stream, sid, gfp); } diff --git a/net/sctp/stream_sched_prio.c b/net/sctp/stream_sched_prio.c index 7997d35dd0fd..2245083a98f2 100644 --- a/net/sctp/stream_sched_prio.c +++ b/net/sctp/stream_sched_prio.c @@ -75,10 +75,10 @@ static struct sctp_stream_priorities *sctp_sched_prio_get_head( /* No luck. So we search on all streams now. */ for (i = 0; i < stream->outcnt; i++) { - if (!stream->out[i].ext) + if (!SCTP_SO(stream, i)->ext) continue; - p = stream->out[i].ext->prio_head; + p = SCTP_SO(stream, i)->ext->prio_head; if (!p) /* Means all other streams won't be initialized * as well. @@ -165,7 +165,7 @@ static void sctp_sched_prio_sched(struct sctp_stream *stream, static int sctp_sched_prio_set(struct sctp_stream *stream, __u16 sid, __u16 prio, gfp_t gfp) { - struct sctp_stream_out *sout = &stream->out[sid]; + struct sctp_stream_out *sout = SCTP_SO(stream, sid); struct sctp_stream_out_ext *soute = sout->ext; struct sctp_stream_priorities *prio_head, *old; bool reschedule = false; @@ -186,7 +186,7 @@ static int sctp_sched_prio_set(struct sctp_stream *stream, __u16 sid, return 0; for (i = 0; i < stream->outcnt; i++) { - soute = stream->out[i].ext; + soute = SCTP_SO(stream, i)->ext; if (soute && soute->prio_head == old) /* It's still in use, nothing else to do here. */ return 0; @@ -201,7 +201,7 @@ static int sctp_sched_prio_set(struct sctp_stream *stream, __u16 sid, static int sctp_sched_prio_get(struct sctp_stream *stream, __u16 sid, __u16 *value) { - *value = stream->out[sid].ext->prio_head->prio; + *value = SCTP_SO(stream, sid)->ext->prio_head->prio; return 0; } @@ -215,7 +215,7 @@ static int sctp_sched_prio_init(struct sctp_stream *stream) static int sctp_sched_prio_init_sid(struct sctp_stream *stream, __u16 sid, gfp_t gfp) { - INIT_LIST_HEAD(&stream->out[sid].ext->prio_list); + INIT_LIST_HEAD(&SCTP_SO(stream, sid)->ext->prio_list); return sctp_sched_prio_set(stream, sid, 0, gfp); } @@ -233,9 +233,9 @@ static void sctp_sched_prio_free(struct sctp_stream *stream) */ sctp_sched_prio_unsched_all(stream); for (i = 0; i < stream->outcnt; i++) { - if (!stream->out[i].ext) + if (!SCTP_SO(stream, i)->ext) continue; - prio = stream->out[i].ext->prio_head; + prio = SCTP_SO(stream, i)->ext->prio_head; if (prio && list_empty(&prio->prio_sched)) list_add(&prio->prio_sched, &list); } @@ -255,7 +255,7 @@ static void sctp_sched_prio_enqueue(struct sctp_outq *q, ch = list_first_entry(&msg->chunks, struct sctp_chunk, frag_list); sid = sctp_chunk_stream_no(ch); stream = &q->asoc->stream; - sctp_sched_prio_sched(stream, stream->out[sid].ext); + sctp_sched_prio_sched(stream, SCTP_SO(stream, sid)->ext); } static struct sctp_chunk *sctp_sched_prio_dequeue(struct sctp_outq *q) @@ -297,7 +297,7 @@ static void sctp_sched_prio_dequeue_done(struct sctp_outq *q, * this priority. */ sid = sctp_chunk_stream_no(ch); - soute = q->asoc->stream.out[sid].ext; + soute = SCTP_SO(&q->asoc->stream, sid)->ext; prio = soute->prio_head; sctp_sched_prio_next_stream(prio); @@ -317,7 +317,7 @@ static void sctp_sched_prio_sched_all(struct sctp_stream *stream) __u16 sid; sid = sctp_chunk_stream_no(ch); - sout = &stream->out[sid]; + sout = SCTP_SO(stream, sid); if (sout->ext) sctp_sched_prio_sched(stream, sout->ext); } diff --git a/net/sctp/stream_sched_rr.c b/net/sctp/stream_sched_rr.c index 1155692448f1..52ba743fa7a7 100644 --- a/net/sctp/stream_sched_rr.c +++ b/net/sctp/stream_sched_rr.c @@ -100,7 +100,7 @@ static int sctp_sched_rr_init(struct sctp_stream *stream) static int sctp_sched_rr_init_sid(struct sctp_stream *stream, __u16 sid, gfp_t gfp) { - INIT_LIST_HEAD(&stream->out[sid].ext->rr_list); + INIT_LIST_HEAD(&SCTP_SO(stream, sid)->ext->rr_list); return 0; } @@ -120,7 +120,7 @@ static void sctp_sched_rr_enqueue(struct sctp_outq *q, ch = list_first_entry(&msg->chunks, struct sctp_chunk, frag_list); sid = sctp_chunk_stream_no(ch); stream = &q->asoc->stream; - sctp_sched_rr_sched(stream, stream->out[sid].ext); + sctp_sched_rr_sched(stream, SCTP_SO(stream, sid)->ext); } static struct sctp_chunk *sctp_sched_rr_dequeue(struct sctp_outq *q) @@ -154,7 +154,7 @@ static void sctp_sched_rr_dequeue_done(struct sctp_outq *q, /* Last chunk on that msg, move to the next stream */ sid = sctp_chunk_stream_no(ch); - soute = q->asoc->stream.out[sid].ext; + soute = SCTP_SO(&q->asoc->stream, sid)->ext; sctp_sched_rr_next_stream(&q->asoc->stream); @@ -173,7 +173,7 @@ static void sctp_sched_rr_sched_all(struct sctp_stream *stream) __u16 sid; sid = sctp_chunk_stream_no(ch); - soute = stream->out[sid].ext; + soute = SCTP_SO(stream, sid)->ext; if (soute) sctp_sched_rr_sched(stream, soute); } -- cgit v1.2.3 From 0d493b4d0be352b5e361e4fa0bc3efe952d8b10e Mon Sep 17 00:00:00 2001 From: Konstantin Khorenko Date: Fri, 10 Aug 2018 20:11:43 +0300 Subject: net/sctp: Replace in/out stream arrays with flex_array This path replaces physically contiguous memory arrays allocated using kmalloc_array() with flexible arrays. This enables to avoid memory allocation failures on the systems under a memory stress. Signed-off-by: Oleg Babin Signed-off-by: Konstantin Khorenko Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 9 ++--- net/sctp/stream.c | 88 ++++++++++++++++++++++++++++++++++------------ 2 files changed, 71 insertions(+), 26 deletions(-) (limited to 'include') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 6b2b8df8a1d2..28a7c8e44636 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -57,6 +57,7 @@ #include /* This gets us atomic counters. */ #include /* We need sk_buff_head. */ #include /* We need tq_struct. */ +#include /* We need flex_array. */ #include /* We need sctp* header structs. */ #include /* We need auth specific structs */ #include /* For inet_skb_parm */ @@ -1438,8 +1439,8 @@ struct sctp_stream_in { }; struct sctp_stream { - struct sctp_stream_out *out; - struct sctp_stream_in *in; + struct flex_array *out; + struct flex_array *in; __u16 outcnt; __u16 incnt; /* Current stream being sent, if any */ @@ -1465,14 +1466,14 @@ static inline struct sctp_stream_out *sctp_stream_out( const struct sctp_stream *stream, __u16 sid) { - return ((struct sctp_stream_out *)(stream->out)) + sid; + return flex_array_get(stream->out, sid); } static inline struct sctp_stream_in *sctp_stream_in( const struct sctp_stream *stream, __u16 sid) { - return ((struct sctp_stream_in *)(stream->in)) + sid; + return flex_array_get(stream->in, sid); } #define SCTP_SO(s, i) sctp_stream_out((s), (i)) diff --git a/net/sctp/stream.c b/net/sctp/stream.c index 7ca6fe4e7882..ffb940d3b57c 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -37,6 +37,53 @@ #include #include +static struct flex_array *fa_alloc(size_t elem_size, size_t elem_count, + gfp_t gfp) +{ + struct flex_array *result; + int err; + + result = flex_array_alloc(elem_size, elem_count, gfp); + if (result) { + err = flex_array_prealloc(result, 0, elem_count, gfp); + if (err) { + flex_array_free(result); + result = NULL; + } + } + + return result; +} + +static void fa_free(struct flex_array *fa) +{ + if (fa) + flex_array_free(fa); +} + +static void fa_copy(struct flex_array *fa, struct flex_array *from, + size_t index, size_t count) +{ + void *elem; + + while (count--) { + elem = flex_array_get(from, index); + flex_array_put(fa, index, elem, 0); + index++; + } +} + +static void fa_zero(struct flex_array *fa, size_t index, size_t count) +{ + void *elem; + + while (count--) { + elem = flex_array_get(fa, index); + memset(elem, 0, fa->element_size); + index++; + } +} + /* Migrates chunks from stream queues to new stream queues if needed, * but not across associations. Also, removes those chunks to streams * higher than the new max. @@ -78,34 +125,33 @@ static void sctp_stream_outq_migrate(struct sctp_stream *stream, * sctp_stream_update will swap ->out pointers. */ for (i = 0; i < outcnt; i++) { - kfree(new->out[i].ext); - new->out[i].ext = stream->out[i].ext; - stream->out[i].ext = NULL; + kfree(SCTP_SO(new, i)->ext); + SCTP_SO(new, i)->ext = SCTP_SO(stream, i)->ext; + SCTP_SO(stream, i)->ext = NULL; } } for (i = outcnt; i < stream->outcnt; i++) - kfree(stream->out[i].ext); + kfree(SCTP_SO(stream, i)->ext); } static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt, gfp_t gfp) { - struct sctp_stream_out *out; + struct flex_array *out; + size_t elem_size = sizeof(struct sctp_stream_out); - out = kmalloc_array(outcnt, sizeof(*out), gfp); + out = fa_alloc(elem_size, outcnt, gfp); if (!out) return -ENOMEM; if (stream->out) { - memcpy(out, stream->out, min(outcnt, stream->outcnt) * - sizeof(*out)); - kfree(stream->out); + fa_copy(out, stream->out, 0, min(outcnt, stream->outcnt)); + fa_free(stream->out); } if (outcnt > stream->outcnt) - memset(out + stream->outcnt, 0, - (outcnt - stream->outcnt) * sizeof(*out)); + fa_zero(out, stream->outcnt, (outcnt - stream->outcnt)); stream->out = out; @@ -115,22 +161,20 @@ static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt, static int sctp_stream_alloc_in(struct sctp_stream *stream, __u16 incnt, gfp_t gfp) { - struct sctp_stream_in *in; - - in = kmalloc_array(incnt, sizeof(*stream->in), gfp); + struct flex_array *in; + size_t elem_size = sizeof(struct sctp_stream_in); + in = fa_alloc(elem_size, incnt, gfp); if (!in) return -ENOMEM; if (stream->in) { - memcpy(in, stream->in, min(incnt, stream->incnt) * - sizeof(*in)); - kfree(stream->in); + fa_copy(in, stream->in, 0, min(incnt, stream->incnt)); + fa_free(stream->in); } if (incnt > stream->incnt) - memset(in + stream->incnt, 0, - (incnt - stream->incnt) * sizeof(*in)); + fa_zero(in, stream->incnt, (incnt - stream->incnt)); stream->in = in; @@ -174,7 +218,7 @@ in: ret = sctp_stream_alloc_in(stream, incnt, gfp); if (ret) { sched->free(stream); - kfree(stream->out); + fa_free(stream->out); stream->out = NULL; stream->outcnt = 0; goto out; @@ -206,8 +250,8 @@ void sctp_stream_free(struct sctp_stream *stream) sched->free(stream); for (i = 0; i < stream->outcnt; i++) kfree(SCTP_SO(stream, i)->ext); - kfree(stream->out); - kfree(stream->in); + fa_free(stream->out); + fa_free(stream->in); } void sctp_stream_clear(struct sctp_stream *stream) -- cgit v1.2.3 From 84a75b329be84c108a21ab9c02a52a9bf9e5a919 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Fri, 10 Aug 2018 20:51:52 +0300 Subject: net: sched: extend action ops with put_dev callback As a preparation for removing dependency on rtnl lock from rules update path, all users of shared objects must take reference while working with them. Extend action ops with put_dev() API to be used on net device returned by get_dev(). Modify mirred action (only action that implements get_dev callback): - Take reference to net device in get_dev. - Implement put_dev API that releases reference to net device. Signed-off-by: Vlad Buslov Signed-off-by: David S. Miller --- include/net/act_api.h | 1 + net/sched/act_mirred.c | 12 +++++++++++- net/sched/cls_api.c | 1 + 3 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/act_api.h b/include/net/act_api.h index 8c9bc02d05e1..1ad5b19e83a9 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -101,6 +101,7 @@ struct tc_action_ops { void (*stats_update)(struct tc_action *, u64, u32, u64); size_t (*get_fill_size)(const struct tc_action *act); struct net_device *(*get_dev)(const struct tc_action *a); + void (*put_dev)(struct net_device *dev); int (*delete)(struct net *net, u32 index); }; diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index b26d060da08e..7a045cc7fe3b 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -358,8 +358,17 @@ static struct notifier_block mirred_device_notifier = { static struct net_device *tcf_mirred_get_dev(const struct tc_action *a) { struct tcf_mirred *m = to_mirred(a); + struct net_device *dev = rtnl_dereference(m->tcfm_dev); + + if (dev) + dev_hold(dev); - return rtnl_dereference(m->tcfm_dev); + return dev; +} + +static void tcf_mirred_put_dev(struct net_device *dev) +{ + dev_put(dev); } static int tcf_mirred_delete(struct net *net, u32 index) @@ -382,6 +391,7 @@ static struct tc_action_ops act_mirred_ops = { .lookup = tcf_mirred_search, .size = sizeof(struct tcf_mirred), .get_dev = tcf_mirred_get_dev, + .put_dev = tcf_mirred_put_dev, .delete = tcf_mirred_delete, }; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index f922ce27ed5e..31bd1439cf60 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -2176,6 +2176,7 @@ static int tc_exts_setup_cb_egdev_call(struct tcf_exts *exts, if (!dev) continue; ret = tc_setup_cb_egdev_call(dev, type, type_data, err_stop); + a->ops->put_dev(dev); if (ret < 0) return ret; ok_count += ret; -- cgit v1.2.3 From 51a9f5ae653979ac4bdbd81778a10431f0177e3c Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Fri, 10 Aug 2018 20:51:54 +0300 Subject: net: core: protect rate estimator statistics pointer with lock Extend gen_new_estimator() to also take stats_lock when re-assigning rate estimator statistics pointer. (to be used by unlocked actions) Rename 'stats_lock' to 'lock' and change argument description to explain that it is now also used for control path. Signed-off-by: Vlad Buslov Signed-off-by: David S. Miller --- include/net/gen_stats.h | 4 ++-- net/core/gen_estimator.c | 21 +++++++++++++-------- 2 files changed, 15 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h index 0304ba2ae353..883bb9085f15 100644 --- a/include/net/gen_stats.h +++ b/include/net/gen_stats.h @@ -59,13 +59,13 @@ int gnet_stats_finish_copy(struct gnet_dump *d); int gen_new_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_basic_cpu __percpu *cpu_bstats, struct net_rate_estimator __rcu **rate_est, - spinlock_t *stats_lock, + spinlock_t *lock, seqcount_t *running, struct nlattr *opt); void gen_kill_estimator(struct net_rate_estimator __rcu **ptr); int gen_replace_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_basic_cpu __percpu *cpu_bstats, struct net_rate_estimator __rcu **ptr, - spinlock_t *stats_lock, + spinlock_t *lock, seqcount_t *running, struct nlattr *opt); bool gen_estimator_active(struct net_rate_estimator __rcu **ptr); bool gen_estimator_read(struct net_rate_estimator __rcu **ptr, diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c index 98fd12721221..e4e442d70c2d 100644 --- a/net/core/gen_estimator.c +++ b/net/core/gen_estimator.c @@ -112,7 +112,7 @@ static void est_timer(struct timer_list *t) * @bstats: basic statistics * @cpu_bstats: bstats per cpu * @rate_est: rate estimator statistics - * @stats_lock: statistics lock + * @lock: lock for statistics and control path * @running: qdisc running seqcount * @opt: rate estimator configuration TLV * @@ -128,7 +128,7 @@ static void est_timer(struct timer_list *t) int gen_new_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_basic_cpu __percpu *cpu_bstats, struct net_rate_estimator __rcu **rate_est, - spinlock_t *stats_lock, + spinlock_t *lock, seqcount_t *running, struct nlattr *opt) { @@ -154,19 +154,22 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats, seqcount_init(&est->seq); intvl_log = parm->interval + 2; est->bstats = bstats; - est->stats_lock = stats_lock; + est->stats_lock = lock; est->running = running; est->ewma_log = parm->ewma_log; est->intvl_log = intvl_log; est->cpu_bstats = cpu_bstats; - if (stats_lock) + if (lock) local_bh_disable(); est_fetch_counters(est, &b); - if (stats_lock) + if (lock) local_bh_enable(); est->last_bytes = b.bytes; est->last_packets = b.packets; + + if (lock) + spin_lock_bh(lock); old = rcu_dereference_protected(*rate_est, 1); if (old) { del_timer_sync(&old->timer); @@ -179,6 +182,8 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats, mod_timer(&est->timer, est->next_jiffies); rcu_assign_pointer(*rate_est, est); + if (lock) + spin_unlock_bh(lock); if (old) kfree_rcu(old, rcu); return 0; @@ -209,7 +214,7 @@ EXPORT_SYMBOL(gen_kill_estimator); * @bstats: basic statistics * @cpu_bstats: bstats per cpu * @rate_est: rate estimator statistics - * @stats_lock: statistics lock + * @lock: lock for statistics and control path * @running: qdisc running seqcount (might be NULL) * @opt: rate estimator configuration TLV * @@ -221,11 +226,11 @@ EXPORT_SYMBOL(gen_kill_estimator); int gen_replace_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_basic_cpu __percpu *cpu_bstats, struct net_rate_estimator __rcu **rate_est, - spinlock_t *stats_lock, + spinlock_t *lock, seqcount_t *running, struct nlattr *opt) { return gen_new_estimator(bstats, cpu_bstats, rate_est, - stats_lock, running, opt); + lock, running, opt); } EXPORT_SYMBOL(gen_replace_estimator); -- cgit v1.2.3 From b86d865cb1cae1e61527ea0b8977078bbf694328 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Fri, 10 Aug 2018 13:28:07 -0700 Subject: blkcg: Make blkg_root_lookup() work for queues in bypass mode For legacy queues the only call of blkg_root_lookup() happens after bypass mode has been enabled. Since blkg_lookup() returns NULL for queues in bypass mode, modify the blkg_root_lookup() such that it no longer depends on bypass mode. Rename the function into blk_queue_root_blkg() as suggested by Tejun. Suggested-by: Tejun Heo Fixes: 6bad9b210a22 ("blkcg: Introduce blkg_root_lookup()") Signed-off-by: Bart Van Assche Cc: Tejun Heo Signed-off-by: Jens Axboe --- block/blk-sysfs.c | 2 +- include/linux/blk-cgroup.h | 15 +++++---------- 2 files changed, 6 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 380bc284ced1..bb109bb0a055 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -813,7 +813,7 @@ static void __blk_release_queue(struct work_struct *work) blk_exit_queue(q); } - WARN(blkg_root_lookup(q), + WARN(blk_queue_root_blkg(q), "request queue %p is being released but it has not yet been removed from the blkcg controller\n", q); diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 1361cfc9b878..34aec30e06c7 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -342,20 +342,14 @@ static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, } /** - * blkg_lookup - look up blkg for the specified request queue + * blk_queue_root_blkg - return blkg for the (blkcg_root, @q) pair * @q: request_queue of interest * * Lookup blkg for @q at the root level. See also blkg_lookup(). */ -static inline struct blkcg_gq *blkg_root_lookup(struct request_queue *q) +static inline struct blkcg_gq *blk_queue_root_blkg(struct request_queue *q) { - struct blkcg_gq *blkg; - - rcu_read_lock(); - blkg = blkg_lookup(&blkcg_root, q); - rcu_read_unlock(); - - return blkg; + return q->root_blkg; } /** @@ -881,7 +875,8 @@ static inline bool blk_cgroup_congested(void) { return false; } static inline void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay) { } static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; } -static inline struct blkcg_gq *blkg_root_lookup(struct request_queue *q) { return NULL; } +static inline struct blkcg_gq *blk_queue_root_blkg(struct request_queue *q) +{ return NULL; } static inline int blkcg_init_queue(struct request_queue *q) { return 0; } static inline void blkcg_drain_queue(struct request_queue *q) { } static inline void blkcg_exit_queue(struct request_queue *q) { } -- cgit v1.2.3 From 353c9cb360874e737fb000545f783df756c06f9a Mon Sep 17 00:00:00 2001 From: Peter Oskolkov Date: Sat, 11 Aug 2018 20:27:24 +0000 Subject: ip: add helpers to process in-order fragments faster. This patch introduces several helper functions/macros that will be used in the follow-up patch. No runtime changes yet. The new logic (fully implemented in the second patch) is as follows: * Nodes in the rb-tree will now contain not single fragments, but lists of consecutive fragments ("runs"). * At each point in time, the current "active" run at the tail is maintained/tracked. Fragments that arrive in-order, adjacent to the previous tail fragment, are added to this tail run without triggering the re-balancing of the rb-tree. * If a fragment arrives out of order with the offset _before_ the tail run, it is inserted into the rb-tree as a single fragment. * If a fragment arrives after the current tail fragment (with a gap), it starts a new "tail" run, as is inserted into the rb-tree at the end as the head of the new run. skb->cb is used to store additional information needed here (suggested by Eric Dumazet). Reported-by: Willem de Bruijn Signed-off-by: Peter Oskolkov Cc: Eric Dumazet Cc: Florian Westphal Signed-off-by: David S. Miller --- include/net/inet_frag.h | 6 ++++ net/ipv4/ip_fragment.c | 73 +++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 79 insertions(+) (limited to 'include') diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index b86d14528188..1662cbc0b46b 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -57,7 +57,9 @@ struct frag_v6_compare_key { * @lock: spinlock protecting this frag * @refcnt: reference count of the queue * @fragments: received fragments head + * @rb_fragments: received fragments rb-tree root * @fragments_tail: received fragments tail + * @last_run_head: the head of the last "run". see ip_fragment.c * @stamp: timestamp of the last received fragment * @len: total length of the original datagram * @meat: length of received fragments so far @@ -78,6 +80,7 @@ struct inet_frag_queue { struct sk_buff *fragments; /* Used in IPv6. */ struct rb_root rb_fragments; /* Used in IPv4. */ struct sk_buff *fragments_tail; + struct sk_buff *last_run_head; ktime_t stamp; int len; int meat; @@ -113,6 +116,9 @@ void inet_frag_kill(struct inet_frag_queue *q); void inet_frag_destroy(struct inet_frag_queue *q); struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key); +/* Free all skbs in the queue; return the sum of their truesizes. */ +unsigned int inet_frag_rbtree_purge(struct rb_root *root); + static inline void inet_frag_put(struct inet_frag_queue *q) { if (refcount_dec_and_test(&q->refcnt)) diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 7cb7ed761d8c..26ace9d2d976 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -57,6 +57,57 @@ */ static const char ip_frag_cache_name[] = "ip4-frags"; +/* Use skb->cb to track consecutive/adjacent fragments coming at + * the end of the queue. Nodes in the rb-tree queue will + * contain "runs" of one or more adjacent fragments. + * + * Invariants: + * - next_frag is NULL at the tail of a "run"; + * - the head of a "run" has the sum of all fragment lengths in frag_run_len. + */ +struct ipfrag_skb_cb { + struct inet_skb_parm h; + struct sk_buff *next_frag; + int frag_run_len; +}; + +#define FRAG_CB(skb) ((struct ipfrag_skb_cb *)((skb)->cb)) + +static void ip4_frag_init_run(struct sk_buff *skb) +{ + BUILD_BUG_ON(sizeof(struct ipfrag_skb_cb) > sizeof(skb->cb)); + + FRAG_CB(skb)->next_frag = NULL; + FRAG_CB(skb)->frag_run_len = skb->len; +} + +/* Append skb to the last "run". */ +static void ip4_frag_append_to_last_run(struct inet_frag_queue *q, + struct sk_buff *skb) +{ + RB_CLEAR_NODE(&skb->rbnode); + FRAG_CB(skb)->next_frag = NULL; + + FRAG_CB(q->last_run_head)->frag_run_len += skb->len; + FRAG_CB(q->fragments_tail)->next_frag = skb; + q->fragments_tail = skb; +} + +/* Create a new "run" with the skb. */ +static void ip4_frag_create_run(struct inet_frag_queue *q, struct sk_buff *skb) +{ + if (q->last_run_head) + rb_link_node(&skb->rbnode, &q->last_run_head->rbnode, + &q->last_run_head->rbnode.rb_right); + else + rb_link_node(&skb->rbnode, NULL, &q->rb_fragments.rb_node); + rb_insert_color(&skb->rbnode, &q->rb_fragments); + + ip4_frag_init_run(skb); + q->fragments_tail = skb; + q->last_run_head = skb; +} + /* Describe an entry in the "incomplete datagrams" queue. */ struct ipq { struct inet_frag_queue q; @@ -654,6 +705,28 @@ struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user) } EXPORT_SYMBOL(ip_check_defrag); +unsigned int inet_frag_rbtree_purge(struct rb_root *root) +{ + struct rb_node *p = rb_first(root); + unsigned int sum = 0; + + while (p) { + struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode); + + p = rb_next(p); + rb_erase(&skb->rbnode, root); + while (skb) { + struct sk_buff *next = FRAG_CB(skb)->next_frag; + + sum += skb->truesize; + kfree_skb(skb); + skb = next; + } + } + return sum; +} +EXPORT_SYMBOL(inet_frag_rbtree_purge); + #ifdef CONFIG_SYSCTL static int dist_min; -- cgit v1.2.3 From e8d2bec0457962e8f348a9a3627b398f7fe5c5fc Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 12 Aug 2018 01:59:17 +0200 Subject: bpf: decouple btf from seq bpf fs dump and enable more maps Commit a26ca7c982cb ("bpf: btf: Add pretty print support to the basic arraymap") and 699c86d6ec21 ("bpf: btf: add pretty print for hash/lru_hash maps") enabled support for BTF and dumping via BPF fs for array and hash/lru map. However, both can be decoupled from each other such that regular BPF maps can be supported for attaching BTF key/value information, while not all maps necessarily need to dump via map_seq_show_elem() callback. The basic sanity check which is a prerequisite for all maps is that key/value size has to match in any case, and some maps can have extra checks via map_check_btf() callback, e.g. probing certain types or indicating no support in general. With that we can also enable retrieving BTF info for per-cpu map types and lpm. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Acked-by: Yonghong Song --- include/linux/bpf.h | 13 +++++++++---- kernel/bpf/arraymap.c | 26 ++++++++++++-------------- kernel/bpf/cpumap.c | 1 + kernel/bpf/devmap.c | 1 + kernel/bpf/hashtab.c | 20 +------------------- kernel/bpf/inode.c | 3 ++- kernel/bpf/local_storage.c | 1 + kernel/bpf/lpm_trie.c | 12 ++++++++++++ kernel/bpf/sockmap.c | 2 ++ kernel/bpf/stackmap.c | 1 + kernel/bpf/syscall.c | 36 ++++++++++++++++++++++++++++++++---- kernel/bpf/xskmap.c | 3 +-- 12 files changed, 75 insertions(+), 44 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index db11662faea6..523481a3471b 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -23,7 +23,7 @@ struct bpf_prog; struct bpf_map; struct sock; struct seq_file; -struct btf; +struct btf_type; /* map is generic key/value storage optionally accesible by eBPF programs */ struct bpf_map_ops { @@ -48,8 +48,9 @@ struct bpf_map_ops { u32 (*map_fd_sys_lookup_elem)(void *ptr); void (*map_seq_show_elem)(struct bpf_map *map, void *key, struct seq_file *m); - int (*map_check_btf)(const struct bpf_map *map, const struct btf *btf, - u32 key_type_id, u32 value_type_id); + int (*map_check_btf)(const struct bpf_map *map, + const struct btf_type *key_type, + const struct btf_type *value_type); }; struct bpf_map { @@ -118,9 +119,13 @@ static inline bool bpf_map_offload_neutral(const struct bpf_map *map) static inline bool bpf_map_support_seq_show(const struct bpf_map *map) { - return map->ops->map_seq_show_elem && map->ops->map_check_btf; + return map->btf && map->ops->map_seq_show_elem; } +int map_check_no_btf(const struct bpf_map *map, + const struct btf_type *key_type, + const struct btf_type *value_type); + extern const struct bpf_map_ops bpf_map_offload_ops; /* function argument constraints */ diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index f6ca3e712831..0c17aab3ce5f 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -358,27 +358,20 @@ static void array_map_seq_show_elem(struct bpf_map *map, void *key, rcu_read_unlock(); } -static int array_map_check_btf(const struct bpf_map *map, const struct btf *btf, - u32 btf_key_id, u32 btf_value_id) +static int array_map_check_btf(const struct bpf_map *map, + const struct btf_type *key_type, + const struct btf_type *value_type) { - const struct btf_type *key_type, *value_type; - u32 key_size, value_size; u32 int_data; - key_type = btf_type_id_size(btf, &btf_key_id, &key_size); - if (!key_type || BTF_INFO_KIND(key_type->info) != BTF_KIND_INT) + if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT) return -EINVAL; int_data = *(u32 *)(key_type + 1); - /* bpf array can only take a u32 key. This check makes - * sure that the btf matches the attr used during map_create. + /* bpf array can only take a u32 key. This check makes sure + * that the btf matches the attr used during map_create. */ - if (BTF_INT_BITS(int_data) != 32 || key_size != 4 || - BTF_INT_OFFSET(int_data)) - return -EINVAL; - - value_type = btf_type_id_size(btf, &btf_value_id, &value_size); - if (!value_type || value_size != map->value_size) + if (BTF_INT_BITS(int_data) != 32 || BTF_INT_OFFSET(int_data)) return -EINVAL; return 0; @@ -405,6 +398,7 @@ const struct bpf_map_ops percpu_array_map_ops = { .map_lookup_elem = percpu_array_map_lookup_elem, .map_update_elem = array_map_update_elem, .map_delete_elem = array_map_delete_elem, + .map_check_btf = array_map_check_btf, }; static int fd_array_map_alloc_check(union bpf_attr *attr) @@ -546,6 +540,7 @@ const struct bpf_map_ops prog_array_map_ops = { .map_fd_put_ptr = prog_fd_array_put_ptr, .map_fd_sys_lookup_elem = prog_fd_array_sys_lookup_elem, .map_release_uref = bpf_fd_array_map_clear, + .map_check_btf = map_check_no_btf, }; static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file, @@ -634,6 +629,7 @@ const struct bpf_map_ops perf_event_array_map_ops = { .map_fd_get_ptr = perf_event_fd_array_get_ptr, .map_fd_put_ptr = perf_event_fd_array_put_ptr, .map_release = perf_event_fd_array_release, + .map_check_btf = map_check_no_btf, }; #ifdef CONFIG_CGROUPS @@ -665,6 +661,7 @@ const struct bpf_map_ops cgroup_array_map_ops = { .map_delete_elem = fd_array_map_delete_elem, .map_fd_get_ptr = cgroup_fd_array_get_ptr, .map_fd_put_ptr = cgroup_fd_array_put_ptr, + .map_check_btf = map_check_no_btf, }; #endif @@ -749,4 +746,5 @@ const struct bpf_map_ops array_of_maps_map_ops = { .map_fd_put_ptr = bpf_map_fd_put_ptr, .map_fd_sys_lookup_elem = bpf_map_fd_sys_lookup_elem, .map_gen_lookup = array_of_map_gen_lookup, + .map_check_btf = map_check_no_btf, }; diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index e0918d180f08..3b494941a44a 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -555,6 +555,7 @@ const struct bpf_map_ops cpu_map_ops = { .map_update_elem = cpu_map_update_elem, .map_lookup_elem = cpu_map_lookup_elem, .map_get_next_key = cpu_map_get_next_key, + .map_check_btf = map_check_no_btf, }; static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu, diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index d361fc1e3bf3..a7c6620d8389 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -484,6 +484,7 @@ const struct bpf_map_ops dev_map_ops = { .map_lookup_elem = dev_map_lookup_elem, .map_update_elem = dev_map_update_elem, .map_delete_elem = dev_map_delete_elem, + .map_check_btf = map_check_no_btf, }; static int dev_map_notification(struct notifier_block *notifier, diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index d6110042e0d9..04b8eda94e7d 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -1185,23 +1185,6 @@ static void htab_map_seq_show_elem(struct bpf_map *map, void *key, rcu_read_unlock(); } -static int htab_map_check_btf(const struct bpf_map *map, const struct btf *btf, - u32 btf_key_id, u32 btf_value_id) -{ - const struct btf_type *key_type, *value_type; - u32 key_size, value_size; - - key_type = btf_type_id_size(btf, &btf_key_id, &key_size); - if (!key_type || key_size != map->key_size) - return -EINVAL; - - value_type = btf_type_id_size(btf, &btf_value_id, &value_size); - if (!value_type || value_size != map->value_size) - return -EINVAL; - - return 0; -} - const struct bpf_map_ops htab_map_ops = { .map_alloc_check = htab_map_alloc_check, .map_alloc = htab_map_alloc, @@ -1212,7 +1195,6 @@ const struct bpf_map_ops htab_map_ops = { .map_delete_elem = htab_map_delete_elem, .map_gen_lookup = htab_map_gen_lookup, .map_seq_show_elem = htab_map_seq_show_elem, - .map_check_btf = htab_map_check_btf, }; const struct bpf_map_ops htab_lru_map_ops = { @@ -1225,7 +1207,6 @@ const struct bpf_map_ops htab_lru_map_ops = { .map_delete_elem = htab_lru_map_delete_elem, .map_gen_lookup = htab_lru_map_gen_lookup, .map_seq_show_elem = htab_map_seq_show_elem, - .map_check_btf = htab_map_check_btf, }; /* Called from eBPF program */ @@ -1452,4 +1433,5 @@ const struct bpf_map_ops htab_of_maps_map_ops = { .map_fd_put_ptr = bpf_map_fd_put_ptr, .map_fd_sys_lookup_elem = bpf_map_fd_sys_lookup_elem, .map_gen_lookup = htab_of_map_gen_lookup, + .map_check_btf = map_check_no_btf, }; diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index fc5b103512e7..2ada5e21dfa6 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -334,7 +334,8 @@ static int bpf_mkmap(struct dentry *dentry, umode_t mode, void *arg) struct bpf_map *map = arg; return bpf_mkobj_ops(dentry, mode, arg, &bpf_map_iops, - map->btf ? &bpffs_map_fops : &bpffs_obj_fops); + bpf_map_support_seq_show(map) ? + &bpffs_map_fops : &bpffs_obj_fops); } static struct dentry * diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index fc4e37f68f2a..22ad967d1e5f 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -246,6 +246,7 @@ const struct bpf_map_ops cgroup_storage_map_ops = { .map_lookup_elem = cgroup_storage_lookup_elem, .map_update_elem = cgroup_storage_update_elem, .map_delete_elem = cgroup_storage_delete_elem, + .map_check_btf = map_check_no_btf, }; int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *_map) diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index 1603492c9cc7..9058317ba9de 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -10,11 +10,13 @@ */ #include +#include #include #include #include #include #include +#include /* Intermediate node */ #define LPM_TREE_NODE_FLAG_IM BIT(0) @@ -686,6 +688,15 @@ free_stack: return err; } +static int trie_check_btf(const struct bpf_map *map, + const struct btf_type *key_type, + const struct btf_type *value_type) +{ + /* Keys must have struct bpf_lpm_trie_key embedded. */ + return BTF_INFO_KIND(key_type->info) != BTF_KIND_STRUCT ? + -EINVAL : 0; +} + const struct bpf_map_ops trie_map_ops = { .map_alloc = trie_alloc, .map_free = trie_free, @@ -693,4 +704,5 @@ const struct bpf_map_ops trie_map_ops = { .map_lookup_elem = trie_lookup_elem, .map_update_elem = trie_update_elem, .map_delete_elem = trie_delete_elem, + .map_check_btf = trie_check_btf, }; diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 0b38be5a955c..e376ffffebce 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -2495,6 +2495,7 @@ const struct bpf_map_ops sock_map_ops = { .map_update_elem = sock_map_update_elem, .map_delete_elem = sock_map_delete_elem, .map_release_uref = sock_map_release, + .map_check_btf = map_check_no_btf, }; const struct bpf_map_ops sock_hash_ops = { @@ -2505,6 +2506,7 @@ const struct bpf_map_ops sock_hash_ops = { .map_update_elem = sock_hash_update_elem, .map_delete_elem = sock_hash_delete_elem, .map_release_uref = sock_map_release, + .map_check_btf = map_check_no_btf, }; BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock, diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index b675a3f3d141..8061a439ef18 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -607,6 +607,7 @@ const struct bpf_map_ops stack_map_ops = { .map_lookup_elem = stack_map_lookup_elem, .map_update_elem = stack_map_update_elem, .map_delete_elem = stack_map_delete_elem, + .map_check_btf = map_check_no_btf, }; static int __init stack_map_init(void) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 57f4d076141b..43727ed0d94a 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -103,6 +103,7 @@ int bpf_check_uarg_tail_zero(void __user *uaddr, const struct bpf_map_ops bpf_map_offload_ops = { .map_alloc = bpf_map_offload_map_alloc, .map_free = bpf_map_offload_map_free, + .map_check_btf = map_check_no_btf, }; static struct bpf_map *find_and_alloc_map(union bpf_attr *attr) @@ -455,6 +456,34 @@ static int bpf_obj_name_cpy(char *dst, const char *src) return 0; } +int map_check_no_btf(const struct bpf_map *map, + const struct btf_type *key_type, + const struct btf_type *value_type) +{ + return -ENOTSUPP; +} + +static int map_check_btf(const struct bpf_map *map, const struct btf *btf, + u32 btf_key_id, u32 btf_value_id) +{ + const struct btf_type *key_type, *value_type; + u32 key_size, value_size; + int ret = 0; + + key_type = btf_type_id_size(btf, &btf_key_id, &key_size); + if (!key_type || key_size != map->key_size) + return -EINVAL; + + value_type = btf_type_id_size(btf, &btf_value_id, &value_size); + if (!value_type || value_size != map->value_size) + return -EINVAL; + + if (map->ops->map_check_btf) + ret = map->ops->map_check_btf(map, key_type, value_type); + + return ret; +} + #define BPF_MAP_CREATE_LAST_FIELD btf_value_type_id /* called via syscall */ static int map_create(union bpf_attr *attr) @@ -489,8 +518,7 @@ static int map_create(union bpf_attr *attr) atomic_set(&map->refcnt, 1); atomic_set(&map->usercnt, 1); - if (bpf_map_support_seq_show(map) && - (attr->btf_key_type_id || attr->btf_value_type_id)) { + if (attr->btf_key_type_id || attr->btf_value_type_id) { struct btf *btf; if (!attr->btf_key_type_id || !attr->btf_value_type_id) { @@ -504,8 +532,8 @@ static int map_create(union bpf_attr *attr) goto free_map_nouncharge; } - err = map->ops->map_check_btf(map, btf, attr->btf_key_type_id, - attr->btf_value_type_id); + err = map_check_btf(map, btf, attr->btf_key_type_id, + attr->btf_value_type_id); if (err) { btf_put(btf); goto free_map_nouncharge; diff --git a/kernel/bpf/xskmap.c b/kernel/bpf/xskmap.c index b3c557476a8d..4ddf61e158f6 100644 --- a/kernel/bpf/xskmap.c +++ b/kernel/bpf/xskmap.c @@ -227,6 +227,5 @@ const struct bpf_map_ops xsk_map_ops = { .map_lookup_elem = xsk_map_lookup_elem, .map_update_elem = xsk_map_update_elem, .map_delete_elem = xsk_map_delete_elem, + .map_check_btf = map_check_no_btf, }; - - -- cgit v1.2.3 From 7723628101aaeb1d723786747529b4ea65c5b5c5 Mon Sep 17 00:00:00 2001 From: Andrey Ignatov Date: Sun, 12 Aug 2018 10:49:27 -0700 Subject: bpf: Introduce bpf_skb_ancestor_cgroup_id helper == Problem description == It's useful to be able to identify cgroup associated with skb in TC so that a policy can be applied to this skb, and existing bpf_skb_cgroup_id helper can help with this. Though in real life cgroup hierarchy and hierarchy to apply a policy to don't map 1:1. It's often the case that there is a container and corresponding cgroup, but there are many more sub-cgroups inside container, e.g. because it's delegated to containerized application to control resources for its subsystems, or to separate application inside container from infra that belongs to containerization system (e.g. sshd). At the same time it may be useful to apply a policy to container as a whole. If multiple containers like this are run on a host (what is often the case) and many of them have sub-cgroups, it may not be possible to apply per-container policy in TC with existing helpers such as bpf_skb_under_cgroup or bpf_skb_cgroup_id: * bpf_skb_cgroup_id will return id of immediate cgroup associated with skb, i.e. if it's a sub-cgroup inside container, it can't be used to identify container's cgroup; * bpf_skb_under_cgroup can work only with one cgroup and doesn't scale, i.e. if there are N containers on a host and a policy has to be applied to M of them (0 <= M <= N), it'd require M calls to bpf_skb_under_cgroup, and, if M changes, it'd require to rebuild & load new BPF program. == Solution == The patch introduces new helper bpf_skb_ancestor_cgroup_id that can be used to get id of cgroup v2 that is an ancestor of cgroup associated with skb at specified level of cgroup hierarchy. That way admin can place all containers on one level of cgroup hierarchy (what is a good practice in general and already used in many configurations) and identify specific cgroup on this level no matter what sub-cgroup skb is associated with. E.g. if there is a cgroup hierarchy: root/ root/container1/ root/container1/app11/ root/container1/app11/sub-app-a/ root/container1/app12/ root/container2/ root/container2/app21/ root/container2/app22/ root/container2/app22/sub-app-b/ , then having skb associated with root/container1/app11/sub-app-a/ it's possible to get ancestor at level 1, what is container1 and apply policy for this container, or apply another policy if it's container2. Policies can be kept e.g. in a hash map where key is a container cgroup id and value is an action. Levels where container cgroups are created are usually known in advance whether cgroup hierarchy inside container may be hard to predict especially in case when its creation is delegated to containerized application. == Implementation details == The helper gets ancestor by walking parents up to specified level. Another option would be to get different kind of "id" from cgroup->ancestor_ids[level] and use it with idr_find() to get struct cgroup for ancestor. But that would require radix lookup what doesn't seem to be better (at least it's not obviously better). Format of return value of the new helper is same as that of bpf_skb_cgroup_id. Signed-off-by: Andrey Ignatov Signed-off-by: Daniel Borkmann --- include/linux/cgroup.h | 30 ++++++++++++++++++++++++++++++ include/uapi/linux/bpf.h | 21 ++++++++++++++++++++- net/core/filter.c | 28 ++++++++++++++++++++++++++++ 3 files changed, 78 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index c9fdf6f57913..32c553556bbd 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -553,6 +553,36 @@ static inline bool cgroup_is_descendant(struct cgroup *cgrp, return cgrp->ancestor_ids[ancestor->level] == ancestor->id; } +/** + * cgroup_ancestor - find ancestor of cgroup + * @cgrp: cgroup to find ancestor of + * @ancestor_level: level of ancestor to find starting from root + * + * Find ancestor of cgroup at specified level starting from root if it exists + * and return pointer to it. Return NULL if @cgrp doesn't have ancestor at + * @ancestor_level. + * + * This function is safe to call as long as @cgrp is accessible. + */ +static inline struct cgroup *cgroup_ancestor(struct cgroup *cgrp, + int ancestor_level) +{ + struct cgroup *ptr; + + if (cgrp->level < ancestor_level) + return NULL; + + for (ptr = cgrp; + ptr && ptr->level > ancestor_level; + ptr = cgroup_parent(ptr)) + ; + + if (ptr && ptr->level == ancestor_level) + return ptr; + + return NULL; +} + /** * task_under_cgroup_hierarchy - test task's membership of cgroup ancestry * @task: the task to be tested diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 3102a2a23c31..66917a4eba27 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2093,6 +2093,24 @@ union bpf_attr { * Return * The id is returned or 0 in case the id could not be retrieved. * + * u64 bpf_skb_ancestor_cgroup_id(struct sk_buff *skb, int ancestor_level) + * Description + * Return id of cgroup v2 that is ancestor of cgroup associated + * with the *skb* at the *ancestor_level*. The root cgroup is at + * *ancestor_level* zero and each step down the hierarchy + * increments the level. If *ancestor_level* == level of cgroup + * associated with *skb*, then return value will be same as that + * of **bpf_skb_cgroup_id**\ (). + * + * The helper is useful to implement policies based on cgroups + * that are upper in hierarchy than immediate cgroup associated + * with *skb*. + * + * The format of returned id and helper limitations are same as in + * **bpf_skb_cgroup_id**\ (). + * Return + * The id is returned or 0 in case the id could not be retrieved. + * * u64 bpf_get_current_cgroup_id(void) * Return * A 64-bit integer containing the current cgroup id based @@ -2207,7 +2225,8 @@ union bpf_attr { FN(skb_cgroup_id), \ FN(get_current_cgroup_id), \ FN(get_local_storage), \ - FN(sk_select_reuseport), + FN(sk_select_reuseport), \ + FN(skb_ancestor_cgroup_id), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call diff --git a/net/core/filter.c b/net/core/filter.c index 22906b31d43f..15b9d2df92ca 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3778,6 +3778,32 @@ static const struct bpf_func_proto bpf_skb_cgroup_id_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; + +BPF_CALL_2(bpf_skb_ancestor_cgroup_id, const struct sk_buff *, skb, int, + ancestor_level) +{ + struct sock *sk = skb_to_full_sk(skb); + struct cgroup *ancestor; + struct cgroup *cgrp; + + if (!sk || !sk_fullsock(sk)) + return 0; + + cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); + ancestor = cgroup_ancestor(cgrp, ancestor_level); + if (!ancestor) + return 0; + + return ancestor->kn->id.id; +} + +static const struct bpf_func_proto bpf_skb_ancestor_cgroup_id_proto = { + .func = bpf_skb_ancestor_cgroup_id, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, +}; #endif static unsigned long bpf_xdp_copy(void *dst_buff, const void *src_buff, @@ -4966,6 +4992,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) #ifdef CONFIG_SOCK_CGROUP_DATA case BPF_FUNC_skb_cgroup_id: return &bpf_skb_cgroup_id_proto; + case BPF_FUNC_skb_ancestor_cgroup_id: + return &bpf_skb_ancestor_cgroup_id_proto; #endif default: return bpf_base_func_proto(func_id); -- cgit v1.2.3 From 0b243d004ea640875115d1500ec429a3e9f9fae9 Mon Sep 17 00:00:00 2001 From: Vakul Garg Date: Fri, 10 Aug 2018 20:46:41 +0530 Subject: net/tls: Combined memory allocation for decryption request For preparing decryption request, several memory chunks are required (aead_req, sgin, sgout, iv, aad). For submitting the decrypt request to an accelerator, it is required that the buffers which are read by the accelerator must be dma-able and not come from stack. The buffers for aad and iv can be separately kmalloced each, but it is inefficient. This patch does a combined allocation for preparing decryption request and then segments into aead_req || sgin || sgout || iv || aad. Signed-off-by: Vakul Garg Signed-off-by: David S. Miller --- include/net/tls.h | 4 - net/tls/tls_sw.c | 238 ++++++++++++++++++++++++++++++++---------------------- 2 files changed, 142 insertions(+), 100 deletions(-) (limited to 'include') diff --git a/include/net/tls.h b/include/net/tls.h index d8b3b6578c01..d5c683e8bb22 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -124,10 +124,6 @@ struct tls_sw_context_rx { struct sk_buff *recv_pkt; u8 control; bool decrypted; - - char rx_aad_ciphertext[TLS_AAD_SPACE_SIZE]; - char rx_aad_plaintext[TLS_AAD_SPACE_SIZE]; - }; struct tls_record_info { diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 83d67df33f0c..52fbe727d7c1 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -48,19 +48,13 @@ static int tls_do_decryption(struct sock *sk, struct scatterlist *sgout, char *iv_recv, size_t data_len, - struct sk_buff *skb, - gfp_t flags) + struct aead_request *aead_req) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); - struct aead_request *aead_req; - int ret; - aead_req = aead_request_alloc(ctx->aead_recv, flags); - if (!aead_req) - return -ENOMEM; - + aead_request_set_tfm(aead_req, ctx->aead_recv); aead_request_set_ad(aead_req, TLS_AAD_SPACE_SIZE); aead_request_set_crypt(aead_req, sgin, sgout, data_len + tls_ctx->rx.tag_size, @@ -69,8 +63,6 @@ static int tls_do_decryption(struct sock *sk, crypto_req_done, &ctx->async_wait); ret = crypto_wait_req(crypto_aead_decrypt(aead_req), &ctx->async_wait); - - aead_request_free(aead_req); return ret; } @@ -657,8 +649,132 @@ static struct sk_buff *tls_wait_data(struct sock *sk, int flags, return skb; } +/* This function decrypts the input skb into either out_iov or in out_sg + * or in skb buffers itself. The input parameter 'zc' indicates if + * zero-copy mode needs to be tried or not. With zero-copy mode, either + * out_iov or out_sg must be non-NULL. In case both out_iov and out_sg are + * NULL, then the decryption happens inside skb buffers itself, i.e. + * zero-copy gets disabled and 'zc' is updated. + */ + +static int decrypt_internal(struct sock *sk, struct sk_buff *skb, + struct iov_iter *out_iov, + struct scatterlist *out_sg, + int *chunk, bool *zc) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); + struct strp_msg *rxm = strp_msg(skb); + int n_sgin, n_sgout, nsg, mem_size, aead_size, err, pages = 0; + struct aead_request *aead_req; + struct sk_buff *unused; + u8 *aad, *iv, *mem = NULL; + struct scatterlist *sgin = NULL; + struct scatterlist *sgout = NULL; + const int data_len = rxm->full_len - tls_ctx->rx.overhead_size; + + if (*zc && (out_iov || out_sg)) { + if (out_iov) + n_sgout = iov_iter_npages(out_iov, INT_MAX) + 1; + else + n_sgout = sg_nents(out_sg); + } else { + n_sgout = 0; + *zc = false; + } + + n_sgin = skb_cow_data(skb, 0, &unused); + if (n_sgin < 1) + return -EBADMSG; + + /* Increment to accommodate AAD */ + n_sgin = n_sgin + 1; + + nsg = n_sgin + n_sgout; + + aead_size = sizeof(*aead_req) + crypto_aead_reqsize(ctx->aead_recv); + mem_size = aead_size + (nsg * sizeof(struct scatterlist)); + mem_size = mem_size + TLS_AAD_SPACE_SIZE; + mem_size = mem_size + crypto_aead_ivsize(ctx->aead_recv); + + /* Allocate a single block of memory which contains + * aead_req || sgin[] || sgout[] || aad || iv. + * This order achieves correct alignment for aead_req, sgin, sgout. + */ + mem = kmalloc(mem_size, sk->sk_allocation); + if (!mem) + return -ENOMEM; + + /* Segment the allocated memory */ + aead_req = (struct aead_request *)mem; + sgin = (struct scatterlist *)(mem + aead_size); + sgout = sgin + n_sgin; + aad = (u8 *)(sgout + n_sgout); + iv = aad + TLS_AAD_SPACE_SIZE; + + /* Prepare IV */ + err = skb_copy_bits(skb, rxm->offset + TLS_HEADER_SIZE, + iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, + tls_ctx->rx.iv_size); + if (err < 0) { + kfree(mem); + return err; + } + memcpy(iv, tls_ctx->rx.iv, TLS_CIPHER_AES_GCM_128_SALT_SIZE); + + /* Prepare AAD */ + tls_make_aad(aad, rxm->full_len - tls_ctx->rx.overhead_size, + tls_ctx->rx.rec_seq, tls_ctx->rx.rec_seq_size, + ctx->control); + + /* Prepare sgin */ + sg_init_table(sgin, n_sgin); + sg_set_buf(&sgin[0], aad, TLS_AAD_SPACE_SIZE); + err = skb_to_sgvec(skb, &sgin[1], + rxm->offset + tls_ctx->rx.prepend_size, + rxm->full_len - tls_ctx->rx.prepend_size); + if (err < 0) { + kfree(mem); + return err; + } + + if (n_sgout) { + if (out_iov) { + sg_init_table(sgout, n_sgout); + sg_set_buf(&sgout[0], aad, TLS_AAD_SPACE_SIZE); + + *chunk = 0; + err = zerocopy_from_iter(sk, out_iov, data_len, &pages, + chunk, &sgout[1], + (n_sgout - 1), false); + if (err < 0) + goto fallback_to_reg_recv; + } else if (out_sg) { + memcpy(sgout, out_sg, n_sgout * sizeof(*sgout)); + } else { + goto fallback_to_reg_recv; + } + } else { +fallback_to_reg_recv: + sgout = sgin; + pages = 0; + *chunk = 0; + *zc = false; + } + + /* Prepare and submit AEAD request */ + err = tls_do_decryption(sk, sgin, sgout, iv, data_len, aead_req); + + /* Release the pages in case iov was mapped to pages */ + for (; pages > 0; pages--) + put_page(sg_page(&sgout[pages])); + + kfree(mem); + return err; +} + static int decrypt_skb_update(struct sock *sk, struct sk_buff *skb, - struct scatterlist *sgout, bool *zc) + struct iov_iter *dest, int *chunk, bool *zc) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); @@ -671,7 +787,7 @@ static int decrypt_skb_update(struct sock *sk, struct sk_buff *skb, return err; #endif if (!ctx->decrypted) { - err = decrypt_skb(sk, skb, sgout); + err = decrypt_internal(sk, skb, dest, NULL, chunk, zc); if (err < 0) return err; } else { @@ -690,54 +806,10 @@ static int decrypt_skb_update(struct sock *sk, struct sk_buff *skb, int decrypt_skb(struct sock *sk, struct sk_buff *skb, struct scatterlist *sgout) { - struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); - char iv[TLS_CIPHER_AES_GCM_128_SALT_SIZE + MAX_IV_SIZE]; - struct scatterlist sgin_arr[MAX_SKB_FRAGS + 2]; - struct scatterlist *sgin = &sgin_arr[0]; - struct strp_msg *rxm = strp_msg(skb); - int ret, nsg = ARRAY_SIZE(sgin_arr); - struct sk_buff *unused; - - ret = skb_copy_bits(skb, rxm->offset + TLS_HEADER_SIZE, - iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, - tls_ctx->rx.iv_size); - if (ret < 0) - return ret; - - memcpy(iv, tls_ctx->rx.iv, TLS_CIPHER_AES_GCM_128_SALT_SIZE); - if (!sgout) { - nsg = skb_cow_data(skb, 0, &unused) + 1; - sgin = kmalloc_array(nsg, sizeof(*sgin), sk->sk_allocation); - sgout = sgin; - } - - sg_init_table(sgin, nsg); - sg_set_buf(&sgin[0], ctx->rx_aad_ciphertext, TLS_AAD_SPACE_SIZE); - - nsg = skb_to_sgvec(skb, &sgin[1], - rxm->offset + tls_ctx->rx.prepend_size, - rxm->full_len - tls_ctx->rx.prepend_size); - if (nsg < 0) { - ret = nsg; - goto out; - } - - tls_make_aad(ctx->rx_aad_ciphertext, - rxm->full_len - tls_ctx->rx.overhead_size, - tls_ctx->rx.rec_seq, - tls_ctx->rx.rec_seq_size, - ctx->control); - - ret = tls_do_decryption(sk, sgin, sgout, iv, - rxm->full_len - tls_ctx->rx.overhead_size, - skb, sk->sk_allocation); - -out: - if (sgin != &sgin_arr[0]) - kfree(sgin); + bool zc = true; + int chunk; - return ret; + return decrypt_internal(sk, skb, NULL, sgout, &chunk, &zc); } static bool tls_sw_advance_skb(struct sock *sk, struct sk_buff *skb, @@ -816,43 +888,17 @@ int tls_sw_recvmsg(struct sock *sk, } if (!ctx->decrypted) { - int page_count; - int to_copy; - - page_count = iov_iter_npages(&msg->msg_iter, - MAX_SKB_FRAGS); - to_copy = rxm->full_len - tls_ctx->rx.overhead_size; - if (!is_kvec && to_copy <= len && page_count < MAX_SKB_FRAGS && - likely(!(flags & MSG_PEEK))) { - struct scatterlist sgin[MAX_SKB_FRAGS + 1]; - int pages = 0; + int to_copy = rxm->full_len - tls_ctx->rx.overhead_size; + if (!is_kvec && to_copy <= len && + likely(!(flags & MSG_PEEK))) zc = true; - sg_init_table(sgin, MAX_SKB_FRAGS + 1); - sg_set_buf(&sgin[0], ctx->rx_aad_plaintext, - TLS_AAD_SPACE_SIZE); - - err = zerocopy_from_iter(sk, &msg->msg_iter, - to_copy, &pages, - &chunk, &sgin[1], - MAX_SKB_FRAGS, false); - if (err < 0) - goto fallback_to_reg_recv; - - err = decrypt_skb_update(sk, skb, sgin, &zc); - for (; pages > 0; pages--) - put_page(sg_page(&sgin[pages])); - if (err < 0) { - tls_err_abort(sk, EBADMSG); - goto recv_end; - } - } else { -fallback_to_reg_recv: - err = decrypt_skb_update(sk, skb, NULL, &zc); - if (err < 0) { - tls_err_abort(sk, EBADMSG); - goto recv_end; - } + + err = decrypt_skb_update(sk, skb, &msg->msg_iter, + &chunk, &zc); + if (err < 0) { + tls_err_abort(sk, EBADMSG); + goto recv_end; } ctx->decrypted = true; } @@ -903,7 +949,7 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, int err = 0; long timeo; int chunk; - bool zc; + bool zc = false; lock_sock(sk); @@ -920,7 +966,7 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, } if (!ctx->decrypted) { - err = decrypt_skb_update(sk, skb, NULL, &zc); + err = decrypt_skb_update(sk, skb, NULL, &chunk, &zc); if (err < 0) { tls_err_abort(sk, EBADMSG); -- cgit v1.2.3 From e6f86b0f7ae473969a3301b74bf98af9e42ecd0e Mon Sep 17 00:00:00 2001 From: Virgile Jarry Date: Fri, 10 Aug 2018 17:48:15 +0200 Subject: ipv6: Add icmp_echo_ignore_all support for ICMPv6 Preventing the kernel from responding to ICMP Echo Requests messages can be useful in several ways. The sysctl parameter 'icmp_echo_ignore_all' can be used to prevent the kernel from responding to IPv4 ICMP echo requests. For IPv6 pings, such a sysctl kernel parameter did not exist. Add the ability to prevent the kernel from responding to IPv6 ICMP echo requests through the use of the following sysctl parameter : /proc/sys/net/ipv6/icmp/echo_ignore_all. Update the documentation to reflect this change. Signed-off-by: Virgile Jarry Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.txt | 5 +++++ include/net/netns/ipv6.h | 1 + include/uapi/linux/sysctl.h | 3 ++- net/ipv6/af_inet6.c | 1 + net/ipv6/icmp.c | 16 +++++++++++++--- 5 files changed, 22 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index e74515ecaa9c..8313a636dd53 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -1882,6 +1882,11 @@ ratelimit - INTEGER otherwise the minimal space between responses in milliseconds. Default: 1000 +echo_ignore_all - BOOLEAN + If set non-zero, then the kernel will ignore all ICMP ECHO + requests sent to it over the IPv6 protocol. + Default: 0 + xfrm6_gc_thresh - INTEGER The threshold at which we will start garbage collecting for IPv6 destination cache entries. At twice this value the system will diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 762ac9931b62..f0e396ab9bec 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -32,6 +32,7 @@ struct netns_sysctl_ipv6 { int flowlabel_consistency; int auto_flowlabels; int icmpv6_time; + int icmpv6_echo_ignore_all; int anycast_src_echo_reply; int ip_nonlocal_bind; int fwmark_reflect; diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h index 6b58371b1f0d..d71013fffaf6 100644 --- a/include/uapi/linux/sysctl.h +++ b/include/uapi/linux/sysctl.h @@ -575,7 +575,8 @@ enum { /* /proc/sys/net/ipv6/icmp */ enum { - NET_IPV6_ICMP_RATELIMIT=1 + NET_IPV6_ICMP_RATELIMIT = 1, + NET_IPV6_ICMP_ECHO_IGNORE_ALL = 2 }; /* /proc/sys/net//neigh/ */ diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 020f6e14a7af..673bba31eb18 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -832,6 +832,7 @@ static int __net_init inet6_net_init(struct net *net) net->ipv6.sysctl.bindv6only = 0; net->ipv6.sysctl.icmpv6_time = 1*HZ; + net->ipv6.sysctl.icmpv6_echo_ignore_all = 0; net->ipv6.sysctl.flowlabel_consistency = 1; net->ipv6.sysctl.auto_flowlabels = IP6_DEFAULT_AUTO_FLOW_LABELS; net->ipv6.sysctl.idgen_retries = 3; diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 7f6b1f81c200..c9c53ade55c3 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -794,6 +794,7 @@ out: static int icmpv6_rcv(struct sk_buff *skb) { + struct net *net = dev_net(skb->dev); struct net_device *dev = skb->dev; struct inet6_dev *idev = __in6_dev_get(dev); const struct in6_addr *saddr, *daddr; @@ -843,7 +844,8 @@ static int icmpv6_rcv(struct sk_buff *skb) switch (type) { case ICMPV6_ECHO_REQUEST: - icmpv6_echo_reply(skb); + if (!net->ipv6.sysctl.icmpv6_echo_ignore_all) + icmpv6_echo_reply(skb); break; case ICMPV6_ECHO_REPLY: @@ -1104,6 +1106,13 @@ static struct ctl_table ipv6_icmp_table_template[] = { .mode = 0644, .proc_handler = proc_dointvec_ms_jiffies, }, + { + .procname = "echo_ignore_all", + .data = &init_net.ipv6.sysctl.icmpv6_echo_ignore_all, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, { }, }; @@ -1115,9 +1124,10 @@ struct ctl_table * __net_init ipv6_icmp_sysctl_init(struct net *net) sizeof(ipv6_icmp_table_template), GFP_KERNEL); - if (table) + if (table) { table[0].data = &net->ipv6.sysctl.icmpv6_time; - + table[1].data = &net->ipv6.sysctl.icmpv6_echo_ignore_all; + } return table; } #endif -- cgit v1.2.3 From 9af18e56d43ca4864ce65c3542c513827c2697de Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Sun, 12 Aug 2018 09:14:03 -0400 Subject: cpumask: make cpumask_next_wrap available without smp The kbuild robot shows build failure on machines without CONFIG_SMP: drivers/net/virtio_net.c:1916:10: error: implicit declaration of function 'cpumask_next_wrap' cpumask_next_wrap is exported from lib/cpumask.o, which has lib-$(CONFIG_SMP) += cpumask.o same as other functions, also define it as static inline in the NR_CPUS==1 branch in include/linux/cpumask.h. If wrap is true and next == start, return nr_cpumask_bits, or 1. Else wrap across the range of valid cpus, here [0]. Fixes: 2ca653d607ce ("virtio_net: Stripe queue affinities across cores.") Signed-off-by: Willem de Bruijn Tested-by: Krzysztof Kozlowski Signed-off-by: David S. Miller --- include/linux/cpumask.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 57f20a0a7794..147bdec42215 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -159,6 +159,13 @@ static inline unsigned int cpumask_next_and(int n, return n+1; } +static inline unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, + int start, bool wrap) +{ + /* cpu0 unless stop condition, wrap and at cpu0, then nr_cpumask_bits */ + return (wrap && n == 0); +} + /* cpu must be a valid cpu, ie 0, so there's no other choice. */ static inline unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) -- cgit v1.2.3 From 0192e7d46c776f7f735560bfa4d40eac3fd700f9 Mon Sep 17 00:00:00 2001 From: Zong Li Date: Mon, 13 Aug 2018 10:26:52 +0800 Subject: net: Change the layout of structure trace_event_raw_fib_table_lookup There is an unalignment access about the structure 'trace_event_raw_fib_table_lookup'. In include/trace/events/fib.h, there is a memory operation which casting the 'src' data member to a pointer, and then store a value to this pointer point to. p32 = (__be32 *) __entry->src; *p32 = flp->saddr; The offset of 'src' in structure trace_event_raw_fib_table_lookup is not four bytes alignment. On some architectures, they don't permit the unalignment access, it need to pay the price to handle this situation in exception handler. Adjust the layout of structure to avoid this case. Fixes: 9f323973c915 ("net/ipv4: Udate fib_table_lookup tracepoint") Signed-off-by: Zong Li Acked-by: David Ahern Signed-off-by: David S. Miller --- include/trace/events/fib.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/fib.h b/include/trace/events/fib.h index 9763cddd0594..6271bab63bfb 100644 --- a/include/trace/events/fib.h +++ b/include/trace/events/fib.h @@ -22,6 +22,7 @@ TRACE_EVENT(fib_table_lookup, __field( int, err ) __field( int, oif ) __field( int, iif ) + __field( u8, proto ) __field( __u8, tos ) __field( __u8, scope ) __field( __u8, flags ) @@ -31,7 +32,6 @@ TRACE_EVENT(fib_table_lookup, __array( __u8, saddr, 4 ) __field( u16, sport ) __field( u16, dport ) - __field( u8, proto ) __dynamic_array(char, name, IFNAMSIZ ) ), -- cgit v1.2.3 From cf916ffbe0c628bb072ea829f300cff1874162ce Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Sun, 29 Apr 2018 09:17:34 -0500 Subject: net/mlx5: Improve argument name for add flow API The last argument to mlx5_add_flow_rules passes the number of destinations in the struct pointed to by the dest arg. Change the name to better reflect this fact. Signed-off-by: Eli Cohen Reviewed-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 8 ++++---- include/linux/mlx5/fs.h | 2 +- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index a21df24b695e..261cb6aacf12 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1876,7 +1876,7 @@ mlx5_add_flow_rules(struct mlx5_flow_table *ft, struct mlx5_flow_spec *spec, struct mlx5_flow_act *flow_act, struct mlx5_flow_destination *dest, - int dest_num) + int num_dest) { struct mlx5_flow_root_namespace *root = find_root(&ft->node); struct mlx5_flow_destination gen_dest = {}; @@ -1889,7 +1889,7 @@ mlx5_add_flow_rules(struct mlx5_flow_table *ft, if (flow_act->action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) { if (!fwd_next_prio_supported(ft)) return ERR_PTR(-EOPNOTSUPP); - if (dest_num) + if (num_dest) return ERR_PTR(-EINVAL); mutex_lock(&root->chain_lock); next_ft = find_next_chained_ft(prio); @@ -1897,7 +1897,7 @@ mlx5_add_flow_rules(struct mlx5_flow_table *ft, gen_dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; gen_dest.ft = next_ft; dest = &gen_dest; - dest_num = 1; + num_dest = 1; flow_act->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; } else { mutex_unlock(&root->chain_lock); @@ -1905,7 +1905,7 @@ mlx5_add_flow_rules(struct mlx5_flow_table *ft, } } - handle = _mlx5_add_flow_rules(ft, spec, flow_act, dest, dest_num); + handle = _mlx5_add_flow_rules(ft, spec, flow_act, dest, num_dest); if (sw_action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) { if (!IS_ERR_OR_NULL(handle) && diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index c40f2fc68655..71fb503b2b52 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -177,7 +177,7 @@ mlx5_add_flow_rules(struct mlx5_flow_table *ft, struct mlx5_flow_spec *spec, struct mlx5_flow_act *flow_act, struct mlx5_flow_destination *dest, - int dest_num); + int num_dest); void mlx5_del_flow_rules(struct mlx5_flow_handle *fr); int mlx5_modify_rule_destination(struct mlx5_flow_handle *handler, -- cgit v1.2.3 From 96d18d8254dc5a3f0067a629866af4165b3afe32 Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Wed, 1 Aug 2018 14:57:59 -0700 Subject: inet/connection_sock: prefer _THIS_IP_ to current_text_addr As part of the effort to reduce the code duplication between _THIS_IP_ and current_text_addr(), let's consolidate callers of current_text_addr() to use _THIS_IP_. Signed-off-by: Nick Desaulniers Acked-by: David S. Miller Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index fa43b82607d9..371b3b45fd5c 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -19,6 +19,7 @@ #include #include #include +#include #include #include @@ -225,7 +226,7 @@ static inline void inet_csk_reset_xmit_timer(struct sock *sk, const int what, if (when > max_when) { pr_debug("reset_xmit_timer: sk=%p %d when=0x%lx, caller=%p\n", - sk, what, when, current_text_addr()); + sk, what, when, (void *)_THIS_IP_); when = max_when; } -- cgit v1.2.3 From b72ae8cac0caff86fe414fceb940655c2d1371c9 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Sun, 29 Jul 2018 16:16:56 +0300 Subject: PCI: Add PCI_DEVICE_DATA() macro to fully describe device ID entry There are a lot of examples in the kernel where PCI_VDEVICE() is used and still looks not so convenient due to additional driver_data field attached. Introduce PCI_DEVICE_DATA() macro to fully describe device ID entry in shortest possible form. For example, before: { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_MRFLD), (kernel_ulong_t) &dwc3_pci_mrfld_properties, }, after: { PCI_DEVICE_DATA(INTEL, MRFLD, &dwc3_pci_mrfld_properties) }, Drivers can be converted later on in independent way. While here, remove the unused macro with the same name from Ralink wireless driver. Signed-off-by: Andy Shevchenko Signed-off-by: Bjorn Helgaas Acked-by: Kalle Valo # for rt2x00 --- drivers/net/wireless/ralink/rt2x00/rt2x00pci.h | 6 ------ include/linux/pci.h | 15 +++++++++++++++ 2 files changed, 15 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00pci.h b/drivers/net/wireless/ralink/rt2x00/rt2x00pci.h index bc0ca5f58f38..283e2e607bba 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2x00pci.h +++ b/drivers/net/wireless/ralink/rt2x00/rt2x00pci.h @@ -27,12 +27,6 @@ #include #include -/* - * This variable should be used with the - * pci_driver structure initialization. - */ -#define PCI_DEVICE_DATA(__ops) .driver_data = (kernel_ulong_t)(__ops) - /* * PCI driver handlers. */ diff --git a/include/linux/pci.h b/include/linux/pci.h index 340029b2fb38..bf3665c534c2 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -819,6 +819,21 @@ struct pci_driver { .vendor = PCI_VENDOR_ID_##vend, .device = (dev), \ .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, 0, 0 +/** + * PCI_DEVICE_DATA - macro used to describe a specific PCI device in very short form + * @vend: the vendor name (without PCI_VENDOR_ID_ prefix) + * @dev: the device name (without PCI_DEVICE_ID__ prefix) + * @data: the driver data to be filled + * + * This macro is used to create a struct pci_device_id that matches a + * specific PCI device. The subvendor, and subdevice fields will be set + * to PCI_ANY_ID. + */ +#define PCI_DEVICE_DATA(vend, dev, data) \ + .vendor = PCI_VENDOR_ID_##vend, .device = PCI_DEVICE_ID_##vend##_##dev, \ + .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, 0, 0, \ + .driver_data = (kernel_ulong_t)(data) + enum { PCI_REASSIGN_ALL_RSRC = 0x00000001, /* Ignore firmware setup */ PCI_REASSIGN_ALL_BUS = 0x00000002, /* Reassign all bus numbers */ -- cgit v1.2.3 From 2538fb89b8f4ee9e1c1759cfb3c7989d9ef1f6e7 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 14 Aug 2018 16:48:50 -0700 Subject: PCI: Limit config space size for Netronome NFP5000 Like the NFP4000 and NFP6000, the NFP5000 as an erratum where reading/ writing to PCI config space addresses above 0x600 can cause the NFP to generate PCIe completion timeouts. Limit the NFP5000's PF's config space size to 0x600 bytes as is already done for the NFP4000 and NFP6000. The NFP5000's VF is 0x6003 (PCI_DEVICE_ID_NETRONOME_NFP6000_VF), the same device ID as the NFP6000's VF. Thus, its config space is already limited by the existing use of quirk_nfp6000(). Signed-off-by: Jakub Kicinski Signed-off-by: Bjorn Helgaas Reviewed-by: Tony Egan --- drivers/pci/quirks.c | 1 + include/linux/pci_ids.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 502275c092ae..7743cd56b89a 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -460,6 +460,7 @@ static void quirk_nfp6000(struct pci_dev *dev) } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NETRONOME, PCI_DEVICE_ID_NETRONOME_NFP4000, quirk_nfp6000); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NETRONOME, PCI_DEVICE_ID_NETRONOME_NFP6000, quirk_nfp6000); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NETRONOME, PCI_DEVICE_ID_NETRONOME_NFP5000, quirk_nfp6000); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NETRONOME, PCI_DEVICE_ID_NETRONOME_NFP6000_VF, quirk_nfp6000); /* On IBM Crocodile ipr SAS adapters, expand BAR to system page size */ diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 29502238e510..381fc009551d 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2541,6 +2541,7 @@ #define PCI_DEVICE_ID_NETRONOME_NFP3200 0x3200 #define PCI_DEVICE_ID_NETRONOME_NFP3240 0x3240 #define PCI_DEVICE_ID_NETRONOME_NFP4000 0x4000 +#define PCI_DEVICE_ID_NETRONOME_NFP5000 0x5000 #define PCI_DEVICE_ID_NETRONOME_NFP6000 0x6000 #define PCI_DEVICE_ID_NETRONOME_NFP6000_VF 0x6003 -- cgit v1.2.3 From 817aef260037f33ee0f44c17fe341323d3aebd6d Mon Sep 17 00:00:00 2001 From: Yannik Sembritzki Date: Thu, 16 Aug 2018 14:05:10 +0100 Subject: Replace magic for trusting the secondary keyring with #define Replace the use of a magic number that indicates that verify_*_signature() should use the secondary keyring with a symbol. Signed-off-by: Yannik Sembritzki Signed-off-by: David Howells Cc: keyrings@vger.kernel.org Cc: linux-security-module@vger.kernel.org Signed-off-by: Linus Torvalds --- certs/system_keyring.c | 3 ++- crypto/asymmetric_keys/pkcs7_key_type.c | 2 +- include/linux/verification.h | 6 ++++++ 3 files changed, 9 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/certs/system_keyring.c b/certs/system_keyring.c index 6251d1b27f0c..81728717523d 100644 --- a/certs/system_keyring.c +++ b/certs/system_keyring.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -230,7 +231,7 @@ int verify_pkcs7_signature(const void *data, size_t len, if (!trusted_keys) { trusted_keys = builtin_trusted_keys; - } else if (trusted_keys == (void *)1UL) { + } else if (trusted_keys == VERIFY_USE_SECONDARY_KEYRING) { #ifdef CONFIG_SECONDARY_TRUSTED_KEYRING trusted_keys = secondary_trusted_keys; #else diff --git a/crypto/asymmetric_keys/pkcs7_key_type.c b/crypto/asymmetric_keys/pkcs7_key_type.c index e284d9cb9237..5b2f6a2b5585 100644 --- a/crypto/asymmetric_keys/pkcs7_key_type.c +++ b/crypto/asymmetric_keys/pkcs7_key_type.c @@ -63,7 +63,7 @@ static int pkcs7_preparse(struct key_preparsed_payload *prep) return verify_pkcs7_signature(NULL, 0, prep->data, prep->datalen, - (void *)1UL, usage, + VERIFY_USE_SECONDARY_KEYRING, usage, pkcs7_view_content, prep); } diff --git a/include/linux/verification.h b/include/linux/verification.h index a10549a6c7cd..cfa4730d607a 100644 --- a/include/linux/verification.h +++ b/include/linux/verification.h @@ -12,6 +12,12 @@ #ifndef _LINUX_VERIFICATION_H #define _LINUX_VERIFICATION_H +/* + * Indicate that both builtin trusted keys and secondary trusted keys + * should be used. + */ +#define VERIFY_USE_SECONDARY_KEYRING ((struct key *)1UL) + /* * The use to which an asymmetric key is being put. */ -- cgit v1.2.3