From 8e2b7442d27ca2a56a116d44d597e77ca21dfed3 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Thu, 9 Jun 2022 12:31:13 +0200 Subject: media: rockchip: rkisp1: Define macros for DPCC configurations in UAPI Extend the UAPI rkisp1-config.h header with macros for all DPCC configuration fields. While at it, clarify of fix issues in the DPCC documentation. Signed-off-by: Laurent Pinchart Reviewed-by: Paul Elder Reviewed-by: Dafna Hirschfeld Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/rkisp1-config.h | 77 ++++++++++++++++++++++++++++++-------- 1 file changed, 61 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/rkisp1-config.h b/include/uapi/linux/rkisp1-config.h index 583ca0d9a79d..730673ecc63d 100644 --- a/include/uapi/linux/rkisp1-config.h +++ b/include/uapi/linux/rkisp1-config.h @@ -117,7 +117,46 @@ /* * Defect Pixel Cluster Correction */ -#define RKISP1_CIF_ISP_DPCC_METHODS_MAX 3 +#define RKISP1_CIF_ISP_DPCC_METHODS_MAX 3 + +#define RKISP1_CIF_ISP_DPCC_MODE_STAGE1_ENABLE (1U << 2) + +#define RKISP1_CIF_ISP_DPCC_OUTPUT_MODE_STAGE1_INCL_G_CENTER (1U << 0) +#define RKISP1_CIF_ISP_DPCC_OUTPUT_MODE_STAGE1_INCL_RB_CENTER (1U << 1) +#define RKISP1_CIF_ISP_DPCC_OUTPUT_MODE_STAGE1_G_3X3 (1U << 2) +#define RKISP1_CIF_ISP_DPCC_OUTPUT_MODE_STAGE1_RB_3X3 (1U << 3) + +/* 0-2 for sets 1-3 */ +#define RKISP1_CIF_ISP_DPCC_SET_USE_STAGE1_USE_SET(n) ((n) << 0) +#define RKISP1_CIF_ISP_DPCC_SET_USE_STAGE1_USE_FIX_SET (1U << 3) + +#define RKISP1_CIF_ISP_DPCC_METHODS_SET_PG_GREEN_ENABLE (1U << 0) +#define RKISP1_CIF_ISP_DPCC_METHODS_SET_LC_GREEN_ENABLE (1U << 1) +#define RKISP1_CIF_ISP_DPCC_METHODS_SET_RO_GREEN_ENABLE (1U << 2) +#define RKISP1_CIF_ISP_DPCC_METHODS_SET_RND_GREEN_ENABLE (1U << 3) +#define RKISP1_CIF_ISP_DPCC_METHODS_SET_RG_GREEN_ENABLE (1U << 4) +#define RKISP1_CIF_ISP_DPCC_METHODS_SET_PG_RED_BLUE_ENABLE (1U << 8) +#define RKISP1_CIF_ISP_DPCC_METHODS_SET_LC_RED_BLUE_ENABLE (1U << 9) +#define RKISP1_CIF_ISP_DPCC_METHODS_SET_RO_RED_BLUE_ENABLE (1U << 10) +#define RKISP1_CIF_ISP_DPCC_METHODS_SET_RND_RED_BLUE_ENABLE (1U << 11) +#define RKISP1_CIF_ISP_DPCC_METHODS_SET_RG_RED_BLUE_ENABLE (1U << 12) + +#define RKISP1_CIF_ISP_DPCC_LINE_THRESH_G(v) ((v) << 0) +#define RKISP1_CIF_ISP_DPCC_LINE_THRESH_RB(v) ((v) << 8) +#define RKISP1_CIF_ISP_DPCC_LINE_MAD_FAC_G(v) ((v) << 0) +#define RKISP1_CIF_ISP_DPCC_LINE_MAD_FAC_RB(v) ((v) << 8) +#define RKISP1_CIF_ISP_DPCC_PG_FAC_G(v) ((v) << 0) +#define RKISP1_CIF_ISP_DPCC_PG_FAC_RB(v) ((v) << 8) +#define RKISP1_CIF_ISP_DPCC_RND_THRESH_G(v) ((v) << 0) +#define RKISP1_CIF_ISP_DPCC_RND_THRESH_RB(v) ((v) << 8) +#define RKISP1_CIF_ISP_DPCC_RG_FAC_G(v) ((v) << 0) +#define RKISP1_CIF_ISP_DPCC_RG_FAC_RB(v) ((v) << 8) + +#define RKISP1_CIF_ISP_DPCC_RO_LIMITS_n_G(n, v) ((v) << ((n) * 4)) +#define RKISP1_CIF_ISP_DPCC_RO_LIMITS_n_RB(n, v) ((v) << ((n) * 4 + 2)) + +#define RKISP1_CIF_ISP_DPCC_RND_OFFS_n_G(n, v) ((v) << ((n) * 4)) +#define RKISP1_CIF_ISP_DPCC_RND_OFFS_n_RB(n, v) ((v) << ((n) * 4 + 2)) /* * Denoising pre filter @@ -249,16 +288,20 @@ struct rkisp1_cif_isp_bls_config { }; /** - * struct rkisp1_cif_isp_dpcc_methods_config - Methods Configuration used by DPCC + * struct rkisp1_cif_isp_dpcc_methods_config - DPCC methods set configuration * - * Methods Configuration used by Defect Pixel Cluster Correction + * This structure stores the configuration of one set of methods for the DPCC + * algorithm. Multiple methods can be selected in each set (independently for + * the Green and Red/Blue components) through the @method field, the result is + * the logical AND of all enabled methods. The remaining fields set thresholds + * and factors for each method. * - * @method: Method enable bits - * @line_thresh: Line threshold - * @line_mad_fac: Line MAD factor - * @pg_fac: Peak gradient factor - * @rnd_thresh: Rank Neighbor Difference threshold - * @rg_fac: Rank gradient factor + * @method: Method enable bits (RKISP1_CIF_ISP_DPCC_METHODS_SET_*) + * @line_thresh: Line threshold (RKISP1_CIF_ISP_DPCC_LINE_THRESH_*) + * @line_mad_fac: Line Mean Absolute Difference factor (RKISP1_CIF_ISP_DPCC_LINE_MAD_FAC_*) + * @pg_fac: Peak gradient factor (RKISP1_CIF_ISP_DPCC_PG_FAC_*) + * @rnd_thresh: Rank Neighbor Difference threshold (RKISP1_CIF_ISP_DPCC_RND_THRESH_*) + * @rg_fac: Rank gradient factor (RKISP1_CIF_ISP_DPCC_RG_FAC_*) */ struct rkisp1_cif_isp_dpcc_methods_config { __u32 method; @@ -272,14 +315,16 @@ struct rkisp1_cif_isp_dpcc_methods_config { /** * struct rkisp1_cif_isp_dpcc_config - Configuration used by DPCC * - * Configuration used by Defect Pixel Cluster Correction + * Configuration used by Defect Pixel Cluster Correction. Three sets of methods + * can be configured and selected through the @set_use field. The result is the + * logical OR of all enabled sets. * - * @mode: dpcc output mode - * @output_mode: whether use hard coded methods - * @set_use: stage1 methods set - * @methods: methods config - * @ro_limits: rank order limits - * @rnd_offs: differential rank offsets for rank neighbor difference + * @mode: DPCC mode (RKISP1_CIF_ISP_DPCC_MODE_*) + * @output_mode: Interpolation output mode (RKISP1_CIF_ISP_DPCC_OUTPUT_MODE_*) + * @set_use: Methods sets selection (RKISP1_CIF_ISP_DPCC_SET_USE_*) + * @methods: Methods sets configuration + * @ro_limits: Rank order limits (RKISP1_CIF_ISP_DPCC_RO_LIMITS_*) + * @rnd_offs: Differential rank offsets for rank neighbor difference (RKISP1_CIF_ISP_DPCC_RND_OFFS_*) */ struct rkisp1_cif_isp_dpcc_config { __u32 mode; -- cgit v1.2.3 From cd75981ec93a3abf717d0182ff5d56b650873215 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Mon, 29 Aug 2022 16:05:14 +0200 Subject: media: v4l2-ctrls: drop 'elems' argument from control type ops. The type ops for equal, init and validate have an elems argument, but this can be taken from struct v4l2_ctrl: ctrl->elems for equal and init, and ctrl->new_elems for validate (since you are validating a new control value). So drop this argument and update all callers. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/media/platform/nxp/dw100/dw100.c | 4 ++-- drivers/media/v4l2-core/v4l2-ctrls-api.c | 8 ++++---- drivers/media/v4l2-core/v4l2-ctrls-core.c | 19 ++++++++++--------- include/media/v4l2-ctrls.h | 28 +++++++++++----------------- 4 files changed, 27 insertions(+), 32 deletions(-) (limited to 'include') diff --git a/drivers/media/platform/nxp/dw100/dw100.c b/drivers/media/platform/nxp/dw100/dw100.c index b3b057798ab6..f6d48c36f386 100644 --- a/drivers/media/platform/nxp/dw100/dw100.c +++ b/drivers/media/platform/nxp/dw100/dw100.c @@ -373,7 +373,7 @@ static const struct v4l2_ctrl_ops dw100_ctrl_ops = { * The coordinates are saved in UQ12.4 fixed point format. */ static void dw100_ctrl_dewarping_map_init(const struct v4l2_ctrl *ctrl, - u32 from_idx, u32 elems, + u32 from_idx, union v4l2_ctrl_ptr ptr) { struct dw100_ctx *ctx = @@ -398,7 +398,7 @@ static void dw100_ctrl_dewarping_map_init(const struct v4l2_ctrl *ctrl, ctx->map_height = mh; ctx->map_size = mh * mw * sizeof(u32); - for (idx = from_idx; idx < elems; idx++) { + for (idx = from_idx; idx < ctrl->elems; idx++) { qy = min_t(u32, (idx / mw) * qdy, qsh); qx = min_t(u32, (idx % mw) * qdx, qsw); map[idx] = dw100_map_format_coordinates(qx, qy); diff --git a/drivers/media/v4l2-core/v4l2-ctrls-api.c b/drivers/media/v4l2-core/v4l2-ctrls-api.c index a8c354ad3d23..d0a3aa3806fb 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls-api.c +++ b/drivers/media/v4l2-core/v4l2-ctrls-api.c @@ -89,7 +89,7 @@ static int req_to_user(struct v4l2_ext_control *c, /* Helper function: copy the initial control value back to the caller */ static int def_to_user(struct v4l2_ext_control *c, struct v4l2_ctrl *ctrl) { - ctrl->type_ops->init(ctrl, 0, ctrl->elems, ctrl->p_new); + ctrl->type_ops->init(ctrl, 0, ctrl->p_new); return ptr_to_user(c, ctrl, ctrl->p_new); } @@ -126,7 +126,7 @@ static int user_to_new(struct v4l2_ext_control *c, struct v4l2_ctrl *ctrl) if (ctrl->is_dyn_array) ctrl->new_elems = elems; else if (ctrl->is_array) - ctrl->type_ops->init(ctrl, elems, ctrl->elems, ctrl->p_new); + ctrl->type_ops->init(ctrl, elems, ctrl->p_new); return 0; } @@ -494,7 +494,7 @@ EXPORT_SYMBOL(v4l2_g_ext_ctrls); /* Validate a new control */ static int validate_new(const struct v4l2_ctrl *ctrl, union v4l2_ctrl_ptr p_new) { - return ctrl->type_ops->validate(ctrl, ctrl->new_elems, p_new); + return ctrl->type_ops->validate(ctrl, p_new); } /* Validate controls. */ @@ -1007,7 +1007,7 @@ int __v4l2_ctrl_modify_dimensions(struct v4l2_ctrl *ctrl, ctrl->p_cur.p = p_array + elems * ctrl->elem_size; for (i = 0; i < ctrl->nr_of_dims; i++) ctrl->dims[i] = dims[i]; - ctrl->type_ops->init(ctrl, 0, elems, ctrl->p_cur); + ctrl->type_ops->init(ctrl, 0, ctrl->p_cur); cur_to_new(ctrl); send_event(NULL, ctrl, V4L2_EVENT_CTRL_CH_VALUE | V4L2_EVENT_CTRL_CH_DIMENSIONS); diff --git a/drivers/media/v4l2-core/v4l2-ctrls-core.c b/drivers/media/v4l2-core/v4l2-ctrls-core.c index 01f00093f259..0dab1d7b90f0 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls-core.c +++ b/drivers/media/v4l2-core/v4l2-ctrls-core.c @@ -65,7 +65,7 @@ void send_event(struct v4l2_fh *fh, struct v4l2_ctrl *ctrl, u32 changes) v4l2_event_queue_fh(sev->fh, &ev); } -bool v4l2_ctrl_type_op_equal(const struct v4l2_ctrl *ctrl, u32 elems, +bool v4l2_ctrl_type_op_equal(const struct v4l2_ctrl *ctrl, union v4l2_ctrl_ptr ptr1, union v4l2_ctrl_ptr ptr2) { unsigned int i; @@ -74,7 +74,7 @@ bool v4l2_ctrl_type_op_equal(const struct v4l2_ctrl *ctrl, u32 elems, case V4L2_CTRL_TYPE_BUTTON: return false; case V4L2_CTRL_TYPE_STRING: - for (i = 0; i < elems; i++) { + for (i = 0; i < ctrl->elems; i++) { unsigned int idx = i * ctrl->elem_size; /* strings are always 0-terminated */ @@ -84,7 +84,7 @@ bool v4l2_ctrl_type_op_equal(const struct v4l2_ctrl *ctrl, u32 elems, return true; default: return !memcmp(ptr1.p_const, ptr2.p_const, - elems * ctrl->elem_size); + ctrl->elems * ctrl->elem_size); } } EXPORT_SYMBOL(v4l2_ctrl_type_op_equal); @@ -178,9 +178,10 @@ static void std_init_compound(const struct v4l2_ctrl *ctrl, u32 idx, } void v4l2_ctrl_type_op_init(const struct v4l2_ctrl *ctrl, u32 from_idx, - u32 tot_elems, union v4l2_ctrl_ptr ptr) + union v4l2_ctrl_ptr ptr) { unsigned int i; + u32 tot_elems = ctrl->elems; u32 elems = tot_elems - from_idx; if (from_idx >= tot_elems) @@ -995,7 +996,7 @@ static int std_validate_elem(const struct v4l2_ctrl *ctrl, u32 idx, } } -int v4l2_ctrl_type_op_validate(const struct v4l2_ctrl *ctrl, u32 elems, +int v4l2_ctrl_type_op_validate(const struct v4l2_ctrl *ctrl, union v4l2_ctrl_ptr ptr) { unsigned int i; @@ -1017,11 +1018,11 @@ int v4l2_ctrl_type_op_validate(const struct v4l2_ctrl *ctrl, u32 elems, case V4L2_CTRL_TYPE_BUTTON: case V4L2_CTRL_TYPE_CTRL_CLASS: - memset(ptr.p_s32, 0, elems * sizeof(s32)); + memset(ptr.p_s32, 0, ctrl->new_elems * sizeof(s32)); return 0; } - for (i = 0; !ret && i < elems; i++) + for (i = 0; !ret && i < ctrl->new_elems; i++) ret = std_validate_elem(ctrl, i, ptr); return ret; } @@ -1724,7 +1725,7 @@ static struct v4l2_ctrl *v4l2_ctrl_new(struct v4l2_ctrl_handler *hdl, memcpy(ctrl->p_def.p, p_def.p_const, elem_size); } - ctrl->type_ops->init(ctrl, 0, elems, ctrl->p_cur); + ctrl->type_ops->init(ctrl, 0, ctrl->p_cur); cur_to_new(ctrl); if (handler_new_ref(hdl, ctrl, NULL, false, false)) { @@ -2069,7 +2070,7 @@ static int cluster_changed(struct v4l2_ctrl *master) ctrl_changed = true; if (!ctrl_changed) ctrl_changed = !ctrl->type_ops->equal(ctrl, - ctrl->elems, ctrl->p_cur, ctrl->p_new); + ctrl->p_cur, ctrl->p_new); ctrl->has_changed = ctrl_changed; changed |= ctrl->has_changed; } diff --git a/include/media/v4l2-ctrls.h b/include/media/v4l2-ctrls.h index b76a0714d425..e59d9a234631 100644 --- a/include/media/v4l2-ctrls.h +++ b/include/media/v4l2-ctrls.h @@ -121,21 +121,19 @@ struct v4l2_ctrl_ops { * struct v4l2_ctrl_type_ops - The control type operations that the driver * has to provide. * - * @equal: return true if both values are equal. - * @init: initialize the value. + * @equal: return true if all ctrl->elems array elements are equal. + * @init: initialize the value for array elements from from_idx to ctrl->elems. * @log: log the value. - * @validate: validate the value. Return 0 on success and a negative value - * otherwise. + * @validate: validate the value for ctrl->new_elems array elements. + * Return 0 on success and a negative value otherwise. */ struct v4l2_ctrl_type_ops { - bool (*equal)(const struct v4l2_ctrl *ctrl, u32 elems, - union v4l2_ctrl_ptr ptr1, - union v4l2_ctrl_ptr ptr2); - void (*init)(const struct v4l2_ctrl *ctrl, u32 from_idx, u32 tot_elems, + bool (*equal)(const struct v4l2_ctrl *ctrl, + union v4l2_ctrl_ptr ptr1, union v4l2_ctrl_ptr ptr2); + void (*init)(const struct v4l2_ctrl *ctrl, u32 from_idx, union v4l2_ctrl_ptr ptr); void (*log)(const struct v4l2_ctrl *ctrl); - int (*validate)(const struct v4l2_ctrl *ctrl, u32 elems, - union v4l2_ctrl_ptr ptr); + int (*validate)(const struct v4l2_ctrl *ctrl, union v4l2_ctrl_ptr ptr); }; /** @@ -1543,13 +1541,12 @@ int v4l2_ctrl_new_fwnode_properties(struct v4l2_ctrl_handler *hdl, * v4l2_ctrl_type_op_equal - Default v4l2_ctrl_type_ops equal callback. * * @ctrl: The v4l2_ctrl pointer. - * @elems: The number of elements to compare. * @ptr1: A v4l2 control value. * @ptr2: A v4l2 control value. * * Return: true if values are equal, otherwise false. */ -bool v4l2_ctrl_type_op_equal(const struct v4l2_ctrl *ctrl, u32 elems, +bool v4l2_ctrl_type_op_equal(const struct v4l2_ctrl *ctrl, union v4l2_ctrl_ptr ptr1, union v4l2_ctrl_ptr ptr2); /** @@ -1557,13 +1554,12 @@ bool v4l2_ctrl_type_op_equal(const struct v4l2_ctrl *ctrl, u32 elems, * * @ctrl: The v4l2_ctrl pointer. * @from_idx: Starting element index. - * @elems: The number of elements to initialize. * @ptr: The v4l2 control value. * * Return: void */ void v4l2_ctrl_type_op_init(const struct v4l2_ctrl *ctrl, u32 from_idx, - u32 elems, union v4l2_ctrl_ptr ptr); + union v4l2_ctrl_ptr ptr); /** * v4l2_ctrl_type_op_log - Default v4l2_ctrl_type_ops log callback. @@ -1578,12 +1574,10 @@ void v4l2_ctrl_type_op_log(const struct v4l2_ctrl *ctrl); * v4l2_ctrl_type_op_validate - Default v4l2_ctrl_type_ops validate callback. * * @ctrl: The v4l2_ctrl pointer. - * @elems: The number of elements in the control. * @ptr: The v4l2 control value. * * Return: 0 on success, a negative error code on failure. */ -int v4l2_ctrl_type_op_validate(const struct v4l2_ctrl *ctrl, u32 elems, - union v4l2_ctrl_ptr ptr); +int v4l2_ctrl_type_op_validate(const struct v4l2_ctrl *ctrl, union v4l2_ctrl_ptr ptr); #endif -- cgit v1.2.3 From 479747caa5bfa94b856bf47249006e6c8aa8be37 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Tue, 30 Aug 2022 12:37:24 +0200 Subject: media: cec: add support for Absolute Volume Control Add support for this new CEC message. This was added in HDMI 2.1a. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- Documentation/userspace-api/media/cec.h.rst.exceptions | 2 ++ drivers/media/cec/core/cec-adap.c | 1 + include/uapi/linux/cec-funcs.h | 14 ++++++++++++++ include/uapi/linux/cec.h | 2 ++ 4 files changed, 19 insertions(+) (limited to 'include') diff --git a/Documentation/userspace-api/media/cec.h.rst.exceptions b/Documentation/userspace-api/media/cec.h.rst.exceptions index 13de01d9555e..15fa1752d4ef 100644 --- a/Documentation/userspace-api/media/cec.h.rst.exceptions +++ b/Documentation/userspace-api/media/cec.h.rst.exceptions @@ -239,6 +239,7 @@ ignore define CEC_OP_FEAT_DEV_HAS_DECK_CONTROL ignore define CEC_OP_FEAT_DEV_HAS_SET_AUDIO_RATE ignore define CEC_OP_FEAT_DEV_SINK_HAS_ARC_TX ignore define CEC_OP_FEAT_DEV_SOURCE_HAS_ARC_RX +ignore define CEC_OP_FEAT_DEV_HAS_SET_AUDIO_VOLUME_LEVEL ignore define CEC_MSG_GIVE_FEATURES @@ -487,6 +488,7 @@ ignore define CEC_OP_SYS_AUD_STATUS_ON ignore define CEC_MSG_SYSTEM_AUDIO_MODE_REQUEST ignore define CEC_MSG_SYSTEM_AUDIO_MODE_STATUS +ignore define CEC_MSG_SET_AUDIO_VOLUME_LEVEL ignore define CEC_OP_AUD_FMT_ID_CEA861 ignore define CEC_OP_AUD_FMT_ID_CEA861_CXT diff --git a/drivers/media/cec/core/cec-adap.c b/drivers/media/cec/core/cec-adap.c index 41a79293ee02..4f5ab3cae8a7 100644 --- a/drivers/media/cec/core/cec-adap.c +++ b/drivers/media/cec/core/cec-adap.c @@ -1027,6 +1027,7 @@ static const u8 cec_msg_size[256] = { [CEC_MSG_REPORT_SHORT_AUDIO_DESCRIPTOR] = 2 | DIRECTED, [CEC_MSG_REQUEST_SHORT_AUDIO_DESCRIPTOR] = 2 | DIRECTED, [CEC_MSG_SET_SYSTEM_AUDIO_MODE] = 3 | BOTH, + [CEC_MSG_SET_AUDIO_VOLUME_LEVEL] = 3 | DIRECTED, [CEC_MSG_SYSTEM_AUDIO_MODE_REQUEST] = 2 | DIRECTED, [CEC_MSG_SYSTEM_AUDIO_MODE_STATUS] = 3 | DIRECTED, [CEC_MSG_SET_AUDIO_RATE] = 3 | DIRECTED, diff --git a/include/uapi/linux/cec-funcs.h b/include/uapi/linux/cec-funcs.h index c3baaea0b8ef..d58fa1cdcb08 100644 --- a/include/uapi/linux/cec-funcs.h +++ b/include/uapi/linux/cec-funcs.h @@ -1568,6 +1568,20 @@ static inline void cec_ops_request_short_audio_descriptor(const struct cec_msg * } } +static inline void cec_msg_set_audio_volume_level(struct cec_msg *msg, + __u8 audio_volume_level) +{ + msg->len = 3; + msg->msg[1] = CEC_MSG_SET_AUDIO_VOLUME_LEVEL; + msg->msg[2] = audio_volume_level; +} + +static inline void cec_ops_set_audio_volume_level(const struct cec_msg *msg, + __u8 *audio_volume_level) +{ + *audio_volume_level = msg->msg[2]; +} + /* Audio Rate Control Feature */ static inline void cec_msg_set_audio_rate(struct cec_msg *msg, diff --git a/include/uapi/linux/cec.h b/include/uapi/linux/cec.h index 1d48da926216..b8e071abaea5 100644 --- a/include/uapi/linux/cec.h +++ b/include/uapi/linux/cec.h @@ -768,6 +768,7 @@ struct cec_event { #define CEC_OP_FEAT_DEV_HAS_SET_AUDIO_RATE 0x08 #define CEC_OP_FEAT_DEV_SINK_HAS_ARC_TX 0x04 #define CEC_OP_FEAT_DEV_SOURCE_HAS_ARC_RX 0x02 +#define CEC_OP_FEAT_DEV_HAS_SET_AUDIO_VOLUME_LEVEL 0x01 #define CEC_MSG_GIVE_FEATURES 0xa5 /* HDMI 2.0 */ @@ -1059,6 +1060,7 @@ struct cec_event { #define CEC_OP_AUD_FMT_ID_CEA861 0 #define CEC_OP_AUD_FMT_ID_CEA861_CXT 1 +#define CEC_MSG_SET_AUDIO_VOLUME_LEVEL 0x73 /* Audio Rate Control Feature */ #define CEC_MSG_SET_AUDIO_RATE 0x9a -- cgit v1.2.3 From bb9ea2c31fa11b789ade4c3abcdda3c5370a76ab Mon Sep 17 00:00:00 2001 From: Alexander Stein Date: Fri, 22 Jul 2022 09:11:31 +0200 Subject: media: v4l2: Fix v4l2_i2c_subdev_set_name function documentation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The doc says the I²C device's name is used if devname is NULL, but actually the I²C device driver's name is used. Fixes: 0658293012af ("media: v4l: subdev: Add a function to set an I²C sub-device's name") Signed-off-by: Alexander Stein Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-common.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/media/v4l2-common.h b/include/media/v4l2-common.h index b708d63995f4..2ae2be4c87e5 100644 --- a/include/media/v4l2-common.h +++ b/include/media/v4l2-common.h @@ -175,7 +175,8 @@ struct v4l2_subdev *v4l2_i2c_new_subdev_board(struct v4l2_device *v4l2_dev, * * @sd: pointer to &struct v4l2_subdev * @client: pointer to struct i2c_client - * @devname: the name of the device; if NULL, the I²C device's name will be used + * @devname: the name of the device; if NULL, the I²C device drivers's name + * will be used * @postfix: sub-device specific string to put right after the I²C device name; * may be NULL */ -- cgit v1.2.3 From 2ba3e38517f5a4ebf9c997168079dca01b7f9fc6 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Fri, 26 Aug 2022 13:53:58 +0200 Subject: media: v4l: subdev: Fail graciously when getting try data for NULL state The state argument for the functions for obtaining various parts of the state is NULL if it is called by drivers for active state. Fail graciously in that case instead of dereferencing a NULL pointer. Suggested-by: Bingbu Cao Signed-off-by: Sakari Ailus Reviewed-by: Tomi Valkeinen Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-subdev.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h index 9689f38a0af1..ec1896886dbd 100644 --- a/include/media/v4l2-subdev.h +++ b/include/media/v4l2-subdev.h @@ -1046,6 +1046,8 @@ v4l2_subdev_get_pad_format(struct v4l2_subdev *sd, struct v4l2_subdev_state *state, unsigned int pad) { + if (WARN_ON(!state)) + return NULL; if (WARN_ON(pad >= sd->entity.num_pads)) pad = 0; return &state->pads[pad].try_fmt; @@ -1064,6 +1066,8 @@ v4l2_subdev_get_pad_crop(struct v4l2_subdev *sd, struct v4l2_subdev_state *state, unsigned int pad) { + if (WARN_ON(!state)) + return NULL; if (WARN_ON(pad >= sd->entity.num_pads)) pad = 0; return &state->pads[pad].try_crop; @@ -1082,6 +1086,8 @@ v4l2_subdev_get_pad_compose(struct v4l2_subdev *sd, struct v4l2_subdev_state *state, unsigned int pad) { + if (WARN_ON(!state)) + return NULL; if (WARN_ON(pad >= sd->entity.num_pads)) pad = 0; return &state->pads[pad].try_compose; -- cgit v1.2.3 From ac5d4d87e1eb8534c4b8148f77a0771825e780f4 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Mon, 5 Sep 2022 14:35:34 +0200 Subject: media: Remove incorrect comment from struct v4l2_fwnode_endpoint struct v4l2_fwnode_endpoint was zeroed previously apart from the endpoint information itself when the endpoint properties were parsed. Now this hasn't been the case for a few years so remove the comment. Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-fwnode.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/media/v4l2-fwnode.h b/include/media/v4l2-fwnode.h index 15e4ab672223..394d798f3dfa 100644 --- a/include/media/v4l2-fwnode.h +++ b/include/media/v4l2-fwnode.h @@ -45,10 +45,6 @@ struct v4l2_async_subdev; */ struct v4l2_fwnode_endpoint { struct fwnode_endpoint base; - /* - * Fields below this line will be zeroed by - * v4l2_fwnode_endpoint_parse() - */ enum v4l2_mbus_type bus_type; struct { struct v4l2_mbus_config_parallel parallel; -- cgit v1.2.3 From c7097c80ca684f6476a55b2e202b975cf3e36b46 Mon Sep 17 00:00:00 2001 From: Tomi Valkeinen Date: Wed, 31 Aug 2022 16:13:25 +0200 Subject: media: media-entity.h: add include for min() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit ./include/media/media-entity.h:595:34: error: implicit declaration of function ‘min’ Include minmax.h to get the definition for min(). Signed-off-by: Tomi Valkeinen Reviewed-by: Laurent Pinchart Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/media/media-entity.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/media/media-entity.h b/include/media/media-entity.h index f16ffe70f7a6..4a67b1dfdc69 100644 --- a/include/media/media-entity.h +++ b/include/media/media-entity.h @@ -17,6 +17,7 @@ #include #include #include +#include #include /* Enums used internally at the media controller to represent graphs */ -- cgit v1.2.3 From 87d36eb84d4f45657bb422af36c9eed0161cd032 Mon Sep 17 00:00:00 2001 From: Tomi Valkeinen Date: Wed, 31 Aug 2022 16:13:26 +0200 Subject: media: subdev: increase V4L2_FRAME_DESC_ENTRY_MAX to 8 V4L2_FRAME_DESC_ENTRY_MAX is currently set to 4. In theory it's possible to have an arbitrary amount of streams in a single pad, so preferably there should be no hardcoded maximum number. However, I believe a reasonable max is 8, which would cover a CSI-2 pad with 4 streams of pixel data and 4 streams of metadata. Signed-off-by: Tomi Valkeinen Reviewed-by: Laurent Pinchart Reviewed-by: Hans Verkuil Reviewed-by: Jacopo Mondi Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-subdev.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h index ec1896886dbd..2f80c9c818ed 100644 --- a/include/media/v4l2-subdev.h +++ b/include/media/v4l2-subdev.h @@ -358,7 +358,11 @@ struct v4l2_mbus_frame_desc_entry { } bus; }; -#define V4L2_FRAME_DESC_ENTRY_MAX 4 + /* + * If this number is too small, it should be dropped altogether and the + * API switched to a dynamic number of frame descriptor entries. + */ +#define V4L2_FRAME_DESC_ENTRY_MAX 8 /** * enum v4l2_mbus_frame_desc_type - media bus frame description type -- cgit v1.2.3 From b7319e2bd7bd7740a405719727e6fc01be1363ef Mon Sep 17 00:00:00 2001 From: Tomi Valkeinen Date: Wed, 31 Aug 2022 16:13:27 +0200 Subject: media: mc: entity: Rename streaming_count -> start_count 'streaming_count' is a bit misleading name, as the count is increased with media_pipeline_start(). Let's rename it to 'start_count' instead. Signed-off-by: Tomi Valkeinen Reviewed-by: Laurent Pinchart Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- drivers/media/mc/mc-entity.c | 8 ++++---- drivers/media/platform/rockchip/rkisp1/rkisp1-capture.c | 4 ++-- include/media/media-entity.h | 4 ++-- 3 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/drivers/media/mc/mc-entity.c b/drivers/media/mc/mc-entity.c index afd1bd7ff7b6..67d009b617ce 100644 --- a/drivers/media/mc/mc-entity.c +++ b/drivers/media/mc/mc-entity.c @@ -415,8 +415,8 @@ __must_check int __media_pipeline_start(struct media_entity *entity, struct media_link *link; int ret; - if (pipe->streaming_count) { - pipe->streaming_count++; + if (pipe->start_count) { + pipe->start_count++; return 0; } @@ -499,7 +499,7 @@ __must_check int __media_pipeline_start(struct media_entity *entity, } } - pipe->streaming_count++; + pipe->start_count++; return 0; @@ -552,7 +552,7 @@ void __media_pipeline_stop(struct media_entity *entity) if (WARN_ON(!pipe)) return; - if (--pipe->streaming_count) + if (--pipe->start_count) return; media_graph_walk_start(graph, entity); diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-capture.c b/drivers/media/platform/rockchip/rkisp1/rkisp1-capture.c index c66963a2ccd9..6ef09579dc21 100644 --- a/drivers/media/platform/rockchip/rkisp1/rkisp1-capture.c +++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-capture.c @@ -926,7 +926,7 @@ static void rkisp1_pipeline_stream_disable(struct rkisp1_capture *cap) * If the other capture is streaming, isp and sensor nodes shouldn't * be disabled, skip them. */ - if (rkisp1->pipe.streaming_count < 2) + if (rkisp1->pipe.start_count < 2) v4l2_subdev_call(&rkisp1->isp.sd, video, s_stream, false); v4l2_subdev_call(&rkisp1->resizer_devs[cap->id].sd, video, s_stream, @@ -956,7 +956,7 @@ static int rkisp1_pipeline_stream_enable(struct rkisp1_capture *cap) * If the other capture is streaming, isp and sensor nodes are already * enabled, skip them. */ - if (rkisp1->pipe.streaming_count > 1) + if (rkisp1->pipe.start_count > 1) return 0; ret = v4l2_subdev_call(&rkisp1->isp.sd, video, s_stream, true); diff --git a/include/media/media-entity.h b/include/media/media-entity.h index 4a67b1dfdc69..198ea1416ddd 100644 --- a/include/media/media-entity.h +++ b/include/media/media-entity.h @@ -100,11 +100,11 @@ struct media_graph { /** * struct media_pipeline - Media pipeline related information * - * @streaming_count: Streaming start count - streaming stop count + * @start_count: Media pipeline start - stop count * @graph: Media graph walk during pipeline start / stop */ struct media_pipeline { - int streaming_count; + int start_count; struct media_graph graph; }; -- cgit v1.2.3 From 8db465f7d6a0fb573d8f7c953d336b8470c0e831 Mon Sep 17 00:00:00 2001 From: Jacopo Mondi Date: Wed, 31 Aug 2022 16:13:28 +0200 Subject: media: mc: entity: Add iterator helper for entity pads Add an iterator helper to easily cycle through all pads in an entity and use it in media-entity and media-device code where appropriate. Signed-off-by: Jacopo Mondi Reviewed-by: Laurent Pinchart Signed-off-by: Tomi Valkeinen Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- drivers/media/mc/mc-device.c | 13 ++++++------- drivers/media/mc/mc-entity.c | 11 ++++++----- include/media/media-entity.h | 12 ++++++++++++ 3 files changed, 24 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/drivers/media/mc/mc-device.c b/drivers/media/mc/mc-device.c index b8176a3b76d3..25020d58eb06 100644 --- a/drivers/media/mc/mc-device.c +++ b/drivers/media/mc/mc-device.c @@ -581,7 +581,7 @@ static void __media_device_unregister_entity(struct media_entity *entity) struct media_device *mdev = entity->graph_obj.mdev; struct media_link *link, *tmp; struct media_interface *intf; - unsigned int i; + struct media_pad *iter; ida_free(&mdev->entity_internal_idx, entity->internal_idx); @@ -597,8 +597,8 @@ static void __media_device_unregister_entity(struct media_entity *entity) __media_entity_remove_links(entity); /* Remove all pads that belong to this entity */ - for (i = 0; i < entity->num_pads; i++) - media_gobj_destroy(&entity->pads[i].graph_obj); + media_entity_for_each_pad(entity, iter) + media_gobj_destroy(&iter->graph_obj); /* Remove the entity */ media_gobj_destroy(&entity->graph_obj); @@ -610,7 +610,7 @@ int __must_check media_device_register_entity(struct media_device *mdev, struct media_entity *entity) { struct media_entity_notify *notify, *next; - unsigned int i; + struct media_pad *iter; int ret; if (entity->function == MEDIA_ENT_F_V4L2_SUBDEV_UNKNOWN || @@ -639,9 +639,8 @@ int __must_check media_device_register_entity(struct media_device *mdev, media_gobj_create(mdev, MEDIA_GRAPH_ENTITY, &entity->graph_obj); /* Initialize objects at the pads */ - for (i = 0; i < entity->num_pads; i++) - media_gobj_create(mdev, MEDIA_GRAPH_PAD, - &entity->pads[i].graph_obj); + media_entity_for_each_pad(entity, iter) + media_gobj_create(mdev, MEDIA_GRAPH_PAD, &iter->graph_obj); /* invoke entity_notify callbacks */ list_for_each_entry_safe(notify, next, &mdev->entity_notify, list) diff --git a/drivers/media/mc/mc-entity.c b/drivers/media/mc/mc-entity.c index 67d009b617ce..682f424a15ca 100644 --- a/drivers/media/mc/mc-entity.c +++ b/drivers/media/mc/mc-entity.c @@ -193,7 +193,8 @@ int media_entity_pads_init(struct media_entity *entity, u16 num_pads, struct media_pad *pads) { struct media_device *mdev = entity->graph_obj.mdev; - unsigned int i; + struct media_pad *iter; + unsigned int i = 0; if (num_pads >= MEDIA_ENTITY_MAX_PADS) return -E2BIG; @@ -204,12 +205,12 @@ int media_entity_pads_init(struct media_entity *entity, u16 num_pads, if (mdev) mutex_lock(&mdev->graph_mutex); - for (i = 0; i < num_pads; i++) { - pads[i].entity = entity; - pads[i].index = i; + media_entity_for_each_pad(entity, iter) { + iter->entity = entity; + iter->index = i++; if (mdev) media_gobj_create(mdev, MEDIA_GRAPH_PAD, - &entity->pads[i].graph_obj); + &iter->graph_obj); } if (mdev) diff --git a/include/media/media-entity.h b/include/media/media-entity.h index 198ea1416ddd..a5a50350e954 100644 --- a/include/media/media-entity.h +++ b/include/media/media-entity.h @@ -316,6 +316,18 @@ struct media_entity { } info; }; +/** + * media_entity_for_each_pad - Iterate on all pads in an entity + * @entity: The entity the pads belong to + * @iter: The iterator pad + * + * Iterate on all pads in a media entity. + */ +#define media_entity_for_each_pad(entity, iter) \ + for (iter = (entity)->pads; \ + iter < &(entity)->pads[(entity)->num_pads]; \ + ++iter) + /** * struct media_interface - A media interface graph object. * -- cgit v1.2.3 From 49b38947d7841abb6e60c15968f03b2daa2d54d7 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Wed, 31 Aug 2022 16:13:29 +0200 Subject: media: mc: entity: Merge media_entity_enum_init and __media_entity_enum_init The media_entity_enum_init() function is a wrapper around __media_entity_enum_init() that turns a media_device pointer argument into the maximum entity ID in the corresponding media graph. __media_entity_enum_init() is never used outside of media_entity_enum_init(), so the two functions can be merged together. Signed-off-by: Laurent Pinchart Signed-off-by: Tomi Valkeinen Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- drivers/media/mc/mc-entity.c | 10 ++++++---- include/media/media-device.h | 15 --------------- include/media/media-entity.h | 10 +++++----- 3 files changed, 11 insertions(+), 24 deletions(-) (limited to 'include') diff --git a/drivers/media/mc/mc-entity.c b/drivers/media/mc/mc-entity.c index 682f424a15ca..48d8cc98ae04 100644 --- a/drivers/media/mc/mc-entity.c +++ b/drivers/media/mc/mc-entity.c @@ -59,10 +59,12 @@ static inline const char *link_type_name(struct media_link *link) } } -__must_check int __media_entity_enum_init(struct media_entity_enum *ent_enum, - int idx_max) +__must_check int media_entity_enum_init(struct media_entity_enum *ent_enum, + struct media_device *mdev) { - idx_max = ALIGN(idx_max, BITS_PER_LONG); + int idx_max; + + idx_max = ALIGN(mdev->entity_internal_idx_max + 1, BITS_PER_LONG); ent_enum->bmap = bitmap_zalloc(idx_max, GFP_KERNEL); if (!ent_enum->bmap) return -ENOMEM; @@ -71,7 +73,7 @@ __must_check int __media_entity_enum_init(struct media_entity_enum *ent_enum, return 0; } -EXPORT_SYMBOL_GPL(__media_entity_enum_init); +EXPORT_SYMBOL_GPL(media_entity_enum_init); void media_entity_enum_cleanup(struct media_entity_enum *ent_enum) { diff --git a/include/media/media-device.h b/include/media/media-device.h index a10b30507524..86716ee7cc6c 100644 --- a/include/media/media-device.h +++ b/include/media/media-device.h @@ -191,21 +191,6 @@ struct usb_device; #define MEDIA_DEV_NOTIFY_PRE_LINK_CH 0 #define MEDIA_DEV_NOTIFY_POST_LINK_CH 1 -/** - * media_entity_enum_init - Initialise an entity enumeration - * - * @ent_enum: Entity enumeration to be initialised - * @mdev: The related media device - * - * Return: zero on success or a negative error code. - */ -static inline __must_check int media_entity_enum_init( - struct media_entity_enum *ent_enum, struct media_device *mdev) -{ - return __media_entity_enum_init(ent_enum, - mdev->entity_internal_idx_max + 1); -} - /** * media_device_init() - Initializes a media device element * diff --git a/include/media/media-entity.h b/include/media/media-entity.h index a5a50350e954..1030e45e8ee6 100644 --- a/include/media/media-entity.h +++ b/include/media/media-entity.h @@ -439,15 +439,15 @@ static inline bool is_media_entity_v4l2_subdev(struct media_entity *entity) } /** - * __media_entity_enum_init - Initialise an entity enumeration + * media_entity_enum_init - Initialise an entity enumeration * * @ent_enum: Entity enumeration to be initialised - * @idx_max: Maximum number of entities in the enumeration + * @mdev: The related media device * - * Return: Returns zero on success or a negative error code. + * Return: zero on success or a negative error code. */ -__must_check int __media_entity_enum_init(struct media_entity_enum *ent_enum, - int idx_max); +__must_check int media_entity_enum_init(struct media_entity_enum *ent_enum, + struct media_device *mdev); /** * media_entity_enum_cleanup - Release resources of an entity enumeration -- cgit v1.2.3 From 72b603357ae461c0f19ca05d6624b4afd5c74b47 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Wed, 31 Aug 2022 16:13:31 +0200 Subject: media: mc: entity: Add media_entity_pipeline() to access the media pipeline Replace direct access to the pipe field in drivers with a new helper function. This will allow easier refactoring of media pipeline handling in the MC core behind the scenes without affecting drivers. Signed-off-by: Laurent Pinchart Signed-off-by: Tomi Valkeinen Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- drivers/media/mc/mc-entity.c | 6 ++++++ drivers/media/platform/renesas/rcar-vin/rcar-core.c | 5 ++--- drivers/media/platform/renesas/rcar-vin/rcar-dma.c | 2 +- drivers/media/platform/ti/omap3isp/isp.c | 4 +--- drivers/media/platform/ti/omap3isp/ispvideo.c | 3 +-- drivers/media/platform/ti/omap3isp/ispvideo.h | 11 +++++++++-- drivers/media/platform/xilinx/xilinx-dma.c | 3 +-- drivers/media/platform/xilinx/xilinx-dma.h | 7 ++++++- drivers/staging/media/imx/imx-media-utils.c | 2 +- drivers/staging/media/omap4iss/iss.c | 4 +--- drivers/staging/media/omap4iss/iss_video.c | 3 +-- drivers/staging/media/omap4iss/iss_video.h | 11 +++++++++-- include/media/media-entity.h | 18 ++++++++++++++++++ 13 files changed, 57 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/drivers/media/mc/mc-entity.c b/drivers/media/mc/mc-entity.c index c5c66befed0f..7fb97c6dc897 100644 --- a/drivers/media/mc/mc-entity.c +++ b/drivers/media/mc/mc-entity.c @@ -994,6 +994,12 @@ int media_entity_get_fwnode_pad(struct media_entity *entity, } EXPORT_SYMBOL_GPL(media_entity_get_fwnode_pad); +struct media_pipeline *media_entity_pipeline(struct media_entity *entity) +{ + return entity->pipe; +} +EXPORT_SYMBOL_GPL(media_entity_pipeline); + static void media_interface_init(struct media_device *mdev, struct media_interface *intf, u32 gobj_type, diff --git a/drivers/media/platform/renesas/rcar-vin/rcar-core.c b/drivers/media/platform/renesas/rcar-vin/rcar-core.c index 968a74234e92..2f7daa853ed8 100644 --- a/drivers/media/platform/renesas/rcar-vin/rcar-core.c +++ b/drivers/media/platform/renesas/rcar-vin/rcar-core.c @@ -786,9 +786,8 @@ static int rvin_csi2_link_notify(struct media_link *link, u32 flags, return 0; /* - * Don't allow link changes if any entity in the graph is - * streaming, modifying the CHSEL register fields can disrupt - * running streams. + * Don't allow link changes if any stream in the graph is active as + * modifying the CHSEL register fields can disrupt running streams. */ media_device_for_each_entity(entity, &group->mdev) if (media_entity_is_streaming(entity)) diff --git a/drivers/media/platform/renesas/rcar-vin/rcar-dma.c b/drivers/media/platform/renesas/rcar-vin/rcar-dma.c index 8d37fbdc266a..e72bc6fa049f 100644 --- a/drivers/media/platform/renesas/rcar-vin/rcar-dma.c +++ b/drivers/media/platform/renesas/rcar-vin/rcar-dma.c @@ -1281,7 +1281,7 @@ static int rvin_set_stream(struct rvin_dev *vin, int on) */ mdev = vin->vdev.entity.graph_obj.mdev; mutex_lock(&mdev->graph_mutex); - pipe = sd->entity.pipe ? sd->entity.pipe : &vin->vdev.pipe; + pipe = media_entity_pipeline(&sd->entity) ? : &vin->vdev.pipe; ret = __media_pipeline_start(&vin->vdev.entity, pipe); mutex_unlock(&mdev->graph_mutex); if (ret) diff --git a/drivers/media/platform/ti/omap3isp/isp.c b/drivers/media/platform/ti/omap3isp/isp.c index a6052df9bb19..24d2383400b0 100644 --- a/drivers/media/platform/ti/omap3isp/isp.c +++ b/drivers/media/platform/ti/omap3isp/isp.c @@ -937,10 +937,8 @@ static int isp_pipeline_is_last(struct media_entity *me) struct isp_pipeline *pipe; struct media_pad *pad; - if (!me->pipe) - return 0; pipe = to_isp_pipeline(me); - if (pipe->stream_state == ISP_PIPELINE_STREAM_STOPPED) + if (!pipe || pipe->stream_state == ISP_PIPELINE_STREAM_STOPPED) return 0; pad = media_pad_remote_pad_first(&pipe->output->pad); return pad->entity == me; diff --git a/drivers/media/platform/ti/omap3isp/ispvideo.c b/drivers/media/platform/ti/omap3isp/ispvideo.c index cc9a97d5d505..2e7f90603a5a 100644 --- a/drivers/media/platform/ti/omap3isp/ispvideo.c +++ b/drivers/media/platform/ti/omap3isp/ispvideo.c @@ -1093,8 +1093,7 @@ isp_video_streamon(struct file *file, void *fh, enum v4l2_buf_type type) /* Start streaming on the pipeline. No link touching an entity in the * pipeline can be activated or deactivated once streaming is started. */ - pipe = video->video.entity.pipe - ? to_isp_pipeline(&video->video.entity) : &video->pipe; + pipe = to_isp_pipeline(&video->video.entity) ? : &video->pipe; ret = media_entity_enum_init(&pipe->ent_enum, &video->isp->media_dev); if (ret) diff --git a/drivers/media/platform/ti/omap3isp/ispvideo.h b/drivers/media/platform/ti/omap3isp/ispvideo.h index a0908670c0cf..1d23df576e6b 100644 --- a/drivers/media/platform/ti/omap3isp/ispvideo.h +++ b/drivers/media/platform/ti/omap3isp/ispvideo.h @@ -99,8 +99,15 @@ struct isp_pipeline { unsigned int external_width; }; -#define to_isp_pipeline(__e) \ - container_of((__e)->pipe, struct isp_pipeline, pipe) +static inline struct isp_pipeline *to_isp_pipeline(struct media_entity *entity) +{ + struct media_pipeline *pipe = media_entity_pipeline(entity); + + if (!pipe) + return NULL; + + return container_of(pipe, struct isp_pipeline, pipe); +} static inline int isp_pipeline_ready(struct isp_pipeline *pipe) { diff --git a/drivers/media/platform/xilinx/xilinx-dma.c b/drivers/media/platform/xilinx/xilinx-dma.c index 2d1ef7a25c33..3a4d62be0f27 100644 --- a/drivers/media/platform/xilinx/xilinx-dma.c +++ b/drivers/media/platform/xilinx/xilinx-dma.c @@ -402,8 +402,7 @@ static int xvip_dma_start_streaming(struct vb2_queue *vq, unsigned int count) * Use the pipeline object embedded in the first DMA object that starts * streaming. */ - pipe = dma->video.entity.pipe - ? to_xvip_pipeline(&dma->video.entity) : &dma->pipe; + pipe = to_xvip_pipeline(&dma->video.entity) ? : &dma->pipe; ret = media_pipeline_start(&dma->video.entity, &pipe->pipe); if (ret < 0) diff --git a/drivers/media/platform/xilinx/xilinx-dma.h b/drivers/media/platform/xilinx/xilinx-dma.h index 2378bdae57ae..3ea10f6b0bb9 100644 --- a/drivers/media/platform/xilinx/xilinx-dma.h +++ b/drivers/media/platform/xilinx/xilinx-dma.h @@ -47,7 +47,12 @@ struct xvip_pipeline { static inline struct xvip_pipeline *to_xvip_pipeline(struct media_entity *e) { - return container_of(e->pipe, struct xvip_pipeline, pipe); + struct media_pipeline *pipe = media_entity_pipeline(e); + + if (!pipe) + return NULL; + + return container_of(pipe, struct xvip_pipeline, pipe); } /** diff --git a/drivers/staging/media/imx/imx-media-utils.c b/drivers/staging/media/imx/imx-media-utils.c index 294c808b2ebe..e9a3c6d2c66f 100644 --- a/drivers/staging/media/imx/imx-media-utils.c +++ b/drivers/staging/media/imx/imx-media-utils.c @@ -871,7 +871,7 @@ int imx_media_pipeline_set_stream(struct imx_media_dev *imxmd, __media_pipeline_stop(entity); } else { v4l2_subdev_call(sd, video, s_stream, 0); - if (entity->pipe) + if (media_entity_pipeline(entity)) __media_pipeline_stop(entity); } diff --git a/drivers/staging/media/omap4iss/iss.c b/drivers/staging/media/omap4iss/iss.c index 28aacda0f5a7..fa2a36d829d3 100644 --- a/drivers/staging/media/omap4iss/iss.c +++ b/drivers/staging/media/omap4iss/iss.c @@ -548,10 +548,8 @@ static int iss_pipeline_is_last(struct media_entity *me) struct iss_pipeline *pipe; struct media_pad *pad; - if (!me->pipe) - return 0; pipe = to_iss_pipeline(me); - if (pipe->stream_state == ISS_PIPELINE_STREAM_STOPPED) + if (!pipe || pipe->stream_state == ISS_PIPELINE_STREAM_STOPPED) return 0; pad = media_pad_remote_pad_first(&pipe->output->pad); return pad->entity == me; diff --git a/drivers/staging/media/omap4iss/iss_video.c b/drivers/staging/media/omap4iss/iss_video.c index 842509dcfedf..7967a42a3ffa 100644 --- a/drivers/staging/media/omap4iss/iss_video.c +++ b/drivers/staging/media/omap4iss/iss_video.c @@ -870,8 +870,7 @@ iss_video_streamon(struct file *file, void *fh, enum v4l2_buf_type type) * Start streaming on the pipeline. No link touching an entity in the * pipeline can be activated or deactivated once streaming is started. */ - pipe = entity->pipe - ? to_iss_pipeline(entity) : &video->pipe; + pipe = to_iss_pipeline(&video->video.entity) ? : &video->pipe; pipe->external = NULL; pipe->external_rate = 0; pipe->external_bpp = 0; diff --git a/drivers/staging/media/omap4iss/iss_video.h b/drivers/staging/media/omap4iss/iss_video.h index 526281bf0051..ca2d5edb6261 100644 --- a/drivers/staging/media/omap4iss/iss_video.h +++ b/drivers/staging/media/omap4iss/iss_video.h @@ -90,8 +90,15 @@ struct iss_pipeline { int external_bpp; }; -#define to_iss_pipeline(__e) \ - container_of((__e)->pipe, struct iss_pipeline, pipe) +static inline struct iss_pipeline *to_iss_pipeline(struct media_entity *entity) +{ + struct media_pipeline *pipe = media_entity_pipeline(entity); + + if (!pipe) + return NULL; + + return container_of(pipe, struct iss_pipeline, pipe); +} static inline int iss_pipeline_ready(struct iss_pipeline *pipe) { diff --git a/include/media/media-entity.h b/include/media/media-entity.h index 1030e45e8ee6..aaf276f765cf 100644 --- a/include/media/media-entity.h +++ b/include/media/media-entity.h @@ -948,6 +948,24 @@ static inline bool media_entity_is_streaming(const struct media_entity *entity) return entity->pipe; } +/** + * media_entity_pipeline - Get the media pipeline an entity is part of + * @entity: The entity + * + * This function returns the media pipeline that an entity has been associated + * with when constructing the pipeline with media_pipeline_start(). The pointer + * remains valid until media_pipeline_stop() is called. + * + * In general, entities can be part of multiple pipelines, when carrying + * multiple streams (either on different pads, or on the same pad using + * multiplexed streams). This function is to be used only for entities that + * do not support multiple pipelines. + * + * Return: The media_pipeline the entity is part of, or NULL if the entity is + * not part of any pipeline. + */ +struct media_pipeline *media_entity_pipeline(struct media_entity *entity); + /** * media_entity_get_fwnode_pad - Get pad number from fwnode * -- cgit v1.2.3 From 340eba477f0e51bed997e94bd3c2b728a0c6e1ac Mon Sep 17 00:00:00 2001 From: Tomi Valkeinen Date: Wed, 31 Aug 2022 16:13:32 +0200 Subject: media: v4l2-dev: Add videodev wrappers for media pipelines With the upcoming stream related improvements to the pipelines, the pipelines are moved from media entities to media pads. As the drivers currently use the pipelines with the entity based model, moving the pipelines to pads will cause changes to the drivers. However, most of the uses of media pipelines are related to a video device (a DMA engine) with a single pad, and thus there's never a need to support multiple pads in these use cases. We can avoid pushing the complexities of the pad based model to the drivers by adding video device wrappers for the pipeline related functions. This patch adds a number of wrappers to media_pipeline functions, all of which take a video_device as a parameter (instead of a media_entity), and verify that there's just one pad. Signed-off-by: Tomi Valkeinen Reviewed-by: Laurent Pinchart Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- drivers/media/v4l2-core/v4l2-dev.c | 61 ++++++++++++++++++++++++++ include/media/v4l2-dev.h | 88 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 149 insertions(+) (limited to 'include') diff --git a/drivers/media/v4l2-core/v4l2-dev.c b/drivers/media/v4l2-core/v4l2-dev.c index d00237ee4cae..7f933ff89fd4 100644 --- a/drivers/media/v4l2-core/v4l2-dev.c +++ b/drivers/media/v4l2-core/v4l2-dev.c @@ -1095,6 +1095,67 @@ void video_unregister_device(struct video_device *vdev) } EXPORT_SYMBOL(video_unregister_device); +#if defined(CONFIG_MEDIA_CONTROLLER) + +__must_check int video_device_pipeline_start(struct video_device *vdev, + struct media_pipeline *pipe) +{ + struct media_entity *entity = &vdev->entity; + + if (entity->num_pads != 1) + return -ENODEV; + + return media_pipeline_start(entity, pipe); +} +EXPORT_SYMBOL_GPL(video_device_pipeline_start); + +__must_check int __video_device_pipeline_start(struct video_device *vdev, + struct media_pipeline *pipe) +{ + struct media_entity *entity = &vdev->entity; + + if (entity->num_pads != 1) + return -ENODEV; + + return __media_pipeline_start(entity, pipe); +} +EXPORT_SYMBOL_GPL(__video_device_pipeline_start); + +void video_device_pipeline_stop(struct video_device *vdev) +{ + struct media_entity *entity = &vdev->entity; + + if (WARN_ON(entity->num_pads != 1)) + return; + + return media_pipeline_stop(entity); +} +EXPORT_SYMBOL_GPL(video_device_pipeline_stop); + +void __video_device_pipeline_stop(struct video_device *vdev) +{ + struct media_entity *entity = &vdev->entity; + + if (WARN_ON(entity->num_pads != 1)) + return; + + return __media_pipeline_stop(entity); +} +EXPORT_SYMBOL_GPL(__video_device_pipeline_stop); + +struct media_pipeline *video_device_pipeline(struct video_device *vdev) +{ + struct media_entity *entity = &vdev->entity; + + if (WARN_ON(entity->num_pads != 1)) + return NULL; + + return media_entity_pipeline(entity); +} +EXPORT_SYMBOL_GPL(video_device_pipeline); + +#endif /* CONFIG_MEDIA_CONTROLLER */ + /* * Initialise video for linux */ diff --git a/include/media/v4l2-dev.h b/include/media/v4l2-dev.h index 5cf1edefb822..494685872254 100644 --- a/include/media/v4l2-dev.h +++ b/include/media/v4l2-dev.h @@ -539,4 +539,92 @@ static inline int video_is_registered(struct video_device *vdev) return test_bit(V4L2_FL_REGISTERED, &vdev->flags); } +#if defined(CONFIG_MEDIA_CONTROLLER) + +/** + * video_device_pipeline_start - Mark a pipeline as streaming + * @vdev: Starting video device + * @pipe: Media pipeline to be assigned to all entities in the pipeline. + * + * Mark all entities connected to a given video device through enabled links, + * either directly or indirectly, as streaming. The given pipeline object is + * assigned to every entity in the pipeline and stored in the media_entity pipe + * field. + * + * Calls to this function can be nested, in which case the same number of + * video_device_pipeline_stop() calls will be required to stop streaming. The + * pipeline pointer must be identical for all nested calls to + * video_device_pipeline_start(). + * + * The video device must contain a single pad. + * + * This is a convenience wrapper around media_pipeline_start(). + */ +__must_check int video_device_pipeline_start(struct video_device *vdev, + struct media_pipeline *pipe); + +/** + * __video_device_pipeline_start - Mark a pipeline as streaming + * @vdev: Starting video device + * @pipe: Media pipeline to be assigned to all entities in the pipeline. + * + * ..note:: This is the non-locking version of video_device_pipeline_start() + * + * The video device must contain a single pad. + * + * This is a convenience wrapper around __media_pipeline_start(). + */ +__must_check int __video_device_pipeline_start(struct video_device *vdev, + struct media_pipeline *pipe); + +/** + * video_device_pipeline_stop - Mark a pipeline as not streaming + * @vdev: Starting video device + * + * Mark all entities connected to a given video device through enabled links, + * either directly or indirectly, as not streaming. The media_entity pipe field + * is reset to %NULL. + * + * If multiple calls to media_pipeline_start() have been made, the same + * number of calls to this function are required to mark the pipeline as not + * streaming. + * + * The video device must contain a single pad. + * + * This is a convenience wrapper around media_pipeline_stop(). + */ +void video_device_pipeline_stop(struct video_device *vdev); + +/** + * __video_device_pipeline_stop - Mark a pipeline as not streaming + * @vdev: Starting video device + * + * .. note:: This is the non-locking version of media_pipeline_stop() + * + * The video device must contain a single pad. + * + * This is a convenience wrapper around __media_pipeline_stop(). + */ +void __video_device_pipeline_stop(struct video_device *vdev); + +/** + * video_device_pipeline - Get the media pipeline a video device is part of + * @vdev: The video device + * + * This function returns the media pipeline that a video device has been + * associated with when constructing the pipeline with + * video_device_pipeline_start(). The pointer remains valid until + * video_device_pipeline_stop() is called. + * + * Return: The media_pipeline the video device is part of, or NULL if the video + * device is not part of any pipeline. + * + * The video device must contain a single pad. + * + * This is a convenience wrapper around media_entity_pipeline(). + */ +struct media_pipeline *video_device_pipeline(struct video_device *vdev); + +#endif /* CONFIG_MEDIA_CONTROLLER */ + #endif /* _V4L2_DEV_H */ -- cgit v1.2.3 From d9f4434513b499ddb8ba8617fba787b1ce98274e Mon Sep 17 00:00:00 2001 From: Tomi Valkeinen Date: Wed, 31 Aug 2022 16:13:35 +0200 Subject: media: mc: entity: add alloc variant of pipeline_start Add new variant of media_pipeline_start(), media_pipeline_alloc_start(). media_pipeline_alloc_start() can be used by drivers that do not need to extend the media_pipeline. The function will either use the pipeline already associated with the entity, if such exists, or allocate a new pipeline. When media_pipeline_stop() is called and the pipeline's use count drops to zero, the pipeline is automatically freed. Signed-off-by: Tomi Valkeinen Reviewed-by: Laurent Pinchart Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- drivers/media/mc/mc-entity.c | 38 ++++++++++++++++++++++++++++++++++++++ drivers/media/v4l2-core/v4l2-dev.c | 11 +++++++++++ include/media/media-entity.h | 15 +++++++++++++++ include/media/v4l2-dev.h | 14 ++++++++++++++ 4 files changed, 78 insertions(+) (limited to 'include') diff --git a/drivers/media/mc/mc-entity.c b/drivers/media/mc/mc-entity.c index 7fb97c6dc897..ad153a426a36 100644 --- a/drivers/media/mc/mc-entity.c +++ b/drivers/media/mc/mc-entity.c @@ -530,6 +530,8 @@ void __media_pipeline_stop(struct media_entity *entity) media_graph_walk_cleanup(graph); + if (pipe->allocated) + kfree(pipe); } EXPORT_SYMBOL_GPL(__media_pipeline_stop); @@ -543,6 +545,42 @@ void media_pipeline_stop(struct media_entity *entity) } EXPORT_SYMBOL_GPL(media_pipeline_stop); +__must_check int media_pipeline_alloc_start(struct media_entity *entity) +{ + struct media_device *mdev = entity->graph_obj.mdev; + struct media_pipeline *new_pipe = NULL; + struct media_pipeline *pipe; + int ret; + + mutex_lock(&mdev->graph_mutex); + + /* + * Is the entity already part of a pipeline? If not, we need to allocate + * a pipe. + */ + pipe = media_entity_pipeline(entity); + if (!pipe) { + new_pipe = kzalloc(sizeof(*new_pipe), GFP_KERNEL); + if (!new_pipe) { + ret = -ENOMEM; + goto out; + } + + pipe = new_pipe; + pipe->allocated = true; + } + + ret = __media_pipeline_start(entity, pipe); + if (ret) + kfree(new_pipe); + +out: + mutex_unlock(&mdev->graph_mutex); + + return ret; +} +EXPORT_SYMBOL_GPL(media_pipeline_alloc_start); + /* ----------------------------------------------------------------------------- * Links management */ diff --git a/drivers/media/v4l2-core/v4l2-dev.c b/drivers/media/v4l2-core/v4l2-dev.c index 7f933ff89fd4..945bb867a4c1 100644 --- a/drivers/media/v4l2-core/v4l2-dev.c +++ b/drivers/media/v4l2-core/v4l2-dev.c @@ -1143,6 +1143,17 @@ void __video_device_pipeline_stop(struct video_device *vdev) } EXPORT_SYMBOL_GPL(__video_device_pipeline_stop); +__must_check int video_device_pipeline_alloc_start(struct video_device *vdev) +{ + struct media_entity *entity = &vdev->entity; + + if (entity->num_pads != 1) + return -ENODEV; + + return media_pipeline_alloc_start(entity); +} +EXPORT_SYMBOL_GPL(video_device_pipeline_alloc_start); + struct media_pipeline *video_device_pipeline(struct video_device *vdev) { struct media_entity *entity = &vdev->entity; diff --git a/include/media/media-entity.h b/include/media/media-entity.h index aaf276f765cf..a77933afaa48 100644 --- a/include/media/media-entity.h +++ b/include/media/media-entity.h @@ -100,10 +100,12 @@ struct media_graph { /** * struct media_pipeline - Media pipeline related information * + * @allocated: Media pipeline allocated and freed by the framework * @start_count: Media pipeline start - stop count * @graph: Media graph walk during pipeline start / stop */ struct media_pipeline { + bool allocated; int start_count; struct media_graph graph; }; @@ -1092,6 +1094,19 @@ void media_pipeline_stop(struct media_entity *entity); */ void __media_pipeline_stop(struct media_entity *entity); +/** + * media_pipeline_alloc_start - Mark a pipeline as streaming + * @entity: Starting entity + * + * media_pipeline_alloc_start() is similar to media_pipeline_start() but instead + * of working on a given pipeline the function will use an existing pipeline if + * the entity is already part of a pipeline, or allocate a new pipeline. + * + * Calls to media_pipeline_alloc_start() must be matched with + * media_pipeline_stop(). + */ +__must_check int media_pipeline_alloc_start(struct media_entity *entity); + /** * media_devnode_create() - creates and initializes a device node interface * diff --git a/include/media/v4l2-dev.h b/include/media/v4l2-dev.h index 494685872254..643da0740ab0 100644 --- a/include/media/v4l2-dev.h +++ b/include/media/v4l2-dev.h @@ -607,6 +607,20 @@ void video_device_pipeline_stop(struct video_device *vdev); */ void __video_device_pipeline_stop(struct video_device *vdev); +/** + * video_device_pipeline_alloc_start - Mark a pipeline as streaming + * @vdev: Starting video device + * + * video_device_pipeline_alloc_start() is similar to video_device_pipeline_start() + * but instead of working on a given pipeline the function will use an + * existing pipeline if the video device is already part of a pipeline, or + * allocate a new pipeline. + * + * Calls to video_device_pipeline_alloc_start() must be matched with + * video_device_pipeline_stop(). + */ +__must_check int video_device_pipeline_alloc_start(struct video_device *vdev); + /** * video_device_pipeline - Get the media pipeline a video device is part of * @vdev: The video device -- cgit v1.2.3 From ae219872834a32da88408a92a4b4745c11f5a7ce Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Wed, 31 Aug 2022 16:13:37 +0200 Subject: media: mc: entity: Rewrite media_pipeline_start() [Note: the code is mostly from Laurent but the patch description is from Tomi] The media_pipeline_start() and media_pipeline_stop() functions use the media graph walk API to traverse the graph and validate the pipeline. The graph walk traverses the media graph following links between the entities. Also, while the pipeline can't change between the start and stop calls, the graph is walked again from scratch at stop time, or any time a driver needs to inspect the pipeline. With the upcoming multiplexed streams support we will need a bit more intelligent pipeline construction, as e.g. two independent streams may be passing through a single entity via separate pads in which case those pads should not be part of the same pipeline. This patch essentially rewrites the media_pipeline_start/stop so that a pipeline is defined as a set of pads instead of entities and the media graph traversal considers the pad interdependencies when choosing which links to follow. Currently all the entity's pads are considered as interdependent. This means that the behavior with all the current drivers stays the same, but in the future we can define a more fine-grained pipeline construction. Additionally the media pipeline's pads are cached at media_pipeline_start() time, and re-used at media_pipeline_stop() which avoid the need to re-walk the whole graph as the previous implementation did. Also, caching pads in the pipeline can serve in the future as the foundation to provide a better API than the media graph walk to drivers to iterate over pads and entities in the pipeline. Note that the old media_pipeline_start/stop used the media graph walk API. The new version does not use the media graph walk API, but instead a new implementation. There are two reasons for not changing the graph walk: it proved to be rather difficult to change the graph walk to have the features implemented in this patch, and second, this keeps the backward compatibility of the graph walk as there are users of the graph walk API The long term plan is that all the existing code would be converted to use the new cached pipeline, thus allowing us to remove the graph walk. Signed-off-by: Laurent Pinchart Signed-off-by: Tomi Valkeinen Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- Documentation/driver-api/media/mc-core.rst | 7 +- drivers/media/mc/mc-entity.c | 517 ++++++++++++++++++++++++----- include/media/media-entity.h | 71 +++- 3 files changed, 509 insertions(+), 86 deletions(-) (limited to 'include') diff --git a/Documentation/driver-api/media/mc-core.rst b/Documentation/driver-api/media/mc-core.rst index 4bb062d5c2e7..400b8ca29367 100644 --- a/Documentation/driver-api/media/mc-core.rst +++ b/Documentation/driver-api/media/mc-core.rst @@ -230,14 +230,13 @@ When starting streaming, drivers must notify all entities in the pipeline to prevent link states from being modified during streaming by calling :c:func:`media_pipeline_start()`. -The function will mark all entities connected to the given entity through -enabled links, either directly or indirectly, as streaming. +The function will mark all the pads which are part of the pipeline as streaming. The struct media_pipeline instance pointed to by -the pipe argument will be stored in every entity in the pipeline. +the pipe argument will be stored in every pad in the pipeline. Drivers should embed the struct media_pipeline in higher-level pipeline structures and can then access the -pipeline through the struct media_entity +pipeline through the struct media_pad pipe field. Calls to :c:func:`media_pipeline_start()` can be nested. diff --git a/drivers/media/mc/mc-entity.c b/drivers/media/mc/mc-entity.c index ad153a426a36..0a5c92b8bbce 100644 --- a/drivers/media/mc/mc-entity.c +++ b/drivers/media/mc/mc-entity.c @@ -226,6 +226,27 @@ EXPORT_SYMBOL_GPL(media_entity_pads_init); * Graph traversal */ +/* + * This function checks the interdependency inside the entity between @pad0 + * and @pad1. If two pads are interdependent they are part of the same pipeline + * and enabling one of the pads means that the other pad will become "locked" + * and doesn't allow configuration changes. + * + * For the time being all pads are considered interdependent. + */ +static bool media_entity_has_pad_interdep(struct media_entity *entity, + unsigned int pad0, unsigned int pad1) +{ + if (pad0 >= entity->num_pads || pad1 >= entity->num_pads) + return false; + + if (entity->pads[pad0].flags & entity->pads[pad1].flags & + (MEDIA_PAD_FL_SINK | MEDIA_PAD_FL_SOURCE)) + return false; + + return true; +} + static struct media_entity * media_entity_other(struct media_entity *entity, struct media_link *link) { @@ -374,97 +395,436 @@ EXPORT_SYMBOL_GPL(media_graph_walk_next); * Pipeline management */ +/* + * The pipeline traversal stack stores pads that are reached during graph + * traversal, with a list of links to be visited to continue the traversal. + * When a new pad is reached, an entry is pushed on the top of the stack and + * points to the incoming pad and the first link of the entity. + * + * To find further pads in the pipeline, the traversal algorithm follows + * internal pad dependencies in the entity, and then links in the graph. It + * does so by iterating over all links of the entity, and following enabled + * links that originate from a pad that is internally connected to the incoming + * pad, as reported by the media_entity_has_pad_interdep() function. + */ + +/** + * struct media_pipeline_walk_entry - Entry in the pipeline traversal stack + * + * @pad: The media pad being visited + * @links: Links left to be visited + */ +struct media_pipeline_walk_entry { + struct media_pad *pad; + struct list_head *links; +}; + +/** + * struct media_pipeline_walk - State used by the media pipeline traversal + * algorithm + * + * @mdev: The media device + * @stack: Depth-first search stack + * @stack.size: Number of allocated entries in @stack.entries + * @stack.top: Index of the top stack entry (-1 if the stack is empty) + * @stack.entries: Stack entries + */ +struct media_pipeline_walk { + struct media_device *mdev; + + struct { + unsigned int size; + int top; + struct media_pipeline_walk_entry *entries; + } stack; +}; + +#define MEDIA_PIPELINE_STACK_GROW_STEP 16 + +static struct media_pipeline_walk_entry * +media_pipeline_walk_top(struct media_pipeline_walk *walk) +{ + return &walk->stack.entries[walk->stack.top]; +} + +static bool media_pipeline_walk_empty(struct media_pipeline_walk *walk) +{ + return walk->stack.top == -1; +} + +/* Increase the stack size by MEDIA_PIPELINE_STACK_GROW_STEP elements. */ +static int media_pipeline_walk_resize(struct media_pipeline_walk *walk) +{ + struct media_pipeline_walk_entry *entries; + unsigned int new_size; + + /* Safety check, to avoid stack overflows in case of bugs. */ + if (walk->stack.size >= 256) + return -E2BIG; + + new_size = walk->stack.size + MEDIA_PIPELINE_STACK_GROW_STEP; + + entries = krealloc(walk->stack.entries, + new_size * sizeof(*walk->stack.entries), + GFP_KERNEL); + if (!entries) + return -ENOMEM; + + walk->stack.entries = entries; + walk->stack.size = new_size; + + return 0; +} + +/* Push a new entry on the stack. */ +static int media_pipeline_walk_push(struct media_pipeline_walk *walk, + struct media_pad *pad) +{ + struct media_pipeline_walk_entry *entry; + int ret; + + if (walk->stack.top + 1 >= walk->stack.size) { + ret = media_pipeline_walk_resize(walk); + if (ret) + return ret; + } + + walk->stack.top++; + entry = media_pipeline_walk_top(walk); + entry->pad = pad; + entry->links = pad->entity->links.next; + + dev_dbg(walk->mdev->dev, + "media pipeline: pushed entry %u: '%s':%u\n", + walk->stack.top, pad->entity->name, pad->index); + + return 0; +} + +/* + * Move the top entry link cursor to the next link. If all links of the entry + * have been visited, pop the entry itself. + */ +static void media_pipeline_walk_pop(struct media_pipeline_walk *walk) +{ + struct media_pipeline_walk_entry *entry; + + if (WARN_ON(walk->stack.top < 0)) + return; + + entry = media_pipeline_walk_top(walk); + + if (entry->links->next == &entry->pad->entity->links) { + dev_dbg(walk->mdev->dev, + "media pipeline: entry %u has no more links, popping\n", + walk->stack.top); + + walk->stack.top--; + return; + } + + entry->links = entry->links->next; + + dev_dbg(walk->mdev->dev, + "media pipeline: moved entry %u to next link\n", + walk->stack.top); +} + +/* Free all memory allocated while walking the pipeline. */ +static void media_pipeline_walk_destroy(struct media_pipeline_walk *walk) +{ + kfree(walk->stack.entries); +} + +/* Add a pad to the pipeline and push it to the stack. */ +static int media_pipeline_add_pad(struct media_pipeline *pipe, + struct media_pipeline_walk *walk, + struct media_pad *pad) +{ + struct media_pipeline_pad *ppad; + + list_for_each_entry(ppad, &pipe->pads, list) { + if (ppad->pad == pad) { + dev_dbg(pad->graph_obj.mdev->dev, + "media pipeline: already contains pad '%s':%u\n", + pad->entity->name, pad->index); + return 0; + } + } + + ppad = kzalloc(sizeof(*ppad), GFP_KERNEL); + if (!ppad) + return -ENOMEM; + + ppad->pipe = pipe; + ppad->pad = pad; + + list_add_tail(&ppad->list, &pipe->pads); + + dev_dbg(pad->graph_obj.mdev->dev, + "media pipeline: added pad '%s':%u\n", + pad->entity->name, pad->index); + + return media_pipeline_walk_push(walk, pad); +} + +/* Explore the next link of the entity at the top of the stack. */ +static int media_pipeline_explore_next_link(struct media_pipeline *pipe, + struct media_pipeline_walk *walk) +{ + struct media_pipeline_walk_entry *entry = media_pipeline_walk_top(walk); + struct media_pad *pad; + struct media_link *link; + struct media_pad *local; + struct media_pad *remote; + int ret; + + pad = entry->pad; + link = list_entry(entry->links, typeof(*link), list); + media_pipeline_walk_pop(walk); + + dev_dbg(walk->mdev->dev, + "media pipeline: exploring link '%s':%u -> '%s':%u\n", + link->source->entity->name, link->source->index, + link->sink->entity->name, link->sink->index); + + /* Skip links that are not enabled. */ + if (!(link->flags & MEDIA_LNK_FL_ENABLED)) { + dev_dbg(walk->mdev->dev, + "media pipeline: skipping link (disabled)\n"); + return 0; + } + + /* Get the local pad and remote pad. */ + if (link->source->entity == pad->entity) { + local = link->source; + remote = link->sink; + } else { + local = link->sink; + remote = link->source; + } + + /* + * Skip links that originate from a different pad than the incoming pad + * that is not connected internally in the entity to the incoming pad. + */ + if (pad != local && + !media_entity_has_pad_interdep(pad->entity, pad->index, local->index)) { + dev_dbg(walk->mdev->dev, + "media pipeline: skipping link (no route)\n"); + return 0; + } + + /* + * Add the local and remote pads of the link to the pipeline and push + * them to the stack, if they're not already present. + */ + ret = media_pipeline_add_pad(pipe, walk, local); + if (ret) + return ret; + + ret = media_pipeline_add_pad(pipe, walk, remote); + if (ret) + return ret; + + return 0; +} + +static void media_pipeline_cleanup(struct media_pipeline *pipe) +{ + while (!list_empty(&pipe->pads)) { + struct media_pipeline_pad *ppad; + + ppad = list_first_entry(&pipe->pads, typeof(*ppad), list); + list_del(&ppad->list); + kfree(ppad); + } +} + +static int media_pipeline_populate(struct media_pipeline *pipe, + struct media_pad *pad) +{ + struct media_pipeline_walk walk = { }; + struct media_pipeline_pad *ppad; + int ret; + + /* + * Populate the media pipeline by walking the media graph, starting + * from @pad. + */ + INIT_LIST_HEAD(&pipe->pads); + pipe->mdev = pad->graph_obj.mdev; + + walk.mdev = pipe->mdev; + walk.stack.top = -1; + ret = media_pipeline_add_pad(pipe, &walk, pad); + if (ret) + goto done; + + /* + * Use a depth-first search algorithm: as long as the stack is not + * empty, explore the next link of the top entry. The + * media_pipeline_explore_next_link() function will either move to the + * next link, pop the entry if fully visited, or add new entries on + * top. + */ + while (!media_pipeline_walk_empty(&walk)) { + ret = media_pipeline_explore_next_link(pipe, &walk); + if (ret) + goto done; + } + + dev_dbg(pad->graph_obj.mdev->dev, + "media pipeline populated, found pads:\n"); + + list_for_each_entry(ppad, &pipe->pads, list) + dev_dbg(pad->graph_obj.mdev->dev, "- '%s':%u\n", + ppad->pad->entity->name, ppad->pad->index); + + WARN_ON(walk.stack.top != -1); + + ret = 0; + +done: + media_pipeline_walk_destroy(&walk); + + if (ret) + media_pipeline_cleanup(pipe); + + return ret; +} + __must_check int __media_pipeline_start(struct media_entity *entity, struct media_pipeline *pipe) { struct media_device *mdev = entity->graph_obj.mdev; - struct media_graph *graph = &pipe->graph; - struct media_entity *entity_err = entity; - struct media_link *link; + struct media_pipeline_pad *err_ppad; + struct media_pipeline_pad *ppad; int ret; + lockdep_assert_held(&mdev->graph_mutex); + + /* + * media_pipeline_start(entity) only makes sense with entities that have + * a single pad. + */ + + if (WARN_ON(entity->num_pads != 1)) + return -EINVAL; + + /* + * If the entity is already part of a pipeline, that pipeline must + * be the same as the pipe given to media_pipeline_start(). + */ + if (WARN_ON(entity->pads->pipe && entity->pads->pipe != pipe)) + return -EINVAL; + + /* + * If the pipeline has already been started, it is guaranteed to be + * valid, so just increase the start count. + */ if (pipe->start_count) { pipe->start_count++; return 0; } - ret = media_graph_walk_init(&pipe->graph, mdev); + /* + * Populate the pipeline. This populates the media_pipeline pads list + * with media_pipeline_pad instances for each pad found during graph + * walk. + */ + ret = media_pipeline_populate(pipe, entity->pads); if (ret) return ret; - media_graph_walk_start(&pipe->graph, entity); + /* + * Now that all the pads in the pipeline have been gathered, perform + * the validation steps. + */ + + list_for_each_entry(ppad, &pipe->pads, list) { + struct media_pad *pad = ppad->pad; + struct media_entity *entity = pad->entity; + bool has_enabled_link = false; + bool has_link = false; + struct media_link *link; - while ((entity = media_graph_walk_next(graph))) { - DECLARE_BITMAP(active, MEDIA_ENTITY_MAX_PADS); - DECLARE_BITMAP(has_no_links, MEDIA_ENTITY_MAX_PADS); + dev_dbg(mdev->dev, "Validating pad '%s':%u\n", pad->entity->name, + pad->index); - if (entity->pipe && entity->pipe != pipe) { - pr_err("Pipe active for %s. Can't start for %s\n", - entity->name, - entity_err->name); + /* + * 1. Ensure that the pad doesn't already belong to a different + * pipeline. + */ + if (pad->pipe) { + dev_dbg(mdev->dev, "Failed to start pipeline: pad '%s':%u busy\n", + pad->entity->name, pad->index); ret = -EBUSY; goto error; } - /* Already streaming --- no need to check. */ - if (entity->pipe) - continue; - - entity->pipe = pipe; - - if (!entity->ops || !entity->ops->link_validate) - continue; - - bitmap_zero(active, entity->num_pads); - bitmap_fill(has_no_links, entity->num_pads); - + /* + * 2. Validate all active links whose sink is the current pad. + * Validation of the source pads is performed in the context of + * the connected sink pad to avoid duplicating checks. + */ for_each_media_entity_data_link(entity, link) { - struct media_pad *pad = link->sink->entity == entity - ? link->sink : link->source; + /* Skip links unrelated to the current pad. */ + if (link->sink != pad && link->source != pad) + continue; - /* Mark that a pad is connected by a link. */ - bitmap_clear(has_no_links, pad->index, 1); + /* Record if the pad has links and enabled links. */ + if (link->flags & MEDIA_LNK_FL_ENABLED) + has_enabled_link = true; + has_link = true; /* - * Pads that either do not need to connect or - * are connected through an enabled link are - * fine. + * Validate the link if it's enabled and has the + * current pad as its sink. */ - if (!(pad->flags & MEDIA_PAD_FL_MUST_CONNECT) || - link->flags & MEDIA_LNK_FL_ENABLED) - bitmap_set(active, pad->index, 1); + if (!(link->flags & MEDIA_LNK_FL_ENABLED)) + continue; - /* - * Link validation will only take place for - * sink ends of the link that are enabled. - */ - if (link->sink != pad || - !(link->flags & MEDIA_LNK_FL_ENABLED)) + if (link->sink != pad) + continue; + + if (!entity->ops || !entity->ops->link_validate) continue; ret = entity->ops->link_validate(link); - if (ret < 0 && ret != -ENOIOCTLCMD) { - dev_dbg(entity->graph_obj.mdev->dev, - "link validation failed for '%s':%u -> '%s':%u, error %d\n", + if (ret) { + dev_dbg(mdev->dev, + "Link '%s':%u -> '%s':%u failed validation: %d\n", link->source->entity->name, link->source->index, - entity->name, link->sink->index, ret); + link->sink->entity->name, + link->sink->index, ret); goto error; } - } - /* Either no links or validated links are fine. */ - bitmap_or(active, active, has_no_links, entity->num_pads); + dev_dbg(mdev->dev, + "Link '%s':%u -> '%s':%u is valid\n", + link->source->entity->name, + link->source->index, + link->sink->entity->name, + link->sink->index); + } - if (!bitmap_full(active, entity->num_pads)) { + /* + * 3. If the pad has the MEDIA_PAD_FL_MUST_CONNECT flag set, + * ensure that it has either no link or an enabled link. + */ + if ((pad->flags & MEDIA_PAD_FL_MUST_CONNECT) && has_link && + !has_enabled_link) { + dev_dbg(mdev->dev, + "Pad '%s':%u must be connected by an enabled link\n", + pad->entity->name, pad->index); ret = -ENOLINK; - dev_dbg(entity->graph_obj.mdev->dev, - "'%s':%u must be connected by an enabled link\n", - entity->name, - (unsigned)find_first_zero_bit( - active, entity->num_pads)); goto error; } + + /* Validation passed, store the pipe pointer in the pad. */ + pad->pipe = pipe; } pipe->start_count++; @@ -476,20 +836,15 @@ error: * Link validation on graph failed. We revert what we did and * return the error. */ - media_graph_walk_start(graph, entity_err); - - while ((entity_err = media_graph_walk_next(graph))) { - entity_err->pipe = NULL; - /* - * We haven't started entities further than this so we quit - * here. - */ - if (entity_err == entity) + list_for_each_entry(err_ppad, &pipe->pads, list) { + if (err_ppad == ppad) break; + + err_ppad->pad->pipe = NULL; } - media_graph_walk_cleanup(graph); + media_pipeline_cleanup(pipe); return ret; } @@ -510,8 +865,8 @@ EXPORT_SYMBOL_GPL(media_pipeline_start); void __media_pipeline_stop(struct media_entity *entity) { - struct media_graph *graph = &entity->pipe->graph; - struct media_pipeline *pipe = entity->pipe; + struct media_pipeline *pipe = entity->pads->pipe; + struct media_pipeline_pad *ppad; /* * If the following check fails, the driver has performed an @@ -523,12 +878,10 @@ void __media_pipeline_stop(struct media_entity *entity) if (--pipe->start_count) return; - media_graph_walk_start(graph, entity); + list_for_each_entry(ppad, &pipe->pads, list) + ppad->pad->pipe = NULL; - while ((entity = media_graph_walk_next(graph))) - entity->pipe = NULL; - - media_graph_walk_cleanup(graph); + media_pipeline_cleanup(pipe); if (pipe->allocated) kfree(pipe); @@ -835,7 +1188,7 @@ int __media_entity_setup_link(struct media_link *link, u32 flags) { const u32 mask = MEDIA_LNK_FL_ENABLED; struct media_device *mdev; - struct media_entity *source, *sink; + struct media_pad *source, *sink; int ret = -EBUSY; if (link == NULL) @@ -851,12 +1204,11 @@ int __media_entity_setup_link(struct media_link *link, u32 flags) if (link->flags == flags) return 0; - source = link->source->entity; - sink = link->sink->entity; + source = link->source; + sink = link->sink; if (!(link->flags & MEDIA_LNK_FL_DYNAMIC) && - (media_entity_is_streaming(source) || - media_entity_is_streaming(sink))) + (media_pad_is_streaming(source) || media_pad_is_streaming(sink))) return -EBUSY; mdev = source->graph_obj.mdev; @@ -1034,10 +1386,23 @@ EXPORT_SYMBOL_GPL(media_entity_get_fwnode_pad); struct media_pipeline *media_entity_pipeline(struct media_entity *entity) { - return entity->pipe; + struct media_pad *pad; + + media_entity_for_each_pad(entity, pad) { + if (pad->pipe) + return pad->pipe; + } + + return NULL; } EXPORT_SYMBOL_GPL(media_entity_pipeline); +struct media_pipeline *media_pad_pipeline(struct media_pad *pad) +{ + return pad->pipe; +} +EXPORT_SYMBOL_GPL(media_pad_pipeline); + static void media_interface_init(struct media_device *mdev, struct media_interface *intf, u32 gobj_type, diff --git a/include/media/media-entity.h b/include/media/media-entity.h index a77933afaa48..00990b20b3d5 100644 --- a/include/media/media-entity.h +++ b/include/media/media-entity.h @@ -101,13 +101,33 @@ struct media_graph { * struct media_pipeline - Media pipeline related information * * @allocated: Media pipeline allocated and freed by the framework + * @mdev: The media device the pipeline is part of + * @pads: List of media_pipeline_pad * @start_count: Media pipeline start - stop count - * @graph: Media graph walk during pipeline start / stop */ struct media_pipeline { bool allocated; + struct media_device *mdev; + struct list_head pads; int start_count; - struct media_graph graph; +}; + +/** + * struct media_pipeline_pad - A pad part of a media pipeline + * + * @list: Entry in the media_pad pads list + * @pipe: The media_pipeline that the pad is part of + * @pad: The media pad + * + * This structure associate a pad with a media pipeline. Instances of + * media_pipeline_pad are created by media_pipeline_start() when it builds the + * pipeline, and stored in the &media_pad.pads list. media_pipeline_stop() + * removes the entries from the list and deletes them. + */ +struct media_pipeline_pad { + struct list_head list; + struct media_pipeline *pipe; + struct media_pad *pad; }; /** @@ -189,6 +209,8 @@ enum media_pad_signal_type { * @flags: Pad flags, as defined in * :ref:`include/uapi/linux/media.h ` * (seek for ``MEDIA_PAD_FL_*``) + * @pipe: Pipeline this pad belongs to. Use media_entity_pipeline() to + * access this field. */ struct media_pad { struct media_gobj graph_obj; /* must be first field in struct */ @@ -196,6 +218,12 @@ struct media_pad { u16 index; enum media_pad_signal_type sig_type; unsigned long flags; + + /* + * The fields below are private, and should only be accessed via + * appropriate functions. + */ + struct media_pipeline *pipe; }; /** @@ -272,7 +300,6 @@ enum media_entity_type { * @links: List of data links. * @ops: Entity operations. * @use_count: Use count for the entity. - * @pipe: Pipeline this entity belongs to. * @info: Union with devnode information. Kept just for backward * compatibility. * @info.dev: Contains device major and minor info. @@ -308,8 +335,6 @@ struct media_entity { int use_count; - struct media_pipeline *pipe; - union { struct { u32 major; @@ -938,6 +963,18 @@ media_entity_remote_source_pad_unique(const struct media_entity *entity) return media_entity_remote_pad_unique(entity, MEDIA_PAD_FL_SOURCE); } +/** + * media_pad_is_streaming - Test if a pad is part of a streaming pipeline + * @pad: The pad + * + * Return: True if the pad is part of a pipeline started with the + * media_pipeline_start() function, false otherwise. + */ +static inline bool media_pad_is_streaming(const struct media_pad *pad) +{ + return pad->pipe; +} + /** * media_entity_is_streaming - Test if an entity is part of a streaming pipeline * @entity: The entity @@ -947,13 +984,22 @@ media_entity_remote_source_pad_unique(const struct media_entity *entity) */ static inline bool media_entity_is_streaming(const struct media_entity *entity) { - return entity->pipe; + struct media_pad *pad; + + media_entity_for_each_pad(entity, pad) { + if (media_pad_is_streaming(pad)) + return true; + } + + return false; } /** * media_entity_pipeline - Get the media pipeline an entity is part of * @entity: The entity * + * DEPRECATED: use media_pad_pipeline() instead. + * * This function returns the media pipeline that an entity has been associated * with when constructing the pipeline with media_pipeline_start(). The pointer * remains valid until media_pipeline_stop() is called. @@ -968,6 +1014,19 @@ static inline bool media_entity_is_streaming(const struct media_entity *entity) */ struct media_pipeline *media_entity_pipeline(struct media_entity *entity); +/** + * media_pad_pipeline - Get the media pipeline a pad is part of + * @pad: The pad + * + * This function returns the media pipeline that a pad has been associated + * with when constructing the pipeline with media_pipeline_start(). The pointer + * remains valid until media_pipeline_stop() is called. + * + * Return: The media_pipeline the pad is part of, or NULL if the pad is + * not part of any pipeline. + */ +struct media_pipeline *media_pad_pipeline(struct media_pad *pad); + /** * media_entity_get_fwnode_pad - Get pad number from fwnode * -- cgit v1.2.3 From 5b4f9a727532ff9732ffc1bceb2017260b81a0ff Mon Sep 17 00:00:00 2001 From: Tomi Valkeinen Date: Wed, 31 Aug 2022 16:13:38 +0200 Subject: media: mc: entity: Add has_pad_interdep entity operation Add a new media entity operation, has_pad_interdep. The optional op is used to discover the pad interdependencies inside an entity during the pipeline construction. Signed-off-by: Tomi Valkeinen Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- drivers/media/mc/mc-entity.c | 10 ++++++++-- include/media/media-entity.h | 10 ++++++++++ 2 files changed, 18 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/media/mc/mc-entity.c b/drivers/media/mc/mc-entity.c index 0a5c92b8bbce..831076b36847 100644 --- a/drivers/media/mc/mc-entity.c +++ b/drivers/media/mc/mc-entity.c @@ -232,7 +232,10 @@ EXPORT_SYMBOL_GPL(media_entity_pads_init); * and enabling one of the pads means that the other pad will become "locked" * and doesn't allow configuration changes. * - * For the time being all pads are considered interdependent. + * This function uses the &media_entity_operations.has_pad_interdep() operation + * to check the dependency inside the entity between @pad0 and @pad1. If the + * has_pad_interdep operation is not implemented, all pads of the entity are + * considered to be interdependent. */ static bool media_entity_has_pad_interdep(struct media_entity *entity, unsigned int pad0, unsigned int pad1) @@ -244,7 +247,10 @@ static bool media_entity_has_pad_interdep(struct media_entity *entity, (MEDIA_PAD_FL_SINK | MEDIA_PAD_FL_SOURCE)) return false; - return true; + if (!entity->ops || !entity->ops->has_pad_interdep) + return true; + + return entity->ops->has_pad_interdep(entity, pad0, pad1); } static struct media_entity * diff --git a/include/media/media-entity.h b/include/media/media-entity.h index 00990b20b3d5..8e9fd309aa65 100644 --- a/include/media/media-entity.h +++ b/include/media/media-entity.h @@ -237,6 +237,14 @@ struct media_pad { * @link_validate: Return whether a link is valid from the entity point of * view. The media_pipeline_start() function * validates all links by calling this operation. Optional. + * @has_pad_interdep: Return whether a two pads inside the entity are + * interdependent. If two pads are interdependent they are + * part of the same pipeline and enabling one of the pads + * means that the other pad will become "locked" and + * doesn't allow configuration changes. pad0 and pad1 are + * guaranteed to not both be sinks or sources. + * Optional: If the operation isn't implemented all pads + * will be considered as interdependent. * * .. note:: * @@ -250,6 +258,8 @@ struct media_entity_operations { const struct media_pad *local, const struct media_pad *remote, u32 flags); int (*link_validate)(struct media_link *link); + bool (*has_pad_interdep)(struct media_entity *entity, unsigned int pad0, + unsigned int pad1); }; /** -- cgit v1.2.3 From 9e3576a1ae2bb67c4d09d5e6c002fb793c300b58 Mon Sep 17 00:00:00 2001 From: Tomi Valkeinen Date: Wed, 31 Aug 2022 16:13:39 +0200 Subject: media: mc: convert pipeline funcs to take media_pad Now that the pipeline is stored into pads instead of entities, we can change the relevant functions to take pads instead of entities. Signed-off-by: Tomi Valkeinen Reviewed-by: Laurent Pinchart Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- drivers/media/mc/mc-entity.c | 40 +++++++++------------- .../platform/samsung/s3c-camif/camif-capture.c | 6 ++-- drivers/media/usb/au0828/au0828-core.c | 8 ++--- drivers/media/v4l2-core/v4l2-dev.c | 12 +++---- drivers/staging/media/imx/imx-media-utils.c | 8 ++--- include/media/media-entity.h | 34 +++++++++--------- include/media/v4l2-dev.h | 4 +-- 7 files changed, 52 insertions(+), 60 deletions(-) (limited to 'include') diff --git a/drivers/media/mc/mc-entity.c b/drivers/media/mc/mc-entity.c index 831076b36847..b8bcbc734eaf 100644 --- a/drivers/media/mc/mc-entity.c +++ b/drivers/media/mc/mc-entity.c @@ -700,29 +700,21 @@ done: return ret; } -__must_check int __media_pipeline_start(struct media_entity *entity, +__must_check int __media_pipeline_start(struct media_pad *pad, struct media_pipeline *pipe) { - struct media_device *mdev = entity->graph_obj.mdev; + struct media_device *mdev = pad->entity->graph_obj.mdev; struct media_pipeline_pad *err_ppad; struct media_pipeline_pad *ppad; int ret; lockdep_assert_held(&mdev->graph_mutex); - /* - * media_pipeline_start(entity) only makes sense with entities that have - * a single pad. - */ - - if (WARN_ON(entity->num_pads != 1)) - return -EINVAL; - /* * If the entity is already part of a pipeline, that pipeline must * be the same as the pipe given to media_pipeline_start(). */ - if (WARN_ON(entity->pads->pipe && entity->pads->pipe != pipe)) + if (WARN_ON(pad->pipe && pad->pipe != pipe)) return -EINVAL; /* @@ -739,7 +731,7 @@ __must_check int __media_pipeline_start(struct media_entity *entity, * with media_pipeline_pad instances for each pad found during graph * walk. */ - ret = media_pipeline_populate(pipe, entity->pads); + ret = media_pipeline_populate(pipe, pad); if (ret) return ret; @@ -856,22 +848,22 @@ error: } EXPORT_SYMBOL_GPL(__media_pipeline_start); -__must_check int media_pipeline_start(struct media_entity *entity, +__must_check int media_pipeline_start(struct media_pad *pad, struct media_pipeline *pipe) { - struct media_device *mdev = entity->graph_obj.mdev; + struct media_device *mdev = pad->entity->graph_obj.mdev; int ret; mutex_lock(&mdev->graph_mutex); - ret = __media_pipeline_start(entity, pipe); + ret = __media_pipeline_start(pad, pipe); mutex_unlock(&mdev->graph_mutex); return ret; } EXPORT_SYMBOL_GPL(media_pipeline_start); -void __media_pipeline_stop(struct media_entity *entity) +void __media_pipeline_stop(struct media_pad *pad) { - struct media_pipeline *pipe = entity->pads->pipe; + struct media_pipeline *pipe = pad->pipe; struct media_pipeline_pad *ppad; /* @@ -894,19 +886,19 @@ void __media_pipeline_stop(struct media_entity *entity) } EXPORT_SYMBOL_GPL(__media_pipeline_stop); -void media_pipeline_stop(struct media_entity *entity) +void media_pipeline_stop(struct media_pad *pad) { - struct media_device *mdev = entity->graph_obj.mdev; + struct media_device *mdev = pad->entity->graph_obj.mdev; mutex_lock(&mdev->graph_mutex); - __media_pipeline_stop(entity); + __media_pipeline_stop(pad); mutex_unlock(&mdev->graph_mutex); } EXPORT_SYMBOL_GPL(media_pipeline_stop); -__must_check int media_pipeline_alloc_start(struct media_entity *entity) +__must_check int media_pipeline_alloc_start(struct media_pad *pad) { - struct media_device *mdev = entity->graph_obj.mdev; + struct media_device *mdev = pad->entity->graph_obj.mdev; struct media_pipeline *new_pipe = NULL; struct media_pipeline *pipe; int ret; @@ -917,7 +909,7 @@ __must_check int media_pipeline_alloc_start(struct media_entity *entity) * Is the entity already part of a pipeline? If not, we need to allocate * a pipe. */ - pipe = media_entity_pipeline(entity); + pipe = media_pad_pipeline(pad); if (!pipe) { new_pipe = kzalloc(sizeof(*new_pipe), GFP_KERNEL); if (!new_pipe) { @@ -929,7 +921,7 @@ __must_check int media_pipeline_alloc_start(struct media_entity *entity) pipe->allocated = true; } - ret = __media_pipeline_start(entity, pipe); + ret = __media_pipeline_start(pad, pipe); if (ret) kfree(new_pipe); diff --git a/drivers/media/platform/samsung/s3c-camif/camif-capture.c b/drivers/media/platform/samsung/s3c-camif/camif-capture.c index c2d8f1e425d8..db106ebdf870 100644 --- a/drivers/media/platform/samsung/s3c-camif/camif-capture.c +++ b/drivers/media/platform/samsung/s3c-camif/camif-capture.c @@ -848,13 +848,13 @@ static int s3c_camif_streamon(struct file *file, void *priv, if (s3c_vp_active(vp)) return 0; - ret = media_pipeline_start(sensor, camif->m_pipeline); + ret = media_pipeline_start(sensor->pads, camif->m_pipeline); if (ret < 0) return ret; ret = camif_pipeline_validate(camif); if (ret < 0) { - media_pipeline_stop(sensor); + media_pipeline_stop(sensor->pads); return ret; } @@ -878,7 +878,7 @@ static int s3c_camif_streamoff(struct file *file, void *priv, ret = vb2_streamoff(&vp->vb_queue, type); if (ret == 0) - media_pipeline_stop(&camif->sensor.sd->entity); + media_pipeline_stop(camif->sensor.sd->entity.pads); return ret; } diff --git a/drivers/media/usb/au0828/au0828-core.c b/drivers/media/usb/au0828/au0828-core.c index caefac07af92..877e85a451cb 100644 --- a/drivers/media/usb/au0828/au0828-core.c +++ b/drivers/media/usb/au0828/au0828-core.c @@ -410,7 +410,7 @@ static int au0828_enable_source(struct media_entity *entity, goto end; } - ret = __media_pipeline_start(entity, pipe); + ret = __media_pipeline_start(entity->pads, pipe); if (ret) { pr_err("Start Pipeline: %s->%s Error %d\n", source->name, entity->name, ret); @@ -501,12 +501,12 @@ static void au0828_disable_source(struct media_entity *entity) return; /* stop pipeline */ - __media_pipeline_stop(dev->active_link_owner); + __media_pipeline_stop(dev->active_link_owner->pads); pr_debug("Pipeline stop for %s\n", dev->active_link_owner->name); ret = __media_pipeline_start( - dev->active_link_user, + dev->active_link_user->pads, dev->active_link_user_pipe); if (ret) { pr_err("Start Pipeline: %s->%s %d\n", @@ -532,7 +532,7 @@ static void au0828_disable_source(struct media_entity *entity) return; /* stop pipeline */ - __media_pipeline_stop(dev->active_link_owner); + __media_pipeline_stop(dev->active_link_owner->pads); pr_debug("Pipeline stop for %s\n", dev->active_link_owner->name); diff --git a/drivers/media/v4l2-core/v4l2-dev.c b/drivers/media/v4l2-core/v4l2-dev.c index 945bb867a4c1..397d553177fa 100644 --- a/drivers/media/v4l2-core/v4l2-dev.c +++ b/drivers/media/v4l2-core/v4l2-dev.c @@ -1105,7 +1105,7 @@ __must_check int video_device_pipeline_start(struct video_device *vdev, if (entity->num_pads != 1) return -ENODEV; - return media_pipeline_start(entity, pipe); + return media_pipeline_start(&entity->pads[0], pipe); } EXPORT_SYMBOL_GPL(video_device_pipeline_start); @@ -1117,7 +1117,7 @@ __must_check int __video_device_pipeline_start(struct video_device *vdev, if (entity->num_pads != 1) return -ENODEV; - return __media_pipeline_start(entity, pipe); + return __media_pipeline_start(&entity->pads[0], pipe); } EXPORT_SYMBOL_GPL(__video_device_pipeline_start); @@ -1128,7 +1128,7 @@ void video_device_pipeline_stop(struct video_device *vdev) if (WARN_ON(entity->num_pads != 1)) return; - return media_pipeline_stop(entity); + return media_pipeline_stop(&entity->pads[0]); } EXPORT_SYMBOL_GPL(video_device_pipeline_stop); @@ -1139,7 +1139,7 @@ void __video_device_pipeline_stop(struct video_device *vdev) if (WARN_ON(entity->num_pads != 1)) return; - return __media_pipeline_stop(entity); + return __media_pipeline_stop(&entity->pads[0]); } EXPORT_SYMBOL_GPL(__video_device_pipeline_stop); @@ -1150,7 +1150,7 @@ __must_check int video_device_pipeline_alloc_start(struct video_device *vdev) if (entity->num_pads != 1) return -ENODEV; - return media_pipeline_alloc_start(entity); + return media_pipeline_alloc_start(&entity->pads[0]); } EXPORT_SYMBOL_GPL(video_device_pipeline_alloc_start); @@ -1161,7 +1161,7 @@ struct media_pipeline *video_device_pipeline(struct video_device *vdev) if (WARN_ON(entity->num_pads != 1)) return NULL; - return media_entity_pipeline(entity); + return media_pad_pipeline(&entity->pads[0]); } EXPORT_SYMBOL_GPL(video_device_pipeline); diff --git a/drivers/staging/media/imx/imx-media-utils.c b/drivers/staging/media/imx/imx-media-utils.c index e9a3c6d2c66f..3e7462112649 100644 --- a/drivers/staging/media/imx/imx-media-utils.c +++ b/drivers/staging/media/imx/imx-media-utils.c @@ -863,16 +863,16 @@ int imx_media_pipeline_set_stream(struct imx_media_dev *imxmd, mutex_lock(&imxmd->md.graph_mutex); if (on) { - ret = __media_pipeline_start(entity, &imxmd->pipe); + ret = __media_pipeline_start(entity->pads, &imxmd->pipe); if (ret) goto out; ret = v4l2_subdev_call(sd, video, s_stream, 1); if (ret) - __media_pipeline_stop(entity); + __media_pipeline_stop(entity->pads); } else { v4l2_subdev_call(sd, video, s_stream, 0); - if (media_entity_pipeline(entity)) - __media_pipeline_stop(entity); + if (media_pad_pipeline(entity->pads)) + __media_pipeline_stop(entity->pads); } out: diff --git a/include/media/media-entity.h b/include/media/media-entity.h index 8e9fd309aa65..28c9de8a1f34 100644 --- a/include/media/media-entity.h +++ b/include/media/media-entity.h @@ -1115,66 +1115,66 @@ struct media_entity *media_graph_walk_next(struct media_graph *graph); /** * media_pipeline_start - Mark a pipeline as streaming - * @entity: Starting entity - * @pipe: Media pipeline to be assigned to all entities in the pipeline. + * @pad: Starting pad + * @pipe: Media pipeline to be assigned to all pads in the pipeline. * - * Mark all entities connected to a given entity through enabled links, either + * Mark all pads connected to a given pad through enabled links, either * directly or indirectly, as streaming. The given pipeline object is assigned - * to every entity in the pipeline and stored in the media_entity pipe field. + * to every pad in the pipeline and stored in the media_pad pipe field. * * Calls to this function can be nested, in which case the same number of * media_pipeline_stop() calls will be required to stop streaming. The * pipeline pointer must be identical for all nested calls to * media_pipeline_start(). */ -__must_check int media_pipeline_start(struct media_entity *entity, +__must_check int media_pipeline_start(struct media_pad *pad, struct media_pipeline *pipe); /** * __media_pipeline_start - Mark a pipeline as streaming * - * @entity: Starting entity - * @pipe: Media pipeline to be assigned to all entities in the pipeline. + * @pad: Starting pad + * @pipe: Media pipeline to be assigned to all pads in the pipeline. * * ..note:: This is the non-locking version of media_pipeline_start() */ -__must_check int __media_pipeline_start(struct media_entity *entity, +__must_check int __media_pipeline_start(struct media_pad *pad, struct media_pipeline *pipe); /** * media_pipeline_stop - Mark a pipeline as not streaming - * @entity: Starting entity + * @pad: Starting pad * - * Mark all entities connected to a given entity through enabled links, either - * directly or indirectly, as not streaming. The media_entity pipe field is + * Mark all pads connected to a given pads through enabled links, either + * directly or indirectly, as not streaming. The media_pad pipe field is * reset to %NULL. * * If multiple calls to media_pipeline_start() have been made, the same * number of calls to this function are required to mark the pipeline as not * streaming. */ -void media_pipeline_stop(struct media_entity *entity); +void media_pipeline_stop(struct media_pad *pad); /** * __media_pipeline_stop - Mark a pipeline as not streaming * - * @entity: Starting entity + * @pad: Starting pad * * .. note:: This is the non-locking version of media_pipeline_stop() */ -void __media_pipeline_stop(struct media_entity *entity); +void __media_pipeline_stop(struct media_pad *pad); /** * media_pipeline_alloc_start - Mark a pipeline as streaming - * @entity: Starting entity + * @pad: Starting pad * * media_pipeline_alloc_start() is similar to media_pipeline_start() but instead * of working on a given pipeline the function will use an existing pipeline if - * the entity is already part of a pipeline, or allocate a new pipeline. + * the pad is already part of a pipeline, or allocate a new pipeline. * * Calls to media_pipeline_alloc_start() must be matched with * media_pipeline_stop(). */ -__must_check int media_pipeline_alloc_start(struct media_entity *entity); +__must_check int media_pipeline_alloc_start(struct media_pad *pad); /** * media_devnode_create() - creates and initializes a device node interface diff --git a/include/media/v4l2-dev.h b/include/media/v4l2-dev.h index 643da0740ab0..e0a13505f88d 100644 --- a/include/media/v4l2-dev.h +++ b/include/media/v4l2-dev.h @@ -548,7 +548,7 @@ static inline int video_is_registered(struct video_device *vdev) * * Mark all entities connected to a given video device through enabled links, * either directly or indirectly, as streaming. The given pipeline object is - * assigned to every entity in the pipeline and stored in the media_entity pipe + * assigned to every pad in the pipeline and stored in the media_pad pipe * field. * * Calls to this function can be nested, in which case the same number of @@ -582,7 +582,7 @@ __must_check int __video_device_pipeline_start(struct video_device *vdev, * @vdev: Starting video device * * Mark all entities connected to a given video device through enabled links, - * either directly or indirectly, as not streaming. The media_entity pipe field + * either directly or indirectly, as not streaming. The media_pad pipe field * is reset to %NULL. * * If multiple calls to media_pipeline_start() have been made, the same -- cgit v1.2.3 From 39dfd52d0f481de42a435f9fb79c98b376c68c39 Mon Sep 17 00:00:00 2001 From: Daniel González Cabanelas Date: Mon, 7 Feb 2022 15:51:41 +0100 Subject: media: cx88: add IR remote support for NotOnlyTV LV3H MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The PCI hybrid card NotOnlyTV LV3H has a built-in IR receiver connected via I2C bus, currently not supported. This receiver is probably present in more Geniatech cards. It has no capability for repeating when a key is held down. Add support for this built-in IR receiver. Use the existing Total Media In Hand_02 remote keytable (Geniatech Mygica X8507) which matches exactly the LV3H remote. Signed-off-by: Daniel González Cabanelas Signed-off-by: Marek Kidawski Signed-off-by: Sean Young Signed-off-by: Mauro Carvalho Chehab --- drivers/media/i2c/ir-kbd-i2c.c | 47 +++++++++++++++++++++++++++++++++++++ drivers/media/pci/cx88/cx88-input.c | 2 +- drivers/media/pci/cx88/cx88-video.c | 1 + include/media/i2c/ir-kbd-i2c.h | 1 + 4 files changed, 50 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/media/i2c/ir-kbd-i2c.c b/drivers/media/i2c/ir-kbd-i2c.c index 56674173524f..a229e2d69ed6 100644 --- a/drivers/media/i2c/ir-kbd-i2c.c +++ b/drivers/media/i2c/ir-kbd-i2c.c @@ -238,6 +238,43 @@ static int get_key_knc1(struct IR_i2c *ir, enum rc_proto *protocol, return 1; } +static int get_key_geniatech(struct IR_i2c *ir, enum rc_proto *protocol, + u32 *scancode, u8 *toggle) +{ + int i, rc; + unsigned char b; + + /* poll IR chip */ + for (i = 0; i < 4; i++) { + rc = i2c_master_recv(ir->c, &b, 1); + if (rc == 1) + break; + msleep(20); + } + if (rc != 1) { + dev_dbg(&ir->rc->dev, "read error\n"); + if (rc < 0) + return rc; + return -EIO; + } + + /* don't repeat the key */ + if (ir->old == b) + return 0; + ir->old = b; + + /* decode to RC5 */ + b &= 0x7f; + b = (b - 1) / 2; + + dev_dbg(&ir->rc->dev, "key %02x\n", b); + + *protocol = RC_PROTO_RC5; + *scancode = b; + *toggle = ir->old >> 7; + return 1; +} + static int get_key_avermedia_cardbus(struct IR_i2c *ir, enum rc_proto *protocol, u32 *scancode, u8 *toggle) { @@ -766,6 +803,13 @@ static int ir_probe(struct i2c_client *client, const struct i2c_device_id *id) rc_proto = RC_PROTO_BIT_OTHER; ir_codes = RC_MAP_EMPTY; break; + case 0x33: + name = "Geniatech"; + ir->get_key = get_key_geniatech; + rc_proto = RC_PROTO_BIT_RC5; + ir_codes = RC_MAP_TOTAL_MEDIA_IN_HAND_02; + ir->old = 0xfc; + break; case 0x6b: name = "FusionHDTV"; ir->get_key = get_key_fusionhdtv; @@ -825,6 +869,9 @@ static int ir_probe(struct i2c_client *client, const struct i2c_device_id *id) case IR_KBD_GET_KEY_KNC1: ir->get_key = get_key_knc1; break; + case IR_KBD_GET_KEY_GENIATECH: + ir->get_key = get_key_geniatech; + break; case IR_KBD_GET_KEY_FUSIONHDTV: ir->get_key = get_key_fusionhdtv; break; diff --git a/drivers/media/pci/cx88/cx88-input.c b/drivers/media/pci/cx88/cx88-input.c index ce0ef0b8186f..a04a1d33fadb 100644 --- a/drivers/media/pci/cx88/cx88-input.c +++ b/drivers/media/pci/cx88/cx88-input.c @@ -586,7 +586,7 @@ void cx88_i2c_init_ir(struct cx88_core *core) { struct i2c_board_info info; static const unsigned short default_addr_list[] = { - 0x18, 0x6b, 0x71, + 0x18, 0x33, 0x6b, 0x71, I2C_CLIENT_END }; static const unsigned short pvr2000_addr_list[] = { diff --git a/drivers/media/pci/cx88/cx88-video.c b/drivers/media/pci/cx88/cx88-video.c index b509c2a03852..c0ef03ed74f9 100644 --- a/drivers/media/pci/cx88/cx88-video.c +++ b/drivers/media/pci/cx88/cx88-video.c @@ -1388,6 +1388,7 @@ static int cx8800_initdev(struct pci_dev *pci_dev, } fallthrough; case CX88_BOARD_DVICO_FUSIONHDTV_5_PCI_NANO: + case CX88_BOARD_NOTONLYTV_LV3H: request_module("ir-kbd-i2c"); } diff --git a/include/media/i2c/ir-kbd-i2c.h b/include/media/i2c/ir-kbd-i2c.h index 9f47d6a48cff..0b58f8b9e7a4 100644 --- a/include/media/i2c/ir-kbd-i2c.h +++ b/include/media/i2c/ir-kbd-i2c.h @@ -35,6 +35,7 @@ enum ir_kbd_get_key_fn { IR_KBD_GET_KEY_PIXELVIEW, IR_KBD_GET_KEY_HAUP, IR_KBD_GET_KEY_KNC1, + IR_KBD_GET_KEY_GENIATECH, IR_KBD_GET_KEY_FUSIONHDTV, IR_KBD_GET_KEY_HAUP_XVR, IR_KBD_GET_KEY_AVERMEDIA_CARDBUS, -- cgit v1.2.3 From b994d8f0773cf3b01129c094d00050710f2c422b Mon Sep 17 00:00:00 2001 From: Jonathan Neuschäfer Date: Sat, 8 Oct 2022 17:14:59 +0200 Subject: spi: spi-mem: Fix typo (of -> or) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In this instance, "or" makes more sense than "of", so I guess that "or" was intended and "of" was a typo. Signed-off-by: Jonathan Neuschäfer Link: https://lore.kernel.org/r/20221008151459.1421406-1-j.neuschaefer@gmx.net 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 2ba044d0d5e5..8e984d75f5b6 100644 --- a/include/linux/spi/spi-mem.h +++ b/include/linux/spi/spi-mem.h @@ -225,7 +225,7 @@ static inline void *spi_mem_get_drvdata(struct spi_mem *mem) /** * struct spi_controller_mem_ops - SPI memory operations * @adjust_op_size: shrink the data xfer of an operation to match controller's - * limitations (can be alignment of max RX/TX size + * limitations (can be alignment or max RX/TX size * limitations) * @supports_op: check if an operation is supported by the controller * @exec_op: execute a SPI memory operation -- cgit v1.2.3 From a6d1ce5951185ee91bbe6909fe2758f3625561b0 Mon Sep 17 00:00:00 2001 From: Yosry Ahmed Date: Tue, 11 Oct 2022 00:33:58 +0000 Subject: cgroup: add cgroup_v1v2_get_from_[fd/file]() Add cgroup_v1v2_get_from_fd() and cgroup_v1v2_get_from_file() that support both cgroup1 and cgroup2. Signed-off-by: Yosry Ahmed Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 1 + kernel/cgroup/cgroup.c | 50 ++++++++++++++++++++++++++++++++++++++++++++------ 2 files changed, 45 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 398f0bce7c21..a88de5bdeaa9 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -106,6 +106,7 @@ struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, struct cgroup *cgroup_get_from_path(const char *path); struct cgroup *cgroup_get_from_fd(int fd); +struct cgroup *cgroup_v1v2_get_from_fd(int fd); int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 6d8a5a40c24d..6349a9fe9ec1 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -6224,16 +6224,36 @@ void cgroup_fork(struct task_struct *child) INIT_LIST_HEAD(&child->cg_list); } -static struct cgroup *cgroup_get_from_file(struct file *f) +/** + * cgroup_v1v2_get_from_file - get a cgroup pointer from a file pointer + * @f: file corresponding to cgroup_dir + * + * Find the cgroup from a file pointer associated with a cgroup directory. + * Returns a pointer to the cgroup on success. ERR_PTR is returned if the + * cgroup cannot be found. + */ +static struct cgroup *cgroup_v1v2_get_from_file(struct file *f) { struct cgroup_subsys_state *css; - struct cgroup *cgrp; css = css_tryget_online_from_dir(f->f_path.dentry, NULL); if (IS_ERR(css)) return ERR_CAST(css); - cgrp = css->cgroup; + return css->cgroup; +} + +/** + * cgroup_get_from_file - same as cgroup_v1v2_get_from_file, but only supports + * cgroup2. + */ +static struct cgroup *cgroup_get_from_file(struct file *f) +{ + struct cgroup *cgrp = cgroup_v1v2_get_from_file(f); + + if (IS_ERR(cgrp)) + return ERR_CAST(cgrp); + if (!cgroup_on_dfl(cgrp)) { cgroup_put(cgrp); return ERR_PTR(-EBADF); @@ -6734,14 +6754,14 @@ EXPORT_SYMBOL_GPL(cgroup_get_from_path); /** * cgroup_get_from_fd - get a cgroup pointer from a fd - * @fd: fd obtained by open(cgroup2_dir) + * @fd: fd obtained by open(cgroup_dir) * * Find the cgroup from a fd which should be obtained * by opening a cgroup directory. Returns a pointer to the * cgroup on success. ERR_PTR is returned if the cgroup * cannot be found. */ -struct cgroup *cgroup_get_from_fd(int fd) +struct cgroup *cgroup_v1v2_get_from_fd(int fd) { struct cgroup *cgrp; struct file *f; @@ -6750,10 +6770,28 @@ struct cgroup *cgroup_get_from_fd(int fd) if (!f) return ERR_PTR(-EBADF); - cgrp = cgroup_get_from_file(f); + cgrp = cgroup_v1v2_get_from_file(f); fput(f); return cgrp; } + +/** + * cgroup_get_from_fd - same as cgroup_v1v2_get_from_fd, but only supports + * cgroup2. + */ +struct cgroup *cgroup_get_from_fd(int fd) +{ + struct cgroup *cgrp = cgroup_v1v2_get_from_fd(fd); + + if (IS_ERR(cgrp)) + return ERR_CAST(cgrp); + + if (!cgroup_on_dfl(cgrp)) { + cgroup_put(cgrp); + return ERR_PTR(-EBADF); + } + return cgrp; +} EXPORT_SYMBOL_GPL(cgroup_get_from_fd); static u64 power_of_ten(int power) -- cgit v1.2.3 From e25b091bed4946078c0998e4be77bc56824a9adf Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Sat, 8 Oct 2022 19:46:02 +0200 Subject: watchdog: Add tracing events for the most usual watchdog events MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit To simplify debugging which process touches a watchdog and when, add tracing events for .start(), .set_timeout(), .ping() and .stop(). Signed-off-by: Uwe Kleine-König Reviewed-by: Steven Rostedt (Google) Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20221008174602.3972859-1-u.kleine-koenig@pengutronix.de Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- MAINTAINERS | 1 + drivers/watchdog/watchdog_core.c | 4 +++ drivers/watchdog/watchdog_dev.c | 12 ++++++-- include/trace/events/watchdog.h | 66 ++++++++++++++++++++++++++++++++++++++++ 4 files changed, 81 insertions(+), 2 deletions(-) create mode 100644 include/trace/events/watchdog.h (limited to 'include') diff --git a/MAINTAINERS b/MAINTAINERS index 589517372408..9751746559dc 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -21864,6 +21864,7 @@ F: Documentation/watchdog/ F: drivers/watchdog/ F: include/linux/watchdog.h F: include/uapi/linux/watchdog.h +F: include/trace/events/watchdog.h WHISKEYCOVE PMIC GPIO DRIVER M: Kuppuswamy Sathyanarayanan diff --git a/drivers/watchdog/watchdog_core.c b/drivers/watchdog/watchdog_core.c index 3fe8a7edc252..c777a612d932 100644 --- a/drivers/watchdog/watchdog_core.c +++ b/drivers/watchdog/watchdog_core.c @@ -38,6 +38,9 @@ #include "watchdog_core.h" /* For watchdog_dev_register/... */ +#define CREATE_TRACE_POINTS +#include + static DEFINE_IDA(watchdog_ida); static int stop_on_reboot = -1; @@ -163,6 +166,7 @@ static int watchdog_reboot_notifier(struct notifier_block *nb, int ret; ret = wdd->ops->stop(wdd); + trace_watchdog_stop(wdd, ret); if (ret) return NOTIFY_BAD; } diff --git a/drivers/watchdog/watchdog_dev.c b/drivers/watchdog/watchdog_dev.c index 744b2ab75288..55574ed42504 100644 --- a/drivers/watchdog/watchdog_dev.c +++ b/drivers/watchdog/watchdog_dev.c @@ -47,6 +47,8 @@ #include "watchdog_core.h" #include "watchdog_pretimeout.h" +#include + /* the dev_t structure to store the dynamically allocated watchdog devices */ static dev_t watchdog_devt; /* Reference to watchdog device behind /dev/watchdog */ @@ -157,10 +159,13 @@ static int __watchdog_ping(struct watchdog_device *wdd) wd_data->last_hw_keepalive = now; - if (wdd->ops->ping) + if (wdd->ops->ping) { err = wdd->ops->ping(wdd); /* ping the watchdog */ - else + trace_watchdog_ping(wdd, err); + } else { err = wdd->ops->start(wdd); /* restart watchdog */ + trace_watchdog_start(wdd, err); + } if (err == 0) watchdog_hrtimer_pretimeout_start(wdd); @@ -259,6 +264,7 @@ static int watchdog_start(struct watchdog_device *wdd) } } else { err = wdd->ops->start(wdd); + trace_watchdog_start(wdd, err); if (err == 0) { set_bit(WDOG_ACTIVE, &wdd->status); wd_data->last_keepalive = started_at; @@ -297,6 +303,7 @@ static int watchdog_stop(struct watchdog_device *wdd) if (wdd->ops->stop) { clear_bit(WDOG_HW_RUNNING, &wdd->status); err = wdd->ops->stop(wdd); + trace_watchdog_stop(wdd, err); } else { set_bit(WDOG_HW_RUNNING, &wdd->status); } @@ -369,6 +376,7 @@ static int watchdog_set_timeout(struct watchdog_device *wdd, if (wdd->ops->set_timeout) { err = wdd->ops->set_timeout(wdd, timeout); + trace_watchdog_set_timeout(wdd, timeout, err); } else { wdd->timeout = timeout; /* Disable pretimeout if it doesn't fit the new timeout */ diff --git a/include/trace/events/watchdog.h b/include/trace/events/watchdog.h new file mode 100644 index 000000000000..beb9bb3424c8 --- /dev/null +++ b/include/trace/events/watchdog.h @@ -0,0 +1,66 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM watchdog + +#if !defined(_TRACE_WATCHDOG_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_WATCHDOG_H + +#include +#include + +DECLARE_EVENT_CLASS(watchdog_template, + + TP_PROTO(struct watchdog_device *wdd, int err), + + TP_ARGS(wdd, err), + + TP_STRUCT__entry( + __field(int, id) + __field(int, err) + ), + + TP_fast_assign( + __entry->id = wdd->id; + __entry->err = err; + ), + + TP_printk("watchdog%d err=%d", __entry->id, __entry->err) +); + +DEFINE_EVENT(watchdog_template, watchdog_start, + TP_PROTO(struct watchdog_device *wdd, int err), + TP_ARGS(wdd, err)); + +DEFINE_EVENT(watchdog_template, watchdog_ping, + TP_PROTO(struct watchdog_device *wdd, int err), + TP_ARGS(wdd, err)); + +DEFINE_EVENT(watchdog_template, watchdog_stop, + TP_PROTO(struct watchdog_device *wdd, int err), + TP_ARGS(wdd, err)); + +TRACE_EVENT(watchdog_set_timeout, + + TP_PROTO(struct watchdog_device *wdd, unsigned int timeout, int err), + + TP_ARGS(wdd, timeout, err), + + TP_STRUCT__entry( + __field(int, id) + __field(unsigned int, timeout) + __field(int, err) + ), + + TP_fast_assign( + __entry->id = wdd->id; + __entry->timeout = timeout; + __entry->err = err; + ), + + TP_printk("watchdog%d timeout=%u err=%d", __entry->id, __entry->timeout, __entry->err) +); + +#endif /* !defined(_TRACE_WATCHDOG_H) || defined(TRACE_HEADER_MULTI_READ) */ + +/* This part must be outside protection */ +#include -- cgit v1.2.3 From 43d2748394c3feb86c0c771466f5847e274fc043 Mon Sep 17 00:00:00 2001 From: Ashish Kalra Date: Wed, 5 Oct 2022 16:32:53 +0000 Subject: ACPI: APEI: Fix integer overflow in ghes_estatus_pool_init() Change num_ghes from int to unsigned int, preventing an overflow and causing subsequent vmalloc() to fail. The overflow happens in ghes_estatus_pool_init() when calculating len during execution of the statement below as both multiplication operands here are signed int: len += (num_ghes * GHES_ESOURCE_PREALLOC_MAX_SIZE); The following call trace is observed because of this bug: [ 9.317108] swapper/0: vmalloc error: size 18446744071562596352, exceeds total pages, mode:0xcc0(GFP_KERNEL), nodemask=(null),cpuset=/,mems_allowed=0-1 [ 9.317131] Call Trace: [ 9.317134] [ 9.317137] dump_stack_lvl+0x49/0x5f [ 9.317145] dump_stack+0x10/0x12 [ 9.317146] warn_alloc.cold+0x7b/0xdf [ 9.317150] ? __device_attach+0x16a/0x1b0 [ 9.317155] __vmalloc_node_range+0x702/0x740 [ 9.317160] ? device_add+0x17f/0x920 [ 9.317164] ? dev_set_name+0x53/0x70 [ 9.317166] ? platform_device_add+0xf9/0x240 [ 9.317168] __vmalloc_node+0x49/0x50 [ 9.317170] ? ghes_estatus_pool_init+0x43/0xa0 [ 9.317176] vmalloc+0x21/0x30 [ 9.317177] ghes_estatus_pool_init+0x43/0xa0 [ 9.317179] acpi_hest_init+0x129/0x19c [ 9.317185] acpi_init+0x434/0x4a4 [ 9.317188] ? acpi_sleep_proc_init+0x2a/0x2a [ 9.317190] do_one_initcall+0x48/0x200 [ 9.317195] kernel_init_freeable+0x221/0x284 [ 9.317200] ? rest_init+0xe0/0xe0 [ 9.317204] kernel_init+0x1a/0x130 [ 9.317205] ret_from_fork+0x22/0x30 [ 9.317208] Signed-off-by: Ashish Kalra [ rjw: Subject and changelog edits ] Signed-off-by: Rafael J. Wysocki --- drivers/acpi/apei/ghes.c | 2 +- include/acpi/ghes.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index 80ad530583c9..9952f3a792ba 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -163,7 +163,7 @@ static void ghes_unmap(void __iomem *vaddr, enum fixed_addresses fixmap_idx) clear_fixmap(fixmap_idx); } -int ghes_estatus_pool_init(int num_ghes) +int ghes_estatus_pool_init(unsigned int num_ghes) { unsigned long addr, len; int rc; diff --git a/include/acpi/ghes.h b/include/acpi/ghes.h index 34fb3431a8f3..292a5c40bd0c 100644 --- a/include/acpi/ghes.h +++ b/include/acpi/ghes.h @@ -71,7 +71,7 @@ int ghes_register_vendor_record_notifier(struct notifier_block *nb); void ghes_unregister_vendor_record_notifier(struct notifier_block *nb); #endif -int ghes_estatus_pool_init(int num_ghes); +int ghes_estatus_pool_init(unsigned int num_ghes); /* From drivers/edac/ghes_edac.c */ -- cgit v1.2.3 From a2550d3ce53c68f54042bc5e468c4d07491ffe0e Mon Sep 17 00:00:00 2001 From: Christian Marangi Date: Wed, 12 Oct 2022 19:18:36 +0200 Subject: net: dsa: qca8k: fix inband mgmt for big-endian systems The header and the data of the skb for the inband mgmt requires to be in little-endian. This is problematic for big-endian system as the mgmt header is written in the cpu byte order. Fix this by converting each value for the mgmt header and data to little-endian, and convert to cpu byte order the mgmt header and data sent by the switch. Fixes: 5950c7c0a68c ("net: dsa: qca8k: add support for mgmt read/write in Ethernet packet") Tested-by: Pawel Dembicki Tested-by: Lech Perczak Signed-off-by: Christian Marangi Reviewed-by: Lech Perczak Signed-off-by: David S. Miller --- drivers/net/dsa/qca/qca8k-8xxx.c | 63 ++++++++++++++++++++++++++++++---------- include/linux/dsa/tag_qca.h | 6 ++-- 2 files changed, 50 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/drivers/net/dsa/qca/qca8k-8xxx.c b/drivers/net/dsa/qca/qca8k-8xxx.c index 5669c92c93f7..644338ca0510 100644 --- a/drivers/net/dsa/qca/qca8k-8xxx.c +++ b/drivers/net/dsa/qca/qca8k-8xxx.c @@ -137,27 +137,42 @@ static void qca8k_rw_reg_ack_handler(struct dsa_switch *ds, struct sk_buff *skb) struct qca8k_mgmt_eth_data *mgmt_eth_data; struct qca8k_priv *priv = ds->priv; struct qca_mgmt_ethhdr *mgmt_ethhdr; + u32 command; u8 len, cmd; + int i; mgmt_ethhdr = (struct qca_mgmt_ethhdr *)skb_mac_header(skb); mgmt_eth_data = &priv->mgmt_eth_data; - cmd = FIELD_GET(QCA_HDR_MGMT_CMD, mgmt_ethhdr->command); - len = FIELD_GET(QCA_HDR_MGMT_LENGTH, mgmt_ethhdr->command); + command = get_unaligned_le32(&mgmt_ethhdr->command); + cmd = FIELD_GET(QCA_HDR_MGMT_CMD, command); + len = FIELD_GET(QCA_HDR_MGMT_LENGTH, command); /* Make sure the seq match the requested packet */ - if (mgmt_ethhdr->seq == mgmt_eth_data->seq) + if (get_unaligned_le32(&mgmt_ethhdr->seq) == mgmt_eth_data->seq) mgmt_eth_data->ack = true; if (cmd == MDIO_READ) { - mgmt_eth_data->data[0] = mgmt_ethhdr->mdio_data; + u32 *val = mgmt_eth_data->data; + + *val = get_unaligned_le32(&mgmt_ethhdr->mdio_data); /* Get the rest of the 12 byte of data. * The read/write function will extract the requested data. */ - if (len > QCA_HDR_MGMT_DATA1_LEN) - memcpy(mgmt_eth_data->data + 1, skb->data, - QCA_HDR_MGMT_DATA2_LEN); + if (len > QCA_HDR_MGMT_DATA1_LEN) { + __le32 *data2 = (__le32 *)skb->data; + int data_len = min_t(int, QCA_HDR_MGMT_DATA2_LEN, + len - QCA_HDR_MGMT_DATA1_LEN); + + val++; + + for (i = sizeof(u32); i <= data_len; i += sizeof(u32)) { + *val = get_unaligned_le32(data2); + val++; + data2++; + } + } } complete(&mgmt_eth_data->rw_done); @@ -169,8 +184,10 @@ static struct sk_buff *qca8k_alloc_mdio_header(enum mdio_cmd cmd, u32 reg, u32 * struct qca_mgmt_ethhdr *mgmt_ethhdr; unsigned int real_len; struct sk_buff *skb; - u32 *data2; + __le32 *data2; + u32 command; u16 hdr; + int i; skb = dev_alloc_skb(QCA_HDR_MGMT_PKT_LEN); if (!skb) @@ -199,20 +216,32 @@ static struct sk_buff *qca8k_alloc_mdio_header(enum mdio_cmd cmd, u32 reg, u32 * hdr |= FIELD_PREP(QCA_HDR_XMIT_DP_BIT, BIT(0)); hdr |= FIELD_PREP(QCA_HDR_XMIT_CONTROL, QCA_HDR_XMIT_TYPE_RW_REG); - mgmt_ethhdr->command = FIELD_PREP(QCA_HDR_MGMT_ADDR, reg); - mgmt_ethhdr->command |= FIELD_PREP(QCA_HDR_MGMT_LENGTH, real_len); - mgmt_ethhdr->command |= FIELD_PREP(QCA_HDR_MGMT_CMD, cmd); - mgmt_ethhdr->command |= FIELD_PREP(QCA_HDR_MGMT_CHECK_CODE, + command = FIELD_PREP(QCA_HDR_MGMT_ADDR, reg); + command |= FIELD_PREP(QCA_HDR_MGMT_LENGTH, real_len); + command |= FIELD_PREP(QCA_HDR_MGMT_CMD, cmd); + command |= FIELD_PREP(QCA_HDR_MGMT_CHECK_CODE, QCA_HDR_MGMT_CHECK_CODE_VAL); + put_unaligned_le32(command, &mgmt_ethhdr->command); + if (cmd == MDIO_WRITE) - mgmt_ethhdr->mdio_data = *val; + put_unaligned_le32(*val, &mgmt_ethhdr->mdio_data); mgmt_ethhdr->hdr = htons(hdr); data2 = skb_put_zero(skb, QCA_HDR_MGMT_DATA2_LEN + QCA_HDR_MGMT_PADDING_LEN); - if (cmd == MDIO_WRITE && len > QCA_HDR_MGMT_DATA1_LEN) - memcpy(data2, val + 1, len - QCA_HDR_MGMT_DATA1_LEN); + if (cmd == MDIO_WRITE && len > QCA_HDR_MGMT_DATA1_LEN) { + int data_len = min_t(int, QCA_HDR_MGMT_DATA2_LEN, + len - QCA_HDR_MGMT_DATA1_LEN); + + val++; + + for (i = sizeof(u32); i <= data_len; i += sizeof(u32)) { + put_unaligned_le32(*val, data2); + data2++; + val++; + } + } return skb; } @@ -220,9 +249,11 @@ static struct sk_buff *qca8k_alloc_mdio_header(enum mdio_cmd cmd, u32 reg, u32 * static void qca8k_mdio_header_fill_seq_num(struct sk_buff *skb, u32 seq_num) { struct qca_mgmt_ethhdr *mgmt_ethhdr; + u32 seq; + seq = FIELD_PREP(QCA_HDR_MGMT_SEQ_NUM, seq_num); mgmt_ethhdr = (struct qca_mgmt_ethhdr *)skb->data; - mgmt_ethhdr->seq = FIELD_PREP(QCA_HDR_MGMT_SEQ_NUM, seq_num); + put_unaligned_le32(seq, &mgmt_ethhdr->seq); } static int qca8k_read_eth(struct qca8k_priv *priv, u32 reg, u32 *val, int len) diff --git a/include/linux/dsa/tag_qca.h b/include/linux/dsa/tag_qca.h index 50be7cbd93a5..0e176da1e43f 100644 --- a/include/linux/dsa/tag_qca.h +++ b/include/linux/dsa/tag_qca.h @@ -61,9 +61,9 @@ struct sk_buff; /* Special struct emulating a Ethernet header */ struct qca_mgmt_ethhdr { - u32 command; /* command bit 31:0 */ - u32 seq; /* seq 63:32 */ - u32 mdio_data; /* first 4byte mdio */ + __le32 command; /* command bit 31:0 */ + __le32 seq; /* seq 63:32 */ + __le32 mdio_data; /* first 4byte mdio */ __be16 hdr; /* qca hdr */ } __packed; -- cgit v1.2.3 From 0d4636f7d72df3179b20a2d32b647881917a5e2a Mon Sep 17 00:00:00 2001 From: Christian Marangi Date: Wed, 12 Oct 2022 19:18:37 +0200 Subject: net: dsa: qca8k: fix ethtool autocast mib for big-endian systems The switch sends autocast mib in little-endian. This is problematic for big-endian system as the values needs to be converted. Fix this by converting each mib value to cpu byte order. Fixes: 5c957c7ca78c ("net: dsa: qca8k: add support for mib autocast in Ethernet packet") Tested-by: Pawel Dembicki Tested-by: Lech Perczak Signed-off-by: Christian Marangi Signed-off-by: David S. Miller --- drivers/net/dsa/qca/qca8k-8xxx.c | 20 ++++++++------------ include/linux/dsa/tag_qca.h | 2 +- 2 files changed, 9 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/drivers/net/dsa/qca/qca8k-8xxx.c b/drivers/net/dsa/qca/qca8k-8xxx.c index 644338ca0510..c5c3b4e92f28 100644 --- a/drivers/net/dsa/qca/qca8k-8xxx.c +++ b/drivers/net/dsa/qca/qca8k-8xxx.c @@ -1518,9 +1518,9 @@ static void qca8k_mib_autocast_handler(struct dsa_switch *ds, struct sk_buff *sk struct qca8k_priv *priv = ds->priv; const struct qca8k_mib_desc *mib; struct mib_ethhdr *mib_ethhdr; - int i, mib_len, offset = 0; - u64 *data; + __le32 *data2; u8 port; + int i; mib_ethhdr = (struct mib_ethhdr *)skb_mac_header(skb); mib_eth_data = &priv->mib_eth_data; @@ -1532,28 +1532,24 @@ static void qca8k_mib_autocast_handler(struct dsa_switch *ds, struct sk_buff *sk if (port != mib_eth_data->req_port) goto exit; - data = mib_eth_data->data; + data2 = (__le32 *)skb->data; for (i = 0; i < priv->info->mib_count; i++) { mib = &ar8327_mib[i]; /* First 3 mib are present in the skb head */ if (i < 3) { - data[i] = mib_ethhdr->data[i]; + mib_eth_data->data[i] = get_unaligned_le32(mib_ethhdr->data + i); continue; } - mib_len = sizeof(uint32_t); - /* Some mib are 64 bit wide */ if (mib->size == 2) - mib_len = sizeof(uint64_t); - - /* Copy the mib value from packet to the */ - memcpy(data + i, skb->data + offset, mib_len); + mib_eth_data->data[i] = get_unaligned_le64((__le64 *)data2); + else + mib_eth_data->data[i] = get_unaligned_le32(data2); - /* Set the offset for the next mib */ - offset += mib_len; + data2 += mib->size; } exit: diff --git a/include/linux/dsa/tag_qca.h b/include/linux/dsa/tag_qca.h index 0e176da1e43f..b1b5720d89a5 100644 --- a/include/linux/dsa/tag_qca.h +++ b/include/linux/dsa/tag_qca.h @@ -73,7 +73,7 @@ enum mdio_cmd { }; struct mib_ethhdr { - u32 data[3]; /* first 3 mib counter */ + __le32 data[3]; /* first 3 mib counter */ __be16 hdr; /* qca hdr */ } __packed; -- cgit v1.2.3 From fc8695eb11f07d936a4a9dbd15d7797986bc8b89 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 14 Oct 2022 09:07:46 -0700 Subject: Revert "net: fix cpu_max_bits_warn() usage in netif_attrmask_next{,_and}" This reverts commit 854701ba4c39afae2362ba19a580c461cb183e4f. We have more violations around, which leads to: WARNING: CPU: 2 PID: 1 at include/linux/cpumask.h:110 __netif_set_xps_queue+0x14e/0x770 Let's back this out and retry with a larger clean up in -next. Fixes: 854701ba4c39 ("net: fix cpu_max_bits_warn() usage in netif_attrmask_next{,_and}") Link: https://lore.kernel.org/all/20221014030459.3272206-2-guoren@kernel.org/ Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/netdevice.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a36edb0ec199..eddf8ee270e7 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3663,8 +3663,9 @@ static inline bool netif_attr_test_online(unsigned long j, static inline unsigned int netif_attrmask_next(int n, const unsigned long *srcp, unsigned int nr_bits) { - /* n is a prior cpu */ - cpu_max_bits_warn(n + 1, 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); @@ -3685,8 +3686,9 @@ static inline int netif_attrmask_next_and(int n, const unsigned long *src1p, const unsigned long *src2p, unsigned int nr_bits) { - /* n is a prior cpu */ - cpu_max_bits_warn(n + 1, 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); -- cgit v1.2.3 From 96de900ae78e7dbedc937fd91bafe2934579c65a Mon Sep 17 00:00:00 2001 From: Shenwei Wang Date: Fri, 14 Oct 2022 09:47:28 -0500 Subject: net: phylink: add mac_managed_pm in phylink_config structure The recent commit 'commit 744d23c71af3 ("net: phy: Warn about incorrect mdio_bus_phy_resume() state")' requires the MAC driver explicitly tell the phy driver who is managing the PM, otherwise you will see warning during resume stage. Add a boolean property in the phylink_config structure so that the MAC driver can use it to tell the PHY driver if it wants to manage the PM. Fixes: 744d23c71af3 ("net: phy: Warn about incorrect mdio_bus_phy_resume() state") Signed-off-by: Shenwei Wang Acked-by: Florian Fainelli Reviewed-by: Russell King (Oracle) Signed-off-by: David S. Miller --- drivers/net/phy/phylink.c | 3 +++ include/linux/phylink.h | 2 ++ 2 files changed, 5 insertions(+) (limited to 'include') diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 75464df191ef..6547b6cc6cbe 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -1661,6 +1661,9 @@ static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy, if (phy_interrupt_is_valid(phy)) phy_request_interrupt(phy); + if (pl->config->mac_managed_pm) + phy->mac_managed_pm = true; + return 0; } diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 664dd409feb9..3f01ac8017e0 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -122,6 +122,7 @@ enum phylink_op_type { * (See commit 7cceb599d15d ("net: phylink: avoid mac_config calls") * @poll_fixed_state: if true, starts link_poll, * if MAC link is at %MLO_AN_FIXED mode. + * @mac_managed_pm: if true, indicate the MAC driver is responsible for PHY PM. * @ovr_an_inband: if true, override PCS to MLO_AN_INBAND * @get_fixed_state: callback to execute to determine the fixed link state, * if MAC link is at %MLO_AN_FIXED mode. @@ -134,6 +135,7 @@ struct phylink_config { enum phylink_op_type type; bool legacy_pre_march2020; bool poll_fixed_state; + bool mac_managed_pm; bool ovr_an_inband; void (*get_fixed_state)(struct phylink_config *config, struct phylink_link_state *state); -- cgit v1.2.3 From 25b72d530e7aa185955196b63f53c38f751f1632 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 12 Oct 2022 12:18:54 -0700 Subject: fbdev: MIPS supports iomem addresses Add MIPS to fb_* helpers list for iomem addresses. This silences Sparse warnings about lacking __iomem address space casts: drivers/video/fbdev/pvr2fb.c:800:9: sparse: sparse: incorrect type in argument 1 (different address spaces) drivers/video/fbdev/pvr2fb.c:800:9: sparse: expected void const * drivers/video/fbdev/pvr2fb.c:800:9: sparse: got char [noderef] __iomem *screen_base Reported-by: kernel test robot Link: https://lore.kernel.org/lkml/202210100209.tR2Iqbqk-lkp@intel.com/ Cc: Helge Deller Cc: linux-fbdev@vger.kernel.org Cc: dri-devel@lists.freedesktop.org Signed-off-by: Kees Cook Signed-off-by: Helge Deller --- include/linux/fb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/fb.h b/include/linux/fb.h index 0aff76bcbb00..bcb8658f5b64 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -555,7 +555,7 @@ static inline struct apertures_struct *alloc_apertures(unsigned int max_num) { #elif defined(__i386__) || defined(__alpha__) || defined(__x86_64__) || \ defined(__hppa__) || defined(__sh__) || defined(__powerpc__) || \ - defined(__arm__) || defined(__aarch64__) + defined(__arm__) || defined(__aarch64__) || defined(__mips__) #define fb_readb __raw_readb #define fb_readw __raw_readw -- cgit v1.2.3 From 472a1482325b3a285e0bcf82c0b0edc689b7e8cd Mon Sep 17 00:00:00 2001 From: William Breathitt Gray Date: Sun, 2 Oct 2022 08:04:19 -0400 Subject: counter: Reduce DEFINE_COUNTER_ARRAY_POLARITY() to defining counter_array A spare warning was reported for drivers/counter/ti-ecap-capture.c:: sparse warnings: (new ones prefixed by >>) >> drivers/counter/ti-ecap-capture.c:380:8: sparse: sparse: symbol 'ecap_cnt_pol_array' was not declared. Should it be static? vim +/ecap_cnt_pol_array +380 drivers/counter/ti-ecap-capture.c 379 > 380 static DEFINE_COUNTER_ARRAY_POLARITY(ecap_cnt_pol_array, ecap_cnt_pol_avail, ECAP_NB_CEVT); 381 The first argument to the DEFINE_COUNTER_ARRAY_POLARITY() macro is a token serving as the symbol name in the definition of a new struct counter_array structure. However, this macro actually expands to two statements:: #define DEFINE_COUNTER_ARRAY_POLARITY(_name, _enums, _length) \ DEFINE_COUNTER_AVAILABLE(_name##_available, _enums); \ struct counter_array _name = { \ .type = COUNTER_COMP_SIGNAL_POLARITY, \ .avail = &(_name##_available), \ .length = (_length), \ } Because of this, the "static" on line 380 only applies to the first statement. This patch splits out the DEFINE_COUNTER_AVAILABLE() line and leaves DEFINE_COUNTER_ARRAY_POLARITY() as a simple structure definition to avoid issues like this. Reported-by: kernel test robot Link: https://lore.kernel.org/all/202210020619.NQbyomII-lkp@intel.com/ Cc: Julien Panis Signed-off-by: William Breathitt Gray --- drivers/counter/ti-ecap-capture.c | 3 ++- include/linux/counter.h | 5 ++--- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/counter/ti-ecap-capture.c b/drivers/counter/ti-ecap-capture.c index af10de30aba5..b8dbf0212a8e 100644 --- a/drivers/counter/ti-ecap-capture.c +++ b/drivers/counter/ti-ecap-capture.c @@ -377,7 +377,8 @@ static const enum counter_signal_polarity ecap_cnt_pol_avail[] = { COUNTER_SIGNAL_POLARITY_NEGATIVE, }; -static DEFINE_COUNTER_ARRAY_POLARITY(ecap_cnt_pol_array, ecap_cnt_pol_avail, ECAP_NB_CEVT); +static DEFINE_COUNTER_AVAILABLE(ecap_cnt_pol_available, ecap_cnt_pol_avail); +static DEFINE_COUNTER_ARRAY_POLARITY(ecap_cnt_pol_array, ecap_cnt_pol_available, ECAP_NB_CEVT); static struct counter_comp ecap_cnt_signal_ext[] = { COUNTER_COMP_ARRAY_POLARITY(ecap_cnt_pol_read, ecap_cnt_pol_write, ecap_cnt_pol_array), diff --git a/include/linux/counter.h b/include/linux/counter.h index c41fa602ed28..b63746637de2 100644 --- a/include/linux/counter.h +++ b/include/linux/counter.h @@ -542,11 +542,10 @@ struct counter_array { #define DEFINE_COUNTER_ARRAY_CAPTURE(_name, _length) \ DEFINE_COUNTER_ARRAY_U64(_name, _length) -#define DEFINE_COUNTER_ARRAY_POLARITY(_name, _enums, _length) \ - DEFINE_COUNTER_AVAILABLE(_name##_available, _enums); \ +#define DEFINE_COUNTER_ARRAY_POLARITY(_name, _available, _length) \ struct counter_array _name = { \ .type = COUNTER_COMP_SIGNAL_POLARITY, \ - .avail = &(_name##_available), \ + .avail = &(_available), \ .length = (_length), \ } -- cgit v1.2.3 From ca6c21327c6af02b7eec31ce4b9a740a18c6c13f Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 6 Oct 2022 15:00:39 +0200 Subject: perf: Fix missing SIGTRAPs Marco reported: Due to the implementation of how SIGTRAP are delivered if perf_event_attr::sigtrap is set, we've noticed 3 issues: 1. Missing SIGTRAP due to a race with event_sched_out() (more details below). 2. Hardware PMU events being disabled due to returning 1 from perf_event_overflow(). The only way to re-enable the event is for user space to first "properly" disable the event and then re-enable it. 3. The inability to automatically disable an event after a specified number of overflows via PERF_EVENT_IOC_REFRESH. The worst of the 3 issues is problem (1), which occurs when a pending_disable is "consumed" by a racing event_sched_out(), observed as follows: CPU0 | CPU1 --------------------------------+--------------------------- __perf_event_overflow() | perf_event_disable_inatomic() | pending_disable = CPU0 | ... | _perf_event_enable() | event_function_call() | task_function_call() | /* sends IPI to CPU0 */ | ... __perf_event_enable() +--------------------------- ctx_resched() task_ctx_sched_out() ctx_sched_out() group_sched_out() event_sched_out() pending_disable = -1 perf_pending_event() perf_pending_event_disable() /* Fails to send SIGTRAP because no pending_disable! */ In the above case, not only is that particular SIGTRAP missed, but also all future SIGTRAPs because 'event_limit' is not reset back to 1. To fix, rework pending delivery of SIGTRAP via IRQ-work by introduction of a separate 'pending_sigtrap', no longer using 'event_limit' and 'pending_disable' for its delivery. Additionally; and different to Marco's proposed patch: - recognise that pending_disable effectively duplicates oncpu for the case where it is set. As such, change the irq_work handler to use ->oncpu to target the event and use pending_* as boolean toggles. - observe that SIGTRAP targets the ctx->task, so the context switch optimization that carries contexts between tasks is invalid. If the irq_work were delayed enough to hit after a context switch the SIGTRAP would be delivered to the wrong task. - observe that if the event gets scheduled out (rotation/migration/context-switch/...) the irq-work would be insufficient to deliver the SIGTRAP when the event gets scheduled back in (the irq-work might still be pending on the old CPU). Therefore have event_sched_out() convert the pending sigtrap into a task_work which will deliver the signal at return_to_user. Fixes: 97ba62b27867 ("perf: Add support for SIGTRAP on perf events") Reported-by: Dmitry Vyukov Debugged-by: Dmitry Vyukov Reported-by: Marco Elver Debugged-by: Marco Elver Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Marco Elver Tested-by: Marco Elver --- include/linux/perf_event.h | 19 ++++-- kernel/events/core.c | 151 +++++++++++++++++++++++++++++++++----------- kernel/events/ring_buffer.c | 2 +- 3 files changed, 129 insertions(+), 43 deletions(-) (limited to 'include') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 853f64b6c8c2..0031f7b4d9ab 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -756,11 +756,14 @@ struct perf_event { struct fasync_struct *fasync; /* delayed work for NMIs and such */ - int pending_wakeup; - int pending_kill; - int pending_disable; + unsigned int pending_wakeup; + unsigned int pending_kill; + unsigned int pending_disable; + unsigned int pending_sigtrap; unsigned long pending_addr; /* SIGTRAP */ - struct irq_work pending; + struct irq_work pending_irq; + struct callback_head pending_task; + unsigned int pending_work; atomic_t event_limit; @@ -877,6 +880,14 @@ struct perf_event_context { #endif void *task_ctx_data; /* pmu specific data */ struct rcu_head rcu_head; + + /* + * Sum (event->pending_sigtrap + event->pending_work) + * + * The SIGTRAP is targeted at ctx->task, as such it won't do changing + * that until the signal is delivered. + */ + local_t nr_pending; }; /* diff --git a/kernel/events/core.c b/kernel/events/core.c index aefc1e08e015..01933db7629c 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -54,6 +54,7 @@ #include #include #include +#include #include "internal.h" @@ -2276,11 +2277,26 @@ event_sched_out(struct perf_event *event, event->pmu->del(event, 0); event->oncpu = -1; - if (READ_ONCE(event->pending_disable) >= 0) { - WRITE_ONCE(event->pending_disable, -1); + if (event->pending_disable) { + event->pending_disable = 0; perf_cgroup_event_disable(event, ctx); state = PERF_EVENT_STATE_OFF; } + + if (event->pending_sigtrap) { + bool dec = true; + + event->pending_sigtrap = 0; + if (state != PERF_EVENT_STATE_OFF && + !event->pending_work) { + event->pending_work = 1; + dec = false; + task_work_add(current, &event->pending_task, TWA_RESUME); + } + if (dec) + local_dec(&event->ctx->nr_pending); + } + perf_event_set_state(event, state); if (!is_software_event(event)) @@ -2432,7 +2448,7 @@ static void __perf_event_disable(struct perf_event *event, * hold the top-level event's child_mutex, so any descendant that * goes to exit will block in perf_event_exit_event(). * - * When called from perf_pending_event it's OK because event->ctx + * When called from perf_pending_irq it's OK because event->ctx * is the current context on this CPU and preemption is disabled, * hence we can't get into perf_event_task_sched_out for this context. */ @@ -2471,9 +2487,8 @@ EXPORT_SYMBOL_GPL(perf_event_disable); void perf_event_disable_inatomic(struct perf_event *event) { - WRITE_ONCE(event->pending_disable, smp_processor_id()); - /* can fail, see perf_pending_event_disable() */ - irq_work_queue(&event->pending); + event->pending_disable = 1; + irq_work_queue(&event->pending_irq); } #define MAX_INTERRUPTS (~0ULL) @@ -3428,11 +3443,23 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn, raw_spin_lock_nested(&next_ctx->lock, SINGLE_DEPTH_NESTING); if (context_equiv(ctx, next_ctx)) { + perf_pmu_disable(pmu); + + /* PMIs are disabled; ctx->nr_pending is stable. */ + if (local_read(&ctx->nr_pending) || + local_read(&next_ctx->nr_pending)) { + /* + * Must not swap out ctx when there's pending + * events that rely on the ctx->task relation. + */ + raw_spin_unlock(&next_ctx->lock); + rcu_read_unlock(); + goto inside_switch; + } + WRITE_ONCE(ctx->task, next); WRITE_ONCE(next_ctx->task, task); - perf_pmu_disable(pmu); - if (cpuctx->sched_cb_usage && pmu->sched_task) pmu->sched_task(ctx, false); @@ -3473,6 +3500,7 @@ unlock: raw_spin_lock(&ctx->lock); perf_pmu_disable(pmu); +inside_switch: if (cpuctx->sched_cb_usage && pmu->sched_task) pmu->sched_task(ctx, false); task_ctx_sched_out(cpuctx, ctx, EVENT_ALL); @@ -4939,7 +4967,7 @@ static void perf_addr_filters_splice(struct perf_event *event, static void _free_event(struct perf_event *event) { - irq_work_sync(&event->pending); + irq_work_sync(&event->pending_irq); unaccount_event(event); @@ -6439,7 +6467,8 @@ static void perf_sigtrap(struct perf_event *event) return; /* - * perf_pending_event() can race with the task exiting. + * Both perf_pending_task() and perf_pending_irq() can race with the + * task exiting. */ if (current->flags & PF_EXITING) return; @@ -6448,23 +6477,33 @@ static void perf_sigtrap(struct perf_event *event) event->attr.type, event->attr.sig_data); } -static void perf_pending_event_disable(struct perf_event *event) +/* + * Deliver the pending work in-event-context or follow the context. + */ +static void __perf_pending_irq(struct perf_event *event) { - int cpu = READ_ONCE(event->pending_disable); + int cpu = READ_ONCE(event->oncpu); + /* + * If the event isn't running; we done. event_sched_out() will have + * taken care of things. + */ if (cpu < 0) return; + /* + * Yay, we hit home and are in the context of the event. + */ if (cpu == smp_processor_id()) { - WRITE_ONCE(event->pending_disable, -1); - - if (event->attr.sigtrap) { + if (event->pending_sigtrap) { + event->pending_sigtrap = 0; perf_sigtrap(event); - atomic_set_release(&event->event_limit, 1); /* rearm event */ - return; + local_dec(&event->ctx->nr_pending); + } + if (event->pending_disable) { + event->pending_disable = 0; + perf_event_disable_local(event); } - - perf_event_disable_local(event); return; } @@ -6484,35 +6523,62 @@ static void perf_pending_event_disable(struct perf_event *event) * irq_work_queue(); // FAILS * * irq_work_run() - * perf_pending_event() + * perf_pending_irq() * * But the event runs on CPU-B and wants disabling there. */ - irq_work_queue_on(&event->pending, cpu); + irq_work_queue_on(&event->pending_irq, cpu); } -static void perf_pending_event(struct irq_work *entry) +static void perf_pending_irq(struct irq_work *entry) { - struct perf_event *event = container_of(entry, struct perf_event, pending); + struct perf_event *event = container_of(entry, struct perf_event, pending_irq); int rctx; - rctx = perf_swevent_get_recursion_context(); /* * If we 'fail' here, that's OK, it means recursion is already disabled * and we won't recurse 'further'. */ + rctx = perf_swevent_get_recursion_context(); - perf_pending_event_disable(event); - + /* + * The wakeup isn't bound to the context of the event -- it can happen + * irrespective of where the event is. + */ if (event->pending_wakeup) { event->pending_wakeup = 0; perf_event_wakeup(event); } + __perf_pending_irq(event); + if (rctx >= 0) perf_swevent_put_recursion_context(rctx); } +static void perf_pending_task(struct callback_head *head) +{ + struct perf_event *event = container_of(head, struct perf_event, pending_task); + int rctx; + + /* + * If we 'fail' here, that's OK, it means recursion is already disabled + * and we won't recurse 'further'. + */ + preempt_disable_notrace(); + rctx = perf_swevent_get_recursion_context(); + + if (event->pending_work) { + event->pending_work = 0; + perf_sigtrap(event); + local_dec(&event->ctx->nr_pending); + } + + if (rctx >= 0) + perf_swevent_put_recursion_context(rctx); + preempt_enable_notrace(); +} + #ifdef CONFIG_GUEST_PERF_EVENTS struct perf_guest_info_callbacks __rcu *perf_guest_cbs; @@ -9212,8 +9278,8 @@ int perf_event_account_interrupt(struct perf_event *event) */ static int __perf_event_overflow(struct perf_event *event, - int throttle, struct perf_sample_data *data, - struct pt_regs *regs) + int throttle, struct perf_sample_data *data, + struct pt_regs *regs) { int events = atomic_read(&event->event_limit); int ret = 0; @@ -9236,24 +9302,36 @@ static int __perf_event_overflow(struct perf_event *event, if (events && atomic_dec_and_test(&event->event_limit)) { ret = 1; event->pending_kill = POLL_HUP; - event->pending_addr = data->addr; - perf_event_disable_inatomic(event); } + if (event->attr.sigtrap) { + /* + * Should not be able to return to user space without processing + * pending_sigtrap (kernel events can overflow multiple times). + */ + WARN_ON_ONCE(event->pending_sigtrap && event->attr.exclude_kernel); + if (!event->pending_sigtrap) { + event->pending_sigtrap = 1; + local_inc(&event->ctx->nr_pending); + } + event->pending_addr = data->addr; + irq_work_queue(&event->pending_irq); + } + READ_ONCE(event->overflow_handler)(event, data, regs); if (*perf_event_fasync(event) && event->pending_kill) { event->pending_wakeup = 1; - irq_work_queue(&event->pending); + irq_work_queue(&event->pending_irq); } return ret; } int perf_event_overflow(struct perf_event *event, - struct perf_sample_data *data, - struct pt_regs *regs) + struct perf_sample_data *data, + struct pt_regs *regs) { return __perf_event_overflow(event, 1, data, regs); } @@ -11570,8 +11648,8 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, init_waitqueue_head(&event->waitq); - event->pending_disable = -1; - init_irq_work(&event->pending, perf_pending_event); + init_irq_work(&event->pending_irq, perf_pending_irq); + init_task_work(&event->pending_task, perf_pending_task); mutex_init(&event->mmap_mutex); raw_spin_lock_init(&event->addr_filters.lock); @@ -11593,9 +11671,6 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, if (parent_event) event->event_caps = parent_event->event_caps; - if (event->attr.sigtrap) - atomic_set(&event->event_limit, 1); - if (task) { event->attach_state = PERF_ATTACH_TASK; /* diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 726132039c38..273a0fe7910a 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -22,7 +22,7 @@ static void perf_output_wakeup(struct perf_output_handle *handle) atomic_set(&handle->rb->poll, EPOLLIN); handle->event->pending_wakeup = 1; - irq_work_queue(&handle->event->pending); + irq_work_queue(&handle->event->pending_irq); } /* -- cgit v1.2.3 From 69421bf98482d089e50799f45e48b25ce4a8d154 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 14 Oct 2022 11:26:25 -0700 Subject: udp: Update reuse->has_conns under reuseport_lock. When we call connect() for a UDP socket in a reuseport group, we have to update sk->sk_reuseport_cb->has_conns to 1. Otherwise, the kernel could select a unconnected socket wrongly for packets sent to the connected socket. However, the current way to set has_conns is illegal and possible to trigger that problem. reuseport_has_conns() changes has_conns under rcu_read_lock(), which upgrades the RCU reader to the updater. Then, it must do the update under the updater's lock, reuseport_lock, but it doesn't for now. For this reason, there is a race below where we fail to set has_conns resulting in the wrong socket selection. To avoid the race, let's split the reader and updater with proper locking. cpu1 cpu2 +----+ +----+ __ip[46]_datagram_connect() reuseport_grow() . . |- reuseport_has_conns(sk, true) |- more_reuse = __reuseport_alloc(more_socks_size) | . | | |- rcu_read_lock() | |- reuse = rcu_dereference(sk->sk_reuseport_cb) | | | | | /* reuse->has_conns == 0 here */ | | |- more_reuse->has_conns = reuse->has_conns | |- reuse->has_conns = 1 | /* more_reuse->has_conns SHOULD BE 1 HERE */ | | | | | |- rcu_assign_pointer(reuse->socks[i]->sk_reuseport_cb, | | | more_reuse) | `- rcu_read_unlock() `- kfree_rcu(reuse, rcu) | |- sk->sk_state = TCP_ESTABLISHED Note the likely(reuse) in reuseport_has_conns_set() is always true, but we put the test there for ease of review. [0] For the record, usually, sk_reuseport_cb is changed under lock_sock(). The only exception is reuseport_grow() & TCP reqsk migration case. 1) shutdown() TCP listener, which is moved into the latter part of reuse->socks[] to migrate reqsk. 2) New listen() overflows reuse->socks[] and call reuseport_grow(). 3) reuse->max_socks overflows u16 with the new listener. 4) reuseport_grow() pops the old shutdown()ed listener from the array and update its sk->sk_reuseport_cb as NULL without lock_sock(). shutdown()ed TCP sk->sk_reuseport_cb can be changed without lock_sock(), but, reuseport_has_conns_set() is called only for UDP under lock_sock(), so likely(reuse) never be false in reuseport_has_conns_set(). [0]: https://lore.kernel.org/netdev/CANn89iLja=eQHbsM_Ta2sQF0tOGU8vAGrh_izRuuHjuO1ouUag@mail.gmail.com/ Fixes: acdcecc61285 ("udp: correct reuseport selection with connected sockets") Signed-off-by: Kuniyuki Iwashima Link: https://lore.kernel.org/r/20221014182625.89913-1-kuniyu@amazon.com Signed-off-by: Paolo Abeni --- include/net/sock_reuseport.h | 11 +++++------ net/core/sock_reuseport.c | 16 ++++++++++++++++ net/ipv4/datagram.c | 2 +- net/ipv4/udp.c | 2 +- net/ipv6/datagram.c | 2 +- net/ipv6/udp.c | 2 +- 6 files changed, 25 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/net/sock_reuseport.h b/include/net/sock_reuseport.h index 473b0b0fa4ab..efc9085c6892 100644 --- a/include/net/sock_reuseport.h +++ b/include/net/sock_reuseport.h @@ -43,21 +43,20 @@ struct sock *reuseport_migrate_sock(struct sock *sk, extern int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog); extern int reuseport_detach_prog(struct sock *sk); -static inline bool reuseport_has_conns(struct sock *sk, bool set) +static inline bool reuseport_has_conns(struct sock *sk) { struct sock_reuseport *reuse; bool ret = false; rcu_read_lock(); reuse = rcu_dereference(sk->sk_reuseport_cb); - if (reuse) { - if (set) - reuse->has_conns = 1; - ret = reuse->has_conns; - } + if (reuse && reuse->has_conns) + ret = true; rcu_read_unlock(); return ret; } +void reuseport_has_conns_set(struct sock *sk); + #endif /* _SOCK_REUSEPORT_H */ diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c index 5daa1fa54249..fb90e1e00773 100644 --- a/net/core/sock_reuseport.c +++ b/net/core/sock_reuseport.c @@ -21,6 +21,22 @@ static DEFINE_IDA(reuseport_ida); static int reuseport_resurrect(struct sock *sk, struct sock_reuseport *old_reuse, struct sock_reuseport *reuse, bool bind_inany); +void reuseport_has_conns_set(struct sock *sk) +{ + struct sock_reuseport *reuse; + + if (!rcu_access_pointer(sk->sk_reuseport_cb)) + return; + + spin_lock_bh(&reuseport_lock); + reuse = rcu_dereference_protected(sk->sk_reuseport_cb, + lockdep_is_held(&reuseport_lock)); + if (likely(reuse)) + reuse->has_conns = 1; + spin_unlock_bh(&reuseport_lock); +} +EXPORT_SYMBOL(reuseport_has_conns_set); + static int reuseport_sock_index(struct sock *sk, const struct sock_reuseport *reuse, bool closed) diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index 405a8c2aea64..5e66add7befa 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -70,7 +70,7 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len } inet->inet_daddr = fl4->daddr; inet->inet_dport = usin->sin_port; - reuseport_has_conns(sk, true); + reuseport_has_conns_set(sk); sk->sk_state = TCP_ESTABLISHED; sk_set_txhash(sk); inet->inet_id = prandom_u32(); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 8126f67d18b3..752b72892a44 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -448,7 +448,7 @@ static struct sock *udp4_lib_lookup2(struct net *net, result = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum); /* Fall back to scoring if group has connections */ - if (result && !reuseport_has_conns(sk, false)) + if (result && !reuseport_has_conns(sk)) return result; result = result ? : sk; diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index df665d4e8f0f..5ecb56522f9d 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -256,7 +256,7 @@ ipv4_connected: goto out; } - reuseport_has_conns(sk, true); + reuseport_has_conns_set(sk); sk->sk_state = TCP_ESTABLISHED; sk_set_txhash(sk); out: diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 8d09f0ea5b8c..129ec5a9b0eb 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -195,7 +195,7 @@ static struct sock *udp6_lib_lookup2(struct net *net, result = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum); /* Fall back to scoring if group has connections */ - if (result && !reuseport_has_conns(sk, false)) + if (result && !reuseport_has_conns(sk)) return result; result = result ? : sk; -- cgit v1.2.3 From 7b476affcccfc7e644541a0a719f53fc7bd34c53 Mon Sep 17 00:00:00 2001 From: Christian König Date: Fri, 7 Oct 2022 09:51:13 +0200 Subject: drm/sched: add DRM_SCHED_FENCE_DONT_PIPELINE flag MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Setting this flag on a scheduler fence prevents pipelining of jobs depending on this fence. In other words we always insert a full CPU round trip before dependent jobs are pushed to the pipeline. Signed-off-by: Christian König Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/2113#note_1579296 Reviewed-by: Alex Deucher Acked-by: Luben Tuikov Link: https://patchwork.freedesktop.org/patch/msgid/20221014081553.114899-1-christian.koenig@amd.com --- drivers/gpu/drm/scheduler/sched_entity.c | 3 ++- include/drm/gpu_scheduler.h | 9 +++++++++ 2 files changed, 11 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c index 6b25b2f4f5a3..6137537aaea4 100644 --- a/drivers/gpu/drm/scheduler/sched_entity.c +++ b/drivers/gpu/drm/scheduler/sched_entity.c @@ -385,7 +385,8 @@ static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity) } s_fence = to_drm_sched_fence(fence); - if (s_fence && s_fence->sched == sched) { + if (s_fence && s_fence->sched == sched && + !test_bit(DRM_SCHED_FENCE_DONT_PIPELINE, &fence->flags)) { /* * Fence is from the same scheduler, only need to wait for diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index addb135eeea6..289a33e80639 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -32,6 +32,15 @@ #define MAX_WAIT_SCHED_ENTITY_Q_EMPTY msecs_to_jiffies(1000) +/** + * DRM_SCHED_FENCE_DONT_PIPELINE - Prefent dependency pipelining + * + * Setting this flag on a scheduler fence prevents pipelining of jobs depending + * on this fence. In other words we always insert a full CPU round trip before + * dependen jobs are pushed to the hw queue. + */ +#define DRM_SCHED_FENCE_DONT_PIPELINE DMA_FENCE_FLAG_USER_BITS + struct drm_gem_object; struct drm_gpu_scheduler; -- cgit v1.2.3 From 32def55d237e8507d4eb8442628fc2e59a899ea0 Mon Sep 17 00:00:00 2001 From: Aidan MacDonald Date: Wed, 19 Oct 2022 02:23:02 +0100 Subject: ASoC: simple-card: Fix up checks for HW param fixups The "convert-xxx" properties only have an effect for DPCM DAI links. A DAI link is only created as DPCM if the device tree requires it; part of this involves checking for the use of "convert-xxx" properties. When the convert-sample-format property was added, the checks got out of sync. A DAI link that specified only convert-sample-format but did not pass any of the other DPCM checks would not go into DPCM mode and the convert-sample-format property would be silently ignored. Fix this by adding a function to do the "convert-xxx" property checks, instead of open-coding it in simple-card and audio-graph-card. And add "convert-sample-format" to the check function so that DAI links using it will be initialized correctly. Fixes: 047a05366f4b ("ASoC: simple-card-utils: Fixup DAI sample format") Acked-by: Kuninori Morimoto Signed-off-by: Aidan MacDonald Acked-by: Sameer Pujar Link: https://lore.kernel.org/r/20221019012302.633830-1-aidanmacdonald.0x0@gmail.com Signed-off-by: Mark Brown --- include/sound/simple_card_utils.h | 1 + sound/soc/generic/audio-graph-card.c | 2 +- sound/soc/generic/simple-card-utils.c | 15 +++++++++++++++ sound/soc/generic/simple-card.c | 3 +-- 4 files changed, 18 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/sound/simple_card_utils.h b/include/sound/simple_card_utils.h index a0b827f0c2f6..25e049f44178 100644 --- a/include/sound/simple_card_utils.h +++ b/include/sound/simple_card_utils.h @@ -177,6 +177,7 @@ void asoc_simple_convert_fixup(struct asoc_simple_data *data, struct snd_pcm_hw_params *params); void asoc_simple_parse_convert(struct device_node *np, char *prefix, struct asoc_simple_data *data); +bool asoc_simple_is_convert_required(const struct asoc_simple_data *data); int asoc_simple_parse_routing(struct snd_soc_card *card, char *prefix); diff --git a/sound/soc/generic/audio-graph-card.c b/sound/soc/generic/audio-graph-card.c index b327372f2e4a..fe7cf972d44c 100644 --- a/sound/soc/generic/audio-graph-card.c +++ b/sound/soc/generic/audio-graph-card.c @@ -417,7 +417,7 @@ static inline bool parse_as_dpcm_link(struct asoc_simple_priv *priv, * or has convert-xxx property */ if ((of_get_child_count(codec_port) > 1) || - (adata->convert_rate || adata->convert_channels)) + asoc_simple_is_convert_required(adata)) return true; return false; diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c index bef16833c487..be69bbc47f81 100644 --- a/sound/soc/generic/simple-card-utils.c +++ b/sound/soc/generic/simple-card-utils.c @@ -85,6 +85,21 @@ void asoc_simple_parse_convert(struct device_node *np, } EXPORT_SYMBOL_GPL(asoc_simple_parse_convert); +/** + * asoc_simple_is_convert_required() - Query if HW param conversion was requested + * @data: Link data. + * + * Returns true if any HW param conversion was requested for this DAI link with + * any "convert-xxx" properties. + */ +bool asoc_simple_is_convert_required(const struct asoc_simple_data *data) +{ + return data->convert_rate || + data->convert_channels || + data->convert_sample_format; +} +EXPORT_SYMBOL_GPL(asoc_simple_is_convert_required); + int asoc_simple_parse_daifmt(struct device *dev, struct device_node *node, struct device_node *codec, diff --git a/sound/soc/generic/simple-card.c b/sound/soc/generic/simple-card.c index 78419e18717d..feb55b66239b 100644 --- a/sound/soc/generic/simple-card.c +++ b/sound/soc/generic/simple-card.c @@ -393,8 +393,7 @@ static int __simple_for_each_link(struct asoc_simple_priv *priv, * or has convert-xxx property */ if (dpcm_selectable && - (num > 2 || - adata.convert_rate || adata.convert_channels)) { + (num > 2 || asoc_simple_is_convert_required(&adata))) { /* * np * |1(CPU)|0(Codec) li->cpu -- cgit v1.2.3 From a1a824f448ba96c610b85288d844adc9f781828e Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 18 Oct 2022 16:13:10 -0700 Subject: genetlink: fix kdoc warnings Address a bunch of kdoc warnings: include/net/genetlink.h:81: warning: Function parameter or member 'module' not described in 'genl_family' include/net/genetlink.h:243: warning: expecting prototype for struct genl_info. Prototype was for struct genl_dumpit_info instead include/net/genetlink.h:419: warning: Function parameter or member 'net' not described in 'genlmsg_unicast' include/net/genetlink.h:438: warning: expecting prototype for gennlmsg_data(). Prototype was for genlmsg_data() instead include/net/genetlink.h:244: warning: Function parameter or member 'op' not described in 'genl_dumpit_info' Link: https://lore.kernel.org/r/20221018231310.1040482-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/net/genetlink.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 8f780170e2f8..3d08e67b3cfc 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -37,6 +37,7 @@ struct genl_info; * do additional, common, filtering and return an error * @post_doit: called after an operation's doit callback, it may * undo operations done by pre_doit, for example release locks + * @module: pointer to the owning module (set to THIS_MODULE) * @mcgrps: multicast groups used by this family * @n_mcgrps: number of multicast groups * @resv_start_op: first operation for which reserved fields of the header @@ -173,9 +174,9 @@ struct genl_ops { }; /** - * struct genl_info - info that is available during dumpit op call + * struct genl_dumpit_info - info that is available during dumpit op call * @family: generic netlink family - for internal genl code usage - * @ops: generic netlink ops - for internal genl code usage + * @op: generic netlink ops - for internal genl code usage * @attrs: netlink attributes */ struct genl_dumpit_info { @@ -354,6 +355,7 @@ int genlmsg_multicast_allns(const struct genl_family *family, /** * genlmsg_unicast - unicast a netlink message + * @net: network namespace to look up @portid in * @skb: netlink message as socket buffer * @portid: netlink portid of the destination socket */ @@ -373,7 +375,7 @@ static inline int genlmsg_reply(struct sk_buff *skb, struct genl_info *info) } /** - * gennlmsg_data - head of message payload + * genlmsg_data - head of message payload * @gnlh: genetlink message header */ static inline void *genlmsg_data(const struct genlmsghdr *gnlh) -- cgit v1.2.3 From ccd30a476f8e864732de220bd50e6f372f5ebcab Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 11 Oct 2022 14:38:38 -0700 Subject: fscrypt: fix keyring memory leak on mount failure Commit d7e7b9af104c ("fscrypt: stop using keyrings subsystem for fscrypt_master_key") moved the keyring destruction from __put_super() to generic_shutdown_super() so that the filesystem's block device(s) are still available. Unfortunately, this causes a memory leak in the case where a mount is attempted with the test_dummy_encryption mount option, but the mount fails after the option has already been processed. To fix this, attempt the keyring destruction in both places. Reported-by: syzbot+104c2a89561289cec13e@syzkaller.appspotmail.com Fixes: d7e7b9af104c ("fscrypt: stop using keyrings subsystem for fscrypt_master_key") Signed-off-by: Eric Biggers Reviewed-by: Christian Brauner (Microsoft) Link: https://lore.kernel.org/r/20221011213838.209879-1-ebiggers@kernel.org --- fs/crypto/keyring.c | 17 +++++++++++------ fs/super.c | 3 ++- include/linux/fscrypt.h | 4 ++-- 3 files changed, 15 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/fs/crypto/keyring.c b/fs/crypto/keyring.c index 1cca09aa43f8..2a24b1f0ae68 100644 --- a/fs/crypto/keyring.c +++ b/fs/crypto/keyring.c @@ -205,14 +205,19 @@ static int allocate_filesystem_keyring(struct super_block *sb) } /* - * This is called at unmount time to release all encryption keys that have been - * added to the filesystem, along with the keyring that contains them. + * Release all encryption keys that have been added to the filesystem, along + * with the keyring that contains them. * - * Note that besides clearing and freeing memory, this might need to evict keys - * from the keyslots of an inline crypto engine. Therefore, this must be called - * while the filesystem's underlying block device(s) are still available. + * This is called at unmount time. The filesystem's underlying block device(s) + * are still available at this time; this is important because after user file + * accesses have been allowed, this function may need to evict keys from the + * keyslots of an inline crypto engine, which requires the block device(s). + * + * This is also called when the super_block is being freed. This is needed to + * avoid a memory leak if mounting fails after the "test_dummy_encryption" + * option was processed, as in that case the unmount-time call isn't made. */ -void fscrypt_sb_delete(struct super_block *sb) +void fscrypt_destroy_keyring(struct super_block *sb) { struct fscrypt_keyring *keyring = sb->s_master_keys; size_t i; diff --git a/fs/super.c b/fs/super.c index 6a82660e1adb..8d39e4f11cfa 100644 --- a/fs/super.c +++ b/fs/super.c @@ -291,6 +291,7 @@ static void __put_super(struct super_block *s) WARN_ON(s->s_inode_lru.node); WARN_ON(!list_empty(&s->s_mounts)); security_sb_free(s); + fscrypt_destroy_keyring(s); put_user_ns(s->s_user_ns); kfree(s->s_subtype); call_rcu(&s->rcu, destroy_super_rcu); @@ -479,7 +480,7 @@ void generic_shutdown_super(struct super_block *sb) evict_inodes(sb); /* only nonzero refcount inodes can have marks */ fsnotify_sb_delete(sb); - fscrypt_sb_delete(sb); + fscrypt_destroy_keyring(sb); security_sb_delete(sb); if (sb->s_dio_done_wq) { diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index cad78b569c7e..4f5f8a651213 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -307,7 +307,7 @@ fscrypt_free_dummy_policy(struct fscrypt_dummy_policy *dummy_policy) } /* keyring.c */ -void fscrypt_sb_delete(struct super_block *sb); +void fscrypt_destroy_keyring(struct super_block *sb); int fscrypt_ioctl_add_key(struct file *filp, void __user *arg); int fscrypt_add_test_dummy_key(struct super_block *sb, const struct fscrypt_dummy_policy *dummy_policy); @@ -521,7 +521,7 @@ fscrypt_free_dummy_policy(struct fscrypt_dummy_policy *dummy_policy) } /* keyring.c */ -static inline void fscrypt_sb_delete(struct super_block *sb) +static inline void fscrypt_destroy_keyring(struct super_block *sb) { } -- cgit v1.2.3 From 7228d9d79248bd0c8af56a7667a88a875c674e0c Mon Sep 17 00:00:00 2001 From: Steven Price Date: Mon, 17 Oct 2022 11:46:01 +0100 Subject: drm/panfrost: Remove type name from internal structs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The two structs internal to struct panfrost_dump_object_header were named, but sadly that is incompatible with C++, causing an error: "an anonymous union may only have public non-static data members". However nothing refers to struct pan_reg_hdr and struct pan_bomap_hdr and there's no need to export these definitions, so lets drop them. This fixes the C++ build error with the minimum change in userspace API. Reported-by: Adrián Larumbe Fixes: 730c2bf4ad39 ("drm/panfrost: Add support for devcoredump") Reviewed-by: Alyssa Rosenzweig Signed-off-by: Steven Price Link: https://patchwork.freedesktop.org/patch/msgid/20221017104602.142992-2-steven.price@arm.com --- include/uapi/drm/panfrost_drm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/drm/panfrost_drm.h b/include/uapi/drm/panfrost_drm.h index eac87310b348..bd77254be121 100644 --- a/include/uapi/drm/panfrost_drm.h +++ b/include/uapi/drm/panfrost_drm.h @@ -242,7 +242,7 @@ struct panfrost_dump_object_header { __le32 file_offset; union { - struct pan_reg_hdr { + struct { __le64 jc; __le32 gpu_id; __le32 major; @@ -250,7 +250,7 @@ struct panfrost_dump_object_header { __le64 nbos; } reghdr; - struct pan_bomap_hdr { + struct { __le32 valid; __le64 iova; __le32 data[2]; -- cgit v1.2.3 From 72655fb942c1e3d9e71e48e87ee439abe52f3a90 Mon Sep 17 00:00:00 2001 From: Steven Price Date: Mon, 17 Oct 2022 11:46:02 +0100 Subject: drm/panfrost: replace endian-specific types with native ones __le32 and __le64 types aren't portable and are not available on FreeBSD (which uses the same uAPI). Instead of attempting to always output little endian, just use native endianness in the dumps. Tools can detect the endianness in use by looking at the 'magic' field, but equally we don't expect big-endian to be used with Mali (there are no known implementations out there). Bug: https://gitlab.freedesktop.org/mesa/mesa/-/issues/7252 Fixes: 730c2bf4ad39 ("drm/panfrost: Add support for devcoredump") Reviewed-by: Alyssa Rosenzweig Signed-off-by: Steven Price Link: https://patchwork.freedesktop.org/patch/msgid/20221017104602.142992-3-steven.price@arm.com --- drivers/gpu/drm/panfrost/panfrost_dump.c | 36 ++++++++++++++++---------------- include/uapi/drm/panfrost_drm.h | 36 ++++++++++++++++++-------------- 2 files changed, 38 insertions(+), 34 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/panfrost/panfrost_dump.c b/drivers/gpu/drm/panfrost/panfrost_dump.c index 89056a1aac7d..6bd0634e2d58 100644 --- a/drivers/gpu/drm/panfrost/panfrost_dump.c +++ b/drivers/gpu/drm/panfrost/panfrost_dump.c @@ -63,13 +63,13 @@ static void panfrost_core_dump_header(struct panfrost_dump_iterator *iter, { struct panfrost_dump_object_header *hdr = iter->hdr; - hdr->magic = cpu_to_le32(PANFROSTDUMP_MAGIC); - hdr->type = cpu_to_le32(type); - hdr->file_offset = cpu_to_le32(iter->data - iter->start); - hdr->file_size = cpu_to_le32(data_end - iter->data); + hdr->magic = PANFROSTDUMP_MAGIC; + hdr->type = type; + hdr->file_offset = iter->data - iter->start; + hdr->file_size = data_end - iter->data; iter->hdr++; - iter->data += le32_to_cpu(hdr->file_size); + iter->data += hdr->file_size; } static void @@ -93,8 +93,8 @@ panfrost_core_dump_registers(struct panfrost_dump_iterator *iter, reg = panfrost_dump_registers[i] + js_as_offset; - dumpreg->reg = cpu_to_le32(reg); - dumpreg->value = cpu_to_le32(gpu_read(pfdev, reg)); + dumpreg->reg = reg; + dumpreg->value = gpu_read(pfdev, reg); } panfrost_core_dump_header(iter, PANFROSTDUMP_BUF_REG, dumpreg); @@ -106,7 +106,7 @@ void panfrost_core_dump(struct panfrost_job *job) struct panfrost_dump_iterator iter; struct drm_gem_object *dbo; unsigned int n_obj, n_bomap_pages; - __le64 *bomap, *bomap_start; + u64 *bomap, *bomap_start; size_t file_size; u32 as_nr; int slot; @@ -177,11 +177,11 @@ void panfrost_core_dump(struct panfrost_job *job) * For now, we write the job identifier in the register dump header, * so that we can decode the entire dump later with pandecode */ - iter.hdr->reghdr.jc = cpu_to_le64(job->jc); - iter.hdr->reghdr.major = cpu_to_le32(PANFROSTDUMP_MAJOR); - iter.hdr->reghdr.minor = cpu_to_le32(PANFROSTDUMP_MINOR); - iter.hdr->reghdr.gpu_id = cpu_to_le32(pfdev->features.id); - iter.hdr->reghdr.nbos = cpu_to_le64(job->bo_count); + iter.hdr->reghdr.jc = job->jc; + iter.hdr->reghdr.major = PANFROSTDUMP_MAJOR; + iter.hdr->reghdr.minor = PANFROSTDUMP_MINOR; + iter.hdr->reghdr.gpu_id = pfdev->features.id; + iter.hdr->reghdr.nbos = job->bo_count; panfrost_core_dump_registers(&iter, pfdev, as_nr, slot); @@ -218,27 +218,27 @@ void panfrost_core_dump(struct panfrost_job *job) WARN_ON(!mapping->active); - iter.hdr->bomap.data[0] = cpu_to_le32((bomap - bomap_start)); + iter.hdr->bomap.data[0] = bomap - bomap_start; for_each_sgtable_page(bo->base.sgt, &page_iter, 0) { struct page *page = sg_page_iter_page(&page_iter); if (!IS_ERR(page)) { - *bomap++ = cpu_to_le64(page_to_phys(page)); + *bomap++ = page_to_phys(page); } else { dev_err(pfdev->dev, "Panfrost Dump: wrong page\n"); - *bomap++ = ~cpu_to_le64(0); + *bomap++ = 0; } } - iter.hdr->bomap.iova = cpu_to_le64(mapping->mmnode.start << PAGE_SHIFT); + iter.hdr->bomap.iova = mapping->mmnode.start << PAGE_SHIFT; vaddr = map.vaddr; memcpy(iter.data, vaddr, bo->base.base.size); drm_gem_shmem_vunmap(&bo->base, &map); - iter.hdr->bomap.valid = cpu_to_le32(1); + iter.hdr->bomap.valid = 1; dump_header: panfrost_core_dump_header(&iter, PANFROSTDUMP_BUF_BO, iter.data + bo->base.base.size); diff --git a/include/uapi/drm/panfrost_drm.h b/include/uapi/drm/panfrost_drm.h index bd77254be121..6f93c915cc88 100644 --- a/include/uapi/drm/panfrost_drm.h +++ b/include/uapi/drm/panfrost_drm.h @@ -235,25 +235,29 @@ struct drm_panfrost_madvise { #define PANFROSTDUMP_BUF_BO (PANFROSTDUMP_BUF_BOMAP + 1) #define PANFROSTDUMP_BUF_TRAILER (PANFROSTDUMP_BUF_BO + 1) +/* + * This structure is the native endianness of the dumping machine, tools can + * detect the endianness by looking at the value in 'magic'. + */ struct panfrost_dump_object_header { - __le32 magic; - __le32 type; - __le32 file_size; - __le32 file_offset; + __u32 magic; + __u32 type; + __u32 file_size; + __u32 file_offset; union { struct { - __le64 jc; - __le32 gpu_id; - __le32 major; - __le32 minor; - __le64 nbos; + __u64 jc; + __u32 gpu_id; + __u32 major; + __u32 minor; + __u64 nbos; } reghdr; - struct { - __le32 valid; - __le64 iova; - __le32 data[2]; + struct pan_bomap_hdr { + __u32 valid; + __u64 iova; + __u32 data[2]; } bomap; /* @@ -261,14 +265,14 @@ struct panfrost_dump_object_header { * with new fields and also keep it 512-byte aligned */ - __le32 sizer[496]; + __u32 sizer[496]; }; }; /* Registers object, an array of these */ struct panfrost_dump_registers { - __le32 reg; - __le32 value; + __u32 reg; + __u32 value; }; #if defined(__cplusplus) -- cgit v1.2.3 From 883bbbffa5a4ffd1915f8b42934dab81b7f87226 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 18 Oct 2022 13:49:21 +0200 Subject: ftrace,kcfi: Separate ftrace_stub() and ftrace_stub_graph() Different function signatures means they needs to be different functions; otherwise CFI gets upset. As triggered by the ftrace boot tests: [] CFI failure at ftrace_return_to_handler+0xac/0x16c (target: ftrace_stub+0x0/0x14; expected type: 0x0a5d5347) Fixes: 3c516f89e17e ("x86: Add support for CONFIG_CFI_CLANG") Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Mark Rutland Tested-by: Mark Rutland Link: https://lkml.kernel.org/r/Y06dg4e1xF6JTdQq@hirez.programming.kicks-ass.net --- arch/arm64/kernel/entry-ftrace.S | 7 ++++++- arch/x86/kernel/ftrace_64.S | 17 +++++++++-------- include/asm-generic/vmlinux.lds.h | 18 ++++++++++++------ 3 files changed, 27 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S index bd5df50e4643..795344ab4ec4 100644 --- a/arch/arm64/kernel/entry-ftrace.S +++ b/arch/arm64/kernel/entry-ftrace.S @@ -7,6 +7,7 @@ */ #include +#include #include #include #include @@ -294,10 +295,14 @@ SYM_FUNC_END(ftrace_graph_caller) #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ #endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */ -SYM_FUNC_START(ftrace_stub) +SYM_TYPED_FUNC_START(ftrace_stub) ret SYM_FUNC_END(ftrace_stub) +SYM_TYPED_FUNC_START(ftrace_stub_graph) + ret +SYM_FUNC_END(ftrace_stub_graph) + #ifdef CONFIG_FUNCTION_GRAPH_TRACER /* * void return_to_handler(void) diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S index a90c55a6b481..2a4be92fd144 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -4,6 +4,7 @@ */ #include +#include #include #include #include @@ -129,6 +130,14 @@ .endm +SYM_TYPED_FUNC_START(ftrace_stub) + RET +SYM_FUNC_END(ftrace_stub) + +SYM_TYPED_FUNC_START(ftrace_stub_graph) + RET +SYM_FUNC_END(ftrace_stub_graph) + #ifdef CONFIG_DYNAMIC_FTRACE SYM_FUNC_START(__fentry__) @@ -176,11 +185,6 @@ SYM_INNER_LABEL(ftrace_caller_end, SYM_L_GLOBAL) SYM_FUNC_END(ftrace_caller); STACK_FRAME_NON_STANDARD_FP(ftrace_caller) -SYM_FUNC_START(ftrace_stub) - UNWIND_HINT_FUNC - RET -SYM_FUNC_END(ftrace_stub) - SYM_FUNC_START(ftrace_regs_caller) /* Save the current flags before any operations that can change them */ pushfq @@ -282,9 +286,6 @@ STACK_FRAME_NON_STANDARD_FP(ftrace_regs_caller) SYM_FUNC_START(__fentry__) cmpq $ftrace_stub, ftrace_trace_function jnz trace - -SYM_INNER_LABEL(ftrace_stub, SYM_L_GLOBAL) - ENDBR RET trace: diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index c15de165ec8f..d06ada2341cb 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -162,6 +162,16 @@ #define PATCHABLE_DISCARDS *(__patchable_function_entries) #endif +#ifndef CONFIG_ARCH_SUPPORTS_CFI_CLANG +/* + * Simply points to ftrace_stub, but with the proper protocol. + * Defined by the linker script in linux/vmlinux.lds.h + */ +#define FTRACE_STUB_HACK ftrace_stub_graph = ftrace_stub; +#else +#define FTRACE_STUB_HACK +#endif + #ifdef CONFIG_FTRACE_MCOUNT_RECORD /* * The ftrace call sites are logged to a section whose name depends on the @@ -169,10 +179,6 @@ * FTRACE_CALLSITE_SECTION. We capture all of them here to avoid header * dependencies for FTRACE_CALLSITE_SECTION's definition. * - * Need to also make ftrace_stub_graph point to ftrace_stub - * so that the same stub location may have different protocols - * and not mess up with C verifiers. - * * ftrace_ops_list_func will be defined as arch_ftrace_ops_list_func * as some archs will have a different prototype for that function * but ftrace_ops_list_func() will have a single prototype. @@ -182,11 +188,11 @@ KEEP(*(__mcount_loc)) \ KEEP_PATCHABLE \ __stop_mcount_loc = .; \ - ftrace_stub_graph = ftrace_stub; \ + FTRACE_STUB_HACK \ ftrace_ops_list_func = arch_ftrace_ops_list_func; #else # ifdef CONFIG_FUNCTION_TRACER -# define MCOUNT_REC() ftrace_stub_graph = ftrace_stub; \ +# define MCOUNT_REC() FTRACE_STUB_HACK \ ftrace_ops_list_func = arch_ftrace_ops_list_func; # else # define MCOUNT_REC() -- cgit v1.2.3 From dbe69b29988465b011f198f2797b1c2b6980b50e Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 18 Oct 2022 09:59:34 +0200 Subject: bpf: Fix dispatcher patchable function entry to 5 bytes nop The patchable_function_entry(5) might output 5 single nop instructions (depends on toolchain), which will clash with bpf_arch_text_poke check for 5 bytes nop instruction. Adding early init call for dispatcher that checks and change the patchable entry into expected 5 nop instruction if needed. There's no need to take text_mutex, because we are using it in early init call which is called at pre-smp time. Fixes: ceea991a019c ("bpf: Move bpf_dispatcher function out of ftrace locations") Signed-off-by: Jiri Olsa Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20221018075934.574415-1-jolsa@kernel.org Signed-off-by: Alexei Starovoitov --- arch/x86/net/bpf_jit_comp.c | 13 +++++++++++++ include/linux/bpf.h | 14 +++++++++++++- kernel/bpf/dispatcher.c | 6 ++++++ 3 files changed, 32 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 99620428ad78..00127abd89ee 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -388,6 +389,18 @@ out: return ret; } +int __init bpf_arch_init_dispatcher_early(void *ip) +{ + const u8 *nop_insn = x86_nops[5]; + + if (is_endbr(*(u32 *)ip)) + ip += ENDBR_INSN_SIZE; + + if (memcmp(ip, nop_insn, X86_PATCH_SIZE)) + text_poke_early(ip, nop_insn, X86_PATCH_SIZE); + return 0; +} + int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, void *old_addr, void *new_addr) { diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 9e7d46d16032..0566705c1d4e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -27,6 +27,7 @@ #include #include #include +#include struct bpf_verifier_env; struct bpf_verifier_log; @@ -970,6 +971,8 @@ struct bpf_trampoline *bpf_trampoline_get(u64 key, struct bpf_attach_target_info *tgt_info); void bpf_trampoline_put(struct bpf_trampoline *tr); int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_funcs); +int __init bpf_arch_init_dispatcher_early(void *ip); + #define BPF_DISPATCHER_INIT(_name) { \ .mutex = __MUTEX_INITIALIZER(_name.mutex), \ .func = &_name##_func, \ @@ -983,6 +986,13 @@ int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_func }, \ } +#define BPF_DISPATCHER_INIT_CALL(_name) \ + static int __init _name##_init(void) \ + { \ + return bpf_arch_init_dispatcher_early(_name##_func); \ + } \ + early_initcall(_name##_init) + #ifdef CONFIG_X86_64 #define BPF_DISPATCHER_ATTRIBUTES __attribute__((patchable_function_entry(5))) #else @@ -1000,7 +1010,9 @@ int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_func } \ EXPORT_SYMBOL(bpf_dispatcher_##name##_func); \ struct bpf_dispatcher bpf_dispatcher_##name = \ - BPF_DISPATCHER_INIT(bpf_dispatcher_##name); + BPF_DISPATCHER_INIT(bpf_dispatcher_##name); \ + BPF_DISPATCHER_INIT_CALL(bpf_dispatcher_##name); + #define DECLARE_BPF_DISPATCHER(name) \ unsigned int bpf_dispatcher_##name##_func( \ const void *ctx, \ diff --git a/kernel/bpf/dispatcher.c b/kernel/bpf/dispatcher.c index fa64b80b8bca..04f0a045dcaa 100644 --- a/kernel/bpf/dispatcher.c +++ b/kernel/bpf/dispatcher.c @@ -4,6 +4,7 @@ #include #include #include +#include /* The BPF dispatcher is a multiway branch code generator. The * dispatcher is a mechanism to avoid the performance penalty of an @@ -90,6 +91,11 @@ int __weak arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int n return -ENOTSUPP; } +int __weak __init bpf_arch_init_dispatcher_early(void *ip) +{ + return -ENOTSUPP; +} + static int bpf_dispatcher_prepare(struct bpf_dispatcher *d, void *image, void *buf) { s64 ips[BPF_DISPATCHER_MAX] = {}, *ipsp = &ips[0]; -- cgit v1.2.3 From 966f015fe4329199cc49084ee2886cfb626b34d3 Mon Sep 17 00:00:00 2001 From: "Maciej S. Szmigiero" Date: Thu, 20 Oct 2022 22:46:21 +0200 Subject: ALSA: control: add snd_ctl_rename() Add a snd_ctl_rename() function that takes care of updating the control hash entries for callers that already have the relevant struct snd_kcontrol at hand and hold the control write lock (or simply haven't registered the card yet). Fixes: c27e1efb61c5 ("ALSA: control: Use xarray for faster lookups") Cc: stable@vger.kernel.org Signed-off-by: Maciej S. Szmigiero Link: https://lore.kernel.org/r/4170b71117ea81357a4f7eb8410f7cde20836c70.1666296963.git.maciej.szmigiero@oracle.com Signed-off-by: Takashi Iwai --- include/sound/control.h | 1 + sound/core/control.c | 23 +++++++++++++++++++++++ 2 files changed, 24 insertions(+) (limited to 'include') diff --git a/include/sound/control.h b/include/sound/control.h index eae443ba79ba..cc3dcc6cfb0f 100644 --- a/include/sound/control.h +++ b/include/sound/control.h @@ -138,6 +138,7 @@ int snd_ctl_remove(struct snd_card * card, struct snd_kcontrol * kcontrol); int snd_ctl_replace(struct snd_card *card, struct snd_kcontrol *kcontrol, bool add_on_replace); int snd_ctl_remove_id(struct snd_card * card, struct snd_ctl_elem_id *id); int snd_ctl_rename_id(struct snd_card * card, struct snd_ctl_elem_id *src_id, struct snd_ctl_elem_id *dst_id); +void snd_ctl_rename(struct snd_card *card, struct snd_kcontrol *kctl, const char *name); int snd_ctl_activate_id(struct snd_card *card, struct snd_ctl_elem_id *id, int active); struct snd_kcontrol *snd_ctl_find_numid(struct snd_card * card, unsigned int numid); struct snd_kcontrol *snd_ctl_find_id(struct snd_card * card, struct snd_ctl_elem_id *id); diff --git a/sound/core/control.c b/sound/core/control.c index a7271927d875..50e7ba66f187 100644 --- a/sound/core/control.c +++ b/sound/core/control.c @@ -753,6 +753,29 @@ int snd_ctl_rename_id(struct snd_card *card, struct snd_ctl_elem_id *src_id, } EXPORT_SYMBOL(snd_ctl_rename_id); +/** + * snd_ctl_rename - rename the control on the card + * @card: the card instance + * @kctl: the control to rename + * @name: the new name + * + * Renames the specified control on the card to the new name. + * + * Make sure to take the control write lock - down_write(&card->controls_rwsem). + */ +void snd_ctl_rename(struct snd_card *card, struct snd_kcontrol *kctl, + const char *name) +{ + remove_hash_entries(card, kctl); + + if (strscpy(kctl->id.name, name, sizeof(kctl->id.name)) < 0) + pr_warn("ALSA: Renamed control new name '%s' truncated to '%s'\n", + name, kctl->id.name); + + add_hash_entries(card, kctl); +} +EXPORT_SYMBOL(snd_ctl_rename); + #ifndef CONFIG_SND_CTL_FAST_LOOKUP static struct snd_kcontrol * snd_ctl_find_numid_slow(struct snd_card *card, unsigned int numid) -- cgit v1.2.3 From 0251d0107cfb0bb5ab2d3f97710487b9522db020 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Wed, 19 Oct 2022 08:44:44 +0800 Subject: iommu: Add gfp parameter to iommu_alloc_resv_region Add gfp parameter to iommu_alloc_resv_region() for the callers to specify the memory allocation behavior. Thus iommu_alloc_resv_region() could also be available in critical contexts. Signed-off-by: Lu Baolu Tested-by: Alex Williamson Link: https://lore.kernel.org/r/20220927053109.4053662-2-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/acpi/arm64/iort.c | 3 ++- drivers/iommu/amd/iommu.c | 7 ++++--- drivers/iommu/apple-dart.c | 2 +- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 2 +- drivers/iommu/arm/arm-smmu/arm-smmu.c | 2 +- drivers/iommu/intel/iommu.c | 8 +++++--- drivers/iommu/iommu.c | 7 ++++--- drivers/iommu/mtk_iommu.c | 3 ++- drivers/iommu/virtio-iommu.c | 9 ++++++--- include/linux/iommu.h | 2 +- 10 files changed, 27 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c index ca2aed86b540..8059baf4ef27 100644 --- a/drivers/acpi/arm64/iort.c +++ b/drivers/acpi/arm64/iort.c @@ -1142,7 +1142,8 @@ static void iort_iommu_msi_get_resv_regions(struct device *dev, struct iommu_resv_region *region; region = iommu_alloc_resv_region(base + SZ_64K, SZ_64K, - prot, IOMMU_RESV_MSI); + prot, IOMMU_RESV_MSI, + GFP_KERNEL); if (region) list_add_tail(®ion->list, head); } diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 65856e401949..d3b39d0416fa 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -2330,7 +2330,8 @@ static void amd_iommu_get_resv_regions(struct device *dev, type = IOMMU_RESV_RESERVED; region = iommu_alloc_resv_region(entry->address_start, - length, prot, type); + length, prot, type, + GFP_KERNEL); if (!region) { dev_err(dev, "Out of memory allocating dm-regions\n"); return; @@ -2340,14 +2341,14 @@ static void amd_iommu_get_resv_regions(struct device *dev, region = iommu_alloc_resv_region(MSI_RANGE_START, MSI_RANGE_END - MSI_RANGE_START + 1, - 0, IOMMU_RESV_MSI); + 0, IOMMU_RESV_MSI, GFP_KERNEL); if (!region) return; list_add_tail(®ion->list, head); region = iommu_alloc_resv_region(HT_RANGE_START, HT_RANGE_END - HT_RANGE_START + 1, - 0, IOMMU_RESV_RESERVED); + 0, IOMMU_RESV_RESERVED, GFP_KERNEL); if (!region) return; list_add_tail(®ion->list, head); diff --git a/drivers/iommu/apple-dart.c b/drivers/iommu/apple-dart.c index 4526575b999e..4f4a323be0d0 100644 --- a/drivers/iommu/apple-dart.c +++ b/drivers/iommu/apple-dart.c @@ -758,7 +758,7 @@ static void apple_dart_get_resv_regions(struct device *dev, region = iommu_alloc_resv_region(DOORBELL_ADDR, PAGE_SIZE, prot, - IOMMU_RESV_MSI); + IOMMU_RESV_MSI, GFP_KERNEL); if (!region) return; diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index ba47c73f5b8c..6d5df91c5c46 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -2757,7 +2757,7 @@ static void arm_smmu_get_resv_regions(struct device *dev, int prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO; region = iommu_alloc_resv_region(MSI_IOVA_BASE, MSI_IOVA_LENGTH, - prot, IOMMU_RESV_SW_MSI); + prot, IOMMU_RESV_SW_MSI, GFP_KERNEL); if (!region) return; diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c index 6c1114a4d6cc..30dab1418e3f 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c @@ -1534,7 +1534,7 @@ static void arm_smmu_get_resv_regions(struct device *dev, int prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO; region = iommu_alloc_resv_region(MSI_IOVA_BASE, MSI_IOVA_LENGTH, - prot, IOMMU_RESV_SW_MSI); + prot, IOMMU_RESV_SW_MSI, GFP_KERNEL); if (!region) return; diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index a8b36c3fddf1..d5965b4f8b60 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -4552,7 +4552,8 @@ static void intel_iommu_get_resv_regions(struct device *device, IOMMU_RESV_DIRECT_RELAXABLE : IOMMU_RESV_DIRECT; resv = iommu_alloc_resv_region(rmrr->base_address, - length, prot, type); + length, prot, type, + GFP_KERNEL); if (!resv) break; @@ -4567,7 +4568,8 @@ static void intel_iommu_get_resv_regions(struct device *device, if ((pdev->class >> 8) == PCI_CLASS_BRIDGE_ISA) { reg = iommu_alloc_resv_region(0, 1UL << 24, prot, - IOMMU_RESV_DIRECT_RELAXABLE); + IOMMU_RESV_DIRECT_RELAXABLE, + GFP_KERNEL); if (reg) list_add_tail(®->list, head); } @@ -4576,7 +4578,7 @@ static void intel_iommu_get_resv_regions(struct device *device, reg = iommu_alloc_resv_region(IOAPIC_RANGE_START, IOAPIC_RANGE_END - IOAPIC_RANGE_START + 1, - 0, IOMMU_RESV_MSI); + 0, IOMMU_RESV_MSI, GFP_KERNEL); if (!reg) return; list_add_tail(®->list, head); diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 4893c2429ca5..65a3b3d886dc 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -504,7 +504,7 @@ static int iommu_insert_resv_region(struct iommu_resv_region *new, LIST_HEAD(stack); nr = iommu_alloc_resv_region(new->start, new->length, - new->prot, new->type); + new->prot, new->type, GFP_KERNEL); if (!nr) return -ENOMEM; @@ -2579,11 +2579,12 @@ EXPORT_SYMBOL(iommu_put_resv_regions); struct iommu_resv_region *iommu_alloc_resv_region(phys_addr_t start, size_t length, int prot, - enum iommu_resv_type type) + enum iommu_resv_type type, + gfp_t gfp) { struct iommu_resv_region *region; - region = kzalloc(sizeof(*region), GFP_KERNEL); + region = kzalloc(sizeof(*region), gfp); if (!region) return NULL; diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index 5a4e00e4bbbc..2ab2ecfe01f8 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -917,7 +917,8 @@ static void mtk_iommu_get_resv_regions(struct device *dev, continue; region = iommu_alloc_resv_region(resv->iova_base, resv->size, - prot, IOMMU_RESV_RESERVED); + prot, IOMMU_RESV_RESERVED, + GFP_KERNEL); if (!region) return; diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c index b7c22802f57c..8b1b5c270e50 100644 --- a/drivers/iommu/virtio-iommu.c +++ b/drivers/iommu/virtio-iommu.c @@ -490,11 +490,13 @@ static int viommu_add_resv_mem(struct viommu_endpoint *vdev, fallthrough; case VIRTIO_IOMMU_RESV_MEM_T_RESERVED: region = iommu_alloc_resv_region(start, size, 0, - IOMMU_RESV_RESERVED); + IOMMU_RESV_RESERVED, + GFP_KERNEL); break; case VIRTIO_IOMMU_RESV_MEM_T_MSI: region = iommu_alloc_resv_region(start, size, prot, - IOMMU_RESV_MSI); + IOMMU_RESV_MSI, + GFP_KERNEL); break; } if (!region) @@ -909,7 +911,8 @@ static void viommu_get_resv_regions(struct device *dev, struct list_head *head) */ if (!msi) { msi = iommu_alloc_resv_region(MSI_IOVA_BASE, MSI_IOVA_LENGTH, - prot, IOMMU_RESV_SW_MSI); + prot, IOMMU_RESV_SW_MSI, + GFP_KERNEL); if (!msi) return; diff --git a/include/linux/iommu.h b/include/linux/iommu.h index a325532aeab5..3c9da1f8979e 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -455,7 +455,7 @@ extern void iommu_set_default_translated(bool cmd_line); extern bool iommu_default_passthrough(void); extern struct iommu_resv_region * iommu_alloc_resv_region(phys_addr_t start, size_t length, int prot, - enum iommu_resv_type type); + enum iommu_resv_type type, gfp_t gfp); extern int iommu_get_group_resv_regions(struct iommu_group *group, struct list_head *head); -- cgit v1.2.3 From 8a254d90a77580244ec57e82bca7eb65656cc167 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 19 Oct 2022 23:29:58 +0200 Subject: efi: efivars: Fix variable writes without query_variable_store() Commit bbc6d2c6ef22 ("efi: vars: Switch to new wrapper layer") refactored the efivars layer so that the 'business logic' related to which UEFI variables affect the boot flow in which way could be moved out of it, and into the efivarfs driver. This inadvertently broke setting variables on firmware implementations that lack the QueryVariableInfo() boot service, because we no longer tolerate a EFI_UNSUPPORTED result from check_var_size() when calling efivar_entry_set_get_size(), which now ends up calling check_var_size() a second time inadvertently. If QueryVariableInfo() is missing, we support writes of up to 64k - let's move that logic into check_var_size(), and drop the redundant call. Cc: # v6.0 Fixes: bbc6d2c6ef22 ("efi: vars: Switch to new wrapper layer") Signed-off-by: Ard Biesheuvel --- drivers/firmware/efi/vars.c | 10 +++++----- fs/efivarfs/vars.c | 16 ---------------- include/linux/efi.h | 3 --- 3 files changed, 5 insertions(+), 24 deletions(-) (limited to 'include') diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c index dd74d2ad3184..433b61587139 100644 --- a/drivers/firmware/efi/vars.c +++ b/drivers/firmware/efi/vars.c @@ -7,6 +7,7 @@ */ #include +#include #include #include #include @@ -20,19 +21,19 @@ static struct efivars *__efivars; static DEFINE_SEMAPHORE(efivars_lock); -efi_status_t check_var_size(u32 attributes, unsigned long size) +static efi_status_t check_var_size(u32 attributes, unsigned long size) { const struct efivar_operations *fops; fops = __efivars->ops; if (!fops->query_variable_store) - return EFI_UNSUPPORTED; + return (size <= SZ_64K) ? EFI_SUCCESS : EFI_OUT_OF_RESOURCES; return fops->query_variable_store(attributes, size, false); } -EXPORT_SYMBOL_NS_GPL(check_var_size, EFIVAR); +static efi_status_t check_var_size_nonblocking(u32 attributes, unsigned long size) { const struct efivar_operations *fops; @@ -40,11 +41,10 @@ efi_status_t check_var_size_nonblocking(u32 attributes, unsigned long size) fops = __efivars->ops; if (!fops->query_variable_store) - return EFI_UNSUPPORTED; + return (size <= SZ_64K) ? EFI_SUCCESS : EFI_OUT_OF_RESOURCES; return fops->query_variable_store(attributes, size, true); } -EXPORT_SYMBOL_NS_GPL(check_var_size_nonblocking, EFIVAR); /** * efivars_kobject - get the kobject for the registered efivars diff --git a/fs/efivarfs/vars.c b/fs/efivarfs/vars.c index a0ef63cfcecb..9e4f47808bd5 100644 --- a/fs/efivarfs/vars.c +++ b/fs/efivarfs/vars.c @@ -651,22 +651,6 @@ int efivar_entry_set_get_size(struct efivar_entry *entry, u32 attributes, if (err) return err; - /* - * Ensure that the available space hasn't shrunk below the safe level - */ - status = check_var_size(attributes, *size + ucs2_strsize(name, 1024)); - if (status != EFI_SUCCESS) { - if (status != EFI_UNSUPPORTED) { - err = efi_status_to_err(status); - goto out; - } - - if (*size > 65536) { - err = -ENOSPC; - goto out; - } - } - status = efivar_set_variable_locked(name, vendor, attributes, *size, data, false); if (status != EFI_SUCCESS) { diff --git a/include/linux/efi.h b/include/linux/efi.h index da3974bf05d3..80f3c1c7827d 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1085,9 +1085,6 @@ efi_status_t efivar_set_variable_locked(efi_char16_t *name, efi_guid_t *vendor, efi_status_t efivar_set_variable(efi_char16_t *name, efi_guid_t *vendor, u32 attr, unsigned long data_size, void *data); -efi_status_t check_var_size(u32 attributes, unsigned long size); -efi_status_t check_var_size_nonblocking(u32 attributes, unsigned long size); - #if IS_ENABLED(CONFIG_EFI_CAPSULE_LOADER) extern bool efi_capsule_pending(int *reset_type); -- cgit v1.2.3 From ed51862f2f57cbce6fed2d4278cfe70a490899fd Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Mon, 17 Oct 2022 20:45:39 +0200 Subject: kvm: Add support for arch compat vm ioctls We will introduce the first architecture specific compat vm ioctl in the next patch. Add all necessary boilerplate to allow architectures to override compat vm ioctls when necessary. Signed-off-by: Alexander Graf Message-Id: <20221017184541.2658-2-graf@amazon.com> Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 2 ++ virt/kvm/kvm_main.c | 11 +++++++++++ 2 files changed, 13 insertions(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 32f259fa5801..00c3448ba7f8 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1390,6 +1390,8 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap); long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); +long kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl, + unsigned long arg); int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu); int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index e30f1b4ecfa5..1376a47fedee 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -4839,6 +4839,12 @@ struct compat_kvm_clear_dirty_log { }; }; +long __weak kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl, + unsigned long arg) +{ + return -ENOTTY; +} + static long kvm_vm_compat_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -4847,6 +4853,11 @@ static long kvm_vm_compat_ioctl(struct file *filp, if (kvm->mm != current->mm || kvm->vm_dead) return -EIO; + + r = kvm_arch_vm_compat_ioctl(filp, ioctl, arg); + if (r != -ENOTTY) + return r; + switch (ioctl) { #ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT case KVM_CLEAR_DIRTY_LOG: { -- cgit v1.2.3 From e993ffe3da4bcddea0536b03be1031bf35cd8d85 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Fri, 21 Oct 2022 11:16:39 +0100 Subject: net: flag sockets supporting msghdr originated zerocopy We need an efficient way in io_uring to check whether a socket supports zerocopy with msghdr provided ubuf_info. Add a new flag into the struct socket flags fields. Cc: # 6.0 Signed-off-by: Pavel Begunkov Acked-by: Jakub Kicinski Link: https://lore.kernel.org/r/3dafafab822b1c66308bb58a0ac738b1e3f53f74.1666346426.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/linux/net.h | 1 + net/ipv4/tcp.c | 1 + net/ipv4/udp.c | 1 + 3 files changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/net.h b/include/linux/net.h index 711c3593c3b8..18d942bbdf6e 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -41,6 +41,7 @@ struct net; #define SOCK_NOSPACE 2 #define SOCK_PASSCRED 3 #define SOCK_PASSSEC 4 +#define SOCK_SUPPORT_ZC 5 #ifndef ARCH_HAS_SOCKET_TYPES /** diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index f8232811a5be..ef14efa1fb70 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -457,6 +457,7 @@ void tcp_init_sock(struct sock *sk) WRITE_ONCE(sk->sk_sndbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[1])); WRITE_ONCE(sk->sk_rcvbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[1])); + set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); sk_sockets_allocated_inc(sk); } EXPORT_SYMBOL(tcp_init_sock); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 662d717d5123..1c646797cc79 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1624,6 +1624,7 @@ int udp_init_sock(struct sock *sk) { skb_queue_head_init(&udp_sk(sk)->reader_queue); sk->sk_destruct = udp_destruct_sock; + set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); return 0; } -- cgit v1.2.3 From 52826d3b2d1d8e1180a84bef7d72596d6a024a38 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 23 Oct 2022 12:01:01 -0700 Subject: kernel/utsname_sysctl.c: Fix hostname polling Commit bfca3dd3d068 ("kernel/utsname_sysctl.c: print kernel arch") added a new entry to the uts_kern_table[] array, but didn't update the UTS_PROC_xyz enumerators of older entries, breaking anything that used them. Which is admittedly not many cases: it's really just the two uses of uts_proc_notify() in kernel/sys.c. But apparently journald-systemd actually uses this to detect hostname changes. Reported-by: Torsten Hilbrich Fixes: bfca3dd3d068 ("kernel/utsname_sysctl.c: print kernel arch") Link: https://lore.kernel.org/lkml/0c2b92a6-0f25-9538-178f-eee3b06da23f@secunet.com/ Link: https://linux-regtracking.leemhuis.info/regzbot/regression/0c2b92a6-0f25-9538-178f-eee3b06da23f@secunet.com/ Cc: Petr Vorel Signed-off-by: Linus Torvalds --- include/linux/utsname.h | 1 + kernel/utsname_sysctl.c | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/utsname.h b/include/linux/utsname.h index 2b1737c9b244..bf7613ba412b 100644 --- a/include/linux/utsname.h +++ b/include/linux/utsname.h @@ -10,6 +10,7 @@ #include enum uts_proc { + UTS_PROC_ARCH, UTS_PROC_OSTYPE, UTS_PROC_OSRELEASE, UTS_PROC_VERSION, diff --git a/kernel/utsname_sysctl.c b/kernel/utsname_sysctl.c index 064072c16e3d..f50398cb790d 100644 --- a/kernel/utsname_sysctl.c +++ b/kernel/utsname_sysctl.c @@ -74,6 +74,7 @@ static int proc_do_uts_string(struct ctl_table *table, int write, static DEFINE_CTL_TABLE_POLL(hostname_poll); static DEFINE_CTL_TABLE_POLL(domainname_poll); +// Note: update 'enum uts_proc' to match any changes to this table static struct ctl_table uts_kern_table[] = { { .procname = "arch", -- cgit v1.2.3 From 720ca52bcef225b967a339e0fffb6d0c7e962240 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 21 Oct 2022 09:03:04 -0700 Subject: net-memcg: avoid stalls when under memory pressure As Shakeel explains the commit under Fixes had the unintended side-effect of no longer pre-loading the cached memory allowance. Even tho we previously dropped the first packet received when over memory limit - the consecutive ones would get thru by using the cache. The charging was happening in batches of 128kB, so we'd let in 128kB (truesize) worth of packets per one drop. After the change we no longer force charge, there will be no cache filling side effects. This causes significant drops and connection stalls for workloads which use a lot of page cache, since we can't reclaim page cache under GFP_NOWAIT. Some of the latency can be recovered by improving SACK reneg handling but nowhere near enough to get back to the pre-5.15 performance (the application I'm experimenting with still sees 5-10x worst latency). Apply the suggested workaround of using GFP_ATOMIC. We will now be more permissive than previously as we'll drop _no_ packets in softirq when under pressure. But I can't think of any good and simple way to address that within networking. Link: https://lore.kernel.org/all/20221012163300.795e7b86@kernel.org/ Suggested-by: Shakeel Butt Fixes: 4b1327be9fe5 ("net-memcg: pass in gfp_t mask to mem_cgroup_charge_skmem()") Acked-by: Shakeel Butt Acked-by: Roman Gushchin Link: https://lore.kernel.org/r/20221021160304.1362511-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/net/sock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index 9e464f6409a7..22f8bab583dd 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2585,7 +2585,7 @@ static inline gfp_t gfp_any(void) static inline gfp_t gfp_memcg_charge(void) { - return in_softirq() ? GFP_NOWAIT : GFP_KERNEL; + return in_softirq() ? GFP_ATOMIC : GFP_KERNEL; } static inline long sock_rcvtimeo(const struct sock *sk, bool noblock) -- cgit v1.2.3 From 68bc147363bd9769a07d1cbf5cbe2bb4573f4e3c Mon Sep 17 00:00:00 2001 From: David Francis Date: Fri, 16 Sep 2022 11:15:01 -0400 Subject: drm/amd: Add IMU fw version to fw version queries IMU is a new firmware for GFX11. There are four means by which firmware version can be queried from the driver: device attributes, vf2pf, debugfs, and the AMDGPU_INFO_FW_VERSION option in the amdgpu info ioctl. Add IMU as an option for those four methods. V2: Added debugfs Reviewed-by: Likun Gao Reviewed-by: Alex Deucher Signed-off-by: David Francis Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 13 +++++++++++++ drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c | 4 +++- drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c | 1 + drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h | 1 + include/uapi/drm/amdgpu_drm.h | 2 ++ 5 files changed, 20 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index fe23e09eec98..bf1ff8f0e712 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -344,6 +344,10 @@ static int amdgpu_firmware_info(struct drm_amdgpu_info_firmware *fw_info, fw_info->ver = adev->mes.ucode_fw_version[1]; fw_info->feature = 0; break; + case AMDGPU_INFO_FW_IMU: + fw_info->ver = adev->gfx.imu_fw_version; + fw_info->feature = 0; + break; default: return -EINVAL; } @@ -1520,6 +1524,15 @@ static int amdgpu_debugfs_firmware_info_show(struct seq_file *m, void *unused) fw_info.feature, fw_info.ver); } + /* IMU */ + query_fw.fw_type = AMDGPU_INFO_FW_IMU; + query_fw.index = 0; + ret = amdgpu_firmware_info(&fw_info, &query_fw, adev); + if (ret) + return ret; + seq_printf(m, "IMU feature version: %u, firmware version: 0x%08x\n", + fw_info.feature, fw_info.ver); + /* PSP SOS */ query_fw.fw_type = AMDGPU_INFO_FW_SOS; ret = amdgpu_firmware_info(&fw_info, &query_fw, adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c index dd0bc649a57d..5cb62e6249c2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c @@ -698,6 +698,7 @@ FW_VERSION_ATTR(rlc_srlg_fw_version, 0444, gfx.rlc_srlg_fw_version); FW_VERSION_ATTR(rlc_srls_fw_version, 0444, gfx.rlc_srls_fw_version); FW_VERSION_ATTR(mec_fw_version, 0444, gfx.mec_fw_version); FW_VERSION_ATTR(mec2_fw_version, 0444, gfx.mec2_fw_version); +FW_VERSION_ATTR(imu_fw_version, 0444, gfx.imu_fw_version); FW_VERSION_ATTR(sos_fw_version, 0444, psp.sos.fw_version); FW_VERSION_ATTR(asd_fw_version, 0444, psp.asd_context.bin_desc.fw_version); FW_VERSION_ATTR(ta_ras_fw_version, 0444, psp.ras_context.context.bin_desc.fw_version); @@ -719,7 +720,8 @@ static struct attribute *fw_attrs[] = { &dev_attr_ta_ras_fw_version.attr, &dev_attr_ta_xgmi_fw_version.attr, &dev_attr_smc_fw_version.attr, &dev_attr_sdma_fw_version.attr, &dev_attr_sdma2_fw_version.attr, &dev_attr_vcn_fw_version.attr, - &dev_attr_dmcu_fw_version.attr, NULL + &dev_attr_dmcu_fw_version.attr, &dev_attr_imu_fw_version.attr, + NULL }; static const struct attribute_group fw_attr_group = { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c index 9c765b04aae3..c73abe54d974 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c @@ -547,6 +547,7 @@ static void amdgpu_virt_populate_vf2pf_ucode_info(struct amdgpu_device *adev) POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_RLC_SRLS, adev->gfx.rlc_srls_fw_version); POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_MEC, adev->gfx.mec_fw_version); POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_MEC2, adev->gfx.mec2_fw_version); + POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_IMU, adev->gfx.imu_fw_version); POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_SOS, adev->psp.sos.fw_version); POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_ASD, adev->psp.asd_context.bin_desc.fw_version); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h b/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h index e78e4c27b62a..6c97148ca0ed 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h @@ -70,6 +70,7 @@ enum amd_sriov_ucode_engine_id { AMD_SRIOV_UCODE_ID_RLC_SRLS, AMD_SRIOV_UCODE_ID_MEC, AMD_SRIOV_UCODE_ID_MEC2, + AMD_SRIOV_UCODE_ID_IMU, AMD_SRIOV_UCODE_ID_SOS, AMD_SRIOV_UCODE_ID_ASD, AMD_SRIOV_UCODE_ID_TA_RAS, diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index 7ee65c0b4f70..0d93ec132ebb 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -763,6 +763,8 @@ struct drm_amdgpu_cs_chunk_data { #define AMDGPU_INFO_FW_MES_KIQ 0x19 /* Subquery id: Query MES firmware version */ #define AMDGPU_INFO_FW_MES 0x1a + /* Subquery id: Query IMU firmware version */ + #define AMDGPU_INFO_FW_IMU 0x1b /* number of bytes moved for TTM migration */ #define AMDGPU_INFO_NUM_BYTES_MOVED 0x0f -- cgit v1.2.3 From 4fa86555d1cd338afc6e6308cc1ff890a014ec8c Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 21 Oct 2022 12:35:32 -0700 Subject: genetlink: piggy back on resv_op to default to a reject policy To keep backward compatibility we used to leave attribute parsing to the family if no policy is specified. This becomes tedious as we move to more strict validation. Families must define reject all policies if they don't want any attributes accepted. Piggy back on the resv_start_op field as the switchover point. AFAICT only ethtool has added new commands since the resv_start_op was defined, and it has per-op policies so this should be a no-op. Nonetheless the patch should still go into v6.1 for consistency. Link: https://lore.kernel.org/all/20221019125745.3f2e7659@kernel.org/ Link: https://lore.kernel.org/r/20221021193532.1511293-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/net/genetlink.h | 10 +++++++++- net/netlink/genetlink.c | 23 +++++++++++++++++++++++ 2 files changed, 32 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 3d08e67b3cfc..9f97f73615b6 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -41,13 +41,21 @@ struct genl_info; * @mcgrps: multicast groups used by this family * @n_mcgrps: number of multicast groups * @resv_start_op: first operation for which reserved fields of the header - * can be validated, new families should leave this field at zero + * can be validated and policies are required (see below); + * new families should leave this field at zero * @mcgrp_offset: starting number of multicast group IDs in this family * (private) * @ops: the operations supported by this family * @n_ops: number of operations supported by this family * @small_ops: the small-struct operations supported by this family * @n_small_ops: number of small-struct operations supported by this family + * + * Attribute policies (the combination of @policy and @maxattr fields) + * can be attached at the family level or at the operation level. + * If both are present the per-operation policy takes precedence. + * For operations before @resv_start_op lack of policy means that the core + * will perform no attribute parsing or validation. For newer operations + * if policy is not provided core will reject all TLV attributes. */ struct genl_family { int id; /* private */ diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 39b7c00e4cef..b1fd059c9992 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -78,10 +78,29 @@ static unsigned long mc_group_start = 0x3 | BIT(GENL_ID_CTRL) | static unsigned long *mc_groups = &mc_group_start; static unsigned long mc_groups_longs = 1; +/* We need the last attribute with non-zero ID therefore a 2-entry array */ +static struct nla_policy genl_policy_reject_all[] = { + { .type = NLA_REJECT }, + { .type = NLA_REJECT }, +}; + static int genl_ctrl_event(int event, const struct genl_family *family, const struct genl_multicast_group *grp, int grp_id); +static void +genl_op_fill_in_reject_policy(const struct genl_family *family, + struct genl_ops *op) +{ + BUILD_BUG_ON(ARRAY_SIZE(genl_policy_reject_all) - 1 != 1); + + if (op->policy || op->cmd < family->resv_start_op) + return; + + op->policy = genl_policy_reject_all; + op->maxattr = 1; +} + static const struct genl_family *genl_family_find_byid(unsigned int id) { return idr_find(&genl_fam_idr, id); @@ -113,6 +132,8 @@ static void genl_op_from_full(const struct genl_family *family, op->maxattr = family->maxattr; if (!op->policy) op->policy = family->policy; + + genl_op_fill_in_reject_policy(family, op); } static int genl_get_cmd_full(u32 cmd, const struct genl_family *family, @@ -142,6 +163,8 @@ static void genl_op_from_small(const struct genl_family *family, op->maxattr = family->maxattr; op->policy = family->policy; + + genl_op_fill_in_reject_policy(family, op); } static int genl_get_cmd_small(u32 cmd, const struct genl_family *family, -- cgit v1.2.3 From 8da7f0976b9071b528c545008de9d10cc81883b1 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Wed, 12 Oct 2022 16:46:17 +0100 Subject: media: videodev2.h: V4L2_DV_BT_BLANKING_HEIGHT should check 'interlaced' If it is a progressive (non-interlaced) format, then ignore the interlaced timing values. Signed-off-by: Hans Verkuil Fixes: 7f68127fa11f ([media] videodev2.h: defines to calculate blanking and frame sizes) Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/videodev2.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 86cae23cc446..29da1f4b4578 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -1601,7 +1601,8 @@ struct v4l2_bt_timings { ((bt)->width + V4L2_DV_BT_BLANKING_WIDTH(bt)) #define V4L2_DV_BT_BLANKING_HEIGHT(bt) \ ((bt)->vfrontporch + (bt)->vsync + (bt)->vbackporch + \ - (bt)->il_vfrontporch + (bt)->il_vsync + (bt)->il_vbackporch) + ((bt)->interlaced ? \ + ((bt)->il_vfrontporch + (bt)->il_vsync + (bt)->il_vbackporch) : 0)) #define V4L2_DV_BT_FRAME_HEIGHT(bt) \ ((bt)->height + V4L2_DV_BT_BLANKING_HEIGHT(bt)) -- cgit v1.2.3 From 31970608a6d3796c3adbfbfd379fa3092de65c5d Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 26 Sep 2022 12:45:32 -0700 Subject: overflow: Fix kern-doc markup for functions Fix the kern-doc markings for several of the overflow helpers and move their location into the core kernel API documentation, where it belongs (it's not driver-specific). Cc: Jonathan Corbet Cc: linux-doc@vger.kernel.org Cc: linux-hardening@vger.kernel.org Reviewed-by: Akira Yokosawa Signed-off-by: Kees Cook --- Documentation/core-api/kernel-api.rst | 6 ++++++ Documentation/driver-api/basics.rst | 3 --- include/linux/overflow.h | 38 +++++++++++++++-------------------- 3 files changed, 22 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/Documentation/core-api/kernel-api.rst b/Documentation/core-api/kernel-api.rst index 0793c400d4b0..06f4ab122697 100644 --- a/Documentation/core-api/kernel-api.rst +++ b/Documentation/core-api/kernel-api.rst @@ -118,6 +118,12 @@ Text Searching CRC and Math Functions in Linux =============================== +Arithmetic Overflow Checking +---------------------------- + +.. kernel-doc:: include/linux/overflow.h + :internal: + CRC Functions ------------- diff --git a/Documentation/driver-api/basics.rst b/Documentation/driver-api/basics.rst index 3e2dae954898..4b4d8e28d3be 100644 --- a/Documentation/driver-api/basics.rst +++ b/Documentation/driver-api/basics.rst @@ -107,9 +107,6 @@ Kernel utility functions .. kernel-doc:: kernel/panic.c :export: -.. kernel-doc:: include/linux/overflow.h - :internal: - Device Resource Management -------------------------- diff --git a/include/linux/overflow.h b/include/linux/overflow.h index 19dfdd74835e..1d3be1a2204c 100644 --- a/include/linux/overflow.h +++ b/include/linux/overflow.h @@ -51,8 +51,8 @@ static inline bool __must_check __must_check_overflow(bool overflow) return unlikely(overflow); } -/** check_add_overflow() - Calculate addition with overflow checking - * +/** + * check_add_overflow() - Calculate addition with overflow checking * @a: first addend * @b: second addend * @d: pointer to store sum @@ -66,8 +66,8 @@ static inline bool __must_check __must_check_overflow(bool overflow) #define check_add_overflow(a, b, d) \ __must_check_overflow(__builtin_add_overflow(a, b, d)) -/** check_sub_overflow() - Calculate subtraction with overflow checking - * +/** + * check_sub_overflow() - Calculate subtraction with overflow checking * @a: minuend; value to subtract from * @b: subtrahend; value to subtract from @a * @d: pointer to store difference @@ -81,8 +81,8 @@ static inline bool __must_check __must_check_overflow(bool overflow) #define check_sub_overflow(a, b, d) \ __must_check_overflow(__builtin_sub_overflow(a, b, d)) -/** check_mul_overflow() - Calculate multiplication with overflow checking - * +/** + * check_mul_overflow() - Calculate multiplication with overflow checking * @a: first factor * @b: second factor * @d: pointer to store product @@ -96,23 +96,24 @@ static inline bool __must_check __must_check_overflow(bool overflow) #define check_mul_overflow(a, b, d) \ __must_check_overflow(__builtin_mul_overflow(a, b, d)) -/** check_shl_overflow() - Calculate a left-shifted value and check overflow - * +/** + * check_shl_overflow() - Calculate a left-shifted value and check overflow * @a: Value to be shifted * @s: How many bits left to shift * @d: Pointer to where to store the result * * Computes *@d = (@a << @s) * - * Returns true if '*d' cannot hold the result or when 'a << s' doesn't + * Returns true if '*@d' cannot hold the result or when '@a << @s' doesn't * make sense. Example conditions: - * - 'a << s' causes bits to be lost when stored in *d. - * - 's' is garbage (e.g. negative) or so large that the result of - * 'a << s' is guaranteed to be 0. - * - 'a' is negative. - * - 'a << s' sets the sign bit, if any, in '*d'. * - * '*d' will hold the results of the attempted shift, but is not + * - '@a << @s' causes bits to be lost when stored in *@d. + * - '@s' is garbage (e.g. negative) or so large that the result of + * '@a << @s' is guaranteed to be 0. + * - '@a' is negative. + * - '@a << @s' sets the sign bit, if any, in '*@d'. + * + * '*@d' will hold the results of the attempted shift, but is not * considered "safe for use" if true is returned. */ #define check_shl_overflow(a, s, d) __must_check_overflow(({ \ @@ -129,7 +130,6 @@ static inline bool __must_check __must_check_overflow(bool overflow) /** * size_mul() - Calculate size_t multiplication with saturation at SIZE_MAX - * * @factor1: first factor * @factor2: second factor * @@ -149,7 +149,6 @@ static inline size_t __must_check size_mul(size_t factor1, size_t factor2) /** * size_add() - Calculate size_t addition with saturation at SIZE_MAX - * * @addend1: first addend * @addend2: second addend * @@ -169,7 +168,6 @@ static inline size_t __must_check size_add(size_t addend1, size_t addend2) /** * size_sub() - Calculate size_t subtraction with saturation at SIZE_MAX - * * @minuend: value to subtract from * @subtrahend: value to subtract from @minuend * @@ -192,7 +190,6 @@ static inline size_t __must_check size_sub(size_t minuend, size_t subtrahend) /** * array_size() - Calculate size of 2-dimensional array. - * * @a: dimension one * @b: dimension two * @@ -205,7 +202,6 @@ static inline size_t __must_check size_sub(size_t minuend, size_t subtrahend) /** * array3_size() - Calculate size of 3-dimensional array. - * * @a: dimension one * @b: dimension two * @c: dimension three @@ -220,7 +216,6 @@ static inline size_t __must_check size_sub(size_t minuend, size_t subtrahend) /** * flex_array_size() - Calculate size of a flexible array member * within an enclosing structure. - * * @p: Pointer to the structure. * @member: Name of the flexible array member. * @count: Number of elements in the array. @@ -237,7 +232,6 @@ static inline size_t __must_check size_sub(size_t minuend, size_t subtrahend) /** * struct_size() - Calculate size of structure with trailing flexible array. - * * @p: Pointer to the structure. * @member: Name of the array member. * @count: Number of elements in the array. -- cgit v1.2.3 From cb6c18b5a41622c7a439508f7421f8766a91cb87 Mon Sep 17 00:00:00 2001 From: Ravi Bangoria Date: Sat, 1 Oct 2022 11:37:05 +0530 Subject: perf/mem: Rename PERF_MEM_LVLNUM_EXTN_MEM to PERF_MEM_LVLNUM_CXL PERF_MEM_LVLNUM_EXTN_MEM was introduced to cover CXL devices but it's bit ambiguous name and also not generic enough to cover cxl.cache and cxl.io devices. Rename it to PERF_MEM_LVLNUM_CXL to be more specific. Signed-off-by: Ravi Bangoria Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/f6268268-b4e9-9ed6-0453-65792644d953@amd.com --- arch/x86/events/amd/ibs.c | 2 +- include/uapi/linux/perf_event.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c index 3271735f0070..4cb710efbdd9 100644 --- a/arch/x86/events/amd/ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -801,7 +801,7 @@ static void perf_ibs_get_mem_lvl(union ibs_op_data2 *op_data2, /* Extension Memory */ if (ibs_caps & IBS_CAPS_ZEN4 && ibs_data_src == IBS_DATA_SRC_EXT_EXT_MEM) { - data_src->mem_lvl_num = PERF_MEM_LVLNUM_EXTN_MEM; + data_src->mem_lvl_num = PERF_MEM_LVLNUM_CXL; if (op_data2->rmt_node) { data_src->mem_remote = PERF_MEM_REMOTE_REMOTE; /* IBS doesn't provide Remote socket detail */ diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 85be78e0e7f6..ccb7f5dad59b 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -1337,7 +1337,7 @@ union perf_mem_data_src { #define PERF_MEM_LVLNUM_L3 0x03 /* L3 */ #define PERF_MEM_LVLNUM_L4 0x04 /* L4 */ /* 5-0x8 available */ -#define PERF_MEM_LVLNUM_EXTN_MEM 0x09 /* Extension memory */ +#define PERF_MEM_LVLNUM_CXL 0x09 /* CXL */ #define PERF_MEM_LVLNUM_IO 0x0a /* I/O */ #define PERF_MEM_LVLNUM_ANY_CACHE 0x0b /* Any cache */ #define PERF_MEM_LVLNUM_LFB 0x0c /* LFB */ -- cgit v1.2.3 From 2d87d455ead2cbdee7e60463cddc5bff3f98c912 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 27 Oct 2022 16:57:09 +0800 Subject: blk-mq: don't add non-pt request with ->end_io to batch dm-rq implements ->end_io callback for request issued to underlying queue, and it isn't passthrough request. Commit ab3e1d3bbab9 ("block: allow end_io based requests in the completion batch handling") doesn't clear rq->bio and rq->__data_len for request with ->end_io in blk_mq_end_request_batch(), and this way is actually dangerous, but so far it is only for nvme passthrough request. dm-rq needs to clean up remained bios in case of partial completion, and req->bio is required, then use-after-free is triggered, so the underlying clone request can't be completed in blk_mq_end_request_batch. Fix panic by not adding such request into batch list, and the issue can be triggered simply by exposing nvme pci to dm-mpath simply. Fixes: ab3e1d3bbab9 ("block: allow end_io based requests in the completion batch handling") Cc: dm-devel@redhat.com Cc: Mike Snitzer Reported-by: Changhui Zhong Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20221027085709.513175-1-ming.lei@redhat.com Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index ba18e9bdb799..d6119c5d1069 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -853,7 +853,8 @@ static inline bool blk_mq_add_to_batch(struct request *req, struct io_comp_batch *iob, int ioerror, void (*complete)(struct io_comp_batch *)) { - if (!iob || (req->rq_flags & RQF_ELV) || ioerror) + if (!iob || (req->rq_flags & RQF_ELV) || ioerror || + (req->end_io && !blk_rq_is_passthrough(req))) return false; if (!iob->complete) -- cgit v1.2.3 From bacd22df95147ed673bec4692ab2d4d585935241 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Wed, 26 Oct 2022 14:51:45 +0100 Subject: net/mlx5: Fix possible use-after-free in async command interface mlx5_cmd_cleanup_async_ctx should return only after all its callback handlers were completed. Before this patch, the below race between mlx5_cmd_cleanup_async_ctx and mlx5_cmd_exec_cb_handler was possible and lead to a use-after-free: 1. mlx5_cmd_cleanup_async_ctx is called while num_inflight is 2 (i.e. elevated by 1, a single inflight callback). 2. mlx5_cmd_cleanup_async_ctx decreases num_inflight to 1. 3. mlx5_cmd_exec_cb_handler is called, decreases num_inflight to 0 and is about to call wake_up(). 4. mlx5_cmd_cleanup_async_ctx calls wait_event, which returns immediately as the condition (num_inflight == 0) holds. 5. mlx5_cmd_cleanup_async_ctx returns. 6. The caller of mlx5_cmd_cleanup_async_ctx frees the mlx5_async_ctx object. 7. mlx5_cmd_exec_cb_handler goes on and calls wake_up() on the freed object. Fix it by syncing using a completion object. Mark it completed when num_inflight reaches 0. Trace: BUG: KASAN: use-after-free in do_raw_spin_lock+0x23d/0x270 Read of size 4 at addr ffff888139cd12f4 by task swapper/5/0 CPU: 5 PID: 0 Comm: swapper/5 Not tainted 6.0.0-rc3_for_upstream_debug_2022_08_30_13_10 #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 Call Trace: dump_stack_lvl+0x57/0x7d print_report.cold+0x2d5/0x684 ? do_raw_spin_lock+0x23d/0x270 kasan_report+0xb1/0x1a0 ? do_raw_spin_lock+0x23d/0x270 do_raw_spin_lock+0x23d/0x270 ? rwlock_bug.part.0+0x90/0x90 ? __delete_object+0xb8/0x100 ? lock_downgrade+0x6e0/0x6e0 _raw_spin_lock_irqsave+0x43/0x60 ? __wake_up_common_lock+0xb9/0x140 __wake_up_common_lock+0xb9/0x140 ? __wake_up_common+0x650/0x650 ? destroy_tis_callback+0x53/0x70 [mlx5_core] ? kasan_set_track+0x21/0x30 ? destroy_tis_callback+0x53/0x70 [mlx5_core] ? kfree+0x1ba/0x520 ? do_raw_spin_unlock+0x54/0x220 mlx5_cmd_exec_cb_handler+0x136/0x1a0 [mlx5_core] ? mlx5_cmd_cleanup_async_ctx+0x220/0x220 [mlx5_core] ? mlx5_cmd_cleanup_async_ctx+0x220/0x220 [mlx5_core] mlx5_cmd_comp_handler+0x65a/0x12b0 [mlx5_core] ? dump_command+0xcc0/0xcc0 [mlx5_core] ? lockdep_hardirqs_on_prepare+0x400/0x400 ? cmd_comp_notifier+0x7e/0xb0 [mlx5_core] cmd_comp_notifier+0x7e/0xb0 [mlx5_core] atomic_notifier_call_chain+0xd7/0x1d0 mlx5_eq_async_int+0x3ce/0xa20 [mlx5_core] atomic_notifier_call_chain+0xd7/0x1d0 ? irq_release+0x140/0x140 [mlx5_core] irq_int_handler+0x19/0x30 [mlx5_core] __handle_irq_event_percpu+0x1f2/0x620 handle_irq_event+0xb2/0x1d0 handle_edge_irq+0x21e/0xb00 __common_interrupt+0x79/0x1a0 common_interrupt+0x78/0xa0 asm_common_interrupt+0x22/0x40 RIP: 0010:default_idle+0x42/0x60 Code: c1 83 e0 07 48 c1 e9 03 83 c0 03 0f b6 14 11 38 d0 7c 04 84 d2 75 14 8b 05 eb 47 22 02 85 c0 7e 07 0f 00 2d e0 9f 48 00 fb f4 48 c7 c7 80 08 7f 85 e8 d1 d3 3e fe eb de 66 66 2e 0f 1f 84 00 RSP: 0018:ffff888100dbfdf0 EFLAGS: 00000242 RAX: 0000000000000001 RBX: ffffffff84ecbd48 RCX: 1ffffffff0afe110 RDX: 0000000000000004 RSI: 0000000000000000 RDI: ffffffff835cc9bc RBP: 0000000000000005 R08: 0000000000000001 R09: ffff88881dec4ac3 R10: ffffed1103bd8958 R11: 0000017d0ca571c9 R12: 0000000000000005 R13: ffffffff84f024e0 R14: 0000000000000000 R15: dffffc0000000000 ? default_idle_call+0xcc/0x450 default_idle_call+0xec/0x450 do_idle+0x394/0x450 ? arch_cpu_idle_exit+0x40/0x40 ? do_idle+0x17/0x450 cpu_startup_entry+0x19/0x20 start_secondary+0x221/0x2b0 ? set_cpu_sibling_map+0x2070/0x2070 secondary_startup_64_no_verify+0xcd/0xdb Allocated by task 49502: kasan_save_stack+0x1e/0x40 __kasan_kmalloc+0x81/0xa0 kvmalloc_node+0x48/0xe0 mlx5e_bulk_async_init+0x35/0x110 [mlx5_core] mlx5e_tls_priv_tx_list_cleanup+0x84/0x3e0 [mlx5_core] mlx5e_ktls_cleanup_tx+0x38f/0x760 [mlx5_core] mlx5e_cleanup_nic_tx+0xa7/0x100 [mlx5_core] mlx5e_detach_netdev+0x1ca/0x2b0 [mlx5_core] mlx5e_suspend+0xdb/0x140 [mlx5_core] mlx5e_remove+0x89/0x190 [mlx5_core] auxiliary_bus_remove+0x52/0x70 device_release_driver_internal+0x40f/0x650 driver_detach+0xc1/0x180 bus_remove_driver+0x125/0x2f0 auxiliary_driver_unregister+0x16/0x50 mlx5e_cleanup+0x26/0x30 [mlx5_core] cleanup+0xc/0x4e [mlx5_core] __x64_sys_delete_module+0x2b5/0x450 do_syscall_64+0x3d/0x90 entry_SYSCALL_64_after_hwframe+0x46/0xb0 Freed by task 49502: kasan_save_stack+0x1e/0x40 kasan_set_track+0x21/0x30 kasan_set_free_info+0x20/0x30 ____kasan_slab_free+0x11d/0x1b0 kfree+0x1ba/0x520 mlx5e_tls_priv_tx_list_cleanup+0x2e7/0x3e0 [mlx5_core] mlx5e_ktls_cleanup_tx+0x38f/0x760 [mlx5_core] mlx5e_cleanup_nic_tx+0xa7/0x100 [mlx5_core] mlx5e_detach_netdev+0x1ca/0x2b0 [mlx5_core] mlx5e_suspend+0xdb/0x140 [mlx5_core] mlx5e_remove+0x89/0x190 [mlx5_core] auxiliary_bus_remove+0x52/0x70 device_release_driver_internal+0x40f/0x650 driver_detach+0xc1/0x180 bus_remove_driver+0x125/0x2f0 auxiliary_driver_unregister+0x16/0x50 mlx5e_cleanup+0x26/0x30 [mlx5_core] cleanup+0xc/0x4e [mlx5_core] __x64_sys_delete_module+0x2b5/0x450 do_syscall_64+0x3d/0x90 entry_SYSCALL_64_after_hwframe+0x46/0xb0 Fixes: e355477ed9e4 ("net/mlx5: Make mlx5_cmd_exec_cb() a safe API") Signed-off-by: Tariq Toukan Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed Link: https://lore.kernel.org/r/20221026135153.154807-8-saeed@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 10 +++++----- include/linux/mlx5/driver.h | 2 +- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 0377392848d9..46ba4c2faad2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -2004,7 +2004,7 @@ void mlx5_cmd_init_async_ctx(struct mlx5_core_dev *dev, ctx->dev = dev; /* Starts at 1 to avoid doing wake_up if we are not cleaning up */ atomic_set(&ctx->num_inflight, 1); - init_waitqueue_head(&ctx->wait); + init_completion(&ctx->inflight_done); } EXPORT_SYMBOL(mlx5_cmd_init_async_ctx); @@ -2018,8 +2018,8 @@ EXPORT_SYMBOL(mlx5_cmd_init_async_ctx); */ void mlx5_cmd_cleanup_async_ctx(struct mlx5_async_ctx *ctx) { - atomic_dec(&ctx->num_inflight); - wait_event(ctx->wait, atomic_read(&ctx->num_inflight) == 0); + if (!atomic_dec_and_test(&ctx->num_inflight)) + wait_for_completion(&ctx->inflight_done); } EXPORT_SYMBOL(mlx5_cmd_cleanup_async_ctx); @@ -2032,7 +2032,7 @@ static void mlx5_cmd_exec_cb_handler(int status, void *_work) status = cmd_status_err(ctx->dev, status, work->opcode, work->out); work->user_callback(status, work); if (atomic_dec_and_test(&ctx->num_inflight)) - wake_up(&ctx->wait); + complete(&ctx->inflight_done); } int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size, @@ -2050,7 +2050,7 @@ int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size, ret = cmd_exec(ctx->dev, in, in_size, out, out_size, mlx5_cmd_exec_cb_handler, work, false); if (ret && atomic_dec_and_test(&ctx->num_inflight)) - wake_up(&ctx->wait); + complete(&ctx->inflight_done); return ret; } diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index a12929bc31b2..af2ceb4160bc 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -970,7 +970,7 @@ void mlx5_cmd_allowed_opcode(struct mlx5_core_dev *dev, u16 opcode); struct mlx5_async_ctx { struct mlx5_core_dev *dev; atomic_t num_inflight; - struct wait_queue_head wait; + struct completion inflight_done; }; struct mlx5_async_work; -- cgit v1.2.3 From 67eae54bc227b30dedcce9db68b063ba1adb7838 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Mon, 24 Oct 2022 15:33:35 -0400 Subject: mm/uffd: fix vma check on userfault for wp We used to have a report that pte-marker code can be reached even when uffd-wp is not compiled in for file memories, here: https://lore.kernel.org/all/YzeR+R6b4bwBlBHh@x1n/T/#u I just got time to revisit this and found that the root cause is we simply messed up with the vma check, so that for !PTE_MARKER_UFFD_WP system, we will allow UFFDIO_REGISTER of MINOR & WP upon shmem as the check was wrong: if (vm_flags & VM_UFFD_MINOR) return is_vm_hugetlb_page(vma) || vma_is_shmem(vma); Where we'll allow anything to pass on shmem as long as minor mode is requested. Axel did it right when introducing minor mode but I messed it up in b1f9e876862d when moving code around. Fix it. Link: https://lkml.kernel.org/r/20221024193336.1233616-1-peterx@redhat.com Link: https://lkml.kernel.org/r/20221024193336.1233616-2-peterx@redhat.com Fixes: b1f9e876862d ("mm/uffd: enable write protection for shmem & hugetlbfs") Signed-off-by: Peter Xu Cc: Axel Rasmussen Cc: Andrea Arcangeli Cc: Nadav Amit Cc: Signed-off-by: Andrew Morton --- include/linux/userfaultfd_k.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index f07e6998bb68..9df0b9a762cc 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -146,9 +146,9 @@ static inline bool userfaultfd_armed(struct vm_area_struct *vma) static inline bool vma_can_userfault(struct vm_area_struct *vma, unsigned long vm_flags) { - if (vm_flags & VM_UFFD_MINOR) - return is_vm_hugetlb_page(vma) || vma_is_shmem(vma); - + if ((vm_flags & VM_UFFD_MINOR) && + (!is_vm_hugetlb_page(vma) && !vma_is_shmem(vma))) + return false; #ifndef CONFIG_PTE_MARKER_UFFD_WP /* * If user requested uffd-wp but not enabled pte markers for -- cgit v1.2.3 From 78a498c3a227f2ac773a8234b2ce092a4403f2c3 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Mon, 24 Oct 2022 23:21:44 +0200 Subject: x86: fortify: kmsan: fix KMSAN fortify builds Ensure that KMSAN builds replace memset/memcpy/memmove calls with the respective __msan_XXX functions, and that none of the macros are redefined twice. This should allow building kernel with both CONFIG_KMSAN and CONFIG_FORTIFY_SOURCE. Link: https://lkml.kernel.org/r/20221024212144.2852069-5-glider@google.com Link: https://github.com/google/kmsan/issues/89 Signed-off-by: Alexander Potapenko Reported-by: Tamas K Lengyel Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Kees Cook Signed-off-by: Andrew Morton --- arch/x86/include/asm/string_64.h | 11 +++++++---- include/linux/fortify-string.h | 17 +++++++++++++++-- include/linux/kmsan_string.h | 21 +++++++++++++++++++++ mm/kmsan/instrumentation.c | 1 + 4 files changed, 44 insertions(+), 6 deletions(-) create mode 100644 include/linux/kmsan_string.h (limited to 'include') diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h index 3b87d889b6e1..888731ccf1f6 100644 --- a/arch/x86/include/asm/string_64.h +++ b/arch/x86/include/asm/string_64.h @@ -10,10 +10,13 @@ /* Even with __builtin_ the compiler may decide to use the out of line function. */ +#if defined(__SANITIZE_MEMORY__) && defined(__NO_FORTIFY) +#include +#endif + #define __HAVE_ARCH_MEMCPY 1 -#if defined(__SANITIZE_MEMORY__) +#if defined(__SANITIZE_MEMORY__) && defined(__NO_FORTIFY) #undef memcpy -void *__msan_memcpy(void *dst, const void *src, size_t size); #define memcpy __msan_memcpy #else extern void *memcpy(void *to, const void *from, size_t len); @@ -21,7 +24,7 @@ extern void *memcpy(void *to, const void *from, size_t len); extern void *__memcpy(void *to, const void *from, size_t len); #define __HAVE_ARCH_MEMSET -#if defined(__SANITIZE_MEMORY__) +#if defined(__SANITIZE_MEMORY__) && defined(__NO_FORTIFY) extern void *__msan_memset(void *s, int c, size_t n); #undef memset #define memset __msan_memset @@ -67,7 +70,7 @@ static inline void *memset64(uint64_t *s, uint64_t v, size_t n) } #define __HAVE_ARCH_MEMMOVE -#if defined(__SANITIZE_MEMORY__) +#if defined(__SANITIZE_MEMORY__) && defined(__NO_FORTIFY) #undef memmove void *__msan_memmove(void *dest, const void *src, size_t len); #define memmove __msan_memmove diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index 4029fe368a4f..18a31b125f9d 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -43,11 +43,24 @@ extern __kernel_size_t __underlying_strlen(const char *p) __RENAME(strlen); extern char *__underlying_strncat(char *p, const char *q, __kernel_size_t count) __RENAME(strncat); extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) __RENAME(strncpy); #else -#define __underlying_memchr __builtin_memchr -#define __underlying_memcmp __builtin_memcmp + +#if defined(__SANITIZE_MEMORY__) +/* + * For KMSAN builds all memcpy/memset/memmove calls should be replaced by the + * corresponding __msan_XXX functions. + */ +#include +#define __underlying_memcpy __msan_memcpy +#define __underlying_memmove __msan_memmove +#define __underlying_memset __msan_memset +#else #define __underlying_memcpy __builtin_memcpy #define __underlying_memmove __builtin_memmove #define __underlying_memset __builtin_memset +#endif + +#define __underlying_memchr __builtin_memchr +#define __underlying_memcmp __builtin_memcmp #define __underlying_strcat __builtin_strcat #define __underlying_strcpy __builtin_strcpy #define __underlying_strlen __builtin_strlen diff --git a/include/linux/kmsan_string.h b/include/linux/kmsan_string.h new file mode 100644 index 000000000000..7287da6f52ef --- /dev/null +++ b/include/linux/kmsan_string.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * KMSAN string functions API used in other headers. + * + * Copyright (C) 2022 Google LLC + * Author: Alexander Potapenko + * + */ +#ifndef _LINUX_KMSAN_STRING_H +#define _LINUX_KMSAN_STRING_H + +/* + * KMSAN overrides the default memcpy/memset/memmove implementations in the + * kernel, which requires having __msan_XXX function prototypes in several other + * headers. Keep them in one place instead of open-coding. + */ +void *__msan_memcpy(void *dst, const void *src, size_t size); +void *__msan_memset(void *s, int c, size_t n); +void *__msan_memmove(void *dest, const void *src, size_t len); + +#endif /* _LINUX_KMSAN_STRING_H */ diff --git a/mm/kmsan/instrumentation.c b/mm/kmsan/instrumentation.c index 280d15413268..271f135f97a1 100644 --- a/mm/kmsan/instrumentation.c +++ b/mm/kmsan/instrumentation.c @@ -14,6 +14,7 @@ #include "kmsan.h" #include +#include #include #include -- cgit v1.2.3 From fd325cd648f15eb9a8b32a68de3bafc72bcfe753 Mon Sep 17 00:00:00 2001 From: Long Li Date: Thu, 3 Nov 2022 12:16:25 -0700 Subject: net: mana: Move header files to a common location In preparation to add MANA RDMA driver, move all the required header files to a common location for use by both Ethernet and RDMA drivers. Reviewed-by: Dexuan Cui Signed-off-by: Long Li Link: https://lore.kernel.org/r/1667502990-2559-8-git-send-email-longli@linuxonhyperv.com Acked-by: Haiyang Zhang Signed-off-by: Leon Romanovsky --- MAINTAINERS | 1 + drivers/net/ethernet/microsoft/mana/gdma.h | 689 --------------------- drivers/net/ethernet/microsoft/mana/gdma_main.c | 2 +- drivers/net/ethernet/microsoft/mana/hw_channel.c | 4 +- drivers/net/ethernet/microsoft/mana/hw_channel.h | 195 ------ drivers/net/ethernet/microsoft/mana/mana.h | 650 ------------------- .../net/ethernet/microsoft/mana/mana_auxiliary.h | 10 - drivers/net/ethernet/microsoft/mana/mana_bpf.c | 2 +- drivers/net/ethernet/microsoft/mana/mana_en.c | 4 +- drivers/net/ethernet/microsoft/mana/mana_ethtool.c | 2 +- drivers/net/ethernet/microsoft/mana/shm_channel.c | 2 +- drivers/net/ethernet/microsoft/mana/shm_channel.h | 21 - include/net/mana/gdma.h | 689 +++++++++++++++++++++ include/net/mana/hw_channel.h | 195 ++++++ include/net/mana/mana.h | 650 +++++++++++++++++++ include/net/mana/mana_auxiliary.h | 10 + include/net/mana/shm_channel.h | 21 + 17 files changed, 1574 insertions(+), 1573 deletions(-) delete mode 100644 drivers/net/ethernet/microsoft/mana/gdma.h delete mode 100644 drivers/net/ethernet/microsoft/mana/hw_channel.h delete mode 100644 drivers/net/ethernet/microsoft/mana/mana.h delete mode 100644 drivers/net/ethernet/microsoft/mana/mana_auxiliary.h delete mode 100644 drivers/net/ethernet/microsoft/mana/shm_channel.h create mode 100644 include/net/mana/gdma.h create mode 100644 include/net/mana/hw_channel.h create mode 100644 include/net/mana/mana.h create mode 100644 include/net/mana/mana_auxiliary.h create mode 100644 include/net/mana/shm_channel.h (limited to 'include') diff --git a/MAINTAINERS b/MAINTAINERS index 379945f82a64..441a65d41eb4 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9541,6 +9541,7 @@ F: include/asm-generic/hyperv-tlfs.h F: include/asm-generic/mshyperv.h F: include/clocksource/hyperv_timer.h F: include/linux/hyperv.h +F: include/net/mana F: include/uapi/linux/hyperv.h F: net/vmw_vsock/hyperv_transport.c F: tools/hv/ diff --git a/drivers/net/ethernet/microsoft/mana/gdma.h b/drivers/net/ethernet/microsoft/mana/gdma.h deleted file mode 100644 index 72eaec2470c0..000000000000 --- a/drivers/net/ethernet/microsoft/mana/gdma.h +++ /dev/null @@ -1,689 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ -/* Copyright (c) 2021, Microsoft Corporation. */ - -#ifndef _GDMA_H -#define _GDMA_H - -#include -#include - -#include "shm_channel.h" - -/* Structures labeled with "HW DATA" are exchanged with the hardware. All of - * them are naturally aligned and hence don't need __packed. - */ - -enum gdma_request_type { - GDMA_VERIFY_VF_DRIVER_VERSION = 1, - GDMA_QUERY_MAX_RESOURCES = 2, - GDMA_LIST_DEVICES = 3, - GDMA_REGISTER_DEVICE = 4, - GDMA_DEREGISTER_DEVICE = 5, - GDMA_GENERATE_TEST_EQE = 10, - GDMA_CREATE_QUEUE = 12, - GDMA_DISABLE_QUEUE = 13, - GDMA_CREATE_DMA_REGION = 25, - GDMA_DMA_REGION_ADD_PAGES = 26, - GDMA_DESTROY_DMA_REGION = 27, -}; - -enum gdma_queue_type { - GDMA_INVALID_QUEUE, - GDMA_SQ, - GDMA_RQ, - GDMA_CQ, - GDMA_EQ, -}; - -enum gdma_work_request_flags { - GDMA_WR_NONE = 0, - GDMA_WR_OOB_IN_SGL = BIT(0), - GDMA_WR_PAD_BY_SGE0 = BIT(1), -}; - -enum gdma_eqe_type { - GDMA_EQE_COMPLETION = 3, - GDMA_EQE_TEST_EVENT = 64, - GDMA_EQE_HWC_INIT_EQ_ID_DB = 129, - GDMA_EQE_HWC_INIT_DATA = 130, - GDMA_EQE_HWC_INIT_DONE = 131, -}; - -enum { - GDMA_DEVICE_NONE = 0, - GDMA_DEVICE_HWC = 1, - GDMA_DEVICE_MANA = 2, -}; - -struct gdma_resource { - /* Protect the bitmap */ - spinlock_t lock; - - /* The bitmap size in bits. */ - u32 size; - - /* The bitmap tracks the resources. */ - unsigned long *map; -}; - -union gdma_doorbell_entry { - u64 as_uint64; - - struct { - u64 id : 24; - u64 reserved : 8; - u64 tail_ptr : 31; - u64 arm : 1; - } cq; - - struct { - u64 id : 24; - u64 wqe_cnt : 8; - u64 tail_ptr : 32; - } rq; - - struct { - u64 id : 24; - u64 reserved : 8; - u64 tail_ptr : 32; - } sq; - - struct { - u64 id : 16; - u64 reserved : 16; - u64 tail_ptr : 31; - u64 arm : 1; - } eq; -}; /* HW DATA */ - -struct gdma_msg_hdr { - u32 hdr_type; - u32 msg_type; - u16 msg_version; - u16 hwc_msg_id; - u32 msg_size; -}; /* HW DATA */ - -struct gdma_dev_id { - union { - struct { - u16 type; - u16 instance; - }; - - u32 as_uint32; - }; -}; /* HW DATA */ - -struct gdma_req_hdr { - struct gdma_msg_hdr req; - struct gdma_msg_hdr resp; /* The expected response */ - struct gdma_dev_id dev_id; - u32 activity_id; -}; /* HW DATA */ - -struct gdma_resp_hdr { - struct gdma_msg_hdr response; - struct gdma_dev_id dev_id; - u32 activity_id; - u32 status; - u32 reserved; -}; /* HW DATA */ - -struct gdma_general_req { - struct gdma_req_hdr hdr; -}; /* HW DATA */ - -#define GDMA_MESSAGE_V1 1 - -struct gdma_general_resp { - struct gdma_resp_hdr hdr; -}; /* HW DATA */ - -#define GDMA_STANDARD_HEADER_TYPE 0 - -static inline void mana_gd_init_req_hdr(struct gdma_req_hdr *hdr, u32 code, - u32 req_size, u32 resp_size) -{ - hdr->req.hdr_type = GDMA_STANDARD_HEADER_TYPE; - hdr->req.msg_type = code; - hdr->req.msg_version = GDMA_MESSAGE_V1; - hdr->req.msg_size = req_size; - - hdr->resp.hdr_type = GDMA_STANDARD_HEADER_TYPE; - hdr->resp.msg_type = code; - hdr->resp.msg_version = GDMA_MESSAGE_V1; - hdr->resp.msg_size = resp_size; -} - -/* The 16-byte struct is part of the GDMA work queue entry (WQE). */ -struct gdma_sge { - u64 address; - u32 mem_key; - u32 size; -}; /* HW DATA */ - -struct gdma_wqe_request { - struct gdma_sge *sgl; - u32 num_sge; - - u32 inline_oob_size; - const void *inline_oob_data; - - u32 flags; - u32 client_data_unit; -}; - -enum gdma_page_type { - GDMA_PAGE_TYPE_4K, -}; - -#define GDMA_INVALID_DMA_REGION 0 - -struct gdma_mem_info { - struct device *dev; - - dma_addr_t dma_handle; - void *virt_addr; - u64 length; - - /* Allocated by the PF driver */ - u64 gdma_region; -}; - -#define REGISTER_ATB_MST_MKEY_LOWER_SIZE 8 - -struct gdma_dev { - struct gdma_context *gdma_context; - - struct gdma_dev_id dev_id; - - u32 pdid; - u32 doorbell; - u32 gpa_mkey; - - /* GDMA driver specific pointer */ - void *driver_data; - - struct auxiliary_device *adev; -}; - -#define MINIMUM_SUPPORTED_PAGE_SIZE PAGE_SIZE - -#define GDMA_CQE_SIZE 64 -#define GDMA_EQE_SIZE 16 -#define GDMA_MAX_SQE_SIZE 512 -#define GDMA_MAX_RQE_SIZE 256 - -#define GDMA_COMP_DATA_SIZE 0x3C - -#define GDMA_EVENT_DATA_SIZE 0xC - -/* The WQE size must be a multiple of the Basic Unit, which is 32 bytes. */ -#define GDMA_WQE_BU_SIZE 32 - -#define INVALID_PDID UINT_MAX -#define INVALID_DOORBELL UINT_MAX -#define INVALID_MEM_KEY UINT_MAX -#define INVALID_QUEUE_ID UINT_MAX -#define INVALID_PCI_MSIX_INDEX UINT_MAX - -struct gdma_comp { - u32 cqe_data[GDMA_COMP_DATA_SIZE / 4]; - u32 wq_num; - bool is_sq; -}; - -struct gdma_event { - u32 details[GDMA_EVENT_DATA_SIZE / 4]; - u8 type; -}; - -struct gdma_queue; - -struct mana_eq { - struct gdma_queue *eq; -}; - -typedef void gdma_eq_callback(void *context, struct gdma_queue *q, - struct gdma_event *e); - -typedef void gdma_cq_callback(void *context, struct gdma_queue *q); - -/* The 'head' is the producer index. For SQ/RQ, when the driver posts a WQE - * (Note: the WQE size must be a multiple of the 32-byte Basic Unit), the - * driver increases the 'head' in BUs rather than in bytes, and notifies - * the HW of the updated head. For EQ/CQ, the driver uses the 'head' to track - * the HW head, and increases the 'head' by 1 for every processed EQE/CQE. - * - * The 'tail' is the consumer index for SQ/RQ. After the CQE of the SQ/RQ is - * processed, the driver increases the 'tail' to indicate that WQEs have - * been consumed by the HW, so the driver can post new WQEs into the SQ/RQ. - * - * The driver doesn't use the 'tail' for EQ/CQ, because the driver ensures - * that the EQ/CQ is big enough so they can't overflow, and the driver uses - * the owner bits mechanism to detect if the queue has become empty. - */ -struct gdma_queue { - struct gdma_dev *gdma_dev; - - enum gdma_queue_type type; - u32 id; - - struct gdma_mem_info mem_info; - - void *queue_mem_ptr; - u32 queue_size; - - bool monitor_avl_buf; - - u32 head; - u32 tail; - - /* Extra fields specific to EQ/CQ. */ - union { - struct { - bool disable_needed; - - gdma_eq_callback *callback; - void *context; - - unsigned int msix_index; - - u32 log2_throttle_limit; - } eq; - - struct { - gdma_cq_callback *callback; - void *context; - - struct gdma_queue *parent; /* For CQ/EQ relationship */ - } cq; - }; -}; - -struct gdma_queue_spec { - enum gdma_queue_type type; - bool monitor_avl_buf; - unsigned int queue_size; - - /* Extra fields specific to EQ/CQ. */ - union { - struct { - gdma_eq_callback *callback; - void *context; - - unsigned long log2_throttle_limit; - } eq; - - struct { - gdma_cq_callback *callback; - void *context; - - struct gdma_queue *parent_eq; - - } cq; - }; -}; - -struct gdma_irq_context { - void (*handler)(void *arg); - void *arg; -}; - -struct gdma_context { - struct device *dev; - - /* Per-vPort max number of queues */ - unsigned int max_num_queues; - unsigned int max_num_msix; - unsigned int num_msix_usable; - struct gdma_resource msix_resource; - struct gdma_irq_context *irq_contexts; - - /* This maps a CQ index to the queue structure. */ - unsigned int max_num_cqs; - struct gdma_queue **cq_table; - - /* Protect eq_test_event and test_event_eq_id */ - struct mutex eq_test_event_mutex; - struct completion eq_test_event; - u32 test_event_eq_id; - - bool is_pf; - phys_addr_t bar0_pa; - void __iomem *bar0_va; - void __iomem *shm_base; - void __iomem *db_page_base; - phys_addr_t phys_db_page_base; - u32 db_page_size; - - /* Shared memory chanenl (used to bootstrap HWC) */ - struct shm_channel shm_channel; - - /* Hardware communication channel (HWC) */ - struct gdma_dev hwc; - - /* Azure network adapter */ - struct gdma_dev mana; -}; - -#define MAX_NUM_GDMA_DEVICES 4 - -static inline bool mana_gd_is_mana(struct gdma_dev *gd) -{ - return gd->dev_id.type == GDMA_DEVICE_MANA; -} - -static inline bool mana_gd_is_hwc(struct gdma_dev *gd) -{ - return gd->dev_id.type == GDMA_DEVICE_HWC; -} - -u8 *mana_gd_get_wqe_ptr(const struct gdma_queue *wq, u32 wqe_offset); -u32 mana_gd_wq_avail_space(struct gdma_queue *wq); - -int mana_gd_test_eq(struct gdma_context *gc, struct gdma_queue *eq); - -int mana_gd_create_hwc_queue(struct gdma_dev *gd, - const struct gdma_queue_spec *spec, - struct gdma_queue **queue_ptr); - -int mana_gd_create_mana_eq(struct gdma_dev *gd, - const struct gdma_queue_spec *spec, - struct gdma_queue **queue_ptr); - -int mana_gd_create_mana_wq_cq(struct gdma_dev *gd, - const struct gdma_queue_spec *spec, - struct gdma_queue **queue_ptr); - -void mana_gd_destroy_queue(struct gdma_context *gc, struct gdma_queue *queue); - -int mana_gd_poll_cq(struct gdma_queue *cq, struct gdma_comp *comp, int num_cqe); - -void mana_gd_ring_cq(struct gdma_queue *cq, u8 arm_bit); - -struct gdma_wqe { - u32 reserved :24; - u32 last_vbytes :8; - - union { - u32 flags; - - struct { - u32 num_sge :8; - u32 inline_oob_size_div4:3; - u32 client_oob_in_sgl :1; - u32 reserved1 :4; - u32 client_data_unit :14; - u32 reserved2 :2; - }; - }; -}; /* HW DATA */ - -#define INLINE_OOB_SMALL_SIZE 8 -#define INLINE_OOB_LARGE_SIZE 24 - -#define MAX_TX_WQE_SIZE 512 -#define MAX_RX_WQE_SIZE 256 - -struct gdma_cqe { - u32 cqe_data[GDMA_COMP_DATA_SIZE / 4]; - - union { - u32 as_uint32; - - struct { - u32 wq_num : 24; - u32 is_sq : 1; - u32 reserved : 4; - u32 owner_bits : 3; - }; - } cqe_info; -}; /* HW DATA */ - -#define GDMA_CQE_OWNER_BITS 3 - -#define GDMA_CQE_OWNER_MASK ((1 << GDMA_CQE_OWNER_BITS) - 1) - -#define SET_ARM_BIT 1 - -#define GDMA_EQE_OWNER_BITS 3 - -union gdma_eqe_info { - u32 as_uint32; - - struct { - u32 type : 8; - u32 reserved1 : 8; - u32 client_id : 2; - u32 reserved2 : 11; - u32 owner_bits : 3; - }; -}; /* HW DATA */ - -#define GDMA_EQE_OWNER_MASK ((1 << GDMA_EQE_OWNER_BITS) - 1) -#define INITIALIZED_OWNER_BIT(log2_num_entries) (1UL << (log2_num_entries)) - -struct gdma_eqe { - u32 details[GDMA_EVENT_DATA_SIZE / 4]; - u32 eqe_info; -}; /* HW DATA */ - -#define GDMA_REG_DB_PAGE_OFFSET 8 -#define GDMA_REG_DB_PAGE_SIZE 0x10 -#define GDMA_REG_SHM_OFFSET 0x18 - -#define GDMA_PF_REG_DB_PAGE_SIZE 0xD0 -#define GDMA_PF_REG_DB_PAGE_OFF 0xC8 -#define GDMA_PF_REG_SHM_OFF 0x70 - -#define GDMA_SRIOV_REG_CFG_BASE_OFF 0x108 - -#define MANA_PF_DEVICE_ID 0x00B9 -#define MANA_VF_DEVICE_ID 0x00BA - -struct gdma_posted_wqe_info { - u32 wqe_size_in_bu; -}; - -/* GDMA_GENERATE_TEST_EQE */ -struct gdma_generate_test_event_req { - struct gdma_req_hdr hdr; - u32 queue_index; -}; /* HW DATA */ - -/* GDMA_VERIFY_VF_DRIVER_VERSION */ -enum { - GDMA_PROTOCOL_V1 = 1, - GDMA_PROTOCOL_FIRST = GDMA_PROTOCOL_V1, - GDMA_PROTOCOL_LAST = GDMA_PROTOCOL_V1, -}; - -#define GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT BIT(0) - -#define GDMA_DRV_CAP_FLAGS1 GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT - -#define GDMA_DRV_CAP_FLAGS2 0 - -#define GDMA_DRV_CAP_FLAGS3 0 - -#define GDMA_DRV_CAP_FLAGS4 0 - -struct gdma_verify_ver_req { - struct gdma_req_hdr hdr; - - /* Mandatory fields required for protocol establishment */ - u64 protocol_ver_min; - u64 protocol_ver_max; - - /* Gdma Driver Capability Flags */ - u64 gd_drv_cap_flags1; - u64 gd_drv_cap_flags2; - u64 gd_drv_cap_flags3; - u64 gd_drv_cap_flags4; - - /* Advisory fields */ - u64 drv_ver; - u32 os_type; /* Linux = 0x10; Windows = 0x20; Other = 0x30 */ - u32 reserved; - u32 os_ver_major; - u32 os_ver_minor; - u32 os_ver_build; - u32 os_ver_platform; - u64 reserved_2; - u8 os_ver_str1[128]; - u8 os_ver_str2[128]; - u8 os_ver_str3[128]; - u8 os_ver_str4[128]; -}; /* HW DATA */ - -struct gdma_verify_ver_resp { - struct gdma_resp_hdr hdr; - u64 gdma_protocol_ver; - u64 pf_cap_flags1; - u64 pf_cap_flags2; - u64 pf_cap_flags3; - u64 pf_cap_flags4; -}; /* HW DATA */ - -/* GDMA_QUERY_MAX_RESOURCES */ -struct gdma_query_max_resources_resp { - struct gdma_resp_hdr hdr; - u32 status; - u32 max_sq; - u32 max_rq; - u32 max_cq; - u32 max_eq; - u32 max_db; - u32 max_mst; - u32 max_cq_mod_ctx; - u32 max_mod_cq; - u32 max_msix; -}; /* HW DATA */ - -/* GDMA_LIST_DEVICES */ -struct gdma_list_devices_resp { - struct gdma_resp_hdr hdr; - u32 num_of_devs; - u32 reserved; - struct gdma_dev_id devs[64]; -}; /* HW DATA */ - -/* GDMA_REGISTER_DEVICE */ -struct gdma_register_device_resp { - struct gdma_resp_hdr hdr; - u32 pdid; - u32 gpa_mkey; - u32 db_id; -}; /* HW DATA */ - -/* GDMA_CREATE_QUEUE */ -struct gdma_create_queue_req { - struct gdma_req_hdr hdr; - u32 type; - u32 reserved1; - u32 pdid; - u32 doolbell_id; - u64 gdma_region; - u32 reserved2; - u32 queue_size; - u32 log2_throttle_limit; - u32 eq_pci_msix_index; - u32 cq_mod_ctx_id; - u32 cq_parent_eq_id; - u8 rq_drop_on_overrun; - u8 rq_err_on_wqe_overflow; - u8 rq_chain_rec_wqes; - u8 sq_hw_db; - u32 reserved3; -}; /* HW DATA */ - -struct gdma_create_queue_resp { - struct gdma_resp_hdr hdr; - u32 queue_index; -}; /* HW DATA */ - -/* GDMA_DISABLE_QUEUE */ -struct gdma_disable_queue_req { - struct gdma_req_hdr hdr; - u32 type; - u32 queue_index; - u32 alloc_res_id_on_creation; -}; /* HW DATA */ - -/* GDMA_CREATE_DMA_REGION */ -struct gdma_create_dma_region_req { - struct gdma_req_hdr hdr; - - /* The total size of the DMA region */ - u64 length; - - /* The offset in the first page */ - u32 offset_in_page; - - /* enum gdma_page_type */ - u32 gdma_page_type; - - /* The total number of pages */ - u32 page_count; - - /* If page_addr_list_len is smaller than page_count, - * the remaining page addresses will be added via the - * message GDMA_DMA_REGION_ADD_PAGES. - */ - u32 page_addr_list_len; - u64 page_addr_list[]; -}; /* HW DATA */ - -struct gdma_create_dma_region_resp { - struct gdma_resp_hdr hdr; - u64 gdma_region; -}; /* HW DATA */ - -/* GDMA_DMA_REGION_ADD_PAGES */ -struct gdma_dma_region_add_pages_req { - struct gdma_req_hdr hdr; - - u64 gdma_region; - - u32 page_addr_list_len; - u32 reserved3; - - u64 page_addr_list[]; -}; /* HW DATA */ - -/* GDMA_DESTROY_DMA_REGION */ -struct gdma_destroy_dma_region_req { - struct gdma_req_hdr hdr; - - u64 gdma_region; -}; /* HW DATA */ - -int mana_gd_verify_vf_version(struct pci_dev *pdev); - -int mana_gd_register_device(struct gdma_dev *gd); -int mana_gd_deregister_device(struct gdma_dev *gd); - -int mana_gd_post_work_request(struct gdma_queue *wq, - const struct gdma_wqe_request *wqe_req, - struct gdma_posted_wqe_info *wqe_info); - -int mana_gd_post_and_ring(struct gdma_queue *queue, - const struct gdma_wqe_request *wqe, - struct gdma_posted_wqe_info *wqe_info); - -int mana_gd_alloc_res_map(u32 res_avail, struct gdma_resource *r); -void mana_gd_free_res_map(struct gdma_resource *r); - -void mana_gd_wq_ring_doorbell(struct gdma_context *gc, - struct gdma_queue *queue); - -int mana_gd_alloc_memory(struct gdma_context *gc, unsigned int length, - struct gdma_mem_info *gmi); - -void mana_gd_free_memory(struct gdma_mem_info *gmi); - -int mana_gd_send_request(struct gdma_context *gc, u32 req_len, const void *req, - u32 resp_len, void *resp); -#endif /* _GDMA_H */ diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index f0e22954d5c0..69795bc679e7 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -6,7 +6,7 @@ #include #include -#include "mana.h" +#include static u32 mana_gd_r32(struct gdma_context *g, u64 offset) { diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c index 543a5d5c304f..76829ab43d40 100644 --- a/drivers/net/ethernet/microsoft/mana/hw_channel.c +++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c @@ -1,8 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* Copyright (c) 2021, Microsoft Corporation. */ -#include "gdma.h" -#include "hw_channel.h" +#include +#include static int mana_hwc_get_msg_index(struct hw_channel_context *hwc, u16 *msg_id) { diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.h b/drivers/net/ethernet/microsoft/mana/hw_channel.h deleted file mode 100644 index 6a757a6e2732..000000000000 --- a/drivers/net/ethernet/microsoft/mana/hw_channel.h +++ /dev/null @@ -1,195 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ -/* Copyright (c) 2021, Microsoft Corporation. */ - -#ifndef _HW_CHANNEL_H -#define _HW_CHANNEL_H - -#define DEFAULT_LOG2_THROTTLING_FOR_ERROR_EQ 4 - -#define HW_CHANNEL_MAX_REQUEST_SIZE 0x1000 -#define HW_CHANNEL_MAX_RESPONSE_SIZE 0x1000 - -#define HW_CHANNEL_VF_BOOTSTRAP_QUEUE_DEPTH 1 - -#define HWC_INIT_DATA_CQID 1 -#define HWC_INIT_DATA_RQID 2 -#define HWC_INIT_DATA_SQID 3 -#define HWC_INIT_DATA_QUEUE_DEPTH 4 -#define HWC_INIT_DATA_MAX_REQUEST 5 -#define HWC_INIT_DATA_MAX_RESPONSE 6 -#define HWC_INIT_DATA_MAX_NUM_CQS 7 -#define HWC_INIT_DATA_PDID 8 -#define HWC_INIT_DATA_GPA_MKEY 9 -#define HWC_INIT_DATA_PF_DEST_RQ_ID 10 -#define HWC_INIT_DATA_PF_DEST_CQ_ID 11 - -/* Structures labeled with "HW DATA" are exchanged with the hardware. All of - * them are naturally aligned and hence don't need __packed. - */ - -union hwc_init_eq_id_db { - u32 as_uint32; - - struct { - u32 eq_id : 16; - u32 doorbell : 16; - }; -}; /* HW DATA */ - -union hwc_init_type_data { - u32 as_uint32; - - struct { - u32 value : 24; - u32 type : 8; - }; -}; /* HW DATA */ - -struct hwc_rx_oob { - u32 type : 6; - u32 eom : 1; - u32 som : 1; - u32 vendor_err : 8; - u32 reserved1 : 16; - - u32 src_virt_wq : 24; - u32 src_vfid : 8; - - u32 reserved2; - - union { - u32 wqe_addr_low; - u32 wqe_offset; - }; - - u32 wqe_addr_high; - - u32 client_data_unit : 14; - u32 reserved3 : 18; - - u32 tx_oob_data_size; - - u32 chunk_offset : 21; - u32 reserved4 : 11; -}; /* HW DATA */ - -struct hwc_tx_oob { - u32 reserved1; - - u32 reserved2; - - u32 vrq_id : 24; - u32 dest_vfid : 8; - - u32 vrcq_id : 24; - u32 reserved3 : 8; - - u32 vscq_id : 24; - u32 loopback : 1; - u32 lso_override: 1; - u32 dest_pf : 1; - u32 reserved4 : 5; - - u32 vsq_id : 24; - u32 reserved5 : 8; -}; /* HW DATA */ - -struct hwc_work_request { - void *buf_va; - void *buf_sge_addr; - u32 buf_len; - u32 msg_size; - - struct gdma_wqe_request wqe_req; - struct hwc_tx_oob tx_oob; - - struct gdma_sge sge; -}; - -/* hwc_dma_buf represents the array of in-flight WQEs. - * mem_info as know as the GDMA mapped memory is partitioned and used by - * in-flight WQEs. - * The number of WQEs is determined by the number of in-flight messages. - */ -struct hwc_dma_buf { - struct gdma_mem_info mem_info; - - u32 gpa_mkey; - - u32 num_reqs; - struct hwc_work_request reqs[]; -}; - -typedef void hwc_rx_event_handler_t(void *ctx, u32 gdma_rxq_id, - const struct hwc_rx_oob *rx_oob); - -typedef void hwc_tx_event_handler_t(void *ctx, u32 gdma_txq_id, - const struct hwc_rx_oob *rx_oob); - -struct hwc_cq { - struct hw_channel_context *hwc; - - struct gdma_queue *gdma_cq; - struct gdma_queue *gdma_eq; - struct gdma_comp *comp_buf; - u16 queue_depth; - - hwc_rx_event_handler_t *rx_event_handler; - void *rx_event_ctx; - - hwc_tx_event_handler_t *tx_event_handler; - void *tx_event_ctx; -}; - -struct hwc_wq { - struct hw_channel_context *hwc; - - struct gdma_queue *gdma_wq; - struct hwc_dma_buf *msg_buf; - u16 queue_depth; - - struct hwc_cq *hwc_cq; -}; - -struct hwc_caller_ctx { - struct completion comp_event; - void *output_buf; - u32 output_buflen; - - u32 error; /* Linux error code */ - u32 status_code; -}; - -struct hw_channel_context { - struct gdma_dev *gdma_dev; - struct device *dev; - - u16 num_inflight_msg; - u32 max_req_msg_size; - - u16 hwc_init_q_depth_max; - u32 hwc_init_max_req_msg_size; - u32 hwc_init_max_resp_msg_size; - - struct completion hwc_init_eqe_comp; - - struct hwc_wq *rxq; - struct hwc_wq *txq; - struct hwc_cq *cq; - - struct semaphore sema; - struct gdma_resource inflight_msg_res; - - u32 pf_dest_vrq_id; - u32 pf_dest_vrcq_id; - - struct hwc_caller_ctx *caller_ctx; -}; - -int mana_hwc_create_channel(struct gdma_context *gc); -void mana_hwc_destroy_channel(struct gdma_context *gc); - -int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len, - const void *req, u32 resp_len, void *resp); - -#endif /* _HW_CHANNEL_H */ diff --git a/drivers/net/ethernet/microsoft/mana/mana.h b/drivers/net/ethernet/microsoft/mana/mana.h deleted file mode 100644 index 6e9e86fb4c02..000000000000 --- a/drivers/net/ethernet/microsoft/mana/mana.h +++ /dev/null @@ -1,650 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ -/* Copyright (c) 2021, Microsoft Corporation. */ - -#ifndef _MANA_H -#define _MANA_H - -#include "gdma.h" -#include "hw_channel.h" - -/* Microsoft Azure Network Adapter (MANA)'s definitions - * - * Structures labeled with "HW DATA" are exchanged with the hardware. All of - * them are naturally aligned and hence don't need __packed. - */ - -/* MANA protocol version */ -#define MANA_MAJOR_VERSION 0 -#define MANA_MINOR_VERSION 1 -#define MANA_MICRO_VERSION 1 - -typedef u64 mana_handle_t; -#define INVALID_MANA_HANDLE ((mana_handle_t)-1) - -enum TRI_STATE { - TRI_STATE_UNKNOWN = -1, - TRI_STATE_FALSE = 0, - TRI_STATE_TRUE = 1 -}; - -/* Number of entries for hardware indirection table must be in power of 2 */ -#define MANA_INDIRECT_TABLE_SIZE 64 -#define MANA_INDIRECT_TABLE_MASK (MANA_INDIRECT_TABLE_SIZE - 1) - -/* The Toeplitz hash key's length in bytes: should be multiple of 8 */ -#define MANA_HASH_KEY_SIZE 40 - -#define COMP_ENTRY_SIZE 64 - -#define ADAPTER_MTU_SIZE 1500 -#define MAX_FRAME_SIZE (ADAPTER_MTU_SIZE + 14) - -#define RX_BUFFERS_PER_QUEUE 512 - -#define MAX_SEND_BUFFERS_PER_QUEUE 256 - -#define EQ_SIZE (8 * PAGE_SIZE) -#define LOG2_EQ_THROTTLE 3 - -#define MAX_PORTS_IN_MANA_DEV 256 - -struct mana_stats_rx { - u64 packets; - u64 bytes; - u64 xdp_drop; - u64 xdp_tx; - u64 xdp_redirect; - struct u64_stats_sync syncp; -}; - -struct mana_stats_tx { - u64 packets; - u64 bytes; - u64 xdp_xmit; - struct u64_stats_sync syncp; -}; - -struct mana_txq { - struct gdma_queue *gdma_sq; - - union { - u32 gdma_txq_id; - struct { - u32 reserved1 : 10; - u32 vsq_frame : 14; - u32 reserved2 : 8; - }; - }; - - u16 vp_offset; - - struct net_device *ndev; - - /* The SKBs are sent to the HW and we are waiting for the CQEs. */ - struct sk_buff_head pending_skbs; - struct netdev_queue *net_txq; - - atomic_t pending_sends; - - struct mana_stats_tx stats; -}; - -/* skb data and frags dma mappings */ -struct mana_skb_head { - dma_addr_t dma_handle[MAX_SKB_FRAGS + 1]; - - u32 size[MAX_SKB_FRAGS + 1]; -}; - -#define MANA_HEADROOM sizeof(struct mana_skb_head) - -enum mana_tx_pkt_format { - MANA_SHORT_PKT_FMT = 0, - MANA_LONG_PKT_FMT = 1, -}; - -struct mana_tx_short_oob { - u32 pkt_fmt : 2; - u32 is_outer_ipv4 : 1; - u32 is_outer_ipv6 : 1; - u32 comp_iphdr_csum : 1; - u32 comp_tcp_csum : 1; - u32 comp_udp_csum : 1; - u32 supress_txcqe_gen : 1; - u32 vcq_num : 24; - - u32 trans_off : 10; /* Transport header offset */ - u32 vsq_frame : 14; - u32 short_vp_offset : 8; -}; /* HW DATA */ - -struct mana_tx_long_oob { - u32 is_encap : 1; - u32 inner_is_ipv6 : 1; - u32 inner_tcp_opt : 1; - u32 inject_vlan_pri_tag : 1; - u32 reserved1 : 12; - u32 pcp : 3; /* 802.1Q */ - u32 dei : 1; /* 802.1Q */ - u32 vlan_id : 12; /* 802.1Q */ - - u32 inner_frame_offset : 10; - u32 inner_ip_rel_offset : 6; - u32 long_vp_offset : 12; - u32 reserved2 : 4; - - u32 reserved3; - u32 reserved4; -}; /* HW DATA */ - -struct mana_tx_oob { - struct mana_tx_short_oob s_oob; - struct mana_tx_long_oob l_oob; -}; /* HW DATA */ - -enum mana_cq_type { - MANA_CQ_TYPE_RX, - MANA_CQ_TYPE_TX, -}; - -enum mana_cqe_type { - CQE_INVALID = 0, - CQE_RX_OKAY = 1, - CQE_RX_COALESCED_4 = 2, - CQE_RX_OBJECT_FENCE = 3, - CQE_RX_TRUNCATED = 4, - - CQE_TX_OKAY = 32, - CQE_TX_SA_DROP = 33, - CQE_TX_MTU_DROP = 34, - CQE_TX_INVALID_OOB = 35, - CQE_TX_INVALID_ETH_TYPE = 36, - CQE_TX_HDR_PROCESSING_ERROR = 37, - CQE_TX_VF_DISABLED = 38, - CQE_TX_VPORT_IDX_OUT_OF_RANGE = 39, - CQE_TX_VPORT_DISABLED = 40, - CQE_TX_VLAN_TAGGING_VIOLATION = 41, -}; - -#define MANA_CQE_COMPLETION 1 - -struct mana_cqe_header { - u32 cqe_type : 6; - u32 client_type : 2; - u32 vendor_err : 24; -}; /* HW DATA */ - -/* NDIS HASH Types */ -#define NDIS_HASH_IPV4 BIT(0) -#define NDIS_HASH_TCP_IPV4 BIT(1) -#define NDIS_HASH_UDP_IPV4 BIT(2) -#define NDIS_HASH_IPV6 BIT(3) -#define NDIS_HASH_TCP_IPV6 BIT(4) -#define NDIS_HASH_UDP_IPV6 BIT(5) -#define NDIS_HASH_IPV6_EX BIT(6) -#define NDIS_HASH_TCP_IPV6_EX BIT(7) -#define NDIS_HASH_UDP_IPV6_EX BIT(8) - -#define MANA_HASH_L3 (NDIS_HASH_IPV4 | NDIS_HASH_IPV6 | NDIS_HASH_IPV6_EX) -#define MANA_HASH_L4 \ - (NDIS_HASH_TCP_IPV4 | NDIS_HASH_UDP_IPV4 | NDIS_HASH_TCP_IPV6 | \ - NDIS_HASH_UDP_IPV6 | NDIS_HASH_TCP_IPV6_EX | NDIS_HASH_UDP_IPV6_EX) - -struct mana_rxcomp_perpkt_info { - u32 pkt_len : 16; - u32 reserved1 : 16; - u32 reserved2; - u32 pkt_hash; -}; /* HW DATA */ - -#define MANA_RXCOMP_OOB_NUM_PPI 4 - -/* Receive completion OOB */ -struct mana_rxcomp_oob { - struct mana_cqe_header cqe_hdr; - - u32 rx_vlan_id : 12; - u32 rx_vlantag_present : 1; - u32 rx_outer_iphdr_csum_succeed : 1; - u32 rx_outer_iphdr_csum_fail : 1; - u32 reserved1 : 1; - u32 rx_hashtype : 9; - u32 rx_iphdr_csum_succeed : 1; - u32 rx_iphdr_csum_fail : 1; - u32 rx_tcp_csum_succeed : 1; - u32 rx_tcp_csum_fail : 1; - u32 rx_udp_csum_succeed : 1; - u32 rx_udp_csum_fail : 1; - u32 reserved2 : 1; - - struct mana_rxcomp_perpkt_info ppi[MANA_RXCOMP_OOB_NUM_PPI]; - - u32 rx_wqe_offset; -}; /* HW DATA */ - -struct mana_tx_comp_oob { - struct mana_cqe_header cqe_hdr; - - u32 tx_data_offset; - - u32 tx_sgl_offset : 5; - u32 tx_wqe_offset : 27; - - u32 reserved[12]; -}; /* HW DATA */ - -struct mana_rxq; - -#define CQE_POLLING_BUFFER 512 - -struct mana_cq { - struct gdma_queue *gdma_cq; - - /* Cache the CQ id (used to verify if each CQE comes to the right CQ. */ - u32 gdma_id; - - /* Type of the CQ: TX or RX */ - enum mana_cq_type type; - - /* Pointer to the mana_rxq that is pushing RX CQEs to the queue. - * Only and must be non-NULL if type is MANA_CQ_TYPE_RX. - */ - struct mana_rxq *rxq; - - /* Pointer to the mana_txq that is pushing TX CQEs to the queue. - * Only and must be non-NULL if type is MANA_CQ_TYPE_TX. - */ - struct mana_txq *txq; - - /* Buffer which the CQ handler can copy the CQE's into. */ - struct gdma_comp gdma_comp_buf[CQE_POLLING_BUFFER]; - - /* NAPI data */ - struct napi_struct napi; - int work_done; - int budget; -}; - -#define GDMA_MAX_RQE_SGES 15 - -struct mana_recv_buf_oob { - /* A valid GDMA work request representing the data buffer. */ - struct gdma_wqe_request wqe_req; - - void *buf_va; - dma_addr_t buf_dma_addr; - - /* SGL of the buffer going to be sent has part of the work request. */ - u32 num_sge; - struct gdma_sge sgl[GDMA_MAX_RQE_SGES]; - - /* Required to store the result of mana_gd_post_work_request. - * gdma_posted_wqe_info.wqe_size_in_bu is required for progressing the - * work queue when the WQE is consumed. - */ - struct gdma_posted_wqe_info wqe_inf; -}; - -struct mana_rxq { - struct gdma_queue *gdma_rq; - /* Cache the gdma receive queue id */ - u32 gdma_id; - - /* Index of RQ in the vPort, not gdma receive queue id */ - u32 rxq_idx; - - u32 datasize; - - mana_handle_t rxobj; - - struct mana_cq rx_cq; - - struct completion fence_event; - - struct net_device *ndev; - - /* Total number of receive buffers to be allocated */ - u32 num_rx_buf; - - u32 buf_index; - - struct mana_stats_rx stats; - - struct bpf_prog __rcu *bpf_prog; - struct xdp_rxq_info xdp_rxq; - struct page *xdp_save_page; - bool xdp_flush; - int xdp_rc; /* XDP redirect return code */ - - /* MUST BE THE LAST MEMBER: - * Each receive buffer has an associated mana_recv_buf_oob. - */ - struct mana_recv_buf_oob rx_oobs[]; -}; - -struct mana_tx_qp { - struct mana_txq txq; - - struct mana_cq tx_cq; - - mana_handle_t tx_object; -}; - -struct mana_ethtool_stats { - u64 stop_queue; - u64 wake_queue; -}; - -struct mana_context { - struct gdma_dev *gdma_dev; - - u16 num_ports; - - struct mana_eq *eqs; - - struct net_device *ports[MAX_PORTS_IN_MANA_DEV]; -}; - -struct mana_port_context { - struct mana_context *ac; - struct net_device *ndev; - - u8 mac_addr[ETH_ALEN]; - - enum TRI_STATE rss_state; - - mana_handle_t default_rxobj; - bool tx_shortform_allowed; - u16 tx_vp_offset; - - struct mana_tx_qp *tx_qp; - - /* Indirection Table for RX & TX. The values are queue indexes */ - u32 indir_table[MANA_INDIRECT_TABLE_SIZE]; - - /* Indirection table containing RxObject Handles */ - mana_handle_t rxobj_table[MANA_INDIRECT_TABLE_SIZE]; - - /* Hash key used by the NIC */ - u8 hashkey[MANA_HASH_KEY_SIZE]; - - /* This points to an array of num_queues of RQ pointers. */ - struct mana_rxq **rxqs; - - struct bpf_prog *bpf_prog; - - /* Create num_queues EQs, SQs, SQ-CQs, RQs and RQ-CQs, respectively. */ - unsigned int max_queues; - unsigned int num_queues; - - mana_handle_t port_handle; - mana_handle_t pf_filter_handle; - - /* Mutex for sharing access to vport_use_count */ - struct mutex vport_mutex; - int vport_use_count; - - u16 port_idx; - - bool port_is_up; - bool port_st_save; /* Saved port state */ - - struct mana_ethtool_stats eth_stats; -}; - -int mana_start_xmit(struct sk_buff *skb, struct net_device *ndev); -int mana_config_rss(struct mana_port_context *ac, enum TRI_STATE rx, - bool update_hash, bool update_tab); - -int mana_alloc_queues(struct net_device *ndev); -int mana_attach(struct net_device *ndev); -int mana_detach(struct net_device *ndev, bool from_close); - -int mana_probe(struct gdma_dev *gd, bool resuming); -void mana_remove(struct gdma_dev *gd, bool suspending); - -void mana_xdp_tx(struct sk_buff *skb, struct net_device *ndev); -int mana_xdp_xmit(struct net_device *ndev, int n, struct xdp_frame **frames, - u32 flags); -u32 mana_run_xdp(struct net_device *ndev, struct mana_rxq *rxq, - struct xdp_buff *xdp, void *buf_va, uint pkt_len); -struct bpf_prog *mana_xdp_get(struct mana_port_context *apc); -void mana_chn_setxdp(struct mana_port_context *apc, struct bpf_prog *prog); -int mana_bpf(struct net_device *ndev, struct netdev_bpf *bpf); - -extern const struct ethtool_ops mana_ethtool_ops; - -struct mana_obj_spec { - u32 queue_index; - u64 gdma_region; - u32 queue_size; - u32 attached_eq; - u32 modr_ctx_id; -}; - -enum mana_command_code { - MANA_QUERY_DEV_CONFIG = 0x20001, - MANA_QUERY_GF_STAT = 0x20002, - MANA_CONFIG_VPORT_TX = 0x20003, - MANA_CREATE_WQ_OBJ = 0x20004, - MANA_DESTROY_WQ_OBJ = 0x20005, - MANA_FENCE_RQ = 0x20006, - MANA_CONFIG_VPORT_RX = 0x20007, - MANA_QUERY_VPORT_CONFIG = 0x20008, - - /* Privileged commands for the PF mode */ - MANA_REGISTER_FILTER = 0x28000, - MANA_DEREGISTER_FILTER = 0x28001, - MANA_REGISTER_HW_PORT = 0x28003, - MANA_DEREGISTER_HW_PORT = 0x28004, -}; - -/* Query Device Configuration */ -struct mana_query_device_cfg_req { - struct gdma_req_hdr hdr; - - /* MANA Nic Driver Capability flags */ - u64 mn_drv_cap_flags1; - u64 mn_drv_cap_flags2; - u64 mn_drv_cap_flags3; - u64 mn_drv_cap_flags4; - - u32 proto_major_ver; - u32 proto_minor_ver; - u32 proto_micro_ver; - - u32 reserved; -}; /* HW DATA */ - -struct mana_query_device_cfg_resp { - struct gdma_resp_hdr hdr; - - u64 pf_cap_flags1; - u64 pf_cap_flags2; - u64 pf_cap_flags3; - u64 pf_cap_flags4; - - u16 max_num_vports; - u16 reserved; - u32 max_num_eqs; -}; /* HW DATA */ - -/* Query vPort Configuration */ -struct mana_query_vport_cfg_req { - struct gdma_req_hdr hdr; - u32 vport_index; -}; /* HW DATA */ - -struct mana_query_vport_cfg_resp { - struct gdma_resp_hdr hdr; - u32 max_num_sq; - u32 max_num_rq; - u32 num_indirection_ent; - u32 reserved1; - u8 mac_addr[6]; - u8 reserved2[2]; - mana_handle_t vport; -}; /* HW DATA */ - -/* Configure vPort */ -struct mana_config_vport_req { - struct gdma_req_hdr hdr; - mana_handle_t vport; - u32 pdid; - u32 doorbell_pageid; -}; /* HW DATA */ - -struct mana_config_vport_resp { - struct gdma_resp_hdr hdr; - u16 tx_vport_offset; - u8 short_form_allowed; - u8 reserved; -}; /* HW DATA */ - -/* Create WQ Object */ -struct mana_create_wqobj_req { - struct gdma_req_hdr hdr; - mana_handle_t vport; - u32 wq_type; - u32 reserved; - u64 wq_gdma_region; - u64 cq_gdma_region; - u32 wq_size; - u32 cq_size; - u32 cq_moderation_ctx_id; - u32 cq_parent_qid; -}; /* HW DATA */ - -struct mana_create_wqobj_resp { - struct gdma_resp_hdr hdr; - u32 wq_id; - u32 cq_id; - mana_handle_t wq_obj; -}; /* HW DATA */ - -/* Destroy WQ Object */ -struct mana_destroy_wqobj_req { - struct gdma_req_hdr hdr; - u32 wq_type; - u32 reserved; - mana_handle_t wq_obj_handle; -}; /* HW DATA */ - -struct mana_destroy_wqobj_resp { - struct gdma_resp_hdr hdr; -}; /* HW DATA */ - -/* Fence RQ */ -struct mana_fence_rq_req { - struct gdma_req_hdr hdr; - mana_handle_t wq_obj_handle; -}; /* HW DATA */ - -struct mana_fence_rq_resp { - struct gdma_resp_hdr hdr; -}; /* HW DATA */ - -/* Configure vPort Rx Steering */ -struct mana_cfg_rx_steer_req { - struct gdma_req_hdr hdr; - mana_handle_t vport; - u16 num_indir_entries; - u16 indir_tab_offset; - u32 rx_enable; - u32 rss_enable; - u8 update_default_rxobj; - u8 update_hashkey; - u8 update_indir_tab; - u8 reserved; - mana_handle_t default_rxobj; - u8 hashkey[MANA_HASH_KEY_SIZE]; -}; /* HW DATA */ - -struct mana_cfg_rx_steer_resp { - struct gdma_resp_hdr hdr; -}; /* HW DATA */ - -/* Register HW vPort */ -struct mana_register_hw_vport_req { - struct gdma_req_hdr hdr; - u16 attached_gfid; - u8 is_pf_default_vport; - u8 reserved1; - u8 allow_all_ether_types; - u8 reserved2; - u8 reserved3; - u8 reserved4; -}; /* HW DATA */ - -struct mana_register_hw_vport_resp { - struct gdma_resp_hdr hdr; - mana_handle_t hw_vport_handle; -}; /* HW DATA */ - -/* Deregister HW vPort */ -struct mana_deregister_hw_vport_req { - struct gdma_req_hdr hdr; - mana_handle_t hw_vport_handle; -}; /* HW DATA */ - -struct mana_deregister_hw_vport_resp { - struct gdma_resp_hdr hdr; -}; /* HW DATA */ - -/* Register filter */ -struct mana_register_filter_req { - struct gdma_req_hdr hdr; - mana_handle_t vport; - u8 mac_addr[6]; - u8 reserved1; - u8 reserved2; - u8 reserved3; - u8 reserved4; - u16 reserved5; - u32 reserved6; - u32 reserved7; - u32 reserved8; -}; /* HW DATA */ - -struct mana_register_filter_resp { - struct gdma_resp_hdr hdr; - mana_handle_t filter_handle; -}; /* HW DATA */ - -/* Deregister filter */ -struct mana_deregister_filter_req { - struct gdma_req_hdr hdr; - mana_handle_t filter_handle; -}; /* HW DATA */ - -struct mana_deregister_filter_resp { - struct gdma_resp_hdr hdr; -}; /* HW DATA */ - -#define MANA_MAX_NUM_QUEUES 64 - -#define MANA_SHORT_VPORT_OFFSET_MAX ((1U << 8) - 1) - -struct mana_tx_package { - struct gdma_wqe_request wqe_req; - struct gdma_sge sgl_array[5]; - struct gdma_sge *sgl_ptr; - - struct mana_tx_oob tx_oob; - - struct gdma_posted_wqe_info wqe_info; -}; - -int mana_create_wq_obj(struct mana_port_context *apc, - mana_handle_t vport, - u32 wq_type, struct mana_obj_spec *wq_spec, - struct mana_obj_spec *cq_spec, - mana_handle_t *wq_obj); - -void mana_destroy_wq_obj(struct mana_port_context *apc, u32 wq_type, - mana_handle_t wq_obj); - -int mana_cfg_vport(struct mana_port_context *apc, u32 protection_dom_id, - u32 doorbell_pg_id); -void mana_uncfg_vport(struct mana_port_context *apc); -#endif /* _MANA_H */ diff --git a/drivers/net/ethernet/microsoft/mana/mana_auxiliary.h b/drivers/net/ethernet/microsoft/mana/mana_auxiliary.h deleted file mode 100644 index 373d59756846..000000000000 --- a/drivers/net/ethernet/microsoft/mana/mana_auxiliary.h +++ /dev/null @@ -1,10 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* Copyright (c) 2022, Microsoft Corporation. */ - -#include "mana.h" -#include - -struct mana_adev { - struct auxiliary_device adev; - struct gdma_dev *mdev; -}; diff --git a/drivers/net/ethernet/microsoft/mana/mana_bpf.c b/drivers/net/ethernet/microsoft/mana/mana_bpf.c index 421fd39ff3a8..3caea631229c 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_bpf.c +++ b/drivers/net/ethernet/microsoft/mana/mana_bpf.c @@ -8,7 +8,7 @@ #include #include -#include "mana.h" +#include void mana_xdp_tx(struct sk_buff *skb, struct net_device *ndev) { diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index b6303a43fa7c..ffa2a0e2c213 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -12,8 +12,8 @@ #include #include -#include "mana.h" -#include "mana_auxiliary.h" +#include +#include static DEFINE_IDA(mana_adev_ida); diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c index c530db76880f..6f98de6d7440 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c +++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c @@ -5,7 +5,7 @@ #include #include -#include "mana.h" +#include static const struct { char name[ETH_GSTRING_LEN]; diff --git a/drivers/net/ethernet/microsoft/mana/shm_channel.c b/drivers/net/ethernet/microsoft/mana/shm_channel.c index da255da62176..5553af9c8085 100644 --- a/drivers/net/ethernet/microsoft/mana/shm_channel.c +++ b/drivers/net/ethernet/microsoft/mana/shm_channel.c @@ -6,7 +6,7 @@ #include #include -#include "shm_channel.h" +#include #define PAGE_FRAME_L48_WIDTH_BYTES 6 #define PAGE_FRAME_L48_WIDTH_BITS (PAGE_FRAME_L48_WIDTH_BYTES * 8) diff --git a/drivers/net/ethernet/microsoft/mana/shm_channel.h b/drivers/net/ethernet/microsoft/mana/shm_channel.h deleted file mode 100644 index 5199b41497ff..000000000000 --- a/drivers/net/ethernet/microsoft/mana/shm_channel.h +++ /dev/null @@ -1,21 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ -/* Copyright (c) 2021, Microsoft Corporation. */ - -#ifndef _SHM_CHANNEL_H -#define _SHM_CHANNEL_H - -struct shm_channel { - struct device *dev; - void __iomem *base; -}; - -void mana_smc_init(struct shm_channel *sc, struct device *dev, - void __iomem *base); - -int mana_smc_setup_hwc(struct shm_channel *sc, bool reset_vf, u64 eq_addr, - u64 cq_addr, u64 rq_addr, u64 sq_addr, - u32 eq_msix_index); - -int mana_smc_teardown_hwc(struct shm_channel *sc, bool reset_vf); - -#endif /* _SHM_CHANNEL_H */ diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h new file mode 100644 index 000000000000..72eaec2470c0 --- /dev/null +++ b/include/net/mana/gdma.h @@ -0,0 +1,689 @@ +/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ +/* Copyright (c) 2021, Microsoft Corporation. */ + +#ifndef _GDMA_H +#define _GDMA_H + +#include +#include + +#include "shm_channel.h" + +/* Structures labeled with "HW DATA" are exchanged with the hardware. All of + * them are naturally aligned and hence don't need __packed. + */ + +enum gdma_request_type { + GDMA_VERIFY_VF_DRIVER_VERSION = 1, + GDMA_QUERY_MAX_RESOURCES = 2, + GDMA_LIST_DEVICES = 3, + GDMA_REGISTER_DEVICE = 4, + GDMA_DEREGISTER_DEVICE = 5, + GDMA_GENERATE_TEST_EQE = 10, + GDMA_CREATE_QUEUE = 12, + GDMA_DISABLE_QUEUE = 13, + GDMA_CREATE_DMA_REGION = 25, + GDMA_DMA_REGION_ADD_PAGES = 26, + GDMA_DESTROY_DMA_REGION = 27, +}; + +enum gdma_queue_type { + GDMA_INVALID_QUEUE, + GDMA_SQ, + GDMA_RQ, + GDMA_CQ, + GDMA_EQ, +}; + +enum gdma_work_request_flags { + GDMA_WR_NONE = 0, + GDMA_WR_OOB_IN_SGL = BIT(0), + GDMA_WR_PAD_BY_SGE0 = BIT(1), +}; + +enum gdma_eqe_type { + GDMA_EQE_COMPLETION = 3, + GDMA_EQE_TEST_EVENT = 64, + GDMA_EQE_HWC_INIT_EQ_ID_DB = 129, + GDMA_EQE_HWC_INIT_DATA = 130, + GDMA_EQE_HWC_INIT_DONE = 131, +}; + +enum { + GDMA_DEVICE_NONE = 0, + GDMA_DEVICE_HWC = 1, + GDMA_DEVICE_MANA = 2, +}; + +struct gdma_resource { + /* Protect the bitmap */ + spinlock_t lock; + + /* The bitmap size in bits. */ + u32 size; + + /* The bitmap tracks the resources. */ + unsigned long *map; +}; + +union gdma_doorbell_entry { + u64 as_uint64; + + struct { + u64 id : 24; + u64 reserved : 8; + u64 tail_ptr : 31; + u64 arm : 1; + } cq; + + struct { + u64 id : 24; + u64 wqe_cnt : 8; + u64 tail_ptr : 32; + } rq; + + struct { + u64 id : 24; + u64 reserved : 8; + u64 tail_ptr : 32; + } sq; + + struct { + u64 id : 16; + u64 reserved : 16; + u64 tail_ptr : 31; + u64 arm : 1; + } eq; +}; /* HW DATA */ + +struct gdma_msg_hdr { + u32 hdr_type; + u32 msg_type; + u16 msg_version; + u16 hwc_msg_id; + u32 msg_size; +}; /* HW DATA */ + +struct gdma_dev_id { + union { + struct { + u16 type; + u16 instance; + }; + + u32 as_uint32; + }; +}; /* HW DATA */ + +struct gdma_req_hdr { + struct gdma_msg_hdr req; + struct gdma_msg_hdr resp; /* The expected response */ + struct gdma_dev_id dev_id; + u32 activity_id; +}; /* HW DATA */ + +struct gdma_resp_hdr { + struct gdma_msg_hdr response; + struct gdma_dev_id dev_id; + u32 activity_id; + u32 status; + u32 reserved; +}; /* HW DATA */ + +struct gdma_general_req { + struct gdma_req_hdr hdr; +}; /* HW DATA */ + +#define GDMA_MESSAGE_V1 1 + +struct gdma_general_resp { + struct gdma_resp_hdr hdr; +}; /* HW DATA */ + +#define GDMA_STANDARD_HEADER_TYPE 0 + +static inline void mana_gd_init_req_hdr(struct gdma_req_hdr *hdr, u32 code, + u32 req_size, u32 resp_size) +{ + hdr->req.hdr_type = GDMA_STANDARD_HEADER_TYPE; + hdr->req.msg_type = code; + hdr->req.msg_version = GDMA_MESSAGE_V1; + hdr->req.msg_size = req_size; + + hdr->resp.hdr_type = GDMA_STANDARD_HEADER_TYPE; + hdr->resp.msg_type = code; + hdr->resp.msg_version = GDMA_MESSAGE_V1; + hdr->resp.msg_size = resp_size; +} + +/* The 16-byte struct is part of the GDMA work queue entry (WQE). */ +struct gdma_sge { + u64 address; + u32 mem_key; + u32 size; +}; /* HW DATA */ + +struct gdma_wqe_request { + struct gdma_sge *sgl; + u32 num_sge; + + u32 inline_oob_size; + const void *inline_oob_data; + + u32 flags; + u32 client_data_unit; +}; + +enum gdma_page_type { + GDMA_PAGE_TYPE_4K, +}; + +#define GDMA_INVALID_DMA_REGION 0 + +struct gdma_mem_info { + struct device *dev; + + dma_addr_t dma_handle; + void *virt_addr; + u64 length; + + /* Allocated by the PF driver */ + u64 gdma_region; +}; + +#define REGISTER_ATB_MST_MKEY_LOWER_SIZE 8 + +struct gdma_dev { + struct gdma_context *gdma_context; + + struct gdma_dev_id dev_id; + + u32 pdid; + u32 doorbell; + u32 gpa_mkey; + + /* GDMA driver specific pointer */ + void *driver_data; + + struct auxiliary_device *adev; +}; + +#define MINIMUM_SUPPORTED_PAGE_SIZE PAGE_SIZE + +#define GDMA_CQE_SIZE 64 +#define GDMA_EQE_SIZE 16 +#define GDMA_MAX_SQE_SIZE 512 +#define GDMA_MAX_RQE_SIZE 256 + +#define GDMA_COMP_DATA_SIZE 0x3C + +#define GDMA_EVENT_DATA_SIZE 0xC + +/* The WQE size must be a multiple of the Basic Unit, which is 32 bytes. */ +#define GDMA_WQE_BU_SIZE 32 + +#define INVALID_PDID UINT_MAX +#define INVALID_DOORBELL UINT_MAX +#define INVALID_MEM_KEY UINT_MAX +#define INVALID_QUEUE_ID UINT_MAX +#define INVALID_PCI_MSIX_INDEX UINT_MAX + +struct gdma_comp { + u32 cqe_data[GDMA_COMP_DATA_SIZE / 4]; + u32 wq_num; + bool is_sq; +}; + +struct gdma_event { + u32 details[GDMA_EVENT_DATA_SIZE / 4]; + u8 type; +}; + +struct gdma_queue; + +struct mana_eq { + struct gdma_queue *eq; +}; + +typedef void gdma_eq_callback(void *context, struct gdma_queue *q, + struct gdma_event *e); + +typedef void gdma_cq_callback(void *context, struct gdma_queue *q); + +/* The 'head' is the producer index. For SQ/RQ, when the driver posts a WQE + * (Note: the WQE size must be a multiple of the 32-byte Basic Unit), the + * driver increases the 'head' in BUs rather than in bytes, and notifies + * the HW of the updated head. For EQ/CQ, the driver uses the 'head' to track + * the HW head, and increases the 'head' by 1 for every processed EQE/CQE. + * + * The 'tail' is the consumer index for SQ/RQ. After the CQE of the SQ/RQ is + * processed, the driver increases the 'tail' to indicate that WQEs have + * been consumed by the HW, so the driver can post new WQEs into the SQ/RQ. + * + * The driver doesn't use the 'tail' for EQ/CQ, because the driver ensures + * that the EQ/CQ is big enough so they can't overflow, and the driver uses + * the owner bits mechanism to detect if the queue has become empty. + */ +struct gdma_queue { + struct gdma_dev *gdma_dev; + + enum gdma_queue_type type; + u32 id; + + struct gdma_mem_info mem_info; + + void *queue_mem_ptr; + u32 queue_size; + + bool monitor_avl_buf; + + u32 head; + u32 tail; + + /* Extra fields specific to EQ/CQ. */ + union { + struct { + bool disable_needed; + + gdma_eq_callback *callback; + void *context; + + unsigned int msix_index; + + u32 log2_throttle_limit; + } eq; + + struct { + gdma_cq_callback *callback; + void *context; + + struct gdma_queue *parent; /* For CQ/EQ relationship */ + } cq; + }; +}; + +struct gdma_queue_spec { + enum gdma_queue_type type; + bool monitor_avl_buf; + unsigned int queue_size; + + /* Extra fields specific to EQ/CQ. */ + union { + struct { + gdma_eq_callback *callback; + void *context; + + unsigned long log2_throttle_limit; + } eq; + + struct { + gdma_cq_callback *callback; + void *context; + + struct gdma_queue *parent_eq; + + } cq; + }; +}; + +struct gdma_irq_context { + void (*handler)(void *arg); + void *arg; +}; + +struct gdma_context { + struct device *dev; + + /* Per-vPort max number of queues */ + unsigned int max_num_queues; + unsigned int max_num_msix; + unsigned int num_msix_usable; + struct gdma_resource msix_resource; + struct gdma_irq_context *irq_contexts; + + /* This maps a CQ index to the queue structure. */ + unsigned int max_num_cqs; + struct gdma_queue **cq_table; + + /* Protect eq_test_event and test_event_eq_id */ + struct mutex eq_test_event_mutex; + struct completion eq_test_event; + u32 test_event_eq_id; + + bool is_pf; + phys_addr_t bar0_pa; + void __iomem *bar0_va; + void __iomem *shm_base; + void __iomem *db_page_base; + phys_addr_t phys_db_page_base; + u32 db_page_size; + + /* Shared memory chanenl (used to bootstrap HWC) */ + struct shm_channel shm_channel; + + /* Hardware communication channel (HWC) */ + struct gdma_dev hwc; + + /* Azure network adapter */ + struct gdma_dev mana; +}; + +#define MAX_NUM_GDMA_DEVICES 4 + +static inline bool mana_gd_is_mana(struct gdma_dev *gd) +{ + return gd->dev_id.type == GDMA_DEVICE_MANA; +} + +static inline bool mana_gd_is_hwc(struct gdma_dev *gd) +{ + return gd->dev_id.type == GDMA_DEVICE_HWC; +} + +u8 *mana_gd_get_wqe_ptr(const struct gdma_queue *wq, u32 wqe_offset); +u32 mana_gd_wq_avail_space(struct gdma_queue *wq); + +int mana_gd_test_eq(struct gdma_context *gc, struct gdma_queue *eq); + +int mana_gd_create_hwc_queue(struct gdma_dev *gd, + const struct gdma_queue_spec *spec, + struct gdma_queue **queue_ptr); + +int mana_gd_create_mana_eq(struct gdma_dev *gd, + const struct gdma_queue_spec *spec, + struct gdma_queue **queue_ptr); + +int mana_gd_create_mana_wq_cq(struct gdma_dev *gd, + const struct gdma_queue_spec *spec, + struct gdma_queue **queue_ptr); + +void mana_gd_destroy_queue(struct gdma_context *gc, struct gdma_queue *queue); + +int mana_gd_poll_cq(struct gdma_queue *cq, struct gdma_comp *comp, int num_cqe); + +void mana_gd_ring_cq(struct gdma_queue *cq, u8 arm_bit); + +struct gdma_wqe { + u32 reserved :24; + u32 last_vbytes :8; + + union { + u32 flags; + + struct { + u32 num_sge :8; + u32 inline_oob_size_div4:3; + u32 client_oob_in_sgl :1; + u32 reserved1 :4; + u32 client_data_unit :14; + u32 reserved2 :2; + }; + }; +}; /* HW DATA */ + +#define INLINE_OOB_SMALL_SIZE 8 +#define INLINE_OOB_LARGE_SIZE 24 + +#define MAX_TX_WQE_SIZE 512 +#define MAX_RX_WQE_SIZE 256 + +struct gdma_cqe { + u32 cqe_data[GDMA_COMP_DATA_SIZE / 4]; + + union { + u32 as_uint32; + + struct { + u32 wq_num : 24; + u32 is_sq : 1; + u32 reserved : 4; + u32 owner_bits : 3; + }; + } cqe_info; +}; /* HW DATA */ + +#define GDMA_CQE_OWNER_BITS 3 + +#define GDMA_CQE_OWNER_MASK ((1 << GDMA_CQE_OWNER_BITS) - 1) + +#define SET_ARM_BIT 1 + +#define GDMA_EQE_OWNER_BITS 3 + +union gdma_eqe_info { + u32 as_uint32; + + struct { + u32 type : 8; + u32 reserved1 : 8; + u32 client_id : 2; + u32 reserved2 : 11; + u32 owner_bits : 3; + }; +}; /* HW DATA */ + +#define GDMA_EQE_OWNER_MASK ((1 << GDMA_EQE_OWNER_BITS) - 1) +#define INITIALIZED_OWNER_BIT(log2_num_entries) (1UL << (log2_num_entries)) + +struct gdma_eqe { + u32 details[GDMA_EVENT_DATA_SIZE / 4]; + u32 eqe_info; +}; /* HW DATA */ + +#define GDMA_REG_DB_PAGE_OFFSET 8 +#define GDMA_REG_DB_PAGE_SIZE 0x10 +#define GDMA_REG_SHM_OFFSET 0x18 + +#define GDMA_PF_REG_DB_PAGE_SIZE 0xD0 +#define GDMA_PF_REG_DB_PAGE_OFF 0xC8 +#define GDMA_PF_REG_SHM_OFF 0x70 + +#define GDMA_SRIOV_REG_CFG_BASE_OFF 0x108 + +#define MANA_PF_DEVICE_ID 0x00B9 +#define MANA_VF_DEVICE_ID 0x00BA + +struct gdma_posted_wqe_info { + u32 wqe_size_in_bu; +}; + +/* GDMA_GENERATE_TEST_EQE */ +struct gdma_generate_test_event_req { + struct gdma_req_hdr hdr; + u32 queue_index; +}; /* HW DATA */ + +/* GDMA_VERIFY_VF_DRIVER_VERSION */ +enum { + GDMA_PROTOCOL_V1 = 1, + GDMA_PROTOCOL_FIRST = GDMA_PROTOCOL_V1, + GDMA_PROTOCOL_LAST = GDMA_PROTOCOL_V1, +}; + +#define GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT BIT(0) + +#define GDMA_DRV_CAP_FLAGS1 GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT + +#define GDMA_DRV_CAP_FLAGS2 0 + +#define GDMA_DRV_CAP_FLAGS3 0 + +#define GDMA_DRV_CAP_FLAGS4 0 + +struct gdma_verify_ver_req { + struct gdma_req_hdr hdr; + + /* Mandatory fields required for protocol establishment */ + u64 protocol_ver_min; + u64 protocol_ver_max; + + /* Gdma Driver Capability Flags */ + u64 gd_drv_cap_flags1; + u64 gd_drv_cap_flags2; + u64 gd_drv_cap_flags3; + u64 gd_drv_cap_flags4; + + /* Advisory fields */ + u64 drv_ver; + u32 os_type; /* Linux = 0x10; Windows = 0x20; Other = 0x30 */ + u32 reserved; + u32 os_ver_major; + u32 os_ver_minor; + u32 os_ver_build; + u32 os_ver_platform; + u64 reserved_2; + u8 os_ver_str1[128]; + u8 os_ver_str2[128]; + u8 os_ver_str3[128]; + u8 os_ver_str4[128]; +}; /* HW DATA */ + +struct gdma_verify_ver_resp { + struct gdma_resp_hdr hdr; + u64 gdma_protocol_ver; + u64 pf_cap_flags1; + u64 pf_cap_flags2; + u64 pf_cap_flags3; + u64 pf_cap_flags4; +}; /* HW DATA */ + +/* GDMA_QUERY_MAX_RESOURCES */ +struct gdma_query_max_resources_resp { + struct gdma_resp_hdr hdr; + u32 status; + u32 max_sq; + u32 max_rq; + u32 max_cq; + u32 max_eq; + u32 max_db; + u32 max_mst; + u32 max_cq_mod_ctx; + u32 max_mod_cq; + u32 max_msix; +}; /* HW DATA */ + +/* GDMA_LIST_DEVICES */ +struct gdma_list_devices_resp { + struct gdma_resp_hdr hdr; + u32 num_of_devs; + u32 reserved; + struct gdma_dev_id devs[64]; +}; /* HW DATA */ + +/* GDMA_REGISTER_DEVICE */ +struct gdma_register_device_resp { + struct gdma_resp_hdr hdr; + u32 pdid; + u32 gpa_mkey; + u32 db_id; +}; /* HW DATA */ + +/* GDMA_CREATE_QUEUE */ +struct gdma_create_queue_req { + struct gdma_req_hdr hdr; + u32 type; + u32 reserved1; + u32 pdid; + u32 doolbell_id; + u64 gdma_region; + u32 reserved2; + u32 queue_size; + u32 log2_throttle_limit; + u32 eq_pci_msix_index; + u32 cq_mod_ctx_id; + u32 cq_parent_eq_id; + u8 rq_drop_on_overrun; + u8 rq_err_on_wqe_overflow; + u8 rq_chain_rec_wqes; + u8 sq_hw_db; + u32 reserved3; +}; /* HW DATA */ + +struct gdma_create_queue_resp { + struct gdma_resp_hdr hdr; + u32 queue_index; +}; /* HW DATA */ + +/* GDMA_DISABLE_QUEUE */ +struct gdma_disable_queue_req { + struct gdma_req_hdr hdr; + u32 type; + u32 queue_index; + u32 alloc_res_id_on_creation; +}; /* HW DATA */ + +/* GDMA_CREATE_DMA_REGION */ +struct gdma_create_dma_region_req { + struct gdma_req_hdr hdr; + + /* The total size of the DMA region */ + u64 length; + + /* The offset in the first page */ + u32 offset_in_page; + + /* enum gdma_page_type */ + u32 gdma_page_type; + + /* The total number of pages */ + u32 page_count; + + /* If page_addr_list_len is smaller than page_count, + * the remaining page addresses will be added via the + * message GDMA_DMA_REGION_ADD_PAGES. + */ + u32 page_addr_list_len; + u64 page_addr_list[]; +}; /* HW DATA */ + +struct gdma_create_dma_region_resp { + struct gdma_resp_hdr hdr; + u64 gdma_region; +}; /* HW DATA */ + +/* GDMA_DMA_REGION_ADD_PAGES */ +struct gdma_dma_region_add_pages_req { + struct gdma_req_hdr hdr; + + u64 gdma_region; + + u32 page_addr_list_len; + u32 reserved3; + + u64 page_addr_list[]; +}; /* HW DATA */ + +/* GDMA_DESTROY_DMA_REGION */ +struct gdma_destroy_dma_region_req { + struct gdma_req_hdr hdr; + + u64 gdma_region; +}; /* HW DATA */ + +int mana_gd_verify_vf_version(struct pci_dev *pdev); + +int mana_gd_register_device(struct gdma_dev *gd); +int mana_gd_deregister_device(struct gdma_dev *gd); + +int mana_gd_post_work_request(struct gdma_queue *wq, + const struct gdma_wqe_request *wqe_req, + struct gdma_posted_wqe_info *wqe_info); + +int mana_gd_post_and_ring(struct gdma_queue *queue, + const struct gdma_wqe_request *wqe, + struct gdma_posted_wqe_info *wqe_info); + +int mana_gd_alloc_res_map(u32 res_avail, struct gdma_resource *r); +void mana_gd_free_res_map(struct gdma_resource *r); + +void mana_gd_wq_ring_doorbell(struct gdma_context *gc, + struct gdma_queue *queue); + +int mana_gd_alloc_memory(struct gdma_context *gc, unsigned int length, + struct gdma_mem_info *gmi); + +void mana_gd_free_memory(struct gdma_mem_info *gmi); + +int mana_gd_send_request(struct gdma_context *gc, u32 req_len, const void *req, + u32 resp_len, void *resp); +#endif /* _GDMA_H */ diff --git a/include/net/mana/hw_channel.h b/include/net/mana/hw_channel.h new file mode 100644 index 000000000000..6a757a6e2732 --- /dev/null +++ b/include/net/mana/hw_channel.h @@ -0,0 +1,195 @@ +/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ +/* Copyright (c) 2021, Microsoft Corporation. */ + +#ifndef _HW_CHANNEL_H +#define _HW_CHANNEL_H + +#define DEFAULT_LOG2_THROTTLING_FOR_ERROR_EQ 4 + +#define HW_CHANNEL_MAX_REQUEST_SIZE 0x1000 +#define HW_CHANNEL_MAX_RESPONSE_SIZE 0x1000 + +#define HW_CHANNEL_VF_BOOTSTRAP_QUEUE_DEPTH 1 + +#define HWC_INIT_DATA_CQID 1 +#define HWC_INIT_DATA_RQID 2 +#define HWC_INIT_DATA_SQID 3 +#define HWC_INIT_DATA_QUEUE_DEPTH 4 +#define HWC_INIT_DATA_MAX_REQUEST 5 +#define HWC_INIT_DATA_MAX_RESPONSE 6 +#define HWC_INIT_DATA_MAX_NUM_CQS 7 +#define HWC_INIT_DATA_PDID 8 +#define HWC_INIT_DATA_GPA_MKEY 9 +#define HWC_INIT_DATA_PF_DEST_RQ_ID 10 +#define HWC_INIT_DATA_PF_DEST_CQ_ID 11 + +/* Structures labeled with "HW DATA" are exchanged with the hardware. All of + * them are naturally aligned and hence don't need __packed. + */ + +union hwc_init_eq_id_db { + u32 as_uint32; + + struct { + u32 eq_id : 16; + u32 doorbell : 16; + }; +}; /* HW DATA */ + +union hwc_init_type_data { + u32 as_uint32; + + struct { + u32 value : 24; + u32 type : 8; + }; +}; /* HW DATA */ + +struct hwc_rx_oob { + u32 type : 6; + u32 eom : 1; + u32 som : 1; + u32 vendor_err : 8; + u32 reserved1 : 16; + + u32 src_virt_wq : 24; + u32 src_vfid : 8; + + u32 reserved2; + + union { + u32 wqe_addr_low; + u32 wqe_offset; + }; + + u32 wqe_addr_high; + + u32 client_data_unit : 14; + u32 reserved3 : 18; + + u32 tx_oob_data_size; + + u32 chunk_offset : 21; + u32 reserved4 : 11; +}; /* HW DATA */ + +struct hwc_tx_oob { + u32 reserved1; + + u32 reserved2; + + u32 vrq_id : 24; + u32 dest_vfid : 8; + + u32 vrcq_id : 24; + u32 reserved3 : 8; + + u32 vscq_id : 24; + u32 loopback : 1; + u32 lso_override: 1; + u32 dest_pf : 1; + u32 reserved4 : 5; + + u32 vsq_id : 24; + u32 reserved5 : 8; +}; /* HW DATA */ + +struct hwc_work_request { + void *buf_va; + void *buf_sge_addr; + u32 buf_len; + u32 msg_size; + + struct gdma_wqe_request wqe_req; + struct hwc_tx_oob tx_oob; + + struct gdma_sge sge; +}; + +/* hwc_dma_buf represents the array of in-flight WQEs. + * mem_info as know as the GDMA mapped memory is partitioned and used by + * in-flight WQEs. + * The number of WQEs is determined by the number of in-flight messages. + */ +struct hwc_dma_buf { + struct gdma_mem_info mem_info; + + u32 gpa_mkey; + + u32 num_reqs; + struct hwc_work_request reqs[]; +}; + +typedef void hwc_rx_event_handler_t(void *ctx, u32 gdma_rxq_id, + const struct hwc_rx_oob *rx_oob); + +typedef void hwc_tx_event_handler_t(void *ctx, u32 gdma_txq_id, + const struct hwc_rx_oob *rx_oob); + +struct hwc_cq { + struct hw_channel_context *hwc; + + struct gdma_queue *gdma_cq; + struct gdma_queue *gdma_eq; + struct gdma_comp *comp_buf; + u16 queue_depth; + + hwc_rx_event_handler_t *rx_event_handler; + void *rx_event_ctx; + + hwc_tx_event_handler_t *tx_event_handler; + void *tx_event_ctx; +}; + +struct hwc_wq { + struct hw_channel_context *hwc; + + struct gdma_queue *gdma_wq; + struct hwc_dma_buf *msg_buf; + u16 queue_depth; + + struct hwc_cq *hwc_cq; +}; + +struct hwc_caller_ctx { + struct completion comp_event; + void *output_buf; + u32 output_buflen; + + u32 error; /* Linux error code */ + u32 status_code; +}; + +struct hw_channel_context { + struct gdma_dev *gdma_dev; + struct device *dev; + + u16 num_inflight_msg; + u32 max_req_msg_size; + + u16 hwc_init_q_depth_max; + u32 hwc_init_max_req_msg_size; + u32 hwc_init_max_resp_msg_size; + + struct completion hwc_init_eqe_comp; + + struct hwc_wq *rxq; + struct hwc_wq *txq; + struct hwc_cq *cq; + + struct semaphore sema; + struct gdma_resource inflight_msg_res; + + u32 pf_dest_vrq_id; + u32 pf_dest_vrcq_id; + + struct hwc_caller_ctx *caller_ctx; +}; + +int mana_hwc_create_channel(struct gdma_context *gc); +void mana_hwc_destroy_channel(struct gdma_context *gc); + +int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len, + const void *req, u32 resp_len, void *resp); + +#endif /* _HW_CHANNEL_H */ diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h new file mode 100644 index 000000000000..6e9e86fb4c02 --- /dev/null +++ b/include/net/mana/mana.h @@ -0,0 +1,650 @@ +/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ +/* Copyright (c) 2021, Microsoft Corporation. */ + +#ifndef _MANA_H +#define _MANA_H + +#include "gdma.h" +#include "hw_channel.h" + +/* Microsoft Azure Network Adapter (MANA)'s definitions + * + * Structures labeled with "HW DATA" are exchanged with the hardware. All of + * them are naturally aligned and hence don't need __packed. + */ + +/* MANA protocol version */ +#define MANA_MAJOR_VERSION 0 +#define MANA_MINOR_VERSION 1 +#define MANA_MICRO_VERSION 1 + +typedef u64 mana_handle_t; +#define INVALID_MANA_HANDLE ((mana_handle_t)-1) + +enum TRI_STATE { + TRI_STATE_UNKNOWN = -1, + TRI_STATE_FALSE = 0, + TRI_STATE_TRUE = 1 +}; + +/* Number of entries for hardware indirection table must be in power of 2 */ +#define MANA_INDIRECT_TABLE_SIZE 64 +#define MANA_INDIRECT_TABLE_MASK (MANA_INDIRECT_TABLE_SIZE - 1) + +/* The Toeplitz hash key's length in bytes: should be multiple of 8 */ +#define MANA_HASH_KEY_SIZE 40 + +#define COMP_ENTRY_SIZE 64 + +#define ADAPTER_MTU_SIZE 1500 +#define MAX_FRAME_SIZE (ADAPTER_MTU_SIZE + 14) + +#define RX_BUFFERS_PER_QUEUE 512 + +#define MAX_SEND_BUFFERS_PER_QUEUE 256 + +#define EQ_SIZE (8 * PAGE_SIZE) +#define LOG2_EQ_THROTTLE 3 + +#define MAX_PORTS_IN_MANA_DEV 256 + +struct mana_stats_rx { + u64 packets; + u64 bytes; + u64 xdp_drop; + u64 xdp_tx; + u64 xdp_redirect; + struct u64_stats_sync syncp; +}; + +struct mana_stats_tx { + u64 packets; + u64 bytes; + u64 xdp_xmit; + struct u64_stats_sync syncp; +}; + +struct mana_txq { + struct gdma_queue *gdma_sq; + + union { + u32 gdma_txq_id; + struct { + u32 reserved1 : 10; + u32 vsq_frame : 14; + u32 reserved2 : 8; + }; + }; + + u16 vp_offset; + + struct net_device *ndev; + + /* The SKBs are sent to the HW and we are waiting for the CQEs. */ + struct sk_buff_head pending_skbs; + struct netdev_queue *net_txq; + + atomic_t pending_sends; + + struct mana_stats_tx stats; +}; + +/* skb data and frags dma mappings */ +struct mana_skb_head { + dma_addr_t dma_handle[MAX_SKB_FRAGS + 1]; + + u32 size[MAX_SKB_FRAGS + 1]; +}; + +#define MANA_HEADROOM sizeof(struct mana_skb_head) + +enum mana_tx_pkt_format { + MANA_SHORT_PKT_FMT = 0, + MANA_LONG_PKT_FMT = 1, +}; + +struct mana_tx_short_oob { + u32 pkt_fmt : 2; + u32 is_outer_ipv4 : 1; + u32 is_outer_ipv6 : 1; + u32 comp_iphdr_csum : 1; + u32 comp_tcp_csum : 1; + u32 comp_udp_csum : 1; + u32 supress_txcqe_gen : 1; + u32 vcq_num : 24; + + u32 trans_off : 10; /* Transport header offset */ + u32 vsq_frame : 14; + u32 short_vp_offset : 8; +}; /* HW DATA */ + +struct mana_tx_long_oob { + u32 is_encap : 1; + u32 inner_is_ipv6 : 1; + u32 inner_tcp_opt : 1; + u32 inject_vlan_pri_tag : 1; + u32 reserved1 : 12; + u32 pcp : 3; /* 802.1Q */ + u32 dei : 1; /* 802.1Q */ + u32 vlan_id : 12; /* 802.1Q */ + + u32 inner_frame_offset : 10; + u32 inner_ip_rel_offset : 6; + u32 long_vp_offset : 12; + u32 reserved2 : 4; + + u32 reserved3; + u32 reserved4; +}; /* HW DATA */ + +struct mana_tx_oob { + struct mana_tx_short_oob s_oob; + struct mana_tx_long_oob l_oob; +}; /* HW DATA */ + +enum mana_cq_type { + MANA_CQ_TYPE_RX, + MANA_CQ_TYPE_TX, +}; + +enum mana_cqe_type { + CQE_INVALID = 0, + CQE_RX_OKAY = 1, + CQE_RX_COALESCED_4 = 2, + CQE_RX_OBJECT_FENCE = 3, + CQE_RX_TRUNCATED = 4, + + CQE_TX_OKAY = 32, + CQE_TX_SA_DROP = 33, + CQE_TX_MTU_DROP = 34, + CQE_TX_INVALID_OOB = 35, + CQE_TX_INVALID_ETH_TYPE = 36, + CQE_TX_HDR_PROCESSING_ERROR = 37, + CQE_TX_VF_DISABLED = 38, + CQE_TX_VPORT_IDX_OUT_OF_RANGE = 39, + CQE_TX_VPORT_DISABLED = 40, + CQE_TX_VLAN_TAGGING_VIOLATION = 41, +}; + +#define MANA_CQE_COMPLETION 1 + +struct mana_cqe_header { + u32 cqe_type : 6; + u32 client_type : 2; + u32 vendor_err : 24; +}; /* HW DATA */ + +/* NDIS HASH Types */ +#define NDIS_HASH_IPV4 BIT(0) +#define NDIS_HASH_TCP_IPV4 BIT(1) +#define NDIS_HASH_UDP_IPV4 BIT(2) +#define NDIS_HASH_IPV6 BIT(3) +#define NDIS_HASH_TCP_IPV6 BIT(4) +#define NDIS_HASH_UDP_IPV6 BIT(5) +#define NDIS_HASH_IPV6_EX BIT(6) +#define NDIS_HASH_TCP_IPV6_EX BIT(7) +#define NDIS_HASH_UDP_IPV6_EX BIT(8) + +#define MANA_HASH_L3 (NDIS_HASH_IPV4 | NDIS_HASH_IPV6 | NDIS_HASH_IPV6_EX) +#define MANA_HASH_L4 \ + (NDIS_HASH_TCP_IPV4 | NDIS_HASH_UDP_IPV4 | NDIS_HASH_TCP_IPV6 | \ + NDIS_HASH_UDP_IPV6 | NDIS_HASH_TCP_IPV6_EX | NDIS_HASH_UDP_IPV6_EX) + +struct mana_rxcomp_perpkt_info { + u32 pkt_len : 16; + u32 reserved1 : 16; + u32 reserved2; + u32 pkt_hash; +}; /* HW DATA */ + +#define MANA_RXCOMP_OOB_NUM_PPI 4 + +/* Receive completion OOB */ +struct mana_rxcomp_oob { + struct mana_cqe_header cqe_hdr; + + u32 rx_vlan_id : 12; + u32 rx_vlantag_present : 1; + u32 rx_outer_iphdr_csum_succeed : 1; + u32 rx_outer_iphdr_csum_fail : 1; + u32 reserved1 : 1; + u32 rx_hashtype : 9; + u32 rx_iphdr_csum_succeed : 1; + u32 rx_iphdr_csum_fail : 1; + u32 rx_tcp_csum_succeed : 1; + u32 rx_tcp_csum_fail : 1; + u32 rx_udp_csum_succeed : 1; + u32 rx_udp_csum_fail : 1; + u32 reserved2 : 1; + + struct mana_rxcomp_perpkt_info ppi[MANA_RXCOMP_OOB_NUM_PPI]; + + u32 rx_wqe_offset; +}; /* HW DATA */ + +struct mana_tx_comp_oob { + struct mana_cqe_header cqe_hdr; + + u32 tx_data_offset; + + u32 tx_sgl_offset : 5; + u32 tx_wqe_offset : 27; + + u32 reserved[12]; +}; /* HW DATA */ + +struct mana_rxq; + +#define CQE_POLLING_BUFFER 512 + +struct mana_cq { + struct gdma_queue *gdma_cq; + + /* Cache the CQ id (used to verify if each CQE comes to the right CQ. */ + u32 gdma_id; + + /* Type of the CQ: TX or RX */ + enum mana_cq_type type; + + /* Pointer to the mana_rxq that is pushing RX CQEs to the queue. + * Only and must be non-NULL if type is MANA_CQ_TYPE_RX. + */ + struct mana_rxq *rxq; + + /* Pointer to the mana_txq that is pushing TX CQEs to the queue. + * Only and must be non-NULL if type is MANA_CQ_TYPE_TX. + */ + struct mana_txq *txq; + + /* Buffer which the CQ handler can copy the CQE's into. */ + struct gdma_comp gdma_comp_buf[CQE_POLLING_BUFFER]; + + /* NAPI data */ + struct napi_struct napi; + int work_done; + int budget; +}; + +#define GDMA_MAX_RQE_SGES 15 + +struct mana_recv_buf_oob { + /* A valid GDMA work request representing the data buffer. */ + struct gdma_wqe_request wqe_req; + + void *buf_va; + dma_addr_t buf_dma_addr; + + /* SGL of the buffer going to be sent has part of the work request. */ + u32 num_sge; + struct gdma_sge sgl[GDMA_MAX_RQE_SGES]; + + /* Required to store the result of mana_gd_post_work_request. + * gdma_posted_wqe_info.wqe_size_in_bu is required for progressing the + * work queue when the WQE is consumed. + */ + struct gdma_posted_wqe_info wqe_inf; +}; + +struct mana_rxq { + struct gdma_queue *gdma_rq; + /* Cache the gdma receive queue id */ + u32 gdma_id; + + /* Index of RQ in the vPort, not gdma receive queue id */ + u32 rxq_idx; + + u32 datasize; + + mana_handle_t rxobj; + + struct mana_cq rx_cq; + + struct completion fence_event; + + struct net_device *ndev; + + /* Total number of receive buffers to be allocated */ + u32 num_rx_buf; + + u32 buf_index; + + struct mana_stats_rx stats; + + struct bpf_prog __rcu *bpf_prog; + struct xdp_rxq_info xdp_rxq; + struct page *xdp_save_page; + bool xdp_flush; + int xdp_rc; /* XDP redirect return code */ + + /* MUST BE THE LAST MEMBER: + * Each receive buffer has an associated mana_recv_buf_oob. + */ + struct mana_recv_buf_oob rx_oobs[]; +}; + +struct mana_tx_qp { + struct mana_txq txq; + + struct mana_cq tx_cq; + + mana_handle_t tx_object; +}; + +struct mana_ethtool_stats { + u64 stop_queue; + u64 wake_queue; +}; + +struct mana_context { + struct gdma_dev *gdma_dev; + + u16 num_ports; + + struct mana_eq *eqs; + + struct net_device *ports[MAX_PORTS_IN_MANA_DEV]; +}; + +struct mana_port_context { + struct mana_context *ac; + struct net_device *ndev; + + u8 mac_addr[ETH_ALEN]; + + enum TRI_STATE rss_state; + + mana_handle_t default_rxobj; + bool tx_shortform_allowed; + u16 tx_vp_offset; + + struct mana_tx_qp *tx_qp; + + /* Indirection Table for RX & TX. The values are queue indexes */ + u32 indir_table[MANA_INDIRECT_TABLE_SIZE]; + + /* Indirection table containing RxObject Handles */ + mana_handle_t rxobj_table[MANA_INDIRECT_TABLE_SIZE]; + + /* Hash key used by the NIC */ + u8 hashkey[MANA_HASH_KEY_SIZE]; + + /* This points to an array of num_queues of RQ pointers. */ + struct mana_rxq **rxqs; + + struct bpf_prog *bpf_prog; + + /* Create num_queues EQs, SQs, SQ-CQs, RQs and RQ-CQs, respectively. */ + unsigned int max_queues; + unsigned int num_queues; + + mana_handle_t port_handle; + mana_handle_t pf_filter_handle; + + /* Mutex for sharing access to vport_use_count */ + struct mutex vport_mutex; + int vport_use_count; + + u16 port_idx; + + bool port_is_up; + bool port_st_save; /* Saved port state */ + + struct mana_ethtool_stats eth_stats; +}; + +int mana_start_xmit(struct sk_buff *skb, struct net_device *ndev); +int mana_config_rss(struct mana_port_context *ac, enum TRI_STATE rx, + bool update_hash, bool update_tab); + +int mana_alloc_queues(struct net_device *ndev); +int mana_attach(struct net_device *ndev); +int mana_detach(struct net_device *ndev, bool from_close); + +int mana_probe(struct gdma_dev *gd, bool resuming); +void mana_remove(struct gdma_dev *gd, bool suspending); + +void mana_xdp_tx(struct sk_buff *skb, struct net_device *ndev); +int mana_xdp_xmit(struct net_device *ndev, int n, struct xdp_frame **frames, + u32 flags); +u32 mana_run_xdp(struct net_device *ndev, struct mana_rxq *rxq, + struct xdp_buff *xdp, void *buf_va, uint pkt_len); +struct bpf_prog *mana_xdp_get(struct mana_port_context *apc); +void mana_chn_setxdp(struct mana_port_context *apc, struct bpf_prog *prog); +int mana_bpf(struct net_device *ndev, struct netdev_bpf *bpf); + +extern const struct ethtool_ops mana_ethtool_ops; + +struct mana_obj_spec { + u32 queue_index; + u64 gdma_region; + u32 queue_size; + u32 attached_eq; + u32 modr_ctx_id; +}; + +enum mana_command_code { + MANA_QUERY_DEV_CONFIG = 0x20001, + MANA_QUERY_GF_STAT = 0x20002, + MANA_CONFIG_VPORT_TX = 0x20003, + MANA_CREATE_WQ_OBJ = 0x20004, + MANA_DESTROY_WQ_OBJ = 0x20005, + MANA_FENCE_RQ = 0x20006, + MANA_CONFIG_VPORT_RX = 0x20007, + MANA_QUERY_VPORT_CONFIG = 0x20008, + + /* Privileged commands for the PF mode */ + MANA_REGISTER_FILTER = 0x28000, + MANA_DEREGISTER_FILTER = 0x28001, + MANA_REGISTER_HW_PORT = 0x28003, + MANA_DEREGISTER_HW_PORT = 0x28004, +}; + +/* Query Device Configuration */ +struct mana_query_device_cfg_req { + struct gdma_req_hdr hdr; + + /* MANA Nic Driver Capability flags */ + u64 mn_drv_cap_flags1; + u64 mn_drv_cap_flags2; + u64 mn_drv_cap_flags3; + u64 mn_drv_cap_flags4; + + u32 proto_major_ver; + u32 proto_minor_ver; + u32 proto_micro_ver; + + u32 reserved; +}; /* HW DATA */ + +struct mana_query_device_cfg_resp { + struct gdma_resp_hdr hdr; + + u64 pf_cap_flags1; + u64 pf_cap_flags2; + u64 pf_cap_flags3; + u64 pf_cap_flags4; + + u16 max_num_vports; + u16 reserved; + u32 max_num_eqs; +}; /* HW DATA */ + +/* Query vPort Configuration */ +struct mana_query_vport_cfg_req { + struct gdma_req_hdr hdr; + u32 vport_index; +}; /* HW DATA */ + +struct mana_query_vport_cfg_resp { + struct gdma_resp_hdr hdr; + u32 max_num_sq; + u32 max_num_rq; + u32 num_indirection_ent; + u32 reserved1; + u8 mac_addr[6]; + u8 reserved2[2]; + mana_handle_t vport; +}; /* HW DATA */ + +/* Configure vPort */ +struct mana_config_vport_req { + struct gdma_req_hdr hdr; + mana_handle_t vport; + u32 pdid; + u32 doorbell_pageid; +}; /* HW DATA */ + +struct mana_config_vport_resp { + struct gdma_resp_hdr hdr; + u16 tx_vport_offset; + u8 short_form_allowed; + u8 reserved; +}; /* HW DATA */ + +/* Create WQ Object */ +struct mana_create_wqobj_req { + struct gdma_req_hdr hdr; + mana_handle_t vport; + u32 wq_type; + u32 reserved; + u64 wq_gdma_region; + u64 cq_gdma_region; + u32 wq_size; + u32 cq_size; + u32 cq_moderation_ctx_id; + u32 cq_parent_qid; +}; /* HW DATA */ + +struct mana_create_wqobj_resp { + struct gdma_resp_hdr hdr; + u32 wq_id; + u32 cq_id; + mana_handle_t wq_obj; +}; /* HW DATA */ + +/* Destroy WQ Object */ +struct mana_destroy_wqobj_req { + struct gdma_req_hdr hdr; + u32 wq_type; + u32 reserved; + mana_handle_t wq_obj_handle; +}; /* HW DATA */ + +struct mana_destroy_wqobj_resp { + struct gdma_resp_hdr hdr; +}; /* HW DATA */ + +/* Fence RQ */ +struct mana_fence_rq_req { + struct gdma_req_hdr hdr; + mana_handle_t wq_obj_handle; +}; /* HW DATA */ + +struct mana_fence_rq_resp { + struct gdma_resp_hdr hdr; +}; /* HW DATA */ + +/* Configure vPort Rx Steering */ +struct mana_cfg_rx_steer_req { + struct gdma_req_hdr hdr; + mana_handle_t vport; + u16 num_indir_entries; + u16 indir_tab_offset; + u32 rx_enable; + u32 rss_enable; + u8 update_default_rxobj; + u8 update_hashkey; + u8 update_indir_tab; + u8 reserved; + mana_handle_t default_rxobj; + u8 hashkey[MANA_HASH_KEY_SIZE]; +}; /* HW DATA */ + +struct mana_cfg_rx_steer_resp { + struct gdma_resp_hdr hdr; +}; /* HW DATA */ + +/* Register HW vPort */ +struct mana_register_hw_vport_req { + struct gdma_req_hdr hdr; + u16 attached_gfid; + u8 is_pf_default_vport; + u8 reserved1; + u8 allow_all_ether_types; + u8 reserved2; + u8 reserved3; + u8 reserved4; +}; /* HW DATA */ + +struct mana_register_hw_vport_resp { + struct gdma_resp_hdr hdr; + mana_handle_t hw_vport_handle; +}; /* HW DATA */ + +/* Deregister HW vPort */ +struct mana_deregister_hw_vport_req { + struct gdma_req_hdr hdr; + mana_handle_t hw_vport_handle; +}; /* HW DATA */ + +struct mana_deregister_hw_vport_resp { + struct gdma_resp_hdr hdr; +}; /* HW DATA */ + +/* Register filter */ +struct mana_register_filter_req { + struct gdma_req_hdr hdr; + mana_handle_t vport; + u8 mac_addr[6]; + u8 reserved1; + u8 reserved2; + u8 reserved3; + u8 reserved4; + u16 reserved5; + u32 reserved6; + u32 reserved7; + u32 reserved8; +}; /* HW DATA */ + +struct mana_register_filter_resp { + struct gdma_resp_hdr hdr; + mana_handle_t filter_handle; +}; /* HW DATA */ + +/* Deregister filter */ +struct mana_deregister_filter_req { + struct gdma_req_hdr hdr; + mana_handle_t filter_handle; +}; /* HW DATA */ + +struct mana_deregister_filter_resp { + struct gdma_resp_hdr hdr; +}; /* HW DATA */ + +#define MANA_MAX_NUM_QUEUES 64 + +#define MANA_SHORT_VPORT_OFFSET_MAX ((1U << 8) - 1) + +struct mana_tx_package { + struct gdma_wqe_request wqe_req; + struct gdma_sge sgl_array[5]; + struct gdma_sge *sgl_ptr; + + struct mana_tx_oob tx_oob; + + struct gdma_posted_wqe_info wqe_info; +}; + +int mana_create_wq_obj(struct mana_port_context *apc, + mana_handle_t vport, + u32 wq_type, struct mana_obj_spec *wq_spec, + struct mana_obj_spec *cq_spec, + mana_handle_t *wq_obj); + +void mana_destroy_wq_obj(struct mana_port_context *apc, u32 wq_type, + mana_handle_t wq_obj); + +int mana_cfg_vport(struct mana_port_context *apc, u32 protection_dom_id, + u32 doorbell_pg_id); +void mana_uncfg_vport(struct mana_port_context *apc); +#endif /* _MANA_H */ diff --git a/include/net/mana/mana_auxiliary.h b/include/net/mana/mana_auxiliary.h new file mode 100644 index 000000000000..373d59756846 --- /dev/null +++ b/include/net/mana/mana_auxiliary.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (c) 2022, Microsoft Corporation. */ + +#include "mana.h" +#include + +struct mana_adev { + struct auxiliary_device adev; + struct gdma_dev *mdev; +}; diff --git a/include/net/mana/shm_channel.h b/include/net/mana/shm_channel.h new file mode 100644 index 000000000000..5199b41497ff --- /dev/null +++ b/include/net/mana/shm_channel.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ +/* Copyright (c) 2021, Microsoft Corporation. */ + +#ifndef _SHM_CHANNEL_H +#define _SHM_CHANNEL_H + +struct shm_channel { + struct device *dev; + void __iomem *base; +}; + +void mana_smc_init(struct shm_channel *sc, struct device *dev, + void __iomem *base); + +int mana_smc_setup_hwc(struct shm_channel *sc, bool reset_vf, u64 eq_addr, + u64 cq_addr, u64 rq_addr, u64 sq_addr, + u32 eq_msix_index); + +int mana_smc_teardown_hwc(struct shm_channel *sc, bool reset_vf); + +#endif /* _SHM_CHANNEL_H */ -- cgit v1.2.3 From aa56549792fb348892fbbae67f6f0c71bb750b65 Mon Sep 17 00:00:00 2001 From: Long Li Date: Thu, 3 Nov 2022 12:16:26 -0700 Subject: net: mana: Define max values for SGL entries The number of maximum SGl entries should be computed from the maximum WQE size for the intended queue type and the corresponding OOB data size. This guarantees the hardware queue can successfully queue requests up to the queue depth exposed to the upper layer. Reviewed-by: Dexuan Cui Signed-off-by: Long Li Link: https://lore.kernel.org/r/1667502990-2559-9-git-send-email-longli@linuxonhyperv.com Acked-by: Haiyang Zhang Signed-off-by: Leon Romanovsky --- drivers/net/ethernet/microsoft/mana/mana_en.c | 2 +- include/net/mana/gdma.h | 7 +++++++ include/net/mana/mana.h | 4 +--- 3 files changed, 9 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index ffa2a0e2c213..f6bcd0cc6cda 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -189,7 +189,7 @@ int mana_start_xmit(struct sk_buff *skb, struct net_device *ndev) pkg.wqe_req.client_data_unit = 0; pkg.wqe_req.num_sge = 1 + skb_shinfo(skb)->nr_frags; - WARN_ON_ONCE(pkg.wqe_req.num_sge > 30); + WARN_ON_ONCE(pkg.wqe_req.num_sge > MAX_TX_WQE_SGL_ENTRIES); if (pkg.wqe_req.num_sge <= ARRAY_SIZE(pkg.sgl_array)) { pkg.wqe_req.sgl = pkg.sgl_array; diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h index 72eaec2470c0..0b0c0cd0b6bd 100644 --- a/include/net/mana/gdma.h +++ b/include/net/mana/gdma.h @@ -427,6 +427,13 @@ struct gdma_wqe { #define MAX_TX_WQE_SIZE 512 #define MAX_RX_WQE_SIZE 256 +#define MAX_TX_WQE_SGL_ENTRIES ((GDMA_MAX_SQE_SIZE - \ + sizeof(struct gdma_sge) - INLINE_OOB_SMALL_SIZE) / \ + sizeof(struct gdma_sge)) + +#define MAX_RX_WQE_SGL_ENTRIES ((GDMA_MAX_RQE_SIZE - \ + sizeof(struct gdma_sge)) / sizeof(struct gdma_sge)) + struct gdma_cqe { u32 cqe_data[GDMA_COMP_DATA_SIZE / 4]; diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index 6e9e86fb4c02..713a8f8cca9a 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -265,8 +265,6 @@ struct mana_cq { int budget; }; -#define GDMA_MAX_RQE_SGES 15 - struct mana_recv_buf_oob { /* A valid GDMA work request representing the data buffer. */ struct gdma_wqe_request wqe_req; @@ -276,7 +274,7 @@ struct mana_recv_buf_oob { /* SGL of the buffer going to be sent has part of the work request. */ u32 num_sge; - struct gdma_sge sgl[GDMA_MAX_RQE_SGES]; + struct gdma_sge sgl[MAX_RX_WQE_SGL_ENTRIES]; /* Required to store the result of mana_gd_post_work_request. * gdma_posted_wqe_info.wqe_size_in_bu is required for progressing the -- cgit v1.2.3 From de372f2a9ca7ada2698ecac7df8f02407cd98fa0 Mon Sep 17 00:00:00 2001 From: Ajay Sharma Date: Thu, 3 Nov 2022 12:16:27 -0700 Subject: net: mana: Define and process GDMA response code GDMA_STATUS_MORE_ENTRIES When doing memory registration, the PF may respond with GDMA_STATUS_MORE_ENTRIES to indicate a follow request is needed. This is not an error and should be processed as expected. Signed-off-by: Ajay Sharma Reviewed-by: Dexuan Cui Signed-off-by: Long Li Link: https://lore.kernel.org/r/1667502990-2559-10-git-send-email-longli@linuxonhyperv.com Acked-by: Haiyang Zhang Signed-off-by: Leon Romanovsky --- drivers/net/ethernet/microsoft/mana/hw_channel.c | 2 +- include/net/mana/gdma.h | 2 ++ 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c index 76829ab43d40..9d1507eba5b9 100644 --- a/drivers/net/ethernet/microsoft/mana/hw_channel.c +++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c @@ -836,7 +836,7 @@ int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len, goto out; } - if (ctx->status_code) { + if (ctx->status_code && ctx->status_code != GDMA_STATUS_MORE_ENTRIES) { dev_err(hwc->dev, "HWC: Failed hw_channel req: 0x%x\n", ctx->status_code); err = -EPROTO; diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h index 0b0c0cd0b6bd..a9b7930dfbf8 100644 --- a/include/net/mana/gdma.h +++ b/include/net/mana/gdma.h @@ -9,6 +9,8 @@ #include "shm_channel.h" +#define GDMA_STATUS_MORE_ENTRIES 0x00000105 + /* Structures labeled with "HW DATA" are exchanged with the hardware. All of * them are naturally aligned and hence don't need __packed. */ -- cgit v1.2.3 From f72ececfc197e9b0bbb5595294908a950cf444fa Mon Sep 17 00:00:00 2001 From: Long Li Date: Thu, 3 Nov 2022 12:16:28 -0700 Subject: net: mana: Define data structures for allocating doorbell page from GDMA The RDMA device needs to allocate doorbell pages for each user context. Define the GDMA data structures for use by the RDMA driver. Reviewed-by: Dexuan Cui Signed-off-by: Long Li Link: https://lore.kernel.org/r/1667502990-2559-11-git-send-email-longli@linuxonhyperv.com Acked-by: Haiyang Zhang Signed-off-by: Leon Romanovsky --- include/net/mana/gdma.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include') diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h index a9b7930dfbf8..055408a5baf3 100644 --- a/include/net/mana/gdma.h +++ b/include/net/mana/gdma.h @@ -24,11 +24,15 @@ enum gdma_request_type { GDMA_GENERATE_TEST_EQE = 10, GDMA_CREATE_QUEUE = 12, GDMA_DISABLE_QUEUE = 13, + GDMA_ALLOCATE_RESOURCE_RANGE = 22, + GDMA_DESTROY_RESOURCE_RANGE = 24, GDMA_CREATE_DMA_REGION = 25, GDMA_DMA_REGION_ADD_PAGES = 26, GDMA_DESTROY_DMA_REGION = 27, }; +#define GDMA_RESOURCE_DOORBELL_PAGE 27 + enum gdma_queue_type { GDMA_INVALID_QUEUE, GDMA_SQ, @@ -587,6 +591,26 @@ struct gdma_register_device_resp { u32 db_id; }; /* HW DATA */ +struct gdma_allocate_resource_range_req { + struct gdma_req_hdr hdr; + u32 resource_type; + u32 num_resources; + u32 alignment; + u32 allocated_resources; +}; + +struct gdma_allocate_resource_range_resp { + struct gdma_resp_hdr hdr; + u32 allocated_resources; +}; + +struct gdma_destroy_resource_range_req { + struct gdma_req_hdr hdr; + u32 resource_type; + u32 num_resources; + u32 allocated_resources; +}; + /* GDMA_CREATE_QUEUE */ struct gdma_create_queue_req { struct gdma_req_hdr hdr; -- cgit v1.2.3 From 28c66cfa45388af1126985d1114e0ed762eb2abd Mon Sep 17 00:00:00 2001 From: Ajay Sharma Date: Thu, 3 Nov 2022 12:16:29 -0700 Subject: net: mana: Define data structures for protection domain and memory registration The MANA hardware support protection domain and memory registration for use in RDMA environment. Add those definitions and expose them for use by the RDMA driver. Signed-off-by: Ajay Sharma Signed-off-by: Long Li Link: https://lore.kernel.org/r/1667502990-2559-12-git-send-email-longli@linuxonhyperv.com Reviewed-by: Dexuan Cui Acked-by: Haiyang Zhang Signed-off-by: Leon Romanovsky --- drivers/net/ethernet/microsoft/mana/gdma_main.c | 27 ++++-- drivers/net/ethernet/microsoft/mana/mana_en.c | 18 ++-- include/net/mana/gdma.h | 121 +++++++++++++++++++++++- 3 files changed, 143 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index 69795bc679e7..46a7d1e6ece9 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -198,7 +198,7 @@ static int mana_gd_create_hw_eq(struct gdma_context *gc, req.type = queue->type; req.pdid = queue->gdma_dev->pdid; req.doolbell_id = queue->gdma_dev->doorbell; - req.gdma_region = queue->mem_info.gdma_region; + req.gdma_region = queue->mem_info.dma_region_handle; req.queue_size = queue->queue_size; req.log2_throttle_limit = queue->eq.log2_throttle_limit; req.eq_pci_msix_index = queue->eq.msix_index; @@ -212,7 +212,7 @@ static int mana_gd_create_hw_eq(struct gdma_context *gc, queue->id = resp.queue_index; queue->eq.disable_needed = true; - queue->mem_info.gdma_region = GDMA_INVALID_DMA_REGION; + queue->mem_info.dma_region_handle = GDMA_INVALID_DMA_REGION; return 0; } @@ -671,24 +671,30 @@ free_q: return err; } -static void mana_gd_destroy_dma_region(struct gdma_context *gc, u64 gdma_region) +int mana_gd_destroy_dma_region(struct gdma_context *gc, + gdma_obj_handle_t dma_region_handle) { struct gdma_destroy_dma_region_req req = {}; struct gdma_general_resp resp = {}; int err; - if (gdma_region == GDMA_INVALID_DMA_REGION) - return; + if (dma_region_handle == GDMA_INVALID_DMA_REGION) + return 0; mana_gd_init_req_hdr(&req.hdr, GDMA_DESTROY_DMA_REGION, sizeof(req), sizeof(resp)); - req.gdma_region = gdma_region; + req.dma_region_handle = dma_region_handle; err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp); - if (err || resp.hdr.status) + if (err || resp.hdr.status) { dev_err(gc->dev, "Failed to destroy DMA region: %d, 0x%x\n", err, resp.hdr.status); + return -EPROTO; + } + + return 0; } +EXPORT_SYMBOL_NS(mana_gd_destroy_dma_region, NET_MANA); static int mana_gd_create_dma_region(struct gdma_dev *gd, struct gdma_mem_info *gmi) @@ -733,14 +739,15 @@ static int mana_gd_create_dma_region(struct gdma_dev *gd, if (err) goto out; - if (resp.hdr.status || resp.gdma_region == GDMA_INVALID_DMA_REGION) { + if (resp.hdr.status || + resp.dma_region_handle == GDMA_INVALID_DMA_REGION) { dev_err(gc->dev, "Failed to create DMA region: 0x%x\n", resp.hdr.status); err = -EPROTO; goto out; } - gmi->gdma_region = resp.gdma_region; + gmi->dma_region_handle = resp.dma_region_handle; out: kfree(req); return err; @@ -863,7 +870,7 @@ void mana_gd_destroy_queue(struct gdma_context *gc, struct gdma_queue *queue) return; } - mana_gd_destroy_dma_region(gc, gmi->gdma_region); + mana_gd_destroy_dma_region(gc, gmi->dma_region_handle); mana_gd_free_memory(gmi); kfree(queue); } diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index f6bcd0cc6cda..1c59502d34b5 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -1523,10 +1523,10 @@ static int mana_create_txq(struct mana_port_context *apc, memset(&wq_spec, 0, sizeof(wq_spec)); memset(&cq_spec, 0, sizeof(cq_spec)); - wq_spec.gdma_region = txq->gdma_sq->mem_info.gdma_region; + wq_spec.gdma_region = txq->gdma_sq->mem_info.dma_region_handle; wq_spec.queue_size = txq->gdma_sq->queue_size; - cq_spec.gdma_region = cq->gdma_cq->mem_info.gdma_region; + cq_spec.gdma_region = cq->gdma_cq->mem_info.dma_region_handle; cq_spec.queue_size = cq->gdma_cq->queue_size; cq_spec.modr_ctx_id = 0; cq_spec.attached_eq = cq->gdma_cq->cq.parent->id; @@ -1541,8 +1541,10 @@ static int mana_create_txq(struct mana_port_context *apc, txq->gdma_sq->id = wq_spec.queue_index; cq->gdma_cq->id = cq_spec.queue_index; - txq->gdma_sq->mem_info.gdma_region = GDMA_INVALID_DMA_REGION; - cq->gdma_cq->mem_info.gdma_region = GDMA_INVALID_DMA_REGION; + txq->gdma_sq->mem_info.dma_region_handle = + GDMA_INVALID_DMA_REGION; + cq->gdma_cq->mem_info.dma_region_handle = + GDMA_INVALID_DMA_REGION; txq->gdma_txq_id = txq->gdma_sq->id; @@ -1753,10 +1755,10 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc, memset(&wq_spec, 0, sizeof(wq_spec)); memset(&cq_spec, 0, sizeof(cq_spec)); - wq_spec.gdma_region = rxq->gdma_rq->mem_info.gdma_region; + wq_spec.gdma_region = rxq->gdma_rq->mem_info.dma_region_handle; wq_spec.queue_size = rxq->gdma_rq->queue_size; - cq_spec.gdma_region = cq->gdma_cq->mem_info.gdma_region; + cq_spec.gdma_region = cq->gdma_cq->mem_info.dma_region_handle; cq_spec.queue_size = cq->gdma_cq->queue_size; cq_spec.modr_ctx_id = 0; cq_spec.attached_eq = cq->gdma_cq->cq.parent->id; @@ -1769,8 +1771,8 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc, rxq->gdma_rq->id = wq_spec.queue_index; cq->gdma_cq->id = cq_spec.queue_index; - rxq->gdma_rq->mem_info.gdma_region = GDMA_INVALID_DMA_REGION; - cq->gdma_cq->mem_info.gdma_region = GDMA_INVALID_DMA_REGION; + rxq->gdma_rq->mem_info.dma_region_handle = GDMA_INVALID_DMA_REGION; + cq->gdma_cq->mem_info.dma_region_handle = GDMA_INVALID_DMA_REGION; rxq->gdma_id = rxq->gdma_rq->id; cq->gdma_id = cq->gdma_cq->id; diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h index 055408a5baf3..221adc96340c 100644 --- a/include/net/mana/gdma.h +++ b/include/net/mana/gdma.h @@ -29,6 +29,10 @@ enum gdma_request_type { GDMA_CREATE_DMA_REGION = 25, GDMA_DMA_REGION_ADD_PAGES = 26, GDMA_DESTROY_DMA_REGION = 27, + GDMA_CREATE_PD = 29, + GDMA_DESTROY_PD = 30, + GDMA_CREATE_MR = 31, + GDMA_DESTROY_MR = 32, }; #define GDMA_RESOURCE_DOORBELL_PAGE 27 @@ -61,6 +65,8 @@ enum { GDMA_DEVICE_MANA = 2, }; +typedef u64 gdma_obj_handle_t; + struct gdma_resource { /* Protect the bitmap */ spinlock_t lock; @@ -194,7 +200,7 @@ struct gdma_mem_info { u64 length; /* Allocated by the PF driver */ - u64 gdma_region; + gdma_obj_handle_t dma_region_handle; }; #define REGISTER_ATB_MST_MKEY_LOWER_SIZE 8 @@ -618,7 +624,7 @@ struct gdma_create_queue_req { u32 reserved1; u32 pdid; u32 doolbell_id; - u64 gdma_region; + gdma_obj_handle_t gdma_region; u32 reserved2; u32 queue_size; u32 log2_throttle_limit; @@ -645,6 +651,28 @@ struct gdma_disable_queue_req { u32 alloc_res_id_on_creation; }; /* HW DATA */ +enum atb_page_size { + ATB_PAGE_SIZE_4K, + ATB_PAGE_SIZE_8K, + ATB_PAGE_SIZE_16K, + ATB_PAGE_SIZE_32K, + ATB_PAGE_SIZE_64K, + ATB_PAGE_SIZE_128K, + ATB_PAGE_SIZE_256K, + ATB_PAGE_SIZE_512K, + ATB_PAGE_SIZE_1M, + ATB_PAGE_SIZE_2M, + ATB_PAGE_SIZE_MAX, +}; + +enum gdma_mr_access_flags { + GDMA_ACCESS_FLAG_LOCAL_READ = BIT_ULL(0), + GDMA_ACCESS_FLAG_LOCAL_WRITE = BIT_ULL(1), + GDMA_ACCESS_FLAG_REMOTE_READ = BIT_ULL(2), + GDMA_ACCESS_FLAG_REMOTE_WRITE = BIT_ULL(3), + GDMA_ACCESS_FLAG_REMOTE_ATOMIC = BIT_ULL(4), +}; + /* GDMA_CREATE_DMA_REGION */ struct gdma_create_dma_region_req { struct gdma_req_hdr hdr; @@ -671,14 +699,14 @@ struct gdma_create_dma_region_req { struct gdma_create_dma_region_resp { struct gdma_resp_hdr hdr; - u64 gdma_region; + gdma_obj_handle_t dma_region_handle; }; /* HW DATA */ /* GDMA_DMA_REGION_ADD_PAGES */ struct gdma_dma_region_add_pages_req { struct gdma_req_hdr hdr; - u64 gdma_region; + gdma_obj_handle_t dma_region_handle; u32 page_addr_list_len; u32 reserved3; @@ -690,9 +718,88 @@ struct gdma_dma_region_add_pages_req { struct gdma_destroy_dma_region_req { struct gdma_req_hdr hdr; - u64 gdma_region; + gdma_obj_handle_t dma_region_handle; }; /* HW DATA */ +enum gdma_pd_flags { + GDMA_PD_FLAG_INVALID = 0, +}; + +struct gdma_create_pd_req { + struct gdma_req_hdr hdr; + enum gdma_pd_flags flags; + u32 reserved; +};/* HW DATA */ + +struct gdma_create_pd_resp { + struct gdma_resp_hdr hdr; + gdma_obj_handle_t pd_handle; + u32 pd_id; + u32 reserved; +};/* HW DATA */ + +struct gdma_destroy_pd_req { + struct gdma_req_hdr hdr; + gdma_obj_handle_t pd_handle; +};/* HW DATA */ + +struct gdma_destory_pd_resp { + struct gdma_resp_hdr hdr; +};/* HW DATA */ + +enum gdma_mr_type { + /* Guest Virtual Address - MRs of this type allow access + * to memory mapped by PTEs associated with this MR using a virtual + * address that is set up in the MST + */ + GDMA_MR_TYPE_GVA = 2, +}; + +struct gdma_create_mr_params { + gdma_obj_handle_t pd_handle; + enum gdma_mr_type mr_type; + union { + struct { + gdma_obj_handle_t dma_region_handle; + u64 virtual_address; + enum gdma_mr_access_flags access_flags; + } gva; + }; +}; + +struct gdma_create_mr_request { + struct gdma_req_hdr hdr; + gdma_obj_handle_t pd_handle; + enum gdma_mr_type mr_type; + u32 reserved_1; + + union { + struct { + gdma_obj_handle_t dma_region_handle; + u64 virtual_address; + enum gdma_mr_access_flags access_flags; + } gva; + + }; + u32 reserved_2; +};/* HW DATA */ + +struct gdma_create_mr_response { + struct gdma_resp_hdr hdr; + gdma_obj_handle_t mr_handle; + u32 lkey; + u32 rkey; +};/* HW DATA */ + +struct gdma_destroy_mr_request { + struct gdma_req_hdr hdr; + gdma_obj_handle_t mr_handle; +};/* HW DATA */ + +struct gdma_destroy_mr_response { + struct gdma_resp_hdr hdr; +};/* HW DATA */ + int mana_gd_verify_vf_version(struct pci_dev *pdev); int mana_gd_register_device(struct gdma_dev *gd); @@ -719,4 +826,8 @@ void mana_gd_free_memory(struct gdma_mem_info *gmi); int mana_gd_send_request(struct gdma_context *gc, u32 req_len, const void *req, u32 resp_len, void *resp); + +int mana_gd_destroy_dma_region(struct gdma_context *gc, + gdma_obj_handle_t dma_region_handle); + #endif /* _GDMA_H */ -- cgit v1.2.3